diff --git a/.gitattributes b/.gitattributes index 22803b2f7573fc4eaca05dbeb43623704f04f900..e29d38a89b43e40999b3b8b3d8419a8e29cf5efc 100644 --- a/.gitattributes +++ b/.gitattributes @@ -180,3 +180,4 @@ tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/_inductor/_ .venv/lib/python3.11/site-packages/ray/rllib/algorithms/__pycache__/algorithm_config.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text .venv/lib/python3.11/site-packages/ray/rllib/env/__pycache__/multi_agent_episode.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text .venv/lib/python3.11/site-packages/ray/tune/execution/__pycache__/tune_controller.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text +.venv/lib/python3.11/site-packages/ray/thirdparty_files/psutil/_psutil_linux.abi3.so filter=lfs diff=lfs merge=lfs -text diff --git a/.venv/lib/python3.11/site-packages/_pytest/_argcomplete.py b/.venv/lib/python3.11/site-packages/_pytest/_argcomplete.py new file mode 100644 index 0000000000000000000000000000000000000000..59426ef949ed9276b5708f9f44e6893f2333f2e1 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/_argcomplete.py @@ -0,0 +1,117 @@ +"""Allow bash-completion for argparse with argcomplete if installed. + +Needs argcomplete>=0.5.6 for python 3.2/3.3 (older versions fail +to find the magic string, so _ARGCOMPLETE env. var is never set, and +this does not need special code). + +Function try_argcomplete(parser) should be called directly before +the call to ArgumentParser.parse_args(). + +The filescompleter is what you normally would use on the positional +arguments specification, in order to get "dirname/" after "dirn" +instead of the default "dirname ": + + optparser.add_argument(Config._file_or_dir, nargs='*').completer=filescompleter + +Other, application specific, completers should go in the file +doing the add_argument calls as they need to be specified as .completer +attributes as well. (If argcomplete is not installed, the function the +attribute points to will not be used). + +SPEEDUP +======= + +The generic argcomplete script for bash-completion +(/etc/bash_completion.d/python-argcomplete.sh) +uses a python program to determine startup script generated by pip. +You can speed up completion somewhat by changing this script to include + # PYTHON_ARGCOMPLETE_OK +so the python-argcomplete-check-easy-install-script does not +need to be called to find the entry point of the code and see if that is +marked with PYTHON_ARGCOMPLETE_OK. + +INSTALL/DEBUGGING +================= + +To include this support in another application that has setup.py generated +scripts: + +- Add the line: + # PYTHON_ARGCOMPLETE_OK + near the top of the main python entry point. + +- Include in the file calling parse_args(): + from _argcomplete import try_argcomplete, filescompleter + Call try_argcomplete just before parse_args(), and optionally add + filescompleter to the positional arguments' add_argument(). + +If things do not work right away: + +- Switch on argcomplete debugging with (also helpful when doing custom + completers): + export _ARC_DEBUG=1 + +- Run: + python-argcomplete-check-easy-install-script $(which appname) + echo $? + will echo 0 if the magic line has been found, 1 if not. + +- Sometimes it helps to find early on errors using: + _ARGCOMPLETE=1 _ARC_DEBUG=1 appname + which should throw a KeyError: 'COMPLINE' (which is properly set by the + global argcomplete script). +""" + +from __future__ import annotations + +import argparse +from glob import glob +import os +import sys +from typing import Any + + +class FastFilesCompleter: + """Fast file completer class.""" + + def __init__(self, directories: bool = True) -> None: + self.directories = directories + + def __call__(self, prefix: str, **kwargs: Any) -> list[str]: + # Only called on non option completions. + if os.sep in prefix[1:]: + prefix_dir = len(os.path.dirname(prefix) + os.sep) + else: + prefix_dir = 0 + completion = [] + globbed = [] + if "*" not in prefix and "?" not in prefix: + # We are on unix, otherwise no bash. + if not prefix or prefix[-1] == os.sep: + globbed.extend(glob(prefix + ".*")) + prefix += "*" + globbed.extend(glob(prefix)) + for x in sorted(globbed): + if os.path.isdir(x): + x += "/" + # Append stripping the prefix (like bash, not like compgen). + completion.append(x[prefix_dir:]) + return completion + + +if os.environ.get("_ARGCOMPLETE"): + try: + import argcomplete.completers + except ImportError: + sys.exit(-1) + filescompleter: FastFilesCompleter | None = FastFilesCompleter() + + def try_argcomplete(parser: argparse.ArgumentParser) -> None: + argcomplete.autocomplete(parser, always_complete_options=False) + +else: + + def try_argcomplete(parser: argparse.ArgumentParser) -> None: + pass + + filescompleter = None diff --git a/.venv/lib/python3.11/site-packages/_pytest/cacheprovider.py b/.venv/lib/python3.11/site-packages/_pytest/cacheprovider.py new file mode 100644 index 0000000000000000000000000000000000000000..1b236efdc9b3196a0e3238306b627c03fee69fa1 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/cacheprovider.py @@ -0,0 +1,626 @@ +# mypy: allow-untyped-defs +"""Implementation of the cache provider.""" + +# This plugin was not named "cache" to avoid conflicts with the external +# pytest-cache version. +from __future__ import annotations + +import dataclasses +import errno +import json +import os +from pathlib import Path +import tempfile +from typing import final +from typing import Generator +from typing import Iterable + +from .pathlib import resolve_from_str +from .pathlib import rm_rf +from .reports import CollectReport +from _pytest import nodes +from _pytest._io import TerminalWriter +from _pytest.config import Config +from _pytest.config import ExitCode +from _pytest.config import hookimpl +from _pytest.config.argparsing import Parser +from _pytest.deprecated import check_ispytest +from _pytest.fixtures import fixture +from _pytest.fixtures import FixtureRequest +from _pytest.main import Session +from _pytest.nodes import Directory +from _pytest.nodes import File +from _pytest.reports import TestReport + + +README_CONTENT = """\ +# pytest cache directory # + +This directory contains data from the pytest's cache plugin, +which provides the `--lf` and `--ff` options, as well as the `cache` fixture. + +**Do not** commit this to version control. + +See [the docs](https://docs.pytest.org/en/stable/how-to/cache.html) for more information. +""" + +CACHEDIR_TAG_CONTENT = b"""\ +Signature: 8a477f597d28d172789f06886806bc55 +# This file is a cache directory tag created by pytest. +# For information about cache directory tags, see: +# https://bford.info/cachedir/spec.html +""" + + +@final +@dataclasses.dataclass +class Cache: + """Instance of the `cache` fixture.""" + + _cachedir: Path = dataclasses.field(repr=False) + _config: Config = dataclasses.field(repr=False) + + # Sub-directory under cache-dir for directories created by `mkdir()`. + _CACHE_PREFIX_DIRS = "d" + + # Sub-directory under cache-dir for values created by `set()`. + _CACHE_PREFIX_VALUES = "v" + + def __init__( + self, cachedir: Path, config: Config, *, _ispytest: bool = False + ) -> None: + check_ispytest(_ispytest) + self._cachedir = cachedir + self._config = config + + @classmethod + def for_config(cls, config: Config, *, _ispytest: bool = False) -> Cache: + """Create the Cache instance for a Config. + + :meta private: + """ + check_ispytest(_ispytest) + cachedir = cls.cache_dir_from_config(config, _ispytest=True) + if config.getoption("cacheclear") and cachedir.is_dir(): + cls.clear_cache(cachedir, _ispytest=True) + return cls(cachedir, config, _ispytest=True) + + @classmethod + def clear_cache(cls, cachedir: Path, _ispytest: bool = False) -> None: + """Clear the sub-directories used to hold cached directories and values. + + :meta private: + """ + check_ispytest(_ispytest) + for prefix in (cls._CACHE_PREFIX_DIRS, cls._CACHE_PREFIX_VALUES): + d = cachedir / prefix + if d.is_dir(): + rm_rf(d) + + @staticmethod + def cache_dir_from_config(config: Config, *, _ispytest: bool = False) -> Path: + """Get the path to the cache directory for a Config. + + :meta private: + """ + check_ispytest(_ispytest) + return resolve_from_str(config.getini("cache_dir"), config.rootpath) + + def warn(self, fmt: str, *, _ispytest: bool = False, **args: object) -> None: + """Issue a cache warning. + + :meta private: + """ + check_ispytest(_ispytest) + import warnings + + from _pytest.warning_types import PytestCacheWarning + + warnings.warn( + PytestCacheWarning(fmt.format(**args) if args else fmt), + self._config.hook, + stacklevel=3, + ) + + def _mkdir(self, path: Path) -> None: + self._ensure_cache_dir_and_supporting_files() + path.mkdir(exist_ok=True, parents=True) + + def mkdir(self, name: str) -> Path: + """Return a directory path object with the given name. + + If the directory does not yet exist, it will be created. You can use + it to manage files to e.g. store/retrieve database dumps across test + sessions. + + .. versionadded:: 7.0 + + :param name: + Must be a string not containing a ``/`` separator. + Make sure the name contains your plugin or application + identifiers to prevent clashes with other cache users. + """ + path = Path(name) + if len(path.parts) > 1: + raise ValueError("name is not allowed to contain path separators") + res = self._cachedir.joinpath(self._CACHE_PREFIX_DIRS, path) + self._mkdir(res) + return res + + def _getvaluepath(self, key: str) -> Path: + return self._cachedir.joinpath(self._CACHE_PREFIX_VALUES, Path(key)) + + def get(self, key: str, default): + """Return the cached value for the given key. + + If no value was yet cached or the value cannot be read, the specified + default is returned. + + :param key: + Must be a ``/`` separated value. Usually the first + name is the name of your plugin or your application. + :param default: + The value to return in case of a cache-miss or invalid cache value. + """ + path = self._getvaluepath(key) + try: + with path.open("r", encoding="UTF-8") as f: + return json.load(f) + except (ValueError, OSError): + return default + + def set(self, key: str, value: object) -> None: + """Save value for the given key. + + :param key: + Must be a ``/`` separated value. Usually the first + name is the name of your plugin or your application. + :param value: + Must be of any combination of basic python types, + including nested types like lists of dictionaries. + """ + path = self._getvaluepath(key) + try: + self._mkdir(path.parent) + except OSError as exc: + self.warn( + f"could not create cache path {path}: {exc}", + _ispytest=True, + ) + return + data = json.dumps(value, ensure_ascii=False, indent=2) + try: + f = path.open("w", encoding="UTF-8") + except OSError as exc: + self.warn( + f"cache could not write path {path}: {exc}", + _ispytest=True, + ) + else: + with f: + f.write(data) + + def _ensure_cache_dir_and_supporting_files(self) -> None: + """Create the cache dir and its supporting files.""" + if self._cachedir.is_dir(): + return + + self._cachedir.parent.mkdir(parents=True, exist_ok=True) + with tempfile.TemporaryDirectory( + prefix="pytest-cache-files-", + dir=self._cachedir.parent, + ) as newpath: + path = Path(newpath) + + # Reset permissions to the default, see #12308. + # Note: there's no way to get the current umask atomically, eek. + umask = os.umask(0o022) + os.umask(umask) + path.chmod(0o777 - umask) + + with open(path.joinpath("README.md"), "x", encoding="UTF-8") as f: + f.write(README_CONTENT) + with open(path.joinpath(".gitignore"), "x", encoding="UTF-8") as f: + f.write("# Created by pytest automatically.\n*\n") + with open(path.joinpath("CACHEDIR.TAG"), "xb") as f: + f.write(CACHEDIR_TAG_CONTENT) + + try: + path.rename(self._cachedir) + except OSError as e: + # If 2 concurrent pytests both race to the rename, the loser + # gets "Directory not empty" from the rename. In this case, + # everything is handled so just continue (while letting the + # temporary directory be cleaned up). + # On Windows, the error is a FileExistsError which translates to EEXIST. + if e.errno not in (errno.ENOTEMPTY, errno.EEXIST): + raise + else: + # Create a directory in place of the one we just moved so that + # `TemporaryDirectory`'s cleanup doesn't complain. + # + # TODO: pass ignore_cleanup_errors=True when we no longer support python < 3.10. + # See https://github.com/python/cpython/issues/74168. Note that passing + # delete=False would do the wrong thing in case of errors and isn't supported + # until python 3.12. + path.mkdir() + + +class LFPluginCollWrapper: + def __init__(self, lfplugin: LFPlugin) -> None: + self.lfplugin = lfplugin + self._collected_at_least_one_failure = False + + @hookimpl(wrapper=True) + def pytest_make_collect_report( + self, collector: nodes.Collector + ) -> Generator[None, CollectReport, CollectReport]: + res = yield + if isinstance(collector, (Session, Directory)): + # Sort any lf-paths to the beginning. + lf_paths = self.lfplugin._last_failed_paths + + # Use stable sort to prioritize last failed. + def sort_key(node: nodes.Item | nodes.Collector) -> bool: + return node.path in lf_paths + + res.result = sorted( + res.result, + key=sort_key, + reverse=True, + ) + + elif isinstance(collector, File): + if collector.path in self.lfplugin._last_failed_paths: + result = res.result + lastfailed = self.lfplugin.lastfailed + + # Only filter with known failures. + if not self._collected_at_least_one_failure: + if not any(x.nodeid in lastfailed for x in result): + return res + self.lfplugin.config.pluginmanager.register( + LFPluginCollSkipfiles(self.lfplugin), "lfplugin-collskip" + ) + self._collected_at_least_one_failure = True + + session = collector.session + result[:] = [ + x + for x in result + if x.nodeid in lastfailed + # Include any passed arguments (not trivial to filter). + or session.isinitpath(x.path) + # Keep all sub-collectors. + or isinstance(x, nodes.Collector) + ] + + return res + + +class LFPluginCollSkipfiles: + def __init__(self, lfplugin: LFPlugin) -> None: + self.lfplugin = lfplugin + + @hookimpl + def pytest_make_collect_report( + self, collector: nodes.Collector + ) -> CollectReport | None: + if isinstance(collector, File): + if collector.path not in self.lfplugin._last_failed_paths: + self.lfplugin._skipped_files += 1 + + return CollectReport( + collector.nodeid, "passed", longrepr=None, result=[] + ) + return None + + +class LFPlugin: + """Plugin which implements the --lf (run last-failing) option.""" + + def __init__(self, config: Config) -> None: + self.config = config + active_keys = "lf", "failedfirst" + self.active = any(config.getoption(key) for key in active_keys) + assert config.cache + self.lastfailed: dict[str, bool] = config.cache.get("cache/lastfailed", {}) + self._previously_failed_count: int | None = None + self._report_status: str | None = None + self._skipped_files = 0 # count skipped files during collection due to --lf + + if config.getoption("lf"): + self._last_failed_paths = self.get_last_failed_paths() + config.pluginmanager.register( + LFPluginCollWrapper(self), "lfplugin-collwrapper" + ) + + def get_last_failed_paths(self) -> set[Path]: + """Return a set with all Paths of the previously failed nodeids and + their parents.""" + rootpath = self.config.rootpath + result = set() + for nodeid in self.lastfailed: + path = rootpath / nodeid.split("::")[0] + result.add(path) + result.update(path.parents) + return {x for x in result if x.exists()} + + def pytest_report_collectionfinish(self) -> str | None: + if self.active and self.config.get_verbosity() >= 0: + return f"run-last-failure: {self._report_status}" + return None + + def pytest_runtest_logreport(self, report: TestReport) -> None: + if (report.when == "call" and report.passed) or report.skipped: + self.lastfailed.pop(report.nodeid, None) + elif report.failed: + self.lastfailed[report.nodeid] = True + + def pytest_collectreport(self, report: CollectReport) -> None: + passed = report.outcome in ("passed", "skipped") + if passed: + if report.nodeid in self.lastfailed: + self.lastfailed.pop(report.nodeid) + self.lastfailed.update((item.nodeid, True) for item in report.result) + else: + self.lastfailed[report.nodeid] = True + + @hookimpl(wrapper=True, tryfirst=True) + def pytest_collection_modifyitems( + self, config: Config, items: list[nodes.Item] + ) -> Generator[None]: + res = yield + + if not self.active: + return res + + if self.lastfailed: + previously_failed = [] + previously_passed = [] + for item in items: + if item.nodeid in self.lastfailed: + previously_failed.append(item) + else: + previously_passed.append(item) + self._previously_failed_count = len(previously_failed) + + if not previously_failed: + # Running a subset of all tests with recorded failures + # only outside of it. + self._report_status = "%d known failures not in selected tests" % ( + len(self.lastfailed), + ) + else: + if self.config.getoption("lf"): + items[:] = previously_failed + config.hook.pytest_deselected(items=previously_passed) + else: # --failedfirst + items[:] = previously_failed + previously_passed + + noun = "failure" if self._previously_failed_count == 1 else "failures" + suffix = " first" if self.config.getoption("failedfirst") else "" + self._report_status = ( + f"rerun previous {self._previously_failed_count} {noun}{suffix}" + ) + + if self._skipped_files > 0: + files_noun = "file" if self._skipped_files == 1 else "files" + self._report_status += f" (skipped {self._skipped_files} {files_noun})" + else: + self._report_status = "no previously failed tests, " + if self.config.getoption("last_failed_no_failures") == "none": + self._report_status += "deselecting all items." + config.hook.pytest_deselected(items=items[:]) + items[:] = [] + else: + self._report_status += "not deselecting items." + + return res + + def pytest_sessionfinish(self, session: Session) -> None: + config = self.config + if config.getoption("cacheshow") or hasattr(config, "workerinput"): + return + + assert config.cache is not None + saved_lastfailed = config.cache.get("cache/lastfailed", {}) + if saved_lastfailed != self.lastfailed: + config.cache.set("cache/lastfailed", self.lastfailed) + + +class NFPlugin: + """Plugin which implements the --nf (run new-first) option.""" + + def __init__(self, config: Config) -> None: + self.config = config + self.active = config.option.newfirst + assert config.cache is not None + self.cached_nodeids = set(config.cache.get("cache/nodeids", [])) + + @hookimpl(wrapper=True, tryfirst=True) + def pytest_collection_modifyitems(self, items: list[nodes.Item]) -> Generator[None]: + res = yield + + if self.active: + new_items: dict[str, nodes.Item] = {} + other_items: dict[str, nodes.Item] = {} + for item in items: + if item.nodeid not in self.cached_nodeids: + new_items[item.nodeid] = item + else: + other_items[item.nodeid] = item + + items[:] = self._get_increasing_order( + new_items.values() + ) + self._get_increasing_order(other_items.values()) + self.cached_nodeids.update(new_items) + else: + self.cached_nodeids.update(item.nodeid for item in items) + + return res + + def _get_increasing_order(self, items: Iterable[nodes.Item]) -> list[nodes.Item]: + return sorted(items, key=lambda item: item.path.stat().st_mtime, reverse=True) + + def pytest_sessionfinish(self) -> None: + config = self.config + if config.getoption("cacheshow") or hasattr(config, "workerinput"): + return + + if config.getoption("collectonly"): + return + + assert config.cache is not None + config.cache.set("cache/nodeids", sorted(self.cached_nodeids)) + + +def pytest_addoption(parser: Parser) -> None: + group = parser.getgroup("general") + group.addoption( + "--lf", + "--last-failed", + action="store_true", + dest="lf", + help="Rerun only the tests that failed " + "at the last run (or all if none failed)", + ) + group.addoption( + "--ff", + "--failed-first", + action="store_true", + dest="failedfirst", + help="Run all tests, but run the last failures first. " + "This may re-order tests and thus lead to " + "repeated fixture setup/teardown.", + ) + group.addoption( + "--nf", + "--new-first", + action="store_true", + dest="newfirst", + help="Run tests from new files first, then the rest of the tests " + "sorted by file mtime", + ) + group.addoption( + "--cache-show", + action="append", + nargs="?", + dest="cacheshow", + help=( + "Show cache contents, don't perform collection or tests. " + "Optional argument: glob (default: '*')." + ), + ) + group.addoption( + "--cache-clear", + action="store_true", + dest="cacheclear", + help="Remove all cache contents at start of test run", + ) + cache_dir_default = ".pytest_cache" + if "TOX_ENV_DIR" in os.environ: + cache_dir_default = os.path.join(os.environ["TOX_ENV_DIR"], cache_dir_default) + parser.addini("cache_dir", default=cache_dir_default, help="Cache directory path") + group.addoption( + "--lfnf", + "--last-failed-no-failures", + action="store", + dest="last_failed_no_failures", + choices=("all", "none"), + default="all", + help="With ``--lf``, determines whether to execute tests when there " + "are no previously (known) failures or when no " + "cached ``lastfailed`` data was found. " + "``all`` (the default) runs the full test suite again. " + "``none`` just emits a message about no known failures and exits successfully.", + ) + + +def pytest_cmdline_main(config: Config) -> int | ExitCode | None: + if config.option.cacheshow and not config.option.help: + from _pytest.main import wrap_session + + return wrap_session(config, cacheshow) + return None + + +@hookimpl(tryfirst=True) +def pytest_configure(config: Config) -> None: + config.cache = Cache.for_config(config, _ispytest=True) + config.pluginmanager.register(LFPlugin(config), "lfplugin") + config.pluginmanager.register(NFPlugin(config), "nfplugin") + + +@fixture +def cache(request: FixtureRequest) -> Cache: + """Return a cache object that can persist state between testing sessions. + + cache.get(key, default) + cache.set(key, value) + + Keys must be ``/`` separated strings, where the first part is usually the + name of your plugin or application to avoid clashes with other cache users. + + Values can be any object handled by the json stdlib module. + """ + assert request.config.cache is not None + return request.config.cache + + +def pytest_report_header(config: Config) -> str | None: + """Display cachedir with --cache-show and if non-default.""" + if config.option.verbose > 0 or config.getini("cache_dir") != ".pytest_cache": + assert config.cache is not None + cachedir = config.cache._cachedir + # TODO: evaluate generating upward relative paths + # starting with .., ../.. if sensible + + try: + displaypath = cachedir.relative_to(config.rootpath) + except ValueError: + displaypath = cachedir + return f"cachedir: {displaypath}" + return None + + +def cacheshow(config: Config, session: Session) -> int: + from pprint import pformat + + assert config.cache is not None + + tw = TerminalWriter() + tw.line("cachedir: " + str(config.cache._cachedir)) + if not config.cache._cachedir.is_dir(): + tw.line("cache is empty") + return 0 + + glob = config.option.cacheshow[0] + if glob is None: + glob = "*" + + dummy = object() + basedir = config.cache._cachedir + vdir = basedir / Cache._CACHE_PREFIX_VALUES + tw.sep("-", f"cache values for {glob!r}") + for valpath in sorted(x for x in vdir.rglob(glob) if x.is_file()): + key = str(valpath.relative_to(vdir)) + val = config.cache.get(key, dummy) + if val is dummy: + tw.line(f"{key} contains unreadable content, will be ignored") + else: + tw.line(f"{key} contains:") + for line in pformat(val).splitlines(): + tw.line(" " + line) + + ddir = basedir / Cache._CACHE_PREFIX_DIRS + if ddir.is_dir(): + contents = sorted(ddir.rglob(glob)) + tw.sep("-", f"cache directories for {glob!r}") + for p in contents: + # if p.is_dir(): + # print("%s/" % p.relative_to(basedir)) + if p.is_file(): + key = str(p.relative_to(basedir)) + tw.line(f"{key} is a file of length {p.stat().st_size:d}") + return 0 diff --git a/.venv/lib/python3.11/site-packages/_pytest/compat.py b/.venv/lib/python3.11/site-packages/_pytest/compat.py new file mode 100644 index 0000000000000000000000000000000000000000..614848e0dbaeb2cfc1356d3393b0d0992922d47f --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/compat.py @@ -0,0 +1,351 @@ +# mypy: allow-untyped-defs +"""Python version compatibility code.""" + +from __future__ import annotations + +import dataclasses +import enum +import functools +import inspect +from inspect import Parameter +from inspect import signature +import os +from pathlib import Path +import sys +from typing import Any +from typing import Callable +from typing import Final +from typing import NoReturn + +import py + + +#: constant to prepare valuing pylib path replacements/lazy proxies later on +# intended for removal in pytest 8.0 or 9.0 + +# fmt: off +# intentional space to create a fake difference for the verification +LEGACY_PATH = py.path. local +# fmt: on + + +def legacy_path(path: str | os.PathLike[str]) -> LEGACY_PATH: + """Internal wrapper to prepare lazy proxies for legacy_path instances""" + return LEGACY_PATH(path) + + +# fmt: off +# Singleton type for NOTSET, as described in: +# https://www.python.org/dev/peps/pep-0484/#support-for-singleton-types-in-unions +class NotSetType(enum.Enum): + token = 0 +NOTSET: Final = NotSetType.token +# fmt: on + + +def is_generator(func: object) -> bool: + genfunc = inspect.isgeneratorfunction(func) + return genfunc and not iscoroutinefunction(func) + + +def iscoroutinefunction(func: object) -> bool: + """Return True if func is a coroutine function (a function defined with async + def syntax, and doesn't contain yield), or a function decorated with + @asyncio.coroutine. + + Note: copied and modified from Python 3.5's builtin coroutines.py to avoid + importing asyncio directly, which in turns also initializes the "logging" + module as a side-effect (see issue #8). + """ + return inspect.iscoroutinefunction(func) or getattr(func, "_is_coroutine", False) + + +def is_async_function(func: object) -> bool: + """Return True if the given function seems to be an async function or + an async generator.""" + return iscoroutinefunction(func) or inspect.isasyncgenfunction(func) + + +def getlocation(function, curdir: str | os.PathLike[str] | None = None) -> str: + function = get_real_func(function) + fn = Path(inspect.getfile(function)) + lineno = function.