url stringlengths 11 2.25k | text stringlengths 88 50k | ts timestamp[s]date 2026-01-13 08:47:33 2026-01-13 09:30:40 |
|---|---|---|
https://rust-lang.github.io/rust-clippy/stable/index.html#assertions_on_result_states | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:16 |
https://support.atlassian.com/jira-software-cloud | Jira Cloud support | Jira Cloud | Atlassian Support Skip to main content Jira Cloud Support Apps Documentation Knowledge base Resources Contact us Sign in Sign in Atlassian Support Jira Software Cloud Data Center Jira Cloud support Documentation Get help using and administering apps. View documentation Knowledge Base Find troubleshooting articles. View knowledge base Community Find answers, support, and inspiration from other Atlassian users. Visit Atlassian Community System Status Check the health of our cloud apps and services View system status Suggestions and bug reports Find existing feature suggestions and bug reports. View suggestions and bugs Marketplace apps Find features to customize your apps View Marketplace Billing and licensing See FAQs about billing and licensing. View FAQs What's new See the latest and greatest updates and new features for your Atlassian cloud apps and services. View release notes Not finding the help you need? Accessibility Notice at Collection Privacy Policy Terms of Use Security 2026 Atlassian | 2026-01-13T09:29:16 |
https://www.k15t.com/go/scroll-viewport | Scroll Sites for Confluence | Transform knowledge into impact with apps for Confluence and Jira Products Solutions Company Resources Try it free for 30 days Try it free for 30 days Back Content Tools for Confluence Learn more Create Interactive images & smart templates. Scroll ImageMap Create from Template Pro Manage Track versions, languages & content variants. Scroll Documents Scroll Versions Scroll Translations Publish Custom-branded exports & sites. Scroll Sites Scroll PDF Exporter Scroll Word Exporter Scroll HTML Exporter Tools for Jira Work Sync Collaborate better in Jira. Backbone Work Sync Back Knowledge Bases Turn Confluence into a Self-Service Knowledge Base Product Documentation Deliver Great Product Documentation Right from Confluence User Manuals Create Better User Manuals from Confluence Back About Us Learn more about K15t, our values, and the people behind the brand. Careers Browse open positions and learn how we work. Find a Partner Find a partner in your region to help you implement our solutions. Become a Partner Trust Center Contact Back Learn Documentation Guide A great product with thoughtful documentation enables your users to do what they love. Learn how your team can work together to create thoughtful documentation in Confluence. Confluence Practices After completing this learning journey, the learner will be able to evaluate and apply clean core principles to ERP so that they can maximize business process agility, reduce adaptation efforts, and accelerate innovation. Visit our Confluence Collaboration Hub Resources Blog Sharing our know how: News, best practices, and work life at K15t. PDF Template Library Share Confluence content as beautiful PDF documents. Choose from a variety of templates to get started. Support Need help with one of our apps? Head to our help center. Launch Branded Websites From Confluence The next generation of Scroll Viewport is here! Publish your Confluence content as branded, high-performance websites. Try it free Book a demo Bring Your Confluence Knowledge to Life in 3 Simple Steps Set up your site Choose a ready-to-use theme to fit your use case. Pick a domain and style the look. Add your content Choose the Confluence pages and spaces that belong on your site. Create! You’re all set! Your knowledge is now live, ready to empower users wherever they are. Launch Sites That Fit Every Need Quick start with ready-to-use themes to serve a variety of use cases like help centers, knowledge bases, and blogs. Sites are automatically optimized for SEO, performance, and accessibility so users get the content they need, when and where it's needed. Tailor Your Sites with Ease – No Code Required Simple, code-free styling to make every site feel like your own. Use design tokens or apply custom CSS / JS for advanced customization. Add custom domains, AI search, and integrate with your support & analytics tools. Control What, Where, and How Content is Published Make your site publicly available or restrict with authentication. Flexibility to publish live or manual updates, versioned and translated content, and embed content in various interfaces, like directly in your product. Learn How to Upgrade from Scroll Viewport For over 10 years, we’ve helped teams share their Confluence content online as beautifully branded help centers with Scroll Viewport – and we will continue to do so with Scroll Sites! If you’re currently using Viewport, watch the recent live session for a guided walkthrough of how to upgrade to Scroll Sites. Watch the recording What Does Scroll Sites Have to Offer? Scroll Sites gives you the tools your team needs to build beautiful, powerful sites. Multiple Ready-to Use Themes Get started in minutes with out-of-the-box themes that look great and perform even better. Custom Domains Connect your custom domain to enhance brand trust and recognition. AI-Powered Search Empower your users to surface answers quickly with a fast, intuitive, and intelligent search experience right in your site. Protected Sites Keep your content secure! Make your site public or restrict access with single sign-on or token authentication. In-App Help Integrate your site information and help content directly in your app’s UI, giving users the answers they need without missing a beat. Publishing Workflows Control if changes to your content go live on your site immediately or on your command. Site Analytics See how users interact with your content, identify trends, and make data-driven improvements to enhance their experience. Customize with Ease Make your site your own with simple, no-code customization. Works With Your Tools Connect with the tools you rely on to better support and enable your users. Inject Custom Code Customize beyond the basics with advanced styling and design tokens. Real Feedback From Real Users Our customers say it best. Here’s how the app helps teams work better, every day. A great tool that transforms your Confluence spaces into a proper documentation website. No more worrying about comments being public, and different versions of the pages being available. You can focus on using Confluence to build the documentation, and use Scroll Sites to show it. Maxime Lefebvre, Developer at Okapya See more reviews Get a Head Start with Ready-to-Use Themes Get started quickly with K15t’s Help Center theme, already trusted by thousands of Scroll Viewport users to share knowledge and documentation. More themes coming soon to offer even more ways to create the perfect site. Help Center K15t GmbH Product Blog Gorilla Apps On-the-Job Assist halbautomaten Knowledge Blog for Confluence Gorilla Apps Launch Branded Websites From Confluence The next generation of Scroll Viewport is here! Publish your Confluence content as branded, high-performance websites. Try it free for 30 days FAQs Why is Scroll Sites being introduced? Over the years, we’ve seen Scroll Viewport evolve far beyond just providing a ‘view’ on Confluence content. Our users are building and launching fully-fledged sites—help centers, knowledge bases, documentation sites, and more. We want to take that even further. Scroll Sites is our next step in empowering teams to create more types of sites for their audiences. With this relaunch, we’re introducing new functionality and expanding customization options, making it easier than ever to build sites that look great and serve your users effectively. Whether you need a help center, a product documentation site, or something entirely new, Scroll Sites is designed to give you the flexibility to make it happen. How does Scroll Sites differ from Scroll Viewport? Scroll Sites builds on what you’ve loved about Scroll Viewport while introducing new features to support even more use cases. Here are a few of the new features you’ll experience: Multiple themes – Choose from a variety of themes to create different types of sites. Live updates – Publish changes instantly, alongside the manual updates you’re already familiar with. Publish blog pages – Besides choosing to publish normal pages from a space or Scroll Document like today in Scroll Viewport, you can also choose to publish only the blog posts of your space. Flexible URL structures – Choose between flat or hierarchical URLs to optimize navigation and SEO. Learn more about the changes for you, as a Scroll Viewport Cloud user What types of themes are available in Scroll Sites? In addition to the Help Center theme that Scroll Viewport users know and rely on today, Scroll Sites offer additional themes to support blog content, step-by-step documentation processes, and more. Does Scroll Sites support all the integrations I use with Scroll Viewport today? Yes! Scroll Sites will continue to support Scroll Documents and its features, including versioning, variant management, and translated content. Beyond that, we know many users rely on additional integrations to enhance their sites. Our goal is to ensure that the integrations you depend on today remain supported in Scroll Sites, and we’re actively working on expanding compatibility where needed. Scroll Help Site Not Found ✕ The scrollhelp.site you requested could not be located. It might not exist or the URL may have changed. Products Scroll Sites Scroll Documents Scroll PDF Exporter Scroll Word Exporter Scroll HTML Exporter Scroll ImageMap Create from Template Pro Backbone Work Sync Scroll Versions Scroll Translations Solutions Knowledge Bases Product Documentation User Manuals Learn more about Scroll Company About Us Careers Trust Center Find a Partner Become a Partner Contact Resources Confluence Collaboration Hub Blog Support PDF Template Library Copyright © 2025 K15t Powered by Atlassian Confluence and Scroll Sites Privacy Statement Legal Notice Privacy Settings Confluence Tips Right in Your Inbox! ✕ Subscribe for regular updates from K15t, including a collection of our free best practice content, Confluence tips and tricks, Atlassian news, and more. Email 19 " > Subscribe With the submission of this form, you agree with our privacy statement. Reset Cookies ✕ The following services will be reset and deactivated for you. Hyvor Talk: We're using Hyvor Talk as a comment tool. Hyvor Talk sets a local storage when activated. By clicking "Disable all services" you're no longer able to post or read comments on our website until accepting the service again. YouTube: We're using YouTube to embed video into our website. YouTube sets cookies when activated. By clicking "Disable all services" you're no longer able to watch our embedded videos on the website until accepting the service again. By clicking "Disable all services" all cookies and local storages related to the services will be removed. Before using them on our website again, you need to accept them. Disable all services | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/tencentglobal-tencent-cloud-instant-messaging-im/?trk=products_details_guest_other_products_by_org_section_product_link_result-card_image-click#main-content | Tencent Cloud Instant Messaging (IM) | LinkedIn Skip to main content LinkedIn Tencent in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms by Tencent See who's skilled in this Add as skill Learn more Report this product About Tencent Cloud Instant Messaging (IM) provides globally interconnected chat APIs, multi-platform SDKs, and UIKit components to help you quickly bring messaging capabilities such as one-to-one chat, group chat, chat rooms, and system notifications to your applications and websites. Similar products Slack Slack Cloud Communications Platforms Avaya Cloud Office Avaya Cloud Office Cloud Communications Platforms MessageBird MessageBird Cloud Communications Platforms Vonage Communications APIs Vonage Communications APIs Cloud Communications Platforms CPaaS CPaaS Cloud Communications Platforms Channelize.io: Live Stream Shopping Platform Channelize.io: Live Stream Shopping Platform Cloud Communications Platforms Sign in to see more Show more Show less Tencent products Cloud Native Database TDSQL-C Cloud Native Database TDSQL-C Relational Database Management Systems Cloud Object Storage (COS) Cloud Object Storage (COS) Object Storage Software Cloud Virtual Machine (CVM) Cloud Virtual Machine (CVM) Server Virtualization Software Simple Email Service (SES) Simple Email Service (SES) Email Marketing Software Tencent Cloud Automation Tools Tencent Cloud Automation Tools Build Automation Tools Tencent Cloud Block Storage Tencent Cloud Block Storage Block Storage Software Tencent Cloud Lighthouse Tencent Cloud Lighthouse Enterprise Cloud Platforms Tencent Effect SDK Tencent Effect SDK Software Development Kits (SDK) Tencent Real-Time Communication (TRTC) Tencent Real-Time Communication (TRTC) Live Streaming Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:16 |
https://docs.softwareheritage.org/devel/swh-model/persistent-identifiers.html#main-content | SoftWare Heritage persistent IDentifiers (SWHIDs) — Software Heritage documentation Skip to main content Back to top Ctrl + K Development API reference Usage Resources Infrastructure More About GitLab PyPI System Status Software Heritage Homepage Development API reference Usage Resources Infrastructure About GitLab PyPI System Status Software Heritage Homepage Section Navigation swh.alter Using swh-alter Removal algorithm Recovery bundles swh.alter package swh.alter.bech32 module swh.alter.cli module swh.alter.inventory module swh.alter.mirror_notification_watcher module swh.alter.notifications module swh.alter.operations module swh.alter.progressbar module swh.alter.recovery_bundle module swh.alter.removable module swh.alter.subgraph module swh.alter.utils module swh.auth Command-line interface Django components swh.auth package swh.auth.django package swh.auth.django.backends module swh.auth.django.middlewares module swh.auth.django.models module swh.auth.django.utils module swh.auth.django.views module swh.auth.starlette package swh.auth.starlette.backends module swh.auth.cli module swh.auth.keycloak module swh.auth.pytest_plugin module swh.auth.utils module swh.coarnotify Explanations What’s COAR Notify ? What are we doing with the metadata ? swh.coarnotify package swh.coarnotify.server package swh.coarnotify.server.management package swh.coarnotify.server.admin module swh.coarnotify.server.apps module swh.coarnotify.server.forms module swh.coarnotify.server.handlers module swh.coarnotify.server.models module swh.coarnotify.server.signals module swh.coarnotify.server.utils module swh.coarnotify.server.views module swh.coarnotify.settings package swh.coarnotify.settings.common module swh.coarnotify.settings.development module swh.coarnotify.settings.production module swh.coarnotify.settings.tests module swh.coarnotify.cli module swh.coarnotify.client module swh.coarnotify.manage module swh.coarnotify.parsers module swh.coarnotify.renderers module swh.coarnotify.tasks module swh.coarnotify.urls module How-to guides Install swh-coarnotify Access the inbox Send a mention of a software in a scientific paper References Workflows Specifications Rest API Command Line Interface Notification payloads swh.core Command-line interface Common database utilities swh.core package swh.core.api package swh.core.api.asynchronous module swh.core.api.classes module swh.core.api.gunicorn_config module swh.core.api.negotiation module swh.core.api.serializers module swh.core.cli package swh.core.cli.backend module swh.core.cli.db module swh.core.cli.nar module swh.core.cli.sentry module swh.core.db package swh.core.db.common module swh.core.db.db_utils module swh.core.github package swh.core.github.pytest_plugin module swh.core.github.utils module swh.core.s3 namespace swh.core.s3.downloader module swh.core.s3.pytest_plugin module swh.core.api_async module swh.core.collections module swh.core.config module swh.core.logger module swh.core.logging module swh.core.nar module swh.core.pytest_plugin module swh.core.retry module swh.core.sentry module swh.core.statsd module swh.core.tarball module swh.core.utils module swh.counters swh.counters package swh.counters.api package swh.counters.api.client module swh.counters.api.server module swh.counters.cli module swh.counters.history module swh.counters.in_memory module swh.counters.interface module swh.counters.journal_client module swh.counters.kafka_client module swh.counters.redis module swh.dataportal How to guides How to use the CLI References Static site generation process Data used to generate the website swh.datasets Luigi workflows Command-line interface swh.datasets package swh.datasets.luigi package swh.datasets.luigi.aggregate_datasets module swh.datasets.luigi.blobs_datasets module swh.datasets.luigi.file_names module swh.datasets.luigi.impact module swh.datasets.luigi.origin_contributors module swh.datasets.cli module swh.datasets.download module swh.datasets.shell module swh.deposit Deposit API User Manual API Documentation Service document Create deposit Update content Update metadata Retrieve status Display content Deposit metadata Use cases Register account Deposit internals Running swh-deposit locally Production deployment Authentication Loading workflow Specifications Loading specification Protocol reference The metadata-only deposit swh.deposit package swh.deposit.api package swh.deposit.api.private package swh.deposit.api.collection module swh.deposit.api.common module swh.deposit.api.content module swh.deposit.api.converters module swh.deposit.api.edit module swh.deposit.api.edit_media module swh.deposit.api.service_document module swh.deposit.api.state module swh.deposit.api.sword_edit module swh.deposit.api.urls module swh.deposit.api.utils module swh.deposit.cli package swh.deposit.cli.admin module swh.deposit.cli.client module swh.deposit.fixtures package swh.deposit.loader package swh.deposit.loader.checker module swh.deposit.loader.checks module swh.deposit.loader.tasks module swh.deposit.templates package swh.deposit.templates.deposit package swh.deposit.tests_migration package swh.deposit.apps module swh.deposit.auth module swh.deposit.client module swh.deposit.config module swh.deposit.errors module swh.deposit.exception module swh.deposit.gunicorn_config module swh.deposit.manage module swh.deposit.models module swh.deposit.parsers module swh.deposit.urls module swh.deposit.utils module Command-line interface swh.digestmap Design document for a hash conversion service swh.digestmap module swh.export Software Heritage Graph Dataset Dataset Relational schema Setup on Amazon Athena Setup on Azure Databricks Exporting a dataset Exporting a subdataset swh.export package swh.export.exporters package swh.export.exporters.edges module swh.export.exporters.orc module swh.export.test namespace swh.export.test.test_edges module swh.export.test.test_journal_processor module swh.export.test.test_orc module swh.export.test.test_utils module swh.export.athena module swh.export.cli module swh.export.exporter module swh.export.fullnames module swh.export.journalprocessor module swh.export.luigi module swh.export.relational module swh.export.utils module swh.fuse Tutorial Configuration Advice for parallelization Design notes Command-line interface swh.fuse package swh.fuse.backends package swh.fuse.backends.compressed module swh.fuse.backends.objstorage module swh.fuse.backends.web_api module swh.fuse.fs namespace swh.fuse.fs.artifact module swh.fuse.fs.entry module swh.fuse.fs.mountpoint module swh.fuse.cache module swh.fuse.cli module swh.fuse.fuse module swh.graph Quickstart Graph Querying HTTP API Using the gRPC API Rust API Memory & Performance tuning Graph compression Command-line interface Docker environment git2graph Test graphs Example dataset Provenance index swh.graph namespace swh.graph.example_dataset package swh.graph.example_dataset.generate_dataset module swh.graph.grpc namespace swh.graph.grpc.swhgraph_pb2 module swh.graph.grpc.swhgraph_pb2_grpc module swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.shell module swh.graph.luigi package swh.graph.luigi.compressed_graph module swh.graph.luigi.subdataset module swh.graph.luigi.utils module swh.graph.cli module swh.graph.client module swh.graph.config module swh.graph.download module swh.graph.e2e_check module swh.graph.find_context module swh.graph.grpc_server module swh.graph.http_client module swh.graph.http_naive_client module swh.graph.http_rpc_server module swh.graph.naive_client module swh.graph.pytest_plugin module swh.graph.shell module swh.graph.webgraph module swh.graph.libs swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.luigi.topology module swh.graph.libs.shell module Software Heritage GraphQL API swh.indexer Software Heritage - Indexer Metadata workflow SwhPkg Vocabulary swh.indexer package swh.indexer.metadata_dictionary package swh.indexer.metadata_dictionary.base module swh.indexer.metadata_dictionary.cff module swh.indexer.metadata_dictionary.codemeta module swh.indexer.metadata_dictionary.composer module swh.indexer.metadata_dictionary.dart module swh.indexer.metadata_dictionary.gitea module swh.indexer.metadata_dictionary.github module swh.indexer.metadata_dictionary.maven module swh.indexer.metadata_dictionary.npm module swh.indexer.metadata_dictionary.nuget module swh.indexer.metadata_dictionary.python module swh.indexer.metadata_dictionary.ruby module swh.indexer.metadata_dictionary.utils module swh.indexer.storage package swh.indexer.storage.api package swh.indexer.storage.converters module swh.indexer.storage.db module swh.indexer.storage.exc module swh.indexer.storage.in_memory module swh.indexer.storage.interface module swh.indexer.storage.metrics module swh.indexer.storage.model module swh.indexer.storage.writer module swh.indexer.bibtex module swh.indexer.cli module swh.indexer.codemeta module swh.indexer.fossology_license module swh.indexer.indexer module swh.indexer.metadata module swh.indexer.metadata_detector module swh.indexer.mimetype module swh.indexer.namespaces module swh.indexer.origin_head module swh.indexer.rehash module Command-line interface swh.journal Software Heritage Journal clients swh.journal package swh.journal.writer package swh.journal.writer.inmemory module swh.journal.writer.interface module swh.journal.writer.kafka module swh.journal.writer.stream module swh.journal.client module swh.journal.pytest_plugin module swh.journal.serializers module swh.lister Tutorial: list the content of your favorite forge in just a few steps Tutorial: run a lister within docker-dev in just a few steps Save a forge swh.lister package swh.lister.arch package swh.lister.arch.lister module swh.lister.arch.tasks module swh.lister.aur package swh.lister.aur.lister module swh.lister.aur.tasks module swh.lister.bioconductor package swh.lister.bioconductor.lister module swh.lister.bioconductor.tasks module swh.lister.bitbucket package swh.lister.bitbucket.lister module swh.lister.bitbucket.tasks module swh.lister.bower package swh.lister.bower.lister module swh.lister.bower.tasks module swh.lister.cgit package swh.lister.cgit.lister module swh.lister.cgit.tasks module swh.lister.conda package swh.lister.conda.lister module swh.lister.conda.tasks module swh.lister.cpan package swh.lister.cpan.lister module swh.lister.cpan.tasks module swh.lister.cran package swh.lister.cran.lister module swh.lister.cran.tasks module swh.lister.crates package swh.lister.crates.lister module swh.lister.crates.tasks module swh.lister.debian package swh.lister.debian.lister module swh.lister.debian.tasks module swh.lister.dlang package swh.lister.dlang.lister module swh.lister.dlang.tasks module swh.lister.elm package swh.lister.elm.lister module swh.lister.elm.tasks module swh.lister.gitea package swh.lister.gitea.lister module swh.lister.gitea.tasks module swh.lister.github package swh.lister.github.lister module swh.lister.github.tasks module swh.lister.gitiles package swh.lister.gitiles.lister module swh.lister.gitiles.tasks module swh.lister.gitlab package swh.lister.gitlab.lister module swh.lister.gitlab.tasks module swh.lister.gitweb package swh.lister.gitweb.lister module swh.lister.gitweb.tasks module swh.lister.gnu package swh.lister.gnu.lister module swh.lister.gnu.tasks module swh.lister.gnu.tree module swh.lister.gogs package swh.lister.gogs.lister module swh.lister.gogs.tasks module swh.lister.golang package swh.lister.golang.lister module swh.lister.golang.tasks module swh.lister.hackage package swh.lister.hackage.lister module swh.lister.hackage.tasks module swh.lister.hex package swh.lister.hex.lister module swh.lister.hex.tasks module swh.lister.julia package swh.lister.julia.lister module swh.lister.julia.tasks module swh.lister.launchpad package swh.lister.launchpad.lister module swh.lister.launchpad.tasks module swh.lister.maven package swh.lister.maven.lister module swh.lister.maven.tasks module swh.lister.nixguix package swh.lister.nixguix.lister module swh.lister.nixguix.tasks module swh.lister.npm package swh.lister.npm.lister module swh.lister.npm.tasks module swh.lister.nuget package swh.lister.nuget.lister module swh.lister.nuget.tasks module swh.lister.opam package swh.lister.opam.lister module swh.lister.opam.tasks module swh.lister.packagist package swh.lister.packagist.lister module swh.lister.packagist.tasks module swh.lister.pagure package swh.lister.pagure.lister module swh.lister.pagure.tasks module swh.lister.phabricator package swh.lister.phabricator.lister module swh.lister.phabricator.tasks module swh.lister.pubdev package swh.lister.pubdev.lister module swh.lister.pubdev.tasks module swh.lister.puppet package swh.lister.puppet.lister module swh.lister.puppet.tasks module swh.lister.pypi package swh.lister.pypi.lister module swh.lister.pypi.tasks module swh.lister.rpm package swh.lister.rpm.lister module swh.lister.rpm.tasks module swh.lister.rubygems package swh.lister.rubygems.lister module swh.lister.rubygems.tasks module swh.lister.save_bulk package swh.lister.save_bulk.lister module swh.lister.save_bulk.tasks module swh.lister.sourceforge package swh.lister.sourceforge.lister module swh.lister.sourceforge.tasks module swh.lister.stagit package swh.lister.stagit.lister module swh.lister.stagit.tasks module swh.lister.tuleap package swh.lister.tuleap.lister module swh.lister.tuleap.tasks module swh.lister.cli module swh.lister.pattern module swh.lister.utils module Command-line interface swh.loader swh.loader.core VCS Loader Overview Package Loader Tutorial Package loader specifications swh.loader.core package swh.loader.core.converters module swh.loader.core.loader module swh.loader.core.metadata_fetchers module swh.loader.core.tasks module swh.loader.core.utils module Command-line interface swh.loader.bzr Software Heritage - How Bazaar/Breezy works swh.loader.bzr package swh.loader.bzr.loader module swh.loader.bzr.tasks module Software Heritage - CVS loader swh.loader.git swh.loader.git package swh.loader.git.base module swh.loader.git.converters module swh.loader.git.directory module swh.loader.git.from_disk module swh.loader.git.loader module swh.loader.git.tasks module swh.loader.git.utils module swh.loader.mercurial swh.loader.mercurial package swh.loader.mercurial.archive_extract module swh.loader.mercurial.converters module swh.loader.mercurial.directory module swh.loader.mercurial.hgutil module swh.loader.mercurial.identify module swh.loader.mercurial.loader module swh.loader.mercurial.tasks module swh.loader.mercurial.utils module swh.loader.metadata swh.loader.metadata package swh.loader.metadata.base module swh.loader.metadata.cli module swh.loader.metadata.gitea module swh.loader.metadata.github module swh.loader.metadata.journal_client module swh.loader.svn swh.loader.svn package swh.loader.svn.converters module swh.loader.svn.directory module swh.loader.svn.exception module swh.loader.svn.fast_crawler module swh.loader.svn.loader module swh.loader.svn.replay module swh.loader.svn.svn_repo module swh.loader.svn.svn_retry module swh.loader.svn.tasks module swh.loader.svn.utils module swh.model Data model SoftWare Heritage persistent IDentifiers (SWHIDs) Command-line interface swh.model package swh.model.fields package swh.model.fields.compound module swh.model.fields.hashes module swh.model.fields.simple module swh.model.cli module swh.model.collections module swh.model.discovery module swh.model.exceptions module swh.model.from_disk module swh.model.git_objects module swh.model.hashutil module swh.model.hypothesis_strategies module swh.model.merkle module swh.model.model module swh.model.swhids module swh.model.toposort module swh.model.validators module swh.objstorage Command-line interface Winery backend swh.objstorage namespace swh.objstorage.api namespace swh.objstorage.api.client module swh.objstorage.api.server module swh.objstorage.backends package swh.objstorage.backends.seaweedfs package swh.objstorage.backends.winery package swh.objstorage.backends.azure module swh.objstorage.backends.http module swh.objstorage.backends.in_memory module swh.objstorage.backends.libcloud module swh.objstorage.backends.noop module swh.objstorage.backends.pathslicing module swh.objstorage.proxies namespace swh.objstorage.proxies.readonly module swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module swh.objstorage.cli module swh.objstorage.constants module swh.objstorage.exc module swh.objstorage.factory module swh.objstorage.interface module swh.objstorage.multiplexer module swh.objstorage.objstorage module swh.objstorage.pytest_plugin module swh.objstorage.utils module swh.objstorage.replayer Command-line interface swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module Software Heritage - Provenance swh.scanner Command-line interface swh.scanner package swh.scanner.dashboard package swh.scanner.dashboard.dashboard module swh.scanner.cli module swh.scanner.config module swh.scanner.data module swh.scanner.exceptions module swh.scanner.output module swh.scanner.policy module swh.scanner.scanner module swh.scanner.setup_wizard module swh.scheduler Command-line interface Software Heritage Scheduler Simulator swh.scheduler package swh.scheduler.api package swh.scheduler.api.client module swh.scheduler.api.serializers module swh.scheduler.api.server module swh.scheduler.celery_backend package swh.scheduler.celery_backend.config module swh.scheduler.celery_backend.first_visits module swh.scheduler.celery_backend.pika_listener module swh.scheduler.celery_backend.recurrent_visits module swh.scheduler.celery_backend.runner module swh.scheduler.celery_backend.utils module swh.scheduler.cli package swh.scheduler.cli.add_forge_now module swh.scheduler.cli.admin module swh.scheduler.cli.celery_monitor module swh.scheduler.cli.config module swh.scheduler.cli.journal module swh.scheduler.cli.origin module swh.scheduler.cli.origin_utils module swh.scheduler.cli.simulator module swh.scheduler.cli.task module swh.scheduler.cli.task_type module swh.scheduler.cli.utils module swh.scheduler.simulator package swh.scheduler.simulator.common module swh.scheduler.simulator.origin_scheduler module swh.scheduler.simulator.origins module swh.scheduler.simulator.task_scheduler module swh.scheduler.sql package swh.scheduler.sql.upgrades package swh.scheduler.backend module swh.scheduler.cli_utils module swh.scheduler.exc module swh.scheduler.in_memory module swh.scheduler.interface module swh.scheduler.journal_client module swh.scheduler.model module swh.scheduler.pytest_plugin module swh.scheduler.task module swh.scheduler.utils module swh.scrubber Command-line interface swh.scrubber package swh.scrubber.base_checker module swh.scrubber.cli module swh.scrubber.db module swh.scrubber.fixer module swh.scrubber.journal_checker module swh.scrubber.objstorage_checker module swh.scrubber.origin_locator module swh.scrubber.storage_checker module swh.scrubber.utils module swh.search Command-line interface Search Query Language swh.search package swh.search.api package swh.search.api.client module swh.search.api.server module swh.search.cli module swh.search.elasticsearch module swh.search.exc module swh.search.in_memory module swh.search.interface module swh.search.journal_client module swh.search.metrics module swh.search.translator module swh.search.utils module swh.shard Read Shard format Benchmarks swh.shard package swh.shard.cli module swh.storage Extrinsic metadata specification Object Masking swh.storage package swh.storage.algos package swh.storage.algos.diff module swh.storage.algos.dir_iterators module swh.storage.algos.directory module swh.storage.algos.discovery module swh.storage.algos.origin module swh.storage.algos.revisions_walker module swh.storage.algos.snapshot module swh.storage.algos.swhid module swh.storage.api package swh.storage.api.client module swh.storage.api.serializers module swh.storage.api.server module swh.storage.cassandra package swh.storage.cassandra.common module swh.storage.cassandra.converters module swh.storage.cassandra.cql module swh.storage.cassandra.diagram module swh.storage.cassandra.migrations module swh.storage.cassandra.model module swh.storage.cassandra.schema module swh.storage.cassandra.storage module swh.storage.postgresql package swh.storage.postgresql.converters module swh.storage.postgresql.db module swh.storage.postgresql.storage module swh.storage.proxies package swh.storage.proxies.blocking package swh.storage.proxies.masking package swh.storage.proxies.buffer module swh.storage.proxies.filter module swh.storage.proxies.record_references module swh.storage.proxies.retry module swh.storage.proxies.tenacious module swh.storage.proxies.validate module swh.storage.backfill module swh.storage.cli module swh.storage.common module swh.storage.exc module swh.storage.fixer module swh.storage.in_memory module swh.storage.interface module swh.storage.metrics module swh.storage.migrate_extrinsic_metadata module swh.storage.objstorage module swh.storage.pytest_plugin module swh.storage.replay module swh.storage.utils module swh.storage.writer module Database schema Cassandra migrations Storage replayer Command-line interface swh.vault Getting started Vault API Reference swh.vault package swh.vault.api package swh.vault.api.client module swh.vault.api.serializers module swh.vault.api.server module swh.vault.cookers package swh.vault.cookers.base module swh.vault.cookers.directory module swh.vault.cookers.git_bare module swh.vault.cookers.revision_flat module swh.vault.cookers.revision_gitfast module swh.vault.cookers.utils module swh.vault.backend module swh.vault.cache module swh.vault.cli module swh.vault.cooking_tasks module swh.vault.exc module swh.vault.in_memory_backend module swh.vault.interface module swh.vault.to_disk module Command-line interface swh.web Developers Information swh-web API URLs URI scheme for swh-web Browse application URI scheme for SoftWare Hash IDentifiers (SWHIDs) Miscellaneous URLs swh.web package swh.web.add_forge_now package swh.web.add_forge_now.admin_views module swh.web.add_forge_now.api_views module swh.web.add_forge_now.apps module swh.web.add_forge_now.models module swh.web.add_forge_now.signal_receivers module swh.web.add_forge_now.urls module swh.web.add_forge_now.utils module swh.web.add_forge_now.views module swh.web.admin package swh.web.admin.apps module swh.web.admin.urls module swh.web.alter package swh.web.alter.templatetags package swh.web.alter.apps module swh.web.alter.emails module swh.web.alter.forms module swh.web.alter.models module swh.web.alter.urls module swh.web.alter.utils module swh.web.alter.views module swh.web.api package swh.web.api.views package swh.web.api.apidoc module swh.web.api.apiresponse module swh.web.api.apiurls module swh.web.api.parsers module swh.web.api.renderers module swh.web.api.serializers module swh.web.api.throttling module swh.web.api.urls module swh.web.api.utils module swh.web.archive_coverage package swh.web.archive_coverage.urls module swh.web.archive_coverage.views module swh.web.auth package swh.web.auth.apps module swh.web.auth.models module swh.web.auth.urls module swh.web.auth.utils module swh.web.auth.views module swh.web.badges package swh.web.badges.urls module swh.web.banners package swh.web.banners.urls module swh.web.banners.views module swh.web.browse package swh.web.browse.views package swh.web.browse.browseurls module swh.web.browse.identifiers module swh.web.browse.snapshot_context module swh.web.browse.urls module swh.web.browse.utils module swh.web.client package swh.web.client.cli module swh.web.client.client module swh.web.deposit package swh.web.deposit.urls module swh.web.inbound_email package swh.web.inbound_email.management package swh.web.inbound_email.apps module swh.web.inbound_email.handle_message module swh.web.inbound_email.signals module swh.web.inbound_email.urls module swh.web.inbound_email.utils module swh.web.inbound_email.views module swh.web.jslicenses package swh.web.jslicenses.urls module swh.web.mailmap package swh.web.mailmap.management package swh.web.mailmap.apps module swh.web.mailmap.models module swh.web.mailmap.urls module swh.web.mailmap.views module swh.web.metrics package swh.web.metrics.prometheus module swh.web.metrics.urls module swh.web.metrics.views module swh.web.provenance package swh.web.provenance.api_views module swh.web.provenance.apps module swh.web.provenance.urls module swh.web.save_bulk package swh.web.save_bulk.api_views module swh.web.save_bulk.apps module swh.web.save_bulk.models module swh.web.save_bulk.urls module swh.web.save_bulk.views module swh.web.save_code_now package swh.web.save_code_now.management package swh.web.save_code_now.admin_views module swh.web.save_code_now.api_views module swh.web.save_code_now.apps module swh.web.save_code_now.models module swh.web.save_code_now.origin_save module swh.web.save_code_now.origin_visit_webhook module swh.web.save_code_now.urls module swh.web.save_code_now.views module swh.web.save_origin_webhooks package swh.web.save_origin_webhooks.bitbucket module swh.web.save_origin_webhooks.generic_receiver module swh.web.save_origin_webhooks.gitea module swh.web.save_origin_webhooks.github module swh.web.save_origin_webhooks.gitlab module swh.web.save_origin_webhooks.sourceforge module swh.web.save_origin_webhooks.urls module swh.web.utils package swh.web.utils.management package swh.web.utils.archive module swh.web.utils.citation module swh.web.utils.converters module swh.web.utils.exc module swh.web.utils.highlightjs module swh.web.utils.identifiers module swh.web.utils.middlewares module swh.web.utils.origin_visits module swh.web.utils.query module swh.web.utils.swh_templatetags module swh.web.utils.typing module swh.web.utils.url_path_converters module swh.web.utils.urlsindex module swh.web.vault package swh.web.vault.api_views module swh.web.vault.urls module swh.web.webapp package swh.web.webapp.urls module swh.web.config module swh.web.gunicorn_config module swh.web.manage module swh.web.urls module swh.web.client swh.webhooks swh.webhooks package swh.webhooks.cli module swh.webhooks.interface module swh.webhooks.journal_client module swh.webhooks.svix_retry module swh.webhooks.utils module Development API reference Software Heritage - Data model SoftWare Heritage persistent IDentifiers (SWHIDs) SoftWare Heritage persistent IDentifiers (SWHIDs) # version 1.6, last modified 2021-04-30 Overview Syntax Semantics Core identifiers Qualifiers Interoperability URI scheme Git compatibility Automatically fixing invalid SWHIDs Examples Core identifiers Identifiers with qualifiers Implementation Computing Choosing what type of SWHID to use Resolvers References Overview # You can point to objects present in the Software Heritage archive by the means of SoftWare Heritage persistent IDentifiers , or SWHIDs for short, that are guaranteed to remain stable (persistent) over time. Their syntax, meaning, and usage is described below. Note that they are identifiers and not URLs, even though URL-based resolvers for SWHIDs are also available. A SWHID consists of two separate parts, a mandatory core identifier that can point to any software artifact (or “object”) available in the Software Heritage archive, and an optional list of qualifiers that allows to specify the context where the object is meant to be seen and point to a subpart of the object itself. Objects come in different types: contents directories revisions releases snapshots Each object is identified by an intrinsic, type-specific object identifier that is embedded in its SWHID as described below. The intrinsic identifiers embedded in SWHIDs are strong cryptographic hashes computed on the entire set of object properties. Together, these identifiers form a Merkle structure , specifically a Merkle DAG . See the Software Heritage data model for an overview of object types and how they are linked together. See swh.model.git_objects for details on how the intrinsic identifiers embedded in SWHIDs are computed. The optional qualifiers are of two kinds: context qualifiers: carry information about the context where a given object is meant to be seen. This is particularly important, as the same object can be reached in the Merkle graph following different paths starting from different nodes (or anchors ), and it may have been retrieved from different origins , that may evolve between different visits fragment qualifiers: allow to pinpoint specific subparts of an object Syntax # Syntactically, SWHIDs are generated by the <identifier> entry point in the following grammar: < identifier > ::= < identifier_core > [ < qualifiers > ] ; < identifier_core > ::= "swh" ":" < scheme_version > ":" < object_type > ":" < object_id > ; < scheme_version > ::= "1" ; < object_type > ::= "snp" (* snapshot *) | "rel" (* release *) | "rev" (* revision *) | "dir" (* directory *) | "cnt" (* content *) ; < object_id > ::= 40 * < hex_digit > ; (* intrinsic object id, as hex-encoded SHA1 *) < dec_digit > ::= "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9" ; < hex_digit > ::= < dec_digit > | "a" | "b" | "c" | "d" | "e" | "f" ; < qualifiers > := ";" < qualifier > [ < qualifiers > ] ; < qualifier > ::= < context_qualifier > | < fragment_qualifier > ; < context_qualifier > ::= < origin_ctxt > | < visit_ctxt > | < anchor_ctxt > | < path_ctxt > ; < origin_ctxt > ::= "origin" "=" < url_escaped > ; < visit_ctxt > ::= "visit" "=" < identifier_core > ; < anchor_ctxt > ::= "anchor" "=" < identifier_core > ; < path_ctxt > ::= "path" "=" < path_absolute_escaped > ; < fragment_qualifier > ::= "lines" "=" < line_number > ["-" < line_number > ] ; < line_number > ::= < dec_digit > + ; < url_escaped > ::= (* RFC 3987 IRI *) < path_absolute_escaped > ::= (* RFC 3987 absolute path *) Where: <path_absolute_escaped> is an <ipath-absolute> from RFC 3987 , and <url_escaped> is a RFC 3987 IRI in either case all occurrences of ; (and % , as required by the RFC) have been percent-encoded (as %3B and %25 respectively). Other characters can be percent-encoded, e.g., to improve readability and/or embeddability of SWHID in other contexts. Semantics # Core identifiers # : is used as separator between the logical parts of core identifiers. The swh prefix makes explicit that these identifiers are related to SoftWare Heritage . 1 ( <scheme_version> ) is the current version of this identifier scheme . Future editions will use higher version numbers, possibly breaking backward compatibility, but without breaking the resolvability of SWHIDs that conform to previous versions of the scheme. A SWHID points to a single object, whose type is explicitly captured by <object_type> : snp to snapshots , rel to releases , rev to revisions , dir to directories , cnt to contents . The actual object pointed to is identified by the intrinsic identifier <object_id> , which is a hex-encoded (using lowercase ASCII characters) SHA1 computed on the content and metadata of the object itself, as follows: for snapshots , intrinsic identifiers are SHA1 hashes of manifests computed as per swh.model.git_objects.snapshot_git_object() for releases , as per swh.model.git_objects.release_git_object() that produces the same result as a git release hash for revisions , as per swh.model.git_objects.revision_git_object() that produces the same result as a git commit hash for directories , per swh.model.git_objects.directory_git_object() that produces the same result as a git tree hash for contents , the intrinsic identifier is the sha1_git hash returned by swh.hashutil.MultiHash.digest() , i.e., the SHA1 of a byte sequence obtained by juxtaposing the ASCII string "blob" (without quotes), a space, the length of the content as decimal digits, a NULL byte, and the actual content of the file. Qualifiers # ; is used as separator between the core identifier and the optional qualifiers, as well as between qualifiers. Each qualifier is specified as a key/value pair, using = as a separator. The following context qualifiers are available: origin: the software origin where an object has been found or observed in the wild, as an URI; visit: the core identifier of a snapshot corresponding to a specific visit of a repository containing the designated object; anchor: a designated node in the Merkle DAG relative to which a path to the object is specified, as the core identifier of a directory, a revision, a release or a snapshot; path: the absolute file path , from the root directory associated to the anchor node , to the object; when the anchor denotes a directory or a revision, and almost always when it’s a release, the root directory is uniquely determined; when the anchor denotes a snapshot, the root directory is the one pointed to by HEAD (possibly indirectly), and undefined if such a reference is missing; The following fragment qualifier is available: lines: line number(s) of interest, usually within a content object We recommend to equip identifiers meant to be shared with as many qualifiers as possible. While qualifiers may be listed in any order, it is good practice to present them in the order given above, i.e., origin , visit , anchor , path , lines . Redundant information should be omitted: for example, if the visit is present, and the path is relative to the snapshot indicated there, then the anchor qualifier is superfluous; similarly, if the path is empty, it may be omitted. Interoperability # URI scheme # The swh URI scheme is registered at IANA for SWHIDs. The present documents constitutes the scheme specification for such URI scheme. Git compatibility # SWHIDs for contents, directories, revisions, and releases are, at present, compatible with the Git way of computing identifiers for its objects. The <object_id> part of a SWHID for a content object is the Git blob identifier of any file with the same content; for a revision it is the Git commit identifier for the same revision, etc. This is not the case for snapshot identifiers, as Git does not have a corresponding object type. Note that Git compatibility is incidental and is not guaranteed to be maintained in future versions of this scheme (or Git). Automatically fixing invalid SWHIDs # User interfaces may fix invalid SWHIDs, by lower-casing the <identifier_core> part of a SWHID, if it contains upper-case letters because of user errors or limitations in software displaying SWHIDs. However, implementations displaying or generating SWHIDs should not rely on this behavior, and must display or generate only valid SWHIDs when technically possible. User interfaces should show an error when such an automatic fix occurs, so users have a chance to fix their SWHID before pasting it to an other interface that does not perform the same corrections. This also makes it easier to understand issues when a case-sensitive qualifier has its casing altered. Examples # Core identifiers # swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2 points to the content of a file containing the full text of the GPL3 license swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505 points to a directory containing the source code of the Darktable photography application as it was at some point on 4 May 2017 swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d points to a commit in the development history of Darktable, dated 16 January 2017, that added undo/redo supports for masks swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f points to Darktable release 2.3.0, dated 24 December 2016 swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453 points to a snapshot of the entire Darktable Git repository taken on 4 May 2017 from GitHub Identifiers with qualifiers # The following SWHID denotes the lines 9 to 15 of a file content that can be found at absolute path /Examples/SimpleFarm/simplefarm.ml from the root directory of the revision swh:1:rev:2db189928c94d62a3b4757b3eec68f0a4d4113f0 that is contained in the snapshot swh:1:snp:d7f1b9eb7ccb596c2622c4780febaa02549830f9 taken from the origin https://gitorious.org/ocamlp3l/ocamlp3l_cvs.git : swh : 1 : cnt : 4 d99d2d18326621ccdd70f5ea66c2e2ac236ad8b ; origin = https : // gitorious . org / ocamlp3l / ocamlp3l_cvs . git ; visit = swh : 1 : snp : d7f1b9eb7ccb596c2622c4780febaa02549830f9 ; anchor = swh : 1 : rev : 2 db189928c94d62a3b4757b3eec68f0a4d4113f0 ; path =/ Examples / SimpleFarm / simplefarm . ml ; lines = 9 - 15 Here is an example of a SWHID with a file path that requires percent-escaping: swh : 1 : cnt : f10371aa7b8ccabca8479196d6cd640676fd4a04 ; origin = https : // github . com / web - platform - tests / wpt ; visit = swh : 1 : snp : b37d435721bbd450624165f334724e3585346499 ; anchor = swh : 1 : rev : 259 d0612af038d14f2cd889a14a3adb6c9e96d96 ; path =/ html / semantics / document - metadata / the - meta - element / pragma - directives / attr - meta - http - equiv - refresh / support / x % 3 Burl = foo / Implementation # Computing # An important property of any SWHID is that its core identifier is intrinsic : it can be computed from the object itself , without having to rely on any third party. An implementation of SWHID that allows to do so locally is the swh identify tool, available from the swh.model Python package under the GPL license. This package can be installed via the pip package manager with the one liner pip3 install swh.model[cli] on any machine with Python (at least version 3.7) and pip installed (on a Debian or Ubuntu system a simple apt install python3 python3-pip will suffice, see the general instructions for other platforms). SWHIDs are also automatically computed by Software Heritage for all archived objects as part of its archival activity, and can be looked up via the project Web interface . This has various practical implications: when a software artifact is obtained from Software Heritage by resolving a SWHID, it is straightforward to verify that it is exactly the intended one: just compute the core identifier from the artefact itself, and check that it is the same as the core identifier part of the SHWID the core identifier of a software artifact can be computed before its archival on Software Heritage Choosing what type of SWHID to use # swh:1:dir: SWHIDs are the most robust SWHIDs, as they can be recomputed from the simplest objects (a directory structure on a filesystem), even when all metadata is lost, without relying on the Software Heritage archive. Therefore, we advise implementers and users to prefer this type of SWHIDs over swh:1:rev: and swh:1:rel: to reference a source code artifacts. However, since keeping the metadata is also important, you should add an anchor qualifier to swh:1:dir: SWHIDs whenever possible, so the metadata stored in the Software Heritage archive can be retrieved when needed. This means, for example, that you should prefer swh:1:dir:a8eded6a2d062c998ba2dcc3dcb0ce68a4e15a58;anchor=swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f over swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f . Resolvers # Software Heritage resolver # SWHIDs can be resolved using the Software Heritage Web interface . In particular, the root endpoint / can be given a SWHID and will lead to the browsing page of the corresponding object, like this: https://archive.softwareheritage.org/<identifier> . A dedicated /resolve endpoint of the Software Heritage Web API is also available to programmatically resolve SWHIDs; see: GET /api/1/resolve/(swhid)/ . Examples: https://archive.softwareheritage.org/swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2 https://archive.softwareheritage.org/swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505 https://archive.softwareheritage.org/api/1/resolve/swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d https://archive.softwareheritage.org/api/1/resolve/swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f https://archive.softwareheritage.org/api/1/resolve/swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453 https://archive.softwareheritage.org/swh:1:cnt:4d99d2d18326621ccdd70f5ea66c2e2ac236ad8b;origin=https://gitorious.org/ocamlp3l/ocamlp3l_cvs.git;visit=swh:1:snp:d7f1b9eb7ccb596c2622c4780febaa02549830f9;anchor=swh:1:rev:2db189928c94d62a3b4757b3eec68f0a4d4113f0;path=/Examples/SimpleFarm/simplefarm.ml;lines=9-15 https://archive.softwareheritage.org/swh:1:cnt:f10371aa7b8ccabca8479196d6cd640676fd4a04;origin=https://github.com/web-platform-tests/wpt;visit=swh:1:snp:b37d435721bbd450624165f334724e3585346499;anchor=swh:1:rev:259d0612af038d14f2cd889a14a3adb6c9e96d96;path=/html/semantics/document-metadata/the-meta-element/pragma-directives/attr-meta-http-equiv-refresh/support/x%253Burl=foo/ Third-party resolvers # The following third party resolvers support SWHID resolution: Identifiers.org ; see: http://identifiers.org/swh/ (registry identifier MIR:00000655 ). Name-to-Thing (N2T) Note that resolution via Identifiers.org currently only supports core identifiers due to syntactic incompatibilities with qualifiers . Examples: https://identifiers.org/swh:1:cnt:94a9ed024d3859793618152ea559a168bbcbb5e2 https://identifiers.org/swh:1:dir:d198bc9d7a6bcf6db04f476d29314f157507d505 https://identifiers.org/swh:1:rev:309cf2674ee7a0749978cf8265ab91a60aea0f7d https://n2t.net/swh:1:rel:22ece559cc7cc2364edc5e5593d63ae8bd229f9f https://n2t.net/swh:1:snp:c7c108084bc0bf3d81436bf980b46e98bd338453 https://n2t.net/swh:1:cnt:4d99d2d18326621ccdd70f5ea66c2e2ac236ad8b;origin=https://gitorious.org/ocamlp3l/ocamlp3l_cvs.git;visit=swh:1:snp:d7f1b9eb7ccb596c2622c4780febaa02549830f9;anchor=swh:1:rev:2db189928c94d62a3b4757b3eec68f0a4d4113f0;path=/Examples/SimpleFarm/simplefarm.ml;lines=9-15 https://n2t.net/swh:1:cnt:f10371aa7b8ccabca8479196d6cd640676fd4a04;origin=https://github.com/web-platform-tests/wpt;visit=swh:1:snp:b37d435721bbd450624165f334724e3585346499;anchor=swh:1:rev:259d0612af038d14f2cd889a14a3adb6c9e96d96;path=/html/semantics/document-metadata/the-meta-element/pragma-directives/attr-meta-http-equiv-refresh/support/x%25253Burl=foo/ References # Roberto Di Cosmo, Morane Gruenpeter, Stefano Zacchiroli. Identifiers for Digital Objects: the Case of Software Source Code Preservation . In Proceedings of iPRES 2018 : 15th International Conference on Digital Preservation, Boston, MA, USA, September 2018, 9 pages. Roberto Di Cosmo, Morane Gruenpeter, Stefano Zacchiroli. Referencing Source Code Artifacts: a Separate Concern in Software Citation . In Computing in Science and Engineering, volume 22, issue 2, pages 33-43. ISSN 1521-9615, IEEE. March 2020. previous Data model next Command-line interface On this page Overview Syntax Semantics Core identifiers Qualifiers Interoperability URI scheme Git compatibility Automatically fixing invalid SWHIDs Examples Core identifiers Identifiers with qualifiers Implementation Computing Choosing what type of SWHID to use Resolvers Software Heritage resolver Third-party resolvers References Edit This Page Show Source so the DOM is not blocked --> © Copyright 2015-2025 The Software Heritage developers. Created using Sphinx 7.4.7. Built with the PyData Sphinx Theme 0.16.1. | 2026-01-13T09:29:16 |
