problems.json

[
    {
        "id": 1,
        "title": "Broken CLI Argument Parser",
        "difficulty": "Easy",
        "description": "Fix a command-line tool that parses user input to determine file operations (read, write, append). The implementation uses enums and pattern matching but contains: Mismatched types in enum variants, Incomplete match arms, Incorrect handling of optional arguments. The parser must compile and correctly interpret valid command-line inputs like: 'read file.txt' -> FileOp::Read('file.txt'), 'write file.txt content' -> FileOp::Write('file.txt', Some('content')), 'append file.txt' -> FileOp::Append('file.txt')",
        "header_section": "#[derive(Debug, PartialEq)]\nenum FileOp {\n    Read(String),\n    Write(String, Option<String>),\n    Append(String),\n}\n\nfn parse_command(input: &str) -> Option<FileOp> {\n    let parts: Vec<&str> = input.split_whitespace().collect();\n    \n    match parts.get(0) {\n        Some(&\"read\") => {\n            let filename = parts.get(1)?;\n            FileOp::Read(filename.to_string())  // BUG: Missing Some()\n        }\n        Some(&\"write\") => {\n            let filename = parts.get(1)?;\n            let content = parts.get(2).map(|s| s.to_string());\n            Some(FileOp::Write(filename.to_string(), content))\n        }\n        Some(&\"append\") => {\n            let filename = parts.get(1)?;\n            // BUG: Missing return statement\n        }\n        _ => None,\n    }\n}\n\nfn main() {\n    println!(\"CLI Parser Test\");\n}",
        "tests": [
            {
                "name": "parse_read_command",
                "input_code": "parse_command(\"read file.txt\")",
                "expected_output": "Some\\(FileOp::Read\\(\"file\\.txt\"\\)\\)",
                "should_compile": false,
                "test_assertion": "assert_eq!(parse_command(\"read file.txt\"), Some(FileOp::Read(\"file.txt\".to_string())))"
            },
            {
                "name": "parse_write_command",
                "input_code": "parse_command(\"write file.txt hello\")",
                "expected_output": "Some\\(FileOp::Write\\(\"file\\.txt\", Some\\(\"hello\"\\)\\)\\)",
                "should_compile": false,
                "test_assertion": "assert_eq!(parse_command(\"write file.txt hello\"), Some(FileOp::Write(\"file.txt\".to_string(), Some(\"hello\".to_string()))))"
            },
            {
                "name": "parse_append_command",
                "input_code": "parse_command(\"append file.txt\")",
                "expected_output": "Some\\(FileOp::Append\\(\"file\\.txt\"\\)\\)",
                "should_compile": false,
                "test_assertion": "assert_eq!(parse_command(\"append file.txt\"), Some(FileOp::Append(\"file.txt\".to_string())))"
            }
        ],
        "performance_baseline_ms": 10.0
    },
    {
        "id": 2,
        "title": "Conflicting Borrows in Collection Processing",
        "difficulty": "Easy\u2192Medium",
        "description": "Fix a function that processes a vector of strings while conditionally modifying elements and storing references for later use. The implementation mixes mutable and immutable borrows within the same scope, causing borrow checker conflicts. Requirements: Iterate through vector of strings, Store uppercase versions in a results vector, Handle optional transformations without borrowing conflicts, Must compile and execute without panics",
        "header_section": "fn process_strings(strings: &mut Vec<String>) -> Vec<String> {\n    let mut results = Vec::new();\n    \n    for s in strings {\n        // BUG: Cannot borrow as mutable while immutable borrow is active\n        let upper = s.to_uppercase();\n        s.push_str(\"_processed\");  // Mutable borrow\n        results.push(upper);\n    }\n    \n    results\n}\n\nfn main() {\n    println!(\"String processing\");\n}",
        "tests": [
            {
                "name": "process_single_string",
                "input_code": "let mut v = vec![\"hello\".to_string()]; process_strings(&mut v);",
                "should_compile": false,
                "test_assertion": "assert_eq!(process_strings(&mut vec![\"hello\".to_string()]), vec![\"HELLO\".to_string()])"
            },
            {
                "name": "process_multiple_strings",
                "input_code": "let mut v = vec![\"a\".to_string(), \"b\".to_string()]; process_strings(&mut v);",