__code__.co_firstlineno + if curdir is not None: + try: + relfn = fn.relative_to(curdir) + except ValueError: + pass + else: + return "%s:%d" % (relfn, lineno + 1) + return "%s:%d" % (fn, lineno + 1) + + +def num_mock_patch_args(function) -> int: + """Return number of arguments used up by mock arguments (if any).""" + patchings = getattr(function, "patchings", None) + if not patchings: + return 0 + + mock_sentinel = getattr(sys.modules.get("mock"), "DEFAULT", object()) + ut_mock_sentinel = getattr(sys.modules.get("unittest.mock"), "DEFAULT", object()) + + return len( + [ + p + for p in patchings + if not p.attribute_name + and (p.new is mock_sentinel or p.new is ut_mock_sentinel) + ] + ) + + +def getfuncargnames( + function: Callable[..., object], + *, + name: str = "", + cls: type | None = None, +) -> tuple[str, ...]: + """Return the names of a function's mandatory arguments. + + Should return the names of all function arguments that: + * Aren't bound to an instance or type as in instance or class methods. + * Don't have default values. + * Aren't bound with functools.partial. + * Aren't replaced with mocks. + + The cls arguments indicate that the function should be treated as a bound + method even though it's not unless the function is a static method. + + The name parameter should be the original name in which the function was collected. + """ + # TODO(RonnyPfannschmidt): This function should be refactored when we + # revisit fixtures. The fixture mechanism should ask the node for + # the fixture names, and not try to obtain directly from the + # function object well after collection has occurred. + + # The parameters attribute of a Signature object contains an + # ordered mapping of parameter names to Parameter instances. This + # creates a tuple of the names of the parameters that don't have + # defaults. + try: + parameters = signature(function).parameters + except (ValueError, TypeError) as e: + from _pytest.outcomes import fail + + fail( + f"Could not determine arguments of {function!r}: {e}", + pytrace=False, + ) + + arg_names = tuple( + p.name + for p in parameters.values() + if ( + p.kind is Parameter.POSITIONAL_OR_KEYWORD + or p.kind is Parameter.KEYWORD_ONLY + ) + and p.default is Parameter.empty + ) + if not name: + name = function.__name__ + + # If this function should be treated as a bound method even though + # it's passed as an unbound method or function, remove the first + # parameter name. + if ( + # Not using `getattr` because we don't want to resolve the staticmethod. + # Not using `cls.__dict__` because we want to check the entire MRO. + cls + and not isinstance( + inspect.getattr_static(cls, name, default=None), staticmethod + ) + ): + arg_names = arg_names[1:] + # Remove any names that will be replaced with mocks. + if hasattr(function, "__wrapped__"): + arg_names = arg_names[num_mock_patch_args(function) :] + return arg_names + + +def get_default_arg_names(function: Callable[..., Any]) -> tuple[str, ...]: + # Note: this code intentionally mirrors the code at the beginning of + # getfuncargnames, to get the arguments which were excluded from its result + # because they had default values. + return tuple( + p.name + for p in signature(function).parameters.values() + if p.kind in (Parameter.POSITIONAL_OR_KEYWORD, Parameter.KEYWORD_ONLY) + and p.default is not Parameter.empty + ) + + +_non_printable_ascii_translate_table = { + i: f"\\x{i:02x}" for i in range(128) if i not in range(32, 127) +} +_non_printable_ascii_translate_table.update( + {ord("\t"): "\\t", ord("\r"): "\\r", ord("\n"): "\\n"} +) + + +def ascii_escaped(val: bytes | str) -> str: + r"""If val is pure ASCII, return it as an str, otherwise, escape + bytes objects into a sequence of escaped bytes: + + b'\xc3\xb4\xc5\xd6' -> r'\xc3\xb4\xc5\xd6' + + and escapes strings into a sequence of escaped unicode ids, e.g.: + + r'4\nV\U00043efa\x0eMXWB\x1e\u3028\u15fd\xcd\U0007d944' + + Note: + The obvious "v.decode('unicode-escape')" will return + valid UTF-8 unicode if it finds them in bytes, but we + want to return escaped bytes for any byte, even if they match + a UTF-8 string. + """ + if isinstance(val, bytes): + ret = val.decode("ascii", "backslashreplace") + else: + ret = val.encode("unicode_escape").decode("ascii") + return ret.translate(_non_printable_ascii_translate_table) + + +@dataclasses.dataclass +class _PytestWrapper: + """Dummy wrapper around a function object for internal use only. + + Used to correctly unwrap the underlying function object when we are + creating fixtures, because we wrap the function object ourselves with a + decorator to issue warnings when the fixture function is called directly. + """ + + obj: Any + + +def get_real_func(obj): + """Get the real function object of the (possibly) wrapped object by + functools.wraps or functools.partial.""" + start_obj = obj + for i in range(100): + # __pytest_wrapped__ is set by @pytest.fixture when wrapping the fixture function + # to trigger a warning if it gets called directly instead of by pytest: we don't + # want to unwrap further than this otherwise we lose useful wrappings like @mock.patch (#3774) + new_obj = getattr(obj, "__pytest_wrapped__", None) + if isinstance(new_obj, _PytestWrapper): + obj = new_obj.obj + break + new_obj = getattr(obj, "__wrapped__", None) + if new_obj is None: + break + obj = new_obj + else: + from _pytest._io.saferepr import saferepr + + raise ValueError( + f"could not find real function of {saferepr(start_obj)}\nstopped at {saferepr(obj)}" + ) + if isinstance(obj, functools.partial): + obj = obj.func + return obj + + +def get_real_method(obj, holder): + """Attempt to obtain the real function object that might be wrapping + ``obj``, while at the same time returning a bound method to ``holder`` if + the original object was a bound method.""" + try: + is_method = hasattr(obj, "__func__") + obj = get_real_func(obj) + except Exception: # pragma: no cover + return obj + if is_method and hasattr(obj, "__get__") and callable(obj.__get__): + obj = obj.__get__(holder) + return obj + + +def getimfunc(func): + try: + return func.__func__ + except AttributeError: + return func + + +def safe_getattr(object: Any, name: str, default: Any) -> Any: + """Like getattr but return default upon any Exception or any OutcomeException. + + Attribute access can potentially fail for 'evil' Python objects. + See issue #214. + It catches OutcomeException because of #2490 (issue #580), new outcomes + are derived from BaseException instead of Exception (for more details + check #2707). + """ + from _pytest.outcomes import TEST_OUTCOME + + try: + return getattr(object, name, default) + except TEST_OUTCOME: + return default + + +def safe_isclass(obj: object) -> bool: + """Ignore any exception via isinstance on Python 3.""" + try: + return inspect.isclass(obj) + except Exception: + return False + + +def get_user_id() -> int | None: + """Return the current process's real user id or None if it could not be + determined. + + :return: The user id or None if it could not be determined. + """ + # mypy follows the version and platform checking expectation of PEP 484: + # https://mypy.readthedocs.io/en/stable/common_issues.html?highlight=platform#python-version-and-system-platform-checks + # Containment checks are too complex for mypy v1.5.0 and cause failure. + if sys.platform == "win32" or sys.platform == "emscripten": + # win32 does not have a getuid() function. + # Emscripten has a return 0 stub. + return None + else: + # On other platforms, a return value of -1 is assumed to indicate that + # the current process's real user id could not be determined. + ERROR = -1 + uid = os.getuid() + return uid if uid != ERROR else None + + +# Perform exhaustiveness checking. +# +# Consider this example: +# +# MyUnion = Union[int, str] +# +# def handle(x: MyUnion) -> int { +# if isinstance(x, int): +# return 1 +# elif isinstance(x, str): +# return 2 +# else: +# raise Exception('unreachable') +# +# Now suppose we add a new variant: +# +# MyUnion = Union[int, str, bytes] +# +# After doing this, we must remember ourselves to go and update the handle +# function to handle the new variant. +# +# With `assert_never` we can do better: +# +# // raise Exception('unreachable') +# return assert_never(x) +# +# Now, if we forget to handle the new variant, the type-checker will emit a +# compile-time error, instead of the runtime error we would have gotten +# previously. +# +# This also work for Enums (if you use `is` to compare) and Literals. +def assert_never(value: NoReturn) -> NoReturn: + assert False, f"Unhandled value: {value} ({type(value).__name__})" diff --git a/.venv/lib/python3.11/site-packages/_pytest/doctest.py b/.venv/lib/python3.11/site-packages/_pytest/doctest.py new file mode 100644 index 0000000000000000000000000000000000000000..384dea976adad1c3d6004888078dd0fe00b4c268 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/doctest.py @@ -0,0 +1,755 @@ +# mypy: allow-untyped-defs +"""Discover and run doctests in modules and test files.""" + +from __future__ import annotations + +import bdb +from contextlib import contextmanager +import functools +import inspect +import os +from pathlib import Path +import platform +import sys +import traceback +import types +from typing import Any +from typing import Callable +from typing import Generator +from typing import Iterable +from typing import Pattern +from typing import Sequence +from typing import TYPE_CHECKING +import warnings + +from _pytest import outcomes +from _pytest._code.code import ExceptionInfo +from _pytest._code.code import ReprFileLocation +from _pytest._code.code import TerminalRepr +from _pytest._io import TerminalWriter +from _pytest.compat import safe_getattr +from _pytest.config import Config +from _pytest.config.argparsing import Parser +from _pytest.fixtures import fixture +from _pytest.fixtures import TopRequest +from _pytest.nodes import Collector +from _pytest.nodes import Item +from _pytest.outcomes import OutcomeException +from _pytest.outcomes import skip +from _pytest.pathlib import fnmatch_ex +from _pytest.python import Module +from _pytest.python_api import approx +from _pytest.warning_types import PytestWarning + + +if TYPE_CHECKING: + import doctest + + from typing_extensions import Self + +DOCTEST_REPORT_CHOICE_NONE = "none" +DOCTEST_REPORT_CHOICE_CDIFF = "cdiff" +DOCTEST_REPORT_CHOICE_NDIFF = "ndiff" +DOCTEST_REPORT_CHOICE_UDIFF = "udiff" +DOCTEST_REPORT_CHOICE_ONLY_FIRST_FAILURE = "only_first_failure" + +DOCTEST_REPORT_CHOICES = ( + DOCTEST_REPORT_CHOICE_NONE, + DOCTEST_REPORT_CHOICE_CDIFF, + DOCTEST_REPORT_CHOICE_NDIFF, + DOCTEST_REPORT_CHOICE_UDIFF, + DOCTEST_REPORT_CHOICE_ONLY_FIRST_FAILURE, +) + +# Lazy definition of runner class +RUNNER_CLASS = None +# Lazy definition of output checker class +CHECKER_CLASS: type[doctest.OutputChecker] | None = None + + +def pytest_addoption(parser: Parser) -> None: + parser.addini( + "doctest_optionflags", + "Option flags for doctests", + type="args", + default=["ELLIPSIS"], + ) + parser.addini( + "doctest_encoding", "Encoding used for doctest files", default="utf-8" + ) + group = parser.getgroup("collect") + group.addoption( + "--doctest-modules", + action="store_true", + default=False, + help="Run doctests in all .py modules", + dest="doctestmodules", + ) + group.addoption( + "--doctest-report", + type=str.lower, + default="udiff", + help="Choose another output format for diffs on doctest failure", + choices=DOCTEST_REPORT_CHOICES, + dest="doctestreport", + ) + group.addoption( + "--doctest-glob", + action="append", + default=[], + metavar="pat", + help="Doctests file matching pattern, default: test*.txt", + dest="doctestglob", + ) + group.addoption( + "--doctest-ignore-import-errors", + action="store_true", + default=False, + help="Ignore doctest collection errors", + dest="doctest_ignore_import_errors", + ) + group.addoption( + "--doctest-continue-on-failure", + action="store_true", + default=False, + help="For a given doctest, continue to run after the first failure", + dest="doctest_continue_on_failure", + ) + + +def pytest_unconfigure() -> None: + global RUNNER_CLASS + + RUNNER_CLASS = None + + +def pytest_collect_file( + file_path: Path, + parent: Collector, +) -> DoctestModule | DoctestTextfile | None: + config = parent.config + if file_path.suffix == ".py": + if config.option.doctestmodules and not any( + (_is_setup_py(file_path), _is_main_py(file_path)) + ): + return DoctestModule.from_parent(parent, path=file_path) + elif _is_doctest(config, file_path, parent): + return DoctestTextfile.from_parent(parent, path=file_path) + return None + + +def _is_setup_py(path: Path) -> bool: + if path.name != "setup.py": + return False + contents = path.read_bytes() + return b"setuptools" in contents or b"distutils" in contents + + +def _is_doctest(config: Config, path: Path, parent: Collector) -> bool: + if path.suffix in (".txt", ".rst") and parent.session.isinitpath(path): + return True + globs = config.getoption("doctestglob") or ["test*.txt"] + return any(fnmatch_ex(glob, path) for glob in globs) + + +def _is_main_py(path: Path) -> bool: + return path.name == "__main__.py" + + +class ReprFailDoctest(TerminalRepr): + def __init__( + self, reprlocation_lines: Sequence[tuple[ReprFileLocation, Sequence[str]]] + ) -> None: + self.reprlocation_lines = reprlocation_lines + + def toterminal(self, tw: TerminalWriter) -> None: + for reprlocation, lines in self.reprlocation_lines: + for line in lines: + tw.line(line) + reprlocation.toterminal(tw) + + +class MultipleDoctestFailures(Exception): + def __init__(self, failures: Sequence[doctest.DocTestFailure]) -> None: + super().__init__() + self.failures = failures + + +def _init_runner_class() -> type[doctest.DocTestRunner]: + import doctest + + class PytestDoctestRunner(doctest.DebugRunner): + """Runner to collect failures. + + Note that the out variable in this case is a list instead of a + stdout-like object. + """ + + def __init__( + self, + checker: doctest.OutputChecker | None = None, + verbose: bool | None = None, + optionflags: int = 0, + continue_on_failure: bool = True, + ) -> None: + super().__init__(checker=checker, verbose=verbose, optionflags=optionflags) + self.continue_on_failure = continue_on_failure + + def report_failure( + self, + out, + test: doctest.DocTest, + example: doctest.Example, + got: str, + ) -> None: + failure = doctest.DocTestFailure(test, example, got) + if self.continue_on_failure: + out.append(failure) + else: + raise failure + + def report_unexpected_exception( + self, + out, + test: doctest.DocTest, + example: doctest.Example, + exc_info: tuple[type[BaseException], BaseException, types.TracebackType], + ) -> None: + if isinstance(exc_info[1], OutcomeException): + raise exc_info[1] + if isinstance(exc_info[1], bdb.BdbQuit): + outcomes.exit("Quitting debugger") + failure = doctest.UnexpectedException(test, example, exc_info) + if self.continue_on_failure: + out.append(failure) + else: + raise failure + + return PytestDoctestRunner + + +def _get_runner( + checker: doctest.OutputChecker | None = None, + verbose: bool | None = None, + optionflags: int = 0, + continue_on_failure: bool = True, +) -> doctest.DocTestRunner: + # We need this in order to do a lazy import on doctest + global RUNNER_CLASS + if RUNNER_CLASS is None: + RUNNER_CLASS = _init_runner_class() + # Type ignored because the continue_on_failure argument is only defined on + # PytestDoctestRunner, which is lazily defined so can't be used as a type. + return RUNNER_CLASS( # type: ignore + checker=checker, + verbose=verbose, + optionflags=optionflags, + continue_on_failure=continue_on_failure, + ) + + +class DoctestItem(Item): + def __init__( + self, + name: str, + parent: DoctestTextfile | DoctestModule, + runner: doctest.DocTestRunner, + dtest: doctest.DocTest, + ) -> None: + super().__init__(name, parent) + self.runner = runner + self.dtest = dtest + + # Stuff needed for fixture support. + self.obj = None + fm = self.session._fixturemanager + fixtureinfo = fm.getfixtureinfo(node=self, func=None, cls=None) + self._fixtureinfo = fixtureinfo + self.fixturenames = fixtureinfo.names_closure + self._initrequest() + + @classmethod + def from_parent( # type: ignore[override] + cls, + parent: DoctestTextfile | DoctestModule, + *, + name: str, + runner: doctest.DocTestRunner, + dtest: doctest.DocTest, + ) -> Self: + # incompatible signature due to imposed limits on subclass + """The public named constructor.""" + return super().from_parent(name=name, parent=parent, runner=runner, dtest=dtest) + + def _initrequest(self) -> None: + self.funcargs: dict[str, object] = {} + self._request = TopRequest(self, _ispytest=True) # type: ignore[arg-type] + + def setup(self) -> None: + self._request._fillfixtures() + globs = dict(getfixture=self._request.getfixturevalue) + for name, value in self._request.getfixturevalue("doctest_namespace").items(): + globs[name] = value + self.dtest.globs.update(globs) + + def runtest(self) -> None: + _check_all_skipped(self.dtest) + self._disable_output_capturing_for_darwin() + failures: list[doctest.DocTestFailure] = [] + # Type ignored because we change the type of `out` from what + # doctest expects. + self.runner.run(self.dtest, out=failures) # type: ignore[arg-type] + if failures: + raise MultipleDoctestFailures(failures) + + def _disable_output_capturing_for_darwin(self) -> None: + """Disable output capturing. Otherwise, stdout is lost to doctest (#985).""" + if platform.system() != "Darwin": + return + capman = self.config.pluginmanager.getplugin("capturemanager") + if capman: + capman.suspend_global_capture(in_=True) + out, err = capman.read_global_capture() + sys.stdout.write(out) + sys.stderr.write(err) + + # TODO: Type ignored -- breaks Liskov Substitution. + def repr_failure( # type: ignore[override] + self, + excinfo: ExceptionInfo[BaseException], + ) -> str | TerminalRepr: + import doctest + + failures: ( + Sequence[doctest.DocTestFailure | doctest.UnexpectedException] | None + ) = None + if isinstance( + excinfo.value, (doctest.DocTestFailure, doctest.UnexpectedException) + ): + failures = [excinfo.value] + elif isinstance(excinfo.value, MultipleDoctestFailures): + failures = excinfo.value.failures + + if failures is None: + return super().repr_failure(excinfo) + + reprlocation_lines = [] + for failure in failures: + example = failure.example + test = failure.test + filename = test.filename + if test.lineno is None: + lineno = None + else: + lineno = test.lineno + example.lineno + 1 + message = type(failure).__name__ + # TODO: ReprFileLocation doesn't expect a None lineno. + reprlocation = ReprFileLocation(filename, lineno, message) # type: ignore[arg-type] + checker = _get_checker() + report_choice = _get_report_choice(self.config.getoption("doctestreport")) + if lineno is not None: + assert failure.test.docstring is not None + lines = failure.test.docstring.splitlines(False) + # add line numbers to the left of the error message + assert test.lineno is not None + lines = [ + "%03d %s" % (i + test.lineno + 1, x) for (i, x) in enumerate(lines) + ] + # trim docstring error lines to 10 + lines = lines[max(example.lineno - 9, 0) : example.lineno + 1] + else: + lines = [ + "EXAMPLE LOCATION UNKNOWN, not showing all tests of that example" + ] + indent = ">>>" + for line in example.source.splitlines(): + lines.append(f"??? {indent} {line}") + indent = "..." + if isinstance(failure, doctest.DocTestFailure): + lines += checker.output_difference( + example, failure.got, report_choice + ).split("\n") + else: + inner_excinfo = ExceptionInfo.from_exc_info(failure.exc_info) + lines += [f"UNEXPECTED EXCEPTION: {inner_excinfo.value!r}"] + lines += [ + x.strip("\n") for x in traceback.format_exception(*failure.exc_info) + ] + reprlocation_lines.append((reprlocation, lines)) + return ReprFailDoctest(reprlocation_lines) + + def reportinfo(self) -> tuple[os.PathLike[str] | str, int | None, str]: + return self.path, self.dtest.lineno, f"[doctest] {self.name}" + + +def _get_flag_lookup() -> dict[str, int]: + import doctest + + return dict( + DONT_ACCEPT_TRUE_FOR_1=doctest.DONT_ACCEPT_TRUE_FOR_1, + DONT_ACCEPT_BLANKLINE=doctest.DONT_ACCEPT_BLANKLINE, + NORMALIZE_WHITESPACE=doctest.NORMALIZE_WHITESPACE, + ELLIPSIS=doctest.ELLIPSIS, + IGNORE_EXCEPTION_DETAIL=doctest.IGNORE_EXCEPTION_DETAIL, + COMPARISON_FLAGS=doctest.COMPARISON_FLAGS, + ALLOW_UNICODE=_get_allow_unicode_flag(), + ALLOW_BYTES=_get_allow_bytes_flag(), + NUMBER=_get_number_flag(), + ) + + +def get_optionflags(config: Config) -> int: + optionflags_str = config.getini("doctest_optionflags") + flag_lookup_table = _get_flag_lookup() + flag_acc = 0 + for flag in optionflags_str: + flag_acc |= flag_lookup_table[flag] + return flag_acc + + +def _get_continue_on_failure(config: Config) -> bool: + continue_on_failure: bool = config.getvalue("doctest_continue_on_failure") + if continue_on_failure: + # We need to turn off this if we use pdb since we should stop at + # the first failure. + if config.getvalue("usepdb"): + continue_on_failure = False + return continue_on_failure + + +class DoctestTextfile(Module): + obj = None + + def collect(self) -> Iterable[DoctestItem]: + import doctest + + # Inspired by doctest.testfile; ideally we would use it directly, + # but it doesn't support passing a custom checker. + encoding = self.config.getini("doctest_encoding") + text = self.path.read_text(encoding) + filename = str(self.path) + name = self.path.name + globs = {"__name__": "__main__"} + + optionflags = get_optionflags(self.config) + + runner = _get_runner( + verbose=False, + optionflags=optionflags, + checker=_get_checker(), + continue_on_failure=_get_continue_on_failure(self.config), + ) + + parser = doctest.DocTestParser() + test = parser.get_doctest(text, globs, name, filename, 0) + if test.examples: + yield DoctestItem.from_parent( + self, name=test.name, runner=runner, dtest=test + ) + + +def _check_all_skipped(test: doctest.DocTest) -> None: + """Raise pytest.skip() if all examples in the given DocTest have the SKIP + option set.""" + import doctest + + all_skipped = all(x.options.get(doctest.SKIP, False) for x in test.examples) + if all_skipped: + skip("all tests skipped by +SKIP option") + + +def _is_mocked(obj: object) -> bool: + """Return if an object is possibly a mock object by checking the + existence of a highly improbable attribute.""" + return ( + safe_getattr(obj, "pytest_mock_example_attribute_that_shouldnt_exist", None) + is not None + ) + + +@contextmanager +def _patch_unwrap_mock_aware() -> Generator[None]: + """Context manager which replaces ``inspect.unwrap`` with a version + that's aware of mock objects and doesn't recurse into them.""" + real_unwrap = inspect.unwrap + + def _mock_aware_unwrap( + func: Callable[..., Any], *, stop: Callable[[Any], Any] | None = None + ) -> Any: + try: + if stop is None or stop is _is_mocked: + return real_unwrap(func, stop=_is_mocked) + _stop = stop + return real_unwrap(func, stop=lambda obj: _is_mocked(obj) or _stop(func)) + except Exception as e: + warnings.warn( + f"Got {e!r} when unwrapping {func!r}. This is usually caused " + "by a violation of Python's object protocol; see e.g. " + "https://github.com/pytest-dev/pytest/issues/5080", + PytestWarning, + ) + raise + + inspect.unwrap = _mock_aware_unwrap + try: + yield + finally: + inspect.unwrap = real_unwrap + + +class DoctestModule(Module): + def collect(self) -> Iterable[DoctestItem]: + import doctest + + class MockAwareDocTestFinder(doctest.DocTestFinder): + py_ver_info_minor = sys.version_info[:2] + is_find_lineno_broken = ( + py_ver_info_minor < (3, 11) + or (py_ver_info_minor == (3, 11) and sys.version_info.micro < 9) + or (py_ver_info_minor == (3, 12) and sys.version_info.micro < 3) + ) + if is_find_lineno_broken: + + def _find_lineno(self, obj, source_lines): + """On older Pythons, doctest code does not take into account + `@property`. https://github.com/python/cpython/issues/61648 + + Moreover, wrapped Doctests need to be unwrapped so the correct + line number is returned. #8796 + """ + if isinstance(obj, property): + obj = getattr(obj, "fget", obj) + + if hasattr(obj, "__wrapped__"): + # Get the main obj in case of it being wrapped + obj = inspect.unwrap(obj) + + # Type ignored because this is a private function. + return super()._find_lineno( # type:ignore[misc] + obj, + source_lines, + ) + + if sys.version_info < (3, 10): + + def _find( + self, tests, obj, name, module, source_lines, globs, seen + ) -> None: + """Override _find to work around issue in stdlib. + + https://github.com/pytest-dev/pytest/issues/3456 + https://github.com/python/cpython/issues/69718 + """ + if _is_mocked(obj): + return # pragma: no cover + with _patch_unwrap_mock_aware(): + # Type ignored because this is a private function. + super()._find( # type:ignore[misc] + tests, obj, name, module, source_lines, globs, seen + ) + + if sys.version_info < (3, 13): + + def _from_module(self, module, object): + """`cached_property` objects are never considered a part + of the 'current module'. As such they are skipped by doctest. + Here we override `_from_module` to check the underlying + function instead. https://github.com/python/cpython/issues/107995 + """ + if isinstance(object, functools.cached_property): + object = object.func + + # Type ignored because this is a private function. + return super()._from_module(module, object) # type: ignore[misc] + + try: + module = self.obj + except Collector.CollectError: + if self.config.getvalue("doctest_ignore_import_errors"): + skip(f"unable to import module {self.path!r}") + else: + raise + + # While doctests currently don't support fixtures directly, we still + # need to pick up autouse fixtures. + self.session._fixturemanager.parsefactories(self) + + # Uses internal doctest module parsing mechanism. + finder = MockAwareDocTestFinder() + optionflags = get_optionflags(self.config) + runner = _get_runner( + verbose=False, + optionflags=optionflags, + checker=_get_checker(), + continue_on_failure=_get_continue_on_failure(self.config), + ) + + for test in finder.find(module, module.__name__): + if test.examples: # skip empty doctests + yield DoctestItem.from_parent( + self, name=test.name, runner=runner, dtest=test + ) + + +def _init_checker_class() -> type[doctest.OutputChecker]: + import doctest + import re + + class LiteralsOutputChecker(doctest.OutputChecker): + # Based on doctest_nose_plugin.py from the nltk project + # (https://github.com/nltk/nltk) and on the "numtest" doctest extension + # by Sebastien Boisgerault (https://github.com/boisgera/numtest). + + _unicode_literal_re = re.compile(r"(\W|^)[uU]([rR]?[\'\"])", re.UNICODE) + _bytes_literal_re = re.compile(r"(\W|^)[bB]([rR]?[\'\"])", re.UNICODE) + _number_re = re.compile( + r""" + (?P + (?P + (?P [+-]?\d*)\.(?P\d+) + | + (?P [+-]?\d+)\. + ) + (?: + [Ee] + (?P [+-]?\d+) + )? + | + (?P [+-]?\d+) + (?: + [Ee] + (?P [+-]?