https://huggingface.co/datasets/Bingguang/HardGen | Bingguang/HardGen · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: Bingguang / HardGen like 65 Tasks: Question Answering Text Generation Modalities: Text Formats: json Languages: English Size: 10K - 100K ArXiv: arxiv: 2601.01498 arxiv: 2510.24645 Tags: agent Agentic Learning tool use BFCL Libraries: Datasets pandas Polars + 1 License: apache-2.0 Dataset card Data Studio Files Files and versions xet Community 4 \\nOkay, let's tackle the user's request step by step. The user wants to determine the current working directory path and then search for all files and directories in the current directory and its subdirectories.\\n\\nFirst, I need to figure out the current working directory. The 'pwd' command is perfect for that. It doesn't require any parameters, so I'll call it first. That should give the user the path they're in.\\n\\nNext, the user wants to search all files and directories in the current directory and subdirectories. The 'find' function can do this. The 'find' tool has parameters 'path' and 'name'. The default for 'path' is \\\".\\\", which is the current directory. Since they want everything, the 'name' parameter should be None (or omitted) to return all items. The default for 'name' is already None, so I just need to call find with the default parameters. \\n\\nWait, the user specified \\\"its subdirectories\\\" so the recursive search is covered by the find tool's description. So using find with path \\\".\\\" and no name should work. I don't need to specify any parameters except maybe path, but since it's default, it's okay. \\n\\nSo the function calls should be first pwd, then find. Let me check the parameters again. The find function's 'path' defaults to \\\".\\\", which is correct. The 'name' is optional and defaults to None. So the correct calls are [pwd(), find(path=\\\".\\\")]. \\n\\nI need to make sure that the parameters are correctly formatted. Since 'path' is set to \\\".\\\", even though it's the default, including it explicitly might be better to ensure clarity. The user might expect the search to start at the current directory, so specifying path=\\\".\\\" is safe. \\n\\nNo other functions are needed here. The 'ls' command only lists the current directory, not subdirectories, so 'find' is the right choice. Alright, that should cover the user's needs.\\n \\n[pwd(), find(path=\\\".\\\")]\",\n \"current_working_directory\": \"workspace\",\n \"error_tool_response\": null,\n \"gpt_analysis\": \"gpt_analysis\",\n \"have_retry\": null,\n \"initial_config\": null,\n \"involved_classes\": null,\n \"role\": \"assistant\",\n \"ziped_function_call_list\": null\n}"},"3":{"kind":"string","value":"{\n \"content\": \"[{'pwd()': '{\\\"current_working_directory\\\": \\\"/workspace\\\"}'}, {'find(path=\\\".\\\")': '{\\\"matches\\\": [\\\"./processed\\\", \\\"./processed/vqrqs3933.md\\\", \\\"./processed/akqff.md\\\", \\\"./processed/documents\\\", \\\"./requirements.txt\\\", \\\"./dqyiu_68828.json\\\", \\\"./ulyuo.json\\\", \\\"./data\\\", \\\"./data/raw\\\", \\\"./data/raw/dtpsp.json\\\", \\\"./data/metadata.json\\\", \\\"./data/vwccl.md\\\", \\\"./data/unggv.json\\\", \\\"./data/code\\\", \\\"./data/project\\\"]}'}]\",\n \"role\": \"tool\"\n}"},"4":{"kind":"string","value":"{\n \"content\": \" \\nOkay, let's see what the user needs here. The user asked to determine the current working directory and then search all files and directories in the current directory and subdirectories.\\n\\nFirst, the assistant already called pwd() and find(path=\\\".\\\") in the previous turn. The tool responses show that pwd() returned \\\"/workspace\\\" as the current directory. The find function with path \\\".\\\" gave a list of matches including various files and directories under the current directory and its subdirectories. \\n\\nNow, the user's requirement is to address their query in the next step. Since the user wanted both the current directory and a search, the assistant already executed both functions successfully. The tool_response includes the path and the matches. \\n\\nThe thought process should confirm that both functions were executed and their results are available. The reply should describe the results. Since the user's needs were met, there's no need for further function calls. The assistant should present the findings, like stating the current directory and listing the found items. But according to the output format, the reply_to_the_user should either be function calls or a description. Since the functions are already done, the reply should be a description summarizing the results. \\n\\nWait, the output format says if you need to give a description, output a sentence. So the assistant should say something like \\\"The current working directory is /workspace. The search found the following items: [list of matches].\\\" But the matches are in the tool_response's find result. However, the user might just need the info presented. \\n\\nBut looking back at the instructions, in the reply_to_the_user section, if you need to give a description, output a sentence. Since the functions have been executed, the next step is to describe the results. So the assistant should format the answer with the current directory and the matches from find. \\n\\nWait, but the example given in the instructions for reply_to_the_user when giving a description is like \\\"the cd function is executed success, and current workdirctory is src.\\\" So in this case, the assistant should combine both results. \\n\\nSo the thought process would note that both functions were executed successfully. The reply should state the current directory and list the found items. But since the matches are many, maybe just mention that the search found items like those listed. \\n\\nAlternatively, the exact answer should reference the tool_response data. The current_working_directory is /workspace, and the matches array includes all those paths. So the assistant can present that info concisely.\\n \\nThe current working directory is /workspace. The search found the following items: [\\\"./processed\\\", \\\"./processed/vqrqs3933.md\\\", \\\"./processed/akqff.md\\\", \\\"./processed/documents\\\", \\\"./requirements.txt\\\", \\\"./dqyiu_68828.json\\\", \\\"./ulyuo.json\\\", \\\"./data\\\", \\\"./data/raw\\\", \\\"./data/raw/dtpsp.json\\\", \\\"./data/metadata.json\\\", \\\"./data/vwccl.md\\\", \\\"./data/unggv.json\\\", \\\"./data/code\\\", \\\"./data/project\\\"].\",\n \"current_working_directory\": null,\n \"error_tool_response\": null,\n \"full_content\": null,\n \"gpt_analysis\": null,\n \"have_retry\": null,\n \"initial_config\": null,\n \"role\": \"assistant\"\n}"},"5":{"kind":"string","value":"{\n \"content\": \"Display the contents of the file named unggv.json in the data directory, and then display the last 7 lines of the file named dtpsp.json, which is in the data directory of the raw directory.\",\n \"role\": \"user\"\n}"},"6":{"kind":"string","value":"{\n \"content\": \" \\nOkay, let's tackle the user's latest request. They want to display the contents of \\\"unggv.json\\\" in the data directory and the last 7 lines of \\\"dtpsp.json\\\" located in the data/raw directory.\\n\\nFirst, I need to check the current directory. From the previous tool response, the current working directory is \\\"/workspace\\\". The user mentioned \\\"data directory\\\", so \\\"unggv.json\\\" is directly under \\\"/workspace/data/unggv.json\\\". But to access it, I should use the 'cat' command. However, 'cat' requires the file to be in the current directory. Since the current directory is \\\"/workspace\\\", I need to check if \\\"unggv.json\\\" is there. Wait, looking back at the find results, \\\"unggv.json\\\" is listed under \\\"./data/unggv.json\\\". So it's in the data subdirectory. To access it, I need to either change into the data directory first or specify the path, but the 'cat' tool only allows the file name in the current directory. Therefore, I should first 'cd' into the data directory. \\n\\nWait, the 'cd' tool changes the directory, so first step: cd into 'data'. Then, use 'cat unggv.json'. After that, for the second part, the user wants the last 7 lines of 'dtpsp.json' in data/raw. Since we are now in the data directory, the 'raw' directory is a subdirectory. So we need to 'cd raw' to get into that directory, then use 'tail' with lines=7 on 'dtpsp.json'. But after that, we might need to go back, but the user didn't ask for that. Alternatively, maybe we can do it without changing directories again by specifying the path, but according to the tool's parameters, 'tail' only takes the file name in the current directory. \\n\\nWait, the 'tail' parameters say \\\"No path is allowed and you can only perform on file at local directory.\\\" So to access 'data/raw/dtpsp.json', we need to be in the 'data/raw' directory. So the steps would be:\\n\\n1. Current directory is /workspace. First, to access 'unggv.json' in data/, do 'cd data', then 'cat unggv.json'.\\n2. Then, to get into data/raw, do 'cd raw', then 'tail(file_name=\\\"dtpsp.json\\\", lines=7)'.\\n\\nBut after the first 'cd data', the current directory becomes /workspace/data. Then after 'cd raw', it becomes /workspace/data/raw. Then after those commands, the user might want to return, but since it's a multi-step process, the assistant should just proceed step by step.\\n\\nHowever, the user's request is to first display unggv.json and then dtpsp.json. So the function calls would be:\\n\\nFirst, cd into data: [cd(folder=\\\"data\\\")]\\n\\nThen, cat unggv.json: [cat(file_name=\\\"unggv.json\\\")]\\n\\nThen, cd into raw: [cd(folder=\\\"raw\\\")]\\n\\nThen, tail dtpsp.json with 7 lines: [tail(file_name=\\\"dtpsp.json\\\", lines=7)]\\n\\nBut after these steps, the current directory is now data/raw. The user might need to go back, but since the user didn't ask, maybe it's okay. Alternatively, maybe there's another way without changing directories multiple times, but according to the tool constraints, it's necessary.\\n\\nWait, but the 'find' result shows that 'dtpsp.json' is in \\\"./data/raw/dtpsp.json\\\". So the path from the current directory (which is /workspace) would require navigating into data/raw. So the steps are necessary.\\n\\nTherefore, the function calls should be in the order:\\n\\n1. cd into data\\n2. cat unggv.json\\n3. cd into raw\\n4. tail dtpsp.json with lines=7\\n\\nSo the function calls would be:\\n\\n[cd(folder=\\\"data\\\"), cat(file_name=\\\"unggv.json\\\"), cd(folder=\\\"raw\\\"), tail(file_name=\\\"dtpsp.json\\\", lines=7)]\\n\\nBut I need to make sure each step is correct. Let me check each function's parameters again.\\n\\nFor 'cd', the parameter is 'folder', which is the directory to change to. So first cd to \\\"data\\\", then from there cd to \\\"raw\\\" (since current is now data/). \\n\\nThe 'cat' requires the file name in current directory. After cd data, unggv.json is there. Then, after cd raw, dtpsp.json is in current directory. So yes, that works.\\n\\nTherefore, the correct function calls are as above.\\n \\n[cd(folder=\\\"data\\\"), cat(file_name=\\\"unggv.json\\\"), cd(folder=\\\"raw\\\"), tail(file_name=\\\"dtpsp.json\\\", lines=7)]\",\n \"current_working_directory\": \"workspace\",\n \"full_content\": null,\n \"gpt_analysis\": null,\n \"have_retry\": null,\n \"initial_config\": null,\n \"involved_classes\": null,\n \"role\": \"assistant\",\n \"ziped_function_call_list\": null\n}"},"7":{"kind":"string","value":"{\n \"content\": \"[{'cd(folder=\\\"data\\\")': '{\\\"current_working_directory\\\": \\\"data\\\"}'}, {'cat(file_name=\\\"unggv.json\\\")': '{\\\"file_content\\\": \\\"{ \\\\\\\\\\\"data\\\\\\\\\\\": { \\\\\\\\\\\"id\\\\\\\\\\\": \\\\\\\\\\\"94\\\\\\\\\\\", \\\\\\\\\\\"type\\\\\\\\\\\": \\\\\\\\\\\"product\\\\\\\\\\\" }}\\\"}'}, {'cd(folder=\\\"raw\\\")': '{\\\"current_working_directory\\\": \\\"raw\\\"}'}, {'tail(file_name=\\\"dtpsp.json\\\", lines=7)': '{\\\"last_lines\\\": \\\"{ \\\\\\\\\\\"data\\\\\\\\\\\": { \\\\\\\\\\\"id\\\\\\\\\\\": \\\\\\\\\\\"27\\\\\\\\\\\", \\\\\\\\\\\"type\\\\\\\\\\\": \\\\\\\\\\\"user\\\\\\\\\\\" }}\\\"}'}]\",\n \"role\": \"tool\"\n}"},"8":{"kind":"string","value":"{\n \"content\": \" \\nOkay, let's see what the user is asking for now. The user's latest query was to display the contents of \\\"unggv.json\\\" in the data directory and the last 7 lines of \\\"dtpsp.json\\\" located in the data/raw directory.\\n\\nLooking at the previous interactions, the assistant first used pwd() and find() to get the current directory and list all files. Then, the user's next request required navigating into the data directory with cd(\\\"data\\\"), then using cat on unggv.json. After that, they changed to the raw directory with cd(\\\"raw\\\") and used tail on dtpsp.json with lines=7. \\n\\nThe tool responses show that all these commands were executed successfully. The current working directory was first changed to \\\"data\\\", then to \\\"raw\\\". The cat and tail commands both returned the expected file contents. Since all the functions called in the assistant's response have been executed without errors, there's no need to repeat any commands. The user's requirements have been fully met. Now, the assistant should present the results of these commands to the user in a clear manner, mentioning the contents of unggv.json and the last lines of dtpsp.json as per the tool responses.\\n \\nThe contents of \\\"unggv.json\\\" in the data directory are: \\n\\\"{ \\\"data\\\": { \\\"id\\\": \\\"94\\\", \\\"type\\\": \\\"product\\\" }}\\\". \\n\\nThe last 7 lines of \\\"dtpsp.json\\\" in the data/raw directory are: \\n\\\"{ \\\"data\\\": { \\\"id\\\": \\\"27\\\", \\\"type\\\": \\\"user\\\" }}\\\".\",\n \"current_working_directory\": null,\n \"error_tool_response\": null,\n \"gpt_analysis\": null,\n \"have_retry\": null,\n \"initial_config\": null,\n \"involved_classes\": null,\n \"role\": \"assistant\",\n \"ziped_function_call_list\": null\n}"},"9":{"kind":"null"},"10":{"kind":"null"},"11":{"kind":"null"},"12":{"kind":"null"},"13":{"kind":"null"},"14":{"kind":"null"},"15":{"kind":"null"},"16":{"kind":"null"}}},{"rowIdx":1,"cells":{"0":{"kind":"string","value":"{\n \"content\": \"You are an expert in composing functions. You are given a question and a set of possible functions. Based on the question, you will need to make one or more function/tool calls to achieve the purpose.\\nIf none of the functions can be used, point it out. If the given question lacks the parameters required by the function, also point it out.\\nYou should only return the function calls in your response.\\n\\nIf you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]\\nYou SHOULD NOT include any other text in the response.\\n\\nAt each turn, you should try your best to complete the tasks requested by the user within the current turn. Continue to output functions to call until you have fulfilled the user's request to the best of your ability. Once you have no more functions to call, the system will consider the current turn complete and proceed to the next turn or task. \\n\\nHere is a list of functions in JSON format that you can invoke.\\n [{\\\"name\\\": \\\"cat\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Display the contents of a file of any extension from currrent directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file from current directory to display. No path is allowed. \\\"}}, \\\"required\\\": [\\\"file_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_content\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The content of the file.\\\"}}}}, {\\\"name\\\": \\\"cd\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Change the current working directory to the specified folder.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"folder\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The folder of the directory to change to. You can only change one folder at a time. \\\"}}, \\\"required\\\": [\\\"folder\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"current_working_directory\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The new current working directory path.\\\"}}}}, {\\\"name\\\": \\\"cp\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Copy a file or directory from one location to another. If the destination is a directory, the source file or directory will be copied into the destination directory. Both source and destination must be local to the current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"source\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file or directory to copy.\\\"}, \\\"destination\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The destination name to copy the file or directory to. If the destination is a directory, the source will be copied into this directory. No file paths allowed. \\\"}}, \\\"required\\\": [\\\"source\\\", \\\"destination\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"result\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The result of the copy operation or an error message if the operation fails.\\\"}}}}, {\\\"name\\\": \\\"diff\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Compare two files of any extension line by line at the current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name1\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the first file in current directory.\\\"}, \\\"file_name2\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the second file in current directorry. \\\"}}, \\\"required\\\": [\\\"file_name1\\\", \\\"file_name2\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"diff_lines\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The differences between the two files.\\\"}}}}, {\\\"name\\\": \\\"du\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Estimate the disk usage of a directory and its contents.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"human_readable\\\": {\\\"type\\\": \\\"boolean\\\", \\\"description\\\": \\\"If True, returns the size in human-readable format (e.g., KB, MB). \\\", \\\"default\\\": false}}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"disk_usage\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The estimated disk usage.\\\"}}}}, {\\\"name\\\": \\\"echo\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Write content to a file at current directory or display it in the terminal.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"content\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The content to write or display.\\\"}, \\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file at current directory to write the content to. Defaults to None. \\\", \\\"default\\\": \\\"None\\\"}}, \\\"required\\\": [\\\"content\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"terminal_output\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The content if no file name is provided, or None if written to file.\\\"}}}}, {\\\"name\\\": \\\"find\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Find any file or directories under specific path that contain name in its file name. This method searches for files of any extension and directories within a specified path that match the given name. If no name is provided, it returns all files and directories in the specified path and its subdirectories. Note: This method performs a recursive search through all subdirectories of the given path.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"path\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The directory path to start the search. Defaults to the current directory (\\\\\\\".\\\\\\\").\\\", \\\"default\\\": \\\".\\\"}, \\\"name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file or directory to search for. If None, all items are returned. \\\", \\\"default\\\": \\\"None\\\"}}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"matches\\\": {\\\"type\\\": \\\"array\\\", \\\"description\\\": \\\"A list of matching file and directory paths relative to the given path.\\\", \\\"items\\\": {\\\"type\\\": \\\"string\\\"}}}}}, {\\\"name\\\": \\\"grep\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Search for lines in a file of any extension at current directory that contain the specified pattern.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file to search. No path is allowed and you can only perform on file at local directory.\\\"}, \\\"pattern\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The pattern to search for. \\\"}}, \\\"required\\\": [\\\"file_name\\\", \\\"pattern\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"matching_lines\\\": {\\\"type\\\": \\\"array\\\", \\\"description\\\": \\\"Lines that match the pattern.\\\", \\\"items\\\": {\\\"type\\\": \\\"string\\\"}}}}}, {\\\"name\\\": \\\"ls\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: List the contents of the current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"a\\\": {\\\"type\\\": \\\"boolean\\\", \\\"description\\\": \\\"Show hidden files and directories. Defaults to False. \\\", \\\"default\\\": false}}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"current_directory_content\\\": {\\\"type\\\": \\\"array\\\", \\\"description\\\": \\\"A list of the contents of the specified directory.\\\", \\\"items\\\": {\\\"type\\\": \\\"string\\\"}}}}}, {\\\"name\\\": \\\"mkdir\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Create a new directory in the current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"dir_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the new directory at current directory. You can only create directory at current directory.\\\"}}, \\\"required\\\": [\\\"dir_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {}}}, {\\\"name\\\": \\\"mv\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Move a file or directory from one location to another. so\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"source\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Source name of the file or directory to move. Source must be local to the current directory.\\\"}, \\\"destination\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The destination name to move the file or directory to. Destination must be local to the current directory and cannot be a path. If destination is not an existing directory like when renaming something, destination is the new file name. \\\"}}, \\\"required\\\": [\\\"source\\\", \\\"destination\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"result\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The result of the move operation.\\\"}}}}, {\\\"name\\\": \\\"pwd\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Return the current working directory path.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"current_working_directory\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The current working directory path.\\\"}}}}, {\\\"name\\\": \\\"rm\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Remove a file or directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file or directory to remove. \\\"}}, \\\"required\\\": [\\\"file_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"result\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The result of the remove operation.\\\"}}}}, {\\\"name\\\": \\\"rmdir\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Remove a directory at current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"dir_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the directory to remove. Directory must be local to the current directory. \\\"}}, \\\"required\\\": [\\\"dir_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"result\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The result of the remove operation.\\\"}}}}, {\\\"name\\\": \\\"sort\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Sort the contents of a file line by line.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file appeared at current directory to sort. \\\"}}, \\\"required\\\": [\\\"file_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"sorted_content\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The sorted content of the file.\\\"}}}}, {\\\"name\\\": \\\"tail\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Display the last part of a file of any extension.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the file to display. No path is allowed and you can only perform on file at local directory.\\\"}, \\\"lines\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"The number of lines to display from the end of the file. Defaults to 10. \\\", \\\"default\\\": 10}}, \\\"required\\\": [\\\"file_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"last_lines\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The last part of the file.\\\"}}}}, {\\\"name\\\": \\\"touch\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Create a new file of any extension in the current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The name of the new file in the current directory. file_name is local to the current directory and does not allow path.\\\"}}, \\\"required\\\": [\\\"file_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {}}}, {\\\"name\\\": \\\"wc\\\", \\\"description\\\": \\\"This tool belongs to the Gorilla file system. It is a simple file system that allows users to perform basic file operations such as navigating directories, creating files and directories, reading and writing to files, etc. Tool description: Count the number of lines, words, and characters in a file of any extension from current directory.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"file_name\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Name of the file of current directory to perform wc operation on.\\\"}, \\\"mode\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Mode of operation ('l' for lines, 'w' for words, 'c' for characters). \\\", \\\"default\\\": \\\"l\\\"}}, \\\"required\\\": [\\\"file_name\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"count\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"The count of the number of lines, words, or characters in the file.\\\"}, \\\"type\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The type of unit we are counting. [Enum]: [\\\\\\\"lines\\\\\\\", \\\\\\\"words\\\\\\\", \\\\\\\"characters\\\\\\\"]\\\"}}}}, {\\\"name\\\": \\\"add_to_watchlist\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Add a stock to the watchlist.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"stock\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"the stock symbol to add to the watchlist. \\\"}}, \\\"required\\\": [\\\"stock\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"symbol\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"the symbol that were successfully added to the watchlist.\\\"}}}}, {\\\"name\\\": \\\"cancel_order\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Cancel an order.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"order_id\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"ID of the order to cancel. \\\"}}, \\\"required\\\": [\\\"order_id\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"order_id\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"ID of the cancelled order.\\\"}, \\\"status\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"New status of the order after cancellation attempt.\\\"}}}}, {\\\"name\\\": \\\"filter_stocks_by_price\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Filter stocks based on a price range.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"stocks\\\": {\\\"type\\\": \\\"array\\\", \\\"items\\\": {\\\"type\\\": \\\"string\\\"}, \\\"description\\\": \\\"List of stock symbols to filter.\\\"}, \\\"min_price\\\": {\\\"type\\\": \\\"float\\\", \\\"description\\\": \\\"Minimum stock price.\\\"}, \\\"max_price\\\": {\\\"type\\\": \\\"float\\\", \\\"description\\\": \\\"Maximum stock price. \\\"}}, \\\"required\\\": [\\\"stocks\\\", \\\"min_price\\\", \\\"max_price\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"filtered_stocks\\\": {\\\"type\\\": \\\"array\\\", \\\"description\\\": \\\"Filtered list of stock symbols within the price range.\\\", \\\"items\\\": {\\\"type\\\": \\\"string\\\"}}}}}, {\\\"name\\\": \\\"fund_account\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Fund the account with the specified amount.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"amount\\\": {\\\"type\\\": \\\"float\\\", \\\"description\\\": \\\"Amount to fund the account with. \\\"}}, \\\"required\\\": [\\\"amount\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"status\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Status of the funding operation.\\\"}, \\\"new_balance\\\": {\\\"type\\\": \\\"float\\\", \\\"description\\\": \\\"Updated account balance after funding.\\\"}}}}, {\\\"name\\\": \\\"get_account_info\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Get account information.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"account_id\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"ID of the account.\\\"}, \\\"balance\\\": {\\\"type\\\": \\\"float\\\", \\\"description\\\": \\\"Current balance of the account.\\\"}, \\\"binding_card\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"Card number associated with the account.\\\"}}}}, {\\\"name\\\": \\\"get_available_stocks\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Get a list of stock symbols in the given sector.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"sector\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"The sector to retrieve stocks from (e.g., 'Technology'). \\\"}}, \\\"required\\\": [\\\"sector\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"stock_list\\\": {\\\"type\\\": \\\"array\\\", \\\"description\\\": \\\"List of stock symbols in the specified sector.\\\", \\\"items\\\": {\\\"type\\\": \\\"string\\\"}}}}}, {\\\"name\\\": \\\"get_current_time\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Get the current time.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"current_time\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Current time in HH:MM AM/PM format.\\\"}}}}, {\\\"name\\\": \\\"get_order_details\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Get the details of an order.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"order_id\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"ID of the order. \\\"}}, \\\"required\\\": [\\\"order_id\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"id\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"ID of the order.\\\"}, \\\"order_type\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Type of the order.\\\"}, \\\"symbol\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Symbol of the stock in the order.\\\"}, \\\"price\\\": {\\\"type\\\": \\\"float\\\", \\\"description\\\": \\\"Price at which the order was placed.\\\"}, \\\"amount\\\": {\\\"type\\\": \\\"integer\\\", \\\"description\\\": \\\"Number of shares in the order.\\\"}, \\\"status\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Current status of the order. [Enum]: [\\\\\\\"Open\\\\\\\", \\\\\\\"Pending\\\\\\\", \\\\\\\"Completed\\\\\\\", \\\\\\\"Cancelled\\\\\\\"]\\\"}}}}, {\\\"name\\\": \\\"get_order_history\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Get the stock order ID history.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {}, \\\"required\\\": []}, \\\"response\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"order_history\\\": {\\\"type\\\": \\\"array\\\", \\\"description\\\": \\\"List of orders ID in the order history.\\\", \\\"items\\\": {\\\"type\\\": \\\"integer\\\"}}}}}, {\\\"name\\\": \\\"get_stock_info\\\", \\\"description\\\": \\\"This tool belongs to the trading system, which allows users to trade stocks, manage their account, and view stock information. Tool description: Get the details of a stock.\\\", \\\"parameters\\\": {\\\"type\\\": \\\"dict\\\", \\\"properties\\\": {\\\"symbol\\\": {\\\"type\\\": \\\"string\\\", \\\"description\\\": \\\"Symbol that uniquely identifies the stock. \\\"}}, \\\"required\\\": [\\\"symbol\\\"]}, \\\"response\\\": {\\\"type\\\": \\\"d | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/categories/block-storage-software?trk=products_details_guest_other_products_by_org_section_product_link_result-card_subtitle-click#main-content | Best Block Storage Software | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Information Technology Manager (3) Storage Engineer (2) Information Technology Specialist (2) Information Communication Technology Manager (1) Information Technology Consultant (1) See all products Find top products in Block Storage Software category Software used to store large scalable volumes of structured data in blocks. - Store data in separate, fixed-size blocks with distinct addresses - Configure and move data blocks and edit individual components - Use inbuilt security features such as data encryption and restricted access 27 results Tencent Cloud Block Storage Block Storage Software by Tencent A stable, low-latency, scalable, and persistent block storage service. View product OVHcloud Block Storage Block Storage Software by OVHcloud With Block Storage, you can use secure and flexible storage volumes that are available on demand. Block Storage is based on Ceph, an open-source technology. View product DigitalOcean Block Storage Block Storage Software by DigitalOcean Block storage gives developers scalable and highly available SSD-based cloud storage to attach to Droplets. From 1GB to 16TB, priced at $0.10/GB per month. View product Vultr Block Storage Software by Vultr View details and pricing information for the entire suite of Vultr products, including cloud compute, cloud GPU, bare metal, Kubernetes, and more. View product Vultr Bare Metal Block Storage Software by Vultr Stay in full control of your environment with high performance single-tenant dedicated servers, accelerated by AMD and NVIDIA GPUs and high-performance CPUs from AMD and Intel. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights DataCore SANsymphony Block Storage Software by DataCore Software DataCore SANsymphony is a software-defined storage platform that unifies and safeguards diverse storage systems across SAN and HCI environments. It delivers continuous data availability and cyber resilience through automated business continuity and disaster recovery workflows and continuous data protection. SANsymphony keeps your infrastructure secure and recoverable from outages, hardware failures, or ransomware—ensuring mission-critical workloads stay online and your data always remains in control. Built for flexibility, performance, and efficiency, SANsymphony lets you modernize without disruption—integrating new storage technologies seamlessly while maximizing the value of existing assets. Its intelligent caching, auto-tiering, and parallel I/O acceleration drive consistent high-speed performance, while centralized management and automation reduce operational overhead and lower TCO. DataCore SANsymphony gives enterprises true storage freedom—resilient, optimized, and future-ready. View product Vultr Block Storage Block Storage Software by Vultr Create expandable HDD or NVMe SSD storage volumes and mount them directly to your compute instances. View product Software-Defined Block Storage Block Storage Software by Lightbits Labs Lightbits Labs invented the NVMe over TCP protocol and offers best-of-breed software-defined block storage that enables data center infrastructure modernization for organizations building a private or public cloud. Built from the ground up for low consistent latency, scalability, resiliency, and cost-efficiency, Lightbits software delivers the best price/performance for real-time analytics, transactional, and AI/ML workloads. View product Ceph Block Storage Block Storage Software by Ceph Ceph’s object storage system isn’t limited to native binding or RESTful APIs. You can mount Ceph as a thinly provisioned block device! When you write data to Ceph using a block device, Ceph automatically stripes and replicates the data across the cluster. Ceph’s RADOS Block Device (RBD) also integrates with Kernel Virtual Machines (KVMs), bringing Ceph’s virtually unlimited storage to KVMs running on your Ceph clients. View product Open-E Software Defined Storage Block Storage Software by Pardis Co. سیستم عامل ذخیره سازی Open-E مبتنی بر ZFS شرکت Oracle است. این تکنولوژی برای ذخیره سازی اطلاعات در پروژههای مجازیسازی و پشتیبانگیری با Performance بسیار بالا پیشنهاد میگردد. این محصول قابلیت رقابت با سیستمهای SAN Storage سنتی همچون EMC Unity و HP 3PAR را دارای میباشد. https://www.open-e.com/where-to-buy/partners/pardis-virtualization-solutions-provider/ View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:16 |
https://www.linkedin.com/products/cloudflare-waf/?trk=products_seo_search | Cloudflare WAF | LinkedIn Skip to main content LinkedIn Cloudflare in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Cloudflare WAF Web Application Firewalls (WAF) by Cloudflare See who's skilled in this Add as skill Get started Report this product About Built for the modern enterprise architecture An intelligent, integrated, and scalable solution to protect your business-critical web applications from malicious attacks, with no changes to your existing infrastructure. Media Products media viewer No more previous content Cloudflare WAF: Product Demo The Cloudflare web application firewall, or WAF, is an OSI layer 7 intelligent, integrated, and scalable solution to secure your web applications, without changing your existing infrastructure or sacrificing performance. The Cloudflare WAF protects against a large number of web attack vectors including file inclusion, Cross-Site Scripting attacks, SQL injections, and many other vulnerabilities. This video will highlight key features of the Cloudflare WAF, including how to use the WAF rulesets t Cloudflare Web Application Firewall Cloudflare Web Application Firewall's intuitive dashboard enables users to build powerful rules through easy clicks and also provides Terraform integration. Every request to the WAF is inspected against the rule engine and the threat intelligence curated from protecting approximately 25 million websites. Suspicious requests can be blocked, challenged or logged as per the needs of the user while legitimate requests are routed to the destination, agnostic of whether it lives on-premise or in the c No more next content Featured customers of Cloudflare WAF Sony Music Entertainment Musicians 1,282,988 followers Zerodha Financial Services 580,035 followers Chrono24 Retail Luxury Goods and Jewelry 15,639 followers OneTrust Software Development 380,493 followers Blackmores Group Wellness and Fitness Services 61,966 followers Maropost Commerce Cloud Software Development 3,187 followers TMB (Trusted Media Brands) Media Production 132,785 followers ThredUp Retail Apparel and Fashion 73,324 followers Quintype Technologies Inc. Software Development 32,538 followers Kathmandu Retail 25,574 followers orderbird IT Services and IT Consulting 5,084 followers Oak National Academy E-Learning Providers 25,588 followers Carousell Group Software Development 129,533 followers Naranja X Financial Services 837,339 followers INSEAD Higher Education 739,009 followers Hemnet Real Estate 12,582 followers Trendyol Group Technology, Information and Internet 536,123 followers udaan.com Technology, Information and Internet 606,047 followers 早稲田大学 WASEDA University Higher Education 112,057 followers SurePrep, part of Thomson Reuters Software Development 9,598 followers Show more Show less Similar products Akamai Web Application Protector Akamai Web Application Protector Web Application Firewalls (WAF) Imperva Web Application Firewall (WAF) Imperva Web Application Firewall (WAF) Web Application Firewalls (WAF) Advanced API Security Advanced API Security Web Application Firewalls (WAF) Radware Cloud WAF Radware Cloud WAF Web Application Firewalls (WAF) Alibaba Web Application Firewall Alibaba Web Application Firewall Web Application Firewalls (WAF) DNSFilter DNSFilter Web Application Firewalls (WAF) Sign in to see more Show more Show less Cloudflare products Argo Smart Routing Argo Smart Routing Network Management Software Cloudflare DDoS Protection Cloudflare DDoS Protection DDoS Protection Software Cloudflare DNS Cloudflare DNS Managed DNS Services Software Cloudflare Load Balancing Cloudflare Load Balancing Load Balancing Software Cloudflare Registrar Cloudflare Registrar Managed DNS Services Software Cloudflare Spectrum Cloudflare Spectrum DDoS Protection Software Cloudflare SSL / TLS Cloudflare SSL / TLS SSL Certificates Software Cloudflare Web Analytics Cloudflare Web Analytics Digital Analytics Software Cloudflare Workers Cloudflare Workers Server Virtualization Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fcardano-foundation-veridian%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/tencentglobal-tencent-cloud-instant-messaging-im/ | Tencent Cloud Instant Messaging (IM) | LinkedIn Skip to main content LinkedIn Tencent in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms by Tencent See who's skilled in this Add as skill Learn more Report this product About Tencent Cloud Instant Messaging (IM) provides globally interconnected chat APIs, multi-platform SDKs, and UIKit components to help you quickly bring messaging capabilities such as one-to-one chat, group chat, chat rooms, and system notifications to your applications and websites. Similar products Slack Slack Cloud Communications Platforms Avaya Cloud Office Avaya Cloud Office Cloud Communications Platforms MessageBird MessageBird Cloud Communications Platforms Vonage Communications APIs Vonage Communications APIs Cloud Communications Platforms CPaaS CPaaS Cloud Communications Platforms Channelize.io: Live Stream Shopping Platform Channelize.io: Live Stream Shopping Platform Cloud Communications Platforms Sign in to see more Show more Show less Tencent products Cloud Native Database TDSQL-C Cloud Native Database TDSQL-C Relational Database Management Systems Cloud Object Storage (COS) Cloud Object Storage (COS) Object Storage Software Cloud Virtual Machine (CVM) Cloud Virtual Machine (CVM) Server Virtualization Software Simple Email Service (SES) Simple Email Service (SES) Email Marketing Software Tencent Cloud Automation Tools Tencent Cloud Automation Tools Build Automation Tools Tencent Cloud Block Storage Tencent Cloud Block Storage Block Storage Software Tencent Cloud Lighthouse Tencent Cloud Lighthouse Enterprise Cloud Platforms Tencent Effect SDK Tencent Effect SDK Software Development Kits (SDK) Tencent Real-Time Communication (TRTC) Tencent Real-Time Communication (TRTC) Live Streaming Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://docs.softwareheritage.org/devel/swh-model/data-model.html | Data model — Software Heritage documentation Skip to main content Back to top Ctrl + K Development API reference Usage Resources Infrastructure More About GitLab PyPI System Status Software Heritage Homepage Development API reference Usage Resources Infrastructure About GitLab PyPI System Status Software Heritage Homepage Section Navigation swh.alter Using swh-alter Removal algorithm Recovery bundles swh.alter package swh.alter.bech32 module swh.alter.cli module swh.alter.inventory module swh.alter.mirror_notification_watcher module swh.alter.notifications module swh.alter.operations module swh.alter.progressbar module swh.alter.recovery_bundle module swh.alter.removable module swh.alter.subgraph module swh.alter.utils module swh.auth Command-line interface Django components swh.auth package swh.auth.django package swh.auth.django.backends module swh.auth.django.middlewares module swh.auth.django.models module swh.auth.django.utils module swh.auth.django.views module swh.auth.starlette package swh.auth.starlette.backends module swh.auth.cli module swh.auth.keycloak module swh.auth.pytest_plugin module swh.auth.utils module swh.coarnotify Explanations What’s COAR Notify ? What are we doing with the metadata ? swh.coarnotify package swh.coarnotify.server package swh.coarnotify.server.management package swh.coarnotify.server.admin module swh.coarnotify.server.apps module swh.coarnotify.server.forms module swh.coarnotify.server.handlers module swh.coarnotify.server.models module swh.coarnotify.server.signals module swh.coarnotify.server.utils module swh.coarnotify.server.views module swh.coarnotify.settings package swh.coarnotify.settings.common module swh.coarnotify.settings.development module swh.coarnotify.settings.production module swh.coarnotify.settings.tests module swh.coarnotify.cli module swh.coarnotify.client module swh.coarnotify.manage module swh.coarnotify.parsers module swh.coarnotify.renderers module swh.coarnotify.tasks module swh.coarnotify.urls module How-to guides Install swh-coarnotify Access the inbox Send a mention of a software in a scientific paper References Workflows Specifications Rest API Command Line Interface Notification payloads swh.core Command-line interface Common database utilities swh.core package swh.core.api package swh.core.api.asynchronous module swh.core.api.classes module swh.core.api.gunicorn_config module swh.core.api.negotiation module swh.core.api.serializers module swh.core.cli package swh.core.cli.backend module swh.core.cli.db module swh.core.cli.nar module swh.core.cli.sentry module swh.core.db package swh.core.db.common module swh.core.db.db_utils module swh.core.github package swh.core.github.pytest_plugin module swh.core.github.utils module swh.core.s3 namespace swh.core.s3.downloader module swh.core.s3.pytest_plugin module swh.core.api_async module swh.core.collections module swh.core.config module swh.core.logger module swh.core.logging module swh.core.nar module swh.core.pytest_plugin module swh.core.retry module swh.core.sentry module swh.core.statsd module swh.core.tarball module swh.core.utils module swh.counters swh.counters package swh.counters.api package swh.counters.api.client module swh.counters.api.server module swh.counters.cli module swh.counters.history module swh.counters.in_memory module swh.counters.interface module swh.counters.journal_client module swh.counters.kafka_client module swh.counters.redis module swh.dataportal How to guides How to use the CLI References Static site generation process Data used to generate the website swh.datasets Luigi workflows Command-line interface swh.datasets package swh.datasets.luigi package swh.datasets.luigi.aggregate_datasets module swh.datasets.luigi.blobs_datasets module swh.datasets.luigi.file_names module swh.datasets.luigi.impact module swh.datasets.luigi.origin_contributors module swh.datasets.cli module swh.datasets.download module swh.datasets.shell module swh.deposit Deposit API User Manual API Documentation Service document Create deposit Update content Update metadata Retrieve status Display content Deposit metadata Use cases Register account Deposit internals Running swh-deposit locally Production deployment Authentication Loading workflow Specifications Loading specification Protocol reference The metadata-only deposit swh.deposit package swh.deposit.api package swh.deposit.api.private package swh.deposit.api.collection module swh.deposit.api.common module swh.deposit.api.content module swh.deposit.api.converters module swh.deposit.api.edit module swh.deposit.api.edit_media module swh.deposit.api.service_document module swh.deposit.api.state module swh.deposit.api.sword_edit module swh.deposit.api.urls module swh.deposit.api.utils module swh.deposit.cli package swh.deposit.cli.admin module swh.deposit.cli.client module swh.deposit.fixtures package swh.deposit.loader package swh.deposit.loader.checker module swh.deposit.loader.checks module swh.deposit.loader.tasks module swh.deposit.templates package swh.deposit.templates.deposit package swh.deposit.tests_migration package swh.deposit.apps module swh.deposit.auth module swh.deposit.client module swh.deposit.config module swh.deposit.errors module swh.deposit.exception module swh.deposit.gunicorn_config module swh.deposit.manage module swh.deposit.models module swh.deposit.parsers module swh.deposit.urls module swh.deposit.utils module Command-line interface swh.digestmap Design document for a hash conversion service swh.digestmap module swh.export Software Heritage Graph Dataset Dataset Relational schema Setup on Amazon Athena Setup on Azure Databricks Exporting a dataset Exporting a subdataset swh.export package swh.export.exporters package swh.export.exporters.edges module swh.export.exporters.orc module swh.export.test namespace swh.export.test.test_edges module swh.export.test.test_journal_processor module swh.export.test.test_orc module swh.export.test.test_utils module swh.export.athena module swh.export.cli module swh.export.exporter module swh.export.fullnames module swh.export.journalprocessor module swh.export.luigi module swh.export.relational module swh.export.utils module swh.fuse Tutorial Configuration Advice for parallelization Design notes Command-line interface swh.fuse package swh.fuse.backends package swh.fuse.backends.compressed module swh.fuse.backends.objstorage module swh.fuse.backends.web_api module swh.fuse.fs namespace swh.fuse.fs.artifact module swh.fuse.fs.entry module swh.fuse.fs.mountpoint module swh.fuse.cache module swh.fuse.cli module swh.fuse.fuse module swh.graph Quickstart Graph Querying HTTP API Using the gRPC API Rust API Memory & Performance tuning Graph compression Command-line interface Docker environment git2graph Test graphs Example dataset Provenance index swh.graph namespace swh.graph.example_dataset package swh.graph.example_dataset.generate_dataset module swh.graph.grpc namespace swh.graph.grpc.swhgraph_pb2 module swh.graph.grpc.swhgraph_pb2_grpc module swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.shell module swh.graph.luigi package swh.graph.luigi.compressed_graph module swh.graph.luigi.subdataset module swh.graph.luigi.utils module swh.graph.cli module swh.graph.client module swh.graph.config module swh.graph.download module swh.graph.e2e_check module swh.graph.find_context module swh.graph.grpc_server module swh.graph.http_client module swh.graph.http_naive_client module swh.graph.http_rpc_server module swh.graph.naive_client module swh.graph.pytest_plugin module swh.graph.shell module swh.graph.webgraph module swh.graph.libs swh.graph.libs package swh.graph.libs.luigi package swh.graph.libs.luigi.topology module swh.graph.libs.shell module Software Heritage GraphQL API swh.indexer Software Heritage - Indexer Metadata workflow SwhPkg Vocabulary swh.indexer package swh.indexer.metadata_dictionary package swh.indexer.metadata_dictionary.base module swh.indexer.metadata_dictionary.cff module swh.indexer.metadata_dictionary.codemeta module swh.indexer.metadata_dictionary.composer module swh.indexer.metadata_dictionary.dart module swh.indexer.metadata_dictionary.gitea module swh.indexer.metadata_dictionary.github module swh.indexer.metadata_dictionary.maven module swh.indexer.metadata_dictionary.npm module swh.indexer.metadata_dictionary.nuget module swh.indexer.metadata_dictionary.python module swh.indexer.metadata_dictionary.ruby module swh.indexer.metadata_dictionary.utils module swh.indexer.storage package swh.indexer.storage.api package swh.indexer.storage.converters module swh.indexer.storage.db module swh.indexer.storage.exc module swh.indexer.storage.in_memory module swh.indexer.storage.interface module swh.indexer.storage.metrics module swh.indexer.storage.model module swh.indexer.storage.writer module swh.indexer.bibtex module swh.indexer.cli module swh.indexer.codemeta module swh.indexer.fossology_license module swh.indexer.indexer module swh.indexer.metadata module swh.indexer.metadata_detector module swh.indexer.mimetype module swh.indexer.namespaces module swh.indexer.origin_head module swh.indexer.rehash module Command-line interface swh.journal Software Heritage Journal clients swh.journal package swh.journal.writer package swh.journal.writer.inmemory module swh.journal.writer.interface module swh.journal.writer.kafka module swh.journal.writer.stream module swh.journal.client module swh.journal.pytest_plugin module swh.journal.serializers module swh.lister Tutorial: list the content of your favorite forge in just a few steps Tutorial: run a lister within docker-dev in just a few steps Save a forge swh.lister package swh.lister.arch package swh.lister.arch.lister module swh.lister.arch.tasks module swh.lister.aur package swh.lister.aur.lister module swh.lister.aur.tasks module swh.lister.bioconductor package swh.lister.bioconductor.lister module swh.lister.bioconductor.tasks module swh.lister.bitbucket package swh.lister.bitbucket.lister module swh.lister.bitbucket.tasks module swh.lister.bower package swh.lister.bower.lister module swh.lister.bower.tasks module swh.lister.cgit package swh.lister.cgit.lister module swh.lister.cgit.tasks module swh.lister.conda package swh.lister.conda.lister module swh.lister.conda.tasks module swh.lister.cpan package swh.lister.cpan.lister module swh.lister.cpan.tasks module swh.lister.cran package swh.lister.cran.lister module swh.lister.cran.tasks module swh.lister.crates package swh.lister.crates.lister module swh.lister.crates.tasks module swh.lister.debian package swh.lister.debian.lister module swh.lister.debian.tasks module swh.lister.dlang package swh.lister.dlang.lister module swh.lister.dlang.tasks module swh.lister.elm package swh.lister.elm.lister module swh.lister.elm.tasks module swh.lister.gitea package swh.lister.gitea.lister module swh.lister.gitea.tasks module swh.lister.github package swh.lister.github.lister module swh.lister.github.tasks module swh.lister.gitiles package swh.lister.gitiles.lister module swh.lister.gitiles.tasks module swh.lister.gitlab package swh.lister.gitlab.lister module swh.lister.gitlab.tasks module swh.lister.gitweb package swh.lister.gitweb.lister module swh.lister.gitweb.tasks module swh.lister.gnu package swh.lister.gnu.lister module swh.lister.gnu.tasks module swh.lister.gnu.tree module swh.lister.gogs package swh.lister.gogs.lister module swh.lister.gogs.tasks module swh.lister.golang package swh.lister.golang.lister module swh.lister.golang.tasks module swh.lister.hackage package swh.lister.hackage.lister module swh.lister.hackage.tasks module swh.lister.hex package swh.lister.hex.lister module swh.lister.hex.tasks module swh.lister.julia package swh.lister.julia.lister module swh.lister.julia.tasks module swh.lister.launchpad package swh.lister.launchpad.lister module swh.lister.launchpad.tasks module swh.lister.maven package swh.lister.maven.lister module swh.lister.maven.tasks module swh.lister.nixguix package swh.lister.nixguix.lister module swh.lister.nixguix.tasks module swh.lister.npm package swh.lister.npm.lister module swh.lister.npm.tasks module swh.lister.nuget package swh.lister.nuget.lister module swh.lister.nuget.tasks module swh.lister.opam package swh.lister.opam.lister module swh.lister.opam.tasks module swh.lister.packagist package swh.lister.packagist.lister module swh.lister.packagist.tasks module swh.lister.pagure package swh.lister.pagure.lister module swh.lister.pagure.tasks module swh.lister.phabricator package swh.lister.phabricator.lister module swh.lister.phabricator.tasks module swh.lister.pubdev package swh.lister.pubdev.lister module swh.lister.pubdev.tasks module swh.lister.puppet package swh.lister.puppet.lister module swh.lister.puppet.tasks module swh.lister.pypi package swh.lister.pypi.lister module swh.lister.pypi.tasks module swh.lister.rpm package swh.lister.rpm.lister module swh.lister.rpm.tasks module swh.lister.rubygems package swh.lister.rubygems.lister module swh.lister.rubygems.tasks module swh.lister.save_bulk package swh.lister.save_bulk.lister module swh.lister.save_bulk.tasks module swh.lister.sourceforge package swh.lister.sourceforge.lister module swh.lister.sourceforge.tasks module swh.lister.stagit package swh.lister.stagit.lister module swh.lister.stagit.tasks module swh.lister.tuleap package swh.lister.tuleap.lister module swh.lister.tuleap.tasks module swh.lister.cli module swh.lister.pattern module swh.lister.utils module Command-line interface swh.loader swh.loader.core VCS Loader Overview Package Loader Tutorial Package loader specifications swh.loader.core package swh.loader.core.converters module swh.loader.core.loader module swh.loader.core.metadata_fetchers module swh.loader.core.tasks module swh.loader.core.utils module Command-line interface swh.loader.bzr Software Heritage - How Bazaar/Breezy works swh.loader.bzr package swh.loader.bzr.loader module swh.loader.bzr.tasks module Software Heritage - CVS loader swh.loader.git swh.loader.git package swh.loader.git.base module swh.loader.git.converters module swh.loader.git.directory module swh.loader.git.from_disk module swh.loader.git.loader module swh.loader.git.tasks module swh.loader.git.utils module swh.loader.mercurial swh.loader.mercurial package swh.loader.mercurial.archive_extract module swh.loader.mercurial.converters module swh.loader.mercurial.directory module swh.loader.mercurial.hgutil module swh.loader.mercurial.identify module swh.loader.mercurial.loader module swh.loader.mercurial.tasks module swh.loader.mercurial.utils module swh.loader.metadata swh.loader.metadata package swh.loader.metadata.base module swh.loader.metadata.cli module swh.loader.metadata.gitea module swh.loader.metadata.github module swh.loader.metadata.journal_client module swh.loader.svn swh.loader.svn package swh.loader.svn.converters module swh.loader.svn.directory module swh.loader.svn.exception module swh.loader.svn.fast_crawler module swh.loader.svn.loader module swh.loader.svn.replay module swh.loader.svn.svn_repo module swh.loader.svn.svn_retry module swh.loader.svn.tasks module swh.loader.svn.utils module swh.model Data model SoftWare Heritage persistent IDentifiers (SWHIDs) Command-line interface swh.model package swh.model.fields package swh.model.fields.compound module swh.model.fields.hashes module swh.model.fields.simple module swh.model.cli module swh.model.collections module swh.model.discovery module swh.model.exceptions module swh.model.from_disk module swh.model.git_objects module swh.model.hashutil module swh.model.hypothesis_strategies module swh.model.merkle module swh.model.model module swh.model.swhids module swh.model.toposort module swh.model.validators module swh.objstorage Command-line interface Winery backend swh.objstorage namespace swh.objstorage.api namespace swh.objstorage.api.client module swh.objstorage.api.server module swh.objstorage.backends package swh.objstorage.backends.seaweedfs package swh.objstorage.backends.winery package swh.objstorage.backends.azure module swh.objstorage.backends.http module swh.objstorage.backends.in_memory module swh.objstorage.backends.libcloud module swh.objstorage.backends.noop module swh.objstorage.backends.pathslicing module swh.objstorage.proxies namespace swh.objstorage.proxies.readonly module swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module swh.objstorage.cli module swh.objstorage.constants module swh.objstorage.exc module swh.objstorage.factory module swh.objstorage.interface module swh.objstorage.multiplexer module swh.objstorage.objstorage module swh.objstorage.pytest_plugin module swh.objstorage.utils module swh.objstorage.replayer Command-line interface swh.objstorage.replayer package swh.objstorage.replayer.cli module swh.objstorage.replayer.replay module Software Heritage - Provenance swh.scanner Command-line interface swh.scanner package swh.scanner.dashboard package swh.scanner.dashboard.dashboard module swh.scanner.cli module swh.scanner.config module swh.scanner.data module swh.scanner.exceptions module swh.scanner.output module swh.scanner.policy module swh.scanner.scanner module swh.scanner.setup_wizard module swh.scheduler Command-line interface Software Heritage Scheduler Simulator swh.scheduler package swh.scheduler.api package swh.scheduler.api.client module swh.scheduler.api.serializers module swh.scheduler.api.server module swh.scheduler.celery_backend package swh.scheduler.celery_backend.config module swh.scheduler.celery_backend.first_visits module swh.scheduler.celery_backend.pika_listener module swh.scheduler.celery_backend.recurrent_visits module swh.scheduler.celery_backend.runner module swh.scheduler.celery_backend.utils module swh.scheduler.cli package swh.scheduler.cli.add_forge_now module swh.scheduler.cli.admin module swh.scheduler.cli.celery_monitor module swh.scheduler.cli.config module swh.scheduler.cli.journal module swh.scheduler.cli.origin module swh.scheduler.cli.origin_utils module swh.scheduler.cli.simulator module swh.scheduler.cli.task module swh.scheduler.cli.task_type module swh.scheduler.cli.utils module swh.scheduler.simulator package swh.scheduler.simulator.common module swh.scheduler.simulator.origin_scheduler module swh.scheduler.simulator.origins module swh.scheduler.simulator.task_scheduler module swh.scheduler.sql package swh.scheduler.sql.upgrades package swh.scheduler.backend module swh.scheduler.cli_utils module swh.scheduler.exc module swh.scheduler.in_memory module swh.scheduler.interface module swh.scheduler.journal_client module swh.scheduler.model module swh.scheduler.pytest_plugin module swh.scheduler.task module swh.scheduler.utils module swh.scrubber Command-line interface swh.scrubber package swh.scrubber.base_checker module swh.scrubber.cli module swh.scrubber.db module swh.scrubber.fixer module swh.scrubber.journal_checker module swh.scrubber.objstorage_checker module swh.scrubber.origin_locator module swh.scrubber.storage_checker module swh.scrubber.utils module swh.search Command-line interface Search Query Language swh.search package swh.search.api package swh.search.api.client module swh.search.api.server module swh.search.cli module swh.search.elasticsearch module swh.search.exc module swh.search.in_memory module swh.search.interface module swh.search.journal_client module swh.search.metrics module swh.search.translator module swh.search.utils module swh.shard Read Shard format Benchmarks swh.shard package swh.shard.cli module swh.storage Extrinsic metadata specification Object Masking swh.storage package swh.storage.algos package swh.storage.algos.diff module swh.storage.algos.dir_iterators module swh.storage.algos.directory module swh.storage.algos.discovery module swh.storage.algos.origin module swh.storage.algos.revisions_walker module swh.storage.algos.snapshot module swh.storage.algos.swhid module swh.storage.api package swh.storage.api.client module swh.storage.api.serializers module swh.storage.api.server module swh.storage.cassandra package swh.storage.cassandra.common module swh.storage.cassandra.converters module swh.storage.cassandra.cql module swh.storage.cassandra.diagram module swh.storage.cassandra.migrations module swh.storage.cassandra.model module swh.storage.cassandra.schema module swh.storage.cassandra.storage module swh.storage.postgresql package swh.storage.postgresql.converters module swh.storage.postgresql.db module swh.storage.postgresql.storage module swh.storage.proxies package swh.storage.proxies.blocking package swh.storage.proxies.masking package swh.storage.proxies.buffer module swh.storage.proxies.filter module swh.storage.proxies.record_references module swh.storage.proxies.retry module swh.storage.proxies.tenacious module swh.storage.proxies.validate module swh.storage.backfill module swh.storage.cli module swh.storage.common module swh.storage.exc module swh.storage.fixer module swh.storage.in_memory module swh.storage.interface module swh.storage.metrics module swh.storage.migrate_extrinsic_metadata module swh.storage.objstorage module swh.storage.pytest_plugin module swh.storage.replay module swh.storage.utils module swh.storage.writer module Database schema Cassandra migrations Storage replayer Command-line interface swh.vault Getting started Vault API Reference swh.vault package swh.vault.api package swh.vault.api.client module swh.vault.api.serializers module swh.vault.api.server module swh.vault.cookers package swh.vault.cookers.base module swh.vault.cookers.directory module swh.vault.cookers.git_bare module swh.vault.cookers.revision_flat module swh.vault.cookers.revision_gitfast module swh.vault.cookers.utils module swh.vault.backend module swh.vault.cache module swh.vault.cli module swh.vault.cooking_tasks module swh.vault.exc module swh.vault.in_memory_backend module swh.vault.interface module swh.vault.to_disk module Command-line interface swh.web Developers Information swh-web API URLs URI scheme for swh-web Browse application URI scheme for SoftWare Hash IDentifiers (SWHIDs) Miscellaneous URLs swh.web package swh.web.add_forge_now package swh.web.add_forge_now.admin_views module swh.web.add_forge_now.api_views module swh.web.add_forge_now.apps module swh.web.add_forge_now.models module swh.web.add_forge_now.signal_receivers module swh.web.add_forge_now.urls module swh.web.add_forge_now.utils module swh.web.add_forge_now.views module swh.web.admin package swh.web.admin.apps module swh.web.admin.urls module swh.web.alter package swh.web.alter.templatetags package swh.web.alter.apps module swh.web.alter.emails module swh.web.alter.forms module swh.web.alter.models module swh.web.alter.urls module swh.web.alter.utils module swh.web.alter.views module swh.web.api package swh.web.api.views package swh.web.api.apidoc module swh.web.api.apiresponse module swh.web.api.apiurls module swh.web.api.parsers module swh.web.api.renderers module swh.web.api.serializers module swh.web.api.throttling module swh.web.api.urls module swh.web.api.utils module swh.web.archive_coverage package swh.web.archive_coverage.urls module swh.web.archive_coverage.views module swh.web.auth package swh.web.auth.apps module swh.web.auth.models module swh.web.auth.urls module swh.web.auth.utils module swh.web.auth.views module swh.web.badges package swh.web.badges.urls module swh.web.banners package swh.web.banners.urls module swh.web.banners.views module swh.web.browse package swh.web.browse.views package swh.web.browse.browseurls module swh.web.browse.identifiers module swh.web.browse.snapshot_context module swh.web.browse.urls module swh.web.browse.utils module swh.web.client package swh.web.client.cli module swh.web.client.client module swh.web.deposit package swh.web.deposit.urls module swh.web.inbound_email package swh.web.inbound_email.management package swh.web.inbound_email.apps module swh.web.inbound_email.handle_message module swh.web.inbound_email.signals module swh.web.inbound_email.urls module swh.web.inbound_email.utils module swh.web.inbound_email.views module swh.web.jslicenses package swh.web.jslicenses.urls module swh.web.mailmap package swh.web.mailmap.management package swh.web.mailmap.apps module swh.web.mailmap.models module swh.web.mailmap.urls module swh.web.mailmap.views module swh.web.metrics package swh.web.metrics.prometheus module swh.web.metrics.urls module swh.web.metrics.views module swh.web.provenance package swh.web.provenance.api_views module swh.web.provenance.apps module swh.web.provenance.urls module swh.web.save_bulk package swh.web.save_bulk.api_views module swh.web.save_bulk.apps module swh.web.save_bulk.models module swh.web.save_bulk.urls module swh.web.save_bulk.views module swh.web.save_code_now package swh.web.save_code_now.management package swh.web.save_code_now.admin_views module swh.web.save_code_now.api_views module swh.web.save_code_now.apps module swh.web.save_code_now.models module swh.web.save_code_now.origin_save module swh.web.save_code_now.origin_visit_webhook module swh.web.save_code_now.urls module swh.web.save_code_now.views module swh.web.save_origin_webhooks package swh.web.save_origin_webhooks.bitbucket module swh.web.save_origin_webhooks.generic_receiver module swh.web.save_origin_webhooks.gitea module swh.web.save_origin_webhooks.github module swh.web.save_origin_webhooks.gitlab module swh.web.save_origin_webhooks.sourceforge module swh.web.save_origin_webhooks.urls module swh.web.utils package swh.web.utils.management package swh.web.utils.archive module swh.web.utils.citation module swh.web.utils.converters module swh.web.utils.exc module swh.web.utils.highlightjs module swh.web.utils.identifiers module swh.web.utils.middlewares module swh.web.utils.origin_visits module swh.web.utils.query module swh.web.utils.swh_templatetags module swh.web.utils.typing module swh.web.utils.url_path_converters module swh.web.utils.urlsindex module swh.web.vault package swh.web.vault.api_views module swh.web.vault.urls module swh.web.webapp package swh.web.webapp.urls module swh.web.config module swh.web.gunicorn_config module swh.web.manage module swh.web.urls module swh.web.client swh.webhooks swh.webhooks package swh.webhooks.cli module swh.webhooks.interface module swh.webhooks.journal_client module swh.webhooks.svix_retry module swh.webhooks.utils module Development API reference Software Heritage - Data model Data model Data model # Note The text below is adapted from §7 of the article Software Heritage: Why and How to Preserve Software Source Code (in proceedings of iPRES 2017 , 14th International Conference on Digital Preservation, by Roberto Di Cosmo and Stefano Zacchiroli), which also provides a more general description of Software Heritage for the digital preservation research community. In any archival project the choice of the underlying data model—at the logical level, independently from how data is actually stored on physical media—is paramount. The data model adopted by Software Heritage to represent the information that it collects is centered around the notion of software artifact , described below. It is important to notice that according to our principles, we must store with every software artifact full information on where it has been found (provenance), that is also captured in our data model, so we start by providing some basic information on the nature of this provenance information. Source code hosting places # Currently, Software Heritage uses of a curated list of source code hosting places to crawl. The most common entries we expect to place in such a list are popular collaborative development forges (e.g., GitHub, Bitbucket), package manager repositories that host source package (e.g., CPAN, npm), and FOSS distributions (e.g., Fedora, FreeBSD). But we may of course allow also more niche entries, such as URLs of personal or institutional project collections not hosted on major forges. While currently entirely manual, the curation of such a list might easily be semi-automatic, with entries suggested by fellow archivists and/or concerned users that want to notify Software Heritage of the need of archiving specific pieces of endangered source code. This approach is entirely compatible with Web-wide crawling approaches: crawlers capable of detecting the presence of source code might enrich the list. In both cases the list will remain curated, with (semi-automated) review processes that will need to pass before a hosting place starts to be used. Software artifacts # Once the hosting places are known, they will need to be periodically looked at in order to add to the archive missing software artifacts. Which software artifacts will be found there? In general, each software distribution mechanism hosts multiple releases of a given software at any given time. For VCS (Version Control Systems), this is the natural behaviour; for software packages, while a single version of a package is just a snapshot of the corresponding software product, one can often retrieve both current and past versions of the package from its distribution site. By reviewing and generalizing existing VCS and source package formats, we have identified the following recurrent artifacts as commonly found at source code hosting places. They form the basic ingredients of the Software Heritage archive. As the terminology varies quite a bit from technology to technology, we provide below both the canonical name used in Software Heritage and popular synonyms. contents (AKA “blobs”) the raw content of (source code) files as a sequence of bytes, without file names or any other metadata. File contents are often recurrent, e.g., across different versions of the same software, different directories of the same project, or different projects all together. directories a list of named directory entries, each of which pointing to other artifacts, usually file contents or sub-directories. Directory entries are also associated to some metadata stored as permission bits. revisions (AKA “commits”) software development within a specific project is essentially a time-indexed series of copies of a single “root” directory that contains the entire project source code. Software evolves when a developer modifies the content of one or more files in that directory and record their changes. Each recorded copy of the root directory is known as a “revision”. It points to a fully-determined directory and is equipped with arbitrary metadata. Some of those are added manually by the developer (e.g., commit message), others are automatically synthesized (timestamps, preceding commit(s), etc). releases (AKA “tags”) some revisions are more equals than others and get selected by developers as denoting important project milestones known as “releases”. Each release points to the last commit in project history corresponding to the release and carries metadata: release name and version, release message, cryptographic signatures, etc. Additionally, the following crawling-related information are stored as provenance information in the Software Heritage archive: origins code “hosting places” as previously described are usually large platforms that host several unrelated software projects. For software provenance purposes it is important to be more specific than that. Software origins are fine grained references to where source code artifacts archived by Software Heritage have been retrieved from. They take the form of (type, url) pairs, where url is a canonical URL (e.g., the address at which one can git clone a repository or download a source tarball) and type the kind of software origin (e.g., git, svn, or dsc for Debian source packages). snapshots any kind of software origin offers multiple pointers to the “current” state of a development project. In the case of VCS this is reflected by branches (e.g., master, development, but also so called feature branches dedicated to extending the software in a specific direction); in the case of package distributions by notions such as suites that correspond to different maturity levels of individual packages (e.g., stable, development, etc.). A “snapshot” of a given software origin records all entry points found there and where each of them was pointing at the time. For example, a snapshot object might track the commit where the master branch was pointing to at any given time, as well as the most recent release of a given package in the stable suite of a FOSS distribution. visits links together software origins with snapshots. Every time an origin is consulted a new visit object is created, recording when (according to Software Heritage clock) the visit happened and the full snapshot of the state of the software origin at the time. Note This model currently records visits as a single point in time. However, the actual visit process is not instantaneous. Loaders can record successive changes to the state of the visit, as their work progresses, as updates to the visit object. Data structure # Software Heritage archive as a Merkle DAG, augmented with crawling information (click to zoom). # With all the bits of what we want to archive in place, the next question is how to organize them, i.e., which logical data structure to adopt for their storage. A key observation for this decision is that source code artifacts are massively duplicated. This is so for several reasons: code