                "should_compile": false,
                "test_assertion": "assert_eq!(process_strings(&mut vec![\"a\".to_string(), \"b\".to_string()]), vec![\"A\".to_string(), \"B\".to_string()])"
            }
        ],
        "performance_baseline_ms": 50.0
    },
    {
        "id": 3,
        "title": "Invalid Lifetime Annotations in Text API",
        "difficulty": "Medium",
        "description": "Fix a text-processing utility that accepts multiple string slices and returns a reference derived from them. The function either fails to compile or produces incorrect lifetime relationships, risking references that outlive their input data. Requirements: Function must accept multiple &str parameters, Return a &str derived from the inputs, Properly annotate lifetimes, Must be safe (no dangling references)",
        "header_section": "// BUG: Invalid lifetime annotations - which lifetime should the return type use?\nfn longest_text<'a>(s1: &'a str, s2: &'a str) -> &'a str {\n    if s1.len() > s2.len() {\n        s1\n    } else {\n        s2\n    }\n}\n\n// BUG: This function has a lifetime issue\nfn find_first_word(s: &str) -> &str {\n    let bytes = s.as_bytes();\n    for (i, &byte) in bytes.iter().enumerate() {\n        if byte == b' ' {\n            return &s[0..i];\n        }\n    }\n    &s[..]\n}\n\nfn main() {\n    println!(\"Lifetime test\");\n}",
        "tests": [
            {
                "name": "longest_text_basic",
                "input_code": "longest_text(\"abc\", \"de\")",
                "expected_output": "\"abc\"",
                "should_compile": true,
                "test_assertion": "assert_eq!(longest_text(\"abc\", \"de\"), \"abc\")"
            },
            {
                "name": "find_first_word_with_space",
                "input_code": "find_first_word(\"hello world\")",
                "expected_output": "\"hello\"",
                "should_compile": true,
                "test_assertion": "assert_eq!(find_first_word(\"hello world\"), \"hello\")"
            },
            {
                "name": "find_first_word_no_space",
                "input_code": "find_first_word(\"hello\")",
                "expected_output": "\"hello\"",
                "should_compile": true,
                "test_assertion": "assert_eq!(find_first_word(\"hello\"), \"hello\")"
            }
        ],
        "performance_baseline_ms": 10.0
    },
    {
        "id": 4,
        "title": "Business Logic Producing Incorrect Results",
        "difficulty": "Medium",
        "description": "Fix a module implementing order validation logic including pricing, discounts, and boundary conditions. The code compiles but produces incorrect outputs for edge cases such as: Zero values, Overlapping discounts, Large numeric inputs, Negative prices. Requirements: Calculate order total correctly, Apply discounts properly (no double-counting), Handle edge cases (zero items, negative values), Be mathematically sound",
        "header_section": "#[derive(Debug, Clone)]\nstruct Order {\n    quantity: i32,\n    unit_price: f64,\n    discount_percent: f64,\n}\n\nimpl Order {\n    fn new(quantity: i32, unit_price: f64) -> Self {\n        Order {\n            quantity,\n            unit_price,\n            discount_percent: 0.0,\n        }\n    }\n\n    fn with_discount(mut self, discount: f64) -> Self {\n        self.discount_percent = discount;\n        self\n    }\n\n    fn calculate_total(&self) -> f64 {\n        let subtotal = self.quantity as f64 * self.unit_price;\n        // BUG: Incorrect discount calculation\n        let discount = subtotal * (self.discount_percent / 100.0);\n        subtotal - discount  // Missing rounding/validation\n    }\n}\n\nfn main() {\n    println!(\"Order test\");\n}",
        "tests": [
            {
                "name": "simple_order",
                "input_code": "Order::new(10, 5.0).calculate_total()",
                "expected_output": "50\\.0",
                "should_compile": true,
                "test_assertion": "assert_eq!(Order::new(10, 5.0).calculate_total(), 50.0)"
            },
            {
                "name": "order_with_discount",
                "input_code": "Order::new(10, 5.0).with_discount(10.0).calculate_total()",
                "expected_output": "45\\.0",
                "should_compile": true,
                "test_assertion": "assert_eq!(Order::new(10, 5.0).with_discount(10.0).calculate_total(), 45.0)"