\d+) + ) + ) + """, + re.VERBOSE, + ) + + def check_output(self, want: str, got: str, optionflags: int) -> bool: + if super().check_output(want, got, optionflags): + return True + + allow_unicode = optionflags & _get_allow_unicode_flag() + allow_bytes = optionflags & _get_allow_bytes_flag() + allow_number = optionflags & _get_number_flag() + + if not allow_unicode and not allow_bytes and not allow_number: + return False + + def remove_prefixes(regex: Pattern[str], txt: str) -> str: + return re.sub(regex, r"\1\2", txt) + + if allow_unicode: + want = remove_prefixes(self._unicode_literal_re, want) + got = remove_prefixes(self._unicode_literal_re, got) + + if allow_bytes: + want = remove_prefixes(self._bytes_literal_re, want) + got = remove_prefixes(self._bytes_literal_re, got) + + if allow_number: + got = self._remove_unwanted_precision(want, got) + + return super().check_output(want, got, optionflags) + + def _remove_unwanted_precision(self, want: str, got: str) -> str: + wants = list(self._number_re.finditer(want)) + gots = list(self._number_re.finditer(got)) + if len(wants) != len(gots): + return got + offset = 0 + for w, g in zip(wants, gots): + fraction: str | None = w.group("fraction") + exponent: str | None = w.group("exponent1") + if exponent is None: + exponent = w.group("exponent2") + precision = 0 if fraction is None else len(fraction) + if exponent is not None: + precision -= int(exponent) + if float(w.group()) == approx(float(g.group()), abs=10**-precision): + # They're close enough. Replace the text we actually + # got with the text we want, so that it will match when we + # check the string literally. + got = ( + got[: g.start() + offset] + w.group() + got[g.end() + offset :] + ) + offset += w.end() - w.start() - (g.end() - g.start()) + return got + + return LiteralsOutputChecker + + +def _get_checker() -> doctest.OutputChecker: + """Return a doctest.OutputChecker subclass that supports some + additional options: + + * ALLOW_UNICODE and ALLOW_BYTES options to ignore u'' and b'' + prefixes (respectively) in string literals. Useful when the same + doctest should run in Python 2 and Python 3. + + * NUMBER to ignore floating-point differences smaller than the + precision of the literal number in the doctest. + + An inner class is used to avoid importing "doctest" at the module + level. + """ + global CHECKER_CLASS + if CHECKER_CLASS is None: + CHECKER_CLASS = _init_checker_class() + return CHECKER_CLASS() + + +def _get_allow_unicode_flag() -> int: + """Register and return the ALLOW_UNICODE flag.""" + import doctest + + return doctest.register_optionflag("ALLOW_UNICODE") + + +def _get_allow_bytes_flag() -> int: + """Register and return the ALLOW_BYTES flag.""" + import doctest + + return doctest.register_optionflag("ALLOW_BYTES") + + +def _get_number_flag() -> int: + """Register and return the NUMBER flag.""" + import doctest + + return doctest.register_optionflag("NUMBER") + + +def _get_report_choice(key: str) -> int: + """Return the actual `doctest` module flag value. + + We want to do it as late as possible to avoid importing `doctest` and all + its dependencies when parsing options, as it adds overhead and breaks tests. + """ + import doctest + + return { + DOCTEST_REPORT_CHOICE_UDIFF: doctest.REPORT_UDIFF, + DOCTEST_REPORT_CHOICE_CDIFF: doctest.REPORT_CDIFF, + DOCTEST_REPORT_CHOICE_NDIFF: doctest.REPORT_NDIFF, + DOCTEST_REPORT_CHOICE_ONLY_FIRST_FAILURE: doctest.REPORT_ONLY_FIRST_FAILURE, + DOCTEST_REPORT_CHOICE_NONE: 0, + }[key] + + +@fixture(scope="session") +def doctest_namespace() -> dict[str, Any]: + """Fixture that returns a :py:class:`dict` that will be injected into the + namespace of doctests. + + Usually this fixture is used in conjunction with another ``autouse`` fixture: + + .. code-block:: python + + @pytest.fixture(autouse=True) + def add_np(doctest_namespace): + doctest_namespace["np"] = numpy + + For more details: :ref:`doctest_namespace`. + """ + return dict() diff --git a/.venv/lib/python3.11/site-packages/_pytest/helpconfig.py b/.venv/lib/python3.11/site-packages/_pytest/helpconfig.py new file mode 100644 index 0000000000000000000000000000000000000000..1886d5c93426fc327a4a2e6da28a4afeb2aae540 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/helpconfig.py @@ -0,0 +1,276 @@ +# mypy: allow-untyped-defs +"""Version info, help messages, tracing configuration.""" + +from __future__ import annotations + +from argparse import Action +import os +import sys +from typing import Generator + +from _pytest.config import Config +from _pytest.config import ExitCode +from _pytest.config import PrintHelp +from _pytest.config.argparsing import Parser +from _pytest.terminal import TerminalReporter +import pytest + + +class HelpAction(Action): + """An argparse Action that will raise an exception in order to skip the + rest of the argument parsing when --help is passed. + + This prevents argparse from quitting due to missing required arguments + when any are defined, for example by ``pytest_addoption``. + This is similar to the way that the builtin argparse --help option is + implemented by raising SystemExit. + """ + + def __init__(self, option_strings, dest=None, default=False, help=None): + super().__init__( + option_strings=option_strings, + dest=dest, + const=True, + default=default, + nargs=0, + help=help, + ) + + def __call__(self, parser, namespace, values, option_string=None): + setattr(namespace, self.dest, self.const) + + # We should only skip the rest of the parsing after preparse is done. + if getattr(parser._parser, "after_preparse", False): + raise PrintHelp + + +def pytest_addoption(parser: Parser) -> None: + group = parser.getgroup("debugconfig") + group.addoption( + "--version", + "-V", + action="count", + default=0, + dest="version", + help="Display pytest version and information about plugins. " + "When given twice, also display information about plugins.", + ) + group._addoption( + "-h", + "--help", + action=HelpAction, + dest="help", + help="Show help message and configuration info", + ) + group._addoption( + "-p", + action="append", + dest="plugins", + default=[], + metavar="name", + help="Early-load given plugin module name or entry point (multi-allowed). " + "To avoid loading of plugins, use the `no:` prefix, e.g. " + "`no:doctest`.", + ) + group.addoption( + "--traceconfig", + "--trace-config", + action="store_true", + default=False, + help="Trace considerations of conftest.py files", + ) + group.addoption( + "--debug", + action="store", + nargs="?", + const="pytestdebug.log", + dest="debug", + metavar="DEBUG_FILE_NAME", + help="Store internal tracing debug information in this log file. " + "This file is opened with 'w' and truncated as a result, care advised. " + "Default: pytestdebug.log.", + ) + group._addoption( + "-o", + "--override-ini", + dest="override_ini", + action="append", + help='Override ini option with "option=value" style, ' + "e.g. `-o xfail_strict=True -o cache_dir=cache`.", + ) + + +@pytest.hookimpl(wrapper=True) +def pytest_cmdline_parse() -> Generator[None, Config, Config]: + config = yield + + if config.option.debug: + # --debug | --debug was provided. + path = config.option.debug + debugfile = open(path, "w", encoding="utf-8") + debugfile.write( + "versions pytest-{}, " + "python-{}\ninvocation_dir={}\ncwd={}\nargs={}\n\n".format( + pytest.__version__, + ".".join(map(str, sys.version_info)), + config.invocation_params.dir, + os.getcwd(), + config.invocation_params.args, + ) + ) + config.trace.root.setwriter(debugfile.write) + undo_tracing = config.pluginmanager.enable_tracing() + sys.stderr.write(f"writing pytest debug information to {path}\n") + + def unset_tracing() -> None: + debugfile.close() + sys.stderr.write(f"wrote pytest debug information to {debugfile.name}\n") + config.trace.root.setwriter(None) + undo_tracing() + + config.add_cleanup(unset_tracing) + + return config + + +def showversion(config: Config) -> None: + if config.option.version > 1: + sys.stdout.write( + f"This is pytest version {pytest.__version__}, imported from {pytest.__file__}\n" + ) + plugininfo = getpluginversioninfo(config) + if plugininfo: + for line in plugininfo: + sys.stdout.write(line + "\n") + else: + sys.stdout.write(f"pytest {pytest.__version__}\n") + + +def pytest_cmdline_main(config: Config) -> int | ExitCode | None: + if config.option.version > 0: + showversion(config) + return 0 + elif config.option.help: + config._do_configure() + showhelp(config) + config._ensure_unconfigure() + return 0 + return None + + +def showhelp(config: Config) -> None: + import textwrap + + reporter: TerminalReporter | None = config.pluginmanager.get_plugin( + "terminalreporter" + ) + assert reporter is not None + tw = reporter._tw + tw.write(config._parser.optparser.format_help()) + tw.line() + tw.line( + "[pytest] ini-options in the first " + "pytest.ini|tox.ini|setup.cfg|pyproject.toml file found:" + ) + tw.line() + + columns = tw.fullwidth # costly call + indent_len = 24 # based on argparse's max_help_position=24 + indent = " " * indent_len + for name in config._parser._ininames: + help, type, default = config._parser._inidict[name] + if type is None: + type = "string" + if help is None: + raise TypeError(f"help argument cannot be None for {name}") + spec = f"{name} ({type}):" + tw.write(f" {spec}") + spec_len = len(spec) + if spec_len > (indent_len - 3): + # Display help starting at a new line. + tw.line() + helplines = textwrap.wrap( + help, + columns, + initial_indent=indent, + subsequent_indent=indent, + break_on_hyphens=False, + ) + + for line in helplines: + tw.line(line) + else: + # Display help starting after the spec, following lines indented. + tw.write(" " * (indent_len - spec_len - 2)) + wrapped = textwrap.wrap(help, columns - indent_len, break_on_hyphens=False) + + if wrapped: + tw.line(wrapped[0]) + for line in wrapped[1:]: + tw.line(indent + line) + + tw.line() + tw.line("Environment variables:") + vars = [ + ( + "CI", + "When set (regardless of value), pytest knows it is running in a " + "CI process and does not truncate summary info", + ), + ("BUILD_NUMBER", "Equivalent to CI"), + ("PYTEST_ADDOPTS", "Extra command line options"), + ("PYTEST_PLUGINS", "Comma-separated plugins to load during startup"), + ("PYTEST_DISABLE_PLUGIN_AUTOLOAD", "Set to disable plugin auto-loading"), + ("PYTEST_DEBUG", "Set to enable debug tracing of pytest's internals"), + ] + for name, help in vars: + tw.line(f" {name:<24} {help}") + tw.line() + tw.line() + + tw.line("to see available markers type: pytest --markers") + tw.line("to see available fixtures type: pytest --fixtures") + tw.line( + "(shown according to specified file_or_dir or current dir " + "if not specified; fixtures with leading '_' are only shown " + "with the '-v' option" + ) + + for warningreport in reporter.stats.get("warnings", []): + tw.line("warning : " + warningreport.message, red=True) + + +conftest_options = [("pytest_plugins", "list of plugin names to load")] + + +def getpluginversioninfo(config: Config) -> list[str]: + lines = [] + plugininfo = config.pluginmanager.list_plugin_distinfo() + if plugininfo: + lines.append("registered third-party plugins:") + for plugin, dist in plugininfo: + loc = getattr(plugin, "__file__", repr(plugin)) + content = f"{dist.project_name}-{dist.version} at {loc}" + lines.append(" " + content) + return lines + + +def pytest_report_header(config: Config) -> list[str]: + lines = [] + if config.option.debug or config.option.traceconfig: + lines.append(f"using: pytest-{pytest.__version__}") + + verinfo = getpluginversioninfo(config) + if verinfo: + lines.extend(verinfo) + + if config.option.traceconfig: + lines.append("active plugins:") + items = config.pluginmanager.list_name_plugin() + for name, plugin in items: + if hasattr(plugin, "__file__"): + r = plugin.__file__ + else: + r = repr(plugin) + lines.append(f" {name:<20}: {r}") + return lines diff --git a/.venv/lib/python3.11/site-packages/_pytest/hookspec.py b/.venv/lib/python3.11/site-packages/_pytest/hookspec.py new file mode 100644 index 0000000000000000000000000000000000000000..0a41b0aca471a15bbf41d5d0c7d31f36ec69a2fd --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/hookspec.py @@ -0,0 +1,1333 @@ +# mypy: allow-untyped-defs +# ruff: noqa: T100 +"""Hook specifications for pytest plugins which are invoked by pytest itself +and by builtin plugins.""" + +from __future__ import annotations + +from pathlib import Path +from typing import Any +from typing import Mapping +from typing import Sequence +from typing import TYPE_CHECKING + +from pluggy import HookspecMarker + +from .deprecated import HOOK_LEGACY_PATH_ARG + + +if TYPE_CHECKING: + import pdb + from typing import Literal + import warnings + + from _pytest._code.code import ExceptionInfo + from _pytest._code.code import ExceptionRepr + from _pytest.compat import LEGACY_PATH + from _pytest.config import _PluggyPlugin + from _pytest.config import Config + from _pytest.config import ExitCode + from _pytest.config import PytestPluginManager + from _pytest.config.argparsing import Parser + from _pytest.fixtures import FixtureDef + from _pytest.fixtures import SubRequest + from _pytest.main import Session + from _pytest.nodes import Collector + from _pytest.nodes import Item + from _pytest.outcomes import Exit + from _pytest.python import Class + from _pytest.python import Function + from _pytest.python import Metafunc + from _pytest.python import Module + from _pytest.reports import CollectReport + from _pytest.reports import TestReport + from _pytest.runner import CallInfo + from _pytest.terminal import TerminalReporter + from _pytest.terminal import TestShortLogReport + + +hookspec = HookspecMarker("pytest") + +# ------------------------------------------------------------------------- +# Initialization hooks called for every plugin +# ------------------------------------------------------------------------- + + +@hookspec(historic=True) +def pytest_addhooks(pluginmanager: PytestPluginManager) -> None: + """Called at plugin registration time to allow adding new hooks via a call to + :func:`pluginmanager.add_hookspecs(module_or_class, prefix) `. + + :param pluginmanager: The pytest plugin manager. + + .. note:: + This hook is incompatible with hook wrappers. + + Use in conftest plugins + ======================= + + If a conftest plugin implements this hook, it will be called immediately + when the conftest is registered. + """ + + +@hookspec(historic=True) +def pytest_plugin_registered( + plugin: _PluggyPlugin, + plugin_name: str, + manager: PytestPluginManager, +) -> None: + """A new pytest plugin got registered. + + :param plugin: The plugin module or instance. + :param plugin_name: The name by which the plugin is registered. + :param manager: The pytest plugin manager. + + .. note:: + This hook is incompatible with hook wrappers. + + Use in conftest plugins + ======================= + + If a conftest plugin implements this hook, it will be called immediately + when the conftest is registered, once for each plugin registered thus far + (including itself!), and for all plugins thereafter when they are + registered. + """ + + +@hookspec(historic=True) +def pytest_addoption(parser: Parser, pluginmanager: PytestPluginManager) -> None: + """Register argparse-style options and ini-style config values, + called once at the beginning of a test run. + + :param parser: + To add command line options, call + :py:func:`parser.addoption(...) `. + To add ini-file values call :py:func:`parser.addini(...) + `. + + :param pluginmanager: + The pytest plugin manager, which can be used to install :py:func:`~pytest.hookspec`'s + or :py:func:`~pytest.hookimpl`'s and allow one plugin to call another plugin's hooks + to change how command line options are added. + + Options can later be accessed through the + :py:class:`config ` object, respectively: + + - :py:func:`config.getoption(name) ` to + retrieve the value of a command line option. + + - :py:func:`config.getini(name) ` to retrieve + a value read from an ini-style file. + + The config object is passed around on many internal objects via the ``.config`` + attribute or can be retrieved as the ``pytestconfig`` fixture. + + .. note:: + This hook is incompatible with hook wrappers. + + Use in conftest plugins + ======================= + + If a conftest plugin implements this hook, it will be called immediately + when the conftest is registered. + + This hook is only called for :ref:`initial conftests `. + """ + + +@hookspec(historic=True) +def pytest_configure(config: Config) -> None: + """Allow plugins and conftest files to perform initial configuration. + + .. note:: + This hook is incompatible with hook wrappers. + + :param config: The pytest config object. + + Use in conftest plugins + ======================= + + This hook is called for every :ref:`initial conftest ` file + after command line options have been parsed. After that, the hook is called + for other conftest files as they are registered. + """ + + +# ------------------------------------------------------------------------- +# Bootstrapping hooks called for plugins registered early enough: +# internal and 3rd party plugins. +# ------------------------------------------------------------------------- + + +@hookspec(firstresult=True) +def pytest_cmdline_parse( + pluginmanager: PytestPluginManager, args: list[str] +) -> Config | None: + """Return an initialized :class:`~pytest.Config`, parsing the specified args. + + Stops at first non-None result, see :ref:`firstresult`. + + .. note:: + This hook is only called for plugin classes passed to the + ``plugins`` arg when using `pytest.main`_ to perform an in-process + test run. + + :param pluginmanager: The pytest plugin manager. + :param args: List of arguments passed on the command line. + :returns: A pytest config object. + + Use in conftest plugins + ======================= + + This hook is not called for conftest files. + """ + + +def pytest_load_initial_conftests( + early_config: Config, parser: Parser, args: list[str] +) -> None: + """Called to implement the loading of :ref:`initial conftest files + ` ahead of command line option parsing. + + :param early_config: The pytest config object. + :param args: Arguments passed on the command line. + :param parser: To add command line options. + + Use in conftest plugins + ======================= + + This hook is not called for conftest files. + """ + + +@hookspec(firstresult=True) +def pytest_cmdline_main(config: Config) -> ExitCode | int | None: + """Called for performing the main command line action. + + The default implementation will invoke the configure hooks and + :hook:`pytest_runtestloop`. + + Stops at first non-None result, see :ref:`firstresult`. + + :param config: The pytest config object. + :returns: The exit code. + + Use in conftest plugins + ======================= + + This hook is only called for :ref:`initial conftests `. + """ + + +# ------------------------------------------------------------------------- +# collection hooks +# ------------------------------------------------------------------------- + + +@hookspec(firstresult=True) +def pytest_collection(session: Session) -> object | None: + """Perform the collection phase for the given session. + + Stops at first non-None result, see :ref:`firstresult`. + The return value is not used, but only stops further processing. + + The default collection phase is this (see individual hooks for full details): + + 1. Starting from ``session`` as the initial collector: + + 1. ``pytest_collectstart(collector)`` + 2. ``report = pytest_make_collect_report(collector)`` + 3. ``pytest_exception_interact(collector, call, report)`` if an interactive exception occurred + 4. For each collected node: + + 1. If an item, ``pytest_itemcollected(item)`` + 2. If a collector, recurse into it. + + 5. ``pytest_collectreport(report)`` + + 2. ``pytest_collection_modifyitems(session, config, items)`` + + 1. ``pytest_deselected(items)`` for any deselected items (may be called multiple times) + + 3. ``pytest_collection_finish(session)`` + 4. Set ``session.items`` to the list of collected items + 5. Set ``session.testscollected`` to the number of collected items + + You can implement this hook to only perform some action before collection, + for example the terminal plugin uses it to start displaying the collection + counter (and returns `None`). + + :param session: The pytest session object. + + Use in conftest plugins + ======================= + + This hook is only called for :ref:`initial conftests `. + """ + + +def pytest_collection_modifyitems( + session: Session, config: Config, items: list[Item] +) -> None: + """Called after collection has been performed. May filter or re-order + the items in-place. + + When items are deselected (filtered out from ``items``), + the hook :hook:`pytest_deselected` must be called explicitly + with the deselected items to properly notify other plugins, + e.g. with ``config.hook.pytest_deselected(deselected_items)``. + + :param session: The pytest session object. + :param config: The pytest config object. + :param items: List of item objects. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +def pytest_collection_finish(session: Session) -> None: + """Called after collection has been performed and modified. + + :param session: The pytest session object. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +@hookspec( + firstresult=True, + warn_on_impl_args={ + "path": HOOK_LEGACY_PATH_ARG.format( + pylib_path_arg="path", pathlib_path_arg="collection_path" + ), + }, +) +def pytest_ignore_collect( + collection_path: Path, path: LEGACY_PATH, config: Config +) -> bool | None: + """Return ``True`` to ignore this path for collection. + + Return ``None`` to let other plugins ignore the path for collection. + + Returning ``False`` will forcefully *not* ignore this path for collection, + without giving a chance for other plugins to ignore this path. + + This hook is consulted for all files and directories prior to calling + more specific hooks. + + Stops at first non-None result, see :ref:`firstresult`. + + :param collection_path: The path to analyze. + :type collection_path: pathlib.Path + :param path: The path to analyze (deprecated). + :param config: The pytest config object. + + .. versionchanged:: 7.0.0 + The ``collection_path`` parameter was added as a :class:`pathlib.Path` + equivalent of the ``path`` parameter. The ``path`` parameter + has been deprecated. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given collection path, only + conftest files in parent directories of the collection path are consulted + (if the path is a directory, its own conftest file is *not* consulted - a + directory cannot ignore itself!). + """ + + +@hookspec(firstresult=True) +def pytest_collect_directory(path: Path, parent: Collector) -> Collector | None: + """Create a :class:`~pytest.Collector` for the given directory, or None if + not relevant. + + .. versionadded:: 8.0 + + For best results, the returned collector should be a subclass of + :class:`~pytest.Directory`, but this is not required. + + The new node needs to have the specified ``parent`` as a parent. + + Stops at first non-None result, see :ref:`firstresult`. + + :param path: The path to analyze. + :type path: pathlib.Path + + See :ref:`custom directory collectors` for a simple example of use of this + hook. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given collection path, only + conftest files in parent directories of the collection path are consulted + (if the path is a directory, its own conftest file is *not* consulted - a + directory cannot collect itself!). + """ + + +@hookspec( + warn_on_impl_args={ + "path": HOOK_LEGACY_PATH_ARG.format( + pylib_path_arg="path", pathlib_path_arg="file_path" + ), + }, +) +def pytest_collect_file( + file_path: Path, path: LEGACY_PATH, parent: Collector +) -> Collector | None: + """Create a :class:`~pytest.Collector` for the given path, or None if not relevant. + + For best results, the returned collector should be a subclass of + :class:`~pytest.File`, but this is not required. + + The new node needs to have the specified ``parent`` as a parent. + + :param file_path: The path to analyze. + :type file_path: pathlib.Path + :param path: The path to collect (deprecated). + + .. versionchanged:: 7.0.0 + The ``file_path`` parameter was added as a :class:`pathlib.Path` + equivalent of the ``path`` parameter. The ``path`` parameter + has been deprecated. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given file path, only + conftest files in parent directories of the file path are consulted. + """ + + +# logging hooks for collection + + +def pytest_collectstart(collector: Collector) -> None: + """Collector starts collecting. + + :param collector: + The collector. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given collector, only + conftest files in the collector's directory and its parent directories are + consulted. + """ + + +def pytest_itemcollected(item: Item) -> None: + """We just collected a test item. + + :param item: + The item. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_collectreport(report: CollectReport) -> None: + """Collector finished collecting. + + :param report: + The collect report. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given collector, only + conftest files in the collector's directory and its parent directories are + consulted. + """ + + +def pytest_deselected(items: Sequence[Item]) -> None: + """Called for deselected test items, e.g. by keyword. + + Note that this hook has two integration aspects for plugins: + + - it can be *implemented* to be notified of deselected items + - it must be *called* from :hook:`pytest_collection_modifyitems` + implementations when items are deselected (to properly notify other plugins). + + May be called multiple times. + + :param items: + The items. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. + """ + + +@hookspec(firstresult=True) +def pytest_make_collect_report(collector: Collector) -> CollectReport | None: + """Perform :func:`collector.collect() ` and return + a :class:`~pytest.CollectReport`. + + Stops at first non-None result, see :ref:`firstresult`. + + :param collector: + The collector. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given collector, only + conftest files in the collector's directory and its parent directories are + consulted. + """ + + +# ------------------------------------------------------------------------- +# Python test function related hooks +# ------------------------------------------------------------------------- + + +@hookspec( + firstresult=True, + warn_on_impl_args={ + "path": HOOK_LEGACY_PATH_ARG.format( + pylib_path_arg="path", pathlib_path_arg="module_path" + ), + }, +) +def pytest_pycollect_makemodule( + module_path: Path, path: LEGACY_PATH, parent +) -> Module | None: + """Return a :class:`pytest.Module` collector or None for the given path. + + This hook will be called for each matching test module path. + The :hook:`pytest_collect_file` hook needs to be used if you want to + create test modules for files that do not match as a test module. + + Stops at first non-None result, see :ref:`firstresult`. + + :param module_path: The path of the module to collect. + :type module_path: pathlib.Path + :param path: The path of the module to collect (deprecated). + + .. versionchanged:: 7.0.0 + The ``module_path`` parameter was added as a :class:`pathlib.Path` + equivalent of the ``path`` parameter. + + The ``path`` parameter has been deprecated in favor of ``fspath``. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given parent collector, + only conftest files in the collector's directory and its parent directories + are consulted. + """ + + +@hookspec(firstresult=True) +def pytest_pycollect_makeitem( + collector: Module | Class, name: str, obj: object +) -> None | Item | Collector | list[Item | Collector]: + """Return a custom item/collector for a Python object in a module, or None. + + Stops at first non-None result, see :ref:`firstresult`. + + :param collector: + The module/class collector. + :param name: + The name of the object in the module/class. + :param obj: + The object. + :returns: + The created items/collectors. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given collector, only + conftest files in the collector's directory and its parent directories + are consulted. + """ + + +@hookspec(firstresult=True) +def pytest_pyfunc_call(pyfuncitem: Function) -> object | None: + """Call underlying test function. + + Stops at first non-None result, see :ref:`firstresult`. + + :param pyfuncitem: + The function item. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only + conftest files in the item's directory and its parent directories + are consulted. + """ + + +def pytest_generate_tests(metafunc: Metafunc) -> None: + """Generate (multiple) parametrized calls to a test function. + + :param metafunc: + The :class:`~pytest.Metafunc` helper for the test function. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given function definition, + only conftest files in the functions's directory and its parent directories + are consulted. + """ + + +@hookspec(firstresult=True) +def pytest_make_parametrize_id(config: Config, val: object, argname: str) -> str | None: + """Return a user-friendly string representation of the given ``val`` + that will be used by @pytest.mark.parametrize calls, or None if the hook + doesn't know about ``val``. + + The parameter name is available as ``argname``, if required. + + Stops at first non-None result, see :ref:`firstresult`. + + :param config: The pytest config object. + :param val: The parametrized value. + :param argname: The automatic parameter name produced by pytest. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. + """ + + +# ------------------------------------------------------------------------- +# runtest related hooks +# ------------------------------------------------------------------------- + + +@hookspec(firstresult=True) +def pytest_runtestloop(session: Session) -> object | None: + """Perform the main runtest loop (after collection finished). + + The default hook implementation performs the runtest protocol for all items + collected in the session (``session.items``), unless the collection failed + or the ``collectonly`` pytest option is set. + + If at any point :py:func:`pytest.exit` is called, the loop is + terminated immediately. + + If at any point ``session.shouldfail`` or ``session.shouldstop`` are set, the + loop is terminated after the runtest protocol for the current item is finished. + + :param session: The pytest session object. + + Stops at first non-None result, see :ref:`firstresult`. + The return value is not used, but only stops further processing. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. + """ + + +@hookspec(firstresult=True) +def pytest_runtest_protocol(item: Item, nextitem: Item | None) -> object | None: + """Perform the runtest protocol for a single test item. + + The default runtest protocol is this (see individual hooks for full details): + + - ``pytest_runtest_logstart(nodeid, location)`` + + - Setup phase: + - ``call = pytest_runtest_setup(item)`` (wrapped in ``CallInfo(when="setup")``) + - ``report = pytest_runtest_makereport(item, call)`` + - ``pytest_runtest_logreport(report)`` + - ``pytest_exception_interact(call, report)`` if an interactive exception occurred + + - Call phase, if the setup passed and the ``setuponly`` pytest option is not set: + - ``call = pytest_runtest_call(item)`` (wrapped in ``CallInfo(when="call")``) + - ``report = pytest_runtest_makereport(item, call)`` + - ``pytest_runtest_logreport(report)`` + - ``pytest_exception_interact(call, report)`` if an interactive exception occurred + + - Teardown phase: + - ``call = pytest_runtest_teardown(item, nextitem)`` (wrapped in ``CallInfo(when="teardown")``) + - ``report = pytest_runtest_makereport(item, call)`` + - ``pytest_runtest_logreport(report)`` + - ``pytest_exception_interact(call, report)`` if an interactive exception occurred + + - ``pytest_runtest_logfinish(nodeid, location)`` + + :param item: Test item for which the runtest protocol is performed. + :param nextitem: The scheduled-to-be-next test item (or None if this is the end my friend). + + Stops at first non-None result, see :ref:`firstresult`. + The return value is not used, but only stops further processing. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. + """ + + +def pytest_runtest_logstart(nodeid: str, location: tuple[str, int | None, str]) -> None: + """Called at the start of running the runtest protocol for a single item. + + See :hook:`pytest_runtest_protocol` for a description of the runtest protocol. + + :param nodeid: Full node ID of the item. + :param location: A tuple of ``(filename, lineno, testname)`` + where ``filename`` is a file path relative to ``config.rootpath`` + and ``lineno`` is 0-based. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_runtest_logfinish( + nodeid: str, location: tuple[str, int | None, str] +) -> None: + """Called at the end of running the runtest protocol for a single item. + + See :hook:`pytest_runtest_protocol` for a description of the runtest protocol. + + :param nodeid: Full node ID of the item. + :param location: A tuple of ``(filename, lineno, testname)`` + where ``filename`` is a file path relative to ``config.rootpath`` + and ``lineno`` is 0-based. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_runtest_setup(item: Item) -> None: + """Called to perform the setup phase for a test item. + + The default implementation runs ``setup()`` on ``item`` and all of its + parents (which haven't been setup yet). This includes obtaining the + values of fixtures required by the item (which haven't been obtained + yet). + + :param item: + The item. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_runtest_call(item: Item) -> None: + """Called to run the test for test item (the call phase). + + The default implementation calls ``item.runtest()``. + + :param item: + The item. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_runtest_teardown(item: Item, nextitem: Item | None) -> None: + """Called to perform the teardown phase for a test item. + + The default implementation runs the finalizers and calls ``teardown()`` + on ``item`` and all of its parents (which need to be torn down). This + includes running the teardown phase of fixtures required by the item (if + they go out of scope). + + :param item: + The item. + :param nextitem: + The scheduled-to-be-next test item (None if no further test item is + scheduled). This argument is used to perform exact teardowns, i.e. + calling just enough finalizers so that nextitem only needs to call + setup functions. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +@hookspec(firstresult=True) +def pytest_runtest_makereport(item: Item, call: CallInfo[None]) -> TestReport | None: + """Called to create a :class:`~pytest.TestReport` for each of + the setup, call and teardown runtest phases of a test item. + + See :hook:`pytest_runtest_protocol` for a description of the runtest protocol. + + :param item: The item. + :param call: The :class:`~pytest.CallInfo` for the phase. + + Stops at first non-None result, see :ref:`firstresult`. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_runtest_logreport(report: TestReport) -> None: + """Process the :class:`~pytest.TestReport` produced for each + of the setup, call and teardown runtest phases of an item. + + See :hook:`pytest_runtest_protocol` for a description of the runtest protocol. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +@hookspec(firstresult=True) +def pytest_report_to_serializable( + config: Config, + report: CollectReport | TestReport, +) -> dict[str, Any] | None: + """Serialize the given report object into a data structure suitable for + sending over the wire, e.g. converted to JSON. + + :param config: The pytest config object. + :param report: The report. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. The exact details may depend + on the plugin which calls the hook. + """ + + +@hookspec(firstresult=True) +def pytest_report_from_serializable( + config: Config, + data: dict[str, Any], +) -> CollectReport | TestReport | None: + """Restore a report object previously serialized with + :hook:`pytest_report_to_serializable`. + + :param config: The pytest config object. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. The exact details may depend + on the plugin which calls the hook. + """ + + +# ------------------------------------------------------------------------- +# Fixture related hooks +# ------------------------------------------------------------------------- + + +@hookspec(firstresult=True) +def pytest_fixture_setup( + fixturedef: FixtureDef[Any], request: SubRequest +) -> object | None: + """Perform fixture setup execution. + + :param fixturedef: + The fixture definition object. + :param request: + The fixture request object. + :returns: + The return value of the call to the fixture function. + + Stops at first non-None result, see :ref:`firstresult`. + + .. note:: + If the fixture function returns None, other implementations of + this hook function will continue to be called, according to the + behavior of the :ref:`firstresult` option. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given fixture, only + conftest files in the fixture scope's directory and its parent directories + are consulted. + """ + + +def pytest_fixture_post_finalizer( + fixturedef: FixtureDef[Any], request: SubRequest +) -> None: + """Called after fixture teardown, but before the cache is cleared, so + the fixture result ``fixturedef.cached_result`` is still available (not + ``None``). + + :param fixturedef: + The fixture definition object. + :param request: + The fixture request object. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given fixture, only + conftest files in the fixture scope's directory and its parent directories + are consulted. + """ + + +# ------------------------------------------------------------------------- +# test session related hooks +# ------------------------------------------------------------------------- + + +def pytest_sessionstart(session: Session) -> None: + """Called after the ``Session`` object has been created and before performing collection + and entering the run test loop. + + :param session: The pytest session object. + + Use in conftest plugins + ======================= + + This hook is only called for :ref:`initial conftests `. + """ + + +def pytest_sessionfinish( + session: Session, + exitstatus: int | ExitCode, +) -> None: + """Called after whole test run finished, right before returning the exit status to the system. + + :param session: The pytest session object. + :param exitstatus: The status which pytest will return to the system. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. + """ + + +def pytest_unconfigure(config: Config) -> None: + """Called before test process is exited. + + :param config: The pytest config object. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. + """ + + +# ------------------------------------------------------------------------- +# hooks for customizing the assert methods +# ------------------------------------------------------------------------- + + +def pytest_assertrepr_compare( + config: Config, op: str, left: object, right: object +) -> list[str] | None: + """Return explanation for comparisons in failing assert expressions. + + Return None for no custom explanation, otherwise return a list + of strings. The strings will be joined by newlines but any newlines + *in* a string will be escaped. Note that all but the first line will + be indented slightly, the intention is for the first line to be a summary. + + :param config: The pytest config object. + :param op: The operator, e.g. `"=="`, `"!="`, `"not in"`. + :param left: The left operand. + :param right: The right operand. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +def pytest_assertion_pass(item: Item, lineno: int, orig: str, expl: str) -> None: + """Called whenever an assertion passes. + + .. versionadded:: 5.0 + + Use this hook to do some processing after a passing assertion. + The original assertion information is available in the `orig` string + and the pytest introspected assertion information is available in the + `expl` string. + + This hook must be explicitly enabled by the ``enable_assertion_pass_hook`` + ini-file option: + + .. code-block:: ini + + [pytest] + enable_assertion_pass_hook=true + + You need to **clean the .pyc** files in your project directory and interpreter libraries + when enabling this option, as assertions will require to be re-written. + + :param item: pytest item object of current test. + :param lineno: Line number of the assert statement. + :param orig: String with the original assertion. + :param expl: String with the assert explanation. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in the item's directory and its parent directories are consulted. + """ + + +# ------------------------------------------------------------------------- +# Hooks for influencing reporting (invoked from _pytest_terminal). +# ------------------------------------------------------------------------- + + +@hookspec( + warn_on_impl_args={ + "startdir": HOOK_LEGACY_PATH_ARG.format( + pylib_path_arg="startdir", pathlib_path_arg="start_path" + ), + }, +) +def pytest_report_header( # type:ignore[empty-body] + config: Config, start_path: Path, startdir: LEGACY_PATH +) -> str | list[str]: + """Return a string or list of strings to be displayed as header info for terminal reporting. + + :param config: The pytest config object. + :param start_path: The starting dir. + :type start_path: pathlib.Path + :param startdir: The starting dir (deprecated). + + .. note:: + + Lines returned by a plugin are displayed before those of plugins which + ran before it. + If you want to have your line(s) displayed first, use + :ref:`trylast=True `. + + .. versionchanged:: 7.0.0 + The ``start_path`` parameter was added as a :class:`pathlib.Path` + equivalent of the ``startdir`` parameter. The ``startdir`` parameter + has been deprecated. + + Use in conftest plugins + ======================= + + This hook is only called for :ref:`initial conftests `. + """ + + +@hookspec( + warn_on_impl_args={ + "startdir": HOOK_LEGACY_PATH_ARG.format( + pylib_path_arg="startdir", pathlib_path_arg="start_path" + ), + }, +) +def pytest_report_collectionfinish( # type:ignore[empty-body] + config: Config, + start_path: Path, + startdir: LEGACY_PATH, + items: Sequence[Item], +) -> str | list[str]: + """Return a string or list of strings to be displayed after collection + has finished successfully. + + These strings will be displayed after the standard "collected X items" message. + + .. versionadded:: 3.2 + + :param config: The pytest config object. + :param start_path: The starting dir. + :type start_path: pathlib.Path + :param startdir: The starting dir (deprecated). + :param items: List of pytest items that are going to be executed; this list should not be modified. + + .. note:: + + Lines returned by a plugin are displayed before those of plugins which + ran before it. + If you want to have your line(s) displayed first, use + :ref:`trylast=True `. + + .. versionchanged:: 7.0.0 + The ``start_path`` parameter was added as a :class:`pathlib.Path` + equivalent of the ``startdir`` parameter. The ``startdir`` parameter + has been deprecated. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +@hookspec(firstresult=True) +def pytest_report_teststatus( # type:ignore[empty-body] + report: CollectReport | TestReport, config: Config +) -> TestShortLogReport | tuple[str, str, str | tuple[str, Mapping[str, bool]]]: + """Return result-category, shortletter and verbose word for status + reporting. + + The result-category is a category in which to count the result, for + example "passed", "skipped", "error" or the empty string. + + The shortletter is shown as testing progresses, for example ".", "s", + "E" or the empty string. + + The verbose word is shown as testing progresses in verbose mode, for + example "PASSED", "SKIPPED", "ERROR" or the empty string. + + pytest may style these implicitly according to the report outcome. + To provide explicit styling, return a tuple for the verbose word, + for example ``"rerun", "R", ("RERUN", {"yellow": True})``. + + :param report: The report object whose status is to be returned. + :param config: The pytest config object. + :returns: The test status. + + Stops at first non-None result, see :ref:`firstresult`. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +def pytest_terminal_summary( + terminalreporter: TerminalReporter, + exitstatus: ExitCode, + config: Config, +) -> None: + """Add a section to terminal summary reporting. + + :param terminalreporter: The internal terminal reporter object. + :param exitstatus: The exit status that will be reported back to the OS. + :param config: The pytest config object. + + .. versionadded:: 4.2 + The ``config`` parameter. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +@hookspec(historic=True) +def pytest_warning_recorded( + warning_message: warnings.WarningMessage, + when: Literal["config", "collect", "runtest"], + nodeid: str, + location: tuple[str, int, str] | None, +) -> None: + """Process a warning captured by the internal pytest warnings plugin. + + :param warning_message: + The captured warning. This is the same object produced by :class:`warnings.catch_warnings`, + and contains the same attributes as the parameters of :py:func:`warnings.showwarning`. + + :param when: + Indicates when the warning was captured. Possible values: + + * ``"config"``: during pytest configuration/initialization stage. + * ``"collect"``: during test collection. + * ``"runtest"``: during test execution. + + :param nodeid: + Full id of the item. Empty string for warnings that are not specific to + a particular node. + + :param location: + When available, holds information about the execution context of the captured + warning (filename, linenumber, function). ``function`` evaluates to + when the execution context is at the module level. + + .. versionadded:: 6.0 + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. If the warning is specific to a + particular node, only conftest files in parent directories of the node are + consulted. + """ + + +# ------------------------------------------------------------------------- +# Hooks for influencing skipping +# ------------------------------------------------------------------------- + + +def pytest_markeval_namespace( # type:ignore[empty-body] + config: Config, +) -> dict[str, Any]: + """Called when constructing the globals dictionary used for + evaluating string conditions in xfail/skipif markers. + + This is useful when the condition for a marker requires + objects that are expensive or impossible to obtain during + collection time, which is required by normal boolean + conditions. + + .. versionadded:: 6.2 + + :param config: The pytest config object. + :returns: A dictionary of additional globals to add. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given item, only conftest + files in parent directories of the item are consulted. + """ + + +# ------------------------------------------------------------------------- +# error handling and internal debugging hooks +# ------------------------------------------------------------------------- + + +def pytest_internalerror( + excrepr: ExceptionRepr, + excinfo: ExceptionInfo[BaseException], +) -> bool | None: + """Called for internal errors. + + Return True to suppress the fallback handling of printing an + INTERNALERROR message directly to sys.stderr. + + :param excrepr: The exception repr object. + :param excinfo: The exception info. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +def pytest_keyboard_interrupt( + excinfo: ExceptionInfo[KeyboardInterrupt | Exit], +) -> None: + """Called for keyboard interrupt. + + :param excinfo: The exception info. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +def pytest_exception_interact( + node: Item | Collector, + call: CallInfo[Any], + report: CollectReport | TestReport, +) -> None: + """Called when an exception was raised which can potentially be + interactively handled. + + May be called during collection (see :hook:`pytest_make_collect_report`), + in which case ``report`` is a :class:`~pytest.CollectReport`. + + May be called during runtest of an item (see :hook:`pytest_runtest_protocol`), + in which case ``report`` is a :class:`~pytest.TestReport`. + + This hook is not called if the exception that was raised is an internal + exception like ``skip.Exception``. + + :param node: + The item or collector. + :param call: + The call information. Contains the exception. + :param report: + The collection or test report. + + Use in conftest plugins + ======================= + + Any conftest file can implement this hook. For a given node, only conftest + files in parent directories of the node are consulted. + """ + + +def pytest_enter_pdb(config: Config, pdb: pdb.Pdb) -> None: + """Called upon pdb.set_trace(). + + Can be used by plugins to take special action just before the python + debugger enters interactive mode. + + :param config: The pytest config object. + :param pdb: The Pdb instance. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ + + +def pytest_leave_pdb(config: Config, pdb: pdb.Pdb) -> None: + """Called when leaving pdb (e.g. with continue after pdb.set_trace()). + + Can be used by plugins to take special action just after the python + debugger leaves interactive mode. + + :param config: The pytest config object. + :param pdb: The Pdb instance. + + Use in conftest plugins + ======================= + + Any conftest plugin can implement this hook. + """ diff --git a/.venv/lib/python3.11/site-packages/_pytest/legacypath.py b/.venv/lib/python3.11/site-packages/_pytest/legacypath.py new file mode 100644 index 0000000000000000000000000000000000000000..59e8ef6e7427ed2f548c1da72c9acceb82ef31fa --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/legacypath.py @@ -0,0 +1,468 @@ +# mypy: allow-untyped-defs +"""Add backward compatibility support for the legacy py path type.""" + +from __future__ import annotations + +import dataclasses +from pathlib import Path +import shlex +import subprocess +from typing import Final +from typing import final +from typing import TYPE_CHECKING + +from iniconfig import SectionWrapper + +from _pytest.cacheprovider import Cache +from _pytest.compat import LEGACY_PATH +from _pytest.compat import legacy_path +from _pytest.config import Config +from _pytest.config import hookimpl +from _pytest.config import PytestPluginManager +from _pytest.deprecated import check_ispytest +from _pytest.fixtures import fixture +from _pytest.fixtures import FixtureRequest +from _pytest.main import Session +from _pytest.monkeypatch import MonkeyPatch +from _pytest.nodes import Collector +from _pytest.nodes import Item +from _pytest.nodes import Node +from _pytest.pytester import HookRecorder +from _pytest.pytester import Pytester +from _pytest.pytester import RunResult +from _pytest.terminal import TerminalReporter +from _pytest.tmpdir import TempPathFactory + + +if TYPE_CHECKING: + import pexpect + + +@final +class Testdir: + """ + Similar to :class:`Pytester`, but this class works with legacy legacy_path objects instead. + + All methods just forward to an internal :class:`Pytester` instance, converting results + to `legacy_path` objects as necessary. + """ + + __test__ = False + + CLOSE_STDIN: Final = Pytester.CLOSE_STDIN + TimeoutExpired: Final = Pytester.TimeoutExpired + + def __init__(self, pytester: Pytester, *, _ispytest: bool = False) -> None: + check_ispytest(_ispytest) + self._pytester = pytester + + @property + def tmpdir(self) -> LEGACY_PATH: + """Temporary directory where tests are executed.""" + return legacy_path(self._pytester.path) + + @property + def test_tmproot(self) -> LEGACY_PATH: + return legacy_path(self._pytester._test_tmproot) + + @property + def request(self): + return self._pytester._request + + @property + def plugins(self): + return self._pytester.plugins + + @plugins.setter + def plugins(self, plugins): + self._pytester.plugins = plugins + + @property + def monkeypatch(self) -> MonkeyPatch: + return self._pytester._monkeypatch + + def make_hook_recorder(self, pluginmanager) -> HookRecorder: + """See :meth:`Pytester.make_hook_recorder`.""" + return self._pytester.make_hook_recorder(pluginmanager) + + def chdir(self) -> None: + """See :meth:`Pytester.chdir`.""" + return self._pytester.chdir() + + def finalize(self) -> None: + return self._pytester._finalize() + + def makefile(self, ext, *args, **kwargs) -> LEGACY_PATH: + """See :meth:`Pytester.makefile`.""" + if ext and not ext.startswith("."): + # pytester.makefile is going to throw a ValueError in a way that + # testdir.makefile did not, because + # pathlib.Path is stricter suffixes than py.path + # This ext arguments is likely user error, but since testdir has + # allowed this, we will prepend "." as a workaround to avoid breaking + # testdir usage that worked before + ext = "." + ext + return legacy_path(self._pytester.makefile(ext, *args, **kwargs)) + + def makeconftest(self, source) -> LEGACY_PATH: + """See :meth:`Pytester.makeconftest`.""" + return legacy_path(self._pytester.makeconftest(source)) + + def makeini(self, source) -> LEGACY_PATH: + """See :meth:`Pytester.makeini`.""" + return