hosting diaspora (i.e., project development moving to the most recent/cool collaborative development technology over time); copy/paste (AKA “vendoring”) of parts or entire external FOSS software components into other software products; large overlap between revisions of the same project: usually only a very small amount of files/directories are modified by a single commit; emergence of DVCS (distributed version control systems), which natively work by replicating entire repository copies around. GitHub-style pull requests are the pinnacle of this, as they result in creating an additional repository copy at each change done by a new developer; migration from one VCS to another—e.g., migrations from Subversion to Git, which are really popular these days—resulting in additional copies, but in a different distribution format, of the very same development histories. These trends seem to be neither stopping nor slowing down, and it is reasonable to expect that they will be even more prominent in the future, due to the decreasing costs of storage and bandwidth. For this reason we argue that any sustainable storage layout for archiving source code in the very long term should support deduplication, allowing to pay for the cost of storing source code artifacts that are encountered more than once only once. For storage efficiency, deduplication should be supported for all the software artifacts we have discussed, namely: file contents, directories, revisions, releases, snapshots. Realizing that principle, the Software Heritage archive is conceptually a single (big) Merkle Direct Acyclic Graph (DAG) , as depicted in Figure Software Heritage Merkle DAG . In such a graph each of the artifacts we have described—from file contents up to entire snapshots—correspond to a node. Edges between nodes emerge naturally: directory entries point to other directories or file contents; revisions point to directories and previous revisions, releases point to revisions, snapshots point to revisions and releases. Additionally, each node contains all metadata that are specific to the node itself rather than to pointed nodes; e.g., commit messages, timestamps, or file names. Note that the structure is really a DAG, and not a tree, due to the fact that the line of revisions nodes might be forked and merged back. In a Merkle structure each node is identified by an intrinsic identifier computed as a cryptographic hash of the node content. In the case of Software Heritage identifiers are computed taking into account both node-specific metadata and the identifiers of child nodes. Consider the revision node in the picture whose identifier starts with c7640e08d.. . it points to a directory (identifier starting with 45f0c078.. ), which has also been archived. That directory contains a full copy, at a specific point in time, of a software component—in the example the Hello World software component available on our forge. The revision node also points to the preceding revision node ( 43ef7dcd.. ) in the project development history. Finally, the node contains revision-specific metadata, such as the author and committer of the given change, its timestamps, and the message entered by the author at commit time. The identifier of the revision node itself ( c7640e08d.. ) is computed as a cryptographic hash of a (canonical representation of) all the information shown in figure. A change in any of them—metadata and/or pointed nodes—would result in an entirely different node identifier. All other types of nodes in the Software Heritage archive behave similarly. The Software Heritage archive inherits useful properties from the underlying Merkle structure. In particular, deduplication is built-in. Any software artifacts encountered in the wild gets added to the archive only if a corresponding node with a matching intrinsic identifier is not already available in the graph—file content, commits, entire directories or project snapshots are all deduplicated incurring storage costs only once. Furthermore, as a side effect of this data model choice, the entire development history of all the source code archived in Software Heritage—which ambitions to match all published source code in the world—is available as a unified whole, making emergent structures such as code reuse across different projects or software origins, readily available. Further reinforcing the Software Heritage use cases, this object could become a veritable “map of the stars” of our entire software commons. Extended data model # In addition to the artifacts detailed above used to represent original software artifacts, the Software Heritage archive stores information about these artifacts. extid a relationship between an original identifier of an artifact, in its native/upstream environment, and a core SWHID <persistent-identifiers> , which is specific to Software Heritage. As such, it includes: the external identifier, stored as bytes whose format is opaque to the data model a type (a simple name and a version), to identify the type of relationship the “target”, which is a core SWHID An extid may also include a “payload”, which is arbitrary data about the relationship. For example, an extid might link a directory to the cryptographic hash of the tarball that originally contained it. In this case, the payload could include data useful for reconstructing the original tarball from the directory. The payload data is stored separately. An extid refers to it by its sha1_git hash. raw extrinsic metadata an opaque bytestring, along with its format (a simple name), an identifier of the object the metadata is about and in which context (similar to a qualified SWHID <persistent-identifiers> ), and provenance information (the authority who provided it, the fetcher tool used to get it, and the data it was discovered at). It provides both a way to store information about an artifact contributed by external entities, after the artifact was created, and an escape hatch to store metadata that would not otherwise fit in the data model. previous Software Heritage - Data model next SoftWare Heritage persistent IDentifiers (SWHIDs) On this page Source code hosting places Software artifacts Data structure Extended data model Edit This Page Show Source so the DOM is not blocked --> © Copyright 2015-2025 The Software Heritage developers. Created using Sphinx 7.4.7. Built with the PyData Sphinx Theme 0.16.1. | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#as_pointer_underscore | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/stratsys-strategic-planning/#main-content | Stratsys platform for compliance and efficiency | LinkedIn Skip to main content LinkedIn Stratsys in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Stratsys platform for compliance and efficiency Strategic Planning Software by Stratsys See who's skilled in this Add as skill Learn more Report this product About Stratsys offers a SaaS platform that streamlines compliance in business-critical areas such as sustainability, GRC and governance for medium to large organizations in the Nordics. Unlike other compliance tools, Stratsys takes it a step further to move organizations from reporting to action and effectively allocate responsibilities internally. For many organizations, coordination and lack of structure is a challenge, which can lead to the whole business not working towards the same goal. With Stratsys, you can easily solve these problems by bringing your work together in one place. From sustainability, risk management, quality management and much more. This product is intended for Sustainability Manager Chief Information Security Officer Head of Sustainability Sustainability Specialist Information Technology Security Specialist Information Technology Security Manager Risk Manager Chief Technology Officer Media Products media viewer No more previous content Stratsys platform Compliance made smart Samla arbetet kring regulatoriska krav i en plattform Tips på hur organisationer kan hantera de ökade regulatoriska kraven No more next content Featured customers of Stratsys platform for compliance and efficiency Stena AB Maritime 21,445 followers Vectura Real Estate 6,487 followers ALEKTUM GROUP Financial Services 6,083 followers Elenia Electric Power Transmission, Control, and Distribution 7,310 followers Avanza Bank Financial Services 88,349 followers Aleris Hospitals and Health Care 17,509 followers Svenska kraftnät Utilities 55,492 followers Vattenfall Utilities 325,018 followers MAX Burgers Restaurants 16,961 followers Länsförsäkringar Insurance 86,859 followers Bostads AB Mimer Real Estate 3,889 followers Domstolsverket Courts of Law 12,337 followers Stockholms stad Government Administration 112,744 followers Region Stockholm Government Administration 61,413 followers Pensionsmyndigheten Government Administration 18,947 followers Region Gävleborg Government Administration 10,577 followers Returpack / Pantamera Wholesale Recyclable Materials 2,262 followers Peab Construction 122,975 followers Trafikverket Government Administration 123,777 followers Göteborgs Stad Government Administration 72,231 followers JM Construction 56,642 followers Show more Show less Similar products Focus Focus Strategic Planning Software Aha! Roadmaps Aha! Roadmaps Strategic Planning Software DIGITAL PRODUCTS DIGITAL PRODUCTS Strategic Planning Software Cascade Cascade Strategic Planning Software WorkBoard WorkBoard Strategic Planning Software Dataport Consulting Dataport Consulting Strategic Planning Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/dataport-a%C3%B6r-dataportai/ | data[port]ai | LinkedIn Skip to main content LinkedIn Dataport AöR in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in data[port]ai Data Science & Machine Learning Platforms by Dataport AöR See who's skilled in this Add as skill Learn more Report this product About data[port]ai ist Ihr Wissens- und Lösungshub für Daten, KI-Technologien und sicheren Betrieb. Sie erhalten Zugang zu leistungsstarken KI-Werkzeugen wie großen Sprachmodellen (LLM), Chatbots sowie automatischer Sprach-, Bild- und Texterkennung. Ihre Vorteile mit Dataport: modernste Infrastruktur, höchste Datensicherheit, Souveränität und eine starke Trägergemeinschaft. Auf einen Blick: ✅ KI-Lösungen ✅ Plattformleistungen ✅ Beratung This product is intended for Machine Learning Specialist Data Scientist Artificial Intelligence Consultant Artificial Intelligence Engineer Artificial Intelligence Specialist Product Manager DevOps Engineer Media Products media viewer No more previous content data[port]ai Aus Daten Chancen machen No more next content Similar products Amazon SageMaker Amazon SageMaker Data Science & Machine Learning Platforms The Databricks Data Intelligence Platform The Databricks Data Intelligence Platform Data Science & Machine Learning Platforms ZAIDYN ZAIDYN Data Science & Machine Learning Platforms Dataiku Dataiku Data Science & Machine Learning Platforms Datalore Datalore Data Science & Machine Learning Platforms DataRobot DataRobot Data Science & Machine Learning Platforms Sign in to see more Show more Show less Dataport AöR products Dataport Consulting Dataport Consulting Strategic Planning Software dDataBox dDataBox Managed File Transfer (MFT) Software dMessenger dMessenger Enterprise Messaging Software dProjectTracking dProjectTracking Project Management Software dWebService dWebService Web Hosting dWorkflow dWorkflow Workflow Management Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/company/adobemarketoengage?trk=products_details_guest_organization_image | Adobe Marketo | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join now Adobe Marketo Software Development San Jose, California 178,692 followers Adobe Marketo Engage orchestrates unforgettable experiences at every step of the B2B buying journey Follow View all 676 employees Report this company About us Adobe Marketo Engage offers the leading Engagement Platform that empowers marketers to build brand value, grow revenue, and prove impact. Consistently recognized as the industry’s innovation pioneer, Adobe Marketo Engage is the trusted platform for thousands of CMOs thanks to its scalability, reliability, and openness. To learn more about the Adobe Marketo Engage platform, LaunchPoint® partner ecosystem, and the vast community that is the Marketing Nation®, visit www.marketo.com. Website http://www.marketo.com/ External link for Adobe Marketo Industry Software Development Company size 1,001-5,000 employees Headquarters San Jose, California Type Privately Held Founded 2006 Specialties lead management, lead nurturing, marketing automation, demand generation, revenue performance management, social marketing, engagement marketing, and lead management Products Adobe Marketo Adobe Marketo Marketing Automation Software End-to-end engagement for modern demand marketing. Deliver exceptional experiences across every stage of the customer journey to drive efficient growth in concert with Sales. Locations Primary 345 Park Ave San Jose, California 95110, US Get directions Cairn House South County Business Park Dublin 18, IE Get directions Level 12 50 Pitt Street Sydney, NSW 2000, AU Get directions 3340 Peachtree Rd NE 720 Atlanta, Georgia 30326, US Get directions 1500 SW 1st Ave #300 Portland, Oregan 97201, US Get directions Totseret ha-Arets Street 7 Tel Aviv, Yafo 67891, IL Get directions 6-10-1 Roppongi, Minato-ku Tokyo, Japan 106-6134, JP Get directions 707 17th Street Suite 2200 Denver, Colorado 80202, US Get directions Amadeus House, 27b Floral Street Suite 213-217 London , Covent Garden WC2E 9DP, GB Get directions Ratinger Straße 9 Ground floor, 1st, 2nd, 3rd floor, Andreas Quartier Düsseldorf, North Rhine-Westphalia 40213, DE Get directions 88, Avenue Charles de Gaulle Neuilly-sur-Seine, Ile-de-France 92200, FR Get directions Show more locations Show fewer locations Employees at Adobe Marketo Michael Bagdonas Agha Ahsan Michael Knudsen Adrienne Whitten See all employees Updates Adobe Marketo 178,692 followers 1mo Report this post On MongoDB This content isn’t available here Access this content and more in the LinkedIn app Download the app 9 Like Comment Share Join now to see what you are missing Find people you know at Adobe Marketo Browse recommended jobs for you View all updates, news, and articles Join now Affiliated pages Adobe Software Development San Jose, CA Similar pages Adobe Software Development San Jose, CA HubSpot Software Development Cambridge, Massachusetts Salesforce Software Development San Francisco, California Marketo Marketing Services tehran, tehran Google Software Development Mountain View, CA Oracle IT Services and IT Consulting Austin, Texas Adobe Commerce Technology, Information and Internet San Jose, California Klaviyo Marketing Services Boston, Massachusetts Eloqua Software Development San Francisco, California Outreach Software Development Seattle, Washington Show more similar pages Show fewer similar pages Browse jobs Engineer jobs 555,845 open jobs Developer jobs 258,935 open jobs Manager jobs 1,880,925 open jobs Marketing Manager jobs 106,879 open jobs Marketing Specialist jobs 49,178 open jobs Lead Software Engineer jobs 68,215 open jobs Analyst jobs 694,057 open jobs Account Executive jobs 71,457 open jobs Associate jobs 1,091,945 open jobs Vice President jobs 235,270 open jobs Product Manager jobs 199,941 open jobs Digital Strategist jobs 11,121 open jobs Design Consultant jobs 18,292 open jobs Principal Product Manager jobs 10,879 open jobs Vice President Solutions jobs 4,429 open jobs Designer jobs 65,273 open jobs Salesforce Administrator jobs 7,827 open jobs Senior Software Engineer jobs 78,145 open jobs Product Test Engineer jobs 11,413 open jobs Account Manager jobs 121,519 open jobs Show more jobs like this Show fewer jobs like this More searches More searches Developer jobs Analyst jobs Partner jobs Engineer jobs MBA Intern jobs Cloud Architect jobs Intern jobs Sales Manager jobs Senior Event Marketing Manager jobs Sales Director jobs Sales Account Manager jobs Customer Engagement Manager jobs Lead Software Engineer jobs Co-Founder jobs Technical Lead jobs Channel Sales Manager jobs Director Corporate Strategy jobs Account Manager jobs Debt Collector jobs Partnerships Manager jobs Account Executive jobs Legal Assistant jobs User Researcher jobs Full Stack Engineer jobs Event Specialist jobs Manager jobs Operations Executive jobs Content Writer jobs Claims Handler jobs Marketing Manager jobs User Experience Specialist jobs Handler jobs Product Developer jobs Technology Intern jobs User Experience Designer jobs Senior Manager jobs Chief Executive Officer jobs Marketing Specialist jobs Coordinator jobs Director jobs Business Development Specialist jobs Business Development Manager jobs Marketing Executive jobs Search Engine Optimization Specialist jobs Digital Marketing Specialist jobs Guide jobs Test Associate jobs Sales Specialist jobs Product Specialist jobs Enterprise Sales Executive jobs Software Quality Engineer jobs Freelance Recruiter jobs Customer Success Manager jobs Salesforce Administrator jobs Senior Accounting Manager jobs Python Developer jobs Marketing Operations Manager jobs Business Account Executive jobs Recruiter jobs Advisory Consultant jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Adobe Marketo Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#as_underscore | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://www.linkedin.com/login?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fposts%2Fhacker-combat-cybersecurity-community_cybersecurity-dataleak-instagram-activity-7416708698489675777-IiGE&fromSignIn=true&trk=public_post_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://huggingface.co/datasets/openmed-community/MedReason-Stenographic | openmed-community/MedReason-Stenographic · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: openmed-community / MedReason-Stenographic like 22 Follow OpenMed Community 107 Tasks: Question Answering Text Generation Modalities: Text Formats: parquet optimized-parquet Languages: English Size: 10K - 100K Tags: medical reasoning chain-of-thought stenographic-reasoning Synthetic Libraries: Datasets pandas Polars + 1 License: apache-2.0 Dataset card Data Studio Files Files and versions xet Community 1 → ∴"},"answer":{"kind":"string","value":"D. Urea breath test"},"thinking":{"kind":"string","value":"The user is asking a medical question about the most sensitive test for H. pylori (Helicobacter pylori). This is a knowledge/retrieval question with multiple choice options.\n\nLet me analyze:\n- H. pylori is a bacterium that causes stomach ulcers and gastritis\n- The options are:\n A. Fecal antigen test - detects H. pylori antigens in stool\n B. Biopsy urease test - invasive, done during endoscopy, detects urease enzyme\n C. Serological test - detects antibodies in blood\n D. Urea breath test - patient drinks urea, if H. pylori is present, it breaks down urea and releases CO2 that can be measured\n\nFrom medical knowledge:\n- Urea breath test is considered the most sensitive and specific non-invasive test\n- Sensitivity of urea breath test: ~95-98%\n- Fecal antigen test: ~90-95% sensitive\n- Biopsy urease test: ~90-95% sensitive but invasive\n- Serological test: ~80-90% sensitive but can't distinguish past from current infection\n\nThe urea breath test is widely considered the most sensitive test for detecting active H. pylori infection.\n\nI need to format this according to the protocol:\n- This is a knowledge retrieval task\n- I should use the RAG schema\n- Include reasoning trace\n- Final answer\n\nLet me construct the reasoning trace following the symbolic lexicon."},"id_in_dataset":{"kind":"number","value":7134,"string":"7,134"}}},{"rowIdx":1,"cells":{"query":{"kind":"string","value":"Typhoid investigation of choice in 1st week"},"reasoning":{"kind":"string","value":"Identify(Pathogen:S. typhi) ● → Timeline(Week1:Bacteremia, Week2:Gallbladder, Week3:Urine) ● → Sensitivity(Blood:40-80%) ◐ → Sensitivity(Stool:Low Week1) ◐ → Sensitivity(Urine:Low Week1) ◐ → Widal(Antibodies:Not developed Week1) ⚠ → → BloodCulture(Gold Standard Week1) ● → ∴"},"answer":{"kind":"string","value":"A. Blood culture"},"thinking":{"kind":"string","value":"This is a medical microbiology question about typhoid fever diagnosis. Let me think through this carefully.\n\nTyphoid fever is caused by Salmonella typhi. The question asks about the investigation of choice during the 1st week of illness.\n\nKey points about typhoid diagnosis timing:\n- 1st week: Blood culture is the best (sensitivity 40-80%) because bacteremia occurs early\n- 2nd week: Stool culture becomes more positive (gallbladder colonization)\n- 3rd week: Urine culture may be positive\n- Widal test: Detects antibodies, rises after 1st week, not useful in 1st week\n\nThe Widal test is not reliable in the 1st week because:\n- Antibodies haven't had time to develop\n- False positives from previous infections or vaccinations\n- Not specific\n\nBlood culture in 1st week:\n- Salmonella typhi is present in blood during bacteremic phase\n- Highest yield in first week (40-80% sensitivity)\n- Gold standard for definitive diagnosis\n\nStool culture:\n- More positive in 2nd-3rd week when bacteria colonize gallbladder\n- Lower sensitivity in 1st week\n\nUrine culture:\n- Usually positive in 3rd week\n- Not useful in 1st week\n\nThe answer should be A. Blood culture.\n\nNow I need to format this according to the Stenographic Reasoning Protocol."},"id_in_dataset":{"kind":"number","value":7138,"string":"7,138"}}},{"rowIdx":2,"cells":{"query":{"kind":"string","value":"Urogenital Diaphragm is made up of the following, except:\nA. Deep transverse Perineus\nB. Perinial membrane\nC. Colle's fascia\nD. Sphincter Urethrae"},"reasoning":{"kind":"string","value":"Parse(Query) ● → Classify(Type:Anatomy) ● → Constraint(Identify Components of Urogenital Diaphragm) ※ → DeepTransversePerineus ● → PerinealMembrane ● → SphincterUrethrae ● → CollesFascia ● → DistractorAnalysis(C not part) ⚠ → → ∴"},"answer":{"kind":"string","value":"C. Colle's fascia"},"thinking":{"kind":"string","value":"We need to answer a multiple choice anatomy question: \"Urogenital Diaphragm is made up of the following, except:\" Options: A. Deep transverse Perineus, B. Perinial membrane, C. Colle's fascia, D. Sphincter Urethrae.\n\nWe need to choose which is NOT part of the urogenital diaphragm.\n\nWe need to consider anatomy: The urogenital diaphragm (also called the perineal membrane) is a thin sheet of fascia that stretches across the pubic arch, forming the floor of the perineum. It includes the deep transverse perineal muscle, the sphincter urethrae muscle (external urethral sphincter). The perineal membrane (the inferior fascia of the urogenital diaphragm) is part of it. Colles' fascia is the superficial perineal fascia (of the superficial perineal pouch), not part of the urogenital diaphragm. So the answer is C: Colle's fascia.\n\nThus the answer: C.\n\nBut we need to output JSON with fields: query, reasoning, answer. Use the reasoning format per the guidelines: Stenographic Reasoning Trace with symbols and abbreviations.\n\nWe need to follow the format: The reasoning should be a continuous sequence of symbols and abbreviations.\n\nWe need to include phases: Phase 0 meta-analysis and query decomposition, etc.\n\nBut we must follow the Stenographic Protocol.\n\nThus:\n\n{\n \"query\": \"Urogenital Diaphragm is made up of the following, except: ...\",\n \"reasoning\": \"Parse(Query) ● → Classify(Type:Anatomy) ● → Constraint(Identify Components of Urogenital Diaphragm) ※ → DeepTransversePerineus ● → PerinealMembrane ● → SphincterUrethrae ● → CollesFascia ● → DistractorAnalysis(C not part) ⚠ → \\u003cH≈0.2\\u003e → ∴\",\n \"answer\": \"C\"\n}\n\nBut ensure the reasoning is a single string with no spaces except within parentheses? It should be continuous but we can have spaces for readability? The spec says \"continuous sequence of symbols and abbreviations following the architecture below. No prose or conjunctions.\" The examples show spaces between symbols but not within tokens like \"DeepTransversePerineus\". That is okay. We should not have any natural language.\n\nThus output:\n\n{\n \"query\": \"Urogenital Diaphragm is made up of the following, except:\\nA. Deep transverse Perineus\\nB. Perinial membrane\\nC. Colle's fascia\\nD. Sphincter Urethrae\",\n \"reasoning\": \"Parse(Query) ● → Classify(Type:Anatomy) ● → Constraint(Identify Components of Urogenital Diaphragm) ※ → DeepTransversePerineus ● → PerinealMembrane ● → SphincterUrethrae ● → CollesFascia ● → DistractorAnalysis(C not part) ⚠ → \\u003cH≈0.2\\u003e → ∴\",\n \"answer\": \"C\"\n}\n\nCheck for compliance:\n\n- JSON output: yes.\n- reasoning: continuous sequence of symbols and abbreviations. Contains \"Parse(Query) ● → Classify(Type:Anatomy) ● → Constraint(Identify Components of Urogenital Diaphragm) ※ → DeepTransversePerineus ● → PerinealMembrane ● → SphincterUrethrae ● → CollesFascia ● → DistractorAnalysis(C not part) ⚠ → → ∴\". That seems okay.\n\nWe have no prose. Good.\n\nThus final answer."},"id_in_dataset":{"kind":"number","value":7131,"string":"7,131"}}},{"rowIdx":3,"cells":{"query":{"kind":"string","value":"The technique for accurate quantification of gene expression is"},"reasoning":{"kind":"string","value":"Detect(Task:RAG) ● → Domain(MolecularBiology) ● → QueryParse(QuantifyGeneExpression) ● → OptionEval: NorthernBlot(Qualitative) ⚠ → OptionEval: PCR(NonQuantitative) ⚠ → OptionEval: RT_PCR(SemiQuant) ◐ → OptionEval: RealTimeRT_PCR(Quantitative) ● → Insight(!) → ∴"},"answer":{"kind":"string","value":"C. Real-Time Reverse Transcriptase PCR"},"thinking":{"kind":"string","value":"We have a user asking a multiple-choice question: \"The technique for accurate quantification of gene expression is\". Options: A. Nohern blot (likely \"Northern blot\"), B. PCR, C. Real-Time Reverse Transcriptase PCR, D. Reverse Transcriptase PCR.\n\nWe need to answer: The technique for accurate quantification of gene expression is Real-Time Reverse Transcriptase PCR (also called qRT-PCR). The answer is C.\n\nBut the instruction: We are to output a JSON with fields query, reasoning, answer. Reasoning must follow the Stenographic Reasoning Trace format.\n\nWe need to parse the question, identify domain: gene expression quantification, technique.\n\nWe need to consider that the answer is \"Real-Time Reverse Transcriptase PCR\". Use appropriate symbols.\n\nWe need to output JSON. Ensure no extra text.\n\nWe need to embed reasoning trace as per protocol.\n\nWe must also include entropy markers.\n\nThe reasoning trace: Detect (Task: Knowledge) → Domain (Molecular Biology) → Fact Extraction (Gene expression quantification) → Evaluate options: Northern blot (qualitative, low sensitivity) → PCR (non-quantitative) → Reverse Transcriptase PCR (semi-quantitative) → Real-Time RT-PCR (quantitative) → Insight (!) → Convergence ∴.\n\nMake sure we use symbols. Include \"※\" for constraint/trap detection (maybe detection of distractors). Use \"?\" for missing info.\n\nUse \"●\" for ground truth. Use \"◐\" for inference. Use \"○\" for speculation.\n\nLet's design:\n\n\"Detect(Task:RAG) ● → Domain(MolecularBiology) ● → QueryParse(QuantifyGeneExpression) ● → OptionEval: NorthernBlot(Qualitative) ⚠ → OptionEval: PCR(NonQuantitative) ⚠ → OptionEval: RT-PCR(SemiQuant) ◐ → OptionEval: RealTimeRT-PCR(Quantitative) ● → Insight(!) → ∴\"\n\nAdd entropy marker: maybe.\n\nThus answer: \"C. Real-Time Reverse Transcriptase PCR\".\n\nMake sure to output JSON object.\n\nPotential pitfalls: The answer must be just the answer (maybe the letter and description). The question is multiple-choice; answer likely letter C or full text. The instruction says answer field is final answer.\n\nThus answer: \"C. Real-Time Reverse Transcriptase PCR\". Or \"Real-Time Reverse Transcriptase PCR\". The question: \"The technique for accurate quantification of gene expression is\". So answer: Real-Time Reverse Transcriptase PCR. Probably include the letter: C.\n\nThus final JSON.\n\nNow produce final answer."},"id_in_dataset":{"kind":"number","value":7144,"string":"7,144"}}},{"rowIdx":4,"cells":{"query":{"kind":"string","value":"Child with Type I Diabetes. What is the advised time for fundus examinations from the time of diagnosis?"},"reasoning":{"kind":"string","value":"Parse(Query)●→Classify(Type:MedicalRAG)●→Constraint(AnswerOption)※→GuidelineSearch●→Source(ADA2023)●→Rule(5yrspostdiagnosis)●→ChildAgeConsideration(≥10y)◐→DistractorEval(OptionB:2y,OptionC:10y,OptionD:diagnosis)⚠→Refine↺→Insight(!)→ →∴"},"answer":{"kind":"string","value":"After 5 years"},"thinking":{"kind":"string","value":"We need to answer a medical question: \"Child with Type I Diabetes. What is the advised time for fundus examinations from the time of diagnosis?\" Options: A. After 5 years, B. After 2 years, C. After 10 years, D. At the time of diagnosis.\n\nWe need to answer with the correct answer.\n\nWe must output JSON with fields: query, reasoning, answer.\n\nThe reasoning must be a symbolic trace following the given protocol. It must be a continuous sequence of symbols and abbreviations, no prose or conjunctions.\n\nWe need to incorporate the knowledge: For type I diabetes mellitus, screening for diabetic retinopathy (fundus exam) is recommended starting 3-5 years after diagnosis (for type 1) and then annually. In children, guidelines may differ: American Diabetes Association (ADA) recommends that children with type 1 diabetes have an initial dilated and comprehensive eye exam within 5 years after onset of diabetes (i.e., after 5 years). However, some guidelines say at age 10 or after 3-5 years. The question: \"Child with Type I Diabetes. What is the advised time for fundus examinations from the time of diagnosis?\" Options: A. After 5 years, B. After 2 years, C. After 10 years, D. At the time of diagnosis. The correct answer likely \"After 5 years\".\n\nBut we must verify guidelines: The ADA 2023 guidelines for diabetic retinopathy screening: For type 1 diabetes, initiate screening 5 years after diagnosis, then annually. For type 2 diabetes, at diagnosis. For children with type 1, screening begins at age 10 or 5 years after diagnosis, whichever earlier. However the question likely expects answer A (after 5 years). Option B after 2 years is not typical for type 1. Option C after 10 years is too late. Option D at diagnosis is for type 2.\n\nThus answer: A. After 5 years.\n\nNow need to produce reasoning trace.\n\nWe need to include symbols like \"→\", \"↺\", \"∴\", \"●\", \"◐\", \"○\", \"!\", \"※\", \"?\", \"⚠\", \" \".\n\nThe reasoning must be a continuous sequence of symbols and abbreviations, not prose. Should reflect phases: Phase 0 meta-analysis, Phase 1 context retrieval, Phase 2 mechanism analysis, Phase 3 synthesis.\n\nWe can produce something like:\n\n\"Detect(Task:RAG) ● → Domain(DiabeticRetinopathyScreening) ● → GuidelineSource(ADA2023) ● → TypeIDM(TypeI) ● → InitiationRule(5yearspostdiagnosis) ● → ChildAgeConsideration(≥10y) ◐ → DistractorAnalysis(OptionB:2y, OptionC:10y, OptionD:diagnosis) ⚠ → EliminateFalseOptions ↺ → Insight(!) → → ∴\"\n\nBut we must ensure we include \"→\" between steps, \"↺\" for refinement loops (if needed), \"∴\" for convergence. The format must be a single string with no prose. Ensure we use abbreviations and symbols.\n\nCheck the instructions: The \"reasoning\" string must be a continuous sequence of symbols and abbreviations following the architecture: Phase 0, Phase 1, Phase 2, Phase 3.\n\nThus we need to include something like:\n\n\"Parse(Query) ● → Classify(Type:MedicalRAG) ● → Constraint(AnswerOption) ※ → GuidelineSearch ● → Source(ADA2023) ● → Rule(5yrspostdiagnosis) ● → ChildScreeningCriteria(≥10y) ◐ → DistractorEval(OptionB,OptionC,OptionD) ⚠ → Refine ↺ → Insight(!) → → ∴\"\n\nBut we must include \"↺\" for self-correction loops if needed. Possibly we can incorporate a loop: \"DistractorEval → Refine ↺\". That may be enough.\n\nThe final answer: \"After 5 years\" or \"A\". The answer field should contain the final answer. The question: \"Child with Type I Diabetes. What is the advised time for fundus examinations from the time of diagnosis?\" So answer: \"After 5 years\". Or \"A\". The answer field likely expects the text of the answer choice. Usually in such tasks, answer field contains the letter or the answer text. The instruction says \"Final Answer\". It could be the answer text. Let's output \"After 5 years\". Or \"A\". The format: \"answer\": \"After 5 years\". Or \"answer\": \"A\". The safe approach: Provide the answer text as the choice. The prompt includes answer choices, so answer should be the correct choice letter. But the instruction says \"answer\": \"[Final Answer]\" - not specified if letter or phrase. I'd output the text of the correct answer: \"After 5 years\". That matches the choice.\n\nThus final JSON:\n\n{\n \"query\": \"Child with Type I Diabetes. What is the advised time for fundus examinations from the time of diagnosis?\",\n \"reasoning\": \"Parse(Query) ● → Classify(Type:MedicalRAG) ● → Constraint(AnswerOption) ※ → GuidelineSearch ● → Source(ADA2023) ● → Rule(5yrspostdiagnosis) ● → ChildAgeConsideration(≥10y) ◐ → DistractorEval(OptionB:2y, OptionC:10y, OptionD:diagnosis) ⚠ → Refine ↺ → Insight(!) → → ∴\",\n \"answer\": \"After 5 years\"\n}\n\nCheck reasoning string: Should be continuous. No spaces? The spec says continuous sequence of symbols and abbreviations. However spaces may be allowed. But they said \"continuous sequence of symbols and abbreviations\". Typically they want no prose. They didn't forbid spaces. But we can keep spaces for readability. However to be safe, we can remove spaces between steps, but that might make it unreadable. The spec says \"continuous sequence of symbols and abbreviations\". That implies something like \"Parse(Query)●→Classify(Type:MedicalRAG)●→Constraint(AnswerOption)※→GuidelineSearch●→Source(ADA2023)●→Rule(5yrspostdiagnosis)●→ChildAgeConsideration(≥10y)◐→DistractorEval(OptionB:2y,OptionC:10y,OptionD:diagnosis)⚠→Refine↺→Insight(!)→ →∴\". That is continuous.\n\nWe need to ensure we include \"↺\" for refinement loop. We have \"Refine↺\". That is fine.\n\nWe need to include \"※\" for constraints. We have \"Constraint(AnswerOption)※\". Good.\n\nWe need to include \"⚠\" for risk. We have \"⚠\". Good.\n\nWe need to include \"!\" for insight. We have \"(!)\". Good.\n\nWe need to include \" \" for entropy marker. Good.\n\nWe need to include \"∴\". Good.\n\nThus final answer is ready.\n\nNow produce JSON."},"id_in_dataset":{"kind":"number","value":7133,"string":"7,133"}}},{"rowIdx":5,"cells":{"query":{"kind":"string","value":"Perforation of stomach is more common due to ingestion of -"},"reasoning":{"kind":"string","value":"Identify intent (medical MCQ) ● → Domain (toxicology/corrosion) ● → Key facts: strong mineral acids cause corrosive injury; among them sulphuric acid is most commonly implicated in gastric perforation due to deep coagulative necrosis ● → Compare options: nitric acid (less common), hydrochloric acid (stomach already resistant), carbolic acid (phenol, causes CNS and renal toxicity but less frequent perforation) ● → Conclusion ◐ → → ∴"},"answer":{"kind":"string","value":"B. Sulphuric acid"},"thinking":{"kind":"string","value":"The user asks: \"Perforation of stomach is more common due to ingestion of - Answer Choices: A. Nitric acid B. Sulphuric acid C. Hydrochloric acid D. Carbolic acid\"\n\nThis is a medical question. They ask: Perforation of stomach is more common due to ingestion of which acid? The answer likely relates to corrosive injury. Ingestion of strong acids can cause gastric perforation. However, which acid is more commonly associated with stomach perforation? In clinical practice, ingestion of strong mineral acids like sulphuric acid and nitric acid cause severe corrosive injury. Hydrochloric acid is also a strong acid but less likely to cause perforation compared to carbolic acid (phenol) which is a potent protein coagulant? Let's think.\n\nThe question: \"Perforation of stomach is more common due to ingestion of -\" Means which acid ingestion leads to gastric perforation. The choices: nitric acid, sulphuric acid, hydrochloric acid, carbolic acid (phenol). The answer may be \"Sulphuric acid\". In medical toxicology, ingestion of strong mineral acids like sulphuric acid cause coagulative necrosis, leading to perforation. However, also nitric acid is a strong oxidizing acid and may cause perforation. Carbolic acid (phenol) is also corrosive and can cause necrosis but may cause less perforation? Let's recall the typical board exam question: \"Perforation of stomach is more common due to ingestion of - A. Nitric acid B. Sulphuric acid C. Hydrochloric acid D. Carbolic acid\". I think the answer is \"Sulphuric acid\". Actually, let's analyze.\n\nThe pathophysiology: Ingestion of strong mineral acids (like sulphuric, nitric, hydrochloric) leads to coagulation necrosis, which may protect deeper layers because coagulated proteins form a barrier, but if the acid is strong, it may penetrate deeper. Carbolic acid (phenol) is a protein coagulant causing coagulation necrosis as well. However, phenol is also a strong corrosive that can cause severe burns. But which is more common for gastric perforation? I recall a question that says \"Perforation of stomach is more common after ingestion of - a. Nitric acid b. Sulphuric acid c. Hydrochloric acid d. Carbolic acid\" and answer is \"Sulphuric acid\". But I'm not entirely sure. Let's search memory: In forensic medicine and toxicology, ingestion of strong acids leads to necrosis. The severity depends on concentration and type. Among mineral acids, sulphuric acid is the most common cause of corrosive injury in India and many places. Also, it's widely available in industrial contexts. The question likely expects sulphuric acid as answer. However, I'm aware that \"carbolic acid\" (phenol) may cause deep necrosis and is more likely to cause perforation? Let's examine.\n\nLet's recall specifics: Carbolic acid is a phenol, a weak acid but highly protein coagulant. It is used as a disinfectant. Ingestion leads to central nervous system depression, metabolic acidosis, and also severe burns of oral mucosa and esophagus. However, the stomach is less affected due to less exposure? The main pathology is coagulative necrosis of the upper GI tract. Carbolic acid also causes hepatic and renal toxicity.\n\nMineral acids: Hydrochloric acid is present in gastric juice normally; ingestion may cause severe injury but the stomach may be less vulnerable because it's acid-resistant? However, ingestion of concentrated HCl can cause severe injury. However, the question asks which ingestion is more common for perforation.\n\nIf we consider the relative frequency of perforation after ingestion of corrosive acids, sulphuric acid is the most common cause of perforation of stomach. Because it is a strong dehydrating and corrosive acid, and is commonly used in industry. Nitric acid is also corrosive but less common. Hydrochloric acid is common but less likely to cause perforation because the stomach is already exposed to HCl. Carbolic acid may cause necrosis but may not lead to perforation as commonly.\n\nThus answer: B. Sulphuric acid.\n\nBut let's verify with some sources. I recall a forensic medicine textbook: \"Corrosive poisoning - The commonest acids causing perforation of the stomach are mineral acids, especially sulphuric acid.\" Also, \"Ingestion of sulphuric acid leads to deep necrosis and perforation of stomach.\" So answer B.\n\nThus final answer: B. Sulphuric acid.\n\nThe user expects answer only? They gave multiple choice. So answer: B.\n\nThus I will output the answer.\n\nBut let's consider if there is any nuance: The question says \"Perforation of stomach is more common due to ingestion of -\". So answer: Sulphuric acid.\n\nThus output: B.\n\nWe should respond with the answer choice. Could also explain briefly. But the system says we must use the reasoning trace format. Wait, the system is set up for a particular role: \"You are a Reasoning Refiner.\" But the user is asking a direct question, not a refinement of reasoning. So I think we should answer directly with the answer choice, maybe with brief reasoning. However, the system is set to output a JSON with fields: query, reasoning, answer. But that is for the previous \"Stenographic Reasoning Trace\"? The user hasn't provided a reasoning trace. So we are not required to output JSON. The user just asks a direct MCQ. So answer normally.\n\nThus final answer: B. Sulphuric acid.\n\nBut we might want to add some explanation: Because sulphuric acid is a strong mineral acid causing deep necrosis and is most commonly associated with gastric perforation.\n\nThus answer: B."},"id_in_dataset":{"kind":"number","value":7141,"string":"7,141"}}},{"rowIdx":6,"cells":{"query":{"kind":"string","value":"Brown tumour is seen in"},"reasoning":{"kind":"string","value":"Detect(Task:RAG) ● → Domain(Endocrine) ● → ExtractFacts(BrownTumour) ● → PremiseCheck(Misconception) ⚠ → DistractorAnalysis(HypoPTH|HypoThyroid|HypeThyroid) ※ → → EliminateFalseOptions → Insight(!) → ∴"},"answer":{"kind":"string","value":"A. Hyperparathyroidism"},"thinking":{"kind":"string","value":"We have a user query: \"Brown tumour is seen in\n\nAnswer Choices:\nA. Hyperparathyroidism\nB. Hypoparathyroidism\nC. Hypothyroidism\nD. Hypehyroidism\"\n\nThe user is likely asking: In which condition is a brown tumor seen? The answer is hyperparathyroidism, specifically primary hyperparathyroidism, leads to brown tumors (osteitis fibrosa cystica). So the answer is A.\n\nThe question is a simple medical MCQ. According to the protocol, we must produce a JSON with fields: query, reasoning, answer. Reasoning must follow the \"Stenographic Reasoning Trace\" format using symbols, abbreviations, and no prose.\n\nWe must adhere to the Grand Unified Reasoning Protocol. The domain is knowledge retrieval. Use the appropriate schema. The \"reasoning\" string must be a continuous sequence of symbols and abbreviations following the architecture. Must include entropy markers and appropriate symbols.\n\nWe need to parse the query, detect it's a RAG-type question (knowledge retrieval). The answer is \"Hyperparathyroidism\".\n\nWe must use symbols: → for flow, ↺ for refinement loops, ∴ for conclusion, ● for ground truth, ◐ for inference, ! for insight, ※ for constraint, ⚠ for risk, etc.\n\nThe reasoning trace: Detect(Task:RAG) → Domain(Endocrine) ● → ExtractFacts(Brown tumour) ● → Association(Hyperparathyroidism) ● → DistractorAnalysis(Hypoparathyroidism, Hypothyroidism, Hypehyroidism) ⚠ → EliminateFalseOptions → Insight(!) → ∴\n\nWe need to include an entropy marker somewhere, maybe after extraction. Use for knowledge retrieval.\n\nWe need to ensure we use the correct field names: query, reasoning, answer. Provide a JSON object.\n\nWe must not have comments. The JSON must be valid. The reasoning must be a string.\n\nMake sure no natural language. Use abbreviations like \"RAG\", \"Endo\", \"BrownTum\", \"HyperPTH\". Use symbols.\n\nPotential reasoning string: \"Detect(Task:RAG) ● → Domain(Endo) ● → Fact(BrownTum) ● → Assoc(HyperPTH) ● → Distractor(HypoPTH|HypoThyroid|HypeThyroid) ⚠ → EliminateFalseOptions → Insight(!) → → ∴\"\n\nBut we need to ensure the order: The protocol says Phase 0: Meta-Analysis & Query Decomposition: (Intent Classification ● → Trap Detection ※ → Language ID ↺ → Token Parse → Ambiguity Check ? → Translation ↺). Phase 1: Context Retrieval & Domain Overview: (Constraint Extraction ※ → Domain Context ● → Key Facts ● → Knowledge Gaps ⚠ → Seed Alignment → \\ ). Phase 2: Mechanism Analysis & Comparative Assessment: (Mechanism Mapping → Variable Definition ● → Model Equations ● → Comparative Criteria ※ → Inference ◐ → Risk Assessment ⚠ → Self‑Correction ↺ → \\ ). Phase 3: Synthesis & Convergence: (Integration of Evidence → Cross‑Check ↺ → Identification of Insights \\! → Convergence ∴ → Final Answer).\n\nThus we need to incorporate these phases. However, the schema for Knowledge & Retrieval says:\n\n{\n \"query\": \"[Canonical Question]\",\n \"reasoning\": \"Detect(Task:RAG) ● → Domain(Era/Topic) ● → ExtractFacts(Sources) ● → PremiseCheck(Misconception) ⚠ → DistractorAnalysis ※ → \\ → EliminateFalseOptions → Insight(!) → ∴\",\n \"answer\": \"[Final Fact/Selection]\"\n}\n\nThus we can follow that. The domain is \"Endocrine\". The facts: Brown tumour is a bone lesion seen in hyperparathyroidism. The distractor analysis: Hypoparathyroidism, hypothyroidism, hyperthyroidism (typo \"Hypehyroidism\").\n\nThus reasoning: \"Detect(Task:RAG) ● → Domain(Endocrine) ● → ExtractFacts(BrownTumour) ● → PremiseCheck(Misconception) ⚠ → DistractorAnalysis(HypoPTH|HypoThyroid|HypeThyroid) ※ → → EliminateFalseOptions → Insight(!) → ∴\"\n\nWe need to include the answer: \"Hyperparathyroidism\". Or \"A. Hyperparathyroidism\". The answer field can be \"A. Hyperparathyroidism\" or just \"Hyperparathyroidism\". The question asks \"Brown tumour is seen in\". So answer: \"Hyperparathyroidism\". We'll include \"A. Hyperparathyroidism\". Or just \"A\". The protocol says final answer should be the answer.\n\nThus answer: \"A. Hyperparathyroidism\".\n\nNow produce JSON.\n\nCheck for any potential pitfalls: The reasoning string must be a continuous sequence of symbols and abbreviations. No spaces? The examples show spaces between symbols? They show \"Detect(Task:RAG) ● → Domain(Era/Topic) ● → ExtractFacts(Sources) ● → PremiseCheck(Misconception) ⚠ → DistractorAnalysis ※ → \\ → EliminateFalseOptions → Insight(!) → ∴\". There are spaces between tokens. That's okay. We need to ensure we include the entropy marker with the proper syntax: \\ (escaped as ). In JSON we need to escape backslashes? Actually, the marker is a literal string: \" \". In the example they wrote \\ but that's for representation. In actual JSON we can include directly. But we need to escape the backslash? The example shows a backslash before . However, the spec says \"Insert before major cognitive shifts\". So we need to include it. We'll include . Ensure no extra spaces inside the marker.\n\nThus reasoning: \"Detect(Task:RAG) ● → Domain(Endocrine) ● → ExtractFacts(BrownTumour) ● → PremiseCheck(Misconception) ⚠ → DistractorAnalysis(HypoPTH|HypoThyroid|HypeThyroid) ※ → → EliminateFalseOptions → Insight(!) → ∴\"\n\nCheck for any missing symbol: The \"DistractorAnalysis\" uses parentheses and includes the distractors separated by vertical bars. That's fine.\n\nNow produce JSON.\n\nWe need to ensure JSON is valid: double quotes around keys and string values. No trailing commas.\n\nThus:\n\n{\n \"query\": \"Brown tumour is seen in\",\n \"reasoning\": \"Detect(Task:RAG) ● → Domain(Endocrine) ● → ExtractFacts(BrownTumour) ● → PremiseCheck(Misconception) ⚠ → DistractorAnalysis(HypoPTH|HypoThyroid|HypeThyroid) ※ → → EliminateFalseOptions → Insight(!) → ∴\",\n \"answer\": \"A. Hyperparathyroidism\"\n}\n\nCheck for any missing punctuation: The answer field is a string. It's fine.\n\nNow output."},"id_in_dataset":{"kind":"number","value":7143,"string":"7,143"}}},{"rowIdx":7,"cells":{"query":{"kind":"string","value":"Cytosolic cytochrome C plays an important function in -"},"reasoning":{"kind":"string","value":"Parse(Query) ● → Classify(Type:Fact) ● → Domain(Cell Biology) ● → Fact(CytochromeC cytosolic role) ● → Apoptosis trigger ● → Electron transport chain (mitochondrial) ↺ → DistractorAnalysis ※ → EliminateOptions(B, C, D) → Insight(!) → ∴"},"answer":{"kind":"string","value":"A. Apoptosis"},"thinking":{"kind":"string","value":"The user asks: \"Cytosolic cytochrome C plays an impoant function in -\" (typo: \"impoant\" likely \"important\").\n\nAnswer choices:\nA. Apoptosis\nB. Cell necrosis\nC. Electron transport chain\nD. Cell division\n\nWe need to answer correctly. Cytosolic cytochrome c is involved in apoptosis. The mitochondrial cytochrome c is part of electron transport chain, but when released into cytosol, it triggers apoptosis via apoptosome formation. So answer: A. Apoptosis.\n\nThus produce JSON with query, reasoning, answer.\n\nWe must follow the reasoning format: a trace of symbols. Use SYNTH style: parse, classify, etc. The reasoning string must be a continuous sequence of symbols and abbreviations, no prose. Use appropriate symbols: →, ↺, ∴, ●, ◐, ○, !, ※, ?, ⚠, .\n\nWe'll produce something like:\n\n\"Parse(Query) ● → Classify(Type:Fact) ● → Domain(Cell Biology) ● → Fact(CytochromeC cytosolic role) ● → Apoptosis trigger ● → Electron transport chain (mitochondrial) ↺ → DistractorAnalysis ※ → Eliminate(B,C,D) → Insight(!) → ∴\"\n\nAdd .\n\nMake sure JSON is valid.\n\nThus answer: Apoptosis.\n\nWe'll output JSON."},"id_in_dataset":{"kind":"number","value":7149,"string":"7,149"}}},{"rowIdx":8,"cells":{"query":{"kind":"string","value":"Ligation of the common hepatic aery will compromise blood flow in"},"reasoning":{"kind":"string","value":"Intent(Anatomy) ● → TrapDetect(LeftGastric) ※ → LangID(EN) ● → TokenParse → AmbiguityCheck(?) → NoAmbiguity ● → ConstraintExtract(BranchList) ※ → DomainContext(CeliacTrunk) ● → KeyFacts(CH→ProperHepatic+GDA) ● → GDA→RGEA ● → ProperHepatic→RGA ● → SGA→Splenic ● → SeedAlign(Choices) → → MechanismMap(CH→Downstream) → Variables(RGA,RGEA,…) ● → ComparativeCriteria(DownstreamOnly) ◐ → Infer(D only) ! → SelfCorrect ↺ → → IntegrateEvidence → CrossCheck ↺ → Insight(!) → ∴"},"answer":{"kind":"string","value":"D. Right gastric and right gastroepiploic aery"},"thinking":{"kind":"string","value":"We need to answer a question: \"Ligation of the common hepatic artery will compromise blood flow in ...\" and answer choices are:\n\nA. Right and Left gastric artery\nB. Right gastric and short gastric arteries\nC. Right gastroepiploic and short gastric arteries\nD. Right gastric and right gastroepiploic artery\n\nWe need to determine which arteries are compromised if the common hepatic artery is ligated.\n\nFirst, need to understand the anatomy of the hepatic arterial supply. The common hepatic artery is a branch of the celiac trunk. It gives off the proper hepatic artery after the gastroduodenal artery branches off. The proper hepatic artery continues to the liver. The gastroduodenal artery gives off the right gastroepiploic artery (or right gastro-omental artery) and the superior pancreaticoduodenal arteries. The left gastric artery is a direct branch of the celiac trunk (or sometimes the common hepatic artery). The right gastric artery is usually a branch of the proper hepatic artery, sometimes from the common hepatic or from the gastroduodenal. The short gastric arteries are branches of the splenic artery.\n\nThus, ligating the common hepatic artery will affect its branches: proper hepatic artery, gastroduodenal artery (which gives right gastroepiploic), right gastric artery (if branch from common hepatic), possibly left gastric? Actually left gastric is directly from celiac trunk, not from common hepatic. So left gastric would be preserved.\n\nThus compromise would be to the proper hepatic artery (which supplies liver), the right gastric artery (if branch from common hepatic), and the right gastroepiploic artery (branch from gastroduodenal). But the question says \"Ligation of the common hepatic artery will compromise blood flow in ...\" The answer likely includes the right gastric artery and the right gastroepiploic artery.\n\nCheck answer choices:\n\nA. Right and Left gastric artery (includes left gastric, not correct)\nB. Right gastric and short gastric arteries (short gastric not from common hepatic)\nC. Right gastroepiploic and short gastric arteries (short gastric not from common hepatic)\nD. Right gastric and right gastroepiploic artery (both are from common hepatic via its branches)\n\nThus answer D.\n\nBut we must produce JSON with reasoning trace.\n\nWe need to follow the stenographic reasoning protocol: Use symbols, abbreviations, no prose. The reasoning must be a continuous string of symbols and abbreviations.\n\nWe need to output JSON with fields: query, reasoning, answer.\n\nThe query is the question: \"Ligation of the common hepatic aery will compromise blood flow in\" (typo \"aery\" but we keep as is). The answer choices are given.\n\nWe need to produce reasoning trace that includes parse, classification, constraint extraction, knowledge retrieval, mechanism analysis, inference, conclusion.\n\nWe need to include entropy markers where appropriate. For anatomical knowledge, we can set entropy around 0.5.\n\nWe need to include symbols: →, ↺, ∴, ●, ◐, ○, !, ※, ?, ⚠, .\n\nWe need to ensure no natural language except abbreviations and symbols. The reasoning must be a continuous sequence of symbols and abbreviations. Use standard abbreviations: CH (common hepatic), HA (hepatic artery), GDA (gastroduodenal), RGA (right gastric), LGA (left gastric), RGEA (right gastroepiploic), SGA (short gastric), CT (celiac trunk), etc.\n\nWe need to include steps: Intent classification, trap detection, etc.\n\nWe need to include the answer: \"D. Right gastric and right gastroepiploic artery\". Or maybe just the letter D? The answer field should contain the final answer. The answer can be \"D\". But better to include the full text as answer choice. The instruction says \"Answer Choices: ...\" and the answer should be the correct choice. So answer field should be \"D. Right gastric and right gastroepiploic artery\". That is fine.\n\nNow produce reasoning trace.\n\nWe need to follow the universal reasoning architecture: Phase 0: Meta-Analysis & Query Decomposition, Phase 1: Context Retrieval & Domain Overview, Phase 2: Mechanism Analysis & Comparative Assessment, Phase 3: Synthesis & Convergence.\n\nWe need to embed the appropriate symbols.\n\nWe need to include after major cognitive shift.\n\nWe need to include risk warnings if needed. But we can include ⚠ for risk of misinterpretation.\n\nWe need to include ! for insight.\n\nWe need to include ↺ for refinement loops.\n\nWe need to include ? for ambiguity.\n\nWe need to include ※ for constraints/traps.\n\nWe need to include ◐ for inference.\n\nWe need to include ● for ground truth.\n\nWe need to include ○ for speculation.\n\nWe need to include ∴ for conclusion.\n\nWe need to include → for flow.\n\nNow we need to produce a reasoning string.\n\nLet's outline:\n\nPhase 0: Meta-Analysis & Query Decomposition:\n\n- Detect intent: Identify which arteries are compromised by CH ligation. (Task: Anatomy, Clinical knowledge)\n- Trap detection: Ensure not to confuse left gastric (branch of celiac) with right gastric.\n- Language ID: English.\n- Token parse: \"Ligation of the common hepatic artery will compromise blood flow in\".\n- Ambiguity check: None.\n- Translation: None.\n\nThus: Intent(Anatomy) ● → TrapDetect(LeftGastric) ※ → LangID(EN) ● → TokenParse → AmbiguityCheck(?) → NoAmbiguity ●\n\nPhase 1: Context Retrieval & Domain Overview:\n\n- Constraint extraction: Need to know arterial branches of common hepatic artery.\n- Domain context: Celiac trunk branches: left gastric, splenic, common hepatic. Common hepatic branches: proper hepatic, gastroduodenal (which gives right gastroepiploic), right gastric (branch from proper hepatic or common hepatic). Short gastric from splenic.\n- Key facts: CH → proper hepatic + GDA. GDA → RGEA + pancreaticoduodenal. Proper hepatic → RGA + hepatic.\n- Knowledge gaps: None.\n- Seed alignment: Align with answer choices.\n\nThus: ConstraintExtract(BranchList) ※ → DomainContext(CeliacTrunk) ● → KeyFacts(CH→ProperHepatic+GDA) ● → GDA→RGEA ● → ProperHepatic→RGA ● → SGA→Splenic ● → SeedAlign(Choices) → \n\nPhase 2: Mechanism Analysis & Comparative Assessment:\n\n- Mechanism mapping: Ligation of CH stops flow to all downstream branches: proper hepatic, GDA, RGA, RGEA.\n- Variable definition: CH (common hepatic), RGA (right gastric), RGEA (right gastroepiploic), LGA (left gastric), SGA (short gastric).\n- Model equations: None needed.\n- Comparative criteria: Which of the answer options includes only branches downstream of CH.\n- Inference: Options A includes LGA (not downstream). Option B includes SGA (not downstream). Option C includes SGA (not downstream). Option D includes RGA + RGEA (both downstream). Therefore D is correct.\n\n- Risk assessment: No risk of hallucination.\n\n- Self-correction: Verify that RGA is indeed branch of proper hepatic or common hepatic; yes. So D correct.\n\nThus: MechanismMap(CH→Downstream) → Variables(RGA,RGEA,…) ● → ComparativeCriteria(DownstreamOnly) ◐ → Infer(D only) ! → SelfCorrect ↺ → \n\nPhase 3: Synthesis & Convergence:\n\n- Integration of evidence: All downstream branches identified.\n- Cross-check: None contradictory.\n- Identification of insights: D matches downstream branches.\n- Convergence: ∴\n\nThus: IntegrateEvidence → CrossCheck ↺ → Insight(!) → ∴\n\nNow final answer: D. Right gastric and right gastroepiploic artery.\n\nThus produce JSON:\n\n{\n \"query\": \"Ligation of the common hepatic aery will compromise blood flow in\",\n \"reasoning\": \"Intent(Anatomy) ● → TrapDetect(LeftGastric) ※ → LangID(EN) ● → TokenParse → AmbiguityCheck(?) → NoAmbiguity ● → ConstraintExtract(BranchList) ※ → DomainContext(CeliacTrunk) ● → KeyFacts(CH→ProperHepatic+GDA) ● → GDA→RGEA ● → ProperHepatic→RGA ● → SGA→Splenic ● → SeedAlign(Choices) → → MechanismMap(CH→Downstream) → Variables(RGA,RGEA,…) ● → ComparativeCriteria(DownstreamOnly) ◐ → Infer(D only) ! → SelfCorrect ↺ → → IntegrateEvidence → CrossCheck ↺ → Insight(!) → ∴\",\n \"answer\": \"D. Right gastric and right gastroepiploic artery\"\n}\n\nMake sure reasoning string is continuous, no line breaks, no extra spaces? It can have spaces for readability but it's okay. The protocol says continuous sequence of symbols and abbreviations. It can have spaces between tokens, but it's okay.\n\nNow produce final answer."},"id_in_dataset":{"kind":"number","value":7137,"string":"7,137"}}},{"rowIdx":9,"cells":{"query":{"kind":"string","value":"The arrow marked structure is which part of corpus callosum: Answer Choices: A. Rostrum B. Genu C. Body D. Splenium"},"reasoning":{"kind":"string","value":"Detect(Task:RAG) ● → Domain(Neuroanatomy) ● → ExtractFacts(CorpusCallosumParts) ● → VisualizeParts(Rostrum:most anterior inferior; Genu:anterior bend; Body:midportion; Splenium:posterior bulge) ● → MapArrowToPosteriorBulge ◐ → IdentifySplenium ◐ → → ∴"},"answer":{"kind":"string","value":"D. Splenium"},"thinking":{"kind":"string","value":"The user asks: \"The arrow marked structure is which part of corpus callosum: Answer Choices: A. Rostrum B. Genu C. Body D. Splenium\". Likely they have an image with an arrow pointing to a part of corpus callosum, and they want to know which region is indicated. The corpus callosum has four main parts: rostrum (most anterior inferior part), genu (anterior bend), body (trunk), splenium (posterior bulge). If the arrow points to the posterior thick part, it's splenium. If pointing to the anterior bend, it's genu. If pointing to the rostrum (most anterior inferior part), it's rostrum. If pointing to the middle part, it's body.\n\nGiven typical anatomy question, the arrow likely points to the splenium. However, I need to be sure. The question is ambiguous without the image. But typical test question: \"The arrow marked structure is which part of corpus callosum?\" Usually they show a sagittal brain MRI with an arrow pointing to the posterior end (splenium). That is a common exam question: identify splenium. The answer likely D. Splenium.\n\nThus answer: D. Splenium.\n\nBut the prompt is not about solving, but about producing reasoning trace. According to the system instructions: output JSON with query, reasoning (stenographic), answer. So we need to produce a JSON object with fields: query, reasoning, answer.\n\nWe need to follow the SYNTH-style reasoning: using symbols and abbreviations.\n\nGiven the nature of this question (anatomical identification), we can classify as Knowledge & Retrieval (RAG). Domain: Neuroanatomy. The reasoning must be compressed.\n\nWe'll produce:\n\n{\n \"query\": \"The arrow marked structure is which part of corpus callosum: Answer Choices: A. Rostrum B. Genu C. Body D. Splenium\",\n \"reasoning\": \"Detect(Task:RAG) ● → Domain(Neuroanatomy) ● → ExtractFacts(CorpusCallosumParts) ● → VisualizeParts(Rostrum:most anterior inferior; Genu:anterior bend; Body:midportion; Splenium:posterior bulge) ● → MapArrowToPosteriorBulge ◐ → IdentifySplenium ◐ → \\u003cH≈0.6\\u003e → ∴\",\n \"answer\": \"D. Splenium\"\n}\n\nMake sure to follow JSON format with proper escapes. Use \\u003c for .\n\nThus final answer."},"id_in_dataset":{"kind":"number","value":7148,"string":"7,148"}}},{"rowIdx":10,"cells":{"query":{"kind":"string","value":"Trigeminal nerve has how many nucleus? Answer Choices: A. 2 B. 3 C. 4 D. 5"},"reasoning":{"kind":"string","value":"Detect(Task:RAG) ● → Domain(Neuroanatomy) ● → ExtractFacts(TrigeminalNuclei) ● → PremiseCheck(Number) ⚠ → DistractorAnalysis(Choices) ※ → Insight(!: 4 nuclei: principal sensory, spinal, mesencephalic, motor) → → ∴"},"answer":{"kind":"string","value":"C"},"thinking":{"kind":"string","value":"The user asks: \"Trigeminal nerve has how many nucleus? Answer Choices: A. 2 B. 3 C. 4 D. 5\"\n\nWe need to answer with the correct answer.\n\nThe trigeminal nerve (cranial nerve V) has four nuclei: three sensory nuclei (principal sensory nucleus, spinal trigeminal nucleus, mesencephalic nucleus) and one motor nucleus (motor nucleus of trigeminal). Actually the standard teaching is that the trigeminal nerve has four nucle | 2026-01-13T09:29:17 |