            },
            {
                "name": "zero_quantity",
                "input_code": "Order::new(0, 5.0).calculate_total()",
                "expected_output": "0\\.0",
                "should_compile": true,
                "test_assertion": "assert_eq!(Order::new(0, 5.0).calculate_total(), 0.0)"
            }
        ],
        "performance_baseline_ms": 10.0
    },
    {
        "id": 5,
        "title": "Corrupted Singly Linked List",
        "difficulty": "Medium\u2192Hard",
        "description": "Fix a custom singly linked list that supports insertion, deletion, and traversal. The implementation incorrectly manages node ownership and pointer transitions, resulting in: Lost nodes, Inconsistent traversal output, Occasional runtime panics. Requirements: Insert elements at head, Delete elements correctly, Traverse without panics, No memory leaks or lost data",
        "header_section": "use std::ptr;\n\n#[derive(Debug)]\nstruct Node<T> {\n    value: T,\n    next: Option<Box<Node<T>>>,\n}\n\n#[derive(Debug)]\nstruct LinkedList<T> {\n    head: Option<Box<Node<T>>>,\n}\n\nimpl<T> LinkedList<T> {\n    fn new() -> Self {\n        LinkedList { head: None }\n    }\n\n    fn insert(&mut self, value: T) {\n        let new_node = Box::new(Node {\n            value,\n            next: None,  // BUG: Should move self.head into next\n        });\n        self.head = Some(new_node);\n    }\n\n    fn len(&self) -> usize {\n        let mut count = 0;\n        let mut current = &self.head;\n        while let Some(node) = current {\n            count += 1;\n            current = &node.next;  // Correct, but insert is broken\n        }\n        count\n    }\n}\n\nfn main() {\n    println!(\"LinkedList test\");\n}",
        "tests": [
            {
                "name": "insert_single_element",
                "input_code": "let mut ll = LinkedList::new(); ll.insert(5); ll.len()",
                "expected_output": "1",
                "should_compile": true,
                "test_assertion": "let mut ll = LinkedList::new(); ll.insert(5); assert_eq!(ll.len(), 1)"
            },
            {
                "name": "insert_multiple_elements",
                "input_code": "let mut ll = LinkedList::new(); ll.insert(1); ll.insert(2); ll.insert(3); ll.len()",
                "expected_output": "3",
                "should_compile": true,
                "test_assertion": "let mut ll = LinkedList::new(); ll.insert(1); ll.insert(2); ll.insert(3); assert_eq!(ll.len(), 3)"
            }
        ],
        "performance_baseline_ms": 20.0
    },
    {
        "id": 6,
        "title": "Deadlock in Multi-threaded Worker System",
        "difficulty": "Hard",
        "description": "Fix a worker system using multiple threads to process jobs from a shared queue protected by synchronization primitives. Under certain workloads, threads block indefinitely due to: Improper lock acquisition order, Shared state handling issues, Missing signal/wake mechanisms. Requirements: Spawn N worker threads, Process jobs from shared queue without deadlock, Handle shutdown gracefully, No panics under load",
        "header_section": "use std::sync::{Arc, Mutex, mpsc};\nuse std::thread;\n\nfn worker_system(num_workers: usize, jobs: Vec<i32>) -> Vec<i32> {\n    let (tx, rx) = mpsc::channel();\n    let rx = Arc::new(Mutex::new(rx));\n    let results = Arc::new(Mutex::new(Vec::new()));\n    \n    let mut handles = vec![];\n    \n    for _ in 0..num_workers {\n        let rx = Arc::clone(&rx);\n        let results = Arc::clone(&results);\n        \n        let handle = thread::spawn(move || {\n            loop {\n                // BUG: Lock acquired but never released before trying to acquire results lock\n                let receiver = rx.lock().unwrap();\n                match receiver.try_recv() {\n                    Ok(job) => {\n                        let result = job * 2;\n                        // BUG: Tries to lock results while still holding rx lock - DEADLOCK\n                        results.lock().unwrap().push(result);\n                    }\n                    Err(_) => break,\n                }\n            }\n        });\n        handles.push(handle);\n    }\n    \n    for job in jobs {\n        let _ = tx.send(job);  // Ignore send errors\n    }\n    drop(tx);\n    \n    for handle in handles {\n        let _ = handle.join();\n    }\n    \n    Arc::try_unwrap(results)\n        .unwrap()\n        .into_inner()\n        .unwrap()\n}\n\nfn main() {\n    println!(\"Worker system test\");\n}",