legacy_path(self._pytester.makeini(source)) + + def getinicfg(self, source: str) -> SectionWrapper: + """See :meth:`Pytester.getinicfg`.""" + return self._pytester.getinicfg(source) + + def makepyprojecttoml(self, source) -> LEGACY_PATH: + """See :meth:`Pytester.makepyprojecttoml`.""" + return legacy_path(self._pytester.makepyprojecttoml(source)) + + def makepyfile(self, *args, **kwargs) -> LEGACY_PATH: + """See :meth:`Pytester.makepyfile`.""" + return legacy_path(self._pytester.makepyfile(*args, **kwargs)) + + def maketxtfile(self, *args, **kwargs) -> LEGACY_PATH: + """See :meth:`Pytester.maketxtfile`.""" + return legacy_path(self._pytester.maketxtfile(*args, **kwargs)) + + def syspathinsert(self, path=None) -> None: + """See :meth:`Pytester.syspathinsert`.""" + return self._pytester.syspathinsert(path) + + def mkdir(self, name) -> LEGACY_PATH: + """See :meth:`Pytester.mkdir`.""" + return legacy_path(self._pytester.mkdir(name)) + + def mkpydir(self, name) -> LEGACY_PATH: + """See :meth:`Pytester.mkpydir`.""" + return legacy_path(self._pytester.mkpydir(name)) + + def copy_example(self, name=None) -> LEGACY_PATH: + """See :meth:`Pytester.copy_example`.""" + return legacy_path(self._pytester.copy_example(name)) + + def getnode(self, config: Config, arg) -> Item | Collector | None: + """See :meth:`Pytester.getnode`.""" + return self._pytester.getnode(config, arg) + + def getpathnode(self, path): + """See :meth:`Pytester.getpathnode`.""" + return self._pytester.getpathnode(path) + + def genitems(self, colitems: list[Item | Collector]) -> list[Item]: + """See :meth:`Pytester.genitems`.""" + return self._pytester.genitems(colitems) + + def runitem(self, source): + """See :meth:`Pytester.runitem`.""" + return self._pytester.runitem(source) + + def inline_runsource(self, source, *cmdlineargs): + """See :meth:`Pytester.inline_runsource`.""" + return self._pytester.inline_runsource(source, *cmdlineargs) + + def inline_genitems(self, *args): + """See :meth:`Pytester.inline_genitems`.""" + return self._pytester.inline_genitems(*args) + + def inline_run(self, *args, plugins=(), no_reraise_ctrlc: bool = False): + """See :meth:`Pytester.inline_run`.""" + return self._pytester.inline_run( + *args, plugins=plugins, no_reraise_ctrlc=no_reraise_ctrlc + ) + + def runpytest_inprocess(self, *args, **kwargs) -> RunResult: + """See :meth:`Pytester.runpytest_inprocess`.""" + return self._pytester.runpytest_inprocess(*args, **kwargs) + + def runpytest(self, *args, **kwargs) -> RunResult: + """See :meth:`Pytester.runpytest`.""" + return self._pytester.runpytest(*args, **kwargs) + + def parseconfig(self, *args) -> Config: + """See :meth:`Pytester.parseconfig`.""" + return self._pytester.parseconfig(*args) + + def parseconfigure(self, *args) -> Config: + """See :meth:`Pytester.parseconfigure`.""" + return self._pytester.parseconfigure(*args) + + def getitem(self, source, funcname="test_func"): + """See :meth:`Pytester.getitem`.""" + return self._pytester.getitem(source, funcname) + + def getitems(self, source): + """See :meth:`Pytester.getitems`.""" + return self._pytester.getitems(source) + + def getmodulecol(self, source, configargs=(), withinit=False): + """See :meth:`Pytester.getmodulecol`.""" + return self._pytester.getmodulecol( + source, configargs=configargs, withinit=withinit + ) + + def collect_by_name(self, modcol: Collector, name: str) -> Item | Collector | None: + """See :meth:`Pytester.collect_by_name`.""" + return self._pytester.collect_by_name(modcol, name) + + def popen( + self, + cmdargs, + stdout=subprocess.PIPE, + stderr=subprocess.PIPE, + stdin=CLOSE_STDIN, + **kw, + ): + """See :meth:`Pytester.popen`.""" + return self._pytester.popen(cmdargs, stdout, stderr, stdin, **kw) + + def run(self, *cmdargs, timeout=None, stdin=CLOSE_STDIN) -> RunResult: + """See :meth:`Pytester.run`.""" + return self._pytester.run(*cmdargs, timeout=timeout, stdin=stdin) + + def runpython(self, script) -> RunResult: + """See :meth:`Pytester.runpython`.""" + return self._pytester.runpython(script) + + def runpython_c(self, command): + """See :meth:`Pytester.runpython_c`.""" + return self._pytester.runpython_c(command) + + def runpytest_subprocess(self, *args, timeout=None) -> RunResult: + """See :meth:`Pytester.runpytest_subprocess`.""" + return self._pytester.runpytest_subprocess(*args, timeout=timeout) + + def spawn_pytest(self, string: str, expect_timeout: float = 10.0) -> pexpect.spawn: + """See :meth:`Pytester.spawn_pytest`.""" + return self._pytester.spawn_pytest(string, expect_timeout=expect_timeout) + + def spawn(self, cmd: str, expect_timeout: float = 10.0) -> pexpect.spawn: + """See :meth:`Pytester.spawn`.""" + return self._pytester.spawn(cmd, expect_timeout=expect_timeout) + + def __repr__(self) -> str: + return f"" + + def __str__(self) -> str: + return str(self.tmpdir) + + +class LegacyTestdirPlugin: + @staticmethod + @fixture + def testdir(pytester: Pytester) -> Testdir: + """ + Identical to :fixture:`pytester`, and provides an instance whose methods return + legacy ``LEGACY_PATH`` objects instead when applicable. + + New code should avoid using :fixture:`testdir` in favor of :fixture:`pytester`. + """ + return Testdir(pytester, _ispytest=True) + + +@final +@dataclasses.dataclass +class TempdirFactory: + """Backward compatibility wrapper that implements ``py.path.local`` + for :class:`TempPathFactory`. + + .. note:: + These days, it is preferred to use ``tmp_path_factory``. + + :ref:`About the tmpdir and tmpdir_factory fixtures`. + + """ + + _tmppath_factory: TempPathFactory + + def __init__( + self, tmppath_factory: TempPathFactory, *, _ispytest: bool = False + ) -> None: + check_ispytest(_ispytest) + self._tmppath_factory = tmppath_factory + + def mktemp(self, basename: str, numbered: bool = True) -> LEGACY_PATH: + """Same as :meth:`TempPathFactory.mktemp`, but returns a ``py.path.local`` object.""" + return legacy_path(self._tmppath_factory.mktemp(basename, numbered).resolve()) + + def getbasetemp(self) -> LEGACY_PATH: + """Same as :meth:`TempPathFactory.getbasetemp`, but returns a ``py.path.local`` object.""" + return legacy_path(self._tmppath_factory.getbasetemp().resolve()) + + +class LegacyTmpdirPlugin: + @staticmethod + @fixture(scope="session") + def tmpdir_factory(request: FixtureRequest) -> TempdirFactory: + """Return a :class:`pytest.TempdirFactory` instance for the test session.""" + # Set dynamically by pytest_configure(). + return request.config._tmpdirhandler # type: ignore + + @staticmethod + @fixture + def tmpdir(tmp_path: Path) -> LEGACY_PATH: + """Return a temporary directory (as `legacy_path`_ object) + which is unique to each test function invocation. + The temporary directory is created as a subdirectory + of the base temporary directory, with configurable retention, + as discussed in :ref:`temporary directory location and retention`. + + .. note:: + These days, it is preferred to use ``tmp_path``. + + :ref:`About the tmpdir and tmpdir_factory fixtures`. + + .. _legacy_path: https://py.readthedocs.io/en/latest/path.html + """ + return legacy_path(tmp_path) + + +def Cache_makedir(self: Cache, name: str) -> LEGACY_PATH: + """Return a directory path object with the given name. + + Same as :func:`mkdir`, but returns a legacy py path instance. + """ + return legacy_path(self.mkdir(name)) + + +def FixtureRequest_fspath(self: FixtureRequest) -> LEGACY_PATH: + """(deprecated) The file system path of the test module which collected this test.""" + return legacy_path(self.path) + + +def TerminalReporter_startdir(self: TerminalReporter) -> LEGACY_PATH: + """The directory from which pytest was invoked. + + Prefer to use ``startpath`` which is a :class:`pathlib.Path`. + + :type: LEGACY_PATH + """ + return legacy_path(self.startpath) + + +def Config_invocation_dir(self: Config) -> LEGACY_PATH: + """The directory from which pytest was invoked. + + Prefer to use :attr:`invocation_params.dir `, + which is a :class:`pathlib.Path`. + + :type: LEGACY_PATH + """ + return legacy_path(str(self.invocation_params.dir)) + + +def Config_rootdir(self: Config) -> LEGACY_PATH: + """The path to the :ref:`rootdir `. + + Prefer to use :attr:`rootpath`, which is a :class:`pathlib.Path`. + + :type: LEGACY_PATH + """ + return legacy_path(str(self.rootpath)) + + +def Config_inifile(self: Config) -> LEGACY_PATH | None: + """The path to the :ref:`configfile `. + + Prefer to use :attr:`inipath`, which is a :class:`pathlib.Path`. + + :type: Optional[LEGACY_PATH] + """ + return legacy_path(str(self.inipath)) if self.inipath else None + + +def Session_startdir(self: Session) -> LEGACY_PATH: + """The path from which pytest was invoked. + + Prefer to use ``startpath`` which is a :class:`pathlib.Path`. + + :type: LEGACY_PATH + """ + return legacy_path(self.startpath) + + +def Config__getini_unknown_type(self, name: str, type: str, value: str | list[str]): + if type == "pathlist": + # TODO: This assert is probably not valid in all cases. + assert self.inipath is not None + dp = self.inipath.parent + input_values = shlex.split(value) if isinstance(value, str) else value + return [legacy_path(str(dp / x)) for x in input_values] + else: + raise ValueError(f"unknown configuration type: {type}", value) + + +def Node_fspath(self: Node) -> LEGACY_PATH: + """(deprecated) returns a legacy_path copy of self.path""" + return legacy_path(self.path) + + +def Node_fspath_set(self: Node, value: LEGACY_PATH) -> None: + self.path = Path(value) + + +@hookimpl(tryfirst=True) +def pytest_load_initial_conftests(early_config: Config) -> None: + """Monkeypatch legacy path attributes in several classes, as early as possible.""" + mp = MonkeyPatch() + early_config.add_cleanup(mp.undo) + + # Add Cache.makedir(). + mp.setattr(Cache, "makedir", Cache_makedir, raising=False) + + # Add FixtureRequest.fspath property. + mp.setattr(FixtureRequest, "fspath", property(FixtureRequest_fspath), raising=False) + + # Add TerminalReporter.startdir property. + mp.setattr( + TerminalReporter, "startdir", property(TerminalReporter_startdir), raising=False + ) + + # Add Config.{invocation_dir,rootdir,inifile} properties. + mp.setattr(Config, "invocation_dir", property(Config_invocation_dir), raising=False) + mp.setattr(Config, "rootdir", property(Config_rootdir), raising=False) + mp.setattr(Config, "inifile", property(Config_inifile), raising=False) + + # Add Session.startdir property. + mp.setattr(Session, "startdir", property(Session_startdir), raising=False) + + # Add pathlist configuration type. + mp.setattr(Config, "_getini_unknown_type", Config__getini_unknown_type) + + # Add Node.fspath property. + mp.setattr(Node, "fspath", property(Node_fspath, Node_fspath_set), raising=False) + + +@hookimpl +def pytest_configure(config: Config) -> None: + """Installs the LegacyTmpdirPlugin if the ``tmpdir`` plugin is also installed.""" + if config.pluginmanager.has_plugin("tmpdir"): + mp = MonkeyPatch() + config.add_cleanup(mp.undo) + # Create TmpdirFactory and attach it to the config object. + # + # This is to comply with existing plugins which expect the handler to be + # available at pytest_configure time, but ideally should be moved entirely + # to the tmpdir_factory session fixture. + try: + tmp_path_factory = config._tmp_path_factory # type: ignore[attr-defined] + except AttributeError: + # tmpdir plugin is blocked. + pass + else: + _tmpdirhandler = TempdirFactory(tmp_path_factory, _ispytest=True) + mp.setattr(config, "_tmpdirhandler", _tmpdirhandler, raising=False) + + config.pluginmanager.register(LegacyTmpdirPlugin, "legacypath-tmpdir") + + +@hookimpl +def pytest_plugin_registered(plugin: object, manager: PytestPluginManager) -> None: + # pytester is not loaded by default and is commonly loaded from a conftest, + # so checking for it in `pytest_configure` is not enough. + is_pytester = plugin is manager.get_plugin("pytester") + if is_pytester and not manager.is_registered(LegacyTestdirPlugin): + manager.register(LegacyTestdirPlugin, "legacypath-pytester") diff --git a/.venv/lib/python3.11/site-packages/_pytest/logging.py b/.venv/lib/python3.11/site-packages/_pytest/logging.py new file mode 100644 index 0000000000000000000000000000000000000000..08c826ff6d43a7e34be0adfd28f7f542ec3c21f2 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/logging.py @@ -0,0 +1,955 @@ +# mypy: allow-untyped-defs +"""Access and control log capturing.""" + +from __future__ import annotations + +from contextlib import contextmanager +from contextlib import nullcontext +from datetime import datetime +from datetime import timedelta +from datetime import timezone +import io +from io import StringIO +import logging +from logging import LogRecord +import os +from pathlib import Path +import re +from types import TracebackType +from typing import AbstractSet +from typing import Dict +from typing import final +from typing import Generator +from typing import Generic +from typing import List +from typing import Literal +from typing import Mapping +from typing import TYPE_CHECKING +from typing import TypeVar + +from _pytest import nodes +from _pytest._io import TerminalWriter +from _pytest.capture import CaptureManager +from _pytest.config import _strtobool +from _pytest.config import Config +from _pytest.config import create_terminal_writer +from _pytest.config import hookimpl +from _pytest.config import UsageError +from _pytest.config.argparsing import Parser +from _pytest.deprecated import check_ispytest +from _pytest.fixtures import fixture +from _pytest.fixtures import FixtureRequest +from _pytest.main import Session +from _pytest.stash import StashKey +from _pytest.terminal import TerminalReporter + + +if TYPE_CHECKING: + logging_StreamHandler = logging.StreamHandler[StringIO] +else: + logging_StreamHandler = logging.StreamHandler + +DEFAULT_LOG_FORMAT = "%(levelname)-8s %(name)s:%(filename)s:%(lineno)d %(message)s" +DEFAULT_LOG_DATE_FORMAT = "%H:%M:%S" +_ANSI_ESCAPE_SEQ = re.compile(r"\x1b\[[\d;]+m") +caplog_handler_key = StashKey["LogCaptureHandler"]() +caplog_records_key = StashKey[Dict[str, List[logging.LogRecord]]]() + + +def _remove_ansi_escape_sequences(text: str) -> str: + return _ANSI_ESCAPE_SEQ.sub("", text) + + +class DatetimeFormatter(logging.Formatter): + """A logging formatter which formats record with + :func:`datetime.datetime.strftime` formatter instead of + :func:`time.strftime` in case of microseconds in format string. + """ + + def formatTime(self, record: LogRecord, datefmt: str | None = None) -> str: + if datefmt and "%f" in datefmt: + ct = self.converter(record.created) + tz = timezone(timedelta(seconds=ct.tm_gmtoff), ct.tm_zone) + # Construct `datetime.datetime` object from `struct_time` + # and msecs information from `record` + # Using int() instead of round() to avoid it exceeding 1_000_000 and causing a ValueError (#11861). + dt = datetime(*ct[0:6], microsecond=int(record.msecs * 1000), tzinfo=tz) + return dt.strftime(datefmt) + # Use `logging.Formatter` for non-microsecond formats + return super().formatTime(record, datefmt) + + +class ColoredLevelFormatter(DatetimeFormatter): + """A logging formatter which colorizes the %(levelname)..s part of the + log format passed to __init__.""" + + LOGLEVEL_COLOROPTS: Mapping[int, AbstractSet[str]] = { + logging.CRITICAL: {"red"}, + logging.ERROR: {"red", "bold"}, + logging.WARNING: {"yellow"}, + logging.WARN: {"yellow"}, + logging.INFO: {"green"}, + logging.DEBUG: {"purple"}, + logging.NOTSET: set(), + } + LEVELNAME_FMT_REGEX = re.compile(r"%\(levelname\)([+-.]?\d*(?:\.\d+)?s)") + + def __init__(self, terminalwriter: TerminalWriter, *args, **kwargs) -> None: + super().__init__(*args, **kwargs) + self._terminalwriter = terminalwriter + self._original_fmt = self._style._fmt + self._level_to_fmt_mapping: dict[int, str] = {} + + for level, color_opts in self.LOGLEVEL_COLOROPTS.items(): + self.add_color_level(level, *color_opts) + + def add_color_level(self, level: int, *color_opts: str) -> None: + """Add or update color opts for a log level. + + :param level: + Log level to apply a style to, e.g. ``logging.INFO``. + :param color_opts: + ANSI escape sequence color options. Capitalized colors indicates + background color, i.e. ``'green', 'Yellow', 'bold'`` will give bold + green text on yellow background. + + .. warning:: + This is an experimental API. + """ + assert self._fmt is not None + levelname_fmt_match = self.LEVELNAME_FMT_REGEX.search(self._fmt) + if not levelname_fmt_match: + return + levelname_fmt = levelname_fmt_match.group() + + formatted_levelname = levelname_fmt % {"levelname": logging.getLevelName(level)} + + # add ANSI escape sequences around the formatted levelname + color_kwargs = {name: True for name in color_opts} + colorized_formatted_levelname = self._terminalwriter.markup( + formatted_levelname, **color_kwargs + ) + self._level_to_fmt_mapping[level] = self.LEVELNAME_FMT_REGEX.sub( + colorized_formatted_levelname, self._fmt + ) + + def format(self, record: logging.LogRecord) -> str: + fmt = self._level_to_fmt_mapping.get(record.levelno, self._original_fmt) + self._style._fmt = fmt + return super().format(record) + + +class PercentStyleMultiline(logging.PercentStyle): + """A logging style with special support for multiline messages. + + If the message of a record consists of multiple lines, this style + formats the message as if each line were logged separately. + """ + + def __init__(self, fmt: str, auto_indent: int | str | bool | None) -> None: + super().__init__(fmt) + self._auto_indent = self._get_auto_indent(auto_indent) + + @staticmethod + def _get_auto_indent(auto_indent_option: int | str | bool | None) -> int: + """Determine the current auto indentation setting. + + Specify auto indent behavior (on/off/fixed) by passing in + extra={"auto_indent": [value]} to the call to logging.log() or + using a --log-auto-indent [value] command line or the + log_auto_indent [value] config option. + + Default behavior is auto-indent off. + + Using the string "True" or "on" or the boolean True as the value + turns auto indent on, using the string "False" or "off" or the + boolean False or the int 0 turns it off, and specifying a + positive integer fixes the indentation position to the value + specified. + + Any other values for the option are invalid, and will silently be + converted to the default. + + :param None|bool|int|str auto_indent_option: + User specified option for indentation from command line, config + or extra kwarg. Accepts int, bool or str. str option accepts the + same range of values as boolean config options, as well as + positive integers represented in str form. + + :returns: + Indentation value, which can be + -1 (automatically determine indentation) or + 0 (auto-indent turned off) or + >0 (explicitly set indentation position). + """ + if auto_indent_option is None: + return 0 + elif isinstance(auto_indent_option, bool): + if auto_indent_option: + return -1 + else: + return 0 + elif isinstance(auto_indent_option, int): + return int(auto_indent_option) + elif isinstance(auto_indent_option, str): + try: + return int(auto_indent_option) + except ValueError: + pass + try: + if _strtobool(auto_indent_option): + return -1 + except ValueError: + return 0 + + return 0 + + def format(self, record: logging.LogRecord) -> str: + if "\n" in record.message: + if hasattr(record, "auto_indent"): + # Passed in from the "extra={}" kwarg on the call to logging.log(). + auto_indent = self._get_auto_indent(record.auto_indent) + else: + auto_indent = self._auto_indent + + if auto_indent: + lines = record.message.splitlines() + formatted = self._fmt % {**record.__dict__, "message": lines[0]} + + if auto_indent < 0: + indentation = _remove_ansi_escape_sequences(formatted).find( + lines[0] + ) + else: + # Optimizes logging by allowing a fixed indentation. + indentation = auto_indent + lines[0] = formatted + return ("\n" + " " * indentation).join(lines) + return self._fmt % record.__dict__ + + +def get_option_ini(config: Config, *names: str): + for name in names: + ret = config.getoption(name) # 'default' arg won't work as expected + if ret is None: + ret = config.getini(name) + if ret: + return ret + + +def pytest_addoption(parser: Parser) -> None: + """Add options to control log capturing.""" + group = parser.getgroup("logging") + + def add_option_ini(option, dest, default=None, type=None, **kwargs): + parser.addini( + dest, default=default, type=type, help="Default value for " + option + ) + group.addoption(option, dest=dest, **kwargs) + + add_option_ini( + "--log-level", + dest="log_level", + default=None, + metavar="LEVEL", + help=( + "Level of messages to catch/display." + " Not set by default, so it depends on the root/parent log handler's" + ' effective level, where it is "WARNING" by default.' + ), + ) + add_option_ini( + "--log-format", + dest="log_format", + default=DEFAULT_LOG_FORMAT, + help="Log format used by the logging module", + ) + add_option_ini( + "--log-date-format", + dest="log_date_format", + default=DEFAULT_LOG_DATE_FORMAT, + help="Log date format used by the logging module", + ) + parser.addini( + "log_cli", + default=False, + type="bool", + help='Enable log display during test run (also known as "live logging")', + ) + add_option_ini( + "--log-cli-level", dest="log_cli_level", default=None, help="CLI logging level" + ) + add_option_ini( + "--log-cli-format", + dest="log_cli_format", + default=None, + help="Log format used by the logging module", + ) + add_option_ini( + "--log-cli-date-format", + dest="log_cli_date_format", + default=None, + help="Log date format used by the logging module", + ) + add_option_ini( + "--log-file", + dest="log_file", + default=None, + help="Path to a file when logging will be written to", + ) + add_option_ini( + "--log-file-mode", + dest="log_file_mode", + default="w", + choices=["w", "a"], + help="Log file open mode", + ) + add_option_ini( + "--log-file-level", + dest="log_file_level", + default=None, + help="Log file logging level", + ) + add_option_ini( + "--log-file-format", + dest="log_file_format", + default=None, + help="Log format used by the logging module", + ) + add_option_ini( + "--log-file-date-format", + dest="log_file_date_format", + default=None, + help="Log date format used by the logging module", + ) + add_option_ini( + "--log-auto-indent", + dest="log_auto_indent", + default=None, + help="Auto-indent multiline messages passed to the logging module. Accepts true|on, false|off or an integer.", + ) + group.addoption( + "--log-disable", + action="append", + default=[], + dest="logger_disable", + help="Disable a logger by name. Can be passed multiple times.", + ) + + +_HandlerType = TypeVar("_HandlerType", bound=logging.Handler) + + +# Not using @contextmanager for performance reasons. +class catching_logs(Generic[_HandlerType]): + """Context manager that prepares the whole logging machinery properly.""" + + __slots__ = ("handler", "level", "orig_level") + + def __init__(self, handler: _HandlerType, level: int | None = None) -> None: + self.handler = handler + self.level = level + + def __enter__(self) -> _HandlerType: + root_logger = logging.getLogger() + if self.level is not None: + self.handler.setLevel(self.level) + root_logger.addHandler(self.handler) + if self.level is not None: + self.orig_level = root_logger.level + root_logger.setLevel(min(self.orig_level, self.level)) + return self.handler + + def __exit__( + self, + exc_type: type[BaseException] | None, + exc_val: BaseException | None, + exc_tb: TracebackType | None, + ) -> None: + root_logger = logging.getLogger() + if self.level is not None: + root_logger.setLevel(self.orig_level) + root_logger.removeHandler(self.handler) + + +class LogCaptureHandler(logging_StreamHandler): + """A logging handler that stores log records and the log text.""" + + def __init__(self) -> None: + """Create a new log handler.""" + super().