https://git-scm.com/book/fa/v2/%d8%b4%d8%b1%d9%88%d8%b9-%d8%a8%d9%87-%da%a9%d8%a7%d8%b1-getting-started-%da%af%db%8c%d8%aa-%da%86%db%8c%d8%b3%d8%aa%d8%9f-What-is-Git | Git - گیت چیست؟ (What is Git) About Trademark Learn Book Cheat Sheet Videos External Links Tools Command Line GUIs Hosting Reference Install Community This book is available in English . Full translation available in azərbaycan dili , български език , Deutsch , Español , فارسی , Français , Ελληνικά , 日本語 , 한국어 , Nederlands , Русский , Slovenščina , Tagalog , Українська , 简体中文 , Partial translations available in Čeština , Македонски , Polski , Српски , Ўзбекча , 繁體中文 , Translations started for Беларуская , Indonesian , Italiano , Bahasa Melayu , Português (Brasil) , Português (Portugal) , Svenska , Türkçe . The source of this book is hosted on GitHub. Patches, suggestions and comments are welcome. Chapters ▾ 1. شروع به کار (getting started) 1.1 درباره ورژن کنترل (About Version Control) 1.2 تاریخچه کوتاهی از گیت (A Short History of Git) 1.3 گیت چیست؟ (What is Git) 1.4 نصب گیت (Installing Git) 1.5 ستاپ اولیه گیت (First-Time Git Setup) 1.6 دریافت کمک (Getting Help) 1.7 خلاصه (summary) 2. مقدمات گیت (git basics chapter) 2.1 گرفتن یک مخزن گیت (Getting a Git Repository) 2.2 ثبت تغییرات در مخزن (Recording Changes to the Repository) 2.3 مشاهده تاریخچه کامیتها (Viewing the Commit History) 2.4 بازگرداندن تغییرات (Undoing Things) 2.5 کار کردن با ریموت ها (Working with Remotes) 2.6 تگ کردن (Tagging) 2.7 نام مستعار گیت (Git Aliases) 2.8 خلاصه (summary) 3. انشعابگیری در گیت (Git Branching) 3.1 شاخهها در یک نگاه (Branches in a Nutshell) 3.2 شاخهبندی و ادغام پایهای (Basic Branching and Merging) 3.3 مدیریت شاخهها (Branch Management) 3.4 روندهای کاری شاخهها (Branching Workflows) 3.5 شاخههای راه دور (Remote Branches) 3.6 بازپایهگذاری (Rebasing) 3.7 خلاصه (Summary) 4. گیت روی سرور (Git on the server) 4.1 پروتکلها (The Protocols) 4.2 راهاندازی گیت روی یک سرور (Getting Git on a Server) 4.3 ایجاد کلید عمومی SSH شما (Generating Your SSH Public Key) 4.4 نصب و راهاندازی سرور (Setting up server) 4.5 سرویسدهنده گیت (Git Daemon) 4.6 HTTP هوشمند (Smart HTTP) 4.7 گیتوب (GitWeb) 4.8 گیتلب (GitLab) 4.9 گزینههای میزبانی شخص ثالث (Third Party Hosted Options) 4.10 خلاصه (Summary) 5. گیت توزیعشده (Distributed git) 5.1 جریانهای کاری توزیعشده (Distributed Workflows) 5.2 مشارکت در یک پروژه (Contributing to a Project) 5.3 نگهداری یک پروژه (Maintaining a Project) 5.4 خلاصه (Summary) 6. گیت هاب (GitHub) 6.1 راهاندازی و پیکربندی حساب کاربری (Account Setup and Configuration) 6.2 مشارکت در یک پروژه (Contributing to a Project) 6.3 نگهداری یک پروژه (Maintaining a Project) 6.4 مدیریت یک سازمان (Managing an organization) 6.5 اسکریپتنویسی در گیتهاب (Scripting GitHub) 6.6 خلاصه (Summary) 7. ابزارهای گیت (Git Tools) 7.1 انتخاب بازبینی (Revision Selection) 7.2 مرحلهبندی تعاملی (Interactive Staging) 7.3 ذخیره موقت و پاکسازی (Stashing and Cleaning) 7.4 امضای کارهای شما (Signing Your Work) 7.5 جستجو (Searching) 7.6 بازنویسی تاریخچه (Rewriting History) 7.7 بازنشانی به زبان ساده (Reset Demystified) 7.8 ادغام پیشرفته (Advanced Merging) 7.9 بازاستفاده خودکار از حل تضادها (Rerere) 7.10 اشکالزدایی با گیت (Debugging with Git) 7.11 سابماژول ها (Submodules) 7.12 بستهبندی (Bundling) 7.13 جایگزینی (Replace) 7.14 ذخیرهسازی اطلاعات ورود (Credential Storage) 7.15 خلاصه (Summary) 8. سفارشیسازی Git (Customizing Git) 8.1 پیکربندی گیت (Git Configuration) 8.2 ویژگیهای گیت (Git Attributes) 8.3 هوکهای گیت (Git Hooks) 8.4 یک نمونه سیاست اعمال شده توسط گیت (An Example Git-Enforced Policy) 8.5 خلاصه (Summary) 9. گیت و سیستمهای دیگر (Git and Other Systems) 9.1 گیت بهعنوان کلاینت (Git as a Client) 9.2 مهاجرت به گیت (Migrating to Git) 9.3 خلاصه (Summary) 10. مباحث درونی گیت (Git Internals) 10.1 ابزارها و دستورات سطح پایین (Plumbing and Porcelain) 10.2 اشیا گیت (Git Objects) 10.3 مراجع گیت (Git References) 10.4 فایلهای بسته (Packfiles) 10.5 نگاشت (The Refspec) 10.6 پروتکلهای انتقال (Transfer Protocols) 10.7 نگهداری و بازیابی دادهها (Maintenance and Data Recovery) 10.8 متغیرهای محیطی (Environment Variables) 10.9 خلاصه (Summary) A1. پیوست A: گیت در محیطهای دیگر (Git in Other Environments) A1.1 رابط های گرافیکی (Graphical Interfaces) A1.2 گیت در ویژوال استودیو (Git in Visual Studio) A1.3 گیت در Visual Studio Code (Git in Visual Studio Code) A1.4 گیت در IntelliJ / PyCharm / WebStorm / PhpStorm / RubyMine (Git in IntelliJ / PyCharm / WebStorm / PhpStorm / RubyMine) A1.5 گیت در Sublime Text (Git in Sublime Text) A1.6 گیت در بش (Git in Bash) A1.7 گیت در Zsh (Git in Zsh) A1.8 گیت در PowerShell (Git in PowerShell) A1.9 خلاصه (Summary) A2. پیوست B: گنجاندن گیت در برنامههای شما (Embedding Git in your Applications) A2.1 خط فرمان گیت (Command-line Git) A2.2 کتابخانهٔ گیت به زبان سی (Libgit2) A2.3 کتابخانه گیت برای زبان جاوا (JGit) A2.4 کتابخانه گیت برای زبان گو (go-git) A2.5 کتابخانه گیت پایتون (Dulwich) A3. پیوست C: دستورات گیت (Git Commands) A3.1 تنظیم و پیکربندی (Setup and Config) A3.2 گرفتن و ایجاد پروژهها (Getting and Creating Projects) A3.3 نمونهبرداری پایهای (Basic Snapshotting) A3.4 انشعابگیری و ادغام (Branching and Merging) A3.5 بهاشتراکگذاری و بهروزرسانی پروژهها (Sharing and Updating Projects) A3.6 بازرسی و مقایسه (Inspection and Comparison) A3.7 عیبیابی (Debugging) A3.8 اعمال تغییرات به صورت پچ (Patching) A3.9 ایمیل (Email) A3.10 سیستمهای خارجی (External Systems) A3.11 مدیریت (Administration) A3.12 دستورات سطح پایین گیت (Plumbing Commands) 2nd Edition 1.3 شروع به کار (getting started) - گیت چیست؟ (What is Git) گیت چیست؟ (What is Git) پس، گیت به طور خلاصه چیست؟ این بخش مهمی است که باید به خوبی درک شود، زیرا اگر بفهمید گیت چیست و اصول پایهای نحوه کار آن چگونه است، استفاده مؤثر از گیت برای شما احتمالاً بسیار آسانتر خواهد بود. وقتی در حال یادگیری گیت هستید، سعی کنید ذهن خود را از چیزهایی که ممکن است درباره سایر سیستمهای کنترل نسخه مانند CVS، سابورژن یا پروفورس بدانید پاک کنید — این کار به شما کمک میکند تا هنگام استفاده از این ابزار از سردرگمیهای ظریف جلوگیری کنید. اگرچه رابط کاربری گیت تا حدی شبیه به این سیستمهای کنترل نسخه است، گیت اطلاعات را به روشی بسیار متفاوت ذخیره و پردازش میکند و درک این تفاوتها به شما کمک میکند تا هنگام استفاده از آن دچار سردرگمی نشوید. اسنپ شات ها، بدون تغییرات (Snapshots, Not Differences) تفاوت اصلی بین گیت و هر سیستم کنترل نسخهی دیگری (از جمله سابورژن و مشابهها) در نحوهی تفکر گیت درباره دادههایش است. به طور مفهومی، بیشتر سیستمهای دیگر اطلاعات را به صورت فهرستی از تغییرات مبتنی بر فایل ذخیره میکنند. این سیستمهای دیگر (CVS، سابورژن، پروفورس و غیره) اطلاعاتی که ذخیره میکنند را به عنوان مجموعهای از فایلها و تغییراتی که در هر فایل در طول زمان ایجاد شده است، در نظر میگیرند (که معمولاً به آن کنترل نسخه مبتنی بر دلتا گفته میشود). نمودار 4. Storing data as changes to a base version of each file گیت به این شکل به داده ها فکر نمی کند و آن ها را ذخیره نمی کند. در عوض، گیت داده های خود را بیشتر شبیه به مجموعه ای از عکس های یک فایل سیستم مینیاتوری می داند. با گیت، هر بار که حالت پروژه خود را ذخیره می کنید، گیت اساساً تصویری از تمام فایل های شما در آن لحظه می گیرد و یک مرجع به آن عکس را ذخیره می کند. برای کارآمد بودن، اگر فایل ها تغییر نکرده باشند، Git دوباره فایل را ذخیره نمی کند، فقط یک لینک به فایل مشابه قبلی که قبلا ذخیره شده است. گیت درباره داده های خود بیشتر به عنوان یک جریان از عکس های فوری فکر می کند. نمودار 5. Storing data as snapshots of the project over time این یک تمایز مهم بین گیت و تقریبا تمام VCS های دیگر است. این باعث می شود که گیت تقریباً هر جنبه ای از کنترل نسخه را که اکثر سیستم های دیگر از نسل قبلی کپی کرده اند، دوباره در نظر بگیرد. این باعث می شود که گیت بیشتر شبیه به یک فایل سیستم کوچک با برخی از ابزارهای فوق العاده قدرتمند ساخته شده در بالای آن باشد، نه فقط یک VCS. ما برخی از مزایایی را که با فکر کردن به داده های خود به این شکل به دست می آورید، بررسی خواهیم کرد وقتی که شاخه سازی گیت را در انشعابگیری در گیت (Git Branching) پوشش می دهیم. تقریبا همه عملیات ها محلی هستند (Nearly Every Operation Is Local) بیشتر عملیات در گیت فقط به فایل ها و منابع محلی برای کار نیاز دارد — به طور کلی هیچ اطلاعاتی از کامپیوتر دیگری در شبکه شما مورد نیاز نیست. اگر شما به CVCS عادت کرده اید که در آن بیشتر عملیات ها دارای آن تاخیر شبکه هستند، این جنبه از گیت شما را به فکر می اندازد که خدایان سرعت، گیت را با قدرت های غیرمستقیم برکت داده اند. از آنجا که شما تمام تاریخ پروژه را در دیسک محلی خود دارید، بیشتر عملیات تقریباً فوری به نظر می رسند. به عنوان مثال، برای مرور تاریخ پروژه، گیت نیازی به رفتن به سرور ندارد تا تاریخچه را دریافت کند و آن را برای شما نمایش دهد — آن را به سادگی مستقیما از پایگاه داده محلی شما می خواند. این به این معنی است که شما تاریخچه پروژه را تقریباً بلافاصله می بینید. اگر می خواهید تغییرات ایجاد شده بین نسخه فعلی یک فایل و فایل یک ماه پیش را ببینید، گیت می تواند فایل یک ماه پیش را جستجو کند و محاسبه تفاوت محلی را انجام دهد، به جای اینکه از یک سرور از راه دور بخواهد این کار را انجام دهد یا نسخه قدیمی تری از فایل را از سرور از راه دور برای انجام آن به صورت محلی. این همچنین به این معنی است که اگر شما آفلاین یا VPN هستید، کاری که نمی توانید انجام دهید بسیار کمی وجود دارد. اگر شما سوار هواپیما یا قطار شوید و بخواهید کمی کار کنید، می توانید با خوشحالی (به نسخه محلی خود، به یاد داشته باشید؟) تا وقتی که به یک اتصال شبکه برای آپلود برسید. اگر شما به خانه بروید و نتوانید مشتری VPN خود را به درستی کار کنید، هنوز هم می توانید کار کنید. در بسیاری از سیستم های دیگر، انجام این کار غیرممکن یا دردناک است. به عنوان مثال، در Perforce، وقتی به سرور متصل نیستید، نمی توانید کارهای زیادی انجام دهید؛ در Subversion و CVS، می توانید فایل ها را ویرایش کنید، اما نمی توانید تغییرات را در پایگاه داده خود انجام دهید (زیرا پایگاه داده شما آفلاین است). این شاید چیز بزرگی به نظر نرسد، اما ممکن است تعجب کنید که چه تفاوت بزرگی می تواند ایجاد کند. گیت دارای یکپارچگی است (Git Has Integrity) همه چیز در گیت قبل از ذخیره شدن چک سوم می شود و سپس با آن چک سوم ارجاع داده می شود. این بدان معنی است که تغییر محتویات هر فایل یا دایرکتوری بدون اطلاع گیت غیرممکن است. این قابلیت در پایین ترین سطوح در گیت ساخته شده است و جزء فلسفه آن است. شما نمی توانید اطلاعات را در حین انتقال از دست بدهید یا فایل را خراب کنید بدون اینکه گیت بتواند آن را تشخیص دهد. مکانیزمی که گیت برای این چک سوم استفاده می کند، هش SHA-1 نامیده می شود. SHA-1))) این یک رشته 40 کاراکتر است که از کاراکترهای هگزادسیمال (0 ⁇ 9 و a ⁇ f) تشکیل شده و بر اساس محتویات یک فایل یا ساختار دایرکتوری در گیت محاسبه می شود. یک هش SHA-1 چیزی شبیه به این است: 24b9da6552252987aa493b52f8696cd6d3b00373 شما این ارزش های هش را در همه جا در گیت خواهید دید چون از آنها بسیار استفاده می کند. در واقع، گیت همه چیز را در پایگاه داده خود نه با نام فایل بلکه با ارزش هش محتوای آن ذخیره می کند. گیت به طور کلی فقط داده ها را اضافه می کند (Git Generally Only Adds Data) هنگامی که شما در گیت اعمال انجام می دهید، تقریبا همه آنها فقط داده ها را به پایگاه داده گیت اضافه می کنند. سخت است که سیستم کاری را انجام دهد که غیر قابل برگشت نباشد یا به هیچ وجه داده ها را پاک کند. همانند هر VCS، می توانید تغییرات خود را که هنوز ارتکاب نکرده اید، از دست بدهید یا خراب کنید، اما پس از ارتکاب یک عکس فوری به گیت، از دست دادن آن بسیار دشوار است، به خصوص اگر شما به طور منظم پایگاه داده خود را به یک مخزن دیگر منتقل کنید. این باعث می شود استفاده از گیت لذت بخش باشد زیرا ما می دانیم که می توانیم بدون خطر به شدت خراب کردن چیزها آزمایش کنیم. برای نگاهی عمیق تر به نحوه ذخیره داده های گیت و چگونگی بازیابی داده هایی که به نظر می رسد گم شده اند، به بازگرداندن تغییرات (Undoing Things) مراجعه کنید. سه مرحله (The Three States) حالا توجه کنید — این مهم ترین چیزی است که باید در مورد گیت به خاطر بسپارید اگر می خواهید بقیه فرآیند یادگیری شما بدون مشکل پیش برود. گیت سه حالت اصلی دارد که فایل های شما می توانند در آن باشند: modified ، staged ، و committed : اصلاح شده به این معنی است که شما فایل را تغییر داده اید اما هنوز آن را به پایگاه داده خود اختصاص نداده اید. مرحله ای به این معنی است که شما یک فایل اصلاح شده را در نسخه فعلی آن برای رفتن به عکس فوری بعدی خود علامت گذاری کرده اید. تعهد به این معنی است که داده ها به طور ایمن در پایگاه داده محلی شما ذخیره می شوند. این ما را به سه بخش اصلی یک پروژه گیت می رساند: درخت کار، منطقه مرحله بندی، و دایرکتوری گیت. نمودار 6. Working tree, staging area, and Git directory درخت کار یک چک کردن واحد از یک نسخه از پروژه است. این فایل ها از پایگاه داده فشرده شده در دایرکتوری گیت بیرون آورده می شوند و روی دیسک قرار می گیرند تا شما بتوانند از آن ها استفاده کنید یا آن ها را تغییر دهید. منطقه مرحله بندی یک فایل است، که معمولا در دایرکتوری گیت شما قرار دارد، که اطلاعات مربوط به آنچه که در کامیت بعدی شما قرار می گیرد را ذخیره می کند. نام فنی آن در زبان گیت “index” است، اما عبارت “staging area” نیز به خوبی کار می کند. دایرکتوری گیت جایی است که گیت متاداتا و پایگاه داده شی را برای پروژه شما ذخیره می کند. این مهم ترین بخش گیت است، و این چیزی است که کپی می شود زمانی که شما یک مخزن را از یک کامپیوتر دیگر کپی می کنید. روند کار گیت چیزی شبیه به این است: شما فایل ها را در درخت کار خود اصلاح می کنید. شما به طور انتخابی فقط آن تغییرات را که می خواهید بخشی از commit بعدی خود باشید، که فقط آن تغییرات را به منطقه مرحله بندی اضافه می کند. شما یک کامیت انجام می دهید، که فایل ها را همانطور که در منطقه مرحله بندی هستند می گیرد و آن عکس را به طور دائم در دایرکتوری گیت شما ذخیره می کند. اگر یک نسخه خاص از یک فایل در دایرکتوری گیت باشد، تعهد شده محسوب می شود. اگر آن را اصلاح کرده اند و به منطقه مرحله اضافه شد، آن را staged است. و اگر از زمان چک کردن آن تغییر کرده باشد، اما مرحله ای نشده باشد، تعدیل شده است. در مقدمات گیت (git basics chapter) ، شما بیشتر در مورد این حالت ها خواهید آموخت و اینکه چگونه می توانید از آنها استفاده کنید یا بخش مرحله ای را به طور کامل حذف کنید. خط فرمان (Command Line) راههای مختلفی برای استفاده از گیت وجود دارد. ابزارهای اصلی خط فرمان و همچنین چندین رابط کاربری گرافیکی با امکانات متفاوت در دسترساند. در این کتاب، ما گیت را از طریق خط فرمان به کار خواهیم برد. چرا؟ اول اینکه فقط با خط فرمان میتوانید تمام دستورات گیت را اجرا کنید؛ چون اکثر رابطهای گرافیکی برای سادهتر شدن، فقط بخشی از قابلیتهای گیت را پوشش میدهند. اگر بتوانید نسخه خط فرمان را اجرا کنید، احتمالاً کار با نسخه گرافیکی را هم میتوانید یاد بگیرید، اما برعکس آن همیشه ممکن نیست. همچنین، انتخاب کلاینت گرافیکی بیشتر به سلیقه شخصی شما بستگی دارد، اما همه کاربران معمولا خط فرمان را روی سیستم خود دارند و آن را استفاده میکنند. پس انتظار میرود که بتوانید ترمینال را در مک یا Command Prompt / PowerShell را در ویندوز باز کنید. اگر با این موضوع آشنایی ندارید، بهتر است قبل از ادامه کمی دربارهٔ آن تحقیق کنید تا بتوانید مثالها و توضیحات کتاب را بهتر دنبال کنید. prev | next About this site Patches, suggestions, and comments are welcome. Git is a member of Software Freedom Conservancy | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/vonage-communications-apis/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click | Vonage Communications APIs | LinkedIn Skip to main content LinkedIn Vonage in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Vonage Communications APIs Cloud Communications Platforms by Vonage See who's skilled in this Add as skill Learn more Report this product About With Vonage APIs, growing startups and agile enterprises can build best-in-class communications solutions at scale. Our global platform, comprehensive suite of communications channels, and expert support help you move quickly to offer your customers the most helpful experience possible, sooner rather than later. This product is intended for Developer Chief Technology Officer Engineering Manager Director of Product Management Vice President of Product Management Manager Product Management Director of Product Engineering Chief Product Officer Vice President Product Engineering Digital Transformation Officer Media Products media viewer No more previous content Vonage Communications APIs Companies worldwide rely on the Vonage API platform (formerly Nexmo) to add contextual communications to their business-critical applications. Build an education platform to meet today’s e-learning challenges Vonage Communications APIs enable global education technology pioneers in tutoring, e-learning, training and coaching, and more to build programmable video, messaging, and voice into every learning experience. Solve last mile delivery with omnichannel customer communication Logistics companies are using real-time communications powered by Vonage APIs to provide customers with exceptional service and visibility in "last mile" delivery. Communications APIs transform financial services Innovative financial services companies are using communications APIs to transform the customer experience, delighting sometimes tentative customers with real-time authentication, video, voice, and messaging interactions. Healthcare providers innovate patient-doctor interactions with APIs Healthcare organizations around the world are using Vonage's video, authentication, voice, and messaging APIs to optimize complex patient-doctor interactions seamlessly and efficiently. No more next content Featured customers of Vonage Communications APIs PUBG Corporation Computer Games 41,587 followers Revolut Financial Services 1,685,134 followers Varsity Tutors, a Nerdy Company Technology, Information and Internet 201,964 followers Domino's Restaurants 507,168 followers Aramex Transportation, Logistics, Supply Chain and Storage 731,270 followers Remitly Financial Services 78,202 followers ベルフェイス株式会社 IT Services and IT Consulting 396 followers Allstate Insurance 434,818 followers Fisher & Paykel Appliances Appliances, Electrical, and Electronics Manufacturing 43,220 followers Docplanner Technology, Information and Internet 257,408 followers doxy.me Software Development 12,965 followers Show more Show less Similar products Slack Slack Cloud Communications Platforms Tencent Cloud Instant Messaging (IM) Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Avaya Cloud Office Avaya Cloud Office Cloud Communications Platforms MessageBird MessageBird Cloud Communications Platforms CPaaS CPaaS Cloud Communications Platforms Channelize.io: Live Stream Shopping Platform Channelize.io: Live Stream Shopping Platform Cloud Communications Platforms Sign in to see more Show more Show less Vonage products Vonage Contact Center Vonage Contact Center Call Center Software Vonage Unified Communications Vonage Unified Communications Unified Communications as a Service (UCaaS) Platforms LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://support.atlassian.com/confluence-cloud | Confluence Cloud support | Confluence Cloud | Atlassian Support Skip to main content Confluence Support Apps Documentation Knowledge base Resources Contact us Sign in Sign in Atlassian Support Confluence Cloud Data Center Confluence Cloud support Documentation Get help using and administering apps. View documentation Knowledge Base Find troubleshooting articles. View knowledge base Community Find answers, support, and inspiration from other Atlassian users. Visit Atlassian Community System Status Check the health of our cloud apps and services View system status Suggestions and bug reports Find existing feature suggestions and bug reports. View suggestions and bugs Marketplace apps Find features to customize your apps View Marketplace Billing and licensing See FAQs about billing and licensing. View FAQs What's new See the latest and greatest updates and new features for your Atlassian cloud apps and services. View release notes Not finding the help you need? Accessibility Notice at Collection Privacy Policy Terms of Use Security 2026 Atlassian | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Ftencentglobal-tencent-cloud-instant-messaging-im&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#assigning_clones | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#assign_ops | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#arithmetic_side_effects | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fdataport-a%C3%B6r-dwebservice&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/categories/cloud-communications-platforms?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_subtitle-click | Best Cloud Communications Platforms | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Chief Technology Officer (9) Chief Product Officer (6) Chief Information Officer (4) Information Technology Manager (4) Chief Executive Officer (4) See all products Find top products in Cloud Communications Platforms category Software used to enable voice and text messaging features in mobile applications using APIs. - Use application programming interfaces (APIs) to enable cloud-hosted communications - Customize interface for calling, instant messaging, and verifications in applications - Integrate with VoIP services and implement enhanced security features - Use API documentation and guides to explore features and flexibility 96 results Slack Cloud Communications Platforms by Salesforce Slack is your work operating system. Slack is where humans with agents meet data, workflows, and apps to deliver big results, right where people love to work. View product Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms by Tencent Tencent Cloud Instant Messaging (IM) provides globally interconnected chat APIs, multi-platform SDKs, and UIKit components to help you quickly bring messaging capabilities such as one-to-one chat, group chat, chat rooms, and system notifications to your applications and websites. View product Avaya Cloud Office Cloud Communications Platforms by Avaya Avaya Cloud Office is a cloud-based communications system with enterprise grade voice, video, IM/messaging, meetings, conferencing and collaboration. With Avaya Cloud Office you can easily connect all your workers, whether in the office, mobile, or remote to a single system regardless of their location. View product MessageBird Cloud Communications Platforms by Bird APIs, tools, customer support software, and a global connectivity network to elevate business to customer relationships. View product Vonage Communications APIs Cloud Communications Platforms by Vonage With Vonage APIs, growing startups and agile enterprises can build best-in-class communications solutions at scale. Our global platform, comprehensive suite of communications channels, and expert support help you move quickly to offer your customers the most helpful experience possible, sooner rather than later. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights CPaaS Cloud Communications Platforms by Plivo A CPaaS (communications platform as a service) lets developers add real-time communications features such as SMS messaging and voice call to their applications without the hassle of dealing with the global telecom infrastructure. Plivo's SMS API and Voice API and its Premium Communications Network give businesses a way to communicate with their customers anywhere in the world. Cloud-based communications platforms provide a bridge between businesses and telecom carriers, programmatically connecting a business’s devices and applications via application programming interfaces (API) that provide all the code a business needs to incorporate communication functionality into their applications. On the back end, cloud communications platforms connect to telecommunication carriers and operators to route messages and voice calls on behalf of businesses. View product Channelize.io: Live Stream Shopping Platform Cloud Communications Platforms by BigStep Technologies Channelize.io is a Platform-as-a-Service (PaaS) product that is revolutionizing the way businesses (eCommerce Stores & D2C Brands) are selling online. We enable eCommerce Stores & D2C Brands to leverage the power of Live Stream Shopping and Real-time Engagement to Boost Sales and Enhance their Brand Perception by connecting better with their buyers and showcasing and marketing their products in ways that lead to informed, trusted and accelerated purchases by buyers. We make Live Video Shopping better for brands with consistent, beautiful branded experiences across Websites and Apps. There is no doubt that Live Shopping will become the new normal in retail and will go down in history as an evolution of traditional eCommerce. Our platform, therefore, enables brands to achieve the best of both worlds - ROI and Reach, making them a real Winner in the retail space. Our Platform works through 3 primary mechanisms – entertaining consumers, engaging them, and educating them on the brands. View product Telnyx Cloud Communications Platforms by Telnyx Real-time conversational AI with global telephony, infrastructure & full customizability—all in one platform. View product Structured Cabling Cloud Communications Platforms by IES Communications Backed by 40+ years of experience, we design, install, and maintain scalable cabling systems, delivering high-performance connectivity for reliable network infrastructure. View product CXi Switch Cloud Communications Platforms by Ozonetel | oneCXi CXi Switch, a first-of-its-kind internet communication product, powers instant voice and digital conversations across all touchpoints, as an alternative to telecom channels. It's the core routing engine of the oneCXi platform that drives instant one-click conversations between customers and businesses. A plug-and-play widget seamlessly integrates with apps, websites, online ads, newsletters, in-store displays, digital kiosks, and other touchpoints to power hassle-free voice and digital conversations. It works across devices and form factors. Using internet communication, CXi Switch empowers businesses to take full control of conversations across marketing, sales, and service, creating truly seamless journeys throughout the customer lifecycle. It delivers measurable outcomes with improved brand engagement, 4X higher conversions through contextual conversations, and a 3X increase in lifetime value with improved retention. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#async_yields_async | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://scholar.google.com/citations?user=cwcBTegAAAAJ&hl=ko&oe=ASCII | Ting Wang - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 9363 7000 h-index 46 42 i10-index 137 112 0 2200 1100 550 1650 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 43 75 104 116 130 182 200 180 193 232 296 515 729 953 1375 1766 2129 40 공개 액세스 모두 보기 모두 보기 자료 88개 자료 5개 공개 비공개 재정 지원 요구사항 기준 공동 저자 Shouling Ji Professor, Zhejiang University & Georgia Institute of Technology gatech.edu의 이메일 확인됨 Ling Liu Georgia Institute of Technology cc.gatech.edu의 이메일 확인됨 Tianyu Du Zhejiang University zju.edu.cn의 이메일 확인됨 Xinyang Zhang PhD student, Penn State University psu.edu의 이메일 확인됨 Ren Pang The Pennsylvania State University psu.edu의 이메일 확인됨 Changjiang Li Stony Brook stonybrook.edu의 이메일 확인됨 Fenglong Ma Associate Professor, Pennsylvania State University psu.edu의 이메일 확인됨 Xuhong Zhang Zhejiang University zju.edu.cn의 이메일 확인됨 Jinghui Chen Assistant Professor of Information Sciences and Technology, Penn State University psu.edu의 이메일 확인됨 Bo Li University of Illinois at Urbana–Champaign illinois.edu의 이메일 확인됨 Mihai Christodorescu Google christodorescu.org의 이메일 확인됨 Mudhakar Srivatsa Research Scientist of Computer Science, IBM T. J. Watson Research Center us.ibm.com의 이메일 확인됨 Dakshi Agrawal IBM Fellow, IBM us.ibm.com의 이메일 확인됨 Wendy Hui Wang Stevens Institute of Technology stevens.edu의 이메일 확인됨 Yuan Sun University of Florida ufl.edu의 이메일 확인됨 Xusheng Xiao Associate Professor, Arizona State University asu.edu의 이메일 확인됨 Luca Melis Research Scientist fb.com의 이메일 확인됨 Neil Zhenqiang Gong Associate Professor, Duke University duke.edu의 이메일 확인됨 팔로우 Ting Wang Stony Brook University cs.stonybrook.edu의 이메일 확인됨 - 홈페이지 Security Machine learning Human-computer interaction 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 TextBugger: Generating Adversarial Text Against Real-world Applications J Li, S Ji, T Du, B Li, T Wang Proceedings of the Network and Distributed System Security Symposium (NDSS) , 2019 1037 2019 Supporting anonymous location queries in mobile environments with privacygrid B Bamba, L Liu, P Pesti, T Wang International Conference on World Wide Web , 2008 643 2008 Label inference attacks against vertical federated learning C Fu, X Zhang, S Ji, J Chen, J Wu, S Guo, J Zhou, AX Liu, T Wang USENIX Security Symposium , 2022 343 2022 Interpretable deep learning under fire X Zhang, N Wang, H Shen, S Ji, X Luo, T Wang USENIX Security Symposium , 2020 253 2020 Graph Backdoor Z Xi, R Pang, S Ji, T Wang USENIX Security Symposium , 2021 241 2021 Model-reuse attacks on deep learning systems Y Ji, X Zhang, S Ji, X Luo, T Wang ACM Conference on Computer and Communications Security , 2018 229 2018 Privacy-aware mobile services over road networks T Wang, L Liu Proceedings of the VLDB Endowment 2 (1), 1042-1053 , 2009 229 2009 Differentially private releasing via deep generative model (technical report) X Zhang, S Ji, T Wang ArXiv Pre-prints , 2018 216 2018 Trojaning Language Models for Fun and Profit X Zhang, Z Zhang, S Ji, T Wang 6th IEEE European Symposium on Security and Privacy (EuroS&P '21) , 2021 189 2021 Deepsec: A uniform platform for security analysis of deep learning model X Ling, S Ji, J Zou, J Wang, C Wu, B Li, T Wang IEEE Symposium on Security and Privacy , 2019 189 2019 An Invisible Black-Box Backdoor Attack Through Frequency Domain T Wang, Y Yao, F Xu, S An, H Tong, T Wang European Conference on Computer Vision (ECCV) , 2022 180 * 2022 Unifuzz: A holistic and pragmatic metrics-driven platform for evaluating fuzzers Y Li, S Ji, Y Chen, S Liang, WH Lee, Y Chen, C Lyu, C Wu, R Beyah, ... USENIX Security Symposium , 2021 180 2021 Sirenattack: Generating adversarial audio for end-to-end acoustic systems T Du, S Ji, J Li, Q Gu, T Wang, R Beyah ACM ASIA Conference on Computer and Communications Security , 2020 177 2020 Tokenscope: Automatically detecting inconsistent behaviors of cryptocurrency tokens in ethereum T Chen, Y Zhang, Z Li, X Luo, T Wang, R Cao, X Xiao, X Zhang ACM Conference on Computer and Communications Security , 2019 173 2019 Backdoor pre-trained models can transfer to all L Shen, S Ji, X Zhang, J Li, J Chen, J Shi, C Fang, J Yin, T Wang Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications�… , 2021 163 2021 Adaptive routing for sensor networks using reinforcement learning P Wang, T Wang IEEE International Conference on Computer and Information Technology , 2006 140 2006 A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models R Pang, X Zhang, S Ji, Y Vorobeychik, X Luo, T Wang ACM Conference on Computer and Communications Security , 2020 134 2020 Differentially private distributed online learning C Li, P Zhou, L Xiong, Q Wang, T Wang IEEE transactions on knowledge and data engineering 30 (8), 1440-1453 , 2018 124 2018 TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors R Pang, Z Zhang, X Gao, Z Xi, S Ji, P Cheng, X Luo, T Wang IEEE European Symposium on Security and Privacy (EuroS&P) , 2022 106 * 2022 Back-Propagating System Dependency Impact for Attack Investigation P Fang, P Gao, C Liu, E Ayday, K Jee, T Wang, YF Ye, Z Liu, X Xiao USENIX Security Symposium (Security) , 2022 104 2022 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:17 |
https://opensource.guide/ja/leadership-and-governance/ | リーダーシップと組織運営 | Open Source Guides このサイトについて 貢献する العربية Български Bangla Deutsch Ελληνικά English Español Farsi Français Hindi Magyar Indonesia Italiano 日本語 한국어 Malay Nederlands Pidgin Polski Português Romanian Русский संस्कृतम् Swahili தமிழ் Türkçe 简体中文 繁體中文 Open Source Guides リーダーシップと組織運営 意思決定するためのルールを決めることで、オープンソースプロジェクトを成長させる助けとなります。 目次 成長中のプロジェクトの運営方法を理解しよう オープンソースプロジェクトで使われる公式の役割の例はなんですか？ どのようにしてリーダーシップの役割を明確にするか？ いつ他の人にコミット権限を与えるべきだろうか？ オープンソースプロジェクトによくある運営方法はどのようなものでしょうか？ プロジェクトを立ち上げる時に、運営ドキュメントは必要でしょうか？ 企業の従業員がコントリビュートを提出したら何が起きますか？ 成長中のプロジェクトの運営方法を理解しよう あなたのプロジェクトは成長しており、人々が携わっていて、あなたは物事がこのまま進むように維持することに熱心でしょう。この段階では、あなたはどのようにして通常のコントリビューターをワークフローに組み込むのが良いか悩んでいるかもしれません。誰かにコミット権限を与えるかどうかであったり、コミュニティの議論をどのように収集させるのかであったり。もしこういった疑問があるのであれば、私達は答えを知っています。 オープンソースプロジェクトで使われる公式の役割の例はなんですか？ 多くのプロジェクトでは、コントリビューターの役割は似たようなものを使っています。 しかし、こういった役割が実際の所何を意味するのかは、完全にあなた次第です。下記にあなたが知っているであろう役割を挙げます： メンテナー コントリビューター コミッター 幾つかのプロジェクトでは、「メンテナー」は コミット権限を持っている唯一の人です。他のプロジェクトでは、単に README にメンテナーとして記載されている人であることもあります。 メンテナーはプロジェクトでコードを書いている人である必要はありません。プロジェクトの布教を熱心に行っている人でも良いですし、多くのドキュメントを書くことで他の人がプロジェクトにアクセスしやすくしている人でも良いのです。日常的に何をやっているのかにかかわらず、メンテナーはプロジェクトの方向性に責任を持っていると感じていて、またプロジェクトを改善するのに熱心である人でしょう。 「コントリビューター」は誰でもなり得ます。 それは、イシューやプルリクエストにコメントを書いている人かもしれないし、プロジェクトに価値を与える（イシューを選別する、コードを書く、イベントを運営するなど）人かもしれないし、プルリクエストをマージしてもらった人（おそらくこれが最も狭義のコントリビューターの定義です）かもしれません。 [Node.js では、] イシューにコメントした人やコードを書いた人は皆コミュニティのメンバーなのです。彼らに会えたということは、ユーザーからコントリビューターへの一線を越えたということを意味しています。 — @mikeal, “Healthy Open Source” 「コミッター」という言葉は コミットアクセスという特定の種類の責務を、他の種類のコントリビュートと区別するために使われるでしょう。 あなたの好きなようにプロジェクトの役割を定義できますが、より多くの種類のコントリビュートを奨励するためにより 広い定義を検討しましょう 。プロジェクトに多大なコントリビュートをしている人に対しては、その人の技術スキルがどうであれ、その人のコントリビュートを公式に認めるために、リーダーの役割を使うことができます。 皆さんは私のことをDjangoの「発明者」と認識しているかもしれません…しかし、実際は私は作られてから1年後に採用された人間なのです。 (…) 皆さんは私のプログラミングスキルのおかげで成功したと思うかもしれません…しかし、私はせいぜい平均的なプログラマーなのです。 — @jacobian, “PyCon 2015 Keynote” (video) どのようにしてリーダーシップの役割を明確にするか？ リーダーシップの役割を明確にすることで、人々に責任を持たせ、他のコミュニティメンバーが助けが必要な時に誰に聞くべきかが明確になります。 小さいプロジェクトでは、リーダーを任命することは単に README や CONTRIBUTORS ファイルに名前を追加するだけで済むこともあります。 大きなプロジェクトでは、ウェブサイトを持っているのであれば、チームページやプロジェクトリーダーのリストのページを作りましょう。例えば、 Postgres では チームのリストページ に各コントリビューターの短いプロフィールを記載しています。 もしあなたのプロジェクトのコントリビューターが非常に活発なのであれば、メンテナーの「コアチーム」を作ったり、異なる問題領域ごと（例えば、セキュリティ、イシューの選別、コミュニティ運営）に責任を持つ分科会を持っているかもしれません。あなたが指名するのではなく、人々が自分の興味のある領域の役割に自律的にボランティアしてくれるように任せましょう。 [私達は] コアチームに対して、幾つかの「サブチーム」で支えています。各サブチームはそれぞれ特定の領域にフォーカスしています。例えば、言語設計やライブラリなどです。 (…) 世界をまたがるコラボレーションと、プロジェクト全体として協力で一貫したビジョンを維持するために、各サブチームはコアチームのメンバーによってリードされています。 — “Rust Governance RFC” リーダーシップチームは( IRC のような)専用のチャンネルを作りたいと思ったり、プロジェクトについて定期的に議論するために( Gitter 上や Google Hangout 上で)集まりたいと思うかもしれません。こういったミーティングでさえも公にする事で、他の人も議論を聞けるようにしましょう。例えば、 Cucumber-ruby では、 毎週オフィスアワーを設けています 。 一度リーダーシップの役割を確立したなら、どのようにして彼らにコンタクトを取れるかドキュメントにまとめることを忘れないようにしましょう。メンテナーにどのようにしたらなれるかであったりどのように分科会に参加するのかのプロセスを明確に確立し、 GOVERNANCE.md ファイルにそれを記載しましょう。 Vossibility のようなツールは、プロジェクトに対するコントリビュートを誰がやっているのか（やっていないのか）を公にトラッキングするのに役立ちます。こういった情報をドキュメント化することで、メンテナーは非公開の場で意思決定を行う派閥を作っているとコミュニティから認識されることを避けることができます。 最後に、プロジェクトが GitHub 上にあるのであれば、プロジェクトを個人アカウントから Organization に移し、少なくとも一人の管理者をバックアップとして追加することを検討しましょう。 GitHub Organizations を使うことで、権限や複数のリポジトリを管理し、 所有権を共有することで プロジェクトの資産を守ることがやりやすくなります。 いつ他の人にコミット権限を与えるべきだろうか？ コントリビュートをするすべての人にコミット権限を与えるべきだと考える人もいます。そうすることで、より多くの人にプロジェクトに対して責任を感じてもらうことができます。 その一方で、大きく複雑なプロジェクトでは、プロジェクトに対して熱心に献身している人のみにコミット権限を与えたいと思うかもしれません。唯一の正解はありません - あなたが最も良いと思うことをやりましょう。 もしプロジェクトが GitHub 上にあるのであれば、 protected branches を使うことで、どういった状況で誰が特定のブランチに push できるのかを管理することができます。 誰かがプルリクエストを送ってきたときはいつでも、その人にプロジェクトへのコミット権限を与えましょう。はじめはそれが馬鹿げているように聞こえるかもしれませんが、この戦略によって GitHub の真の力を解き放つことができるようになります。 (…) 一度コミット権限をもらえば、人々はもはや自分のパッチがマージされるかどうか心配せずにすみます。こうすることで、彼らはより多くの仕事を成し遂げてくれるようになるのです。 — @felixge, “The Pull Request Hack” オープンソースプロジェクトによくある運営方法はどのようなものでしょうか？ オープンソースプロジェクトに関連して、3つのよく使われる運営方法があります。 BDFL: BDFL は “Benevolent Dictator for Life（優しい終身の独裁者）” の略です。これは、一人の人間（大抵はプロジェクトを立ち上げた人）が、全てのプロジェクトの大きな決断に最終承認を出すやり方です。 Python は、古くからある例です。小さなプロジェクトではおそらく初めから BDFL を採用しているでしょう。なぜなら、メンテナーが一人か二人しかいないからです。企業が始めたプロジェクトも BDFL のカテゴリーに入るでしょう。 業績主義: (メモ: “業績主義”という言葉は、コミュニティによっては否定的な意味を持つかもしれなく、 複雑な社会的、政治的歴史 があります。) 業績主義のもとでは、活動的なプロジェクトコントリビューター（「業績」を出した人）が、公式の意思決定の役割を与えられます。意思決定はたいてい投票によって行われます。業績主義のコンセプトは Apache Foundation が先鞭をつけました; 全ての Apache プロジェクト は業績主義で運営されています。コントリビュートは、全て企業ではなく代表する個人によってのみ行われます。 自由主義的なコントリビュート: 自由主義的なコントリビュートモデルでは、最も働いている人が最も影響力があると認められますが、これはこれまでのコントリビュートではなく現時点での仕事に基づきます。プロジェクトでの大きな意思決定は、純粋な投票ではなく合意の模索プロセス（大きな不満点について議論する）によって行われます。そして、可能な限りコミュニティ内の多くの知見を集めようと努力します。自由主義的なコントリビュートモデルを採用している有名なプロジェクトの例としては、 Node.js や Rust があります。 どのモデルを使うべきでしょうか？それはあなた次第です！それぞれのモデルには利点と欠点があります。そして、はじめはこれらのモデルは全く異なるように見えるかもしれませんが、見かけ以上にこれらのモデルは共通点が多いのです。もしこれらのモデルのうちの1つを採用することに興味があるのであれば、これらのテンプレートを確認してみましょう： BDFL モデルテンプレート 業績主義モデルテンプレート Node.js の自由主義的コントリビュートポリシー プロジェクトを立ち上げる時に、運営ドキュメントは必要でしょうか？ プロジェクトの運営についてドキュメントを書くのに適切なタイミングはありませんが、コミュニティの力学が明らかになってから定義するほうがずっと簡単です。オープンソース運営における最善の（そして最も大変な）点は、コミュニティによって形作られているということです！ しかしながら、初期段階でドキュメントを書くことでは必ずプロジェクト運営に寄与するでしょう。なので、書けるものから書き始めましょう。例えば、どういった行動を期待するかを明確に定義したり、コントリビューターのプロセスはどうなっているかといったものを、プロジェクトの立ち上げ時点に書きましょう。 もしあなたがオープンソースプロジェクトを立ち上げようとしている企業に所属しているのであれば、立ち上げの前にプロジェクトを進めるにあたって何をコミュニティに期待し、どのように意思決定するのかを内部で議論しておくことは価値のあることです。特に、あなたの企業がプロジェクトにどのように関わるか（もしくはかかわらないか）に関して公に説明しておきたいと思うかもしれません。 Facebook では、社内で実際にこのプロジェクトの仕事をしている小さなチームを GitHub 上のプロジェクトの運営担当としています。例えば、 React は React 開発者によって運営されています。 — @caabernathy, “An inside look at open source at Facebook” 企業の従業員がコントリビュートを提出したら何が起きますか？ 成功したオープンソースプロジェクトは多くの人々や企業によって使われるようになります。そして、幾つかの企業では、プロジェクトが最終的な収益への流れに結びつくことになるかもしれません。例えば、プロジェクトのコードを商用のサービスの一部として使っているかもしれません。 プロジェクトが広く使われるようになるほど、そのプロジェクトに習熟した人たちの需要が高まります - あなた自身もそうかもしれません！そして、プロジェクトでやっている仕事で採用されることも時にはあるでしょう。 企業の活動も、普通の活動と同じであり、1つの開発リソースの源であると捉えることは重要です。当然、給与をもらって開発している人を特別扱いすべきではありません; それぞれのコントリビュートは技術的な功績によって評価されるべきです。しかしながら、企業活動に従事する事を苦痛に感じるべきではありませんし、特定の改善や機能について議論するときにはユースケースを主張することにも苦痛を感じるべきではありません。 「商用利用」は、「オープンソース」とは完全に両立可能です。「商用利用」は単にどこかでお金が絡んでいることを意味するに過ぎません - それはソフトウェアが商取引で使われているということで、プロジェクトが多く採用されるにつれてその可能性は増していきます。（オープンソースソフトウェアがオープンソースではない製品の一部として使われる時、プロダクト全体はそれでも「プロプライエタリ」ソフトウェアですが、オープンソースのように商用も非商用のどちらでも利用可能です。） 他の皆と同様に、お金を支払われて開発を行っている人もプロジェクト内の影響力を得るのは、コントリビュートの質や量によってです。明らかに、お金を支払われている開発者は支払われていない開発者よりも多くのことをできますが、それで良いのです：お金を得ているかどうかは、その人がどのくらいコントリビュートするかに影響を与える要素が多くある中の1つでしかありません。プロジェクト内の議論では、コントリビュートを行う上での外部要因ではなく、コントリビュート自体に集中し続けましょう。 プロジェクトを運営するのに法人は必要ですか？ お金を扱うのでなければ、オープンソースプロジェクトの運営に法人は必要ありません。 例えば、商用ビジネスを立ち上げたいのであれば、（もし US で行うのであれば） C 株式会社や有限会社の立ち上げを考えているでしょう。あなたがオープンソースプロジェクトに関連した請負作業を行うだけであれば、あなたが単独で報酬を受け取るか、もしくは（ US で行うのであれば） LLC を設立することもできます。 あなたのオープンソースプロジェクトで寄付を受け取りたいのであれば、（例えば PayPal や Stripe を使うことで）寄付ボタンを設置することができます。ただし、非営利団体（ US の場合は 501c3 ）でない場合は課税控除の対象にはなりません。 多くのプロジェクトでは非営利団体を設立するという面倒を避けるために、代わりに非営利の財政スポンサーを見つけています。財政スポンサーは、寄付額の一定の割合を受け取ることと引き換えにあなたの代わりに寄付を受け取ります。 Software Freedom Conservancy や Apache Foundation 、 Eclipse Foundation 、 Linux Foundation 、 Open Collective は、オープンソースプロジェクトの財政スポンサーとして活動している団体の例です。 私達のゴールは、コミュニティが自立して持続可能になるようなインフラを提供することで、コントリビューター、支援者、スポンサーの全員が利益を得ることができるような環境を作ることです。 — @piamancini, “Moving beyond the charity framework” もしあなたのプロジェクトが特定の言語やエコシステムと密接に関係しているのであれば、連携できるソフトウェア財団もあるかもしれません。例えば、 Python Software Foundation は PyPI という Python のパッケージマネジャーをサポートしていますし、 Node.js Foundation は Express.js という Node ベースのフレームワークをサポートしています。 すべてのガイドに戻る 関連するガイド メンテナーの為のベストプラクティス プロセスのドキュメント化やコミュニティの活用といったことを通じて、オープンソースメンテナーとしての日々をより楽にしましょう。 オープンソースメトリクス 成功の度合いを計測し続けることで、データをもとにしてあなたのオープンソースプロジェクトに関する意思決定を行おう。 Scroll to Top 貢献する 提案したいことがありますか？このコンテンツはオープンソースです。改善にご協力ください。 貢献する 情報を受け取る GitHub の最新のオープンソースに関するヒントや情報をすぐに受け取りましょう。 メールアドレス fine print と 友達 による のこもった | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Finfoblox-advanced-dns-protection%3FviewConnections%3Dtrue&trk=products_details_guest_face-pile-cta | LinkedIn Login, Sign in | LinkedIn Sign in Stay updated on your professional world. Email or phone Password Show Forgot password? Keep me logged in Sign in or By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in with Apple Sign in with a passkey We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Ftencentglobal-tencent-cloud-instant-messaging-im%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/help/linkedin/answer/a1377116#a11y-main | No access to email address | LinkedIn Help Attention screen reader users, you are in a mobile optimized view and content may not appear where you expect it to be. To return the screen to its desktop view, please maximize your browser. Skip to content Skip to search Close jump menu Help LinkedIn Help Dropdown menu, expand to explore help for other LinkedIn products Close menu Get help with: LinkedIn Corporate Billing Learning Marketing Solutions Recruiter Sales Navigator Talent Insights Go to LinkedIn Sign in Sign in No access to email address Last updated: 3 weeks ago When you create a LinkedIn profile, we suggest adding a secondary email address or phone number to your account that you can use as a recovery method. After you add a recovery method to your account, you can use these credentials to sign in to LinkedIn if you can no longer access your primary email address. Learn more about the benefits of adding a second email address to your account . If you can’t recover your password or don't have access to any of the email address(es) or phone number(s) associated with your account, we can help you access your account by verifying your identity. The verification process ensures that only you can regain access to your account. Learn more about how we verify identity and keep your information safe . Here's a tip We also recommend setting up 2-factor authentication as another layer of security and can greatly reduce unauthorized access to most accounts by identifying new or unknown computers or devices. Recover your email address Click the button to begin the process of getting access to your LinkedIn account. Reset your password To regain account access, please follow the steps below: Select Forgot password on the Sign-in screen. Enter the email address or phone number currently associated with your account and click on Next . In the following screen you’ll be asked to enter a verification code sent to your email. Since you don’t have access to this email account, click on Can’t access this email? If you have more than one email address or phone number associated with your account, you may be prompted to select one to receive a verification code. If you do not have access to any of them, click on Don't have access to any of these? Scan the QR code displayed on your screen. Note : This step only appears on desktop. Enter the new email address you want associated with your account. You may also provide a link to your Linkedin profile (optional). Next, we'll ask you to verify your identity by providing an image of a valid government issued ID. After you submit the image, we'll process your information and contact you for further assistance. We ask for your ID card to ensure that only you regain access to your account and no unauthorized entity is given access. Learn more about identity verification and what types of identification are accepted. Related tasks Turn two-factor authentication on and off Manage your email address Learn more Benefits of Adding a Second Email Address to your Account Two-factor authentication overview Tagged in Basics Account Access Related articles Reset your password LinkedIn Contact us Select a language. The page will automatically refresh after a language has been selected. العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) LinkedIn Corporation © 2026 About Transparency Center Privacy and Terms Cookies Copyright Terms Privacy Guest controls Dismiss Privacy and Terms menu LinkedIn Corporation © 2026 | 2026-01-13T09:29:17 |
https://www.linkedin.com/help/linkedin/answer/a1377116#site-search-common-search-query | No access to email address | LinkedIn Help Attention screen reader users, you are in a mobile optimized view and content may not appear where you expect it to be. To return the screen to its desktop view, please maximize your browser. Skip to content Skip to search Close jump menu Help LinkedIn Help Dropdown menu, expand to explore help for other LinkedIn products Close menu Get help with: LinkedIn Corporate Billing Learning Marketing Solutions Recruiter Sales Navigator Talent Insights Go to LinkedIn Sign in Sign in No access to email address Last updated: 3 weeks ago When you create a LinkedIn profile, we suggest adding a secondary email address or phone number to your account that you can use as a recovery method. After you add a recovery method to your account, you can use these credentials to sign in to LinkedIn if you can no longer access your primary email address. Learn more about the benefits of adding a second email address to your account . If you can’t recover your password or don't have access to any of the email address(es) or phone number(s) associated with your account, we can help you access your account by verifying your identity. The verification process ensures that only you can regain access to your account. Learn more about how we verify identity and keep your information safe . Here's a tip We also recommend setting up 2-factor authentication as another layer of security and can greatly reduce unauthorized access to most accounts by identifying new or unknown computers or devices. Recover your email address Click the button to begin the process of getting access to your LinkedIn account. Reset your password To regain account access, please follow the steps below: Select Forgot password on the Sign-in screen. Enter the email address or phone number currently associated with your account and click on Next . In the following screen you’ll be asked to enter a verification code sent to your email. Since you don’t have access to this email account, click on Can’t access this email? If you have more than one email address or phone number associated with your account, you may be prompted to select one to receive a verification code. If you do not have access to any of them, click on Don't have access to any of these? Scan the QR code displayed on your screen. Note : This step only appears on desktop. Enter the new email address you want associated with your account. You may also provide a link to your Linkedin profile (optional). Next, we'll ask you to verify your identity by providing an image of a valid government issued ID. After you submit the image, we'll process your information and contact you for further assistance. We ask for your ID card to ensure that only you regain access to your account and no unauthorized entity is given access. Learn more about identity verification and what types of identification are accepted. Related tasks Turn two-factor authentication on and off Manage your email address Learn more Benefits of Adding a Second Email Address to your Account Two-factor authentication overview Tagged in Basics Account Access Related articles Reset your password LinkedIn Contact us Select a language. The page will automatically refresh after a language has been selected. العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) LinkedIn Corporation © 2026 About Transparency Center Privacy and Terms Cookies Copyright Terms Privacy Guest controls Dismiss Privacy and Terms menu LinkedIn Corporation © 2026 | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Flarksuite-lark%3FviewConnections%3Dtrue&trk=products_details_guest_face-pile-cta | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/vultr/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click | Vultr | LinkedIn Skip to main content LinkedIn Vultr in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Vultr Block Storage Software by Vultr See who's skilled in this Add as skill Learn more Report this product About View details and pricing information for the entire suite of Vultr products, including cloud compute, cloud GPU, bare metal, Kubernetes, and more. Media Products media viewer No more previous content No more next content Similar products Tencent Cloud Block Storage Tencent Cloud Block Storage Block Storage Software OVHcloud Block Storage OVHcloud Block Storage Block Storage Software DigitalOcean Block Storage DigitalOcean Block Storage Block Storage Software Vultr Bare Metal Vultr Bare Metal Block Storage Software DataCore SANsymphony DataCore SANsymphony Block Storage Software Vultr Block Storage Vultr Block Storage Block Storage Software Sign in to see more Show more Show less Vultr products Vultr Bare Metal Vultr Bare Metal Block Storage Software Vultr Block Storage Vultr Block Storage Block Storage Software LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/legal/user-agreement?session_redirect=%2Fservices%2Fproducts%2Fmightybell-mighty-networks%2F&trk=registration-frontend_join-form-user-agreement | User Agreement | LinkedIn Skip to main content User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws User Agreement Effective on November 3, 2025 Our mission is to connect the world’s professionals to allow them to be more productive and successful. Our services are designed to promote economic opportunity for our members by enabling you and millions of other professionals to meet, exchange ideas, learn, and find opportunities or employees, work, and make decisions in a network of trusted relationships. Table of Contents: Introduction Obligations Rights and Limits Disclaimer and Limit of Liability Termination Governing Law and Dispute Resolution General Terms LinkedIn “Dos and Don’ts” Complaints Regarding Content How To Contact Us Introduction 1.1 Contract When you use our Services you agree to all of these terms. Your use of our Services is also subject to our Cookie Policy and our Privacy Policy, which covers how we collect, use, share, and store your personal information. By creating a LinkedIn account or accessing or using our Services (described below), you are agreeing to enter into a legally binding contract with LinkedIn (even if you are using third party credentials or using our Services on behalf of a company). If you do not agree to this contract (“Contract” or “User Agreement”), do not create an account or access or otherwise use any of our Services. If you wish to terminate this Contract at any time, you can do so by closing your account and no longer accessing or using our Services. As a Visitor or Member of our Services, the collection, use, and sharing of your personal data is subject to our Privacy Policy , our Cookie Policy and other documents referenced in our Privacy Policy , and updates. You acknowledge and have read our Privacy Policy . Services This Contract applies to LinkedIn.com, LinkedIn-branded apps, and other LinkedIn-related sites, apps, communications, and other services that state that they are offered under this Contract (“Services”), including the offsite collection of data for those Services, such as via our ads and the “Apply with LinkedIn” and “Share with LinkedIn” plugins. LinkedIn and other Key Terms You are entering into this Contract with LinkedIn (also referred to as “we” and “us”). Designated Countries . We use the term “Designated Countries” to refer to countries in the European Union (EU), European Economic Area (EEA), and Switzerland. If you reside in the “Designated Countries”, you are entering into this Contract with LinkedIn Ireland Unlimited Company (“LinkedIn Ireland”) and LinkedIn Ireland will be the controller of your personal data provided to, or collected by or for, or processed in connection with our Services. If you reside outside of the “Designated Countries”, you are entering into this Contract with LinkedIn Corporation (“LinkedIn Corp.”) and LinkedIn Corp. will be the controller of (or business responsible for) your personal data provided to, or collected by or for, or processed in connection with our Services. Affiliates . Affiliates are companies controlling, controlled by or under common control with us, including, for example, LinkedIn Ireland, LinkedIn Corporation, LinkedIn Singapore and Microsoft Corporation or any of its subsidiaries (e.g., Github, Inc.). Social Action . Actions that members take on our services such as likes, comments, follows, sharing content. Content . Content includes, for example, feed posts, feedback, comments, profiles, articles (and contributions), group posts, job postings, messages (including InMails), videos, photos, audio, and/or PDFs. 1.2 Members and Visitors This Contract applies to Members and Visitors. When you register and join the LinkedIn Services, you become a “Member”. If you have chosen not to register for our Services, you may access certain features as a “Visitor.” 1.3 Changes We may make changes to this Contract. We may modify this Contract, our Privacy Policy and our Cookie Policy from time to time. If we materially change these terms or if we are legally required to provide notice, we will provide you notice through our Services, or by other means, to provide you the opportunity to review the changes before they become effective. However, we may not always provide prior notice of changes to these terms (1) when those changes are legally required to be implemented with immediate effect, or (2) when those changes relate to a newly launched service or feature. We agree that changes cannot be retroactive. If you object to any of these changes, you may close your account . Your continued use of our Services after we publish or send a notice about our changes to these terms means that you are consenting to the updated terms as of their effective date. 2. Obligations 2.1 Service Eligibility Here are some promises that you make to us in this Contract: You’re eligible to enter into this Contract and you are at least our “Minimum Age.” The Services are not for use by anyone under the age of 16. To use the Services, you agree that: (1) you must be the "Minimum Age" (described below) or older; (2) you will only have one LinkedIn account, which must be in your real name; and (3) you are not already restricted by LinkedIn from using the Services. Creating an account with false information is a violation of our terms, including accounts registered on behalf of others or persons under the age of 16. “Minimum Age” means 16 years old. However, if law requires that you must be older in order for LinkedIn to lawfully provide the Services to you without parental consent (including using your personal data) then the Minimum Age is such older age. Learn More 2.2 Your Account You will keep your password a secret You will not share your account with anyone else and will follow our policies and the law. Members are account holders. You agree to: (1) protect against wrongful access to your account (e.g., use a strong password and keep it confidential); (2) not share or transfer your account or any part of it (e.g., sell or transfer the personal data of others by transferring your connections); and (3) follow the law, our list of Dos and Don’ts (below), and our Professional Community Policies . Learn More You are responsible for anything that happens through your account unless you close it or report misuse. As between you and others (including your employer), your account belongs to you. However, if the Services were purchased by another party for you to use in connection with your work for them (e.g., Recruiter seat or LinkedIn Learning subscription bought by your employer), the party paying for such Service has the right to control access to and get reports on your use of such paid Service; however, they do not have rights to your personal account. 2.3 Payment You’ll honor your payment obligations and you are okay with us storing your payment information. You understand that there may be fees and taxes that are added to our prices. Refunds are subject to our policy, and we may modify our prices and those modified prices will apply prospectively. If you buy any of our paid Services, you agree to pay us the applicable fees and taxes and you agree to the additional terms specific to the paid Services. Failure to pay these fees will result in the termination of your paid Services. Also, you agree that: Your purchase may be subject to foreign exchange fees or differences in prices based on location (e.g., exchange rates). We may store and continue billing your payment method (e.g., credit card), even after it has expired, to avoid interruptions in your paid Services and to use it to pay for other Services you may buy. If your primary payment method fails, we may automatically charge a secondary payment method, if you have provided one. You may update or change your payment method. Learn more If you purchase a subscription, your payment method automatically will be charged at the start of each subscription period for the fees and taxes applicable to that period. To avoid future charges, cancel before the renewal date. Learn how to cancel or suspend your paid subscription Services. We may modify our prices effective prospectively upon reasonable notice to the extent allowed under the law. All of your paid Services are subject to LinkedIn’s refund policy . We may calculate taxes payable by you based on the billing information that you provide us. You can get a copy of your invoice through your LinkedIn account settings under “ Purchase History ”. 2.4 Notices and Messages You’re okay with us providing notices and messages to you through our websites, apps, and contact information. If your contact information is out of date, you may miss out on important notices. You agree that we will provide notices and messages to you in the following ways: (1) within the Services or (2) sent to the contact information you provided us (e.g., email, mobile number, physical address). You agree to keep your contact information up to date. Please review your settings to control and limit the types of messages you receive from us. 2.5 Sharing When you share information on our Services, others can see, copy and use that information. Our Services allow sharing of information (including content) in many ways, such as through your profile, posts, articles, group posts, links to news articles, job postings, messages, and InMails. Depending on the feature and choices you make, information that you share may be seen by other Members, Visitors, or others (on or off of the Services). Where we have made settings available, we will honor the choices you make about who can see content or other information (e.g., message content to your addressees, sharing content only to LinkedIn connections, restricting your profile visibility from search tools, or opting not to notify others of your LinkedIn profile update). For job searching activities, we default to not notifying your connections or the public. So, if you apply for a job through our Services or opt to signal that you are interested in a job, our default is to share it only with the job poster. To the extent that laws allow this, we are not obligated to publish any content or other information on our Services and can remove it with or without notice. 3. Rights and Limits 3.1. Your License to LinkedIn You own all of your original content that you provide to us, but you also grant us a non-exclusive license to it. We’ll honor the choices you make about who gets to see your content, including how it can be used for ads. As between you and LinkedIn, you own your original content that you submit or post to the Services. You grant LinkedIn and our Affiliates the following non-exclusive license to the content and other information you provide (e.g., share, post, upload, and/or otherwise submit) to our Services: A worldwide, transferable and sublicensable right to use, copy, modify, distribute, publicly perform and display, host, and process your content and other information without any further consent, notice and/or compensation to you or others. These rights are limited in the following ways: You can end this license for specific content by deleting such content from the Services, or generally by closing your account, except (a) to the extent you (1) shared it with others as part of the Services and they copied, re-shared it or stored it, (2) we had already sublicensed others prior to your content removal or closing of your account, or (3) we are required by law to retain or share it with others, and (b) for the reasonable time it takes to remove the content you delete from backup and other systems. We will not include your content in advertisements for the products and services of third parties to others without your separate consent (including sponsored content). However, without compensation to you or others, ads may be served near your content and other information, and your social actions may be visible and included with ads, as noted in the Privacy Policy. If you use a Service feature, we may mention that with your name or photo to promote that feature within our Services, subject to your settings. We will honor the audience choices for shared content (e.g., “Connections only”). For example, if you choose to share your post to "Anyone on or off LinkedIn” (or similar): (a) we may make it available off LinkedIn; (b) we may enable others to publicly share onto third-party services (e.g., a Member embedding your post on a third party service); and/or (c) we may enable search tools to make that public content findable though their services. Learn More While we may edit and make format changes to your content (such as translating or transcribing it, modifying the size, layout or file type, and removing or adding labels or metadata), we will take steps to avoid materially modifying the meaning of your expression in content you share with others. Because you own your original content and we only have non-exclusive rights to it, you may choose to make it available to others, including under the terms of a Creative Commons license . You and LinkedIn agree that if content includes personal data, it is subject to our Privacy Policy. You and LinkedIn agree that we may access, store, process, and use any information (including content and/or personal data) that you provide in accordance with the terms of the Privacy Policy and your choices (including settings). By submitting suggestions or other feedback regarding our Services to LinkedIn, you agree that LinkedIn can use and share (but does not have to) such feedback for any purpose without compensation to you. You promise to only provide content and other information that you have the right to share and that your LinkedIn profile will be truthful. You agree to only provide content and other information that does not violate the law or anyone’s rights (including intellectual property rights). You have choices about how much information to provide on your profile but also agree that the profile information you provide will be truthful. LinkedIn may be required by law to remove certain content and other information in certain countries. 3.2 Service Availability We may change or limit the availability of some features, or end any Service. We may change, suspend or discontinue any of our Services. We may also limit the availability of features, content and other information so that they are not available to all Visitors or Members (e.g., by country or by subscription access). We don’t promise to store or show (or keep showing) any information (including content) that you’ve shared. LinkedIn is not a storage service. You agree that we have no obligation to store, maintain or provide you a copy of any content or other information that you or others provide, except to the extent required by applicable law and as noted in our Privacy Policy. 3.3 Other Content, Sites and Apps Your use of others’ content and information posted on our Services, is at your own risk. Others may offer their own products and services through our Services, and we aren’t responsible for those third-party activities. Others’ Content: By using the Services, you may encounter content or other information that might be inaccurate, incomplete, delayed, misleading, illegal, offensive, or otherwise harmful. You agree that we are not responsible for content or other information made available through or within the Services by others, including Members. While we apply automated tools to review much of the content and other information presented in the Services, we cannot always prevent misuse of our Services, and you agree that we are not responsible for any such misuse. You also acknowledge the risk that others may share inaccurate or misleading information about you or your organization, and that you or your organization may be mistakenly associated with content about others, for example, when we let connections and followers know you or your organization were mentioned in the news. Members have choices about this feature . Others’ Products and Services: LinkedIn may help connect you to other Members (e.g., Members using Services Marketplace or our enterprise recruiting, jobs, sales, or marketing products) who offer you opportunities (on behalf of themselves, their organizations, or others) such as offers to become a candidate for employment or other work or offers to purchase products or services. You acknowledge that LinkedIn does not perform these offered services, employ those who perform these services, or provide these offered products. You further acknowledge that LinkedIn does not supervise, direct, control, or monitor Members in the making of these offers, or in their providing you with work, delivering products or performing services, and you agree that (1) LinkedIn is not responsible for these offers, or performance or procurement of them, (2) LinkedIn does not endorse any particular Member’s offers, and (3) LinkedIn is not an agent or employment agency on behalf of any Member offering employment or other work, products or services. With respect to employment or other work, LinkedIn does not make employment or hiring decisions on behalf of Members offering opportunities and does not have such authority from Members or organizations using our products. For Services Marketplace , (a) you must be at least 18 years of age to procure, offer, or perform services, and (b) you represent and warrant that you have all the required licenses and will provide services consistent with the relevant industry standards and our Professional Community Policies . Others’ Events: Similarly, LinkedIn may help you register for and/or attend events organized by Members and connect with other Members who are attendees at such events. You agree that (1) LinkedIn is not responsible for the conduct of any of the Members or other attendees at such events, (2) LinkedIn does not endorse any particular event listed on our Services, (3) LinkedIn does not review and/or vet any of these events or speakers, and (4) you will adhere to the terms and conditions that apply to such events. 3.4 Limits We have the right to limit how you connect and interact on our Services. LinkedIn reserves the right to limit your use of the Services, including the number of your connections and your ability to contact other Members. LinkedIn reserves the right to restrict, suspend, or terminate your account if you breach this Contract or the law or are misusing the Services (e.g., violating any of the Dos and Don’ts or Professional Community Policies ). We can also remove any content or other information you shared if we believe it violates our Professional Community Policies or Dos and Don’ts or otherwise violates this Contract. Learn more about how we moderate content. 3.5 Intellectual Property Rights We’re providing you notice about our intellectual property rights. LinkedIn reserves all of its intellectual property rights in the Services. Trademarks and logos used in connection with the Services are the trademarks of their respective owners. LinkedIn, and “in” logos and other LinkedIn trademarks, service marks, graphics and logos used for our Services are trademarks or registered trademarks of LinkedIn. 3.6 Recommendations and Automated Processing We use data and other information about you to make and order relevant suggestions and to generate content for you and others. Recommendations: We use the data and other information that you provide and that we have about Members and content on the Services to make recommendations for connections, content, ads, and features that may be useful to you. We use that data and other information to recommend and to present information to you in an order that may be more relevant for you. For example, that data and information may be used to recommend jobs to you and you to recruiters and to organize content in your feed in order to optimize your experience and use of the Services. Keeping your profile accurate and up to date helps us to make these recommendations more accurate and relevant. Learn More Generative AI Features: By using the Services, you may interact with features we offer that automate content generation for you. The content that is generated might be inaccurate, incomplete, delayed, misleading or not suitable for your purposes. Please review and edit such content before sharing with others. Like all content you share on our Services, you are responsible for ensuring it complies with our Professional Community Policies , including not sharing misleading information. The Services may include content automatically generated and shared using tools offered by LinkedIn or others off LinkedIn. Like all content and other information on our Services, regardless of whether it's labeled as created by “AI”, be sure to carefully review before relying on it. 4. Disclaimer and Limit of Liability 4.1 No Warranty This is our disclaimer of legal liability for the quality, safety, or reliability of our Services. LINKEDIN AND ITS AFFILIATES MAKE NO REPRESENTATION OR WARRANTY ABOUT THE SERVICES, INCLUDING ANY REPRESENTATION THAT THE SERVICES WILL BE UNINTERRUPTED OR ERROR-FREE, AND PROVIDE THE SERVICES (INCLUDING CONTENT, OUTPUT AND INFORMATION) ON AN “AS IS” AND “AS AVAILABLE” BASIS. TO THE FULLEST EXTENT PERMITTED UNDER APPLICABLE LAW, LINKEDIN AND ITS AFFILIATES DISCLAIM ANY IMPLIED OR STATUTORY WARRANTY, INCLUDING ANY IMPLIED WARRANTY OF TITLE, ACCURACY, NON-INFRINGEMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. If you plan to use content, output and information for any reason, it is your responsibility to verify its accuracy and fitness for your purposes, because any content, output and information on the service may not reflect accurate, complete, or current information. 4.2 Exclusion of Liability These are the limits of legal liability we may have to you. TO THE FULLEST EXTENT PERMITTED BY LAW (AND UNLESS LINKEDIN HAS ENTERED INTO A SEPARATE WRITTEN AGREEMENT THAT OVERRIDES THIS CONTRACT), LINKEDIN AND ITS AFFILIATES, WILL NOT BE LIABLE IN CONNECTION WITH THIS CONTRACT FOR LOST PROFITS OR LOST BUSINESS OPPORTUNITIES, REPUTATION (E.G., OFFENSIVE OR DEFAMATORY STATEMENTS), LOSS OF DATA (E.G., DOWN TIME OR LOSS, USE OF, OR CHANGES TO, YOUR INFORMATION OR CONTENT) OR ANY INDIRECT, INCIDENTAL, CONSEQUENTIAL, SPECIAL OR PUNITIVE DAMAGES. LINKEDIN AND ITS AFFILIATES WILL NOT BE LIABLE TO YOU IN CONNECTION WITH THIS CONTRACT FOR ANY AMOUNT THAT EXCEEDS (A) THE TOTAL FEES PAID OR PAYABLE BY YOU TO LINKEDIN FOR THE SERVICES DURING THE TERM OF THIS CONTRACT, IF ANY, OR (B) US $1000. 4.3 Basis of the Bargain; Exclusions The limitations of liability in this Section 4 are part of the basis of the bargain between you and LinkedIn and shall apply to all claims of liability (e.g., warranty, tort, negligence, contract and law) even if LinkedIn or its affiliates has been told of the possibility of any such damage, and even if these remedies fail their essential purpose. THESE LIMITATIONS OF LIABILITY DO NOT APPLY TO LIABILITY FOR DEATH OR PERSONAL INJURY OR FOR FRAUD, GROSS NEGLIGENCE OR INTENTIONAL MISCONDUCT, OR IN CASES OF NEGLIGENCE, WHERE A MATERIAL OBLIGATION HAS BEEN BREACHED. A MATERIAL OBLIGATION BEING AN OBLIGATION WHICH FORMS A PREREQUISITE TO OUR DELIVERY OF SERVICES AND ON WHICH YOU MAY REASONABLY RELY, BUT ONLY TO THE EXTENT THAT THE DAMAGES WERE DIRECTLY CAUSED BY THE BREACH AND WERE FORESEEABLE UPON CONCLUSION OF THIS CONTRACT AND TO THE EXTENT THAT THEY ARE TYPICAL IN THE CONTEXT OF THIS CONTRACT. 