        "tests": [
            {
                "name": "single_worker_single_job",
                "input_code": "worker_system(1, vec![5])",
                "expected_output": "vec!\\[10\\]",
                "should_compile": true,
                "test_assertion": "assert_eq!(worker_system(1, vec![5]), vec![10])"
            },
            {
                "name": "multiple_workers",
                "input_code": "worker_system(2, vec![1, 2, 3])",
                "expected_output": "vec!\\[(2|4|6)\\].*vec!\\[(2|4|6)\\].*vec!\\[(2|4|6)\\]",
                "should_compile": true,
                "test_assertion": "let mut result = worker_system(2, vec![1, 2, 3]); result.sort(); assert_eq!(result, vec![2, 4, 6])"
            }
        ],
        "performance_baseline_ms": 500.0
    },
    {
        "id": 7,
        "title": "Async Function with Borrowing Conflicts",
        "difficulty": "Hard",
        "description": "Fix an asynchronous function that processes input data and performs non-blocking operations while returning references tied to the input. The implementation violates borrowing constraints in an async context, leading to: Compilation errors when using references across await points, Invalid reference usage. Requirements: Accept &str input, Perform async operation, Return derived reference, Must be sound and compile",
        "header_section": "use std::pin::Pin;\nuse std::future::Future;\n\n// BUG: Cannot return reference that outlives await point\nasync fn process_async(input: &str) -> &str {\n    // Simulating async work\n    // tokio::time::sleep(tokio::time::Duration::from_millis(10)).await;\n    \n    // BUG: input reference cannot be returned from async context like this\n    input\n}\n\n// Better approach: return owned data or 'static reference\nfn process_sync(input: &str) -> String {\n    input.to_uppercase()\n}\n\nfn main() {\n    println!(\"Async test\");\n}",
        "tests": [
            {
                "name": "process_sync_basic",
                "input_code": "process_sync(\"hello\")",
                "expected_output": "\"HELLO\"",
                "should_compile": true,
                "test_assertion": "assert_eq!(process_sync(\"hello\"), \"HELLO\")"
            },
            {
                "name": "process_sync_uppercase",
                "input_code": "process_sync(\"Hello World\")",
                "expected_output": "\"HELLO WORLD\"",
                "should_compile": true,
                "test_assertion": "assert_eq!(process_sync(\"Hello World\"), \"HELLO WORLD\")"
            }
        ],
        "performance_baseline_ms": 50.0
    },
    {
        "id": 8,
        "title": "Unsafe FFI Integration Causing Crashes",
        "difficulty": "Hard",
        "description": "Fix Rust code that interfaces with an external C library using raw pointers. The implementation incorrectly handles: Pointer ownership, Memory allocation and deallocation, Undefined behavior risks. Requirements: Safely wrap C library calls, Properly manage memory (allocate/deallocate), No undefined behavior, Handle errors gracefully",
        "header_section": "extern \"C\" {\n    fn malloc(size: usize) -> *mut u8;\n    fn free(ptr: *mut u8);\n}\n\nfn allocate_and_init(size: usize) -> Vec<u8> {\n    unsafe {\n        let ptr = malloc(size);\n        // BUG: No null check - ptr could be null\n        // BUG: Memory not initialized before use\n        let slice = std::slice::from_raw_parts_mut(ptr, size);\n        \n        // Copy to vec and free\n        let vec = slice.to_vec();\n        free(ptr);  // BUG: Freeing memory still referenced in vec\n        vec\n    }\n}\n\nfn main() {\n    println!(\"FFI test\");\n}",
        "tests": [
            {
                "name": "allocate_small_buffer",
                "input_code": "allocate_and_init(10).len()",
                "expected_output": "10",
                "should_compile": false,
                "test_assertion": "assert_eq!(allocate_and_init(10).len(), 10)"
            }
        ],
        "performance_baseline_ms": 100.0
    },
    {
        "id": 9,
        "title": "Inefficient Data Processing Pipeline",
        "difficulty": "Hard",