__init__(StringIO()) + self.records: list[logging.LogRecord] = [] + + def emit(self, record: logging.LogRecord) -> None: + """Keep the log records in a list in addition to the log text.""" + self.records.append(record) + super().emit(record) + + def reset(self) -> None: + self.records = [] + self.stream = StringIO() + + def clear(self) -> None: + self.records.clear() + self.stream = StringIO() + + def handleError(self, record: logging.LogRecord) -> None: + if logging.raiseExceptions: + # Fail the test if the log message is bad (emit failed). + # The default behavior of logging is to print "Logging error" + # to stderr with the call stack and some extra details. + # pytest wants to make such mistakes visible during testing. + raise # noqa: PLE0704 + + +@final +class LogCaptureFixture: + """Provides access and control of log capturing.""" + + def __init__(self, item: nodes.Node, *, _ispytest: bool = False) -> None: + check_ispytest(_ispytest) + self._item = item + self._initial_handler_level: int | None = None + # Dict of log name -> log level. + self._initial_logger_levels: dict[str | None, int] = {} + self._initial_disabled_logging_level: int | None = None + + def _finalize(self) -> None: + """Finalize the fixture. + + This restores the log levels and the disabled logging levels changed by :meth:`set_level`. + """ + # Restore log levels. + if self._initial_handler_level is not None: + self.handler.setLevel(self._initial_handler_level) + for logger_name, level in self._initial_logger_levels.items(): + logger = logging.getLogger(logger_name) + logger.setLevel(level) + # Disable logging at the original disabled logging level. + if self._initial_disabled_logging_level is not None: + logging.disable(self._initial_disabled_logging_level) + self._initial_disabled_logging_level = None + + @property + def handler(self) -> LogCaptureHandler: + """Get the logging handler used by the fixture.""" + return self._item.stash[caplog_handler_key] + + def get_records( + self, when: Literal["setup", "call", "teardown"] + ) -> list[logging.LogRecord]: + """Get the logging records for one of the possible test phases. + + :param when: + Which test phase to obtain the records from. + Valid values are: "setup", "call" and "teardown". + + :returns: The list of captured records at the given stage. + + .. versionadded:: 3.4 + """ + return self._item.stash[caplog_records_key].get(when, []) + + @property + def text(self) -> str: + """The formatted log text.""" + return _remove_ansi_escape_sequences(self.handler.stream.getvalue()) + + @property + def records(self) -> list[logging.LogRecord]: + """The list of log records.""" + return self.handler.records + + @property + def record_tuples(self) -> list[tuple[str, int, str]]: + """A list of a stripped down version of log records intended + for use in assertion comparison. + + The format of the tuple is: + + (logger_name, log_level, message) + """ + return [(r.name, r.levelno, r.getMessage()) for r in self.records] + + @property + def messages(self) -> list[str]: + """A list of format-interpolated log messages. + + Unlike 'records', which contains the format string and parameters for + interpolation, log messages in this list are all interpolated. + + Unlike 'text', which contains the output from the handler, log + messages in this list are unadorned with levels, timestamps, etc, + making exact comparisons more reliable. + + Note that traceback or stack info (from :func:`logging.exception` or + the `exc_info` or `stack_info` arguments to the logging functions) is + not included, as this is added by the formatter in the handler. + + .. versionadded:: 3.7 + """ + return [r.getMessage() for r in self.records] + + def clear(self) -> None: + """Reset the list of log records and the captured log text.""" + self.handler.clear() + + def _force_enable_logging( + self, level: int | str, logger_obj: logging.Logger + ) -> int: + """Enable the desired logging level if the global level was disabled via ``logging.disabled``. + + Only enables logging levels greater than or equal to the requested ``level``. + + Does nothing if the desired ``level`` wasn't disabled. + + :param level: + The logger level caplog should capture. + All logging is enabled if a non-standard logging level string is supplied. + Valid level strings are in :data:`logging._nameToLevel`. + :param logger_obj: The logger object to check. + + :return: The original disabled logging level. + """ + original_disable_level: int = logger_obj.manager.disable + + if isinstance(level, str): + # Try to translate the level string to an int for `logging.disable()` + level = logging.getLevelName(level) + + if not isinstance(level, int): + # The level provided was not valid, so just un-disable all logging. + logging.disable(logging.NOTSET) + elif not logger_obj.isEnabledFor(level): + # Each level is `10` away from other levels. + # https://docs.python.org/3/library/logging.html#logging-levels + disable_level = max(level - 10, logging.NOTSET) + logging.disable(disable_level) + + return original_disable_level + + def set_level(self, level: int | str, logger: str | None = None) -> None: + """Set the threshold level of a logger for the duration of a test. + + Logging messages which are less severe than this level will not be captured. + + .. versionchanged:: 3.4 + The levels of the loggers changed by this function will be + restored to their initial values at the end of the test. + + Will enable the requested logging level if it was disabled via :func:`logging.disable`. + + :param level: The level. + :param logger: The logger to update. If not given, the root logger. + """ + logger_obj = logging.getLogger(logger) + # Save the original log-level to restore it during teardown. + self._initial_logger_levels.setdefault(logger, logger_obj.level) + logger_obj.setLevel(level) + if self._initial_handler_level is None: + self._initial_handler_level = self.handler.level + self.handler.setLevel(level) + initial_disabled_logging_level = self._force_enable_logging(level, logger_obj) + if self._initial_disabled_logging_level is None: + self._initial_disabled_logging_level = initial_disabled_logging_level + + @contextmanager + def at_level(self, level: int | str, logger: str | None = None) -> Generator[None]: + """Context manager that sets the level for capturing of logs. After + the end of the 'with' statement the level is restored to its original + value. + + Will enable the requested logging level if it was disabled via :func:`logging.disable`. + + :param level: The level. + :param logger: The logger to update. If not given, the root logger. + """ + logger_obj = logging.getLogger(logger) + orig_level = logger_obj.level + logger_obj.setLevel(level) + handler_orig_level = self.handler.level + self.handler.setLevel(level) + original_disable_level = self._force_enable_logging(level, logger_obj) + try: + yield + finally: + logger_obj.setLevel(orig_level) + self.handler.setLevel(handler_orig_level) + logging.disable(original_disable_level) + + @contextmanager + def filtering(self, filter_: logging.Filter) -> Generator[None]: + """Context manager that temporarily adds the given filter to the caplog's + :meth:`handler` for the 'with' statement block, and removes that filter at the + end of the block. + + :param filter_: A custom :class:`logging.Filter` object. + + .. versionadded:: 7.5 + """ + self.handler.addFilter(filter_) + try: + yield + finally: + self.handler.removeFilter(filter_) + + +@fixture +def caplog(request: FixtureRequest) -> Generator[LogCaptureFixture]: + """Access and control log capturing. + + Captured logs are available through the following properties/methods:: + + * caplog.messages -> list of format-interpolated log messages + * caplog.text -> string containing formatted log output + * caplog.records -> list of logging.LogRecord instances + * caplog.record_tuples -> list of (logger_name, level, message) tuples + * caplog.clear() -> clear captured records and formatted log output string + """ + result = LogCaptureFixture(request.node, _ispytest=True) + yield result + result._finalize() + + +def get_log_level_for_setting(config: Config, *setting_names: str) -> int | None: + for setting_name in setting_names: + log_level = config.getoption(setting_name) + if log_level is None: + log_level = config.getini(setting_name) + if log_level: + break + else: + return None + + if isinstance(log_level, str): + log_level = log_level.upper() + try: + return int(getattr(logging, log_level, log_level)) + except ValueError as e: + # Python logging does not recognise this as a logging level + raise UsageError( + f"'{log_level}' is not recognized as a logging level name for " + f"'{setting_name}'. Please consider passing the " + "logging level num instead." + ) from e + + +# run after terminalreporter/capturemanager are configured +@hookimpl(trylast=True) +def pytest_configure(config: Config) -> None: + config.pluginmanager.register(LoggingPlugin(config), "logging-plugin") + + +class LoggingPlugin: + """Attaches to the logging module and captures log messages for each test.""" + + def __init__(self, config: Config) -> None: + """Create a new plugin to capture log messages. + + The formatter can be safely shared across all handlers so + create a single one for the entire test session here. + """ + self._config = config + + # Report logging. + self.formatter = self._create_formatter( + get_option_ini(config, "log_format"), + get_option_ini(config, "log_date_format"), + get_option_ini(config, "log_auto_indent"), + ) + self.log_level = get_log_level_for_setting(config, "log_level") + self.caplog_handler = LogCaptureHandler() + self.caplog_handler.setFormatter(self.formatter) + self.report_handler = LogCaptureHandler() + self.report_handler.setFormatter(self.formatter) + + # File logging. + self.log_file_level = get_log_level_for_setting( + config, "log_file_level", "log_level" + ) + log_file = get_option_ini(config, "log_file") or os.devnull + if log_file != os.devnull: + directory = os.path.dirname(os.path.abspath(log_file)) + if not os.path.isdir(directory): + os.makedirs(directory) + + self.log_file_mode = get_option_ini(config, "log_file_mode") or "w" + self.log_file_handler = _FileHandler( + log_file, mode=self.log_file_mode, encoding="UTF-8" + ) + log_file_format = get_option_ini(config, "log_file_format", "log_format") + log_file_date_format = get_option_ini( + config, "log_file_date_format", "log_date_format" + ) + + log_file_formatter = DatetimeFormatter( + log_file_format, datefmt=log_file_date_format + ) + self.log_file_handler.setFormatter(log_file_formatter) + + # CLI/live logging. + self.log_cli_level = get_log_level_for_setting( + config, "log_cli_level", "log_level" + ) + if self._log_cli_enabled(): + terminal_reporter = config.pluginmanager.get_plugin("terminalreporter") + # Guaranteed by `_log_cli_enabled()`. + assert terminal_reporter is not None + capture_manager = config.pluginmanager.get_plugin("capturemanager") + # if capturemanager plugin is disabled, live logging still works. + self.log_cli_handler: ( + _LiveLoggingStreamHandler | _LiveLoggingNullHandler + ) = _LiveLoggingStreamHandler(terminal_reporter, capture_manager) + else: + self.log_cli_handler = _LiveLoggingNullHandler() + log_cli_formatter = self._create_formatter( + get_option_ini(config, "log_cli_format", "log_format"), + get_option_ini(config, "log_cli_date_format", "log_date_format"), + get_option_ini(config, "log_auto_indent"), + ) + self.log_cli_handler.setFormatter(log_cli_formatter) + self._disable_loggers(loggers_to_disable=config.option.logger_disable) + + def _disable_loggers(self, loggers_to_disable: list[str]) -> None: + if not loggers_to_disable: + return + + for name in loggers_to_disable: + logger = logging.getLogger(name) + logger.disabled = True + + def _create_formatter(self, log_format, log_date_format, auto_indent): + # Color option doesn't exist if terminal plugin is disabled. + color = getattr(self._config.option, "color", "no") + if color != "no" and ColoredLevelFormatter.LEVELNAME_FMT_REGEX.search( + log_format + ): + formatter: logging.Formatter = ColoredLevelFormatter( + create_terminal_writer(self._config), log_format, log_date_format + ) + else: + formatter = DatetimeFormatter(log_format, log_date_format) + + formatter._style = PercentStyleMultiline( + formatter._style._fmt, auto_indent=auto_indent + ) + + return formatter + + def set_log_path(self, fname: str) -> None: + """Set the filename parameter for Logging.FileHandler(). + + Creates parent directory if it does not exist. + + .. warning:: + This is an experimental API. + """ + fpath = Path(fname) + + if not fpath.is_absolute(): + fpath = self._config.rootpath / fpath + + if not fpath.parent.exists(): + fpath.parent.mkdir(exist_ok=True, parents=True) + + # https://github.com/python/mypy/issues/11193 + stream: io.TextIOWrapper = fpath.open(mode=self.log_file_mode, encoding="UTF-8") # type: ignore[assignment] + old_stream = self.log_file_handler.setStream(stream) + if old_stream: + old_stream.close() + + def _log_cli_enabled(self) -> bool: + """Return whether live logging is enabled.""" + enabled = self._config.getoption( + "--log-cli-level" + ) is not None or self._config.getini("log_cli") + if not enabled: + return False + + terminal_reporter = self._config.pluginmanager.get_plugin("terminalreporter") + if terminal_reporter is None: + # terminal reporter is disabled e.g. by pytest-xdist. + return False + + return True + + @hookimpl(wrapper=True, tryfirst=True) + def pytest_sessionstart(self) -> Generator[None]: + self.log_cli_handler.set_when("sessionstart") + + with catching_logs(self.log_cli_handler, level=self.log_cli_level): + with catching_logs(self.log_file_handler, level=self.log_file_level): + return (yield) + + @hookimpl(wrapper=True, tryfirst=True) + def pytest_collection(self) -> Generator[None]: + self.log_cli_handler.set_when("collection") + + with catching_logs(self.log_cli_handler, level=self.log_cli_level): + with catching_logs(self.log_file_handler, level=self.log_file_level): + return (yield) + + @hookimpl(wrapper=True) + def pytest_runtestloop(self, session: Session) -> Generator[None, object, object]: + if session.config.option.collectonly: + return (yield) + + if self._log_cli_enabled() and self._config.get_verbosity() < 1: + # The verbose flag is needed to avoid messy test progress output. + self._config.option.verbose = 1 + + with catching_logs(self.log_cli_handler, level=self.log_cli_level): + with catching_logs(self.log_file_handler, level=self.log_file_level): + return (yield) # Run all the tests. + + @hookimpl + def pytest_runtest_logstart(self) -> None: + self.log_cli_handler.reset() + self.log_cli_handler.set_when("start") + + @hookimpl + def pytest_runtest_logreport(self) -> None: + self.log_cli_handler.set_when("logreport") + + def _runtest_for(self, item: nodes.Item, when: str) -> Generator[None]: + """Implement the internals of the pytest_runtest_xxx() hooks.""" + with catching_logs( + self.caplog_handler, + level=self.log_level, + ) as caplog_handler, catching_logs( + self.report_handler, + level=self.log_level, + ) as report_handler: + caplog_handler.reset() + report_handler.reset() + item.stash[caplog_records_key][when] = caplog_handler.records + item.stash[caplog_handler_key] = caplog_handler + + try: + yield + finally: + log = report_handler.stream.getvalue().strip() + item.add_report_section(when, "log", log) + + @hookimpl(wrapper=True) + def pytest_runtest_setup(self, item: nodes.Item) -> Generator[None]: + self.log_cli_handler.set_when("setup") + + empty: dict[str, list[logging.LogRecord]] = {} + item.stash[caplog_records_key] = empty + yield from self._runtest_for(item, "setup") + + @hookimpl(wrapper=True) + def pytest_runtest_call(self, item: nodes.Item) -> Generator[None]: + self.log_cli_handler.set_when("call") + + yield from self._runtest_for(item, "call") + + @hookimpl(wrapper=True) + def pytest_runtest_teardown(self, item: nodes.Item) -> Generator[None]: + self.log_cli_handler.set_when("teardown") + + try: + yield from self._runtest_for(item, "teardown") + finally: + del item.stash[caplog_records_key] + del item.stash[caplog_handler_key] + + @hookimpl + def pytest_runtest_logfinish(self) -> None: + self.log_cli_handler.set_when("finish") + + @hookimpl(wrapper=True, tryfirst=True) + def pytest_sessionfinish(self) -> Generator[None]: + self.log_cli_handler.set_when("sessionfinish") + + with catching_logs(self.log_cli_handler, level=self.log_cli_level): + with catching_logs(self.log_file_handler, level=self.log_file_level): + return (yield) + + @hookimpl + def pytest_unconfigure(self) -> None: + # Close the FileHandler explicitly. + # (logging.shutdown might have lost the weakref?!) + self.log_file_handler.close() + + +class _FileHandler(logging.FileHandler): + """A logging FileHandler with pytest tweaks.""" + + def handleError(self, record: logging.LogRecord) -> None: + # Handled by LogCaptureHandler. + pass + + +class _LiveLoggingStreamHandler(logging_StreamHandler): + """A logging StreamHandler used by the live logging feature: it will + write a newline before the first log message in each test. + + During live logging we must also explicitly disable stdout/stderr + capturing otherwise it will get captured and won't appear in the + terminal. + """ + + # Officially stream needs to be a IO[str], but TerminalReporter + # isn't. So force it. + stream: TerminalReporter = None # type: ignore + + def __init__( + self, + terminal_reporter: TerminalReporter, + capture_manager: CaptureManager | None, + ) -> None: + super().__init__(stream=terminal_reporter) # type: ignore[arg-type] + self.capture_manager = capture_manager + self.reset() + self.set_when(None) + self._test_outcome_written = False + + def reset(self) -> None: + """Reset the handler; should be called before the start of each test.""" + self._first_record_emitted = False + + def set_when(self, when: str | None) -> None: + """Prepare for the given test phase (setup/call/teardown).""" + self._when = when + self._section_name_shown = False + if when == "start": + self._test_outcome_written = False + + def emit(self, record: logging.LogRecord) -> None: + ctx_manager = ( + self.capture_manager.global_and_fixture_disabled() + if self.capture_manager + else nullcontext() + ) + with ctx_manager: + if not self._first_record_emitted: + self.stream.write("\n") + self._first_record_emitted = True + elif self._when in ("teardown", "finish"): + if not self._test_outcome_written: + self._test_outcome_written = True + self.stream.write("\n") + if not self._section_name_shown and self._when: + self.stream.section("live log " + self._when, sep="-", bold=True) + self._section_name_shown = True + super().emit(record) + + def handleError(self, record: logging.LogRecord) -> None: + # Handled by LogCaptureHandler. + pass + + +class _LiveLoggingNullHandler(logging.NullHandler): + """A logging handler used when live logging is disabled.""" + + def reset(self) -> None: + pass + + def set_when(self, when: str) -> None: + pass + + def handleError(self, record: logging.LogRecord) -> None: + # Handled by LogCaptureHandler. + pass diff --git a/.venv/lib/python3.11/site-packages/_pytest/nodes.py b/.venv/lib/python3.11/site-packages/_pytest/nodes.py new file mode 100644 index 0000000000000000000000000000000000000000..51bc5174628f9d172c037ed76e9f2a63e67ee92e --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/nodes.py @@ -0,0 +1,766 @@ +# mypy: allow-untyped-defs +from __future__ import annotations + +import abc +from functools import cached_property +from inspect import signature +import os +import pathlib +from pathlib import Path +from typing import Any +from typing import Callable +from typing import cast +from typing import Iterable +from typing import Iterator +from typing import MutableMapping +from typing import NoReturn +from typing import overload +from typing import TYPE_CHECKING +from typing import TypeVar +import warnings + +import pluggy + +import _pytest._code +from _pytest._code import getfslineno +from _pytest._code.code import ExceptionInfo +from _pytest._code.code import TerminalRepr +from _pytest._code.code import Traceback +from _pytest._code.code import TracebackStyle +from _pytest.compat import LEGACY_PATH +from _pytest.config import Config +from _pytest.config import ConftestImportFailure +from _pytest.config.compat import _check_path +from _pytest.deprecated import NODE_CTOR_FSPATH_ARG +from _pytest.mark.structures import Mark +from _pytest.mark.structures import MarkDecorator +from _pytest.mark.structures import NodeKeywords +from _pytest.outcomes import fail +from _pytest.pathlib import absolutepath +from _pytest.pathlib import commonpath +from _pytest.stash import Stash +from _pytest.warning_types import PytestWarning + + +if TYPE_CHECKING: + from typing_extensions import Self + + # Imported here due to circular import. + from _pytest.main import Session + + +SEP = "/" + +tracebackcutdir = Path(_pytest.__file__).parent + + +_T = TypeVar("_T") + + +def _imply_path( + node_type: type[Node], + path: Path | None, + fspath: LEGACY_PATH | None, +) -> Path: + if fspath is not None: + warnings.warn( + NODE_CTOR_FSPATH_ARG.format( + node_type_name=node_type.__name__, + ), + stacklevel=6, + ) + if path is not None: + if fspath is not None: + _check_path(path, fspath) + return path + else: + assert fspath is not None + return Path(fspath) + + +_NodeType = TypeVar("_NodeType", bound="Node") + + +class NodeMeta(abc.ABCMeta): + """Metaclass used by :class:`Node` to enforce that direct construction raises + :class:`Failed`. + + This behaviour supports the indirection introduced with :meth:`Node.from_parent`, + the named constructor to be used instead of direct construction. The design + decision to enforce indirection with :class:`NodeMeta` was made as a + temporary aid for refactoring the collection tree, which was diagnosed to + have :class:`Node` objects whose creational patterns were overly entangled. + Once the refactoring is complete, this metaclass can be removed. + + See https://github.com/pytest-dev/pytest/projects/3 for an overview of the + progress on detangling the :class:`Node` classes. + """ + + def __call__(cls, *k, **kw) -> NoReturn: + msg = ( + "Direct construction of {name} has been deprecated, please use {name}.from_parent.\n" + "See " + "https://docs.pytest.org/en/stable/deprecations.html#node-construction-changed-to-node-from-parent" + " for more details." + ).format(name=f"{cls.__module__}.{cls.__name__}") + fail(msg, pytrace=False) + + def _create(cls: type[_T], *k, **kw) -> _T: + try: + return super().__call__(*k, **kw) # type: ignore[no-any-return,misc] + except TypeError: + sig = signature(getattr(cls, "__init__")) + known_kw = {k: v for k, v in kw.items() if k in sig.parameters} + from .warning_types import PytestDeprecationWarning + + warnings.warn( + PytestDeprecationWarning( + f"{cls} is not using a cooperative constructor and only takes {set(known_kw)}.\n" + "See https://docs.pytest.org/en/stable/deprecations.html" + "#constructors-of-custom-pytest-node-subclasses-should-take-kwargs " + "for more details." + ) + ) + + return super().__call__(*k, **known_kw) # type: ignore[no-any-return,misc] + + +class Node(abc.ABC, metaclass=NodeMeta): + r"""Base class of :class:`Collector` and :class:`Item`, the components of + the test collection tree. + + ``Collector``\'s are the internal nodes of the tree, and ``Item``\'s are the + leaf nodes. + """ + + # Implemented in the legacypath plugin. + #: A ``LEGACY_PATH`` copy of the :attr:`path` attribute. Intended for usage + #: for methods not migrated to ``pathlib.Path`` yet, such as + #: :meth:`Item.reportinfo `. Will be deprecated in + #: a future release, prefer using :attr:`path` instead. + fspath: LEGACY_PATH + + # Use __slots__ to make attribute access faster. + # Note that __dict__ is still available. + __slots__ = ( + "name", + "parent", + "config", + "session", + "path", + "_nodeid", + "_store", + "__dict__", + ) + + def __init__( + self, + name: str, + parent: Node | None = None, + config: Config | None = None, + session: Session | None = None, + fspath: LEGACY_PATH | None = None, + path: Path | None = None, + nodeid: str | None = None, + ) -> None: + #: A unique name within the scope of the parent node. + self.name: str = name + + #: The parent collector node. + self.parent = parent + + if config: + #: The pytest config object. + self.config: Config = config + else: + if not parent: + raise TypeError("config or parent must be provided") + self.config = parent.config + + if session: + #: The pytest session this node is part of. + self.session: Session = session + else: + if not parent: + raise TypeError("session or parent must be provided") + self.session = parent.session + + if path is None and fspath is None: + path = getattr(parent, "path", None) + #: Filesystem path where this node was collected from (can be None). + self.path: pathlib.Path = _imply_path(type(self), path, fspath=fspath) + + # The explicit annotation is to avoid publicly exposing NodeKeywords. + #: Keywords/markers collected from all scopes. + self.keywords: MutableMapping[str, Any] = NodeKeywords(self) + + #: The marker objects belonging to this node. + self.own_markers: list[Mark] = [] + + #: Allow adding of extra keywords to use for matching. + self.extra_keyword_matches: set[str] = set() + + if nodeid is not None: + assert "::()" not in nodeid + self._nodeid = nodeid + else: + if not self.parent: + raise TypeError("nodeid or parent must be provided") + self._nodeid = self.parent.nodeid + "::" + self.name + + #: A place where plugins can store information on the node for their + #: own use. + self.stash: Stash = Stash() + # Deprecated alias. Was never public. Can be removed in a few releases. + self._store = self.stash + + @classmethod + def from_parent(cls, parent: Node, **kw) -> Self: + """Public constructor for Nodes. + + This indirection got introduced in order to enable removing + the fragile logic from the node constructors. + + Subclasses can use ``super().from_parent(...)`` when overriding the + construction. + + :param parent: The parent node of this Node. + """ + if "config" in kw: + raise TypeError("config is not a valid argument for from_parent") + if "session" in kw: + raise TypeError("session is not a valid argument for from_parent") + return cls._create(parent=parent, **kw) + + @property + def ihook(self) -> pluggy.HookRelay: + """fspath-sensitive hook proxy used to call pytest hooks.""" + return self.session.gethookproxy(self.path) + + def __repr__(self) -> str: + return "<{} {}>".format(self.__class__.__name__, getattr(self, "name", None)) + + def warn(self, warning: Warning) -> None: + """Issue a warning for this Node. + + Warnings will be displayed after the test session, unless explicitly suppressed. + + :param Warning warning: + The warning instance to issue. + + :raises ValueError: If ``warning`` instance is not a subclass of Warning. + + Example usage: + + .. code-block:: python + + node.warn(PytestWarning("some message")) + node.warn(UserWarning("some message")) + + .. versionchanged:: 6.2 + Any subclass of :class:`Warning` is now accepted, rather than only + :class:`PytestWarning ` subclasses. + """ + # enforce type checks here to avoid getting a generic type error later otherwise. + if not isinstance(warning, Warning): + raise ValueError( + f"warning must be an instance of Warning or subclass, got {warning!r}" + ) + path, lineno = get_fslocation_from_item(self) + assert lineno is not None + warnings.warn_explicit( + warning, + category=None, + filename=str(path), + lineno=lineno + 1, + ) + + # Methods for ordering nodes. + + @property + def nodeid(self) -> str: + """A ::-separated string denoting its collection tree address.""" + return self._nodeid + + def __hash__(self) -> int: + return hash(self._nodeid) + + def setup(self) -> None: + pass + + def teardown(self) -> None: + pass + + def iter_parents(self) -> Iterator[Node]: + """Iterate over all parent collectors starting from and including self + up to the root of the collection tree. + + .. versionadded:: 8.1 + """ + parent: Node | None = self + while parent is not None: + yield parent + parent = parent.parent + + def listchain(self) -> list[Node]: + """Return a list of all parent collectors starting from the root of the + collection tree down to and including self.""" + chain = [] + item: Node | None = self + while item is not None: + chain.append(item) + item = item.parent + chain.reverse() + return chain + + def add_marker(self, marker: str | MarkDecorator, append: bool = True) -> None: + """Dynamically add a marker object to the node. + + :param marker: + The marker. + :param append: + Whether to append the marker, or prepend it. + """ + from _pytest.mark import MARK_GEN + + if isinstance(marker, MarkDecorator): + marker_ = marker + elif isinstance(marker, str): + marker_ = getattr(MARK_GEN, marker) + else: + raise ValueError("is not a string or pytest.mark.