5. Termination We can each end this Contract, but some rights and obligations survive. Both you and LinkedIn may terminate this Contract at any time with notice to the other. On termination, you lose the right to access or use the Services. The following shall survive termination: Our rights to use and disclose your feedback; Section 3 (subject to 3.1.1); Sections 4, 6, 7, and 8.2 of this Contract; and Any amounts owed by either party prior to termination remain owed after termination. You can visit our Help Center to learn about how to close your account 6. Governing Law and Dispute Resolution In the unlikely event we end up in a legal dispute, depending on where you live, you and LinkedIn agree to resolve it in California courts using California law, Dublin, Ireland courts using Irish law, or as otherwise provided in this section. If you live in the Designated Countries, the laws of Ireland govern all claims related to LinkedIn's provision of the Services, but this shall not deprive you of the mandatory consumer protections under the law of the country to which we direct your Services where you have habitual residence. With respect to jurisdiction, you and LinkedIn agree to choose the courts of the country to which we direct your Services where you have habitual residence for all disputes arising out of or relating to this User Agreement, or in the alternative, you may choose the responsible court in Ireland. If you are a business user within the scope of Article 6(12) of the EU Digital Markets Act (“DMA”) and have a dispute arising out of or in connection with Article 6(12) of the DMA, you may also utilize the alternative dispute resolution mechanism available in the Help Center . For others outside of Designated Countries, including those who live outside of the United States: You and LinkedIn agree that the laws of the State of California, U.S.A., excluding its conflict of laws rules, shall exclusively govern any dispute relating to this Contract and/or the Services. You and LinkedIn both agree that all claims and disputes can be litigated only in the federal or state courts in Santa Clara County, California, USA, and you and LinkedIn each agree to personal jurisdiction in those courts. You may have additional rights of redress and appeal for some decisions made by LinkedIn that impact you. 7. General Terms Here are some important details about the Contract. If a court with authority over this Contract finds any part of it unenforceable, you and we agree that the court should modify the terms to make that part enforceable while still achieving its intent. If the court cannot do that, you and we agree to ask the court to remove that unenforceable part and still enforce the rest of this Contract. This Contract (including additional terms that may be provided by us when you engage with a feature of the Services) is the only agreement between us regarding the Services and supersedes all prior agreements for the Services. If we don't act to enforce a breach of this Contract, that does not mean that LinkedIn has waived its right to enforce this Contract. You may not assign or transfer this Contract (or your membership or use of Services) to anyone without our consent. However, you agree that LinkedIn may assign this Contract to its affiliates or a party that buys it without your consent. There are no third-party beneficiaries to this Contract. You agree that the only way to provide us legal notice is at the addresses provided in Section 10. 8. LinkedIn “Dos and Don’ts” LinkedIn is a community of professionals. This list of “Dos and Don’ts” along with our Professional Community Policies limits what you can and cannot do on our Services, unless otherwise explicitly permitted by LinkedIn in a separate writing (e.g., through a research agreement). 8.1. Dos You agree that you will: Comply with all applicable laws, including, without limitation, privacy laws, intellectual property laws, anti-spam laws, export control laws, laws governing the content shared, and other applicable laws and regulatory requirements; Provide accurate contact and identity information to us and keep it updated; Use your real name on your profile; and Use the Services in a professional manner. 8.2. Don’ts You agree that you will not : Create a false identity on LinkedIn, misrepresent your identity, create a Member profile for anyone other than yourself (a real person), or use or attempt to use another’s account (such as sharing log-in credentials or copying cookies); Develop, support or use software, devices, scripts, robots or any other means or processes (such as crawlers, browser plugins and add-ons or any other technology) to scrape or copy the Services, including profiles and other data from the Services; Override any security feature or bypass or circumvent any access controls or use limits of the Services (such as search results, profiles, or videos); Copy, use, display or distribute any information (including content) obtained from the Services, whether directly or through third parties (such as search tools or data aggregators or brokers), without the consent of the content owner (such as LinkedIn for content it owns); Disclose information that you do not have the consent to disclose (such as confidential information of others (including your employer); Violate the intellectual property rights of others, including copyrights, patents, trademarks, trade secrets or other proprietary rights. For example, do not copy or distribute (except through the available sharing functionality) the posts or other content of others without their permission, which they may give by posting under a Creative Commons license; Violate the intellectual property or other rights of LinkedIn, including, without limitation, (i) copying or distributing our learning videos or other materials, (ii) copying or distributing our technology, unless it is released under open source licenses; or (iii) using the word “LinkedIn” or our logos in any business name, email, or URL except as provided in the Brand Guidelines ; Post (or otherwise share) anything that contains software viruses, worms, or any other harmful code; Reverse engineer, decompile, disassemble, decipher or otherwise attempt to derive the source code for the Services or any related technology that is not open source; Imply or state that you are affiliated with or endorsed by LinkedIn without our express consent (e.g., representing yourself as an accredited LinkedIn trainer); Rent, lease, loan, trade, sell/re-sell or otherwise monetize the Services or related data or access to the same, without LinkedIn’s consent; Deep-link to our Services for any purpose other than to promote your profile or a Group on our Services, without LinkedIn’s consent; Use bots or other unauthorized automated methods to access the Services, add or download contacts, send or redirect messages, create, comment on, like, share, or re-share posts, or otherwise drive inauthentic engagement; Engage in “framing”, “mirroring”, or otherwise simulating the appearance or function of the Services; Overlay or otherwise modify the Services or their appearance (such as by inserting elements into the Services or removing, covering, or obscuring an advertisement included on the Services); Interfere with the operation of, or place an unreasonable load on, the Services (e.g., spam, denial of service attack, viruses, manipulating algorithms); Violate the Professional Community Policies , certain third party terms where applicable, or any additional terms concerning a specific Service that are provided when you sign up for or start using such Service; Use our Services to do anything that is unlawful, misleading, discriminatory, fraudulent or deceitful (e.g. manipulated media that wrongfully depicts a person saying or doing something they did not say or do); and/or Misuse our reporting or appeals process, including by submitting duplicative, fraudulent or unfounded reports, complaints or appeals. 9. Complaints Regarding Content Contact information for complaints about content provided by our Members. We ask that you report content and other information that you believe violates your rights (including intellectual property rights), our Professional Community Policies or otherwise violates this Contract or the law. To the extent we can under law, we may remove or restrict access to content, features, services, or information, including if we believe that it’s reasonably necessary to avoid harm to LinkedIn or others, violates the law or is reasonably necessary to prevent misuse of our Services. We reserve the right to take action against serious violations of this Contract, including by implementing account restrictions for significant violations. We respect the intellectual property rights of others. We require that information shared by Members be accurate and not in violation of the intellectual property rights or other rights of third parties. We provide a policy and process for complaints concerning content shared, and/or trademarks used, by our Members. 10. How To Contact Us Our Contact information. Our Help Center also provides information about our Services. For general inquiries, you may contact us online . For legal notices or service of process, you may write us at these addresses . LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/checkpoint/lg/login?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fhelp%2Flinkedin%2Fanswer%2Fa1377116&trk=help_me_menu | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/categories/relational-database-management-systems?trk=products_details_guest_product_category | Best Relational Database Management Systems | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Database Administrator (8) Chief Technology Officer (8) Chief Information Officer (5) Data Scientist (3) Information Technology Manager (3) See all products Find top products in Relational Database Management Systems category Software used to manage, maintain, and access data stored in structured tables. - Store and organize data in columns and rows - Manage simultaneous access of the same data by multiple users - Use Structured Query Language (SQL) to manipulate and view data - Establish ACID (Atomicity, Consistency, Isolation, Durability) compliance of stored data 70 results Amazon Aurora Relational Database Management Systems by Amazon Web Services (AWS) Amazon Aurora is a MySQL and PostgreSQL compatible relational database built for the cloud, that combines the performance and availability of high-end commercial databases with the simplicity and cost-effectiveness of open source databases. View product Amazon RDS Relational Database Management Systems by Amazon Web Services (AWS) With Amazon RDS, set up, operate and scale a commercial or open source relational database in the cloud in just a few clicks while automating time-consuming administrative tasks. View product Google Cloud SQL Relational Database Management Systems by Google Cloud Cloud SQL is a fully managed service that makes it easy to set up, manage, and administer relational databases: PostgreSQL, MySQL, and SQL Server. View product Teradata Vantage Relational Database Management Systems by Teradata Teradata Vantage™ is the most complete cloud analytics and data platform for AI at scale. It combines the scalability of public clouds with the control of private clouds, all on the same portable software stack. Vantage works on public clouds like Amazon Web Services (AWS), Microsoft Azure, and Google Cloud; hybrid multi-cloud setups; on premises; or on commodity hardware with VMware. It emphasizes fit-for-purpose compute connected through a unified data foundation, ensuring optimal performance and cost efficiency while enabling seamless data flow and collaboration across the organization. With no up-front costs and pay-as-you-go pricing, Vantage adapts to emerging needs, especially in the era of generative AI. Teradata Vantage® is the only platform with the massively parallel processing and multidimensional scalability to handle complex data workloads with the ease and flexibility needed to drive faster ROI across your enterprise. View product Cloud Native Database TDSQL-C Relational Database Management Systems by Tencent A cloud native database with high performance, storage capacity, and compatibility View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights SQL Server Relational Database Management Systems by Microsoft SQL Server Get the flexibility you need to use integrated solutions, apps, and innovations in technology with your data—wherever it lives—in the cloud, on-premises, or at the edge. View product CockroachDB Relational Database Management Systems by Cockroach Labs Run your business-critical applications across any environment — whether in the cloud, on-premises, or hybrid — with global scale and unmatched resilience. -> Scale to meet demand: as demand shifts, your CockroachDB clusters will automatically rebalance to ensure peak performance. -> Deliver always-on experiences: eliminate downtime & protect your data w/ multi-active availability & custom survival goals -> Ensure low-latency access to accurate data across the globe -> Simplify database operations CockroachDB delivers the reliability, robust consistency and ACID transactions of RDBMS, while offering the horizontal scaling and distributed architecture of NoSQL. All of this is built to thrive in any environment, ensuring effortless scalability, global availability and distribution, and continuous uptime all with a familiar, compliant SQL interface. Integrate across many systems including applications, analytics, streaming, security, logging, and observability. View product YugabyteDB Relational Database Management Systems by Yugabyte Open source is at the heart of YugabyteDB, a distributed SQL database. Join our community and see how our users are using YugabyteDB for their applications. View product SingleStoreDB Relational Database Management Systems by SingleStore SingleStore is a cloud database available on leading public clouds and delivers elastic scalability, high availability and exceptional price-performance for your applications, without the burden of managing your data infrastructure. SingleStore scales storage independently of compute and includes Jupyter notebooks, data integration services and a compute service for running AI workloads — meaning developers, ML engineers and data engineers can quickly build awesome things together. View product MariaDB Enterprise Platform Relational Database Management Systems by MariaDB MariaDB Enterprise Platform is engineered to deliver best-in-class performance, data security, replication, clustering and high availability for production workloads. MariaDB Enterprise Platform empowers modern data strategies with an end-to-end database solution, delivering consistent performance and unwavering stability for mission-critical applications in demanding environments. Eliminate database sprawl and simplify your data landscape by running all your workloads in a single, robust MariaDB environment, powered by open source technology and fortified with enterprise-grade reliability, security and support. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fcardano-foundation-veridian%3FviewConnections%3Dtrue&trk=products_details_guest_face-pile-cta | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/dataport-a%C3%B6r-dprojecttracking/?trk=products_details_guest_other_products_by_org_section_product_link_result-card_image-click#main-content | dProjectTracking | LinkedIn Skip to main content LinkedIn Dataport AöR in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in dProjectTracking Project Management Software by Dataport AöR See who's skilled in this Add as skill Learn more Report this product About dProjectTracking ist Ihre webbasierte Ticketlösung, mit der Sie für effizientes Teamwork sorgen. Sie basiert auf der Software JIRA von Atlassian, wird aber im BSI-zertifizierten Twin Data Center betrieben. Mit dProjectTracking steuern Sie Projekte agil nach Scrum und KANBAN. Schnell verteilen und bearbeiten Sie Aufgaben, behalten dabei aber stets den Überblick. Auf einen Blick: ✅ Scrum, Kanban Boards ✅ Berichte, Dashboards ✅ Attraktive Projekt-, User- und Speicherplatzpakete ✅ Flexible Laufzeit This product is intended for Referent Head of Section Clerical Officer Civil Servant Scrum Master Project Manager Senior Software Engineer Process Manager Information Technology Application Manager Media Products media viewer No more previous content dProjectTracking Ein Projekt-Tickettool für alle Zwecke No more next content Similar products Jira Jira Project Management Software Trello Trello Project Management Software GitHub Issues GitHub Issues Project Management Software Notion Notion Knowledge Management Software Zoho Projects Zoho Projects Project Management Software Asana Asana Project Management Software Sign in to see more Show more Show less Dataport AöR products data[port]ai data[port]ai Data Science & Machine Learning Platforms Dataport Consulting Dataport Consulting Strategic Planning Software dDataBox dDataBox Managed File Transfer (MFT) Software dMessenger dMessenger Enterprise Messaging Software dWebService dWebService Web Hosting dWorkflow dWorkflow Workflow Management Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2F320mediamatthewhussey&trk=organization_guest_main-feed-card_comment-cta | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Remember me First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/zensar-cloud-transformation/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click | Cloud transformation | LinkedIn Skip to main content LinkedIn Zensar Technologies in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Cloud transformation Enterprise Cloud Platforms by Zensar Technologies See who's skilled in this Add as skill Learn more Report this product About Build a hyper-scale technology backbone with Zensar`s Cloud Services. Media Products media viewer No more previous content Start your cloud journey right Migrate seamlessly, successfully, and securely and embrace a cloud model that meets your organization’s ever-changing needs and allows you to scale without breaking the bank. No more next content Similar products Workday Workday Enterprise Cloud Platforms Cisco+ Hybrid Cloud Cisco+ Hybrid Cloud Enterprise Cloud Platforms Oracle Cloud Infrastructure (OCI) Oracle Cloud Infrastructure (OCI) Enterprise Cloud Platforms Nutanix Central Nutanix Central Enterprise Cloud Platforms Nutanix Kubernetes Platform Nutanix Kubernetes Platform Enterprise Cloud Platforms Nutanix Enterprise AI Nutanix Enterprise AI Enterprise Cloud Platforms Sign in to see more Show more Show less Zensar Technologies products Digital Applications Digital Applications Digital Adoption Platforms Ruptive Ruptive Digital Experience Platforms (DXP) LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/servicenow-now-platform/?trk=products_seo_search | ServiceNow AI Platform | LinkedIn Skip to main content LinkedIn ServiceNow in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in ServiceNow AI Platform Business Process Management Software by ServiceNow See who's skilled in this Add as skill Learn more Report this product About The ServiceNow AI Platform is built for a new era. One platform, ready for anything. Put any AI, any data, any workflow, and any industry to work across the enterprise. Media Products media viewer No more previous content ServiceNow AI Platform ServiceNow AI Platform No more next content Similar products Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less ServiceNow products ServiceNow App Engine ServiceNow App Engine Low-Code Development Platforms LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/servicenow-now-platform/ | ServiceNow AI Platform | LinkedIn Skip to main content LinkedIn ServiceNow in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in ServiceNow AI Platform Business Process Management Software by ServiceNow See who's skilled in this Add as skill Learn more Report this product About The ServiceNow AI Platform is built for a new era. One platform, ready for anything. Put any AI, any data, any workflow, and any industry to work across the enterprise. Media Products media viewer No more previous content ServiceNow AI Platform ServiceNow AI Platform No more next content Similar products Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less ServiceNow products ServiceNow App Engine ServiceNow App Engine Low-Code Development Platforms LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?fromSignIn=true&session_redirect=https%3A%2F%2Fuk.linkedin.com%2Fcompany%2F320mediamatthewhussey&trk=organization_guest_main-feed-card_ellipsis-menu-semaphore-sign-in-redirect&guestReportContentType=POST&_f=guest-reporting | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Ft-systems-business-cockpit%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Fcustomer-relationship-management-software&fromSignIn=true&trk=products_seo_search_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2F320mediamatthewhussey&trk=organization_guest_main-feed-card_share-cta | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password (6+ characters) Show Remember me First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Follow top companies Over 60% of the fortune 100 companies use LinkedIn to hire. Join now Leave | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fsearch%2Fresults%2Fpeople%2F%3FfacetCurrentCompany%3D%255B103289507%255D&trk=org-employees_cta_face-pile-cta | Sign Up | LinkedIn Make the most of your professional life Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Remember me First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Takes less than 2 minutes Join LinkedIn to connect with people, jobs and opportunities that matter Join now Leave | 2026-01-13T09:29:17 |
https://www.linkedin.com/legal/cookie-policy?session_redirect=%2Fservices%2Fproducts%2Fmightybell-mighty-networks%2F&trk=registration-frontend_join-form-cookie-policy | Cookie Policy | LinkedIn Skip to main content User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws Cookie Policy Effective on June 3, 2022 At LinkedIn, we believe in being clear and open about how we collect and use data related to you. This Cookie Policy applies to any LinkedIn product or service that links to this policy or incorporates it by reference. We use cookies and similar technologies such as pixels, local storage and mobile ad IDs (collectively referred to in this policy as “cookies”) to collect and use data as part of our Services, as defined in our Privacy Policy (“Services”) and which includes our sites, communications, mobile applications and off-site Services, such as our ad services and the “Apply with LinkedIn” and “Share with LinkedIn” plugins or tags. In the spirit of transparency, this policy provides detailed information about how and when we use these technologies. By continuing to visit or use our Services, you are agreeing to the use of cookies and similar technologies for the purposes described in this policy. What technologies are used? ENTER A SUMMARY Type of technology Description Cookies A cookie is a small file placed onto your device that enables LinkedIn features and functionality. Any browser visiting our sites may receive cookies from us or cookies from third parties such as our customers, partners or service providers. We or third parties may also place cookies in your browser when you visit non-LinkedIn sites that display ads or that host our plugins or tags . We use two types of cookies: persistent cookies and session cookies. A persistent cookie lasts beyond the current session and is used for many purposes, such as recognizing you as an existing user, so it’s easier to return to LinkedIn and interact with our Services without signing in again. Since a persistent cookie stays in your browser, it will be read by LinkedIn when you return to one of our sites or visit a third party site that uses our Services. Session cookies last only as long as the session (usually the current visit to a website or a browser session). Pixels A pixel is a tiny image that may be embedded within web pages and emails, requiring a call (which provides device and visit information) to our servers in order for the pixel to be rendered in those web pages and emails. We use pixels to learn more about your interactions with email content or web content, such as whether you interacted with ads or posts. Pixels can also enable us and third parties to place cookies on your browser. Local storage Local storage enables a website or application to store information locally on your device(s). Local storage may be used to improve the LinkedIn experience, for example, by enabling features, remembering your preferences and speeding up site functionality. Other similar technologies We also use other tracking technologies, such as mobile advertising IDs and tags for similar purposes as described in this Cookie Policy. References to similar technologies in this policy includes pixels, local storage, and other tracking technologies. Our cookie tables lists cookies and similar technologies that are used as part of our Services. Please note that the names of cookies and similar technologies may change over time. What are these technologies used for? Below we describe the purposes for which we use these technologies. ENTER SUMMARY Purpose Description Authentication We use cookies and similar technologies to recognize you when you visit our Services. If you’re signed into LinkedIn, these technologies help us show you the right information and personalize your experience in line with your settings. For example, cookies enable LinkedIn to identify you and verify your account. Security We use cookies and similar technologies to make your interactions with our Services faster and more secure. For example, we use cookies to enable and support our security features, keep your account safe and to help us detect malicious activity and violations of our User Agreement. Preferences, features and services We use cookies and similar technologies to enable the functionality of our Services, such as helping you to fill out forms on our Services more easily and providing you with features, insights and customized content in conjunction with our plugins. We also use these technologies to remember information about your browser and your preferences. For example, cookies can tell us which language you prefer and what your communications preferences are. We may also use local storage to speed up site functionality. Customized content We use cookies and similar technologies to customize your experience on our Services. For example, we may use cookies to remember previous searches so that when you return to our services, we can offer additional information that relates to your previous search. Plugins on and off LinkedIn We use cookies and similar technologies to enable LinkedIn plugins both on and off the LinkedIn sites. For example, our plugins, including the "Apply with LinkedIn" button or the "Share" button may be found on LinkedIn or third-party sites, such as the sites of our customers and partners. Our plugins use cookies and other technologies to provide analytics and recognize you on LinkedIn and third-party sites. If you interact with a plugin (for instance, by clicking "Apply"), the plugin will use cookies to identify you and initiate your request to apply. You can learn more about plugins in our Privacy Policy . Advertising Cookies and similar technologies help us show relevant advertising to you more effectively, both on and off our Services and to measure the performance of such ads. We use these technologies to learn whether content has been shown to you or whether someone who was presented with an ad later came back and took an action (e.g., downloaded a white paper or made a purchase) on another site. Similarly, our partners or service providers may use these technologies to determine whether we've shown an ad or a post and how it performed or provide us with information about how you interact with ads. We may also work with our customers and partners to show you an ad on or off LinkedIn, such as after you’ve visited a customer’s or partner’s site or application. These technologies help us provide aggregated information to our customers and partners. For further information regarding the use of cookies for advertising purposes, please see Sections 1.4 and 2.4 of the Privacy Policy . As noted in Section 1.4 of our Privacy Policy, outside Designated Countries , we also collect (or rely on others who collect) information about your device where you have not engaged with our Services (e.g., ad ID, IP address, operating system and browser information) so we can provide our Members with relevant ads and better understand their effectiveness. For further information, please see Section 1.4 of the Privacy Policy . Analytics and research Cookies and similar technologies help us learn more about how well our Services and plugins perform in different locations. We or our service providers use these technologies to understand, improve, and research products, features and services, including as you navigate through our sites or when you access LinkedIn from other sites, applications or devices. We or our service providers, use these technologies to determine and measure the performance of ads or posts on and off LinkedIn and to learn whether you have interacted with our websites, content or emails and provide analytics based on those interactions. We also use these technologies to provide aggregated information to our customers and partners as part of our Services. If you are a LinkedIn member but logged out of your account on a browser, LinkedIn may still continue to log your interaction with our Services on that browser until the expiration of the cookie in order to generate usage analytics for our Services. We may share these analytics in aggregate form with our customers. What third parties use these technologies in connection with our Services? Third parties such as our customers, partners and service providers may use cookies in connection with our Services. For example, third parties may use cookies in their LinkedIn pages, job posts and their advertisements on and off LinkedIn for their own marketing purposes. For an illustration, please visit LinkedIn’s Help Center . Third parties may also use cookies in connection with our off-site Services, such as LinkedIn ad services. Third parties may use cookies to help us to provide our Services. We may also work with third parties for our own marketing purposes and to enable us to analyze and research our Services. Your Choices You have choices on how LinkedIn uses cookies and similar technologies. Please note that if you limit the ability of LinkedIn to set cookies and similar technologies, you may worsen your overall user experience, since it may no longer be personalized to you. It may also stop you from saving customized settings like login information. Opt out of targeted advertising As described in Section 2.4 of the Privacy Policy , you have choices regarding the personalized ads you may see. LinkedIn Members can adjust their settings here . Visitor controls can be found here . Some mobile device operating systems such as Android provide the ability to control the use of mobile advertising IDs for ads personalization. You can learn how to use these controls by visiting the manufacturer’s website. We do not use iOS mobile advertising IDs for targeted advertising. Browser Controls Most browsers allow you to control cookies through their settings, which may be adapted to reflect your consent to the use of cookies. Further, most browsers also enable you to review and erase cookies, including LinkedIn cookies. To learn more about browser controls, please consult the documentation that your browser manufacturer provides. What is Do Not Track (DNT)? DNT is a concept that has been promoted by regulatory agencies such as the U.S. Federal Trade Commission (FTC), for the Internet industry to develop and implement a mechanism for allowing Internet users to control the tracking of their online activities across websites by using browser settings. As such, LinkedIn does not generally respond to “do not track” signals. Other helpful resources To learn more about advertisers’ use of cookies, please visit the following links: Internet Advertising Bureau (US) European Interactive Digital Advertising Alliance (EU) Internet Advertising Bureau (EU) LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2F320mediamatthewhussey&trk=organization_guest_main-feed-card_like-cta | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Keep me logged in First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/tencentglobal-tencent-cloud-block-storage/?trk=products_details_guest_other_products_by_org_section_product_link_result-card_full-click#main-content | Tencent Cloud Block Storage | LinkedIn Skip to main content LinkedIn Tencent in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Tencent Cloud Block Storage Block Storage Software by Tencent See who's skilled in this Add as skill Learn more Report this product About A stable, low-latency, scalable, and persistent block storage service. Similar products OVHcloud Block Storage OVHcloud Block Storage Block Storage Software DigitalOcean Block Storage DigitalOcean Block Storage Block Storage Software Vultr Vultr Block Storage Software Vultr Bare Metal Vultr Bare Metal Block Storage Software DataCore SANsymphony DataCore SANsymphony Block Storage Software Vultr Block Storage Vultr Block Storage Block Storage Software Sign in to see more Show more Show less Tencent products Cloud Native Database TDSQL-C Cloud Native Database TDSQL-C Relational Database Management Systems Cloud Object Storage (COS) Cloud Object Storage (COS) Object Storage Software Cloud Virtual Machine (CVM) Cloud Virtual Machine (CVM) Server Virtualization Software Simple Email Service (SES) Simple Email Service (SES) Email Marketing Software Tencent Cloud Automation Tools Tencent Cloud Automation Tools Build Automation Tools Tencent Cloud Instant Messaging (IM) Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Tencent Cloud Lighthouse Tencent Cloud Lighthouse Enterprise Cloud Platforms Tencent Effect SDK Tencent Effect SDK Software Development Kits (SDK) Tencent Real-Time Communication (TRTC) Tencent Real-Time Communication (TRTC) Live Streaming Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/categories/field-service-management-software | Best Field Service Management (FSM) Software | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Field Service Manager (58) Operations Manager (53) Field Service Technician (48) Field Services Engineer (33) Service Manager (28) See all products Find top products in Field Service Management (FSM) Software category Software used to optimize the installation, repair and maintenance services performed by field-based workers. - Track field activities, manage demand, prioritize field work, dispatch suitable workers and technicians to tasks and monitor their performance - Provide access for field workers to scheduling and reporting tools as well as information such as customer location and service history 417 results Zoho FSM Field Service Management (FSM) Software by Zoho Zoho FSM is a field service management platform that automates the entire spectrum of field operations. It streamlines work order management, eases scheduling and dispatching, improves workforce productivity, and simplifies invoicing and payments. It also has a mobile app for Android and iOS that lets field agents access data, log work, and collaborate with the office from the job site. View product Atenea Field Service Management (FSM) Software by hiberus Atenea es el software para SAT más completo de gestión para empresas de servicio técnico. Los responsables de la empresa podrán tener control de sus equipos de servicio técnico, avisos de asistencia, incidencias, clientes, facturación… Con el Software de Servicio de Asistencia Técnica Atenea además contarás con una app móvil que permite tener control de las tareas de los técnicos en tiempo real. Un producto específicamente diseñado para servicio técnico. Software para SAT de Calefacción, Climatización y Gama Recomendada por las principales marcas del sector. 🔹 Digitalización de firmas 🔹 Integración con analizadores de combustión testo 🔹 Live-Tracker de técnicos 🔹 Integración con telefonía IP 🔹 Envío de SMS a clientes View product Field Nation Premier Field Service Management (FSM) Software by Field Nation Thousands of companies have long relied on Field Nation for our marketplace of 100K+ IT techs. Now, with a full suite of innovative tools and unmatched service, Field Nation Premier enables MSPs to strategically leverage the power of an on-demand workforce. • MarketSmart™ Insights uses data from millions of field service jobs to help MSPs bid competitively, protect margins, and win more work. This helps sales win RFPs while still turning a profit, and enables operations to identify and fill coverage gaps proactively. • PeopleSmart Talent Management helps service leaders source, vet, and manage hard-to-find and specialized talent at scale with our team of experts. • WorkSmart Productivity Suite lets service teams move work from "pending" to "done" faster than they ever thought possible with tools like Auto Dispatch and SmartAudit Approval Automation. Field Nation Premier seamlessly integrates with Salesforce Service Cloud, ServiceNow, Autotask, ConnectWise, NetSuite, and much more. View product FieldEdge by Xplor Field Service Management (FSM) Software by Xplor Technologies Our all-in-one solution for home and field services companies. FieldEdge is the ultimate field management service software for contractors that connects every part of their business on one simple, yet powerful system. Accessible from anywhere and updated in real-time, FieldEdge gives everyone an extra edge, from the office to the field. View product Simpro Field Service Management (FSM) Software by Simpro Software Simpro is a leading field service management software for the trades. Since 2002, Simpro has developed a range of solutions to help businesses work smarter, provide exceptional service and maximise profitability. Over 8,500 businesses with over 250,000 users worldwide use Simpro to streamline their operations. Simpro’s powerful features help with quoting and estimating, scheduling, inventory management, communicating in the field, improving cash flow and reporting. Simpro was designed by trade and service contractors for the trade and service industry, including plumbing, electrical, data networking, solar, HVAC, fire protection, security and more. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights Wello Solutions Field Service Management (FSM) Software by Wello Solutions Wеllo Solutions stands as a comprеhеnsivе solution еmpowеring sеrvicе managеrs and tеchnicians to sеamlеssly managе, plan, еxеcutе, and monitor fiеld sеrvicе ordеrs. Our softwarе еncompassеs еquipmеnt managеmеnt, work ordеrs, еfficiеnt planning, a mobilе fiеld sеrvicе app, and dеtailеd sеrvicе rеports. With sеamlеss intеgration capabilities with ovеr 5000+ apps, Wеllo Solutions providеs a vеrsatilе and robust sеrvicе managеmеnt еxpеriеncе. View product Zuper Field Service Management (FSM) Software by Zuper Zuper, the most flexible and customizable field service management software available today, allows organizations across various industries to streamline workflows, improve operational efficiency, and drive customer satisfaction to new heights. Intelligent Workforce Management: Minimize response times by assigning the right technicians with the necessary skills and equipment for each job. Mobile Accessibility: Provide access to work orders, real-time updates, digital documentation, and instant communication channels to your field technicians. Real-Time Visibility: Gain complete visibility into your field operations with real-time updates on technician locations, job progress, and work order status. Data-Driven Insights: Identify trends, measure KPIs, and uncover areas for improvement using powerful analytics and reporting capabilities. Seamless Integrations: Integrate with your existing systems, such as CRM, ERP, and accounting software, to eliminate data. View product Bravo for field management Field Service Management (FSM) Software by envnt. BRAVO is known as one of the leading field management software solutions in Gulf countries. It brings together maximum organizational consistency and time saving techniques supporting all on-field processes starting with work order management, implementations and resource allocation. In addition to providing an extensive set of tailored builders, Management operations, KPIs identifiers, real team communication, Geolocation and much more. View product Fluentgrid MWM Field Service Management (FSM) Software by Fluentgrid Limited Fluentgrid MWM™ is a feature rich mobile workforce management product with 360 degree view on jobs, staff and resources; facilitating continuous real time monitoring, rule based job assignments and reassignments, two-way communication with field staff, and performance analysis. It also comes with an add-on enterprise mobility server including an enterprise app store. View product ServiceTrade Field Service Management (FSM) Software by ServiceTrade ServiceTrade is the software platform that helps commercial HVAC, mechanical, and fire contractors grow their profits. During a persistent skilled labor shortage, contractors use ServiceTrade to control the costly chaos of on-demand work and effectively deliver contract commitments. ServiceTrade streamlines service and project operations to reduce administrative costs, optimizes field performance to increase revenue per technician, and boosts sales and client retention to grow margins. Over 1,300 commercial contractors trust ServiceTrade’s 11+ years of experience to help them manage over 13 million assets and invoice over $7.5 billion in revenue annually. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/tencentglobal-tencent-cloud-lighthouse/ | Tencent Cloud Lighthouse | LinkedIn Skip to main content LinkedIn Tencent in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Tencent Cloud Lighthouse Enterprise Cloud Platforms by Tencent See who's skilled in this Add as skill Learn more Report this product About Tencent Cloud Lighthouse is an out-of-the-box cloud server service for lightweight scenarios Similar products Workday Workday Enterprise Cloud Platforms Cisco+ Hybrid Cloud Cisco+ Hybrid Cloud Enterprise Cloud Platforms Oracle Cloud Infrastructure (OCI) Oracle Cloud Infrastructure (OCI) Enterprise Cloud Platforms Cloud transformation Cloud transformation Enterprise Cloud Platforms Nutanix Central Nutanix Central Enterprise Cloud Platforms Nutanix Kubernetes Platform Nutanix Kubernetes Platform Enterprise Cloud Platforms Sign in to see more Show more Show less Tencent products Cloud Native Database TDSQL-C Cloud Native Database TDSQL-C Relational Database Management Systems Cloud Object Storage (COS) Cloud Object Storage (COS) Object Storage Software Cloud Virtual Machine (CVM) Cloud Virtual Machine (CVM) Server Virtualization Software Simple Email Service (SES) Simple Email Service (SES) Email Marketing Software Tencent Cloud Automation Tools Tencent Cloud Automation Tools Build Automation Tools Tencent Cloud Block Storage Tencent Cloud Block Storage Block Storage Software Tencent Cloud Instant Messaging (IM) Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Tencent Effect SDK Tencent Effect SDK Software Development Kits (SDK) Tencent Real-Time Communication (TRTC) Tencent Real-Time Communication (TRTC) Live Streaming Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.youtube.com/watch?v=0zOg8_B71gE | Pascal Hertleif - Writing Idiomatic Libraries in Rust - YouTube 정보 보도자료 저작권 문의하기 크리에이터 광고 개발자 약관 개인정보처리방침 정책 및 안전 YouTube 작동의 원리 새로운 기능 테스트하기 © 2026 Google LLC, Sundar Pichai, 1600 Amphitheatre Parkway, Mountain View CA 94043, USA, 0807-882-594 (무료), yt-support-solutions-kr@google.com, 호스팅: Google LLC, 사업자정보 , 불법촬영물 신고 크리에이터들이 유튜브 상에 게시, 태그 또는 추천한 상품들은 판매자들의 약관에 따라 판매됩니다. 유튜브는 이러한 제품들을 판매하지 않으며, 그에 대한 책임을 지지 않습니다. var ytInitialData = {"responseContext":{"serviceTrackingParams":[{"service":"CSI","params":[{"key":"c","value":"WEB"},{"key":"cver","value":"2.20260109.01.00"},{"key":"yt_li","value":"0"},{"key":"GetWatchNext_rid","value":"0x6477299baea71008"}]},{"service":"GFEEDBACK","params":[{"key":"logged_in","value":"0"},{"key":"visitor_data","value":"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%3D%3D"}]},{"service":"GUIDED_HELP","params":[{"key":"logged_in","value":"0"}]},{"service":"ECATCHER","params":[{"key":"client.version","value":"2.20260109"},{"key":"client.name","value":"WEB"}]}],"mainAppWebResponseContext":{"loggedOut":true,"trackingParam":"kx_fmPxhoPZR_T9jLOhCYKcxDBeCkSzHTTL-faj4Ew7MX6HRgkussh7BwOcCE59TDtslLKPQ-SS"},"webResponseContextExtensionData":{"webResponseContextPreloadData":{"preloadMessageNames":["twoColumnWatchNextResults","results","videoPrimaryInfoRenderer","videoViewCountRenderer","menuRenderer","menuServiceItemRenderer","segmentedLikeDislikeButtonViewModel","likeButtonViewModel","toggleButtonViewModel","buttonViewModel","modalWithTitleAndButtonRenderer","buttonRenderer","dislikeButtonViewModel","unifiedSharePanelRenderer","menuFlexibleItemRenderer","videoSecondaryInfoRenderer","videoOwnerRenderer","subscribeButtonRenderer","subscriptionNotificationToggleButtonRenderer","menuPopupRenderer","confirmDialogRenderer","metadataRowContainerRenderer","compositeVideoPrimaryInfoRenderer","itemSectionRenderer","continuationItemRenderer","secondaryResults","lockupViewModel","thumbnailViewModel","thumbnailOverlayBadgeViewModel","thumbnailBadgeViewModel","thumbnailHoverOverlayToggleActionsViewModel","lockupMetadataViewModel","decoratedAvatarViewModel","avatarViewModel","contentMetadataViewModel","sheetViewModel","listViewModel","listItemViewModel","badgeViewModel","autoplay","playerOverlayRenderer","menuNavigationItemRenderer","watchNextEndScreenRenderer","endScreenVideoRenderer","thumbnailOverlayTimeStatusRenderer","thumbnailOverlayNowPlayingRenderer","playerOverlayAutoplayRenderer","playerOverlayVideoDetailsRenderer","autoplaySwitchButtonRenderer","quickActionsViewModel","decoratedPlayerBarRenderer","multiMarkersPlayerBarRenderer","speedmasterEduViewModel","engagementPanelSectionListRenderer","engagementPanelTitleHeaderRenderer","sortFilterSubMenuRenderer","sectionListRenderer","adsEngagementPanelContentRenderer","chipBarViewModel","chipViewModel","structuredDescriptionContentRenderer","videoDescriptionHeaderRenderer","factoidRenderer","viewCountFactoidRenderer","expandableVideoDescriptionBodyRenderer","videoDescriptionTranscriptSectionRenderer","videoDescriptionInfocardsSectionRenderer","desktopTopbarRenderer","topbarLogoRenderer","fusionSearchboxRenderer","topbarMenuButtonRenderer","multiPageMenuRenderer","hotkeyDialogRenderer","hotkeyDialogSectionRenderer","hotkeyDialogSectionOptionRenderer","voiceSearchDialogRenderer","cinematicContainerRenderer"]},"ytConfigData":{"visitorData":"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%3D%3D","rootVisualElementType":3832},"webPrefetchData":{"navigationEndpoints":[{"clickTrackingParams":"CAAQg2ciEwi_5bv_mYiSAxXlSw8CHZhlD48yDHJlbGF0ZWQtYXV0b0iBrO-Dv57omdMBmgEFCAMQ-B3KAQQXhYHE","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=QAz-maaH0KM\u0026pp=QAFIAQ%3D%3D","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"QAz-maaH0KM","params":"EAEYAdoBBAgBKgA%3D","playerParams":"QAFIAQ%3D%3D","watchEndpointSupportedPrefetchConfig":{"prefetchHintConfig":{"prefetchPriority":0,"countdownUiRelativeSecondsPrefetchCondition":-3}}}},{"clickTrackingParams":"CAAQg2ciEwi_5bv_mYiSAxXlSw8CHZhlD48yDHJlbGF0ZWQtYXV0b0iBrO-Dv57omdMBmgEFCAMQ-B3KAQQXhYHE","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=QAz-maaH0KM\u0026pp=QAFIAQ%3D%3D","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"QAz-maaH0KM","params":"EAEYAdoBBAgBKgA%3D","playerParams":"QAFIAQ%3D%3D","watchEndpointSupportedPrefetchConfig":{"prefetchHintConfig":{"prefetchPriority":0,"countdownUiRelativeSecondsPrefetchCondition":-3}}}},{"clickTrackingParams":"CAAQg2ciEwi_5bv_mYiSAxXlSw8CHZhlD48yDHJlbGF0ZWQtYXV0b0iBrO-Dv57omdMBmgEFCAMQ-B3KAQQXhYHE","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=QAz-maaH0KM\u0026pp=QAFIAQ%3D%3D","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"QAz-maaH0KM","params":"EAEYAdoBBAgBKgA%3D","playerParams":"QAFIAQ%3D%3D","watchEndpointSupportedPrefetchConfig":{"prefetchHintConfig":{"prefetchPriority":0,"countdownUiRelativeSecondsPrefetchCondition":-3}}}}]},"hasDecorated":true}},"contents":{"twoColumnWatchNextResults":{"results":{"results":{"contents":[{"videoPrimaryInfoRenderer":{"title":{"runs":[{"text":"Pascal Hertleif - Writing Idiomatic Libraries in Rust"}]},"viewCount":{"videoViewCountRenderer":{"viewCount":{"simpleText":"조회수 53,596회"},"shortViewCount":{"simpleText":"조회수 5.3만회"},"originalViewCount":"0"}},"videoActions":{"menuRenderer":{"items":[{"menuServiceItemRenderer":{"text":{"runs":[{"text":"신고"}]},"icon":{"iconType":"FLAG"},"serviceEndpoint":{"clickTrackingParams":"CJECEMyrARgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","showEngagementPanelEndpoint":{"identifier":{"tag":"PAabuse_report"},"globalConfiguration":{"params":"qgdxCAESCzB6T2c4X0I3MWdFGmBFZ3N3ZWs5bk9GOUNOekZuUlVBQldBQjRCWklCTWdvd0VpNW9kSFJ3Y3pvdkwya3VlWFJwYldjdVkyOXRMM1pwTHpCNlQyYzRYMEkzTVdkRkwyUmxabUYxYkhRdWFuQm4%3D"},"engagementPanelPresentationConfigs":{"engagementPanelPopupPresentationConfig":{"popupType":"PANEL_POPUP_TYPE_DIALOG"}}}},"trackingParams":"CJECEMyrARgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}}],"trackingParams":"CJECEMyrARgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","topLevelButtons":[{"segmentedLikeDislikeButtonViewModel":{"likeButtonViewModel":{"likeButtonViewModel":{"toggleButtonViewModel":{"toggleButtonViewModel":{"defaultButtonViewModel":{"buttonViewModel":{"iconName":"LIKE","title":"1.4천","onTap":{"serialCommand":{"commands":[{"logGestureCommand":{"gestureType":"GESTURE_EVENT_TYPE_LOG_GENERIC_CLICK","trackingParams":"CJwCEKVBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},{"innertubeCommand":{"clickTrackingParams":"CJwCEKVBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"ignoreNavigation":true}},"modalEndpoint":{"modal":{"modalWithTitleAndButtonRenderer":{"title":{"simpleText":"동영상이 마음에 드시나요?"},"content":{"simpleText":"로그인하여 의견을 알려주세요."},"button":{"buttonRenderer":{"style":"STYLE_MONO_FILLED","size":"SIZE_DEFAULT","isDisabled":false,"text":{"simpleText":"로그인"},"navigationEndpoint":{"clickTrackingParams":"CJ0CEPqGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"https://accounts.google.com/ServiceLogin?service=youtube\u0026uilel=3\u0026passive=true\u0026continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Faction_handle_signin%3Dtrue%26app%3Ddesktop%26hl%3Dko\u0026hl=ko\u0026ec=66426","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"signInEndpoint":{"nextEndpoint":{"clickTrackingParams":"CJ0CEPqGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/like/like"}},"likeEndpoint":{"status":"LIKE","target":{"videoId":"0zOg8_B71gE"},"likeParams":"Cg0KCzB6T2c4X0I3MWdFIAAyCwjqoJjLBhCkvddA"}},"idamTag":"66426"}},"trackingParams":"CJ0CEPqGBCITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}}}}}}}]}},"accessibilityText":"다른 사용자 1,470명과 함께 이 동영상에 좋아요 표시","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CJwCEKVBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isFullWidth":false,"type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","accessibilityId":"id.video.like.button","tooltip":"이 동영상이 마음에 듭니다."}},"toggledButtonViewModel":{"buttonViewModel":{"iconName":"LIKE","title":"1.4천","onTap":{"serialCommand":{"commands":[{"logGestureCommand":{"gestureType":"GESTURE_EVENT_TYPE_LOG_GENERIC_CLICK","trackingParams":"CJsCEKVBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},{"innertubeCommand":{"clickTrackingParams":"CJsCEKVBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/like/removelike"}},"likeEndpoint":{"status":"INDIFFERENT","target":{"videoId":"0zOg8_B71gE"},"removeLikeParams":"Cg0KCzB6T2c4X0I3MWdFGAAqCwjqoJjLBhDgydhA"}}}]}},"accessibilityText":"다른 사용자 1,470명과 함께 이 동영상에 좋아요 표시","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CJsCEKVBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isFullWidth":false,"type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","accessibilityId":"id.video.like.button","tooltip":"좋아요 취소"}},"identifier":"watch-like","trackingParams":"CJECEMyrARgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isTogglingDisabled":true}},"likeStatusEntityKey":"Egswek9nOF9CNzFnRSA-KAE%3D","likeStatusEntity":{"key":"Egswek9nOF9CNzFnRSA-KAE%3D","likeStatus":"INDIFFERENT"}}},"dislikeButtonViewModel":{"dislikeButtonViewModel":{"toggleButtonViewModel":{"toggleButtonViewModel":{"defaultButtonViewModel":{"buttonViewModel":{"iconName":"DISLIKE","title":"싫어요","onTap":{"serialCommand":{"commands":[{"logGestureCommand":{"gestureType":"GESTURE_EVENT_TYPE_LOG_GENERIC_CLICK","trackingParams":"CJkCEKiPCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}},{"innertubeCommand":{"clickTrackingParams":"CJkCEKiPCSITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"ignoreNavigation":true}},"modalEndpoint":{"modal":{"modalWithTitleAndButtonRenderer":{"title":{"simpleText":"동영상이 마음에 안 드시나요?"},"content":{"simpleText":"로그인하여 의견을 알려주세요."},"button":{"buttonRenderer":{"style":"STYLE_MONO_FILLED","size":"SIZE_DEFAULT","isDisabled":false,"text":{"simpleText":"로그인"},"navigationEndpoint":{"clickTrackingParams":"CJoCEPmGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"https://accounts.google.com/ServiceLogin?service=youtube\u0026uilel=3\u0026passive=true\u0026continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Faction_handle_signin%3Dtrue%26app%3Ddesktop%26hl%3Dko\u0026hl=ko\u0026ec=66425","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"signInEndpoint":{"nextEndpoint":{"clickTrackingParams":"CJoCEPmGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/like/dislike"}},"likeEndpoint":{"status":"DISLIKE","target":{"videoId":"0zOg8_B71gE"},"dislikeParams":"Cg0KCzB6T2c4X0I3MWdFEAAiCwjqoJjLBhDx0dpA"}},"idamTag":"66425"}},"trackingParams":"CJoCEPmGBCITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}}}}}}}]}},"accessibilityText":"동영상에 싫어요 표시","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CJkCEKiPCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw==","isFullWidth":false,"type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","accessibilityId":"id.video.dislike.button","tooltip":"이 동영상이 마음에 들지 않습니다."}},"toggledButtonViewModel":{"buttonViewModel":{"iconName":"DISLIKE","title":"싫어요","onTap":{"serialCommand":{"commands":[{"logGestureCommand":{"gestureType":"GESTURE_EVENT_TYPE_LOG_GENERIC_CLICK","trackingParams":"CJgCEKiPCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}},{"innertubeCommand":{"clickTrackingParams":"CJgCEKiPCSITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/like/removelike"}},"likeEndpoint":{"status":"INDIFFERENT","target":{"videoId":"0zOg8_B71gE"},"removeLikeParams":"Cg0KCzB6T2c4X0I3MWdFGAAqCwjqoJjLBhDs8dpA"}}}]}},"accessibilityText":"동영상에 싫어요 표시","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CJgCEKiPCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw==","isFullWidth":false,"type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","accessibilityId":"id.video.dislike.button","tooltip":"이 동영상이 마음에 들지 않습니다."}},"trackingParams":"CJECEMyrARgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isTogglingDisabled":true}},"dislikeEntityKey":"Egswek9nOF9CNzFnRSA-KAE%3D"}},"iconType":"LIKE_ICON_TYPE_UNKNOWN","likeCountEntity":{"key":"unset_like_count_entity_key"},"dynamicLikeCountUpdateData":{"updateStatusKey":"like_count_update_status_key","placeholderLikeCountValuesKey":"like_count_placeholder_values_key","updateDelayLoopId":"like_count_update_delay_loop_id","updateDelaySec":5},"teasersOrderEntityKey":"Egswek9nOF9CNzFnRSD8AygB"}},{"buttonViewModel":{"iconName":"SHARE","title":"공유","onTap":{"serialCommand":{"commands":[{"logGestureCommand":{"gestureType":"GESTURE_EVENT_TYPE_LOG_GENERIC_CLICK","trackingParams":"CJYCEOWWARgCIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},{"innertubeCommand":{"clickTrackingParams":"CJYCEOWWARgCIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/share/get_share_panel"}},"shareEntityServiceEndpoint":{"serializedShareEntity":"Cgswek9nOF9CNzFnRaABAQ%3D%3D","commands":[{"clickTrackingParams":"CJYCEOWWARgCIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","openPopupAction":{"popup":{"unifiedSharePanelRenderer":{"trackingParams":"CJcCEI5iIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","showLoadingSpinner":true}},"popupType":"DIALOG","beReused":true}}]}}}]}},"accessibilityText":"공유","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CJYCEOWWARgCIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isFullWidth":false,"type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","state":"BUTTON_VIEW_MODEL_STATE_ACTIVE","accessibilityId":"id.video.share.button","tooltip":"공유"}}],"accessibility":{"accessibilityData":{"label":"추가 작업"}},"flexibleItems":[{"menuFlexibleItemRenderer":{"menuItem":{"menuServiceItemRenderer":{"text":{"runs":[{"text":"저장"}]},"icon":{"iconType":"PLAYLIST_ADD"},"serviceEndpoint":{"clickTrackingParams":"CJQCEOuQCSITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"ignoreNavigation":true}},"modalEndpoint":{"modal":{"modalWithTitleAndButtonRenderer":{"title":{"runs":[{"text":"나중에 다시 보고 싶으신가요?"}]},"content":{"runs":[{"text":"로그인하여 동영상을 재생목록에 추가하세요."}]},"button":{"buttonRenderer":{"style":"STYLE_MONO_FILLED","size":"SIZE_DEFAULT","isDisabled":false,"text":{"simpleText":"로그인"},"navigationEndpoint":{"clickTrackingParams":"CJUCEPuGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"https://accounts.google.com/ServiceLogin?service=youtube\u0026uilel=3\u0026passive=true\u0026continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Faction_handle_signin%3Dtrue%26app%3Ddesktop%26hl%3Dko%26next%3D%252Fwatch%253Fv%253D0zOg8_B71gE\u0026hl=ko\u0026ec=66427","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"signInEndpoint":{"nextEndpoint":{"clickTrackingParams":"CJUCEPuGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=0zOg8_B71gE","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"0zOg8_B71gE","watchEndpointSupportedOnesieConfig":{"html5PlaybackOnesieConfig":{"commonConfig":{"url":"https://rr4---sn-ab02a0nfpgxapox-jwwy.googlevideo.com/initplayback?source=youtube\u0026oeis=1\u0026c=WEB\u0026oad=3200\u0026ovd=3200\u0026oaad=11000\u0026oavd=11000\u0026ocs=700\u0026oewis=1\u0026oputc=1\u0026ofpcc=1\u0026msp=1\u0026odepv=1\u0026id=d333a0f3f07bd601\u0026ip=1.208.108.242\u0026initcwndbps=4167500\u0026mt=1768296063\u0026oweuc="}}}}},"idamTag":"66427"}},"trackingParams":"CJUCEPuGBCITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}}}}}},"trackingParams":"CJQCEOuQCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}},"topLevelButton":{"buttonViewModel":{"iconName":"PLAYLIST_ADD","title":"저장","onTap":{"serialCommand":{"commands":[{"logGestureCommand":{"gestureType":"GESTURE_EVENT_TYPE_LOG_GENERIC_CLICK","trackingParams":"CJICEOuQCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}},{"innertubeCommand":{"clickTrackingParams":"CJICEOuQCSITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"ignoreNavigation":true}},"modalEndpoint":{"modal":{"modalWithTitleAndButtonRenderer":{"title":{"runs":[{"text":"나중에 다시 보고 싶으신가요?"}]},"content":{"runs":[{"text":"로그인하여 동영상을 재생목록에 추가하세요."}]},"button":{"buttonRenderer":{"style":"STYLE_MONO_FILLED","size":"SIZE_DEFAULT","isDisabled":false,"text":{"simpleText":"로그인"},"navigationEndpoint":{"clickTrackingParams":"CJMCEPuGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"https://accounts.google.com/ServiceLogin?service=youtube\u0026uilel=3\u0026passive=true\u0026continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Faction_handle_signin%3Dtrue%26app%3Ddesktop%26hl%3Dko%26next%3D%252Fwatch%253Fv%253D0zOg8_B71gE\u0026hl=ko\u0026ec=66427","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"signInEndpoint":{"nextEndpoint":{"clickTrackingParams":"CJMCEPuGBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=0zOg8_B71gE","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"0zOg8_B71gE","watchEndpointSupportedOnesieConfig":{"html5PlaybackOnesieConfig":{"commonConfig":{"url":"https://rr4---sn-ab02a0nfpgxapox-jwwy.googlevideo.com/initplayback?source=youtube\u0026oeis=1\u0026c=WEB\u0026oad=3200\u0026ovd=3200\u0026oaad=11000\u0026oavd=11000\u0026ocs=700\u0026oewis=1\u0026oputc=1\u0026ofpcc=1\u0026msp=1\u0026odepv=1\u0026id=d333a0f3f07bd601\u0026ip=1.208.108.242\u0026initcwndbps=4167500\u0026mt=1768296063\u0026oweuc="}}}}},"idamTag":"66427"}},"trackingParams":"CJMCEPuGBCITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}}}}}}}]}},"accessibilityText":"재생목록에 저장","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CJICEOuQCSITCL_lu_-ZiJIDFeVLDwIdmGUPjw==","isFullWidth":false,"type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","tooltip":"저장"}}}}]}},"trackingParams":"CJECEMyrARgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","dateText":{"simpleText":"2017. 5. 12."},"relativeDateText":{"accessibility":{"accessibilityData":{"label":"8년 전"}},"simpleText":"8년 전"}}},{"videoSecondaryInfoRenderer":{"owner":{"videoOwnerRenderer":{"thumbnail":{"thumbnails":[{"url":"https://yt3.ggpht.com/sAEKab72FRpBfwOeaIJzO_S-uS5qrs2UjxHskpAz9Hvd8XKVUKoxuieSJB6z4b5JkBlSEMidNw=s48-c-k-c0x00ffffff-no-rj","width":48,"height":48},{"url":"https://yt3.ggpht.com/sAEKab72FRpBfwOeaIJzO_S-uS5qrs2UjxHskpAz9Hvd8XKVUKoxuieSJB6z4b5JkBlSEMidNw=s88-c-k-c0x00ffffff-no-rj","width":88,"height":88},{"url":"https://yt3.ggpht.com/sAEKab72FRpBfwOeaIJzO_S-uS5qrs2UjxHskpAz9Hvd8XKVUKoxuieSJB6z4b5JkBlSEMidNw=s176-c-k-c0x00ffffff-no-rj","width":176,"height":176}]},"title":{"runs":[{"text":"Rust Programming Language","navigationEndpoint":{"clickTrackingParams":"CJACEOE5IhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"/@RustVideos","webPageType":"WEB_PAGE_TYPE_CHANNEL","rootVe":3611,"apiUrl":"/youtubei/v1/browse"}},"browseEndpoint":{"browseId":"UCaYhcUwRBNscFNUKTjgPFiA","canonicalBaseUrl":"/@RustVideos"}}}]},"subscriptionButton":{"type":"FREE"},"navigationEndpoint":{"clickTrackingParams":"CJACEOE5IhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"/@RustVideos","webPageType":"WEB_PAGE_TYPE_CHANNEL","rootVe":3611,"apiUrl":"/youtubei/v1/browse"}},"browseEndpoint":{"browseId":"UCaYhcUwRBNscFNUKTjgPFiA","canonicalBaseUrl":"/@RustVideos"}},"subscriberCountText":{"accessibility":{"accessibilityData":{"label":"구독자 6.82만명"}},"simpleText":"구독자 6.82만명"},"trackingParams":"CJACEOE5IhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"subscribeButton":{"subscribeButtonRenderer":{"buttonText":{"runs":[{"text":"구독"}]},"subscribed":false,"enabled":true,"type":"FREE","channelId":"UCaYhcUwRBNscFNUKTjgPFiA","showPreferences":false,"subscribedButtonText":{"runs":[{"text":"구독중"}]},"unsubscribedButtonText":{"runs":[{"text":"구독"}]},"trackingParams":"CIICEJsrIhMIv-W7_5mIkgMV5UsPAh2YZQ-PKPgdMgV3YXRjaA==","unsubscribeButtonText":{"runs":[{"text":"구독 취소"}]},"subscribeAccessibility":{"accessibilityData":{"label":"Rust Programming Language을(를) 구독합니다."}},"unsubscribeAccessibility":{"accessibilityData":{"label":"Rust Programming Language을(를) 구독 취소합니다."}},"notificationPreferenceButton":{"subscriptionNotificationToggleButtonRenderer":{"states":[{"stateId":3,"nextStateId":3,"state":{"buttonRenderer":{"style":"STYLE_TEXT","size":"SIZE_DEFAULT","isDisabled":false,"icon":{"iconType":"NOTIFICATIONS_NONE"},"accessibility":{"label":"현재 설정은 맞춤설정 알림 수신입니다. Rust Programming Language 채널의 알림 설정을 변경하려면 탭하세요."},"trackingParams":"CI8CEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","accessibilityData":{"accessibilityData":{"label":"현재 설정은 맞춤설정 알림 수신입니다. Rust Programming Language 채널의 알림 설정을 변경하려면 탭하세요."}}}}},{"stateId":0,"nextStateId":0,"state":{"buttonRenderer":{"style":"STYLE_TEXT","size":"SIZE_DEFAULT","isDisabled":false,"icon":{"iconType":"NOTIFICATIONS_OFF"},"accessibility":{"label":"현재 설정은 알림 수신 안함입니다. Rust Programming Language 채널의 알림 설정을 변경하려면 탭하세요."},"trackingParams":"CI4CEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","accessibilityData":{"accessibilityData":{"label":"현재 설정은 알림 수신 안함입니다. Rust Programming Language 채널의 알림 설정을 변경하려면 탭하세요."}}}}}],"currentStateId":3,"trackingParams":"CIcCEJf5ASITCL_lu_-ZiJIDFeVLDwIdmGUPjw==","command":{"clickTrackingParams":"CIcCEJf5ASITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandExecutorCommand":{"commands":[{"clickTrackingParams":"CIcCEJf5ASITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","openPopupAction":{"popup":{"menuPopupRenderer":{"items":[{"menuServiceItemRenderer":{"text":{"simpleText":"맞춤설정"},"icon":{"iconType":"NOTIFICATIONS_NONE"},"serviceEndpoint":{"clickTrackingParams":"CI0CEOy1BBgDIhMIv-W7_5mIkgMV5UsPAh2YZQ-PMhJQUkVGRVJFTkNFX0RFRkFVTFTKAQQXhYHE","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/notification/modify_channel_preference"}},"modifyChannelNotificationPreferenceEndpoint":{"params":"ChhVQ2FZaGNVd1JCTnNjRk5VS1RqZ1BGaUESAggBGAAgBFITCgIIAxILMHpPZzhfQjcxZ0UYAA%3D%3D"}},"trackingParams":"CI0CEOy1BBgDIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isSelected":true}},{"menuServiceItemRenderer":{"text":{"simpleText":"없음"},"icon":{"iconType":"NOTIFICATIONS_OFF"},"serviceEndpoint":{"clickTrackingParams":"CIwCEO21BBgEIhMIv-W7_5mIkgMV5UsPAh2YZQ-PMhtQUkVGRVJFTkNFX05PX05PVElGSUNBVElPTlPKAQQXhYHE","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/notification/modify_channel_preference"}},"modifyChannelNotificationPreferenceEndpoint":{"params":"ChhVQ2FZaGNVd1JCTnNjRk5VS1RqZ1BGaUESAggDGAAgBFITCgIIAxILMHpPZzhfQjcxZ0UYAA%3D%3D"}},"trackingParams":"CIwCEO21BBgEIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","isSelected":false}},{"menuServiceItemRenderer":{"text":{"runs":[{"text":"구독 취소"}]},"icon":{"iconType":"PERSON_MINUS"},"serviceEndpoint":{"clickTrackingParams":"CIgCENuLChgFIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true}},"signalServiceEndpoint":{"signal":"CLIENT_SIGNAL","actions":[{"clickTrackingParams":"CIgCENuLChgFIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","openPopupAction":{"popup":{"confirmDialogRenderer":{"trackingParams":"CIkCEMY4IhMIv-W7_5mIkgMV5UsPAh2YZQ-P","dialogMessages":[{"runs":[{"text":"Rust Programming Language"},{"text":" 구독을 취소하시겠습니까?"