        "description": "Fix a data pipeline that reads large datasets, applies transformations, and aggregates results. While functionally correct, the implementation has: Excessive memory allocations, Redundant iterations, Inefficient data copying. Requirements: Process data efficiently, Minimize allocations and copies, Use iterators when possible, Produce correct results with better performance",
        "header_section": "fn process_data(numbers: Vec<i32>) -> i32 {\n    // BUG: Multiple unnecessary allocations and iterations\n    \n    // First pass: filter evens (allocates new vector)\n    let evens: Vec<i32> = numbers.iter()\n        .filter(|n| n % 2 == 0)\n        .copied()\n        .collect();\n    \n    // Second pass: double values (allocates another vector)\n    let doubled: Vec<i32> = evens.iter()\n        .map(|n| n * 2)\n        .collect();\n    \n    // Third pass: sum (unnecessary iteration)\n    let sum: i32 = doubled.iter().sum();\n    \n    // Fourth pass: filter again (redundant)\n    let final_sum: i32 = doubled.iter()\n        .filter(|n| n % 4 == 0)\n        .sum();\n    \n    final_sum\n}\n\nfn main() {\n    println!(\"Efficiency test\");\n}",
        "tests": [
            {
                "name": "simple_pipeline",
                "input_code": "process_data(vec![1, 2, 3, 4, 5, 6])",
                "expected_output": "16",
                "should_compile": true,
                "test_assertion": "assert_eq!(process_data(vec![1, 2, 3, 4, 5, 6]), 16)"
            },
            {
                "name": "all_odd_numbers",
                "input_code": "process_data(vec![1, 3, 5, 7])",
                "expected_output": "0",
                "should_compile": true,
                "test_assertion": "assert_eq!(process_data(vec![1, 3, 5, 7]), 0)"
            }
        ],
        "performance_baseline_ms": 50.0
    },
    {
        "id": 10,
        "title": "Reference-counted Cache with Memory Leak",
        "difficulty": "Hard+",
        "description": "Fix a caching system using reference-counted pointers to share data across components. The design creates cyclic references between cached objects, preventing memory from being released and causing memory usage to grow over time. Requirements: Implement caching without memory leaks, Break circular reference patterns, Use Rc/Arc correctly with Weak pointers when needed, Memory should be released when cache is cleared",
        "header_section": "use std::rc::Rc;\nuse std::cell::RefCell;\n\n#[derive(Debug)]\nstruct CacheNode<T> {\n    key: String,\n    value: T,\n    // BUG: This creates a cycle that prevents garbage collection\n    related: RefCell<Option<Rc<CacheNode<T>>>>,\n}\n\n#[derive(Debug)]\nstruct Cache<T> {\n    items: RefCell<Vec<Rc<CacheNode<T>>>>,\n}\n\nimpl<T: Clone> Cache<T> {\n    fn new() -> Self {\n        Cache {\n            items: RefCell::new(Vec::new()),\n        }\n    }\n\n    fn insert(&self, key: String, value: T) {\n        let node = Rc::new(CacheNode {\n            key,\n            value,\n            related: RefCell::new(None),\n        });\n        \n        // BUG: Creating cyclic references\n        if let Some(last) = self.items.borrow().last() {\n            // Rc to Rc creates a cycle\n            if let Ok(mut r) = last.related.try_borrow_mut() {\n                *r = Some(Rc::clone(&node));  // Cycle here!\n            }\n        }\n        \n        self.items.borrow_mut().push(node);\n    }\n}\n\nfn main() {\n    println!(\"Cache test\");\n}",
        "tests": [
            {
                "name": "cache_insert_single",
                "input_code": "let c = Cache::new(); c.insert(\"key\".to_string(), \"value\".to_string()); c.items.borrow().len()",
                "expected_output": "1",
                "should_compile": true,
                "test_assertion": "let c = Cache::new(); c.insert(\"key\".to_string(), \"value\".to_string()); assert_eq!(c.items.borrow().len(), 1)"
            },
            {
                "name": "cache_insert_multiple",
                "input_code": "let c = Cache::new(); c.insert(\"k1\".to_string(), \"v1\".to_string()); c.insert(\"k2\".to_string(), \"v2\".to_string()); c.items.borrow().len()",
                "expected_output": "2",
                "should_compile": true,
                "test_assertion": "let c = Cache::new(); c.insert(\"k1\".to_string(), \"v1\".to_string()); c.insert(\"k2\".to_string(), \"v2\".to_string()); assert_eq!(c.items.borrow().len(), 2)"
            }
        ],
        "performance_baseline_ms": 100.0
    }
]