* Marker") + self.keywords[marker_.name] = marker_ + if append: + self.own_markers.append(marker_.mark) + else: + self.own_markers.insert(0, marker_.mark) + + def iter_markers(self, name: str | None = None) -> Iterator[Mark]: + """Iterate over all markers of the node. + + :param name: If given, filter the results by the name attribute. + :returns: An iterator of the markers of the node. + """ + return (x[1] for x in self.iter_markers_with_node(name=name)) + + def iter_markers_with_node( + self, name: str | None = None + ) -> Iterator[tuple[Node, Mark]]: + """Iterate over all markers of the node. + + :param name: If given, filter the results by the name attribute. + :returns: An iterator of (node, mark) tuples. + """ + for node in self.iter_parents(): + for mark in node.own_markers: + if name is None or getattr(mark, "name", None) == name: + yield node, mark + + @overload + def get_closest_marker(self, name: str) -> Mark | None: ... + + @overload + def get_closest_marker(self, name: str, default: Mark) -> Mark: ... + + def get_closest_marker(self, name: str, default: Mark | None = None) -> Mark | None: + """Return the first marker matching the name, from closest (for + example function) to farther level (for example module level). + + :param default: Fallback return value if no marker was found. + :param name: Name to filter by. + """ + return next(self.iter_markers(name=name), default) + + def listextrakeywords(self) -> set[str]: + """Return a set of all extra keywords in self and any parents.""" + extra_keywords: set[str] = set() + for item in self.listchain(): + extra_keywords.update(item.extra_keyword_matches) + return extra_keywords + + def listnames(self) -> list[str]: + return [x.name for x in self.listchain()] + + def addfinalizer(self, fin: Callable[[], object]) -> None: + """Register a function to be called without arguments when this node is + finalized. + + This method can only be called when this node is active + in a setup chain, for example during self.setup(). + """ + self.session._setupstate.addfinalizer(fin, self) + + def getparent(self, cls: type[_NodeType]) -> _NodeType | None: + """Get the closest parent node (including self) which is an instance of + the given class. + + :param cls: The node class to search for. + :returns: The node, if found. + """ + for node in self.iter_parents(): + if isinstance(node, cls): + return node + return None + + def _traceback_filter(self, excinfo: ExceptionInfo[BaseException]) -> Traceback: + return excinfo.traceback + + def _repr_failure_py( + self, + excinfo: ExceptionInfo[BaseException], + style: TracebackStyle | None = None, + ) -> TerminalRepr: + from _pytest.fixtures import FixtureLookupError + + if isinstance(excinfo.value, ConftestImportFailure): + excinfo = ExceptionInfo.from_exception(excinfo.value.cause) + if isinstance(excinfo.value, fail.Exception): + if not excinfo.value.pytrace: + style = "value" + if isinstance(excinfo.value, FixtureLookupError): + return excinfo.value.formatrepr() + + tbfilter: bool | Callable[[ExceptionInfo[BaseException]], Traceback] + if self.config.getoption("fulltrace", False): + style = "long" + tbfilter = False + else: + tbfilter = self._traceback_filter + if style == "auto": + style = "long" + # XXX should excinfo.getrepr record all data and toterminal() process it? + if style is None: + if self.config.getoption("tbstyle", "auto") == "short": + style = "short" + else: + style = "long" + + if self.config.get_verbosity() > 1: + truncate_locals = False + else: + truncate_locals = True + + truncate_args = False if self.config.get_verbosity() > 2 else True + + # excinfo.getrepr() formats paths relative to the CWD if `abspath` is False. + # It is possible for a fixture/test to change the CWD while this code runs, which + # would then result in the user seeing confusing paths in the failure message. + # To fix this, if the CWD changed, always display the full absolute path. + # It will be better to just always display paths relative to invocation_dir, but + # this requires a lot of plumbing (#6428). + try: + abspath = Path(os.getcwd()) != self.config.invocation_params.dir + except OSError: + abspath = True + + return excinfo.getrepr( + funcargs=True, + abspath=abspath, + showlocals=self.config.getoption("showlocals", False), + style=style, + tbfilter=tbfilter, + truncate_locals=truncate_locals, + truncate_args=truncate_args, + ) + + def repr_failure( + self, + excinfo: ExceptionInfo[BaseException], + style: TracebackStyle | None = None, + ) -> str | TerminalRepr: + """Return a representation of a collection or test failure. + + .. seealso:: :ref:`non-python tests` + + :param excinfo: Exception information for the failure. + """ + return self._repr_failure_py(excinfo, style) + + +def get_fslocation_from_item(node: Node) -> tuple[str | Path, int | None]: + """Try to extract the actual location from a node, depending on available attributes: + + * "location": a pair (path, lineno) + * "obj": a Python object that the node wraps. + * "path": just a path + + :rtype: A tuple of (str|Path, int) with filename and 0-based line number. + """ + # See Item.location. + location: tuple[str, int | None, str] | None = getattr(node, "location", None) + if location is not None: + return location[:2] + obj = getattr(node, "obj", None) + if obj is not None: + return getfslineno(obj) + return getattr(node, "path", "unknown location"), -1 + + +class Collector(Node, abc.ABC): + """Base class of all collectors. + + Collector create children through `collect()` and thus iteratively build + the collection tree. + """ + + class CollectError(Exception): + """An error during collection, contains a custom message.""" + + @abc.abstractmethod + def collect(self) -> Iterable[Item | Collector]: + """Collect children (items and collectors) for this collector.""" + raise NotImplementedError("abstract") + + # TODO: This omits the style= parameter which breaks Liskov Substitution. + def repr_failure( # type: ignore[override] + self, excinfo: ExceptionInfo[BaseException] + ) -> str | TerminalRepr: + """Return a representation of a collection failure. + + :param excinfo: Exception information for the failure. + """ + if isinstance(excinfo.value, self.CollectError) and not self.config.getoption( + "fulltrace", False + ): + exc = excinfo.value + return str(exc.args[0]) + + # Respect explicit tbstyle option, but default to "short" + # (_repr_failure_py uses "long" with "fulltrace" option always). + tbstyle = self.config.getoption("tbstyle", "auto") + if tbstyle == "auto": + tbstyle = "short" + + return self._repr_failure_py(excinfo, style=tbstyle) + + def _traceback_filter(self, excinfo: ExceptionInfo[BaseException]) -> Traceback: + if hasattr(self, "path"): + traceback = excinfo.traceback + ntraceback = traceback.cut(path=self.path) + if ntraceback == traceback: + ntraceback = ntraceback.cut(excludepath=tracebackcutdir) + return ntraceback.filter(excinfo) + return excinfo.traceback + + +def _check_initialpaths_for_relpath(session: Session, path: Path) -> str | None: + for initial_path in session._initialpaths: + if commonpath(path, initial_path) == initial_path: + rel = str(path.relative_to(initial_path)) + return "" if rel == "." else rel + return None + + +class FSCollector(Collector, abc.ABC): + """Base class for filesystem collectors.""" + + def __init__( + self, + fspath: LEGACY_PATH | None = None, + path_or_parent: Path | Node | None = None, + path: Path | None = None, + name: str | None = None, + parent: Node | None = None, + config: Config | None = None, + session: Session | None = None, + nodeid: str | None = None, + ) -> None: + if path_or_parent: + if isinstance(path_or_parent, Node): + assert parent is None + parent = cast(FSCollector, path_or_parent) + elif isinstance(path_or_parent, Path): + assert path is None + path = path_or_parent + + path = _imply_path(type(self), path, fspath=fspath) + if name is None: + name = path.name + if parent is not None and parent.path != path: + try: + rel = path.relative_to(parent.path) + except ValueError: + pass + else: + name = str(rel) + name = name.replace(os.sep, SEP) + self.path = path + + if session is None: + assert parent is not None + session = parent.session + + if nodeid is None: + try: + nodeid = str(self.path.relative_to(session.config.rootpath)) + except ValueError: + nodeid = _check_initialpaths_for_relpath(session, path) + + if nodeid and os.sep != SEP: + nodeid = nodeid.replace(os.sep, SEP) + + super().__init__( + name=name, + parent=parent, + config=config, + session=session, + nodeid=nodeid, + path=path, + ) + + @classmethod + def from_parent( + cls, + parent, + *, + fspath: LEGACY_PATH | None = None, + path: Path | None = None, + **kw, + ) -> Self: + """The public constructor.""" + return super().from_parent(parent=parent, fspath=fspath, path=path, **kw) + + +class File(FSCollector, abc.ABC): + """Base class for collecting tests from a file. + + :ref:`non-python tests`. + """ + + +class Directory(FSCollector, abc.ABC): + """Base class for collecting files from a directory. + + A basic directory collector does the following: goes over the files and + sub-directories in the directory and creates collectors for them by calling + the hooks :hook:`pytest_collect_directory` and :hook:`pytest_collect_file`, + after checking that they are not ignored using + :hook:`pytest_ignore_collect`. + + The default directory collectors are :class:`~pytest.Dir` and + :class:`~pytest.Package`. + + .. versionadded:: 8.0 + + :ref:`custom directory collectors`. + """ + + +class Item(Node, abc.ABC): + """Base class of all test invocation items. + + Note that for a single function there might be multiple test invocation items. + """ + + nextitem = None + + def __init__( + self, + name, + parent=None, + config: Config | None = None, + session: Session | None = None, + nodeid: str | None = None, + **kw, + ) -> None: + # The first two arguments are intentionally passed positionally, + # to keep plugins who define a node type which inherits from + # (pytest.Item, pytest.File) working (see issue #8435). + # They can be made kwargs when the deprecation above is done. + super().__init__( + name, + parent, + config=config, + session=session, + nodeid=nodeid, + **kw, + ) + self._report_sections: list[tuple[str, str, str]] = [] + + #: A list of tuples (name, value) that holds user defined properties + #: for this test. + self.user_properties: list[tuple[str, object]] = [] + + self._check_item_and_collector_diamond_inheritance() + + def _check_item_and_collector_diamond_inheritance(self) -> None: + """ + Check if the current type inherits from both File and Collector + at the same time, emitting a warning accordingly (#8447). + """ + cls = type(self) + + # We inject an attribute in the type to avoid issuing this warning + # for the same class more than once, which is not helpful. + # It is a hack, but was deemed acceptable in order to avoid + # flooding the user in the common case. + attr_name = "_pytest_diamond_inheritance_warning_shown" + if getattr(cls, attr_name, False): + return + setattr(cls, attr_name, True) + + problems = ", ".join( + base.__name__ for base in cls.__bases__ if issubclass(base, Collector) + ) + if problems: + warnings.warn( + f"{cls.__name__} is an Item subclass and should not be a collector, " + f"however its bases {problems} are collectors.\n" + "Please split the Collectors and the Item into separate node types.\n" + "Pytest Doc example: https://docs.pytest.org/en/latest/example/nonpython.html\n" + "example pull request on a plugin: https://github.com/asmeurer/pytest-flakes/pull/40/", + PytestWarning, + ) + + @abc.abstractmethod + def runtest(self) -> None: + """Run the test case for this item. + + Must be implemented by subclasses. + + .. seealso:: :ref:`non-python tests` + """ + raise NotImplementedError("runtest must be implemented by Item subclass") + + def add_report_section(self, when: str, key: str, content: str) -> None: + """Add a new report section, similar to what's done internally to add + stdout and stderr captured output:: + + item.add_report_section("call", "stdout", "report section contents") + + :param str when: + One of the possible capture states, ``"setup"``, ``"call"``, ``"teardown"``. + :param str key: + Name of the section, can be customized at will. Pytest uses ``"stdout"`` and + ``"stderr"`` internally. + :param str content: + The full contents as a string. + """ + if content: + self._report_sections.append((when, key, content)) + + def reportinfo(self) -> tuple[os.PathLike[str] | str, int | None, str]: + """Get location information for this item for test reports. + + Returns a tuple with three elements: + + - The path of the test (default ``self.path``) + - The 0-based line number of the test (default ``None``) + - A name of the test to be shown (default ``""``) + + .. seealso:: :ref:`non-python tests` + """ + return self.path, None, "" + + @cached_property + def location(self) -> tuple[str, int | None, str]: + """ + Returns a tuple of ``(relfspath, lineno, testname)`` for this item + where ``relfspath`` is file path relative to ``config.rootpath`` + and lineno is a 0-based line number. + """ + location = self.reportinfo() + path = absolutepath(location[0]) + relfspath = self.session._node_location_to_relpath(path) + assert type(location[2]) is str + return (relfspath, location[1], location[2]) diff --git a/.venv/lib/python3.11/site-packages/_pytest/python.py b/.venv/lib/python3.11/site-packages/_pytest/python.py new file mode 100644 index 0000000000000000000000000000000000000000..3478c34c47d167f706a1f54427e3b6dece62b38f --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/python.py @@ -0,0 +1,1679 @@ +# mypy: allow-untyped-defs +"""Python test discovery, setup and run of test functions.""" + +from __future__ import annotations + +import abc +from collections import Counter +from collections import defaultdict +import dataclasses +import enum +import fnmatch +from functools import partial +import inspect +import itertools +import os +from pathlib import Path +import types +from typing import Any +from typing import Callable +from typing import Dict +from typing import final +from typing import Generator +from typing import Iterable +from typing import Iterator +from typing import Literal +from typing import Mapping +from typing import Pattern +from typing import Sequence +from typing import TYPE_CHECKING +import warnings + +import _pytest +from _pytest import fixtures +from _pytest import nodes +from _pytest._code import filter_traceback +from _pytest._code import getfslineno +from _pytest._code.code import ExceptionInfo +from _pytest._code.code import TerminalRepr +from _pytest._code.code import Traceback +from _pytest._io.saferepr import saferepr +from _pytest.compat import ascii_escaped +from _pytest.compat import get_default_arg_names +from _pytest.compat import get_real_func +from _pytest.compat import getimfunc +from _pytest.compat import is_async_function +from _pytest.compat import is_generator +from _pytest.compat import LEGACY_PATH +from _pytest.compat import NOTSET +from _pytest.compat import safe_getattr +from _pytest.compat import safe_isclass +from _pytest.config import Config +from _pytest.config import hookimpl +from _pytest.config.argparsing import Parser +from _pytest.deprecated import check_ispytest +from _pytest.fixtures import FixtureDef +from _pytest.fixtures import FixtureRequest +from _pytest.fixtures import FuncFixtureInfo +from _pytest.fixtures import get_scope_node +from _pytest.main import Session +from _pytest.mark import MARK_GEN +from _pytest.mark import ParameterSet +from _pytest.mark.structures import get_unpacked_marks +from _pytest.mark.structures import Mark +from _pytest.mark.structures import MarkDecorator +from _pytest.mark.structures import normalize_mark_list +from _pytest.outcomes import fail +from _pytest.outcomes import skip +from _pytest.pathlib import fnmatch_ex +from _pytest.pathlib import import_path +from _pytest.pathlib import ImportPathMismatchError +from _pytest.pathlib import scandir +from _pytest.scope import _ScopeName +from _pytest.scope import Scope +from _pytest.stash import StashKey +from _pytest.warning_types import PytestCollectionWarning +from _pytest.warning_types import PytestReturnNotNoneWarning +from _pytest.warning_types import PytestUnhandledCoroutineWarning + + +if TYPE_CHECKING: + from typing_extensions import Self + + +def pytest_addoption(parser: Parser) -> None: + parser.addini( + "python_files", + type="args", + # NOTE: default is also used in AssertionRewritingHook. + default=["test_*.py", "*_test.py"], + help="Glob-style file patterns for Python test module discovery", + ) + parser.addini( + "python_classes", + type="args", + default=["Test"], + help="Prefixes or glob names for Python test class discovery", + ) + parser.addini( + "python_functions", + type="args", + default=["test"], + help="Prefixes or glob names for Python test function and method discovery", + ) + parser.addini( + "disable_test_id_escaping_and_forfeit_all_rights_to_community_support", + type="bool", + default=False, + help="Disable string escape non-ASCII characters, might cause unwanted " + "side effects(use at your own risk)", + ) + + +def pytest_generate_tests(metafunc: Metafunc) -> None: + for marker in metafunc.definition.iter_markers(name="parametrize"): + metafunc.parametrize(*marker.args, **marker.kwargs, _param_mark=marker) + + +def pytest_configure(config: Config) -> None: + config.addinivalue_line( + "markers", + "parametrize(argnames, argvalues): call a test function multiple " + "times passing in different arguments in turn. argvalues generally " + "needs to be a list of values if argnames specifies only one name " + "or a list of tuples of values if argnames specifies multiple names. " + "Example: @parametrize('arg1', [1,2]) would lead to two calls of the " + "decorated test function, one with arg1=1 and another with arg1=2." + "see https://docs.pytest.org/en/stable/how-to/parametrize.html for more info " + "and examples.", + ) + config.addinivalue_line( + "markers", + "usefixtures(fixturename1, fixturename2, ...): mark tests as needing " + "all of the specified fixtures. see " + "https://docs.pytest.org/en/stable/explanation/fixtures.html#usefixtures ", + ) + + +def async_warn_and_skip(nodeid: str) -> None: + msg = "async def functions are not natively supported and have been skipped.\n" + msg += ( + "You need to install a suitable plugin for your async framework, for example:\n" + ) + msg += " - anyio\n" + msg += " - pytest-asyncio\n" + msg += " - pytest-tornasync\n" + msg += " - pytest-trio\n" + msg += " - pytest-twisted" + warnings.warn(PytestUnhandledCoroutineWarning(msg.format(nodeid))) + skip(reason="async def function and no async plugin installed (see warnings)") + + +@hookimpl(trylast=True) +def pytest_pyfunc_call(pyfuncitem: Function) -> object | None: + testfunction = pyfuncitem.obj + if is_async_function(testfunction): + async_warn_and_skip(pyfuncitem.nodeid) + funcargs = pyfuncitem.funcargs + testargs = {arg: funcargs[arg] for arg in pyfuncitem._fixtureinfo.argnames} + result = testfunction(**testargs) + if hasattr(result, "__await__") or hasattr(result, "__aiter__"): + async_warn_and_skip(pyfuncitem.nodeid) + elif result is not None: + warnings.warn( + PytestReturnNotNoneWarning( + f"Expected None, but {pyfuncitem.nodeid} returned {result!r}, which will be an error in a " + "future version of pytest. Did you mean to use `assert` instead of `return`?" + ) + ) + return True + + +def pytest_collect_directory( + path: Path, parent: nodes.Collector +) -> nodes.Collector | None: + pkginit = path / "__init__.py" + try: + has_pkginit = pkginit.is_file() + except PermissionError: + # See https://github.com/pytest-dev/pytest/issues/12120#issuecomment-2106349096. + return None + if has_pkginit: + return Package.from_parent(parent, path=path) + return None + + +def pytest_collect_file(file_path: Path, parent: nodes.Collector) -> Module | None: + if file_path.suffix == ".py": + if not parent.session.isinitpath(file_path): + if not path_matches_patterns( + file_path, parent.config.getini("python_files") + ): + return None + ihook = parent.session.gethookproxy(file_path) + module: Module = ihook.pytest_pycollect_makemodule( + module_path=file_path, parent=parent + ) + return module + return None + + +def path_matches_patterns(path: Path, patterns: Iterable[str]) -> bool: + """Return whether path matches any of the patterns in the list of globs given.""" + return any(fnmatch_ex(pattern, path) for pattern in patterns) + + +def pytest_pycollect_makemodule(module_path: Path, parent) -> Module: + return Module.from_parent(parent, path=module_path) + + +@hookimpl(trylast=True) +def pytest_pycollect_makeitem( + collector: Module | Class, name: str, obj: object +) -> None | nodes.Item | nodes.Collector | list[nodes.Item | nodes.Collector]: + assert isinstance(collector, (Class, Module)), type(collector) + # Nothing was collected elsewhere, let's do it here. + if safe_isclass(obj): + if collector.istestclass(obj, name): + return Class.from_parent(collector, name=name, obj=obj) + elif collector.istestfunction(obj, name): + # mock seems to store unbound methods (issue473), normalize it. + obj = getattr(obj, "__func__", obj) + # We need to try and unwrap the function if it's a functools.partial + # or a functools.wrapped. + # We mustn't if it's been wrapped with mock.patch (python 2 only). + if not (inspect.isfunction(obj) or inspect.isfunction(get_real_func(obj))): + filename, lineno = getfslineno(obj) + warnings.warn_explicit( + message=PytestCollectionWarning( + f"cannot collect {name!r} because it is not a function." + ), + category=None, + filename=str(filename), + lineno=lineno + 1, + ) + elif getattr(obj, "__test__", True): + if is_generator(obj): + res = Function.from_parent(collector, name=name) + reason = ( + f"yield tests were removed in pytest 4.0 - {name} will be ignored" + ) + res.add_marker(MARK_GEN.xfail(run=False, reason=reason)) + res.warn(PytestCollectionWarning(reason)) + return res + else: + return list(collector._genfunctions(name, obj)) + return None + + +class PyobjMixin(nodes.Node): + """this mix-in inherits from Node to carry over the typing information + + as its intended to always mix in before a node + its position in the mro is unaffected""" + + _ALLOW_MARKERS = True + + @property + def module(self): + """Python module object this node was collected from (can be None).""" + node = self.getparent(Module) + return node.obj if node is not None else None + + @property + def cls(self): + """Python class object this node was collected from (can be None).""" + node = self.getparent(Class) + return node.obj if node is not None else None + + @property + def instance(self): + """Python instance object the function is bound to. + + Returns None if not a test method, e.g. for a standalone test function, + a class or a module. + """ + # Overridden by Function. + return None + + @property + def obj(self): + """Underlying Python object.""" + obj = getattr(self, "_obj", None) + if obj is None: + self._obj = obj = self._getobj() + # XXX evil hack + # used to avoid Function marker duplication + if self._ALLOW_MARKERS: + self.own_markers.extend(get_unpacked_marks(self.obj)) + # This assumes that `obj` is called before there is a chance + # to add custom keys to `self.keywords`, so no fear of overriding. + self.keywords.update((mark.name, mark) for mark in self.own_markers) + return obj + + @obj.setter + def obj(self, value): + self._obj = value + + def _getobj(self): + """Get the underlying Python object. May be overwritten by subclasses.""" + # TODO: Improve the type of `parent` such that assert/ignore aren't needed. + assert self.parent is not None + obj = self.parent.obj # type: ignore[attr-defined] + return getattr(obj, self.name) + + def getmodpath(self, stopatmodule: bool = True, includemodule: bool = False) -> str: + """Return Python path relative to the containing module.""" + parts = [] + for node in self.iter_parents(): + name = node.name + if isinstance(node, Module): + name = os.path.splitext(name)[0] + if stopatmodule: + if includemodule: + parts.append(name) + break + parts.append(name) + parts.reverse() + return ".".join(parts) + + def reportinfo(self) -> tuple[os.PathLike[str] | str, int | None, str]: + # XXX caching? + path, lineno = getfslineno(self.obj) + modpath = self.getmodpath() + return path, lineno, modpath + + +# As an optimization, these builtin attribute names are pre-ignored when +# iterating over an object during collection -- the pytest_pycollect_makeitem +# hook is not called for them. +# fmt: off +class _EmptyClass: pass # noqa: E701 +IGNORED_ATTRIBUTES = frozenset.union( + frozenset(), + # Module. + dir(types.ModuleType("empty_module")), + # Some extra module attributes the above doesn't catch. + {"__builtins__", "__file__", "__cached__"}, + # Class. + dir(_EmptyClass), + # Instance. + dir(_EmptyClass()), +) +del _EmptyClass +# fmt: on + + +class PyCollector(PyobjMixin, nodes.Collector, abc.ABC): + def funcnamefilter(self, name: str) -> bool: + return self._matches_prefix_or_glob_option("python_functions", name) + + def isnosetest(self, obj: object) -> bool: + """Look for the __test__ attribute, which is applied by the + @nose.tools.istest decorator. + """ + # We explicitly check for "is True" here to not mistakenly treat + # classes with a custom __getattr__ returning something truthy (like a + # function) as test classes. + return safe_getattr(obj, "__test__", False) is True + + def classnamefilter(self, name: str) -> bool: + return self._matches_prefix_or_glob_option("python_classes", name) + + def istestfunction(self, obj: object, name: str) -> bool: + if self.funcnamefilter(name) or self.isnosetest(obj): + if isinstance(obj, (staticmethod, classmethod)): + # staticmethods and classmethods need to be unwrapped. + obj = safe_getattr(obj, "__func__", False) + return callable(obj) and fixtures.getfixturemarker(obj) is None + else: + return False + + def istestclass(self, obj: object, name: str) -> bool: + if not (self.classnamefilter(name) or self.isnosetest(obj)): + return False + if inspect.isabstract(obj): + return False + return True + + def _matches_prefix_or_glob_option(self, option_name: str, name: str) -> bool: + """Check if the given name matches the prefix or glob-pattern defined + in ini configuration.""" + for option in self.config.getini(option_name): + if name.startswith(option): + return True + # Check that name looks like a glob-string before calling fnmatch + # because this is called for every name in each collected module, + # and fnmatch is somewhat expensive to call. + elif ("*" in option or "?" in option or "[" in option) and fnmatch.fnmatch( + name, option + ): + return True + return False + + def collect(self) -> Iterable[nodes.Item | nodes.Collector]: + if not getattr(self.obj, "__test__", True): + return [] + + # Avoid random getattrs and peek in the __dict__ instead. + dicts = [getattr(self.obj, "__dict__", {})] + if isinstance(self.obj, type): + for basecls in self.obj.__mro__: + dicts.append(basecls.