}]}],"confirmButton":{"buttonRenderer":{"style":"STYLE_BLUE_TEXT","size":"SIZE_DEFAULT","isDisabled":false,"text":{"runs":[{"text":"구독 취소"}]},"serviceEndpoint":{"clickTrackingParams":"CIsCEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PMgV3YXRjaMoBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/subscription/unsubscribe"}},"unsubscribeEndpoint":{"channelIds":["UCaYhcUwRBNscFNUKTjgPFiA"],"params":"CgIIAxILMHpPZzhfQjcxZ0UYAA%3D%3D"}},"accessibility":{"label":"구독 취소"},"trackingParams":"CIsCEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"cancelButton":{"buttonRenderer":{"style":"STYLE_TEXT","size":"SIZE_DEFAULT","isDisabled":false,"text":{"runs":[{"text":"취소"}]},"accessibility":{"label":"취소"},"trackingParams":"CIoCEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"primaryIsCancel":false}},"popupType":"DIALOG"}}]}},"trackingParams":"CIgCENuLChgFIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}}]}},"popupType":"DROPDOWN"}}]}},"targetId":"notification-bell","secondaryIcon":{"iconType":"EXPAND_MORE"}}},"targetId":"watch-subscribe","signInEndpoint":{"clickTrackingParams":"CIICEJsrIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"ignoreNavigation":true}},"modalEndpoint":{"modal":{"modalWithTitleAndButtonRenderer":{"title":{"simpleText":"채널을 구독하시겠습니까?"},"content":{"simpleText":"채널을 구독하려면 로그인하세요."},"button":{"buttonRenderer":{"style":"STYLE_MONO_FILLED","size":"SIZE_DEFAULT","isDisabled":false,"text":{"simpleText":"로그인"},"navigationEndpoint":{"clickTrackingParams":"CIYCEP2GBCITCL_lu_-ZiJIDFeVLDwIdmGUPjzIJc3Vic2NyaWJlygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"https://accounts.google.com/ServiceLogin?service=youtube\u0026uilel=3\u0026passive=true\u0026continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Faction_handle_signin%3Dtrue%26app%3Ddesktop%26hl%3Dko%26next%3D%252Fwatch%253Fv%253D0zOg8_B71gE%26continue_action%3DQUFFLUhqbkozNW16cy01aG5RbjNFbVZqQmVvVkp6Vzd5d3xBQ3Jtc0tsdk5VdWJVOWoxMkdpM1lYUkdJWlJhSFFsYmdWc2twYThuZUF0clAxUkJ0RnREODlOWjF2MnViUXVCcl9TaXhmMlAzTVhoQVZqa3A2dG5wbjB1eW1nX2E2a2c4Q1V6a3Z1X1B1N2lRSjlQZW1jazFCVmJUdFh4ZGJfSHplSFl4SDVWQjk3QmtUMUE0RmRIcld2R1JoWTlnRGpac003TkRURFhNcU0xMUFqWGt1NS1HOUExOWxRWGFNWENvZDJ2NVRwQ0w2SHY\u0026hl=ko\u0026ec=66429","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"signInEndpoint":{"nextEndpoint":{"clickTrackingParams":"CIYCEP2GBCITCL_lu_-ZiJIDFeVLDwIdmGUPj8oBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=0zOg8_B71gE","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"0zOg8_B71gE","watchEndpointSupportedOnesieConfig":{"html5PlaybackOnesieConfig":{"commonConfig":{"url":"https://rr4---sn-ab02a0nfpgxapox-jwwy.googlevideo.com/initplayback?source=youtube\u0026oeis=1\u0026c=WEB\u0026oad=3200\u0026ovd=3200\u0026oaad=11000\u0026oavd=11000\u0026ocs=700\u0026oewis=1\u0026oputc=1\u0026ofpcc=1\u0026msp=1\u0026odepv=1\u0026id=d333a0f3f07bd601\u0026ip=1.208.108.242\u0026initcwndbps=4167500\u0026mt=1768296063\u0026oweuc="}}}}},"continueAction":"QUFFLUhqbkozNW16cy01aG5RbjNFbVZqQmVvVkp6Vzd5d3xBQ3Jtc0tsdk5VdWJVOWoxMkdpM1lYUkdJWlJhSFFsYmdWc2twYThuZUF0clAxUkJ0RnREODlOWjF2MnViUXVCcl9TaXhmMlAzTVhoQVZqa3A2dG5wbjB1eW1nX2E2a2c4Q1V6a3Z1X1B1N2lRSjlQZW1jazFCVmJUdFh4ZGJfSHplSFl4SDVWQjk3QmtUMUE0RmRIcld2R1JoWTlnRGpac003TkRURFhNcU0xMUFqWGt1NS1HOUExOWxRWGFNWENvZDJ2NVRwQ0w2SHY","idamTag":"66429"}},"trackingParams":"CIYCEP2GBCITCL_lu_-ZiJIDFeVLDwIdmGUPjw=="}}}}}},"subscribedEntityKey":"EhhVQ2FZaGNVd1JCTnNjRk5VS1RqZ1BGaUEgMygB","onSubscribeEndpoints":[{"clickTrackingParams":"CIICEJsrIhMIv-W7_5mIkgMV5UsPAh2YZQ-PKPgdMgV3YXRjaMoBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/subscription/subscribe"}},"subscribeEndpoint":{"channelIds":["UCaYhcUwRBNscFNUKTjgPFiA"],"params":"EgIIAxgAIgswek9nOF9CNzFnRQ%3D%3D"}}],"onUnsubscribeEndpoints":[{"clickTrackingParams":"CIICEJsrIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true}},"signalServiceEndpoint":{"signal":"CLIENT_SIGNAL","actions":[{"clickTrackingParams":"CIICEJsrIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","openPopupAction":{"popup":{"confirmDialogRenderer":{"trackingParams":"CIMCEMY4IhMIv-W7_5mIkgMV5UsPAh2YZQ-P","dialogMessages":[{"runs":[{"text":"Rust Programming Language"},{"text":" 구독을 취소하시겠습니까?"}]}],"confirmButton":{"buttonRenderer":{"style":"STYLE_BLUE_TEXT","size":"SIZE_DEFAULT","isDisabled":false,"text":{"runs":[{"text":"구독 취소"}]},"serviceEndpoint":{"clickTrackingParams":"CIUCEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PKPgdMgV3YXRjaMoBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/subscription/unsubscribe"}},"unsubscribeEndpoint":{"channelIds":["UCaYhcUwRBNscFNUKTjgPFiA"],"params":"CgIIAxILMHpPZzhfQjcxZ0UYAA%3D%3D"}},"accessibility":{"label":"구독 취소"},"trackingParams":"CIUCEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"cancelButton":{"buttonRenderer":{"style":"STYLE_TEXT","size":"SIZE_DEFAULT","isDisabled":false,"text":{"runs":[{"text":"취소"}]},"accessibility":{"label":"취소"},"trackingParams":"CIQCEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"primaryIsCancel":false}},"popupType":"DIALOG"}}]}}]}},"metadataRowContainer":{"metadataRowContainerRenderer":{"collapsedItemCount":0,"trackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"showMoreText":{"simpleText":"...더보기"},"showLessText":{"simpleText":"간략히"},"trackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","defaultExpanded":false,"descriptionCollapsedLines":3,"showMoreCommand":{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandExecutorCommand":{"commands":[{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","changeEngagementPanelVisibilityAction":{"targetId":"engagement-panel-structured-description","visibility":"ENGAGEMENT_PANEL_VISIBILITY_EXPANDED"}},{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","scrollToEngagementPanelCommand":{"targetId":"engagement-panel-structured-description"}}]}},"showLessCommand":{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","changeEngagementPanelVisibilityAction":{"targetId":"engagement-panel-structured-description","visibility":"ENGAGEMENT_PANEL_VISIBILITY_HIDDEN"}},"attributedDescription":{"content":"The existence of libraries with nice, user-friendly interfaces is one of the most important factors when choosing a programming language. And while there are lots of books about how to write idiomatic libraries in other languages, finding the same information for Rust is more difficult. With this in mind, this talk will present several techniques that help developers take advantage of all that Rust has to offer and create idiomatic APIs: From implementing conversion traits and session types to using custom iterators and decorating built-in types.\n\nPascal Hertleif\n / killercup \nhttps://github.com/killercup\nhttps://users.rust-lang.org/users/kil...","commandRuns":[{"startIndex":570,"length":15,"onTap":{"innertubeCommand":{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PSIGs74O_nuiZ0wHKAQQXhYHE","commandMetadata":{"webCommandMetadata":{"url":"https://www.youtube.com/redirect?event=video_description\u0026redir_token=QUFFLUhqbnVDQmI2UHBleDZmWlRhOE1nLWZBU0E4ZmExUXxBQ3Jtc0ttMWpsUzM2U2Vqd3hKNVN3Y3EyZTFKTlMzX1ktemtIRWE2ZWpkWjJNcExmTGFGNzQzZEtiQkhObzUzLS1WSTd2cExzX3RqV0xZd3NpUFRXQWlPLXlnY2JHZlo4dm56WEJaRi1yM3R2T2NMYW9VTUY2WQ\u0026q=https%3A%2F%2Ftwitter.com%2Fkillercup\u0026v=0zOg8_B71gE","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"urlEndpoint":{"url":"https://www.youtube.com/redirect?event=video_description\u0026redir_token=QUFFLUhqbnVDQmI2UHBleDZmWlRhOE1nLWZBU0E4ZmExUXxBQ3Jtc0ttMWpsUzM2U2Vqd3hKNVN3Y3EyZTFKTlMzX1ktemtIRWE2ZWpkWjJNcExmTGFGNzQzZEtiQkhObzUzLS1WSTd2cExzX3RqV0xZd3NpUFRXQWlPLXlnY2JHZlo4dm56WEJaRi1yM3R2T2NMYW9VTUY2WQ\u0026q=https%3A%2F%2Ftwitter.com%2Fkillercup\u0026v=0zOg8_B71gE","target":"TARGET_NEW_WINDOW","nofollow":true}}},"onTapOptions":{"accessibilityInfo":{"accessibilityLabel":"Twitter Channel Link: killercup"}}},{"startIndex":586,"length":28,"onTap":{"innertubeCommand":{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PSIGs74O_nuiZ0wHKAQQXhYHE","commandMetadata":{"webCommandMetadata":{"url":"https://www.youtube.com/redirect?event=video_description\u0026redir_token=QUFFLUhqbVN2VkNUbFVEU1lBREZBamxheXFKOVAwRHk1QXxBQ3Jtc0trR0NnRWxFYk9JbWs2Vi03VDllOEIzNVJPT05jTm9Vcy00NUpVY1Y4VV9tLXJobW9rY1pQb0tRSkNMVE9ySi1ObkwtcXRZVEtzNFhBRUdTUFMwUmZCbmRkemljQXd3VUU5Q0Jsc3gtTmhvYzVDLVN1MA\u0026q=https%3A%2F%2Fgithub.com%2Fkillercup\u0026v=0zOg8_B71gE","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"urlEndpoint":{"url":"https://www.youtube.com/redirect?event=video_description\u0026redir_token=QUFFLUhqbVN2VkNUbFVEU1lBREZBamxheXFKOVAwRHk1QXxBQ3Jtc0trR0NnRWxFYk9JbWs2Vi03VDllOEIzNVJPT05jTm9Vcy00NUpVY1Y4VV9tLXJobW9rY1pQb0tRSkNMVE9ySi1ObkwtcXRZVEtzNFhBRUdTUFMwUmZCbmRkemljQXd3VUU5Q0Jsc3gtTmhvYzVDLVN1MA\u0026q=https%3A%2F%2Fgithub.com%2Fkillercup\u0026v=0zOg8_B71gE","target":"TARGET_NEW_WINDOW","nofollow":true}}}},{"startIndex":615,"length":40,"onTap":{"innertubeCommand":{"clickTrackingParams":"CIECEM2rARgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PSIGs74O_nuiZ0wHKAQQXhYHE","commandMetadata":{"webCommandMetadata":{"url":"https://www.youtube.com/redirect?event=video_description\u0026redir_token=QUFFLUhqbjk4X05HRGE0YVV6d0FPSlJPWWc1bDBaSlBEUXxBQ3Jtc0tuekFCRkp5RWJidkxENEJ1ckJRRUZSM0o4WFlqT2REb3FFOVk4ODBXUFh5U2U2TnpBRDVIdmtfMlhiSTB5bl9KeE1QR2tESVVyMzBWYmhDMEtuVURRVkNkbnBQNFZhaXFCNXUtblVEbFI5SHpUS1N3VQ\u0026q=https%3A%2F%2Fusers.rust-lang.org%2Fusers%2Fkillercup%2Factivity\u0026v=0zOg8_B71gE","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"urlEndpoint":{"url":"https://www.youtube.com/redirect?event=video_description\u0026redir_token=QUFFLUhqbjk4X05HRGE0YVV6d0FPSlJPWWc1bDBaSlBEUXxBQ3Jtc0tuekFCRkp5RWJidkxENEJ1ckJRRUZSM0o4WFlqT2REb3FFOVk4ODBXUFh5U2U2TnpBRDVIdmtfMlhiSTB5bl9KeE1QR2tESVVyMzBWYmhDMEtuVURRVkNkbnBQNFZhaXFCNXUtblVEbFI5SHpUS1N3VQ\u0026q=https%3A%2F%2Fusers.rust-lang.org%2Fusers%2Fkillercup%2Factivity\u0026v=0zOg8_B71gE","target":"TARGET_NEW_WINDOW","nofollow":true}}}}],"styleRuns":[{"startIndex":0,"length":570,"styleRunExtensions":{"styleRunColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":4294967295},{"key":"USER_INTERFACE_THEME_LIGHT","value":4279440147}]}},"fontFamilyName":"Roboto"},{"startIndex":570,"length":15,"styleRunExtensions":{"styleRunColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":4294967295},{"key":"USER_INTERFACE_THEME_LIGHT","value":4279440147}]}}},{"startIndex":585,"length":1,"styleRunExtensions":{"styleRunColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":4294967295},{"key":"USER_INTERFACE_THEME_LIGHT","value":4279440147}]}},"fontFamilyName":"Roboto"},{"startIndex":586,"length":28,"styleRunExtensions":{"styleRunColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":4282296063},{"key":"USER_INTERFACE_THEME_LIGHT","value":4278607828}]}},"fontFamilyName":"Roboto"},{"startIndex":614,"length":1,"styleRunExtensions":{"styleRunColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":4294967295},{"key":"USER_INTERFACE_THEME_LIGHT","value":4279440147}]}},"fontFamilyName":"Roboto"},{"startIndex":615,"length":40,"styleRunExtensions":{"styleRunColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":4282296063},{"key":"USER_INTERFACE_THEME_LIGHT","value":4278607828}]}},"fontFamilyName":"Roboto"}],"attachmentRuns":[{"startIndex":571,"length":0,"element":{"type":{"imageType":{"image":{"sources":[{"url":"https://www.gstatic.com/youtube/img/watch/social_media/twitter_1x_v2.png"}]}}},"properties":{"layoutProperties":{"height":{"value":14,"unit":"DIMENSION_UNIT_POINT"},"width":{"value":14,"unit":"DIMENSION_UNIT_POINT"},"margin":{"top":{"value":0.5,"unit":"DIMENSION_UNIT_POINT"}}}}},"alignment":"ALIGNMENT_VERTICAL_CENTER"}],"decorationRuns":[{"textDecorator":{"highlightTextDecorator":{"startIndex":570,"length":15,"backgroundCornerRadius":8,"bottomPadding":1,"highlightTextDecoratorExtensions":{"highlightTextDecoratorColorMapExtension":{"colorMap":[{"key":"USER_INTERFACE_THEME_DARK","value":452984831},{"key":"USER_INTERFACE_THEME_LIGHT","value":218103808}]}}}}}]},"headerRuns":[{"startIndex":0,"length":570,"headerMapping":"ATTRIBUTED_STRING_HEADER_MAPPING_UNSPECIFIED"},{"startIndex":570,"length":15,"headerMapping":"ATTRIBUTED_STRING_HEADER_MAPPING_UNSPECIFIED"},{"startIndex":585,"length":1,"headerMapping":"ATTRIBUTED_STRING_HEADER_MAPPING_UNSPECIFIED"},{"startIndex":586,"length":28,"headerMapping":"ATTRIBUTED_STRING_HEADER_MAPPING_UNSPECIFIED"},{"startIndex":614,"length":1,"headerMapping":"ATTRIBUTED_STRING_HEADER_MAPPING_UNSPECIFIED"},{"startIndex":615,"length":40,"headerMapping":"ATTRIBUTED_STRING_HEADER_MAPPING_UNSPECIFIED"}]}},{"compositeVideoPrimaryInfoRenderer":{}},{"itemSectionRenderer":{"contents":[{"continuationItemRenderer":{"trigger":"CONTINUATION_TRIGGER_ON_ITEM_SHOWN","continuationEndpoint":{"clickTrackingParams":"CIACELsvGAMiEwi_5bv_mYiSAxXlSw8CHZhlD4_KAQQXhYHE","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/next"}},"continuationCommand":{"token":"Eg0SCzB6T2c4X0I3MWdFGAYyJSIRIgswek9nOF9CNzFnRTAAeAJCEGNvbW1lbnRzLXNlY3Rpb24%3D","request":"CONTINUATION_REQUEST_TYPE_WATCH_NEXT"}}}}],"trackingParams":"CIACELsvGAMiEwi_5bv_mYiSAxXlSw8CHZhlD48=","sectionIdentifier":"comment-item-section","targetId":"comments-section"}}],"trackingParams":"CP8BELovIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},"secondaryResults":{"secondaryResults":{"results":[{"lockupViewModel":{"contentImage":{"thumbnailViewModel":{"image":{"sources":[{"url":"https://i.ytimg.com/vi/QAz-maaH0KM/hqdefault.jpg?sqp=-oaymwEiCKgBEF5IWvKriqkDFQgBFQAAAAAYASUAAMhCPQCAokN4AQ==\u0026rs=AOn4CLBkgS1xwhVCLmjSaAgOdB38IkBVeg","width":168,"height":94},{"url":"https://i.ytimg.com/vi/QAz-maaH0KM/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=\u0026rs=AOn4CLBwlMkTrcAjjceuI3QPaUxOLNi08Q","width":336,"height":188}]},"overlays":[{"thumbnailOverlayBadgeViewModel":{"thumbnailBadges":[{"thumbnailBadgeViewModel":{"text":"29:25","badgeStyle":"THUMBNAIL_OVERLAY_BADGE_STYLE_DEFAULT","animationActivationTargetId":"QAz-maaH0KM","animationActivationEntityKey":"Eh8veW91dHViZS9hcHAvd2F0Y2gvcGxheWVyX3N0YXRlIMMCKAE%3D","lottieData":{"url":"https://www.gstatic.com/youtube/img/lottie/audio_indicator/audio_indicator_v2.json","settings":{"loop":true,"autoplay":true}},"animatedText":"지금 재생 중","animationActivationEntitySelectorType":"THUMBNAIL_BADGE_ANIMATION_ENTITY_SELECTOR_TYPE_PLAYER_STATE","rendererContext":{"accessibilityContext":{"label":"29분 25초"}}}}],"position":"THUMBNAIL_OVERLAY_BADGE_POSITION_BOTTOM_END"}},{"thumbnailHoverOverlayToggleActionsViewModel":{"buttons":[{"toggleButtonViewModel":{"defaultButtonViewModel":{"buttonViewModel":{"iconName":"WATCH_LATER","onTap":{"innertubeCommand":{"clickTrackingParams":"CP4BEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/browse/edit_playlist"}},"playlistEditEndpoint":{"playlistId":"WL","actions":[{"addedVideoId":"QAz-maaH0KM","action":"ACTION_ADD_VIDEO"}]}}},"accessibilityText":"나중에 볼 동영상","style":"BUTTON_VIEW_MODEL_STYLE_OVERLAY_DARK","trackingParams":"CP4BEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_COMPACT","state":"BUTTON_VIEW_MODEL_STATE_ACTIVE"}},"toggledButtonViewModel":{"buttonViewModel":{"iconName":"CHECK","onTap":{"innertubeCommand":{"clickTrackingParams":"CP0BEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/browse/edit_playlist"}},"playlistEditEndpoint":{"playlistId":"WL","actions":[{"action":"ACTION_REMOVE_VIDEO_BY_VIDEO_ID","removedVideoId":"QAz-maaH0KM"}]}}},"accessibilityText":"추가됨","style":"BUTTON_VIEW_MODEL_STYLE_OVERLAY_DARK","trackingParams":"CP0BEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_COMPACT","state":"BUTTON_VIEW_MODEL_STATE_ACTIVE"}},"isToggled":false,"trackingParams":"CPYBENTEDBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}},{"toggleButtonViewModel":{"defaultButtonViewModel":{"buttonViewModel":{"iconName":"ADD_TO_QUEUE_TAIL","onTap":{"innertubeCommand":{"clickTrackingParams":"CPwBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true}},"signalServiceEndpoint":{"signal":"CLIENT_SIGNAL","actions":[{"clickTrackingParams":"CPwBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","addToPlaylistCommand":{"openMiniplayer":false,"openListPanel":true,"videoId":"QAz-maaH0KM","listType":"PLAYLIST_EDIT_LIST_TYPE_QUEUE","onCreateListCommand":{"clickTrackingParams":"CPwBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/playlist/create"}},"createPlaylistServiceEndpoint":{"videoIds":["QAz-maaH0KM"],"params":"CAQ%3D"}},"videoIds":["QAz-maaH0KM"],"videoCommand":{"clickTrackingParams":"CPwBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=QAz-maaH0KM","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"QAz-maaH0KM","watchEndpointSupportedOnesieConfig":{"html5PlaybackOnesieConfig":{"commonConfig":{"url":"https://rr7---sn-ab02a0nfpgxapox-bh2ed.googlevideo.com/initplayback?source=youtube\u0026oeis=1\u0026c=WEB\u0026oad=3200\u0026ovd=3200\u0026oaad=11000\u0026oavd=11000\u0026ocs=700\u0026oewis=1\u0026oputc=1\u0026ofpcc=1\u0026msp=1\u0026odepv=1\u0026id=400cfe99a687d0a3\u0026ip=1.208.108.242\u0026initcwndbps=3865000\u0026mt=1768296063\u0026oweuc="}}}}}}}]}}},"accessibilityText":"현재 재생목록에 추가","style":"BUTTON_VIEW_MODEL_STYLE_OVERLAY_DARK","trackingParams":"CPwBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_COMPACT","state":"BUTTON_VIEW_MODEL_STATE_ACTIVE"}},"toggledButtonViewModel":{"buttonViewModel":{"iconName":"CHECK","accessibilityText":"추가됨","style":"BUTTON_VIEW_MODEL_STYLE_OVERLAY_DARK","trackingParams":"CPsBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","type":"BUTTON_VIEW_MODEL_TYPE_TONAL","buttonSize":"BUTTON_VIEW_MODEL_SIZE_COMPACT","state":"BUTTON_VIEW_MODEL_STATE_ACTIVE"}},"isToggled":false,"trackingParams":"CPYBENTEDBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P"}}]}}]}},"metadata":{"lockupMetadataViewModel":{"title":{"content":"Rust NYC: Jon Gjengset - Demystifying unsafe code"},"image":{"decoratedAvatarViewModel":{"avatar":{"avatarViewModel":{"image":{"sources":[{"url":"https://yt3.ggpht.com/sAEKab72FRpBfwOeaIJzO_S-uS5qrs2UjxHskpAz9Hvd8XKVUKoxuieSJB6z4b5JkBlSEMidNw=s68-c-k-c0x00ffffff-no-rj","width":68,"height":68}]},"avatarImageSize":"AVATAR_SIZE_M"}},"a11yLabel":"Rust Programming Language 채널로 이동","rendererContext":{"commandContext":{"onTap":{"innertubeCommand":{"clickTrackingParams":"CPYBENTEDBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"/@RustVideos","webPageType":"WEB_PAGE_TYPE_CHANNEL","rootVe":3611,"apiUrl":"/youtubei/v1/browse"}},"browseEndpoint":{"browseId":"UCaYhcUwRBNscFNUKTjgPFiA","canonicalBaseUrl":"/@RustVideos"}}}}}}},"metadata":{"contentMetadataViewModel":{"metadataRows":[{"metadataParts":[{"text":{"content":"Rust Programming Language"}}]},{"metadataParts":[{"text":{"content":"조회수 2.5만회"}},{"text":{"content":"5년 전"}}]}],"delimiter":" • "}},"menuButton":{"buttonViewModel":{"iconName":"MORE_VERT","onTap":{"innertubeCommand":{"clickTrackingParams":"CPcBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","showSheetCommand":{"panelLoadingStrategy":{"inlineContent":{"sheetViewModel":{"content":{"listViewModel":{"listItems":[{"listItemViewModel":{"title":{"content":"현재 재생목록에 추가"},"leadingImage":{"sources":[{"clientResource":{"imageName":"ADD_TO_QUEUE_TAIL"}}]},"rendererContext":{"loggingContext":{"loggingDirectives":{"trackingParams":"CPoBEP6YBBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","visibility":{"types":"12"}}},"commandContext":{"onTap":{"innertubeCommand":{"clickTrackingParams":"CPoBEP6YBBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true}},"signalServiceEndpoint":{"signal":"CLIENT_SIGNAL","actions":[{"clickTrackingParams":"CPoBEP6YBBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","addToPlaylistCommand":{"openMiniplayer":true,"videoId":"QAz-maaH0KM","listType":"PLAYLIST_EDIT_LIST_TYPE_QUEUE","onCreateListCommand":{"clickTrackingParams":"CPoBEP6YBBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/playlist/create"}},"createPlaylistServiceEndpoint":{"videoIds":["QAz-maaH0KM"],"params":"CAQ%3D"}},"videoIds":["QAz-maaH0KM"],"videoCommand":{"clickTrackingParams":"CPoBEP6YBBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=QAz-maaH0KM","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"QAz-maaH0KM","watchEndpointSupportedOnesieConfig":{"html5PlaybackOnesieConfig":{"commonConfig":{"url":"https://rr7---sn-ab02a0nfpgxapox-bh2ed.googlevideo.com/initplayback?source=youtube\u0026oeis=1\u0026c=WEB\u0026oad=3200\u0026ovd=3200\u0026oaad=11000\u0026oavd=11000\u0026ocs=700\u0026oewis=1\u0026oputc=1\u0026ofpcc=1\u0026msp=1\u0026odepv=1\u0026id=400cfe99a687d0a3\u0026ip=1.208.108.242\u0026initcwndbps=3865000\u0026mt=1768296063\u0026oweuc="}}}}}}}]}}}}}}},{"listItemViewModel":{"title":{"content":"재생목록에 저장"},"leadingImage":{"sources":[{"clientResource":{"imageName":"BOOKMARK_BORDER"}}]},"rendererContext":{"loggingContext":{"loggingDirectives":{"trackingParams":"CPkBEJSsCRgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","visibility":{"types":"12"}}},"commandContext":{"onTap":{"innertubeCommand":{"clickTrackingParams":"CPkBEJSsCRgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"url":"https://accounts.google.com/ServiceLogin?service=youtube\u0026uilel=3\u0026passive=true\u0026continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Faction_handle_signin%3Dtrue%26app%3Ddesktop%26hl%3Dko\u0026hl=ko","webPageType":"WEB_PAGE_TYPE_UNKNOWN","rootVe":83769}},"signInEndpoint":{"nextEndpoint":{"clickTrackingParams":"CPkBEJSsCRgBIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","showSheetCommand":{"panelLoadingStrategy":{"requestTemplate":{"panelId":"PAadd_to_playlist","params":"-gYNCgtRQXotbWFhSDBLTQ%3D%3D"}}}}}}}}}}},{"listItemViewModel":{"title":{"content":"공유"},"leadingImage":{"sources":[{"clientResource":{"imageName":"SHARE"}}]},"rendererContext":{"commandContext":{"onTap":{"innertubeCommand":{"clickTrackingParams":"CPcBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","commandMetadata":{"webCommandMetadata":{"sendPost":true,"apiUrl":"/youtubei/v1/share/get_share_panel"}},"shareEntityServiceEndpoint":{"serializedShareEntity":"CgtRQXotbWFhSDBLTQ%3D%3D","commands":[{"clickTrackingParams":"CPcBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-PygEEF4WBxA==","openPopupAction":{"popup":{"unifiedSharePanelRenderer":{"trackingParams":"CPgBEI5iIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","showLoadingSpinner":true}},"popupType":"DIALOG","beReused":true}}]}}}}}}}]}}}}}}}},"accessibilityText":"추가 작업","style":"BUTTON_VIEW_MODEL_STYLE_MONO","trackingParams":"CPcBEPBbIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","type":"BUTTON_VIEW_MODEL_TYPE_TEXT","buttonSize":"BUTTON_VIEW_MODEL_SIZE_DEFAULT","state":"BUTTON_VIEW_MODEL_STATE_ACTIVE"}}}},"contentId":"QAz-maaH0KM","contentType":"LOCKUP_CONTENT_TYPE_VIDEO","rendererContext":{"loggingContext":{"loggingDirectives":{"trackingParams":"CPYBENTEDBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-P","visibility":{"types":"12"}}},"accessibilityContext":{"label":"Rust NYC: Jon Gjengset - Demystifying unsafe code 29분"},"commandContext":{"onTap":{"innertubeCommand":{"clickTrackingParams":"CPYBENTEDBgAIhMIv-W7_5mIkgMV5UsPAh2YZQ-PMgdyZWxhdGVkSIGs74O_nuiZ0wGaAQUIARD4HcoBBBeFgcQ=","commandMetadata":{"webCommandMetadata":{"url":"/watch?v=QAz-maaH0KM","webPageType":"WEB_PAGE_TYPE_WATCH","rootVe":3832}},"watchEndpoint":{"videoId":"QAz-maaH0KM","nofollow":true,"watchEndpointSupportedOnesieConfig":{"html5PlaybackOnesieConfig":{"commonConfig":{"url":"https://rr7---sn-ab02a0nfpgxapox-bh2ed.googlevideo.com/initplayback?source=youtube\u0026oeis=1\u0026c=WEB\u0026oad=3200\u0026ovd=3200\u0026oaad=11000\u0026oavd=11000\u0026ocs=700\u0026oewis=1\u0026oputc= | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/skan-ai-skan-cpx-skan-cognitive-process-discovery-and-operational-intelligence-platform/ | Skan AI Process Intelligence Platform | LinkedIn Skip to main content LinkedIn Skan AI in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Skan AI Process Intelligence Platform Business Process Management Software by Skan AI See who's skilled in this Add as skill Request demo Report this product About See how work really happens across your entire organization. Our platform captures complete end-to-end processes across every application and user, creating accurate digital twins that reveal inefficiencies others miss. Move from guesswork to certainty with continuous monitoring that spots issues before they become costly and validates improvements after implementation. Traditional process discovery tools leave you blind. Process mining only sees what's logged in your systems—missing the human work that makes up most of your operations. Task mining captures individual actions but can't stitch them into complete processes. Skan's Process Intelligence observes everything: every application including mainframes and VDI, every click, every handoff, every variation. We deploy in weeks, not months, with zero system integrations required. You get the full picture of how work flows across any operation. This product is intended for Operations Manager Chief Financial Officer Chief Operating Officer Process Manager Business Process Manager Media Products media viewer No more previous content What is Skan? With Skan’s process intelligence technology, you can now continuously understand how real work is being done. We can help you unlock your business’ potential to be greater at driving operational excellence, business transformation, and continuous improvement. No more next content Featured customers of Skan AI Process Intelligence Platform Drax Group Utilities 56,486 followers Cisive Human Resources Services 29,528 followers Unum Insurance 96,511 followers Dell Technologies Computer Hardware Manufacturing 5,431,605 followers Protective Life Insurance 38,562 followers Mitie Facilities Services 213,757 followers Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/legal/cookie-policy?session_redirect=%2Fservices%2Fproducts%2Fatlassian-jira%2F&trk=registration-frontend_join-form-cookie-policy#lithograph-app | Cookie Policy | LinkedIn Skip to main content User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws User Agreement Summary of User Agreement Privacy Policy Professional Community Policies Cookie Policy Copyright Policy Regional Info EU Notice California Privacy Disclosure U.S. State Privacy Laws Cookie Policy Effective on June 3, 2022 At LinkedIn, we believe in being clear and open about how we collect and use data related to you. This Cookie Policy applies to any LinkedIn product or service that links to this policy or incorporates it by reference. We use cookies and similar technologies such as pixels, local storage and mobile ad IDs (collectively referred to in this policy as “cookies”) to collect and use data as part of our Services, as defined in our Privacy Policy (“Services”) and which includes our sites, communications, mobile applications and off-site Services, such as our ad services and the “Apply with LinkedIn” and “Share with LinkedIn” plugins or tags. In the spirit of transparency, this policy provides detailed information about how and when we use these technologies. By continuing to visit or use our Services, you are agreeing to the use of cookies and similar technologies for the purposes described in this policy. What technologies are used? ENTER A SUMMARY Type of technology Description Cookies A cookie is a small file placed onto your device that enables LinkedIn features and functionality. Any browser visiting our sites may receive cookies from us or cookies from third parties such as our customers, partners or service providers. We or third parties may also place cookies in your browser when you visit non-LinkedIn sites that display ads or that host our plugins or tags . We use two types of cookies: persistent cookies and session cookies. A persistent cookie lasts beyond the current session and is used for many purposes, such as recognizing you as an existing user, so it’s easier to return to LinkedIn and interact with our Services without signing in again. Since a persistent cookie stays in your browser, it will be read by LinkedIn when you return to one of our sites or visit a third party site that uses our Services. Session cookies last only as long as the session (usually the current visit to a website or a browser session). Pixels A pixel is a tiny image that may be embedded within web pages and emails, requiring a call (which provides device and visit information) to our servers in order for the pixel to be rendered in those web pages and emails. We use pixels to learn more about your interactions with email content or web content, such as whether you interacted with ads or posts. Pixels can also enable us and third parties to place cookies on your browser. Local storage Local storage enables a website or application to store information locally on your device(s). Local storage may be used to improve the LinkedIn experience, for example, by enabling features, remembering your preferences and speeding up site functionality. Other similar technologies We also use other tracking technologies, such as mobile advertising IDs and tags for similar purposes as described in this Cookie Policy. References to similar technologies in this policy includes pixels, local storage, and other tracking technologies. Our cookie tables lists cookies and similar technologies that are used as part of our Services. Please note that the names of cookies and similar technologies may change over time. What are these technologies used for? Below we describe the purposes for which we use these technologies. ENTER SUMMARY Purpose Description Authentication We use cookies and similar technologies to recognize you when you visit our Services. If you’re signed into LinkedIn, these technologies help us show you the right information and personalize your experience in line with your settings. For example, cookies enable LinkedIn to identify you and verify your account. Security We use cookies and similar technologies to make your interactions with our Services faster and more secure. For example, we use cookies to enable and support our security features, keep your account safe and to help us detect malicious activity and violations of our User Agreement. Preferences, features and services We use cookies and similar technologies to enable the functionality of our Services, such as helping you to fill out forms on our Services more easily and providing you with features, insights and customized content in conjunction with our plugins. We also use these technologies to remember information about your browser and your preferences. For example, cookies can tell us which language you prefer and what your communications preferences are. We may also use local storage to speed up site functionality. Customized content We use cookies and similar technologies to customize your experience on our Services. For example, we may use cookies to remember previous searches so that when you return to our services, we can offer additional information that relates to your previous search. Plugins on and off LinkedIn We use cookies and similar technologies to enable LinkedIn plugins both on and off the LinkedIn sites. For example, our plugins, including the "Apply with LinkedIn" button or the "Share" button may be found on LinkedIn or third-party sites, such as the sites of our customers and partners. Our plugins use cookies and other technologies to provide analytics and recognize you on LinkedIn and third-party sites. If you interact with a plugin (for instance, by clicking "Apply"), the plugin will use cookies to identify you and initiate your request to apply. You can learn more about plugins in our Privacy Policy . Advertising Cookies and similar technologies help us show relevant advertising to you more effectively, both on and off our Services and to measure the performance of such ads. We use these technologies to learn whether content has been shown to you or whether someone who was presented with an ad later came back and took an action (e.g., downloaded a white paper or made a purchase) on another site. Similarly, our partners or service providers may use these technologies to determine whether we've shown an ad or a post and how it performed or provide us with information about how you interact with ads. We may also work with our customers and partners to show you an ad on or off LinkedIn, such as after you’ve visited a customer’s or partner’s site or application. These technologies help us provide aggregated information to our customers and partners. For further information regarding the use of cookies for advertising purposes, please see Sections 1.4 and 2.4 of the Privacy Policy . As noted in Section 1.4 of our Privacy Policy, outside Designated Countries , we also collect (or rely on others who collect) information about your device where you have not engaged with our Services (e.g., ad ID, IP address, operating system and browser information) so we can provide our Members with relevant ads and better understand their effectiveness. For further information, please see Section 1.4 of the Privacy Policy . Analytics and research Cookies and similar technologies help us learn more about how well our Services and plugins perform in different locations. We or our service providers use these technologies to understand, improve, and research products, features and services, including as you navigate through our sites or when you access LinkedIn from other sites, applications or devices. We or our service providers, use these technologies to determine and measure the performance of ads or posts on and off LinkedIn and to learn whether you have interacted with our websites, content or emails and provide analytics based on those interactions. We also use these technologies to provide aggregated information to our customers and partners as part of our Services. If you are a LinkedIn member but logged out of your account on a browser, LinkedIn may still continue to log your interaction with our Services on that browser until the expiration of the cookie in order to generate usage analytics for our Services. We may share these analytics in aggregate form with our customers. What third parties use these technologies in connection with our Services? Third parties such as our customers, partners and service providers may use cookies in connection with our Services. For example, third parties may use cookies in their LinkedIn pages, job posts and their advertisements on and off LinkedIn for their own marketing purposes. For an illustration, please visit LinkedIn’s Help Center . Third parties may also use cookies in connection with our off-site Services, such as LinkedIn ad services. Third parties may use cookies to help us to provide our Services. We may also work with third parties for our own marketing purposes and to enable us to analyze and research our Services. Your Choices You have choices on how LinkedIn uses cookies and similar technologies. Please note that if you limit the ability of LinkedIn to set cookies and similar technologies, you may worsen your overall user experience, since it may no longer be personalized to you. It may also stop you from saving customized settings like login information. Opt out of targeted advertising As described in Section 2.4 of the Privacy Policy , you have choices regarding the personalized ads you may see. LinkedIn Members can adjust their settings here . Visitor controls can be found here . Some mobile device operating systems such as Android provide the ability to control the use of mobile advertising IDs for ads personalization. You can learn how to use these controls by visiting the manufacturer’s website. We do not use iOS mobile advertising IDs for targeted advertising. Browser Controls Most browsers allow you to control cookies through their settings, which may be adapted to reflect your consent to the use of cookies. Further, most browsers also enable you to review and erase cookies, including LinkedIn cookies. To learn more about browser controls, please consult the documentation that your browser manufacturer provides. What is Do Not Track (DNT)? DNT is a concept that has been promoted by regulatory agencies such as the U.S. Federal Trade Commission (FTC), for the Internet industry to develop and implement a mechanism for allowing Internet users to control the tracking of their online activities across websites by using browser settings. As such, LinkedIn does not generally respond to “do not track” signals. Other helpful resources To learn more about advertisers’ use of cookies, please visit the following links: Internet Advertising Bureau (US) European Interactive Digital Advertising Alliance (EU) Internet Advertising Bureau (EU) LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/amdocs-techinsights/ | Amdocs TechInsights | LinkedIn Skip to main content LinkedIn Amdocs in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Amdocs TechInsights Business Process Management Software by Amdocs See who's skilled in this Add as skill Learn more Report this product About Enable operational services for mobile network rollouts involving multiple teams and scopes of work Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less Amdocs products Amdocs CatalogONE Amdocs CatalogONE Catalog Management Software Amdocs Customer Engagement Amdocs Customer Engagement Customer Engagement Software Amdocs Freestyle Billing Amdocs Freestyle Billing Billing & Invoicing Software Amdocs Low-Code Experience Platform Amdocs Low-Code Experience Platform Low-Code Development Platforms Amdocs MarketONE Amdocs MarketONE OTT Platforms Amdocs Microservices Management Platform Amdocs Microservices Management Platform Platform as a Service (PaaS) Software Real-Time Billing Real-Time Billing Billing & Invoicing Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/servicenow-now-platform/?trk=products_seo_search | ServiceNow AI Platform | LinkedIn Skip to main content LinkedIn ServiceNow in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in ServiceNow AI Platform Business Process Management Software by ServiceNow See who's skilled in this Add as skill Learn more Report this product About The ServiceNow AI Platform is built for a new era. One platform, ready for anything. Put any AI, any data, any workflow, and any industry to work across the enterprise. Media Products media viewer No more previous content ServiceNow AI Platform ServiceNow AI Platform No more next content Similar products Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less ServiceNow products ServiceNow App Engine ServiceNow App Engine Low-Code Development Platforms LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/categories/business-process-management-software?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_subtitle-click#main-content | Best Business Process Management Software | Products | LinkedIn Skip to main content LinkedIn Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Clear text Used by Used by Chief Executive Officer (36) Operations Manager (25) Information Technology Manager (23) Chief Information Officer (21) Project Manager (18) See all products Find top products in Business Process Management Software category Software used to design, implement, and automate business processes. - View individual or departmental goals in the context of larger company-wide goals - Create scripts and applications to automate and optimize processes - Track and monitor processes across teams 547 results ServiceNow AI Platform Business Process Management Software by ServiceNow The ServiceNow AI Platform is built for a new era. One platform, ready for anything. Put any AI, any data, any workflow, and any industry to work across the enterprise. View product Amdocs TechInsights Business Process Management Software by Amdocs Enable operational services for mobile network rollouts involving multiple teams and scopes of work View product HCL Domino Business Process Management Software by HCLSoftware HCL Domino is an enterprise-grade and secure application development platform designed to solve workflow and process challenges — fast. It powers more than 10 million apps transforming the business of more than 15,000 customers. Domino is more modern and offers more value and lower TCO than ever. Now you can make your apps mobile with zero effort and build new ones 70% faster than before. Domino also provides an enterprise-grade mail, calendar, and contacts platform. The platform is associated with Notes, a professional secure on-premises client which allows users to execute the enterprise applications from their desktop (including the mail client), in a connected or disconnected way. View product Skan AI Process Intelligence Platform Business Process Management Software by Skan AI See how work really happens across your entire organization. Our platform captures complete end-to-end processes across every application and user, creating accurate digital twins that reveal inefficiencies others miss. Move from guesswork to certainty with continuous monitoring that spots issues before they become costly and validates improvements after implementation. Traditional process discovery tools leave you blind. Process mining only sees what's logged in your systems—missing the human work that makes up most of your operations. Task mining captures individual actions but can't stitch them into complete processes. Skan's Process Intelligence observes everything: every application including mainframes and VDI, every click, every handoff, every variation. We deploy in weeks, not months, with zero system integrations required. You get the full picture of how work flows across any operation. View product Business Cockpit Business Process Management Software by T-Systems International Das Business Cockpit ist ein Service, der es ermöglicht, Business Objekte (z.B. Fahrzeuge, Lieferungen) und deren Prozessdurchläufe in Echtzeit graphisch darzustellen und analytisch auszuwerten. Durch ein systemübergreifendes Tracking erkennen Sie schnell Anomalien, können Entscheidungen auf Basis aktueller Fakten treffen und sofort eingreifen. Verringern Sie Prozesskosten und beschleunigen Sie Ihre Abläufe durch gezielte Ursachenanalyse auch von historischen Daten. View product Find products trusted by professionals in your network See which products are used by connections in your network and those that share similar job titles Sign in to view full insights CaseXellence Business Process Management Software by Speridian Technologies Government agencies are in greater need for solutions to streamline processes, communications and workflows in order to manage their caseloads more efficiently. Leveraging decades of Speridian's expertise in developing solutions for the public sector, CaseXellence enables government agencies to take on this challenge and meet the ever-growing demands of public assistance programs. CaseXellence is a low-code intelligent process automation platform that enables public sector enterprises to modernize and transform their legacy infrastructure. CaseXellence has pre-built verticalized solutions designed specifically for public sector automation with security transparency, and traceability at the heart of the platform. View product Decisions Business Process Management Software by Decisions Decisions empowers people to automate everything and be free of inefficient, revenue-draining manual processes. Our no-code, rules-driven process automation platform enables both business and IT departments to unlock growth, increase profitability, and protect their brand. View product ARIS Process Management by Palmira Business Process Management Software by Palmira Software House Business process analysis your way! ARIS is available in different editions to fit the needs of your organization. Looking to start now with minimal investment? ARIS Elements is designed to kickstart your first process improvement project. ARIS Advanced is designed for those who have reached a level of maturity that requires customization and advanced user management. With ARIS Enterprise you can establish a full-scale enterprise BPA program using the complete ARIS capabilities stack. View product Tines Community Edition Business Process Management Software by Tines Discover the power of Tines with a free, fully-featured cloud tenant and generous capacity. Tines is the automation engine for all your workflows. It enables you and your team to automate away manual tasks and create consistency with repeatable and reliable automated processes. With just a few simple building blocks you can rapidly automate a whole host of everyday tasks and workflows. Not only can you create your own agents but you benefit from the ongoing shared contributions of our analysts, engineers, and customers. Whether you leverage our prebuilt blocks or roll your own, it's simple to create actionable and repeatable outcomes that save you time and stress. This frees you up to work on more valuable and creative challenges. Tines is more than just a SoaR(Security Orchestration Automation and Response) platform or API tool, it's an engine that powers a whole range of processes, people, and workflows. View product Marvel.ai - The Business Transformation Engine Business Process Management Software by KGiSL Marvel.ai - The Revolutionary Business Transformation Engine AI-first, cloud-native, and customer experience-centric business transformation engine designed to revolutionize how enterprises across BFSI and all other major industries operate, compete, and thrive in the digital economy. Our platform goes beyond traditional Ai capabilities to deliver intelligent, customer-experience-centric solutions that transform core business processes and reimagine entire operational models. Marvel.ai isn't just another technology platform—it's your partner in reimagining what's possible. Whether you're looking to optimize existing processes, launch new digital initiatives, or completely transform your business model, our business transformation engine provides the foundation for sustainable growth and competitive advantage. View product See more How it works Explore Discover the best product for your need from a growing catalog of 25,000 products and categories trusted by LinkedIn professionals Learn Evaluate new tools, explore trending products in your industry and see who in your network is skilled in the product Grow Join communities of product users to learn best practices, celebrate your progress and accelerate your career LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/n8n/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click | n8n | LinkedIn Skip to main content LinkedIn n8n in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in n8n Workflow Management Software by n8n See who's skilled in this Add as skill Get started Report this product About n8n is a flexible workflow automation tool. With a fair-code distribution model, n8n will always have visible source code, be available to self-host, and allow you to add your own custom functions, logic and integrations. n8n's modular, node-based approach makes it highly versatile, enabling you to connect systems and build powerful AI-infused automations. Media Products media viewer No more previous content Powerful workflow automation tool No more next content Similar products Automation Engine Automation Engine Workflow Management Software Pipefy Pipefy Workflow Management Software Jotform Workflows Jotform Workflows Workflow Management Software TeamViewer Frontline TeamViewer Frontline Workflow Management Software Value Stream Management Value Stream Management Workflow Management Software ApprovalMax ApprovalMax Workflow Management Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/mightybell-mighty-networks?similarProducts=true&trk=products_details_guest_similar_products_section_sign_in#main-content | Mighty Networks | LinkedIn Skip to main content LinkedIn Mighty Networks in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Mighty Networks Enterprise Social Networking Software by Mighty Networks See who's skilled in this Add as skill Try now Report this product About Mighty is where creators, entrepreneurs, and brands build digital communities with cultural software. With content, courses, commerce, and community in one place—under your brand, on every platform. Featured customers of Mighty Networks Tony Robbins Professional Training and Coaching 65,081 followers Hello Seven Professional Training and Coaching 7,217 followers Empify Financial Services 7,037 followers TED Conferences Non-profit Organizations 24,494,928 followers Matthew Hussey / 320 Media Media Production 1,165 followers Yerba Madre Food and Beverage Manufacturing 17,681 followers Crazy Sexy Wellness / kriscarr.com Wellness and Fitness Services 852 followers University of Cambridge Research Services 1,293,210 followers Mindbody Wellness and Fitness Services 228,488 followers This Naked Mind, LLC Wellness and Fitness Services 1,297 followers 143 Studios, LLC Media Production 6,361 followers Hyman Health Hospitals and Health Care 3,216 followers vYve Professional Training and Coaching 1,271 followers KonMari Media, Inc. Online Media 5,031 followers Marie Forleo International E-learning 16,744 followers Keap Software Development 35,555 followers Athletic Brewing Co. Food and Beverage Services 43,400 followers Gupta Program Education 82 followers DEEPAK CHOPRA LLC Artists and Writers 321 followers Whole30 Health, Wellness & Fitness 2,137 followers Civility Media Media Production 415 followers Show more Show less Similar products HCL Connections HCL Connections Enterprise Social Networking Software Circle Circle Enterprise Social Networking Software Lark Lark Enterprise Social Networking Software Meta for Work Meta for Work Enterprise Social Networking Software Krishify Business Suite Krishify Business Suite Enterprise Social Networking Software Network Network Enterprise Social Networking Software Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/company/optimizely?trk=products_details_guest_organization_image | Optimizely | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join for free Optimizely Software Development New York, New York 167,115 followers See jobs Follow View all 1,603 employees Report this company Overview Jobs Life About us Optimizely is on a mission to make the lives of marketers better with Optimizely One, the world’s first operating system for marketing teams. Optimizely One combines industry-leading solutions across content management, content marketing, experimentation, commerce and personalization, powering every stage of the marketing lifecycle through a single, AI-accelerated workflow. With the flexibility of a fully composable platform, Optimizely is proudly helping global brands like Salesforce, Zoom and Toyota create content with speed, launch experiments with confidence, and deliver experiences of the highest quality. Learn more at optimizely.com. Website https://www.optimizely.com External link for Optimizely Industry Software Development Company size 1,001-5,000 employees Headquarters New York, New York Type Privately Held Specialties A/B Testing, Mobile optimization, Conversion Rate Optimization, Split Testing, Customer Experience Optimization, Personalization, Digital experience, CMS, digital commerce, Content Management, Content Marketing, Feature Experimentation, AI, GEO, Web Content Management, Customer Engagement, Marketing Automation, and Agentic Workflows Products No more previous content Optimizely Commerce Optimizely Content Management System Optimizely Content Marketing Platform, Content Marketing Software Optimizely Content Marketing Platform Content Marketing Software Optimizely Data Platform, Customer Data Platforms (CDP) Optimizely Data Platform Customer Data Platforms (CDP) Optimizely Feature Experimentation Optimizely One, Digital Experience Platforms (DXP) Optimizely One Digital Experience Platforms (DXP) Optimizely Web Experimentation, A/B Testing Software Optimizely Web Experimentation A/B Testing Software No more next content Locations Primary 119 5th Ave 7th Floor New York, New York Optimizely, US Get directions Nes 76 Amsterdam, Noord-Holland 1012 KE, NL Get directions 1-2 Hatfields Cargo Works London, SE19PG, GB Get directions 3300 N. Interstate Highway 35 7th Floor Austin, TX 78705, US Get directions Wallstraße 16 Berlin, 10179, DE Get directions No 1 Pacific Highway North Sydney, New South Wales 2060, AU Get directions Al Jaddi Street Dubai Internet City, Building 16 Dubai, AE Get directions Kemal Ataturk Avenue, Plot 58/E 13th Floor Banani 1212 Dhaka, BD Get directions 18 Robinson Road Level 2 Singapore, 048547, SG Get directions 165 Thai Ha Street Song Hong Land Office Building - 7th Floor Hanoi, VN Get directions 729 N Washington Ave Suite 600 Minneapolis, MN 55401, US Get directions 542A Amherst Street (Route 101A) Nashua, NH 03063, US Get directions Torsgatan 11 Stockholm, SE Get directions Hamngatan 16 United Spaces Gothenburg, SE Get directions Adelgatan 21 Malmö, SE Get directions Torggatan 41A Haparanda, 95331, SE Get directions Karenslyst allé 2 Oslo, 0278, NO Get directions Automatikvej 1 Søborg, Capital Region 2860, DK Get directions Eteläesplanadi 2 Helsinki, Uusimaa 00130, FI Get directions Melbourne, AU Get directions Show more locations Show fewer locations Employees at Optimizely Alexander Atzberger Anders Skjønaa Phil Keel Michelle LeBlanc Williams See all employees Updates Optimizely 167,115 followers 19h Report this post What does agility actually look like inside a marketing team? 👀 Hint: it’s not a buzzword — it’s conversations, unblockers, and staying close to the people doing the work. On The Agile Brand with Greg Kihlström® , Optimizely’s SVP of Marketing, Tara Corey , shared her go-to leadership move: regular skip-levels. Because the fastest way to build an agile organization is to understand what’s slowing teams down — and clear those hurdles before they become full-blown roadblocks. And when those blockers disappear... magic happens. Think: launching campaigns at record speed, turning insights into action quickly, and empowering teams to move with confidence instead of friction. Hear more about how Tara keeps her team agile in the full episode: https://lnkd.in/e9nUp9YU …more 13 Like Comment Share Optimizely 167,115 followers 3d Report this post Everyone: “Let’s personalize this page!” Also everyone: creates five versions of the page and hopes for the best 😅 At #Opticon , our very own Michiel Dorjee and Asana 's Mai Tran flipped the script and showed us what successful personalization looks like: 👉 Start with the goal 👉 Optimize for reaching it faster 👉 Remove what doesn’t matter (instead of adding more noise) Because the best personalization? It isn’t creepy. It’s quiet. Watch the full session for more tips on taking your personalization strategy up a notch: https://lnkd.in/eyyU65kN …more 9 Like Comment Share Optimizely reposted this Nick Liemandt 4d Report this post AI has changed how pipeline is created in 2026 so I'm hiring an AI Growth Strategist at Optimizely ! If you enjoy combining AI and pipeline creation, this could be a cool role for you. You’ll design and scale AI-driven workflows alongside our SDRs and shape how AI drives real results for our org. If that sounds like you, please reach out! https://lnkd.in/gZhdeS86 AI Growth Strategist careers.optimizely.com 42 4 Comments Like Comment Share Optimizely 167,115 followers 4d Report this post And the Golden Globe—ahem, Opal Globe—goes to...our amazing customers and partners 🏆✨ This one’s for all the teams pushing digital experiences forward, experimenting boldly, and turning ideas into impact every single day. We see you. We celebrate you. And we can’t wait to see what you do next. Discover how Optimizely Opal empowers award-winning strategies: https://lnkd.in/eZXbhnM4 36 2 Comments Like Comment Share Optimizely reposted this Joey Moore 5d Report this post Such exciting news so I couldn’t wait to share (even though I look terrible, the sound is awful and it meant getting my phone out in public in central London!) …more 79 3 Comments Like Comment Share Optimizely 167,115 followers 4d Report this post Oh, don't mind us, we're just doing some light reading... 📖 Introducing Optimizely’s Big Book of Experimentation, packed with 45+ real-world case studies from brands turning testing into millions in revenue. Every chapter cuts through the guesswork with proven experimentation strategies, warehouse-native analytics, and AI-powered insights—so you’re not just guessing what might work… you’re copying what already did. Big book. Even bigger results. See what’s inside: https://lnkd.in/esfyy5vZ …more 46 Like Comment Share Optimizely 167,115 followers 5d Report this post The Optimizely Opal AI adoption race is officially on, and wow—this one’s a nail-biter. 🥇 Retail sprints ahead at 17.4%, powered by nonstop content demands and hyper-personalized experiences. 🥈 Software (11.8%) and 🥉 Financial Services (9.6%) are right on its heels, keeping the pressure on. 🔥 Business Services (9.1%) isn’t far behind, making it a tight pack at the front. And don’t blink—Healthcare, Education, and Insurance are picking up speed, proving AI-powered marketing isn’t a side quest anymore… it’s the main event. Want to see where your industry lands on the track? Catch the full breakdown in the Opal Benchmark Report: https://lnkd.in/d86ncK4H 37 2 Comments Like Comment Share Optimizely reposted this Ashef Zawad 1w Edited Report this post We’re Hiring: Machine Learning Engineer / Analyst at Optimizely ! We’re looking for an analytical and detail-oriented Machine Learning Engineer / Analyst to join our team. In this role, you’ll build scalable machine learning applications and bridge the gap between technical data science work and actionable business strategy. What We’re Looking For: ✅ 3+ years of hands-on experience building machine learning models and pipelines ✅ Working knowledge of one or more SQL databases (Snowflake, PostgreSQL, etc.) ✅ Proficiency in one or more programming languages or packages (Python, Java, etc.) ✅ Strong understanding of ML fundamentals (regression, classification, forecasting) ✅ Experience with Power BI, Tableau, or Python data visualization libraries ✅ Excellent communication, problem-solving, and stakeholder management skills Nice to Have: ➕ Experience with cloud platforms (AWS, GCP, or Azure) ➕ Exposure to LLMs and tools like Streamlit ➕ Knowledge of NLP (Natural Language Processing) or deep learning frameworks (PyTorch, TensorFlow) 📍 Location: Dhaka, Bangladesh 🕑 Work Hours: 2:00 PM – 10:00 PM (Sunday–Thursday) If this sounds like you or someone you’d like to refer, check out the full job description and apply here: https://lnkd.in/gJQi6yd8 Sajjad Ahmed Niloy #HiringNow #TechCareers #Optimizely #SaaS Machine Learning Engineer/Analyst careers.optimizely.com 30 3 Comments Like Comment Share Optimizely 167,115 followers 6d Report this post Current mood for marketers: Overloaded. Overdue. Over it. 😩 Endless tabs, looming deadlines… we get it. Marketing can feel chaotic. What if getting sh*t done didn’t have to? With AI agents, it doesn’t. Imagine: ✅ Quality content, at scale ✅ Compliance built in ✅ Insights when you need them See how AI agents are transforming real marketing workflows during our virtual event, Agents in Action. Join us on March 4, where human creativity meets infinite possibility. Register today: https://lnkd.in/eyh65SQg …more 41 1 Comment Like Comment Share Optimizely 167,115 followers 1w Report this post Ever feel like your content is yelling at AI: “Pick me! Cite me! Love me!” 😅 You’re not alone — but here’s the truth: in the world of LLMs, copying what already exists won’t earn you visibility or credibility. AI doesn’t reward repetition. It rewards original thinking, factual depth, and real signals of authority. In this video, our very own Michiel Dorjee breaks down why originality beats repetition every time, how brands can earn AI trust (and citations), and the fastest way to check whether AI actually sees you. Watch below!👇 And if you’re ready to stop getting ghosted by robots and start showing up where it matters, see how Optimizely can help: https://lnkd.in/eg9tq45q …more 13 1 Comment Like Comment Share Join now to see what you are missing Find people you know at Optimizely Browse recommended jobs for you View all updates, news, and articles Join now Similar pages Brain Station 23 Software Development Springfield, VA NEXT Ventures Consumer Services Vivasoft Limited Software Development Dhaka, Banani Grameenphone Ltd Telecommunications SELISE Group IT Services and IT Consulting Zürich, Zürich Enosis Solutions Software Development Therap (BD) Ltd. IT Services and IT Consulting Dhaka, Banani Ollyo Software Development Gamma Software Development Field Nation Software Development Minneapolis, Minnesota Show more similar pages Show fewer similar pages Browse jobs Optimizely jobs 1,127 open jobs Analyst jobs 694,057 open jobs Manager jobs 1,880,925 open jobs Engineer jobs 555,845 open jobs Project Manager jobs 253,048 open jobs Developer jobs 258,935 open jobs Intern jobs 71,196 open jobs Account Executive jobs 71,457 open jobs Account Manager jobs 121,519 open jobs Marketing Manager jobs 106,879 open jobs Enterprise Account Executive jobs 44,389 open jobs Director jobs 1,220,357 open jobs Consultant jobs 760,907 open jobs Product Manager jobs 199,941 open jobs Executive jobs 690,514 open jobs Associate jobs 1,091,945 open jobs Senior Software Engineer jobs 78,145 open jobs Customer Success Manager jobs 112,728 open jobs Business Development Representative jobs 52,084 open jobs Scientist jobs 48,969 open jobs Show more jobs like this Show fewer jobs like this Funding Optimizely 10 total rounds Last Round Debt financing Jan 5, 2025 External Crunchbase Link for last round of funding US$ 1.1B Investors Golub Capital See more info on crunchbase More searches More searches Optimizely jobs Engineer jobs Manager jobs Analyst jobs Account Executive jobs Developer jobs Project Manager jobs Account Manager jobs Associate jobs Director jobs Product Manager jobs Enterprise Account Executive jobs Scientist jobs Marketing Manager jobs Senior Software Engineer jobs Intern jobs Machine Learning Engineer jobs Head jobs Sales Manager jobs Business Development Representative jobs Software Engineer jobs Customer Success Manager jobs Business Development Specialist jobs Partner jobs Vice President jobs Sales Director jobs Executive jobs Senior Product Manager jobs Senior Manager jobs Consultant jobs Specialist jobs Marketing Specialist jobs Key Account Manager jobs Associate Product Manager jobs Tester jobs Director of Product Management jobs Full Stack Engineer jobs Solutions Architect jobs Enterprise Account Manager jobs Data Scientist jobs Solutions Engineer jobs Writer jobs Cyber Security Specialist jobs Lead jobs Client Partner jobs President jobs Public Relations Specialist jobs Recruiter jobs Digital Marketing Manager jobs Software Quality Assurance Engineer jobs Site Reliability Engineer jobs User Experience Designer jobs Solutions Manager jobs Marketing Director jobs Head of Sales jobs Data Analyst jobs Administrator jobs Head of Marketing jobs Technical Producer jobs Director of Support jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Optimizely Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/oxygen-forensic-oxygen-forensic%C2%AE-detective/?trk=products_seo_search | Oxygen Forensic® Detective | LinkedIn Skip to main content LinkedIn Oxygen Forensics in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Oxygen Forensic® Detective Digital Forensics Software by Oxygen Forensics See who's skilled in this Add as skill Learn more Report this product About Oxygen Forensic® Detective extracts data quickly and completely from the full digital landscape and facilitates deep analysis and flexible reporting in a single platform. Similar products Kaspersky Digital Footprint Intelligence Kaspersky Digital Footprint Intelligence Digital Forensics Software Argus Argus Digital Forensics Software Regula Forensic Studio Regula Forensic Studio Digital Forensics Software Oxygen Remote Explorer Oxygen Remote Explorer Digital Forensics Software Odyssey Odyssey Digital Forensics Software MOBILedit Forensic MOBILedit Forensic Digital Forensics Software Sign in to see more Show more Show less Oxygen Forensics products Oxygen Remote Explorer Oxygen Remote Explorer Digital Forensics Software Oxygen Review Center Oxygen Review Center Digital Forensics Software LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Fblock-storage-software&trk=products_seo_search_nav-header-join | Sign Up | LinkedIn Make the most of your professional life Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Keep me logged in First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/tencentglobal-simple-email-service-ses/ | Simple Email Service (SES) | LinkedIn Skip to main content LinkedIn Tencent in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Simple Email Service (SES) Email Marketing Software by Tencent See who's skilled in this Add as skill Learn more Report this product About A secure, stable and simple email push service Similar products Square Marketing Square Marketing Email Marketing Software Email Email Email Marketing Software lemlist lemlist Email Marketing Software Everest Everest Email Marketing Software Litmus Litmus Email Marketing Software Kasplo Email Marketing Kasplo Email Marketing Email Marketing Software Sign in to see more Show more Show less Tencent products Cloud Native Database TDSQL-C Cloud Native Database TDSQL-C Relational Database Management Systems Cloud Object Storage (COS) Cloud Object Storage (COS) Object Storage Software Cloud Virtual Machine (CVM) Cloud Virtual Machine (CVM) Server Virtualization Software Tencent Cloud Automation Tools Tencent Cloud Automation Tools Build Automation Tools Tencent Cloud Block Storage Tencent Cloud Block Storage Block Storage Software Tencent Cloud Instant Messaging (IM) Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Tencent Cloud Lighthouse Tencent Cloud Lighthouse Enterprise Cloud Platforms Tencent Effect SDK Tencent Effect SDK Software Development Kits (SDK) Tencent Real-Time Communication (TRTC) Tencent Real-Time Communication (TRTC) Live Streaming Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Fdigital-forensics-software&fromSignIn=true&trk=products_seo_search_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2Fdigitaleconomycouncil&trk=organization_guest_nav-header-join | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Follow top companies Over 60% of the fortune 100 companies use LinkedIn to hire. Join now Leave | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/salesforce-slack/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_full-click | Slack | LinkedIn Skip to main content LinkedIn Salesforce in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Slack Cloud Communications Platforms by Salesforce See who's skilled in this Add as skill Learn more Report this product About Slack is your work operating system. Slack is where humans with agents meet data, workflows, and apps to deliver big results, right where people love to work. Similar products Tencent Cloud Instant Messaging (IM) Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Avaya Cloud Office Avaya Cloud Office Cloud Communications Platforms MessageBird MessageBird Cloud Communications Platforms Vonage Communications APIs Vonage Communications APIs Cloud Communications Platforms CPaaS CPaaS Cloud Communications Platforms Channelize.io: Live Stream Shopping Platform Channelize.io: Live Stream Shopping Platform Cloud Communications Platforms Sign in to see more Show more Show less Salesforce products Agentforce Agentforce Commerce Cloud Commerce Cloud E-Commerce Platforms Data Cloud Data Cloud Customer Data Platforms (CDP) Marketing Cloud Marketing Cloud Marketing Automation Software Net Zero Cloud Net Zero Cloud Data Management Platforms (DMP) Sales Cloud Sales Cloud Customer Relationship Management (CRM) Software Salesforce CRM Salesforce CRM Customer Data Platforms (CDP) Salesforce Platform Salesforce Platform Low-Code Development Platforms Tableau Tableau Business Intelligence (BI) Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://scholar.google.com/citations?user=47vggZsAAAAJ&hl=ko&oe=ASCII | Jing (Selena) He - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 모두 보기 전체 2021년 이후 서지정보 2324 1063 h-index 25 14 i10-index 54 24 0 240 120 60 180 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 8 7 19 47 97 79 131 125 141 148 201 214 225 223 214 195 194 10 공개 액세스 모두 보기 모두 보기 자료 17개 자료 7개 공개 비공개 재정 지원 요구사항 기준 공동 저자 모두 보기 Shouling Ji Professor, Zhejiang University & Georgia Institute of Technology gatech.edu의 이메일 확인됨 Meng Han Intelligence Fusion Research Center （IFRC） zju.edu.cn의 이메일 확인됨 Yi Pan Shenzhen University of Advanced Technology, China cs.gsu.edu의 이메일 확인됨 Yingshu Li Professor, Georgia State University gsu.edu의 이메일 확인됨 Raheem Beyah Dean and Southern Company Chair, Georgia Tech College of Engineering ece.gatech.edu의 이메일 확인됨 Ying Xie Kennesaw State University kennesaw.edu의 이메일 확인됨 Zhipeng Cai Professor, IEEE Fellow, DMACM, Georgia State University cs.gsu.edu의 이메일 확인됨 Mingyuan Yan Assistant Professor, University of North Georgia ung.edu의 이메일 확인됨 Weiqing Li Georgia Institute of Technology gatech.edu의 이메일 확인됨 Mudhakar Srivatsa Research Scientist of Computer Science, IBM T. J. Watson Research Center us.ibm.com의 이메일 확인됨 Amir Atabekov Kennesaw State University valdosta.edu의 이메일 확인됨 Yiyun Zhou National Board of Medical Examiners nbme.org의 이메일 확인됨 Anu G. Bourgeois Georgia State University cs.gsu.edu의 이메일 확인됨 Tianyu Du Zhejiang University zju.edu.cn의 이메일 확인됨 Yanqing Zhang Professor of Computer Science, Georgia State University gsu.edu의 이메일 확인됨 Pingzhi Fan (范平志) Southwest Jiaotong University (西南交通大学) swjtu.edu.cn의 이메일 확인됨 Ai Chunyu University of South Carolina Upstate uscupstate.edu의 이메일 확인됨 Selcuk Uluagac Florida International University fiu.edu의 이메일 확인됨 Xavier Defago Professor of Computer Science at Institute of Science Tokyo comp.isct.ac.jp의 이메일 확인됨 Samee U. Khan Kansas State University ksu.edu의 이메일 확인됨 모두 보기 팔로우 Jing (Selena) He Professor, Department of Computer Science, Kennesaw State University kennesaw.edu의 이메일 확인됨 - 홈페이지 Wireless Network and Mobile Computing Social Networking Big Data Analysis on Clouds Internet of 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 A novel blockchain-based education records verification solution M Han, Z Li, J He, D Wu, Y Xie, A Baba Proceedings of the 19th annual SIG conference on information technology�… , 2018 245 2018 Integrating Internet of Things (IoT) into STEM undergraduate education: Case study of a modern technology infused courseware for embedded system course J He, DCT Lo, Y Xie, J Lartigue 2016 IEEE frontiers in education conference (FIE), 1-9 , 2016 169 2016 Deep learning approach for cyberattack detection Y Zhou, M Han, L Liu, JS He, Y Wang IEEE infocom 2018-ieee conference on computer communications workshops�… , 2018 143 2018 Clinical efficacy of a specifically targeted antimicrobial peptide mouth rinse: targeted elimination of Streptococcus mutans and prevention of demineralization R Sullivan, P Santarpia, S Lavender, E Gittins, Z Liu, MH Anderson, J He, ... Caries research 45 (5), 415-428 , 2011 106 2011 Structure based data de-anonymization of social networks and mobility traces S Ji, W Li, M Srivatsa, JS He, R Beyah International Conference on Information Security, 237-254 , 2014 77 2014 Constructing load-balanced data aggregation trees in probabilistic wireless sensor networks J He, S Ji, Y Pan, Y Li IEEE Transactions on Parallel and Distributed Systems 25 (7), 1681-1690 , 2013 75 2013 Optimal distributed data collection for asynchronous cognitive radio networks Z Cai, S Ji, J He, AG Bourgeois 2012 IEEE 32nd international conference on distributed computing systems�… , 2012 69 2012 Security in fog computing through encryption A Vishwanath, R Peruri, Jing (Selena) He DigitalCommons@ Kennesaw State University , 2016 67 2016 Distributed and Asynchronous Data Collection in Cognitive Radio Networks with Fairness Consideration Z Cai, S Ji, J He, L Wei, AG Bourgeois IEEE , 2012 56 2012 Approximation algorithms for load-balanced virtual backbone construction in wireless sensor networks JS He, S Ji, Y Pan, Z Cai Theoretical Computer Science 507, 2-16 , 2013 54 2013 General graph data de-anonymization: From mobility traces to social networks S Ji, W Li, M Srivatsa, JS He, R Beyah ACM Transactions on Information and System Security (TISSEC) 18 (4), 1-29 , 2016 47 2016 Load–balanced CDS construction in wireless sensor networks via genetic algorithm J He, S Ji, M Yan, Y Pan, Y Li International Journal of Sensor Networks 11 (3), 166-178 , 2012 40 2012 Integrating blockchain technology into healthcare JD Vyas, M Han, L Li, S Pouriyeh, JS He proceedings of the 2020 ACM southeast conference, 197-203 , 2020 39 2020 Constructing a load-balanced virtual backbone in wireless sensor networks J He, S Ji, P Fan, Y Pan, Y Li 2012 International Conference on Computing, Networking and Communications�… , 2012 38 2012 Internet of things (iot)-based learning framework to facilitate stem undergraduate education JS He, S Ji, PO Bobbie Proceedings of the 2017 ACM Southeast Conference, 88-94 , 2017 37 2017 A survey on decentralized flocking schemes for a set of autonomous mobile robots N Xiong, J He, Y Yang, Y He, T Kim, C Lin J. Commun. 5 (1), 31-38 , 2010 36 2010 A survey on fault-tolerance in distributed network systems N Xiong, Y Yang, M Cao, J He, L Shu 2009 International Conference on Computational Science and Engineering 2�… , 2009 36 2009 Minimum-sized influential node set selection for social networks under the independent cascade model J He, S Ji, R Beyah, Z Cai Proceedings of the 15th ACM International Symposium on Mobile ad hoc�… , 2014 35 2014 Spreading social influence with both positive and negative opinions in online networks JS He, M Han, S Ji, T Du, Z Li Big Data Mining and Analytics 2 (2), 100-117 , 2019 34 2019 Data-driven approaches in FinTech: a survey X Tian, JS He, M Han Information Discovery and Delivery 49 (2), 123-135 , 2021 33 2021 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:17 |
https://rust-lang.github.io/rust-clippy/stable/index.html#await_holding_invalid_type | Clippy Lints Theme Ayu Coal Light Navy Rust Disable keyboard shortcuts Clippy Lints Total number: 795 Lints search and filtering only works with JS enabled. :( Lint levels 4 All None Lint groups 9 All Default None Version 0 Clear filters Applicability 4 All None Filter: Clear absolute_paths ¶ 📋 restriction allow What it does Checks for usage of items through absolute paths, like std::env::current_dir . Why restrict this? Many codebases have their own style when it comes to importing, but one that is seldom used is using absolute paths everywhere . This is generally considered unidiomatic, and you should add a use statement. The default maximum segments (2) is pretty strict, you may want to increase this in clippy.toml . Note: One exception to this is code from macro expansion - this does not lint such cases, as using absolute paths is the proper way of referencing items in one. Known issues There are currently a few cases which are not caught by this lint: Macro calls. e.g. path::to::macro!() Derive macros. e.g. #[derive(path::to::macro)] Attribute macros. e.g. #[path::to::macro] Example let x = std::f64::consts::PI; Use any of the below instead, or anything else: use std::f64; use std::f64::consts; use std::f64::consts::PI; let x = f64::consts::PI; let x = consts::PI; let x = PI; use std::f64::consts as f64_consts; let x = f64_consts::PI; Configuration absolute-paths-allowed-crates : Which crates to allow absolute paths from (default: [] ) absolute-paths-max-segments : The maximum number of segments a path can have before being linted, anything above this will be linted. (default: 2 ) Applicability: Unspecified (?) Added in: 1.73.0 Related Issues View Source absurd_extreme_comparisons ¶ 📋 correctness deny What it does Checks for comparisons where one side of the relation is either the minimum or maximum value for its type and warns if it involves a case that is always true or always false. Only integer and boolean types are checked. Why is this bad? An expression like min <= x may misleadingly imply that it is possible for x to be less than the minimum. Expressions like max < x are probably mistakes. Known problems For usize the size of the current compile target will be assumed (e.g., 64 bits on 64 bit systems). This means code that uses such a comparison to detect target pointer width will trigger this lint. One can use mem::sizeof and compare its value or conditional compilation attributes like #[cfg(target_pointer_width = "64")] .. instead. Example let vec: Vec<isize> = Vec::new(); if vec.len() <= 0 {} if 100 > i32::MAX {} Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source alloc_instead_of_core ¶ 📋 restriction allow What it does Finds items imported through alloc when available through core . Why restrict this? Crates which have no_std compatibility and may optionally require alloc may wish to ensure types are imported from core to ensure disabling alloc does not cause the crate to fail to compile. This lint is also useful for crates migrating to become no_std compatible. Known problems The lint is only partially aware of the required MSRV for items that were originally in std but moved to core . Example use alloc::slice::from_ref; Use instead: use core::slice::from_ref; Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source allow_attributes ¶ 📋 restriction allow What it does Checks for usage of the #[allow] attribute and suggests replacing it with the #[expect] attribute (See RFC 2383 ) This lint only warns outer attributes ( #[allow] ), as inner attributes ( #![allow] ) are usually used to enable or disable lints on a global scale. Why is this bad? #[expect] attributes suppress the lint emission, but emit a warning, if the expectation is unfulfilled. This can be useful to be notified when the lint is no longer triggered. Example #[allow(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Use instead: #[expect(unused_mut)] fn foo() -> usize { let mut a = Vec::new(); a.len() } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.70.0 Related Issues View Source allow_attributes_without_reason ¶ 📋 restriction allow What it does Checks for attributes that allow lints without a reason. Why restrict this? Justifying each allow helps readers understand the reasoning, and may allow removing allow attributes if their purpose is obsolete. Example #![allow(clippy::some_lint)] Use instead: #![allow(clippy::some_lint, reason = "False positive rust-lang/rust-clippy#1002020")] Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source almost_complete_range ¶ 📋 suspicious warn What it does Checks for ranges which almost include the entire range of letters from ‘a’ to ‘z’ or digits from ‘0’ to ‘9’, but don’t because they’re a half open range. Why is this bad? This ( 'a'..'z' ) is almost certainly a typo meant to include all letters. Example let _ = 'a'..'z'; Use instead: let _ = 'a'..='z'; Past names almost_complete_letter_range Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MaybeIncorrect (?) Added in: 1.68.0 Related Issues View Source almost_swapped ¶ 📋 correctness deny What it does Checks for foo = bar; bar = foo sequences. Why is this bad? This looks like a failed attempt to swap. Example a = b; b = a; If swapping is intended, use swap() instead: std::mem::swap(&mut a, &mut b); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source approx_constant ¶ 📋 correctness deny What it does Checks for floating point literals that approximate constants which are defined in std::f32::consts or std::f64::consts , respectively, suggesting to use the predefined constant. Why is this bad? Usually, the definition in the standard library is more precise than what people come up with. If you find that your definition is actually more precise, please file a Rust issue . Example let x = 3.14; let y = 1_f64 / x; Use instead: let x = std::f32::consts::PI; let y = std::f64::consts::FRAC_1_PI; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source arbitrary_source_item_ordering ¶ 📋 restriction allow What it does Confirms that items are sorted in source files as per configuration. Why restrict this? Keeping a consistent ordering throughout the codebase helps with working as a team, and possibly improves maintainability of the codebase. The idea is that by defining a consistent and enforceable rule for how source files are structured, less time will be wasted during reviews on a topic that is (under most circumstances) not relevant to the logic implemented in the code. Sometimes this will be referred to as “bikeshedding”. The content of items with a representation clause attribute, such as #[repr(C)] will not be checked, as the order of their fields or variants might be dictated by an external API (application binary interface). Default Ordering and Configuration As there is no generally applicable rule, and each project may have different requirements, the lint can be configured with high granularity. The configuration is split into two stages: Which item kinds that should have an internal order enforced. Individual ordering rules per item kind. The item kinds that can be linted are: Module (with customized groupings, alphabetical within - configurable) Trait (with customized order of associated items, alphabetical within) Enum, Impl, Struct (purely alphabetical) Module Item Order Due to the large variation of items within modules, the ordering can be configured on a very granular level. Item kinds can be grouped together arbitrarily, items within groups will be ordered alphabetically. The following table shows the default groupings: Group Item Kinds modules “mod”, “foreign_mod” use “use” macros “macro” global_asm “global_asm” UPPER_SNAKE_CASE “static”, “const” PascalCase “ty_alias”, “opaque_ty”, “enum”, “struct”, “union”, “trait”, “trait_alias”, “impl” lower_snake_case “fn” The groups’ names are arbitrary and can be changed to suit the conventions that should be enforced for a specific project. All item kinds must be accounted for to create an enforceable linting rule set. Following are some example configurations that may be useful. Example: module inclusions and use statements to be at the top module-item-order-groupings = [ [ "modules", [ "extern_crate", "mod", "foreign_mod" ], ], [ "use", [ "use", ], ], [ "everything_else", [ "macro", "global_asm", "static", "const", "ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl", "fn", ], ], ] Example: only consts and statics should be alphabetically ordered It is also possible to configure a selection of module item groups that should be ordered alphabetically. This may be useful if for example statics and consts should be ordered, but the rest should be left open. module-items-ordered-within-groupings = ["UPPER_SNAKE_CASE"] Known Problems Performance Impact Keep in mind, that ordering source code alphabetically can lead to reduced performance in cases where the most commonly used enum variant isn’t the first entry anymore, and similar optimizations that can reduce branch misses, cache locality and such. Either don’t use this lint if that’s relevant, or disable the lint in modules or items specifically where it matters. Other solutions can be to use profile guided optimization (PGO), post-link optimization (e.g. using BOLT for LLVM), or other advanced optimization methods. A good starting point to dig into optimization is cargo-pgo . Lints on a Contains basis The lint can be disabled only on a “contains” basis, but not per element within a “container”, e.g. the lint works per-module, per-struct, per-enum, etc. but not for “don’t order this particular enum variant”. Module documentation Module level rustdoc comments are not part of the resulting syntax tree and as such cannot be linted from within check_mod . Instead, the rustdoc::missing_documentation lint may be used. Module Tests This lint does not implement detection of module tests (or other feature dependent elements for that matter). To lint the location of mod tests, the lint items_after_test_module can be used instead. Example trait TraitUnordered { const A: bool; const C: bool; const B: bool; type SomeType; fn a(); fn c(); fn b(); } Use instead: trait TraitOrdered { const A: bool; const B: bool; const C: bool; type SomeType; fn a(); fn b(); fn c(); } Configuration module-item-order-groupings : The named groupings of different source item kinds within modules. (default: [["modules", ["extern_crate", "mod", "foreign_mod"]], ["use", ["use"]], ["macros", ["macro"]], ["global_asm", ["global_asm"]], ["UPPER_SNAKE_CASE", ["static", "const"]], ["PascalCase", ["ty_alias", "enum", "struct", "union", "trait", "trait_alias", "impl"]], ["lower_snake_case", ["fn"]]] ) module-items-ordered-within-groupings : Whether the items within module groups should be ordered alphabetically or not. This option can be configured to “all”, “none”, or a list of specific grouping names that should be checked (e.g. only “enums”). (default: "none" ) source-item-ordering : Which kind of elements should be ordered internally, possible values being enum , impl , module , struct , trait . (default: ["enum", "impl", "module", "struct", "trait"] ) trait-assoc-item-kinds-order : The order of associated items in traits. (default: ["const", "type", "fn"] ) Applicability: Unspecified (?) Added in: 1.84.0 Related Issues View Source arc_with_non_send_sync ¶ 📋 suspicious warn What it does. This lint warns when you use Arc with a type that does not implement Send or Sync . Why is this bad? Arc<T> is a thread-safe Rc<T> and guarantees that updates to the reference counter use atomic operations. To send an Arc<T> across thread boundaries and share ownership between multiple threads, T must be both Send and Sync , so either T should be made Send + Sync or an Rc should be used instead of an Arc . Example fn main() { // This is fine, as `i32` implements `Send` and `Sync`. let a = Arc::new(42); // `RefCell` is `!Sync`, so either the `Arc` should be replaced with an `Rc` // or the `RefCell` replaced with something like a `RwLock` let b = Arc::new(RefCell::new(42)); } Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source arithmetic_side_effects ¶ 📋 restriction allow What it does Checks any kind of arithmetic operation of any type. Operators like + , - , * or << are usually capable of overflowing according to the Rust Reference , or can panic ( / , % ). Known safe built-in types like Wrapping or Saturating , floats, operations in constant environments, allowed types and non-constant operations that won’t overflow are ignored. Why restrict this? For integers, overflow will trigger a panic in debug builds or wrap the result in release mode; division by zero will cause a panic in either mode. As a result, it is desirable to explicitly call checked, wrapping or saturating arithmetic methods. Example // `n` can be any number, including `i32::MAX`. fn foo(n: i32) -> i32 { n + 1 } Third-party types can also overflow or present unwanted side-effects. Example use rust_decimal::Decimal; let _n = Decimal::MAX + Decimal::MAX; Past names integer_arithmetic Configuration arithmetic-side-effects-allowed : Suppress checking of the passed type names in all types of operations. If a specific operation is desired, consider using arithmetic_side_effects_allowed_binary or arithmetic_side_effects_allowed_unary instead. Example arithmetic-side-effects-allowed = ["SomeType", "AnotherType"] Noteworthy A type, say SomeType , listed in this configuration has the same behavior of ["SomeType" , "*"], ["*", "SomeType"] in arithmetic_side_effects_allowed_binary . (default: [] ) arithmetic-side-effects-allowed-binary : Suppress checking of the passed type pair names in binary operations like addition or multiplication. Supports the “*” wildcard to indicate that a certain type won’t trigger the lint regardless of the involved counterpart. For example, ["SomeType", "*"] or ["*", "AnotherType"] . Pairs are asymmetric, which means that ["SomeType", "AnotherType"] is not the same as ["AnotherType", "SomeType"] . Example arithmetic-side-effects-allowed-binary = [["SomeType" , "f32"], ["AnotherType", "*"]] (default: [] ) arithmetic-side-effects-allowed-unary : Suppress checking of the passed type names in unary operations like “negation” ( - ). Example arithmetic-side-effects-allowed-unary = ["SomeType", "AnotherType"] (default: [] ) Applicability: Unspecified (?) Added in: 1.64.0 Related Issues View Source as_conversions ¶ 📋 restriction allow What it does Checks for usage of as conversions. Note that this lint is specialized in linting every single use of as regardless of whether good alternatives exist or not. If you want more precise lints for as , please consider using these separate lints: clippy::cast_lossless clippy::cast_possible_truncation clippy::cast_possible_wrap clippy::cast_precision_loss clippy::cast_sign_loss clippy::char_lit_as_u8 clippy::fn_to_numeric_cast clippy::fn_to_numeric_cast_with_truncation clippy::ptr_as_ptr clippy::unnecessary_cast invalid_reference_casting There is a good explanation the reason why this lint should work in this way and how it is useful in this issue . Why restrict this? as conversions will perform many kinds of conversions, including silently lossy conversions and dangerous coercions. There are cases when it makes sense to use as , so the lint is Allow by default. Example let a: u32; ... f(a as u16); Use instead: f(a.try_into()?); // or f(a.try_into().expect("Unexpected u16 overflow in f")); Applicability: Unspecified (?) Added in: 1.41.0 Related Issues View Source as_pointer_underscore ¶ 📋 restriction allow What it does Checks for the usage of as *const _ or as *mut _ conversion using inferred type. Why restrict this? The conversion might include a dangerous cast that might go undetected due to the type being inferred. Example fn as_usize<T>(t: &T) -> usize { // BUG: `t` is already a reference, so we will here // return a dangling pointer to a temporary value instead &t as *const _ as usize } Use instead: fn as_usize<T>(t: &T) -> usize { t as *const T as usize } Applicability: MachineApplicable (?) Added in: 1.85.0 Related Issues View Source as_ptr_cast_mut ¶ 📋 nursery allow What it does Checks for the result of a &self -taking as_ptr being cast to a mutable pointer. Why is this bad? Since as_ptr takes a &self , the pointer won’t have write permissions unless interior mutability is used, making it unlikely that having it as a mutable pointer is correct. Example let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_ptr() as *mut u8; unsafe { ptr.write(4) }; // UNDEFINED BEHAVIOUR Use instead: let mut vec = Vec::<u8>::with_capacity(1); let ptr = vec.as_mut_ptr(); unsafe { ptr.write(4) }; Applicability: MaybeIncorrect (?) Added in: 1.66.0 Related Issues View Source as_underscore ¶ 📋 restriction allow What it does Checks for the usage of as _ conversion using inferred type. Why restrict this? The conversion might include lossy conversion or a dangerous cast that might go undetected due to the type being inferred. The lint is allowed by default as using _ is less wordy than always specifying the type. Example fn foo(n: usize) {} let n: u16 = 256; foo(n as _); Use instead: fn foo(n: usize) {} let n: u16 = 256; foo(n as usize); Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source assertions_on_constants ¶ 📋 style warn What it does Checks for assert!(true) and assert!(false) calls. Why is this bad? Will be optimized out by the compiler or should probably be replaced by a panic!() or unreachable!() Example assert!(false) assert!(true) const B: bool = false; assert!(B) Applicability: Unspecified (?) Added in: 1.34.0 Related Issues View Source assertions_on_result_states ¶ 📋 restriction allow What it does Checks for assert!(r.is_ok()) or assert!(r.is_err()) calls. Why restrict this? This form of assertion does not show any of the information present in the Result other than which variant it isn’t. Known problems The suggested replacement decreases the readability of code and log output. Example assert!(r.is_ok()); assert!(r.is_err()); Use instead: r.unwrap(); r.unwrap_err(); Applicability: MachineApplicable (?) Added in: 1.64.0 Related Issues View Source assign_op_pattern ¶ 📋 style warn What it does Checks for a = a op b or a = b commutative_op a patterns. Why is this bad? These can be written as the shorter a op= b . Known problems While forbidden by the spec, OpAssign traits may have implementations that differ from the regular Op impl. Example let mut a = 5; let b = 0; // ... a = a + b; Use instead: let mut a = 5; let b = 0; // ... a += b; Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source assign_ops ¶ 📋 deprecated none What it does Nothing. This lint has been deprecated Deprecation reason Compound operators are harmless and linting on them is not in scope for clippy. Applicability: Unspecified (?) Deprecated in: 1.30.0 Related Issues assigning_clones ¶ 📋 pedantic allow What it does Checks for code like foo = bar.clone(); Why is this bad? Custom Clone::clone_from() or ToOwned::clone_into implementations allow the objects to share resources and therefore avoid allocations. Example struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { *a = b.clone(); } Use instead: struct Thing; impl Clone for Thing { fn clone(&self) -> Self { todo!() } fn clone_from(&mut self, other: &Self) { todo!() } } pub fn assign_to_ref(a: &mut Thing, b: Thing) { a.clone_from(&b); } Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: Unspecified (?) Added in: 1.78.0 Related Issues View Source async_yields_async ¶ 📋 correctness deny What it does Checks for async blocks that yield values of types that can themselves be awaited. Why is this bad? An await is likely missing. Example async fn foo() {} fn bar() { let x = async { foo() }; } Use instead: async fn foo() {} fn bar() { let x = async { foo().await }; } Applicability: MaybeIncorrect (?) Added in: 1.48.0 Related Issues View Source await_holding_invalid_type ¶ 📋 suspicious warn What it does Allows users to configure types which should not be held across await suspension points. Why is this bad? There are some types which are perfectly safe to use concurrently from a memory access perspective, but that will cause bugs at runtime if they are held in such a way. Example await-holding-invalid-types = [ # You can specify a type name "CustomLockType", # You can (optionally) specify a reason { path = "OtherCustomLockType", reason = "Relies on a thread local" } ] struct CustomLockType; struct OtherCustomLockType; async fn foo() { let _x = CustomLockType; let _y = OtherCustomLockType; baz().await; // Lint violation } Configuration await-holding-invalid-types : The list of types which may not be held across an await point. (default: [] ) Applicability: Unspecified (?) Added in: 1.62.0 Related Issues View Source await_holding_lock ¶ 📋 suspicious warn What it does Checks for calls to await while holding a non-async-aware MutexGuard . Why is this bad? The Mutex types found in std::sync and parking_lot are not designed to operate in an async context across await points. There are two potential solutions. One is to use an async-aware Mutex type. Many asynchronous foundation crates provide such a Mutex type. The other solution is to ensure the mutex is unlocked before calling await , either by introducing a scope or an explicit call to Drop::drop . Known problems Will report false positive for explicitly dropped guards ( #6446 ). A workaround for this is to wrap the .lock() call in a block instead of explicitly dropping the guard. Example async fn foo(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; baz().await; } async fn bar(x: &Mutex<u32>) { let mut guard = x.lock().unwrap(); *guard += 1; drop(guard); // explicit drop baz().await; } Use instead: async fn foo(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } baz().await; } async fn bar(x: &Mutex<u32>) { { let mut guard = x.lock().unwrap(); *guard += 1; } // guard dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.45.0 Related Issues View Source await_holding_refcell_ref ¶ 📋 suspicious warn What it does Checks for calls to await while holding a RefCell , Ref , or RefMut . Why is this bad? RefCell refs only check for exclusive mutable access at runtime. Holding a RefCell ref across an await suspension point risks panics from a mutable ref shared while other refs are outstanding. Known problems Will report false positive for explicitly dropped refs ( #6353 ). A workaround for this is to wrap the .borrow[_mut]() call in a block instead of explicitly dropping the ref. Example async fn foo(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; baz().await; } async fn bar(x: &RefCell<u32>) { let mut y = x.borrow_mut(); *y += 1; drop(y); // explicit drop baz().await; } Use instead: async fn foo(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } baz().await; } async fn bar(x: &RefCell<u32>) { { let mut y = x.borrow_mut(); *y += 1; } // y dropped here at end of scope baz().await; } Applicability: Unspecified (?) Added in: 1.49.0 Related Issues View Source bad_bit_mask ¶ 📋 correctness deny What it does Checks for incompatible bit masks in comparisons. The formula for detecting if an expression of the type _ <bit_op> m <cmp_op> c (where <bit_op> is one of { & , | } and <cmp_op> is one of { != , >= , > , != , >= , > }) can be determined from the following table: Comparison Bit Op Example is always Formula == or != & x & 2 == 3 false c & m != c < or >= & x & 2 < 3 true m < c > or <= & x & 1 > 1 false m <= c == or != | x | 1 == 0 false c | m != c < or >= | x | 1 < 1 false m >= c <= or > | x | 1 > 0 true m > c Why is this bad? If the bits that the comparison cares about are always set to zero or one by the bit mask, the comparison is constant true or false (depending on mask, compared value, and operators). So the code is actively misleading, and the only reason someone would write this intentionally is to win an underhanded Rust contest or create a test-case for this lint. Example if (x & 1 == 2) { } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source big_endian_bytes ¶ 📋 restriction allow What it does Checks for the usage of the to_be_bytes method and/or the function from_be_bytes . Why restrict this? To ensure use of little-endian or the target’s endianness rather than big-endian. Example let _x = 2i32.to_be_bytes(); let _y = 2i64.to_be_bytes(); Applicability: Unspecified (?) Added in: 1.72.0 Related Issues View Source bind_instead_of_map ¶ 📋 complexity warn What it does Checks for usage of _.and_then(|x| Some(y)) , _.and_then(|x| Ok(y)) or _.or_else(|x| Err(y)) . Why is this bad? This can be written more concisely as _.map(|x| y) or _.map_err(|x| y) . Example let _ = opt().and_then(|s| Some(s.len())); let _ = res().and_then(|s| if s.len() == 42 { Ok(10) } else { Ok(20) }); let _ = res().or_else(|s| if s.len() == 42 { Err(10) } else { Err(20) }); The correct use would be: let _ = opt().map(|s| s.len()); let _ = res().map(|s| if s.len() == 42 { 10 } else { 20 }); let _ = res().map_err(|s| if s.len() == 42 { 10 } else { 20 }); Past names option_and_then_some Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source blanket_clippy_restriction_lints ¶ 📋 suspicious warn What it does Checks for warn / deny / forbid attributes targeting the whole clippy::restriction category. Why is this bad? Restriction lints sometimes are in contrast with other lints or even go against idiomatic rust. These lints should only be enabled on a lint-by-lint basis and with careful consideration. Example #![deny(clippy::restriction)] Use instead: #![deny(clippy::as_conversions)] Applicability: Unspecified (?) Added in: 1.47.0 Related Issues View Source blocks_in_conditions ¶ 📋 style warn What it does Checks for if and match conditions that use blocks containing an expression, statements or conditions that use closures with blocks. Why is this bad? Style, using blocks in the condition makes it hard to read. Examples if { true } { /* ... */ } if { let x = somefunc(); x } { /* ... */ } match { let e = somefunc(); e } { // ... } Use instead: if true { /* ... */ } let res = { let x = somefunc(); x }; if res { /* ... */ } let res = { let e = somefunc(); e }; match res { // ... } Past names block_in_if_condition_expr block_in_if_condition_stmt blocks_in_if_conditions Applicability: MachineApplicable (?) Added in: 1.45.0 Related Issues View Source bool_assert_comparison ¶ 📋 style warn What it does This lint warns about boolean comparisons in assert-like macros. Why is this bad? It is shorter to use the equivalent. Example assert_eq!("a".is_empty(), false); assert_ne!("a".is_empty(), true); Use instead: assert!(!"a".is_empty()); Applicability: MachineApplicable (?) Added in: 1.53.0 Related Issues View Source bool_comparison ¶ 📋 complexity warn What it does Checks for expressions of the form x == true , x != true and order comparisons such as x < true (or vice versa) and suggest using the variable directly. Why is this bad? Unnecessary code. Example if x == true {} if y == false {} use x directly: if x {} if !y {} Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source bool_to_int_with_if ¶ 📋 pedantic allow What it does Instead of using an if statement to convert a bool to an int, this lint suggests using a from() function or an as coercion. Why is this bad? Coercion or from() is another way to convert bool to a number. Both methods are guaranteed to return 1 for true, and 0 for false. See https://doc.rust-lang.org/std/primitive.bool.html#impl-From%3Cbool%3E Example if condition { 1_i64 } else { 0 }; Use instead: i64::from(condition); or condition as i64; Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source borrow_as_ptr ¶ 📋 pedantic allow What it does Checks for the usage of &expr as *const T or &mut expr as *mut T , and suggest using &raw const or &raw mut instead. Why is this bad? This would improve readability and avoid creating a reference that points to an uninitialized value or unaligned place. Read the &raw explanation in the Reference for more information. Example let val = 1; let p = &val as *const i32; let mut val_mut = 1; let p_mut = &mut val_mut as *mut i32; Use instead: let val = 1; let p = &raw const val; let mut val_mut = 1; let p_mut = &raw mut val_mut; Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.60.0 Related Issues View Source borrow_deref_ref ¶ 📋 complexity warn What it does Checks for &*(&T) . Why is this bad? Dereferencing and then borrowing a reference value has no effect in most cases. Known problems False negative on such code: let x = &12; let addr_x = &x as *const _ as usize; let addr_y = &&*x as *const _ as usize; // assert ok now, and lint triggered. // But if we fix it, assert will fail. assert_ne!(addr_x, addr_y); Example let s = &String::new(); let a: &String = &* s; Use instead: let a: &String = s; Applicability: MachineApplicable (?) Added in: 1.63.0 Related Issues View Source borrow_interior_mutable_const ¶ 📋 style warn What it does Checks for a borrow of a named constant with interior mutability. Why is this bad? Named constants are copied at every use site which means any change to their value will be lost after the newly created value is dropped. e.g. use core::sync::atomic::{AtomicUsize, Ordering}; const ATOMIC: AtomicUsize = AtomicUsize::new(0); fn add_one() -> usize { // This will always return `0` since `ATOMIC` is copied before it's borrowed // for use by `fetch_add`. ATOMIC.fetch_add(1, Ordering::AcqRel) } Known problems This lint does not, and cannot in general, determine if the borrow of the constant is used in a way which causes a mutation. e.g. use core::cell::Cell; const CELL: Cell<usize> = Cell::new(0); fn get_cell() -> Cell<usize> { // This is fine. It borrows a copy of `CELL`, but never mutates it through the // borrow. CELL.clone() } There also exists types which contain private fields with interior mutability, but no way to both create a value as a constant and modify any mutable field using the type’s public interface (e.g. bytes::Bytes ). As there is no reasonable way to scan a crate’s interface to see if this is the case, all such types will be linted. If this happens use the ignore-interior-mutability configuration option to allow the type. Example use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); CONST_ATOM.store(6, SeqCst); // the content of the atomic is unchanged assert_eq!(CONST_ATOM.load(SeqCst), 12); // because the CONST_ATOM in these lines are distinct Use instead: use std::sync::atomic::{AtomicUsize, Ordering::SeqCst}; const CONST_ATOM: AtomicUsize = AtomicUsize::new(12); static STATIC_ATOM: AtomicUsize = CONST_ATOM; STATIC_ATOM.store(9, SeqCst); assert_eq!(STATIC_ATOM.load(SeqCst), 9); // use a `static` item to refer to the same instance Configuration ignore-interior-mutability : A list of paths to types that should be treated as if they do not contain interior mutability (default: ["bytes::Bytes"] ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source borrowed_box ¶ 📋 complexity warn What it does Checks for usage of &Box<T> anywhere in the code. Check the Box documentation for more information. Why is this bad? A &Box<T> parameter requires the function caller to box T first before passing it to a function. Using &T defines a concrete type for the parameter and generalizes the function, this would also auto-deref to &T at the function call site if passed a &Box<T> . Example fn foo(bar: &Box<T>) { ... } Better: fn foo(bar: &T) { ... } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source box_collection ¶ 📋 perf warn What it does Checks for usage of Box<T> where T is a collection such as Vec anywhere in the code. Check the Box documentation for more information. Why is this bad? Collections already keeps their contents in a separate area on the heap. So if you Box them, you just add another level of indirection without any benefit whatsoever. Example struct X { values: Box<Vec<Foo>>, } Better: struct X { values: Vec<Foo>, } Past names box_vec Configuration avoid-breaking-exported-api : Suppress lints whenever the suggested change would cause breakage for other crates. (default: true ) Applicability: Unspecified (?) Added in: 1.57.0 Related Issues View Source box_default ¶ 📋 style warn What it does checks for Box::new(Default::default()) , which can be written as Box::default() . Why is this bad? Box::default() is equivalent and more concise. Example let x: Box<String> = Box::new(Default::default()); Use instead: let x: Box<String> = Box::default(); Applicability: MachineApplicable (?) Added in: 1.66.0 Related Issues View Source boxed_local ¶ 📋 perf warn What it does Checks for usage of Box<T> where an unboxed T would work fine. Why is this bad? This is an unnecessary allocation, and bad for performance. It is only necessary to allocate if you wish to move the box into something. Example fn foo(x: Box<u32>) {} Use instead: fn foo(x: u32) {} Configuration too-large-for-stack : The maximum size of objects (in bytes) that will be linted. Larger objects are ok on the heap (default: 200 ) Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source branches_sharing_code ¶ 📋 nursery allow What it does Checks if the if and else block contain shared code that can be moved out of the blocks. Why is this bad? Duplicate code is less maintainable. Example let foo = if … { println!("Hello World"); 13 } else { println!("Hello World"); 42 }; Use instead: println!("Hello World"); let foo = if … { 13 } else { 42 }; Applicability: Unspecified (?) Added in: 1.53.0 Related Issues View Source builtin_type_shadow ¶ 📋 style warn What it does Warns if a generic shadows a built-in type. Why is this bad? This gives surprising type errors. Example impl<u32> Foo<u32> { fn impl_func(&self) -> u32 { 42 } } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source byte_char_slices ¶ 📋 style warn What it does Checks for hard to read slices of byte characters, that could be more easily expressed as a byte string. Why is this bad? Potentially makes the string harder to read. Example &[b'H', b'e', b'l', b'l', b'o']; Use instead: b"Hello" Applicability: MachineApplicable (?) Added in: 1.81.0 Related Issues View Source bytes_count_to_len ¶ 📋 complexity warn What it does It checks for str::bytes().count() and suggests replacing it with str::len() . Why is this bad? str::bytes().count() is longer and may not be as performant as using str::len() . Example "hello".bytes().count(); String::from("hello").bytes().count(); Use instead: "hello".len(); String::from("hello").len(); Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source bytes_nth ¶ 📋 style warn What it does Checks for the use of .bytes().nth() . Why is this bad? .as_bytes().get() is more efficient and more readable. Example "Hello".bytes().nth(3); Use instead: "Hello".as_bytes().get(3); Applicability: MachineApplicable (?) Added in: 1.52.0 Related Issues View Source cargo_common_metadata ¶ 📋 cargo allow What it does Checks to see if all common metadata is defined in Cargo.toml . See: https://rust-lang-nursery.github.io/api-guidelines/documentation.html#cargotoml-includes-all-common-metadata-c-metadata Why is this bad? It will be more difficult for users to discover the purpose of the crate, and key information related to it. Example [package] name = "clippy" version = "0.0.212" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Should include a description field like: [package] name = "clippy" version = "0.0.212" description = "A bunch of helpful lints to avoid common pitfalls in Rust" repository = "https://github.com/rust-lang/rust-clippy" readme = "README.md" license = "MIT OR Apache-2.0" keywords = ["clippy", "lint", "plugin"] categories = ["development-tools", "development-tools::cargo-plugins"] Configuration cargo-ignore-publish : For internal testing only, ignores the current publish settings in the Cargo manifest. (default: false ) Applicability: Unspecified (?) Added in: 1.32.0 Related Issues View Source case_sensitive_file_extension_comparisons ¶ 📋 pedantic allow What it does Checks for calls to ends_with with possible file extensions and suggests to use a case-insensitive approach instead. Why is this bad? ends_with is case-sensitive and may not detect files with a valid extension. Example fn is_rust_file(filename: &str) -> bool { filename.ends_with(".rs") } Use instead: fn is_rust_file(filename: &str) -> bool { let filename = std::path::Path::new(filename); filename.extension() .map_or(false, |ext| ext.eq_ignore_ascii_case("rs")) } Applicability: MaybeIncorrect (?) Added in: 1.51.0 Related Issues View Source cast_abs_to_unsigned ¶ 📋 suspicious warn What it does Checks for usage of the abs() method that cast the result to unsigned. Why is this bad? The unsigned_abs() method avoids panic when called on the MIN value. Example let x: i32 = -42; let y: u32 = x.abs() as u32; Use instead: let x: i32 = -42; let y: u32 = x.unsigned_abs(); Configuration msrv : The minimum rust version that the project supports. Defaults to the rust-version field in Cargo.toml (default: current version ) Applicability: MachineApplicable (?) Added in: 1.62.0 Related Issues View Source cast_enum_constructor ¶ 📋 suspicious warn What it does Checks for casts from an enum tuple constructor to an integer. Why is this bad? The cast is easily confused with casting a c-like enum value to an integer. Example enum E { X(i32) }; let _ = E::X as usize; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_enum_truncation ¶ 📋 suspicious warn What it does Checks for casts from an enum type to an integral type that will definitely truncate the value. Why is this bad? The resulting integral value will not match the value of the variant it came from. Example enum E { X = 256 }; let _ = E::X as u8; Applicability: Unspecified (?) Added in: 1.61.0 Related Issues View Source cast_lossless ¶ 📋 pedantic allow What it does Checks for casts between numeric types that can be replaced by safe conversion functions. Why is this bad? Rust’s as keyword will perform many kinds of conversions, including silently lossy conversions. Conversion functions such as i32::from will only perform lossless conversions. Using the conversion functions prevents conversions from becoming silently lossy if the input types ever change, and makes it clear for people reading the code that the conversion is lossless. Example fn as_u64(x: u8) -> u64 { x as u64 } Using ::from would look like this: fn as_u64(x: u8) -> u64 { u64::from(x) } Applicability: MachineApplicable (?) Added in: pre 1.29.0 Related Issues View Source cast_nan_to_int ¶ 📋 suspicious warn What it does Checks for a known NaN float being cast to an integer Why is this bad? NaNs are cast into zero, so one could simply use this and make the code more readable. The lint could also hint at a programmer error. Example let _ = (0.0_f32 / 0.0) as u64; Use instead: let _ = 0_u64; Applicability: Unspecified (?) Added in: 1.66.0 Related Issues View Source cast_possible_truncation ¶ 📋 pedantic allow What it does Checks for casts between numeric types that may truncate large values. This is expected behavior, so the cast is Allow by default. It suggests user either explicitly ignore the lint, or use try_from() and handle the truncation, default, or panic explicitly. Why is this bad? In some problem domains, it is good practice to avoid truncation. This lint can be activated to help assess where additional checks could be beneficial. Example fn as_u8(x: u64) -> u8 { x as u8 } Use instead: fn as_u8(x: u64) -> u8 { if let Ok(x) = u8::try_from(x) { x } else { todo!(); } } // Or #[allow(clippy::cast_possible_truncation)] fn as_u16(x: u64) -> u16 { x as u16 } Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_possible_wrap ¶ 📋 pedantic allow What it does Checks for casts from an unsigned type to a signed type of the same size, or possibly smaller due to target-dependent integers. Performing such a cast is a no-op for the compiler (that is, nothing is changed at the bit level), and the binary representation of the value is reinterpreted. This can cause wrapping if the value is too big for the target signed type. However, the cast works as defined, so this lint is Allow by default. Why is this bad? While such a cast is not bad in itself, the results can be surprising when this is not the intended behavior: Example let _ = u32::MAX as i32; // will yield a value of `-1` Use instead: let _ = i32::try_from(u32::MAX).ok(); Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_precision_loss ¶ 📋 pedantic allow What it does Checks for casts from any numeric type to a float type where the receiving type cannot store all values from the original type without rounding errors. This possible rounding is to be expected, so this lint is Allow by default. Basically, this warns on casting any integer with 32 or more bits to f32 or any 64-bit integer to f64 . Why is this bad? It’s not bad at all. But in some applications it can be helpful to know where precision loss can take place. This lint can help find those places in the code. Example let x = u64::MAX; x as f64; Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_ptr_alignment ¶ 📋 pedantic allow What it does Checks for casts, using as or pointer::cast , from a less strictly aligned pointer to a more strictly aligned pointer. Why is this bad? Dereferencing the resulting pointer may be undefined behavior. Known problems Using std::ptr::read_unaligned and std::ptr::write_unaligned or similar on the resulting pointer is fine. Is over-zealous: casts with manual alignment checks or casts like u64 -> u8 -> u16 can be fine. Miri is able to do a more in-depth analysis. Example let _ = (&1u8 as *const u8) as *const u16; let _ = (&mut 1u8 as *mut u8) as *mut u16; (&1u8 as *const u8).cast::<u16>(); (&mut 1u8 as *mut u8).cast::<u16>(); Applicability: Unspecified (?) Added in: pre 1.29.0 Related Issues View Source cast_sign_loss ¶ 📋 pedantic allow What it does Checks for casts from a signed to an unsigned numeric type. In this case, negative values wrap around to large positive values, which can be quite surprising in practice. However, since the cast works as defined, this lint is Allow by default. Why is this bad? Possibly surprising results. You can activate this lint as a one-time check to see where numeric wrapping can arise. Example let y: i8 = -1; y as u64; // will return 18446744073709551615 Applicability: MaybeIncorrect (?) Added in: pre 1.29.0 Related Issues View Source cast_slice_different_sizes ¶ 📋 correctness deny What it does Checks for as casts between raw pointers to slices with differently sized elements. Why is this bad? The produced raw pointer to a slice does not update its length metadata. The produced pointer will point to a different number of bytes than the original pointer because the length metadata of a raw slice pointer is in elements rather than bytes. Producing a slice reference from the raw pointer will either create a slice with less data (which can be surprising) or create a slice with more data and cause Undefined Behavior. Example // Missing data let a = [1_i32, 2, 3, 4]; let p = &a as *const [i32] as *const [u8]; unsafe { println!("{:?}", &*p); } // Undefined Behavior (note: also potential alignment issues) let a = [1_u8, 2, 3, 4]; let p = &a as *const [u8] as *const [u32]; unsafe { println!("{:?}", &*p); } Instead use ptr::slice_from_raw_parts to construct a slice from a data pointer and the correct length let a = [1_i32, 2, 3, 4]; let old_ptr = &a as *const [i32]; // The data pointer is cast to a pointer to the target `u8` not `[u8]` // The length comes from the known length of 4 i32s times the 4 bytes per i32 let new_ptr = core::ptr::slice_from_raw_parts(old_ptr as *const u8, 16); unsafe { println!("{:?}", &*new_ptr); } Applicability: HasPlaceholders (?) Added in: 1.61.0 Related Issues View Source cast_slice_from_raw_parts ¶ 📋 suspicious warn What it does Checks for a raw slice being cast to a slice pointer Why is this bad? This can result in multiple &mut references to the same location when only a pointer is required. ptr::slice_from_raw_parts is a safe alternative that doesn’t require the same safety requirements to be upheld. Example let _: *const [u8] = std::slice::from_raw_parts(ptr, len) as *const _; let _: *mut [u8] = std::slice::from_raw_parts_mut(ptr, len) as *mut _; Use instead: let _: *const [u8] = std::ptr::slice_from_raw_parts(ptr, len); let _: *mut [u8] = std::ptr::slice_from_raw_parts_mut(ptr, len); Applicability: MachineApplicable (?) Added in: 1.65.0 Related Issues View Source cfg_not_test ¶ 📋 restriction allow What it does Checks for usage of cfg that excludes code from test builds. (i.e., #[cfg(not(test))] ) Why is this bad? This may give the false impression that a codebase has 100% coverage, yet actually has untested code. Enabling this also guards against excessive mockery as well, which is an anti-pattern. Example #[cfg(not(test))] important_check(); // I'm not actually tested, but not including me will falsely increase coverage! Use instead: important_check(); Applicability: Unspecified (?) Added in: 1.81.0 Related Issues View Source char_indices_as_byte_indices ¶ 📋 correctness deny What it does Checks for usage of a character position yielded by .chars().enumerate() in a context where a byte index is expected, such as an argument to a specific str method or indexing into a str or String . Why is this bad? A character (more specifically, a Unicode scalar value) that is yielded by str::chars can take up multiple bytes, so a character position does not necessarily have the same byte index at which the character is stored. Thus, using the character position where a byte index is expected can unexpectedly return wrong values or panic when the string consists of multibyte characters. For example, the character a in äa is stored at byte index 2 but has the character position 1. Using the character position 1 to index into the string will lead to a panic as it is in the middle of the first character. Instead of .chars().enumerate() , the correct iterator to use is .char_indices() , which yields byte indices. This pattern is technically fine if the strings are known to only use the ASCII subset, though in those cases it would be better to use bytes() directly to make the intent clearer, but there is also no downside to just using .char_indices() directly and supporting non-ASCII strings. You may also want to read the chapter on strings in the Rust Book which goes into this in more detail. Example for (idx, c) in s.chars().enumerate() { let _ = s[idx..]; // ⚠️ Panics for strings consisting of multibyte characters } Use instead: for (idx, c) in s.char_indices() { let _ = s[idx..] | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/hclsoftware-hcl-domino/?trk=products_seo_search | HCL Domino | LinkedIn Skip to main content LinkedIn HCLSoftware in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in HCL Domino Business Process Management Software by HCLSoftware See who's skilled in this Add as skill Learn more Report this product About HCL Domino is an enterprise-grade and secure application development platform designed to solve workflow and process challenges — fast. It powers more than 10 million apps transforming the business of more than 15,000 customers. Domino is more modern and offers more value and lower TCO than ever. Now you can make your apps mobile with zero effort and build new ones 70% faster than before. Domino also provides an enterprise-grade mail, calendar, and contacts platform. The platform is associated with Notes, a professional secure on-premises client which allows users to execute the enterprise applications from their desktop (including the mail client), in a connected or disconnected way. This product is intended for Application Architect Application Development Manager Chief Technical Officer Head Business System Lotus Notes Consultant Domino Administrator Business Application Consultant Lotus Domino Administrator Domino Developer Lotus Notes Domino Developer Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less HCLSoftware products HCL BigFix HCL BigFix Endpoint Detection & Response (EDR) Software HCL Commerce+ HCL Commerce+ E-Commerce Platforms HCL Connections HCL Connections Enterprise Social Networking Software HCL Digital Experience HCL Digital Experience Digital Experience Platforms (DXP) HCL Mainframe Solutions HCL Mainframe Solutions Mainframe Management Software HCL Sametime HCL Sametime Employee Communications Software HCL Software DevOps HCL Software DevOps DevOps Software HCL Unica HCL Unica Marketing Automation Software HCL Volt MX HCL Volt MX Low-Code Development Platforms Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/amdocs-techinsights/?trk=products_seo_search | Amdocs TechInsights | LinkedIn Skip to main content LinkedIn Amdocs in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Amdocs TechInsights Business Process Management Software by Amdocs See who's skilled in this Add as skill Learn more Report this product About Enable operational services for mobile network rollouts involving multiple teams and scopes of work Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less Amdocs products Amdocs CatalogONE Amdocs CatalogONE Catalog Management Software Amdocs Customer Engagement Amdocs Customer Engagement Customer Engagement Software Amdocs Freestyle Billing Amdocs Freestyle Billing Billing & Invoicing Software Amdocs Low-Code Experience Platform Amdocs Low-Code Experience Platform Low-Code Development Platforms Amdocs MarketONE Amdocs MarketONE OTT Platforms Amdocs Microservices Management Platform Amdocs Microservices Management Platform Platform as a Service (PaaS) Software Real-Time Billing Real-Time Billing Billing & Invoicing Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/salesforce-sales-cloud/?trk=products_seo_search | Sales Cloud | LinkedIn Skip to main content LinkedIn Salesforce in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Sales Cloud Customer Relationship Management (CRM) Software by Salesforce See who's skilled in this Add as skill Learn more Report this product About Accelerate growth with your Humans + AI dream team. Ready to elevate every step of your sales cycle, from pipeline to paycheck? Scale your team with AI agents, equip your human sellers with the data and insights they need to win, and drive operational efficiency—all on Sales Cloud, the #1 agentic sales software platform. Similar products Zoho CRM Zoho CRM Customer Relationship Management (CRM) Software Bigin by Zoho CRM Bigin by Zoho CRM Customer Relationship Management (CRM) Software Experian DataShare Experian DataShare Customer Relationship Management (CRM) Software Odoo CRM Odoo CRM Customer Relationship Management (CRM) Software Freshsales Freshsales Customer Relationship Management (CRM) Software Clickup Clickup Customer Relationship Management (CRM) Software Sign in to see more Show more Show less Salesforce products Agentforce Agentforce Commerce Cloud Commerce Cloud E-Commerce Platforms Data Cloud Data Cloud Customer Data Platforms (CDP) Marketing Cloud Marketing Cloud Marketing Automation Software Net Zero Cloud Net Zero Cloud Data Management Platforms (DMP) Salesforce CRM Salesforce CRM Customer Data Platforms (CDP) Salesforce Platform Salesforce Platform Low-Code Development Platforms Slack Slack Cloud Communications Platforms Tableau Tableau Business Intelligence (BI) Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/zohocorp-zoho-crm/?trk=products_seo_search | Zoho CRM | LinkedIn Skip to main content LinkedIn Zoho in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Zoho CRM Customer Relationship Management (CRM) Software by Zoho See who's skilled in this Add as skill Learn more Report this product About Zoho CRM is an online customer relationship management software for managing your sales, marketing, support in a single system. Zoho CRM helps businesses of all sizes build excellent customer relationships, with features like an inbuilt AI sales assistant, sales pipeline management, marketing automation, analytics, and more. Zoho CRM empowers a global network of over 150,000 businesses in 180 countries to convert more leads, engage with customers, and grow their revenue. This product is intended for Chief Executive Officer Sales Manager Regional Sales Manager Customer Service Representative Sales Executive Director of Sales Marketing Sales And Marketing Specialist Salesperson Marketer Customer Experience Manager Media Products media viewer No more previous content Get to know Zoho CRM Zoho CRM is an online Customer Relationship Management (CRM) software for managing your sales, marketing & support in a single system. Zoho CRM homepage with dashboards Dashboard is a summarized view of the custom report data in Zoho CRM. It provides a platform for a real-time analysis of the sales stages and business operations. You can create a dashboard and share it with all the users or few selected users. You can also create private dashboards that will be accessible only to you. Customize Zoho CRM to fit your business A truly customizable solution that can be modified as needed to fit your business. Use custom fields, buttons, and layouts to capture various information from your prospects, create custom views, relate information, test customization before rolling out, and even localize the language and currency to fit your users. Analytics and AI In the world of sales, there's no better motivation than numbers. A clear understanding of your company's current performance and its future potential will help you successfully meet changing industry trends and protect you against any adverse economic conditions. Stay on top of your business wherever you go When it comes to business, time is money. If your sales team can't respond quickly, you could be missing out on a deal or be left with an unhappy customer. With Zoho CRM mobile apps, your sales team can keep in touch with their leads on the move, log and access important prospect information, keep track of their KPIs, and make data-driven decisions on the move. You can also find prospects near you so you can keep selling. No more next content Featured customers of Zoho CRM ReBiz Technology, Information and Internet 2,694 followers H+K International Mechanical Or Industrial Engineering 9,267 followers The Streaming Network Technology, Information and Internet 482 followers Arctic Spas (Blue Falls Manufacturing) Wellness and Fitness Services 1,402 followers Call Center Sales Pro Telecommunications 834 followers Recover Health, Inc Hospitals and Health Care 2,584 followers Selectra Technology, Information and Internet 79,939 followers Ecolab, Purolite Resins Manufacturing 31,434 followers Benseron Hospitality - Profit Improvement Specialist for Hospitality Industry Software Development 38 followers Show more Show less Similar products Sales Cloud Sales Cloud Customer Relationship Management (CRM) Software Bigin by Zoho CRM Bigin by Zoho CRM Customer Relationship Management (CRM) Software Experian DataShare Experian DataShare Customer Relationship Management (CRM) Software Odoo CRM Odoo CRM Customer Relationship Management (CRM) Software Freshsales Freshsales Customer Relationship Management (CRM) Software Clickup Clickup Customer Relationship Management (CRM) Software Sign in to see more Show more Show less Zoho products Bigin by Zoho CRM Bigin by Zoho CRM Customer Relationship Management (CRM) Software Zoho Analytics Zoho Analytics Business Intelligence (BI) Software Zoho Commerce Zoho Commerce E-Commerce Platforms Zoho DataPrep Zoho DataPrep Data Preparation Tools Zoho Forms Zoho Forms Online Form Builder Software Zoho FSM Zoho FSM Field Service Management (FSM) Software Zoho One Zoho One Business Management Software Zoho People Zoho People Human Resources Management Systems (HRMS) Zoho RPA Zoho RPA Robotic Process Automation (RPA) Software Zoho Webinar Zoho Webinar Webinar Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://huggingface.co/datasets/nvidia/embed-nemotron-dataset-v1 | nvidia/embed-nemotron-dataset-v1 · Datasets at Hugging Face Hugging Face Models Datasets Spaces Community Docs Enterprise Pricing Log In Sign Up Datasets: nvidia / embed-nemotron-dataset-v1 like 50 Follow NVIDIA 47.5k Tasks: Text Retrieval Text Ranking Sentence Similarity + 1 Modalities: Text Formats: parquet Languages: multilingual Size: 10M - 100M ArXiv: arxiv: 2511.07025 Libraries: Datasets pandas Polars + 1 Dataset card Data Studio Files Files and versions xet Community Dataset Viewer Auto-converted to Parquet API Embed Duplicate Data Studio Subset (28) EmotionClassification · 13k rows EmotionClassification (13k rows) EmotionClassification_corpus (6 rows) FEVER (140k rows) FEVER_corpus (236k rows) GooAQ (100k rows) GooAQ_corpus (86.4k rows) HotpotQA (170k rows) HotpotQA_corpus (755k rows) MAmmoTH2 (317k rows) MAmmoTH2_corpus (317k rows) MIRACL (79.6k rows) MIRACL_corpus (2.57M rows) MSMARCO (533k rows) MSMARCO_corpus (3.67M rows) NFCorpus (3.69k rows) NFCorpus_corpus (3.57k rows) NaturalQuestions (100k rows) NaturalQuestions_corpus (75.2k rows) PAQ (1M rows) PAQ_corpus (932k rows) SQuAD (87.6k rows) SQuAD_corpus (18.9k rows) SciFact (919 rows) SciFact_corpus (3.26k rows) SyntheticClassificationData (1.04M rows) SyntheticClassificationData_corpus (382k rows) TriviaQA (73.3k rows) TriviaQA_corpus (64.1k rows) Split (1) train · 13k rows train (13k rows) SQL Console question_id int64 0 13k question string lengths 3 7 corpus_id string classes 1 value pos_doc list lengths 1 1 neg_doc list lengths 4 4 0 q_2249 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15950" } ] 1 q_15895 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15954" } ] 2 q_12328 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15939" } ] 3 q_8272 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15954" } ] 4 q_1991 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15950" } ] 5 q_273 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" } ] 6 q_9714 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15945" }, { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" } ] 7 q_13502 EmotionClassification [ { "id": "d_15945" } ] [ { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15950" } ] 8 q_5121 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15950" } ] 9 q_12676 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15939" }, { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15950" } ] 10 q_12859 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15953" }, { "id": "d_15939" } ] 11 q_4165 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15950" } ] 12 q_8306 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15945" } ] 13 q_6078 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15939" } ] 14 q_15754 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15955" }, { "id": "d_15939" }, { "id": "d_15950" } ] 15 q_14570 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15953" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15945" } ] 16 q_11932 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15955" }, { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15950" } ] 17 q_2115 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15945" } ] 18 q_8730 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15945" }, { "id": "d_15953" }, { "id": "d_15950" }, { "id": "d_15939" } ] 19 q_14378 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15955" } ] 20 q_6563 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15953" } ] 21 q_5529 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15945" } ] 22 q_14654 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15950" } ] 23 q_11245 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15950" }, { "id": "d_15945" } ] 24 q_3818 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15950" }, { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15939" } ] 25 q_13623 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15945" } ] 26 q_2982 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15955" }, { "id": "d_15939" }, { "id": "d_15953" }, { "id": "d_15945" } ] 27 q_7482 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15945" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15939" } ] 28 q_12207 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15939" }, { "id": "d_15955" } ] 29 q_1832 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15954" }, { "id": "d_15955" }, { "id": "d_15945" }, { "id": "d_15953" } ] 30 q_13864 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15950" } ] 31 q_1633 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15950" } ] 32 q_5777 EmotionClassification [ { "id": "d_15945" } ] [ { "id": "d_15955" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15953" } ] 33 q_144 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15955" } ] 34 q_13931 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15950" } ] 35 q_11373 EmotionClassification [ { "id": "d_15945" } ] [ { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15954" }, { "id": "d_15953" } ] 36 q_8373 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15955" }, { "id": "d_15945" } ] 37 q_7627 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15954" } ] 38 q_5695 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15954" } ] 39 q_253 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15945" }, { "id": "d_15954" } ] 40 q_7929 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15945" }, { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15955" } ] 41 q_13938 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15953" } ] 42 q_3359 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15945" } ] 43 q_2418 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15954" }, { "id": "d_15953" }, { "id": "d_15955" }, { "id": "d_15945" } ] 44 q_4959 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15953" } ] 45 q_2677 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15939" }, { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15954" } ] 46 q_6252 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15954" } ] 47 q_4373 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15955" }, { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15939" } ] 48 q_1769 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15953" } ] 49 q_3905 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15953" } ] 50 q_6558 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15953" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15955" } ] 51 q_15856 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15953" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15945" } ] 52 q_9855 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15950" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15945" } ] 53 q_1381 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15954" } ] 54 q_8547 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15950" }, { "id": "d_15939" }, { "id": "d_15955" } ] 55 q_13202 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15945" } ] 56 q_1729 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15939" } ] 57 q_1799 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15954" } ] 58 q_10420 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15939" }, { "id": "d_15945" }, { "id": "d_15954" }, { "id": "d_15950" } ] 59 q_7219 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15950" }, { "id": "d_15939" }, { "id": "d_15955" } ] 60 q_7038 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15955" } ] 61 q_7993 EmotionClassification [ { "id": "d_15945" } ] [ { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15955" } ] 62 q_15611 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15939" }, { "id": "d_15953" }, { "id": "d_15955" }, { "id": "d_15945" } ] 63 q_4803 EmotionClassification [ { "id": "d_15945" } ] [ { "id": "d_15954" }, { "id": "d_15953" }, { "id": "d_15950" }, { "id": "d_15955" } ] 64 q_2590 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" } ] 65 q_15927 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15939" } ] 66 q_1901 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15950" }, { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15955" } ] 67 q_9050 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15945" }, { "id": "d_15954" }, { "id": "d_15953" }, { "id": "d_15939" } ] 68 q_14285 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15950" } ] 69 q_5402 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15945" } ] 70 q_12383 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15953" } ] 71 q_4965 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15945" }, { "id": "d_15950" }, { "id": "d_15954" }, { "id": "d_15953" } ] 72 q_8402 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15945" }, { "id": "d_15955" } ] 73 q_4840 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15955" } ] 74 q_13789 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15955" } ] 75 q_10607 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15954" }, { "id": "d_15955" }, { "id": "d_15950" } ] 76 q_7098 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15950" }, { "id": "d_15939" }, { "id": "d_15954" } ] 77 q_4304 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15939" } ] 78 q_4446 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15945" }, { "id": "d_15953" }, { "id": "d_15954" }, { "id": "d_15955" } ] 79 q_4398 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15955" }, { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15939" } ] 80 q_10434 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15954" }, { "id": "d_15950" } ] 81 q_12533 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15955" }, { "id": "d_15945" }, { "id": "d_15939" } ] 82 q_8763 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15945" }, { "id": "d_15954" } ] 83 q_9135 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15945" }, { "id": "d_15950" }, { "id": "d_15955" }, { "id": "d_15954" } ] 84 q_125 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15950" } ] 85 q_8498 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15955" } ] 86 q_12660 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15953" }, { "id": "d_15955" }, { "id": "d_15950" }, { "id": "d_15954" } ] 87 q_9118 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15950" }, { "id": "d_15945" }, { "id": "d_15955" }, { "id": "d_15939" } ] 88 q_11838 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15953" }, { "id": "d_15954" }, { "id": "d_15955" }, { "id": "d_15939" } ] 89 q_8174 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15953" }, { "id": "d_15950" } ] 90 q_9302 EmotionClassification [ { "id": "d_15950" } ] [ { "id": "d_15939" }, { "id": "d_15955" }, { "id": "d_15953" }, { "id": "d_15945" } ] 91 q_9370 EmotionClassification [ { "id": "d_15954" } ] [ { "id": "d_15939" }, { "id": "d_15950" }, { "id": "d_15945" }, { "id": "d_15955" } ] 92 q_15503 EmotionClassification [ { "id": "d_15953" } ] [ { "id": "d_15950" }, { "id": "d_15954" }, { "id": "d_15939" }, { "id": "d_15955" } ] 93 q_13498 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15954" }, { "id": "d_15945" }, { "id": "d_15939" }, { "id": "d_15950" } ] 94 q_14616 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15939" }, { "id": "d_15954" }, { "id": "d_15953" }, { "id": "d_15950" } ] 95 q_3462 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15954" }, { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15950" } ] 96 q_4941 EmotionClassification [ { "id": "d_15939" } ] [ { "id": "d_15954" }, { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15945" } ] 97 q_1099 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15950" }, { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15954" } ] 98 q_15275 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15945" }, { "id": "d_15953" }, { "id": "d_15939" }, { "id": "d_15950" } ] 99 q_4569 EmotionClassification [ { "id": "d_15955" } ] [ { "id": "d_15939" }, { "id": "d_15953" }, { "id": "d_15945" }, { "id": "d_15954" } ] End of preview. Expand in Data Studio Previous 1 2 3 ... 131 Next Data Collection Method ","children":[],"isValid":true,"title":"Data Collection Method"},{"id":"labeling-method","label":" Labeling Method ","children":[],"isValid":true,"title":"Labeling Method"}],"isValid":true,"title":"Dataset Characterization"},{"id":"dataset-format","label":"Dataset Format","children":[],"isValid":true,"title":"Dataset Format"},{"id":"usage","label":"Usage","children":[],"isValid":true,"title":"Usage"},{"id":"citation","label":"Citation:","children":[],"isValid":true,"title":"Citation:"},{"id":"ethical-considerations","label":"Ethical Considerations:","children":[],"isValid":true,"title":"Ethical Considerations:"}],"classNames":"top-6"}"> Versions Dataset Description Dataset Owner Dataset Creation Date License/Terms of Use Intended Usage Dataset Composition Tag Legend Dataset Quantification Dataset Characterization Data Collection Method Labeling Method Dataset Format Usage Citation: Ethical Considerations: Embed Nemotron Dataset V1 Versions Date Commit Changes 2026-01-05 8808454 Initial Release Dataset Description This dataset is a compilation of high quality fine-tuning datasets that support NVIDIA's release of llama-embed-nemotron-8b model. llama-embed-nemotron-8b is a versatile text embedding model trained by NVIDIA and optimized for retrieval, reranking, semantic similarity, and classification use cases. This model has robust capabilities for multilingual and cross-lingual text retrieval and is designed to serve as a foundational component in text-based Retrieval-Augmented Generation (RAG) systems. This model achieves state-of-the-art performance on the multilingual MTEB leaderboard as of October 21, 2025. embed-nemotron-dataset-v1 is a selected subset of the fine-tuning data used for training the llama-embed-nemotron-8b model. This data mix is intentionally curated from a variety of sources to ensure robustness and high performance across a broad range of tasks. It comprises both non-synthetic data drawn from established public datasets like MIRACL, HotpotQA, MS MARCO etc.; and synthetic data specifically generated to enhance diversity in task types (for example, classification). Each dataset is additionally transformed with a sophisticated hard negative mining process to maximize the learning signal. Read more details in our technical report: Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks . In the table below, you can see all the subdatasets that we are publishing, with their details. In some cases, the data is redistributed directly. For the remaining ones, we only provide IDs of the queries and documents. In the latter case, we provide python data processing script to fetch original texts given provided IDs. This dataset is for research and development only. Dataset Owner NVIDIA Corporation Dataset Creation Date October 21, 2025 License/Terms of Use Dataset Governing Terms : Use of each dataset in this collection is governed by the license accompanying it, except for the FEVER and MIRACL datasets, which are governed by the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0), and the SyntheticClassificationData , which is governed by the Creative Commons Attribution 4.0 International License (CC BY 4.0). Dataset Additional Information : The SyntheticClassificationData dataset contains synthetic data created using the following models: meta-llama/Llama-3.3-70B-Instruct , meta-llama/Llama-4-Scout-17B-16E-Instruct and meta-llama/Llama-4-Maverick-17B-128E-Instruct . If this dataset is used to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, such AI model may be subject to redistribution and use requirements in the Llama 3.3 Community License Agreement and Llama 4 Community License Agreement . Intended Usage The embed-nemotron-dataset-v1 is intended to be used by the community to continue to improve open models. The data may be freely used to train and evaluate. Dataset Composition Dataset Name Task Samples (Queries / Documents) Size (MB) Governing Terms Source EmotionClassification Classification 13,039 / 6 0.2 public FEVER Retrieval 140,085 / 235,948 118.2 CC BY-SA 4.0 public GooAQ Retrieval 100,000 / 86,393 5.5 public HotpotQA Retrieval 170,000 / 754,756 21.4 public MAmmoTH2 Retrieval 317,180 / 317,205 27.8 public MIRACL Retrieval 79,648 / 2,571,803 1,480.0 CC BY-SA 4.0 public MSMARCO Retrieval 532,751 / 3,672,883 80.6 public NFCorpus Retrieval 3,685 / 3,573 0.2 public NaturalQuestions Retrieval 100,231 / 75,215 5.1 public PAQ Retrieval 1,000,000 / 932,307 108.0 public SQuAD Retrieval 87,599 / 18,891 3.4 public SciFact Retrieval 919 / 3,255 0.1 public SyntheticClassificationData Classification 1,044,212 / 382,227 440.1 CC BY 4.0 synthetic TriviaQA Retrieval 73,346 / 64,137 3.8 public Total (14) 3,662,695 / 9,118,599 2,314.4 Tag Legend public : Origin of the data is another public dataset synthetic : The data was synthetically generated Dataset Quantification Total Number of Datasets : 14 Total Number of Samples : 3,662,695 Queries; 9,118,599 Documents Total Size : 2.3 GB Dataset Characterization Data Collection Method Hybrid: Synthetic, Automated, Human Labeling Method Hybrid: Synthetic, Automated, Human Dataset Format Each given dataset includes two parts: Queries question_id -- id of the query question -- query text (or query ID if texts are not redistributed directly) corpus_id -- name of the dataset pos_doc -- list of the positive documents for the given query neg_doc -- list of the negative documents for the given query Corpus id -- document id corresponding to pos_doc and neg_doc lists from the Queries Optional text -- document text if texts are redistributed directly Usage The data has been prepared to be used with NeMo AutoModel framework. This dataset is a compilation of high quality fine-tuning datasets that support NVIDIA's release of llama-embed-nemotron-8b model. To prepare the data and start training the model, follow the steps provided here . Citation: @misc{babakhin2025llamaembednemotron8buniversaltextembedding, title={Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks}, author={Yauhen Babakhin and Radek Osmulski and Ronay Ak and Gabriel Moreira and Mengyao Xu and Benedikt Schifferer and Bo Liu and Even Oldridge}, year={2025}, eprint={2511.07025}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2511.07025}, Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this dataset meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here . Downloads last month 204 Use this dataset Size of downloaded dataset files: 2.3 GB Size of the auto-converted Parquet files: 2.3 GB Number of rows: 12,781,294 Models trained or fine-tuned on nvidia/embed-nemotron-dataset-v1 nvidia/llama-embed-nemotron-8b Feature Extraction • 8B • Updated 1 day ago • 429k • 116 mradermacher/llama-embed-nemotron-8b-GGUF Feature Extraction • 8B • Updated 6 days ago • 500 Collection including nvidia/embed-nemotron-dataset-v1 Nemotron RAG Collection 14 items • Updated 1 day ago • 59 Paper for nvidia/embed-nemotron-dataset-v1 Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks Paper • 2511.07025 • Published Nov 10, 2025 • 12 System theme Company TOS Privacy About Careers Website Models Datasets Spaces Pricing Docs | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fcybereason-enterprise%3FviewConnections%3Dtrue&trk=products_details_guest_face-pile-cta | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2F320mediamatthewhussey&trk=organization_guest_main-feed-card_social-actions-comments | Sign Up | LinkedIn Join LinkedIn now — it’s free! Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show First name Last name Remember me By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Looks like you’re using Gmail, sign up faster with Google in one tap. Continue with ( not you? ) or Sign up with credential instead Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Follow top companies Over 60% of the fortune 100 companies use LinkedIn to hire. Join now Leave | 2026-01-13T09:29:17 |
https://scholar.google.com/citations?user=SSq1t_YAAAAJ&hl=en | Josh Gardner - Google 학술 검색 로드 중... 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 연간 인용횟수 중복된 서지정보 다음 학술 문서는 학술검색에서 병합되어 있습니다. 총 인용 횟수가 첫 번째 학술 문서에 대해서만 계산됩니다. 병합된 서지정보 이 '인용' 횟수는 학술검색의 다음 학술 문서에 대한 인용문을 포함합니다. * 표시된 인용문은 프로필에 있는 학술 문서와 다를 수 있습니다. 공동 저자 추가 공동 저자 팔로우 이 저자의 새 학술자료 이 저자를 인용한 새 학술자료 이 저자의 연구와 관련된 새 학술자료 업데이트를 받을 이메일 주소 완료 죄송합니다. 현재 Internet Explorer 버전에서는 일부 기능이 작동하지 않을 수 있습니다. 최적의 상태로 사용하려면 Chrome 또는 Mozilla Firefox 를 사용해 주세요. 내 프로필 내 서재 통계 알리미 설정 로그인 로그인 내 프로필 만들기 인용 전체 2021년 이후 서지정보 13023 12360 h-index 23 20 i10-index 34 30 0 3900 1950 975 2925 2018 2019 2020 2021 2022 2023 2024 2025 2026 37 80 448 1052 1736 2273 3315 3871 107 공개 액세스 모두 보기 모두 보기 자료 5개 자료 0개 공개 비공개 재정 지원 요구사항 기준 공동 저자 모두 보기 Christopher A. Brooks University of Michigan umich.edu의 이메일 확인됨 Peter Kairouz Research Scientist, Google google.com의 이메일 확인됨 H. Brendan McMahan Research Scientist, Google Seattle google.com의 이메일 확인됨 Ludwig Schmidt Stanford University and Anthropic stanford.edu의 이메일 확인됨 Jack Hessel Anthropic anthropic.com의 이메일 확인됨 Yonatan Bitton Research Scientist, Google google.com의 이메일 확인됨 Ryan Baker Adelaide University upenn.edu의 이메일 확인됨 Curtis Hawthorne OpenAI openai.com의 이메일 확인됨 Ethan Manilow Google DeepMind u.northwestern.edu의 이메일 확인됨 Ian Simon Google Brain cs.washington.edu의 이메일 확인됨 Jesse H. Engel Google DeepMind google.com의 이메일 확인됨 Pang Wei Koh University of Washington; Allen Institute for AI cs.washington.edu의 이메일 확인됨 Simon Kornblith Anthropic anthropic.com의 이메일 확인됨 Mitchell Wortsman Anthropic anthropic.com의 이메일 확인됨 Gabriel Ilharco Meta Superintelligence Labs cs.washington.edu의 이메일 확인됨 Samir Yitzhak Gadre Anthropic anthropic.com의 이메일 확인됨 Rohan Taori Anthropic anthropic.com의 이메일 확인됨 Danai Koutra University of Michigan, Ann Arbor umich.edu의 이메일 확인됨 Arya Farahi University of Texas at Austin austin.utexas.edu의 이메일 확인됨 Neil Zeghidour Kyutai kyutai.org의 이메일 확인됨 모두 보기 팔로우 Josh Gardner Anthropic cs.washington.edu의 이메일 확인됨 - 홈페이지 Machine Learning Robustness Multimodal Tabular Data Music and Audio 학술자료 인용 공개 액세스 공동 저자 제목 정렬 서지정보순 정렬 연도순 정렬 제목순 정렬 인용 인용 연도 Advances and open problems in federated learning P Kairouz, HB McMahan Foundations and trends in machine learning 14 (1-2), 1-210 , 2021 9917 2021 Openflamingo: An open-source framework for training large autoregressive vision-language models A Awadalla, I Gao, J Gardner, J Hessel, Y Hanafy, W Zhu, K Marathe, ... arXiv preprint arXiv:2308.01390 , 2023 829 2023 Mariana Raykova, Dawn Song, Weikang Song, Sebastian U P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ... Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tram�r, Praneeth�… , 2021 309 2021 Student Success Prediction in MOOCs J Gardner, C Brooks User Modeling and User-Adapted Interaction 28 (2), 127-203 , 2018 280 2018 Evaluating the fairness of predictive student models through slicing analysis J Gardner, C Brooks, R Baker Proceedings of the 9th international conference on learning analytics�… , 2019 264 2019 Datacomp-lm: In search of the next generation of training sets for language models J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, SY Gadre, H Bansal, E Guha, ... Advances in Neural Information Processing Systems 37, 14200-14282 , 2024 198 2024 MT3: Multi-task multitrack music transcription J Gardner, I Simon, E Manilow, C Hawthorne, J Engel arXiv preprint arXiv:2111.03017 , 2021 159 2021 Mlperf inference benchmark. In 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA) VJ Reddi, C Cheng, D Kanter, P Mattson, G Schmuelling, CJ Wu, ... IEEE , 2020 140 2020 Visit-bench: A benchmark for vision-language instruction following inspired by real-world use Y Bitton, H Bansal, J Hessel, R Shao, W Zhu, A Awadalla, J Gardner, ... arXiv preprint arXiv:2308.06595 , 2023 103 2023 Multi-instrument music synthesis with spectrogram diffusion C Hawthorne, I Simon, A Roberts, N Zeghidour, J Gardner, E Manilow, ... arXiv preprint arXiv:2206.05408 , 2022 88 2022 Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G J Li, A Fang, G Smyrnis, M Ivgi, M Jordan, S Gadre, H Bansal, E Guha, ... Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, and Vaishaal Shankar�… , 2024 85 2024 Benchmarking distribution shift in tabular data with tableshift J Gardner, Z Popovic, L Schmidt Advances in Neural Information Processing Systems 36, 53385-53432 , 2023 84 2023 Large scale transfer learning for tabular data via language modeling J Gardner, JC Perdomo, L Schmidt Advances in Neural Information Processing Systems 37, 45155-45205 , 2024 49 2024 Llark: A multimodal instruction-following language model for music J Gardner, S Durand, D Stoller, RM Bittner arXiv preprint arXiv:2310.07160 , 2023 42 2023 Replicating MOOC predictive models at scale J Gardner, C Brooks, JM Andres, R Baker Proceedings of the Fifth Annual ACM Conference on Learning at Scale, 1-10 , 2018 38 2018 Llark: A multimodal foundation model for music JP Gardner, S Durand, D Stoller, RM Bittner 37 2023 Subgroup robustness grows on trees: An empirical baseline investigation J Gardner, Z Popovic, L Schmidt Advances in Neural Information Processing Systems 35, 9939-9954 , 2022 33 2022 MORF: A framework for predictive modeling and replication at scale with privacy-restricted MOOC data J Gardner, C Brooks, JM Andres, RS Baker 2018 IEEE International Conference on Big Data (Big Data), 3235-3244 , 2018 32 2018 Dropout model evaluation in MOOCs J Gardner, C Brooks Proceedings of the AAAI Conference on Artificial Intelligence 32 (1) , 2018 30 2018 Cross-institutional transfer learning for educational models: Implications for model performance, fairness, and equity J Gardner, R Yu, Q Nguyen, C Brooks, R Kizilcec Proceedings of the 2023 acm conference on fairness, accountability, and�… , 2023 28 2023 현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요. 학술자료 1–20 더보기 개인정보처리방침 약관 도움말 학술검색 정보 검색 도움말 | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Fcybereason-enterprise&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/servicenow-now-platform/?trk=products_seo_search | ServiceNow AI Platform | LinkedIn Skip to main content LinkedIn ServiceNow in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in ServiceNow AI Platform Business Process Management Software by ServiceNow See who's skilled in this Add as skill Learn more Report this product About The ServiceNow AI Platform is built for a new era. One platform, ready for anything. Put any AI, any data, any workflow, and any industry to work across the enterprise. Media Products media viewer No more previous content ServiceNow AI Platform ServiceNow AI Platform No more next content Similar products Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less ServiceNow products ServiceNow App Engine ServiceNow App Engine Low-Code Development Platforms LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/company/tencentglobal?trk=products_seo_search | Tencent | LinkedIn Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join now Tencent Software Development Shenzhen, Guangdong 1,256,878 followers Value for Users, Tech for Good See jobs Follow Discover all 89,343 employees Report this company Overview Jobs Life About us Tencent is a world-leading internet and technology company that develops innovative products and services to improve the quality of life of people around the world. Founded in 1998 with its headquarters in Shenzhen, China, Tencent's guiding principle is to use technology for good. Our communication and social services connect more than one billion people around the world, helping them to keep in touch with friends and family, access transportation, pay for daily necessities, and even be entertained. Tencent also publishes some of the world's most popular video games and other high-quality digital content, enriching interactive entertainment experiences for people around the globe. Tencent also offers a range of services such as cloud computing, advertising, FinTech, and other enterprise services to support our clients' digital transformation and business growth. Tencent has been listed on the Stock Exchange of Hong Kong since 2004. Website https://www.tencent.com/en-us/ External link for Tencent Industry Software Development Company size 10,001+ employees Headquarters Shenzhen, Guangdong Type Public Company Founded 1998 Specialties Online Gaming, Social Networking, E-commerce, Online Music, Online Video, Weibo, WeChat Products No more previous content Cloud Native Database TDSQL-C, Relational Database Management Systems Cloud Native Database TDSQL-C Relational Database Management Systems Cloud Object Storage (COS), Object Storage Software Cloud Object Storage (COS) Object Storage Software Cloud Virtual Machine (CVM), Server Virtualization Software Cloud Virtual Machine (CVM) Server Virtualization Software Simple Email Service (SES), Email Marketing Software Simple Email Service (SES) Email Marketing Software Tencent Cloud Automation Tools, Build Automation Tools Tencent Cloud Automation Tools Build Automation Tools Tencent Cloud Block Storage, Block Storage Software Tencent Cloud Block Storage Block Storage Software Tencent Cloud Instant Messaging (IM), Cloud Communications Platforms Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Tencent Cloud Lighthouse, Enterprise Cloud Platforms Tencent Cloud Lighthouse Enterprise Cloud Platforms Tencent Effect SDK, Software Development Kits (SDK) Tencent Effect SDK Software Development Kits (SDK) Tencent Real-Time Communication (TRTC), Live Streaming Software Tencent Real-Time Communication (TRTC) Live Streaming Software No more next content Locations Primary Tencent Seafront Towers Nanshan District Shenzhen, Guangdong, CN Get directions 26th Floor, Mondriaan Tower Amstelplein 54 Amsterdam, 1096 BC, NL Get directions 8 T One Building, 10th,11th and 12th Floor (Unit 4-5), Soi Sukhumvit 40, Sukhumvit Road Phra Khanong, Khlong Toei Bangkok, 10110, OO Get directions Suite 02 & 03, Level 17, Centrepoint South Tower，Mid Valley City Lingkaran Syed Putra Kuala Lumpur, MY Get directions 2747 Park Blvd Palo Alto, California 94306, US Get directions 29F Toranomon Hills Mori Tower, 1-23-1 Toranomon Minato-ku, Tokyo, JP Get directions 40F Gangnam Finance Center, 152, Teheran-ro, Gangnam-gu Seoul, Korea, OO Get directions 29th floor, Tai Koo Plaza Phase 3 Queen's Road East Wan Chai，HongKong, HK Get directions 10th floor, South Tower, global financial center, Harbour City Tsim Sha Tsui，HongKong, HK Get directions Room A1, 21 Floor, No. 68, section 5, Zhongxiao East Road, Xinyi District Taibei City，Taiwan, CN Get directions Show more locations Show fewer locations Employees at Tencent Dowson Tong George Jones Mark 马轶群 Ma Kenneth Siow 萧家武 See all employees Updates Tencent 1,256,878 followers 1w Edited Report this post Meet Connor Dolce , our gamer-turned video producer, YouTube-taught tech wizard, and one of the most entertaining characters you'll meet. From teaching himself technical skills online to creating content at Level Infinite, Connor's journey proves that passion (and a few late-night tutorials) can turn play into a career. Press play to watch Connor's life at Tencent. #LifeAtTencent #GamingCareers #EsportsCareers …more Learning Outside the Classroom and Building a Career in Games 194 11 Comments Like Comment Share Tencent 1,256,878 followers 2w Report this post Level complete: 2025 Ready for 2026 Before we hit start on the new year, a big shout out to our teams, partners, and communities worldwide. Your creativity and collaboration power our progress. New challenges ahead. New worlds to build. Let’s level up together in 2026. …more 162 4 Comments Like Comment Share Tencent 1,256,878 followers 2w Report this post Good news for the global entertainment ecosystem — we're teaming up with Mastercard to make digital payments simpler and more secure. By integrating Mastercard Click to Pay and tokenization into Tencent Midas' overseas payment solutions, users benefit from faster, password-free checkouts, while developers and publishers gain stronger security and fewer payment declines. Less friction. Better protection. Smoother experiences across devices and markets — and an exciting partnership to help advance digital commerce across the online entertainment ecosystem. Learn more: https://lnkd.in/gd7jnUww #DigitalPayments #FinTech 426 8 Comments Like Comment Share Tencent 1,256,878 followers 2w Report this post Staying safe online starts with awareness. As we spend more time chatting, shopping, and managing daily life online, it’s important to be alert to common scam tactics that can appear across digital platforms. To help you stay safe, WeChat has shared a practical guide that highlights common scam tactics — from impersonation and fake offers to emotional manipulation — along with simple tips to protect your account and personal information. You don’t need to be a tech expert. A little awareness and a few smart habits can go a long way in keeping your digital experiences safe and enjoyable. 👉 Read the full anti-scam guide here: https://lnkd.in/gKaWWXVT #WeChat #DigitalSafety #OnlineSafety #ScamAwareness 12 Ways to Protect Your WeChat Account and Stay Safe from Scams newsroom.wechat.com 40 2 Comments Like Comment Share Tencent 1,256,878 followers 3w Report this post Great perspective from Elisabeth TORRE-VINCENT on leadership in video game publishing. Focus, creativity and adaptability matter — and it’s leaders like Elisabeth who help teams and partners thrive. #Tencent #Leadership #Gaming Tencent UK 2,762 followers 3w Three words that sum up Elisabeth TORRE-VINCENT ’s role: → Product-driven → Excellence → Creativity As Head of Western Europe Publishing at Tencent , based in Paris, Elisabeth leads in an environment where plans can change quickly, shaped by community feedback and live events. Her approach is about staying focused, being adaptable and knowing when to stick with a plan and when it’s time to pivot. 🎥 Watch the video to hear her take on modern leadership. #Tencent #Leadership #Gaming Leadership in Video Game Publishing 65 1 Comment Like Comment Share Tencent 1,256,878 followers 4w Report this post Growing up between South Korea and Hong Kong taught Elizabeth Byun that while language is important, real connection comes from understanding people. Having been at Tencent for more than 12 years, she leads Corporate and International Regulatory Legal, showing how communication can bridge laws, policies, cultures, and perspectives. Her story is full of practical insights for anyone navigating complex, cross-functional environments. 🎥 Watch her journey and see how she turns complexity into clear, shared solutions. #LifeAtTencent #LegalCareers #WomenInTech #CareerGrowth #WomenInLaw …more How Growing Up Between Cultures Shaped a Career in International Law | Life at Tencent 387 15 Comments Like Comment Share Tencent 1,256,878 followers 4w Report this post Innovation matters most when it benefits people and society — and that starts with supporting research and collaboration. That was a key message shared by Dowson Tong , Senior Executive Vice President of Tencent, during a recent scientific gathering co-organized by the Tencent Charity Foundation. Since 2018, we've invested over US$56 billion in R&D to explore how tech can accelerate scientific discovery and create real social value. From iDrug, our AI-powered drug discovery platform that helps researchers identify potential treatments faster, to Ethereal Audio, which applies AI to make hearing-assistive technology clearer and more affordable, we're focused on turning innovation into impact. We look forward to working with the scientific community worldwide to turn innovation into impact. #AIForGood #AI #Innovation #Science #Research #SocialImpact #TencentFoundation 135 4 Comments Like Comment Share Tencent 1,256,878 followers 1mo Report this post Congrats to our Singapore team on five years of growth! Tencent Singapore continues to build momentum as a key regional operations hub in our global journey — growing talent, strengthening partnerships, and shaping digital innovation. Here's to what's next. Tencent Singapore 14,827 followers 1mo We’re celebrating 5 years of Tencent Singapore ! Since 2020, we’ve grown alongside Singapore’s tech ecosystem, nurturing talent, building trusted partnerships and contributing to digital innovation across the region. Hear from our Tencent team in Singapore as they reflect on their journeys and the experiences that make being part of Tencent truly special. #Tencent #TencentSingapore #TechForGood 124 2 Comments Like Comment Share Tencent 1,256,878 followers 1mo Report this post A proud moment for our teams in Europe. Congratulations on the opening of the new Paris office. 🎉 #Tencent #Paris Tencent UK 2,762 followers 1mo 🎉 New Office in Paris We’ve opened our new office in Paris, a space for creating, connecting and building what comes next. This is our third office in five years, as we’ve continued to move and expand to keep pace with our growing team. France has become one of our most important markets, and this new space reflects our long-term commitment to supporting creative talent and strengthening partnerships across the region. 📹 Watch the video to see our celebrations. #Tencent #Paris #TencentCloud #TencentGames Tencent’s New Office in Paris 129 Like Comment Share Tencent 1,256,878 followers 1mo Edited Report this post India Browne never set out to become an eSports athlete — she just loved playing games. Yet that spark soon carried her all the way to representing England — undefeated — on the global stage. Watch India’s journey to see what can happen when passion is supported, nurtured, and made healthy. 🎥 Watch India’s story: https://lnkd.in/gZrhWECi #Esports #GamingForGood #FutureOfTalent #CareerPaths #DigitalSkills …more How Gaming Launched an eSports Career | India "Alanis" Browne’s Story 438 11 Comments Like Comment Share Join now to see what you are missing Find people you know at Tencent Browse recommended jobs for you View all updates, news, and articles Join now Affiliated pages Tencent Games Technology, Information and Internet Shenzhen, Guangdong 腾讯企业邮箱 Technology, Information and Internet Similar pages ByteDance Software Development China, China Alibaba Group Software Development Tencent Games Technology, Information and Internet Shenzhen, Guangdong TikTok Entertainment Providers Los Angeles, California Google Software Development Mountain View, CA Riot Games Computer Games Los Angeles, CA Xiaomi Technology Software Development Beijing, Beijing Netflix Entertainment Providers Los Gatos, CA Huawei Telecommunications Shenzhen, Guangdong JD.COM Software Development Show more similar pages Show fewer similar pages Browse jobs Tencent jobs 375 open jobs Intern jobs 71,196 open jobs Analyst jobs 694,057 open jobs Engineer jobs 555,845 open jobs Project Manager jobs 253,048 open jobs Manager jobs 1,880,925 open jobs Graduate jobs 361,130 open jobs Scientist jobs 48,969 open jobs Specialist jobs 768,666 open jobs Marketing Manager jobs 106,879 open jobs Designer jobs 65,273 open jobs Developer jobs 258,935 open jobs Associate jobs 1,091,945 open jobs Director jobs 1,220,357 open jobs Human Resources Specialist jobs 34,340 open jobs Site Reliability Engineer jobs 169,128 open jobs Executive jobs 690,514 open jobs Software Engineer jobs 300,699 open jobs Account Manager jobs 121,519 open jobs Accountant jobs 91,739 open jobs Show more jobs like this Show fewer jobs like this Funding Tencent 7 total rounds Last Round Post IPO debt Oct 16, 2025 External Crunchbase Link for last round of funding US$ 1.3B See more info on crunchbase More searches More searches Tencent jobs Intern jobs Engineer jobs Analyst jobs Manager jobs Developer jobs Software Engineer jobs Project Manager jobs Graduate jobs Designer jobs Scientist jobs Associate jobs 3D Artist jobs Product Manager jobs Director jobs Researcher jobs Consultant jobs Human Resources Specialist jobs Specialist jobs Data Analyst jobs Producer jobs Recruiter jobs Legal Counsel jobs Animator jobs User Experience Designer jobs Business Development Specialist jobs Site Reliability Engineer jobs User Experience Researcher jobs Artist jobs Head jobs Machine Learning Engineer jobs Human Resources Intern jobs Marketing Manager jobs Executive jobs Partner jobs Summer Intern jobs Data Scientist jobs Marketing Specialist jobs Character Artist jobs Translator jobs Sales Manager jobs Software Intern jobs Administrator jobs Trader jobs Account Executive jobs Moderator jobs Accountant jobs Financial Analyst jobs Graduate Software Engineer jobs Technical Artist jobs Data Engineer jobs Marketing Intern jobs Human Resources Business Partner jobs Team Lead jobs Concept Artist jobs Community Manager jobs Product Designer jobs Coordinator jobs Account Manager jobs Operational Specialist jobs LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Sign in to see who you already know at Tencent Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/messagebird-com-messagebird/?trk=products_details_guest_similar_products_section_similar_products_section_product_link_result-card_image-click | MessageBird | LinkedIn Skip to main content LinkedIn Bird in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in MessageBird Cloud Communications Platforms by Bird See who's skilled in this Add as skill Learn more Report this product About APIs, tools, customer support software, and a global connectivity network to elevate business to customer relationships. Media Products media viewer No more previous content No more next content Similar products Slack Slack Cloud Communications Platforms Tencent Cloud Instant Messaging (IM) Tencent Cloud Instant Messaging (IM) Cloud Communications Platforms Avaya Cloud Office Avaya Cloud Office Cloud Communications Platforms Vonage Communications APIs Vonage Communications APIs Cloud Communications Platforms CPaaS CPaaS Cloud Communications Platforms Channelize.io: Live Stream Shopping Platform Channelize.io: Live Stream Shopping Platform Cloud Communications Platforms Sign in to see more Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2Fdigitaleconomycouncil&trk=organization_guest_main-feed-card_social-actions-reactions | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Remember me First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Follow top companies Over 60% of the fortune 100 companies use LinkedIn to hire. Join now Leave | 2026-01-13T09:29:17 |
https://visualstudio.microsoft.com/tr/vs/ | Visual Studio IDE - Kodlama, hata ayıklama ve test için yapay zeka Ana içeriğe atla Microsoft Visual Studio Visual Studio Visual Studio Giriş Geliştirici Araçları Visual Studio Visual Studio Genel Bakış Özellikler Sürümler Uzantılar Kullanmaya Başlayın Hizmet Durumu SSS Desteği Belgeler Blog Visual Studio Code Visual Studio Code Genel Bakış Uzantılar Destek Belgeler Blog Eğitim için VS Code İndirmeler Satın alın Abonelikler Genel Bakış Destek Yönetici Portalı Abone Portalı Dev Essentials Visual Studio Hub Daha fazla Ücretsiz Visual Studio Tüm Microsoft Global Microsoft Güvenlik Azure Dynamics 365 Microsoft 365 Microsoft Teams Windows 365 Teknoloji ve yenilik Teknoloji ve yenilik Yapay Zeka Azure Space Karma gerçeklik Microsoft HoloLens Microsoft Viva Kuantum hesaplama Sürdürülebilirlik Sektörler Sektörler Eğitim Otomotiv Finansal hizmetler Kamu sektörü Sağlık Üretim Perakende Tüm sektörler İş ortakları İş ortakları İş ortağı bulun İş ortağı olun İş Ortakları Ağı Microsoft Marketplace Marketplace Rewards Software development companies Kaynaklar Kaynaklar Blog Microsoft Advertising Geliştirici Merkezi Belgeler Etkinlikler Lisanslama Microsoft Learn Microsoft Research Site Haritasını Göster Oturum aç This device is not currently supported for these products. Visual Studio IDE Visual Studio for Mac Visual Studio Code To continue downloading, click here Visual Studio IDE – Kodlama, hata ayıklama ve test için yapay zeka 2025-12-08T11:16:15-08:00 Yapay zeka ile daha akıllı hale getirilmiş güçlü IDE Aracı modu – artık GitHub Copilot Ücretsiz’de kullanılabilir Sorunları çözen, sonraki adımları koordine eden, değişiklikleri uygulayan ve hataları yineleyen yapay zeka destekli kodlama yardımını deneyimleyin. Visual Studio'yu indirin Community Professional Enterprise Insiders Ücretsiz olarak kullanmaya başlayın Üretkenliği artıran yapay zeka yardımı Aracı moduna sahip gerçek yapay zeka çözümleri Bir istemden planlayın, derleyin, test edin ve düzeltin. İhtiyacınızı doğal bir dil ile açıklayın, gerisini Copilot halletsin. Linter’lar, testler ve komutları Visual Studio’dan çıkmadan çalıştırın. Aracı modunu bugün etkinleştirin Her zaman güncel yapay zeka modelleri Sohbet veya satır içinde en doğru, bağlama duyarlı önerilere erişmek için en son yapay zeka modellerini kullanın. Her görevin gereksinimlerine uygun bir model seçeneğini belirtin. En yeni modelleri alın Ücretsiz ve Visual Studio'ya tamamen tümleştirilmiş Yapay zeka destekli kodlama yardımı, Visual Studio’ya tümleştirilmiştir. 2.000 kod tamamlaması alın. Ayda ücretsiz 50 sohbet mesajı edinin. Copilot Ücretsiz'i etkinleştirin GitHub Copilot’ı çalışırken izleyin Bir daha asla commit mesajı yazmayın: GitHub Copilot'a teşekkürler Visual Studio'da GitHub Copilot için Çoklu Dosya Düzenleme Visual Studio'da GitHub Copilot Ücretsiz'i kullanmaya başlayın Visual Studio ile ilgili her şeyden haberdar olun Visual Studio Merkezi'ni ziyaret edin Geliştirme Hata Ayıkla Test edin Sürüm Denetimi İşbirliği yapın Bulut Tasarım Profil Veri Copilot: çift programcınız Tek bir satır veya tüm kod parçacığı için bağlama duyarlı kod tamamlama önerileriyle geliştirmeyi hızlandırın. Kod gözden geçirme, dosya içi önizleme ve geri alma deneyimi ile çoklu dosya düzenleme için Copilot Edits’i kullanın. Kod önerileri için Copilot’ı kullanın Kod ve sorgularla ilgili yardım almak için sohbet edin GitHub Copilot Chat ile kodlama sorgularınız için gerçek zamanlı yardım alın. Konuşma tarzı Sohbet arabirimi, anında bağlam duyarlı öneriler sunar, hata ayıklamaya yardımcı olur ve ünite testleri oluşturur; hepsi geliştirme ortamınızda. Copilot Chat sonuçlarını iyileştirmek için ipuçları Copilot ile hata ayıklama kolaylaştı AI ile güçlendirilmiş kodunuza yönelik derin içgörülerle hata ayıklamayı hızlandırın. Copilot, istisnalar, kilitlenmeler ve diğer hata ayıklama senaryoları için hedefli çözümler sunmak üzere derinlemesine analizler ve açıklamalar sağlar. Hata ayıklama işleminizi kolaylaştırın Copilot ile test verimliliğini artırın El ile test oluşturma ve kod kalitesini koruma için harcanan zamanı azaltın. Copilot’ın otomasyonu, mevcut kodunuza dayalı ünite ve tümleştirme testleriyle hataları erken tespit ederek güvenilirliği artırmanıza yardımcı olur. Hataları düzeltmek için copilot’ı kullanın Copilot’ı sürüm kontrolünü basitleştirmek için kullanın Kod değişikliklerine dayalı olarak AI tarafından oluşturulan işleme iletileriyle temiz ve düzenli bir kod temeli oluşturun. GitHub Copilot, iş akışınızda, dal yönetiminde ve birleştirme çakışmalarında netlik sağlayarak sürüm kontrolünüzü basitleştirir. GitHub Copilot Chat ile işleme iletileri oluşturun Ekran paylaşımının ötesine geçin Live Share’ın gerçek zamanlı işbirliği oturumları, kullanılan dilden veya platformdan bağımsız olarak ekibinizin düzenleme ve hata ayıklama döngülerini hızlandırır. Erişim denetimleri ve özel düzenleyici ayarlarına sahip kişiselleştirilmiş oturumlar, herkesin kod yazma deneyiminin tutarlılığını sağlar. Live Share aracılığıyla işbirliği Visual Studio’da Azure Visual Studio’da Azure ile derleyin, dağıtın ve ölçeklendirin: IDE’nizin içindeki tümleşik araçları ve yapay zeka özelliklerini kullanarak bulut öncelikli uygulamaları verimli ve güvenli bir şekilde oluşturun. Web uygulamaları, API’ler veya yapay zeka destekli çözümler geliştirirken Visual Studio, kodlamayı kolaylaştırmak için sorunsuz Azure tümleştirme sunar. Azure DevOps ve GitHub Actions ile öğreticileri keşfedin, kodlama becerilerinizi geliştirin ve dağıtımları otomatikleştirin. Visual Studio’nun güçlü araçlarıyla Azure hizmetlerine bağlanın, uygulamaları dağıtın ve gerçek zamanlı hata ayıklama yapın. Visual Studio’da Azure hakkında daha fazla bilgi edinin Harika platformlar arası uygulamalar tasarlayın Visual Studio, Windows, Mac, Linux, iOS ve Android için modern, çapraz platform uygulamaları oluşturmak için en iyi IDE’dir. Karmaşık düzenleri basitleştiren ve kullanıcı arabiriminizi hayata geçiren güçlü görsel tasarımcılar kullanarak WinForms, WPF, WinUI ve MAUI ile zengin istemci uygulamaları oluşturun. Görselleştirme ve modelleme Yerleşik profil oluşturma araçlarıyla hızlı ve duyarlı uygulamalar derleyin Web ve istemci için hızlı ve duyarlı .NET ve C++ uygulamaları derlemek için Visual Studio’daki profil oluşturma araçlarını kullanın. CPU, bellek, XAML, veritabanları, olaylar ve daha fazlası için kullanabileceğiniz profil oluşturucular ile performans sorunlarını tanımlayıp çözmenize yardımcı olan eksiksiz bir araç paketine sahip olursunuz. Uygulama performansını ölçün SOL’i kolaylaştıran araçlar IDE’den ayrılmadan SQL projeleriyle çalışın. Zengin düzenleme deneyimleri ile sorgular oluşturun, sunucuları ve veritabanlarını görüntüleyin ve keşfedin. Veritabanı şemalarını ve sorgularını tamamen Visual Studio’dan görselleştirin. Visual Studio’da verilere erişim Size özel hale getirin Herhangi bir modern geliştirme aracından tıpkı beklediğiniz şekilde yapılandırıp tema oluşturun. İster zaten yüklü olan varsayılan temalardan birini seçin, ister Visual Studio Market’teki yeni temaları keşfedin, düzenleyicinizi veya IDE’nizi gerçekten size özel hale getirme özgürlüğüne sahipsiniz. Temaları keşfedin Uzantılarla daha da ileriye taşıyın Uzantılar; mevcut araçlar için ek ayarlar, özellikler veya kullanımlar dahil olmak üzere Visual Studio’yu özelleştiren ve geliştiren eklentilerdir. Markette sunulan binlerce uzantıyla, üretkenliğinizi artırmak ve iş akışınızın gereksinimlerini karşılamak için çok sayıda seçeneğe sahip olursunuz. Uzantıları Keşfedin GitHub Actions Yüklemeler Visual Studio'da açılan çözümün geçerli deposu için GitHub Actions'ı görüntüleyen bir pencere. @timheuer tarafından sağlanmıştır Uzantıyı edinin Markdown Editor v2 Yüklemeler Canlı önizleme ve sözdizimi vurgulaması özelliklerine sahip tam işlevli bir Markdown editor. GitHub tarzı Markdown'u destekler. Uzantıyı Edinin Visual Studio Tema Paketi Yüklemeler Popüler temalar koleksiyonu şimdi Visual Studio ile kullanılabilir. Daha fazla bilgi SQLite ve SQL Server Compact Araç Kutusu Yüklemeler Bu uzantı, eklediğiniz veritabanı geliştirme çalışmalarınıza yardımcı olacak çeşitli özellikler ekler. Uzantıyı Edinin Visual Studio Community Öğrenciler, açık kaynak ve bireysel geliştiriciler için ücretsiz, tam özellikli IDE. Daha fazla bilgi Ücretsiz indirin Visual Studio Professional Küçük ekipler arasında verimli işbirliği için güçlü geliştirici araçları, hizmetler ve abonelik avantajları. Daha fazla bilgi edinin Ücretsiz deneme Visual Studio Enterprise Gelişmiş hata ayıklama, kurumsal güvenlik, yapay zeka destekli geliştirme ve bulut için Azure Kredileri ve Dev/Test fiyatlandırması. Daha fazla bilgi edinin Ücretsiz deneme Bizi takip edin Dev Essentials Developer Community Bloglar: Visual Studio .NET C++ Yenilikler Kuruluşlar için Copilot Kişisel kullanım için Copilot Microsoft 365 Microsoft ürünlerini keşfedin Windows 11 uygulamaları Microsoft Store Hesap profili İndirme Merkezi Microsoft Store Desteği İadeler Sipariş izleme Eğitim Microsoft Eğitim Eğitim cihazları Eğitim için Microsoft Teams Microsoft 365 Eğitim Office Eğitimi Eğitimci eğitimi ve gelişimi Öğrenciler ve ebeveynler için fırsatlar Öğrenciler için Azure İşletme Microsoft Güvenlik Azure Dynamics 365 Microsoft 365 Microsoft Advertising Microsoft 365 Copilot Microsoft Teams Geliştirici ve BT Microsoft Geliştiricisi Microsoft Learn Yapay zeka market uygulamaları için destek Microsoft Tech Community Microsoft Marketplace Microsoft Power Platform Marketplace Rewards Visual Studio Şirket Kariyer Fırsatları Microsoft Hakkında Microsoft'ta Gizlilik Yatırımcılar Sürdürülebilirlik Türkçe (Türkiye) Gizlilik Tercihleriniz Geri Çevirme Simgesi Gizlilik Tercihleriniz Gizlilik Tercihleriniz Geri Çevirme Simgesi Gizlilik Tercihleriniz Tüketici Durumu Gizliliği Bize ulaşın Gizlilik ve tanımlama bilgileri Tanımlama bilgilerini yönetin Kullanım koşulları Ticari Markalar Reklamlarımız hakkında © Microsoft 2026 | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/servicenow-now-platform/?trk=products_seo_search | ServiceNow AI Platform | LinkedIn Skip to main content LinkedIn ServiceNow in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in ServiceNow AI Platform Business Process Management Software by ServiceNow See who's skilled in this Add as skill Learn more Report this product About The ServiceNow AI Platform is built for a new era. One platform, ready for anything. Put any AI, any data, any workflow, and any industry to work across the enterprise. Media Products media viewer No more previous content ServiceNow AI Platform ServiceNow AI Platform No more next content Similar products Amdocs TechInsights Amdocs TechInsights Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less ServiceNow products ServiceNow App Engine ServiceNow App Engine Low-Code Development Platforms LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/posts/digitaleconomycouncil_registration-is-open-for-day-two-of-the-2026-activity-7414805050742603776-fx8o | Registration is open for Day Two of the 2026 DECA Policy Forum. Day Two will take place on 11 February at Parliament House, Canberra, during the first sitting week of Parliament. The program… | Digital Economy Council of Australia (DECA) Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Join now Digital Economy Council of Australia (DECA)’s Post Digital Economy Council of Australia (DECA) 16,292 followers 5d Report this post Registration is open for Day Two of the 2026 DECA Policy Forum. Day Two will take place on 11 February at Parliament House, Canberra, during the first sitting week of Parliament. The program features a series of plenary sessions designed to brief and inform on the policy, regulatory and economic frameworks shaping Australia’s digital assets and emerging digital infrastructure. Attendance is open to all including parliamentarians, ministerial advisers, regulators and public sector stakeholders. DECA members receive complimentary registration. Guests are welcome to attend a single session or remain for the full program. 📍 Parliament House 📅 11 February 2026 🔗 More information and registration: https://lnkd.in/guJv5vHs 5 1 Comment Like Comment Share Copy LinkedIn Facebook X Tubby Hubby 2d Report this comment Sponsors Ripple No more previous content No more next content Like Reply 1 Reaction To view or add a comment, sign in 16,292 followers View Profile Connect Explore content categories Career Productivity Finance Soft Skills & Emotional Intelligence Project Management Education Technology Leadership Ecommerce User Experience Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Sign in to view more content Create your free account or sign in to continue your search Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:17 |
https://www.linkedin.com/posts/activity-7400129834825191425-UPMB | Matthew Hussey / 320 Media is looking for a Social Media Moderator & Editor to join our team on a short term contract this January 🔥 If you have experience editing short form videos, creating… | Celia Bradfield Agree & Join LinkedIn By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . Skip to main content LinkedIn Top Content People Learning Jobs Games Sign in Create an account Celia Bradfield’s Post Celia Bradfield 1mo Report this post Matthew Hussey / 320 Media is looking for a Social Media Moderator & Editor to join our team on a short term contract this January 🔥 If you have experience editing short form videos, creating posters using Canva templates and connecting with real people to guide them towards the help they need, we'd love to hear from you👇 Check out the ad below for details on how to apply. Social Media Moderator & Editor Matthew Hussey / 320 Media, United Kingdom 8 4 Comments Like Comment Share Copy LinkedIn Facebook X Hagar Hussein 1mo Report this comment I am very interested Like Reply 1 Reaction To view or add a comment, sign in 2,231 followers 38 Posts View Profile Connect Explore content categories Career Productivity Finance Soft Skills & Emotional Intelligence Project Management Education Technology Leadership Ecommerce User Experience Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Sign in to view more content Create your free account or sign in to continue your search Sign in Welcome back Email or phone Password Show Forgot password? Sign in or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . New to LinkedIn? Join now or New to LinkedIn? Join now By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fcategories%2Fbusiness-process-management-software&fromSignIn=true&trk=products_seo_search_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/amdocs-techinsights/?trk=products_seo_search | Amdocs TechInsights | LinkedIn Skip to main content LinkedIn Amdocs in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Amdocs TechInsights Business Process Management Software by Amdocs See who's skilled in this Add as skill Learn more Report this product About Enable operational services for mobile network rollouts involving multiple teams and scopes of work Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less Amdocs products Amdocs CatalogONE Amdocs CatalogONE Catalog Management Software Amdocs Customer Engagement Amdocs Customer Engagement Customer Engagement Software Amdocs Freestyle Billing Amdocs Freestyle Billing Billing & Invoicing Software Amdocs Low-Code Experience Platform Amdocs Low-Code Experience Platform Low-Code Development Platforms Amdocs MarketONE Amdocs MarketONE OTT Platforms Amdocs Microservices Management Platform Amdocs Microservices Management Platform Platform as a Service (PaaS) Software Real-Time Billing Real-Time Billing Billing & Invoicing Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://lnkd.in/gcZKhB6z?trk=organization_guest_main-feed-card-text | LinkedIn LinkedIn This link will take you to a page that’s not on LinkedIn Because this is an external link, we’re unable to verify it for safety. https://urldefense.com/v3/__https://bit.ly/4pqHxeE__;!!PEZBYkTc!ZFb3x0HPK5ykNPcMYpHyORREfOBwA_rRA3VXXDAHhw5vfm-iZsggzLQhFQZD52i6sru4k_zRFQRpiqEXbizuE7I$ This experience is optimized for Chrome, Edge, and Safari Have questions? Learn more | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww.linkedin.com%2Ffeed%2Fhashtag%2Fblackswansummitaustralia&trk=organization_guest_main-feed-card-text | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Keep me logged in First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Follow top companies Over 60% of the fortune 100 companies use LinkedIn to hire. Join now Leave | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/amdocs-techinsights/?trk=products_seo_search | Amdocs TechInsights | LinkedIn Skip to main content LinkedIn Amdocs in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Amdocs TechInsights Business Process Management Software by Amdocs See who's skilled in this Add as skill Learn more Report this product About Enable operational services for mobile network rollouts involving multiple teams and scopes of work Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less Amdocs products Amdocs CatalogONE Amdocs CatalogONE Catalog Management Software Amdocs Customer Engagement Amdocs Customer Engagement Customer Engagement Software Amdocs Freestyle Billing Amdocs Freestyle Billing Billing & Invoicing Software Amdocs Low-Code Experience Platform Amdocs Low-Code Experience Platform Low-Code Development Platforms Amdocs MarketONE Amdocs MarketONE OTT Platforms Amdocs Microservices Management Platform Amdocs Microservices Management Platform Platform as a Service (PaaS) Software Real-Time Billing Real-Time Billing Billing & Invoicing Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fservices%2Fproducts%2Fcybereason-enterprise%2F&fromSignIn=true&trk=products_details_guest_nav-header-signin | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/hclsoftware-hcl-domino/?trk=products_seo_search | HCL Domino | LinkedIn Skip to main content LinkedIn HCLSoftware in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in HCL Domino Business Process Management Software by HCLSoftware See who's skilled in this Add as skill Learn more Report this product About HCL Domino is an enterprise-grade and secure application development platform designed to solve workflow and process challenges — fast. It powers more than 10 million apps transforming the business of more than 15,000 customers. Domino is more modern and offers more value and lower TCO than ever. Now you can make your apps mobile with zero effort and build new ones 70% faster than before. Domino also provides an enterprise-grade mail, calendar, and contacts platform. The platform is associated with Notes, a professional secure on-premises client which allows users to execute the enterprise applications from their desktop (including the mail client), in a connected or disconnected way. This product is intended for Application Architect Application Development Manager Chief Technical Officer Head Business System Lotus Notes Consultant Domino Administrator Business Application Consultant Lotus Domino Administrator Domino Developer Lotus Notes Domino Developer Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software Amdocs TechInsights Amdocs TechInsights Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less HCLSoftware products HCL BigFix HCL BigFix Endpoint Detection & Response (EDR) Software HCL Commerce+ HCL Commerce+ E-Commerce Platforms HCL Connections HCL Connections Enterprise Social Networking Software HCL Digital Experience HCL Digital Experience Digital Experience Platforms (DXP) HCL Mainframe Solutions HCL Mainframe Solutions Mainframe Management Software HCL Sametime HCL Sametime Employee Communications Software HCL Software DevOps HCL Software DevOps DevOps Software HCL Unica HCL Unica Marketing Automation Software HCL Volt MX HCL Volt MX Low-Code Development Platforms Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=%2Fservices%2Fproducts%2Flarksuite-lark%2F&trk=products_details_guest_nav-header-join | Sign Up | LinkedIn Make the most of your professional life Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language Takes less than 2 minutes Join LinkedIn to connect with people, jobs and opportunities that matter Join now Leave | 2026-01-13T09:29:17 |
https://www.linkedin.com/uas/login?session_redirect=%2Fproducts%2Flarksuite-lark&trk=products_details_guest_primary_call_to_action | LinkedIn Login, Sign in | LinkedIn Sign in Sign in with Apple Sign in with a passkey By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . or Email or phone Password Show Forgot password? Keep me logged in Sign in We’ve emailed a one-time link to your primary email address Click on the link to sign in instantly to your LinkedIn account. If you don’t see the email in your inbox, check your spam folder. Resend email Back New to LinkedIn? Join now Agree & Join LinkedIn By clicking Continue, you agree to LinkedIn’s User Agreement , Privacy Policy , and Cookie Policy . LinkedIn © 2026 User Agreement Privacy Policy Community Guidelines Cookie Policy Copyright Policy Send Feedback Language العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) | 2026-01-13T09:29:17 |
https://www.linkedin.com/signup/cold-join?session_redirect=https%3A%2F%2Fwww%2Elinkedin%2Ecom%2Fcompany%2Fdigitaleconomycouncil&trk=organization_guest_main-feed-card_comment-cta | Sign Up | LinkedIn Join LinkedIn now — it’s free! Not you? Remove photo Join LinkedIn To create a LinkedIn account, you must understand how LinkedIn processes your personal information by selecting learn more for each item listed. Agree to all terms We collect and use personal information. Learn more We share personal information with third parties to provide our services. Learn more Further information is available in our Korea Privacy Addendum . Privacy Policy Addendum 1 of 2 2 of 2 Agree to the term Continue Back Agree to all terms Email Password Show Remember me First name Last name By clicking Agree & Join, you agree to the LinkedIn User Agreement , Privacy Policy , and Cookie Policy . Agree & Join or Security verification Already on LinkedIn? Sign in Looking to create a page for a business? Get help LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines العربية (Arabic) বাংলা (Bangla) Čeština (Czech) Dansk (Danish) Deutsch (German) Ελληνικά (Greek) English (English) Español (Spanish) فارسی (Persian) Suomi (Finnish) Français (French) हिंदी (Hindi) Magyar (Hungarian) Bahasa Indonesia (Indonesian) Italiano (Italian) עברית (Hebrew) 日本語 (Japanese) 한국어 (Korean) मराठी (Marathi) Bahasa Malaysia (Malay) Nederlands (Dutch) Norsk (Norwegian) ਪੰਜਾਬੀ (Punjabi) Polski (Polish) Português (Portuguese) Română (Romanian) Русский (Russian) Svenska (Swedish) తెలుగు (Telugu) ภาษาไทย (Thai) Tagalog (Tagalog) Türkçe (Turkish) Українська (Ukrainian) Tiếng Việt (Vietnamese) 简体中文 (Chinese (Simplified)) 正體中文 (Chinese (Traditional)) Language | 2026-01-13T09:29:17 |
https://www.linkedin.com/products/amdocs-techinsights/?trk=products_seo_search | Amdocs TechInsights | LinkedIn Skip to main content LinkedIn Amdocs in Asan Expand search This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection. Jobs People Learning Clear text Clear text Clear text Clear text Clear text Join now Sign in Amdocs TechInsights Business Process Management Software by Amdocs See who's skilled in this Add as skill Learn more Report this product About Enable operational services for mobile network rollouts involving multiple teams and scopes of work Similar products ServiceNow AI Platform ServiceNow AI Platform Business Process Management Software HCL Domino HCL Domino Business Process Management Software Skan AI Process Intelligence Platform Skan AI Process Intelligence Platform Business Process Management Software Business Cockpit Business Cockpit Business Process Management Software CaseXellence CaseXellence Business Process Management Software Decisions Decisions Business Process Management Software Sign in to see more Show more Show less Amdocs products Amdocs CatalogONE Amdocs CatalogONE Catalog Management Software Amdocs Customer Engagement Amdocs Customer Engagement Customer Engagement Software Amdocs Freestyle Billing Amdocs Freestyle Billing Billing & Invoicing Software Amdocs Low-Code Experience Platform Amdocs Low-Code Experience Platform Low-Code Development Platforms Amdocs MarketONE Amdocs MarketONE OTT Platforms Amdocs Microservices Management Platform Amdocs Microservices Management Platform Platform as a Service (PaaS) Software Real-Time Billing Real-Time Billing Billing & Invoicing Software Show more Show less LinkedIn © 2026 About Accessibility User Agreement Privacy Policy Cookie Policy Copyright Policy Brand Policy Guest Controls Community Guidelines English (English) Language | 2026-01-13T09:29:17 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.