__dict__) + + # In each class, nodes should be definition ordered. + # __dict__ is definition ordered. + seen: set[str] = set() + dict_values: list[list[nodes.Item | nodes.Collector]] = [] + ihook = self.ihook + for dic in dicts: + values: list[nodes.Item | nodes.Collector] = [] + # Note: seems like the dict can change during iteration - + # be careful not to remove the list() without consideration. + for name, obj in list(dic.items()): + if name in IGNORED_ATTRIBUTES: + continue + if name in seen: + continue + seen.add(name) + res = ihook.pytest_pycollect_makeitem( + collector=self, name=name, obj=obj + ) + if res is None: + continue + elif isinstance(res, list): + values.extend(res) + else: + values.append(res) + dict_values.append(values) + + # Between classes in the class hierarchy, reverse-MRO order -- nodes + # inherited from base classes should come before subclasses. + result = [] + for values in reversed(dict_values): + result.extend(values) + return result + + def _genfunctions(self, name: str, funcobj) -> Iterator[Function]: + modulecol = self.getparent(Module) + assert modulecol is not None + module = modulecol.obj + clscol = self.getparent(Class) + cls = clscol and clscol.obj or None + + definition = FunctionDefinition.from_parent(self, name=name, callobj=funcobj) + fixtureinfo = definition._fixtureinfo + + # pytest_generate_tests impls call metafunc.parametrize() which fills + # metafunc._calls, the outcome of the hook. + metafunc = Metafunc( + definition=definition, + fixtureinfo=fixtureinfo, + config=self.config, + cls=cls, + module=module, + _ispytest=True, + ) + methods = [] + if hasattr(module, "pytest_generate_tests"): + methods.append(module.pytest_generate_tests) + if cls is not None and hasattr(cls, "pytest_generate_tests"): + methods.append(cls().pytest_generate_tests) + self.ihook.pytest_generate_tests.call_extra(methods, dict(metafunc=metafunc)) + + if not metafunc._calls: + yield Function.from_parent(self, name=name, fixtureinfo=fixtureinfo) + else: + # Direct parametrizations taking place in module/class-specific + # `metafunc.parametrize` calls may have shadowed some fixtures, so make sure + # we update what the function really needs a.k.a its fixture closure. Note that + # direct parametrizations using `@pytest.mark.parametrize` have already been considered + # into making the closure using `ignore_args` arg to `getfixtureclosure`. + fixtureinfo.prune_dependency_tree() + + for callspec in metafunc._calls: + subname = f"{name}[{callspec.id}]" + yield Function.from_parent( + self, + name=subname, + callspec=callspec, + fixtureinfo=fixtureinfo, + keywords={callspec.id: True}, + originalname=name, + ) + + +def importtestmodule( + path: Path, + config: Config, +): + # We assume we are only called once per module. + importmode = config.getoption("--import-mode") + try: + mod = import_path( + path, + mode=importmode, + root=config.rootpath, + consider_namespace_packages=config.getini("consider_namespace_packages"), + ) + except SyntaxError as e: + raise nodes.Collector.CollectError( + ExceptionInfo.from_current().getrepr(style="short") + ) from e + except ImportPathMismatchError as e: + raise nodes.Collector.CollectError( + "import file mismatch:\n" + "imported module {!r} has this __file__ attribute:\n" + " {}\n" + "which is not the same as the test file we want to collect:\n" + " {}\n" + "HINT: remove __pycache__ / .pyc files and/or use a " + "unique basename for your test file modules".format(*e.args) + ) from e + except ImportError as e: + exc_info = ExceptionInfo.from_current() + if config.get_verbosity() < 2: + exc_info.traceback = exc_info.traceback.filter(filter_traceback) + exc_repr = ( + exc_info.getrepr(style="short") + if exc_info.traceback + else exc_info.exconly() + ) + formatted_tb = str(exc_repr) + raise nodes.Collector.CollectError( + f"ImportError while importing test module '{path}'.\n" + "Hint: make sure your test modules/packages have valid Python names.\n" + "Traceback:\n" + f"{formatted_tb}" + ) from e + except skip.Exception as e: + if e.allow_module_level: + raise + raise nodes.Collector.CollectError( + "Using pytest.skip outside of a test will skip the entire module. " + "If that's your intention, pass `allow_module_level=True`. " + "If you want to skip a specific test or an entire class, " + "use the @pytest.mark.skip or @pytest.mark.skipif decorators." + ) from e + config.pluginmanager.consider_module(mod) + return mod + + +class Module(nodes.File, PyCollector): + """Collector for test classes and functions in a Python module.""" + + def _getobj(self): + return importtestmodule(self.path, self.config) + + def collect(self) -> Iterable[nodes.Item | nodes.Collector]: + self._register_setup_module_fixture() + self._register_setup_function_fixture() + self.session._fixturemanager.parsefactories(self) + return super().collect() + + def _register_setup_module_fixture(self) -> None: + """Register an autouse, module-scoped fixture for the collected module object + that invokes setUpModule/tearDownModule if either or both are available. + + Using a fixture to invoke this methods ensures we play nicely and unsurprisingly with + other fixtures (#517). + """ + setup_module = _get_first_non_fixture_func( + self.obj, ("setUpModule", "setup_module") + ) + teardown_module = _get_first_non_fixture_func( + self.obj, ("tearDownModule", "teardown_module") + ) + + if setup_module is None and teardown_module is None: + return + + def xunit_setup_module_fixture(request) -> Generator[None]: + module = request.module + if setup_module is not None: + _call_with_optional_argument(setup_module, module) + yield + if teardown_module is not None: + _call_with_optional_argument(teardown_module, module) + + self.session._fixturemanager._register_fixture( + # Use a unique name to speed up lookup. + name=f"_xunit_setup_module_fixture_{self.obj.__name__}", + func=xunit_setup_module_fixture, + nodeid=self.nodeid, + scope="module", + autouse=True, + ) + + def _register_setup_function_fixture(self) -> None: + """Register an autouse, function-scoped fixture for the collected module object + that invokes setup_function/teardown_function if either or both are available. + + Using a fixture to invoke this methods ensures we play nicely and unsurprisingly with + other fixtures (#517). + """ + setup_function = _get_first_non_fixture_func(self.obj, ("setup_function",)) + teardown_function = _get_first_non_fixture_func( + self.obj, ("teardown_function",) + ) + if setup_function is None and teardown_function is None: + return + + def xunit_setup_function_fixture(request) -> Generator[None]: + if request.instance is not None: + # in this case we are bound to an instance, so we need to let + # setup_method handle this + yield + return + function = request.function + if setup_function is not None: + _call_with_optional_argument(setup_function, function) + yield + if teardown_function is not None: + _call_with_optional_argument(teardown_function, function) + + self.session._fixturemanager._register_fixture( + # Use a unique name to speed up lookup. + name=f"_xunit_setup_function_fixture_{self.obj.__name__}", + func=xunit_setup_function_fixture, + nodeid=self.nodeid, + scope="function", + autouse=True, + ) + + +class Package(nodes.Directory): + """Collector for files and directories in a Python packages -- directories + with an `__init__.py` file. + + .. note:: + + Directories without an `__init__.py` file are instead collected by + :class:`~pytest.Dir` by default. Both are :class:`~pytest.Directory` + collectors. + + .. versionchanged:: 8.0 + + Now inherits from :class:`~pytest.Directory`. + """ + + def __init__( + self, + fspath: LEGACY_PATH | None, + parent: nodes.Collector, + # NOTE: following args are unused: + config=None, + session=None, + nodeid=None, + path: Path | None = None, + ) -> None: + # NOTE: Could be just the following, but kept as-is for compat. + # super().__init__(self, fspath, parent=parent) + session = parent.session + super().__init__( + fspath=fspath, + path=path, + parent=parent, + config=config, + session=session, + nodeid=nodeid, + ) + + def setup(self) -> None: + init_mod = importtestmodule(self.path / "__init__.py", self.config) + + # Not using fixtures to call setup_module here because autouse fixtures + # from packages are not called automatically (#4085). + setup_module = _get_first_non_fixture_func( + init_mod, ("setUpModule", "setup_module") + ) + if setup_module is not None: + _call_with_optional_argument(setup_module, init_mod) + + teardown_module = _get_first_non_fixture_func( + init_mod, ("tearDownModule", "teardown_module") + ) + if teardown_module is not None: + func = partial(_call_with_optional_argument, teardown_module, init_mod) + self.addfinalizer(func) + + def collect(self) -> Iterable[nodes.Item | nodes.Collector]: + # Always collect __init__.py first. + def sort_key(entry: os.DirEntry[str]) -> object: + return (entry.name != "__init__.py", entry.name) + + config = self.config + col: nodes.Collector | None + cols: Sequence[nodes.Collector] + ihook = self.ihook + for direntry in scandir(self.path, sort_key): + if direntry.is_dir(): + path = Path(direntry.path) + if not self.session.isinitpath(path, with_parents=True): + if ihook.pytest_ignore_collect(collection_path=path, config=config): + continue + col = ihook.pytest_collect_directory(path=path, parent=self) + if col is not None: + yield col + + elif direntry.is_file(): + path = Path(direntry.path) + if not self.session.isinitpath(path): + if ihook.pytest_ignore_collect(collection_path=path, config=config): + continue + cols = ihook.pytest_collect_file(file_path=path, parent=self) + yield from cols + + +def _call_with_optional_argument(func, arg) -> None: + """Call the given function with the given argument if func accepts one argument, otherwise + calls func without arguments.""" + arg_count = func.__code__.co_argcount + if inspect.ismethod(func): + arg_count -= 1 + if arg_count: + func(arg) + else: + func() + + +def _get_first_non_fixture_func(obj: object, names: Iterable[str]) -> object | None: + """Return the attribute from the given object to be used as a setup/teardown + xunit-style function, but only if not marked as a fixture to avoid calling it twice. + """ + for name in names: + meth: object | None = getattr(obj, name, None) + if meth is not None and fixtures.getfixturemarker(meth) is None: + return meth + return None + + +class Class(PyCollector): + """Collector for test methods (and nested classes) in a Python class.""" + + @classmethod + def from_parent(cls, parent, *, name, obj=None, **kw) -> Self: # type: ignore[override] + """The public constructor.""" + return super().from_parent(name=name, parent=parent, **kw) + + def newinstance(self): + return self.obj() + + def collect(self) -> Iterable[nodes.Item | nodes.Collector]: + if not safe_getattr(self.obj, "__test__", True): + return [] + if hasinit(self.obj): + assert self.parent is not None + self.warn( + PytestCollectionWarning( + f"cannot collect test class {self.obj.__name__!r} because it has a " + f"__init__ constructor (from: {self.parent.nodeid})" + ) + ) + return [] + elif hasnew(self.obj): + assert self.parent is not None + self.warn( + PytestCollectionWarning( + f"cannot collect test class {self.obj.__name__!r} because it has a " + f"__new__ constructor (from: {self.parent.nodeid})" + ) + ) + return [] + + self._register_setup_class_fixture() + self._register_setup_method_fixture() + + self.session._fixturemanager.parsefactories(self.newinstance(), self.nodeid) + + return super().collect() + + def _register_setup_class_fixture(self) -> None: + """Register an autouse, class scoped fixture into the collected class object + that invokes setup_class/teardown_class if either or both are available. + + Using a fixture to invoke this methods ensures we play nicely and unsurprisingly with + other fixtures (#517). + """ + setup_class = _get_first_non_fixture_func(self.obj, ("setup_class",)) + teardown_class = _get_first_non_fixture_func(self.obj, ("teardown_class",)) + if setup_class is None and teardown_class is None: + return + + def xunit_setup_class_fixture(request) -> Generator[None]: + cls = request.cls + if setup_class is not None: + func = getimfunc(setup_class) + _call_with_optional_argument(func, cls) + yield + if teardown_class is not None: + func = getimfunc(teardown_class) + _call_with_optional_argument(func, cls) + + self.session._fixturemanager._register_fixture( + # Use a unique name to speed up lookup. + name=f"_xunit_setup_class_fixture_{self.obj.__qualname__}", + func=xunit_setup_class_fixture, + nodeid=self.nodeid, + scope="class", + autouse=True, + ) + + def _register_setup_method_fixture(self) -> None: + """Register an autouse, function scoped fixture into the collected class object + that invokes setup_method/teardown_method if either or both are available. + + Using a fixture to invoke these methods ensures we play nicely and unsurprisingly with + other fixtures (#517). + """ + setup_name = "setup_method" + setup_method = _get_first_non_fixture_func(self.obj, (setup_name,)) + teardown_name = "teardown_method" + teardown_method = _get_first_non_fixture_func(self.obj, (teardown_name,)) + if setup_method is None and teardown_method is None: + return + + def xunit_setup_method_fixture(request) -> Generator[None]: + instance = request.instance + method = request.function + if setup_method is not None: + func = getattr(instance, setup_name) + _call_with_optional_argument(func, method) + yield + if teardown_method is not None: + func = getattr(instance, teardown_name) + _call_with_optional_argument(func, method) + + self.session._fixturemanager._register_fixture( + # Use a unique name to speed up lookup. + name=f"_xunit_setup_method_fixture_{self.obj.__qualname__}", + func=xunit_setup_method_fixture, + nodeid=self.nodeid, + scope="function", + autouse=True, + ) + + +def hasinit(obj: object) -> bool: + init: object = getattr(obj, "__init__", None) + if init: + return init != object.__init__ + return False + + +def hasnew(obj: object) -> bool: + new: object = getattr(obj, "__new__", None) + if new: + return new != object.__new__ + return False + + +@final +@dataclasses.dataclass(frozen=True) +class IdMaker: + """Make IDs for a parametrization.""" + + __slots__ = ( + "argnames", + "parametersets", + "idfn", + "ids", + "config", + "nodeid", + "func_name", + ) + + # The argnames of the parametrization. + argnames: Sequence[str] + # The ParameterSets of the parametrization. + parametersets: Sequence[ParameterSet] + # Optionally, a user-provided callable to make IDs for parameters in a + # ParameterSet. + idfn: Callable[[Any], object | None] | None + # Optionally, explicit IDs for ParameterSets by index. + ids: Sequence[object | None] | None + # Optionally, the pytest config. + # Used for controlling ASCII escaping, and for calling the + # :hook:`pytest_make_parametrize_id` hook. + config: Config | None + # Optionally, the ID of the node being parametrized. + # Used only for clearer error messages. + nodeid: str | None + # Optionally, the ID of the function being parametrized. + # Used only for clearer error messages. + func_name: str | None + + def make_unique_parameterset_ids(self) -> list[str]: + """Make a unique identifier for each ParameterSet, that may be used to + identify the parametrization in a node ID. + + Format is -...-[counter], where prm_x_token is + - user-provided id, if given + - else an id derived from the value, applicable for certain types + - else + The counter suffix is appended only in case a string wouldn't be unique + otherwise. + """ + resolved_ids = list(self._resolve_ids()) + # All IDs must be unique! + if len(resolved_ids) != len(set(resolved_ids)): + # Record the number of occurrences of each ID. + id_counts = Counter(resolved_ids) + # Map the ID to its next suffix. + id_suffixes: dict[str, int] = defaultdict(int) + # Suffix non-unique IDs to make them unique. + for index, id in enumerate(resolved_ids): + if id_counts[id] > 1: + suffix = "" + if id and id[-1].isdigit(): + suffix = "_" + new_id = f"{id}{suffix}{id_suffixes[id]}" + while new_id in set(resolved_ids): + id_suffixes[id] += 1 + new_id = f"{id}{suffix}{id_suffixes[id]}" + resolved_ids[index] = new_id + id_suffixes[id] += 1 + assert len(resolved_ids) == len( + set(resolved_ids) + ), f"Internal error: {resolved_ids=}" + return resolved_ids + + def _resolve_ids(self) -> Iterable[str]: + """Resolve IDs for all ParameterSets (may contain duplicates).""" + for idx, parameterset in enumerate(self.parametersets): + if parameterset.id is not None: + # ID provided directly - pytest.param(..., id="...") + yield parameterset.id + elif self.ids and idx < len(self.ids) and self.ids[idx] is not None: + # ID provided in the IDs list - parametrize(..., ids=[...]). + yield self._idval_from_value_required(self.ids[idx], idx) + else: + # ID not provided - generate it. + yield "-".join( + self._idval(val, argname, idx) + for val, argname in zip(parameterset.values, self.argnames) + ) + + def _idval(self, val: object, argname: str, idx: int) -> str: + """Make an ID for a parameter in a ParameterSet.""" + idval = self._idval_from_function(val, argname, idx) + if idval is not None: + return idval + idval = self._idval_from_hook(val, argname) + if idval is not None: + return idval + idval = self._idval_from_value(val) + if idval is not None: + return idval + return self._idval_from_argname(argname, idx) + + def _idval_from_function(self, val: object, argname: str, idx: int) -> str | None: + """Try to make an ID for a parameter in a ParameterSet using the + user-provided id callable, if given.""" + if self.idfn is None: + return None + try: + id = self.idfn(val) + except Exception as e: + prefix = f"{self.nodeid}: " if self.nodeid is not None else "" + msg = "error raised while trying to determine id of parameter '{}' at position {}" + msg = prefix + msg.format(argname, idx) + raise ValueError(msg) from e + if id is None: + return None + return self._idval_from_value(id) + + def _idval_from_hook(self, val: object, argname: str) -> str | None: + """Try to make an ID for a parameter in a ParameterSet by calling the + :hook:`pytest_make_parametrize_id` hook.""" + if self.config: + id: str | None = self.config.hook.pytest_make_parametrize_id( + config=self.config, val=val, argname=argname + ) + return id + return None + + def _idval_from_value(self, val: object) -> str | None: + """Try to make an ID for a parameter in a ParameterSet from its value, + if the value type is supported.""" + if isinstance(val, (str, bytes)): + return _ascii_escaped_by_config(val, self.config) + elif val is None or isinstance(val, (float, int, bool, complex)): + return str(val) + elif isinstance(val, Pattern): + return ascii_escaped(val.pattern) + elif val is NOTSET: + # Fallback to default. Note that NOTSET is an enum.Enum. + pass + elif isinstance(val, enum.Enum): + return str(val) + elif isinstance(getattr(val, "__name__", None), str): + # Name of a class, function, module, etc. + name: str = getattr(val, "__name__") + return name + return None + + def _idval_from_value_required(self, val: object, idx: int) -> str: + """Like _idval_from_value(), but fails if the type is not supported.""" + id = self._idval_from_value(val) + if id is not None: + return id + + # Fail. + if self.func_name is not None: + prefix = f"In {self.func_name}: " + elif self.nodeid is not None: + prefix = f"In {self.nodeid}: " + else: + prefix = "" + msg = ( + f"{prefix}ids contains unsupported value {saferepr(val)} (type: {type(val)!r}) at index {idx}. " + "Supported types are: str, bytes, int, float, complex, bool, enum, regex or anything with a __name__." + ) + fail(msg, pytrace=False) + + @staticmethod + def _idval_from_argname(argname: str, idx: int) -> str: + """Make an ID for a parameter in a ParameterSet from the argument name + and the index of the ParameterSet.""" + return str(argname) + str(idx) + + +@final +@dataclasses.dataclass(frozen=True) +class CallSpec2: + """A planned parameterized invocation of a test function. + + Calculated during collection for a given test function's Metafunc. + Once collection is over, each callspec is turned into a single Item + and stored in item.callspec. + """ + + # arg name -> arg value which will be passed to a fixture or pseudo-fixture + # of the same name. (indirect or direct parametrization respectively) + params: dict[str, object] = dataclasses.field(default_factory=dict) + # arg name -> arg index. + indices: dict[str, int] = dataclasses.field(default_factory=dict) + # Used for sorting parametrized resources. + _arg2scope: Mapping[str, Scope] = dataclasses.field(default_factory=dict) + # Parts which will be added to the item's name in `[..]` separated by "-". + _idlist: Sequence[str] = dataclasses.field(default_factory=tuple) + # Marks which will be applied to the item. + marks: list[Mark] = dataclasses.field(default_factory=list) + + def setmulti( + self, + *, + argnames: Iterable[str], + valset: Iterable[object], + id: str, + marks: Iterable[Mark | MarkDecorator], + scope: Scope, + param_index: int, + ) -> CallSpec2: + params = self.params.copy() + indices = self.indices.copy() + arg2scope = dict(self._arg2scope) + for arg, val in zip(argnames, valset): + if arg in params: + raise ValueError(f"duplicate parametrization of {arg!r}") + params[arg] = val + indices[arg] = param_index + arg2scope[arg] = scope + return CallSpec2( + params=params, + indices=indices, + _arg2scope=arg2scope, + _idlist=[*self._idlist, id], + marks=[*self.marks, *normalize_mark_list(marks)], + ) + + def getparam(self, name: str) -> object: + try: + return self.params[name] + except KeyError as e: + raise ValueError(name) from e + + @property + def id(self) -> str: + return "-".join(self._idlist) + + +def get_direct_param_fixture_func(request: FixtureRequest) -> Any: + return request.param + + +# Used for storing pseudo fixturedefs for direct parametrization. +name2pseudofixturedef_key = StashKey[Dict[str, FixtureDef[Any]]]() + + +@final +class Metafunc: + """Objects passed to the :hook:`pytest_generate_tests` hook. + + They help to inspect a test function and to generate tests according to + test configuration or values specified in the class or module where a + test function is defined. + """ + + def __init__( + self, + definition: FunctionDefinition, + fixtureinfo: fixtures.FuncFixtureInfo, + config: Config, + cls=None, + module=None, + *, + _ispytest: bool = False, + ) -> None: + check_ispytest(_ispytest) + + #: Access to the underlying :class:`_pytest.python.FunctionDefinition`. + self.definition = definition + + #: Access to the :class:`pytest.Config` object for the test session. + self.config = config + + #: The module object where the test function is defined in. + self.module = module + + #: Underlying Python test function. + self.function = definition.obj + + #: Set of fixture names required by the test function. + self.fixturenames = fixtureinfo.names_closure + + #: Class object where the test function is defined in or ``None``. + self.cls = cls + + self._arg2fixturedefs = fixtureinfo.name2fixturedefs + + # Result of parametrize(). + self._calls: list[CallSpec2] = [] + + def parametrize( + self, + argnames: str | Sequence[str], + argvalues: Iterable[ParameterSet | Sequence[object] | object], + indirect: bool | Sequence[str] = False, + ids: Iterable[object | None] | Callable[[Any], object | None] | None = None, + scope: _ScopeName | None = None, + *, + _param_mark: Mark | None = None, + ) -> None: + """Add new invocations to the underlying test function using the list + of argvalues for the given argnames. Parametrization is performed + during the collection phase. If you need to setup expensive resources + see about setting indirect to do it rather than at test setup time. + + Can be called multiple times per test function (but only on different + argument names), in which case each call parametrizes all previous + parametrizations, e.g. + + :: + + unparametrized: t + parametrize ["x", "y"]: t[x], t[y] + parametrize [1, 2]: t[x-1], t[x-2], t[y-1], t[y-2] + + :param argnames: + A comma-separated string denoting one or more argument names, or + a list/tuple of argument strings. + + :param argvalues: + The list of argvalues determines how often a test is invoked with + different argument values. + + If only one argname was specified argvalues is a list of values. + If N argnames were specified, argvalues must be a list of + N-tuples, where each tuple-element specifies a value for its + respective argname. + :type argvalues: Iterable[_pytest.mark.structures.ParameterSet | Sequence[object] | object] + :param indirect: + A list of arguments' names (subset of argnames) or a boolean. + If True the list contains all names from the argnames. Each + argvalue corresponding to an argname in this list will + be passed as request.param to its respective argname fixture + function so that it can perform more expensive setups during the + setup phase of a test rather than at collection time. + + :param ids: + Sequence of (or generator for) ids for ``argvalues``, + or a callable to return part of the id for each argvalue. + + With sequences (and generators like ``itertools.count()``) the + returned ids should be of type ``string``, ``int``, ``float``, + ``bool``, or ``None``. + They are mapped to the corresponding index in ``argvalues``. + ``None`` means to use the auto-generated id. + + If it is a callable it will be called for each entry in + ``argvalues``, and the return value is used as part of the + auto-generated id for the whole set (where parts are joined with + dashes ("-")). + This is useful to provide more specific ids for certain items, e.g. + dates. Returning ``None`` will use an auto-generated id. + + If no ids are provided they will be generated automatically from + the argvalues. + + :param scope: + If specified it denotes the scope of the parameters. + The scope is used for grouping tests by parameter instances. + It will also override any fixture-function defined scope, allowing + to set a dynamic scope using test context or configuration. + """ + argnames, parametersets = ParameterSet._for_parametrize( + argnames, + argvalues, + self.function, + self.config, + nodeid=self.definition.nodeid, + ) + del argvalues + + if "request" in argnames: + fail( + "'request' is a reserved name and cannot be used in @pytest.mark.parametrize", + pytrace=False, + ) + + if scope is not None: + scope_ = Scope.from_user( + scope, descr=f"parametrize() call in {self.function.__name__}" + ) + else: + scope_ = _find_parametrized_scope(argnames, self._arg2fixturedefs, indirect) + + self._validate_if_using_arg_names(argnames, indirect) + + # Use any already (possibly) generated ids with parametrize Marks. + if _param_mark and _param_mark._param_ids_from: + generated_ids = _param_mark._param_ids_from._param_ids_generated + if generated_ids is not None: + ids = generated_ids + + ids = self._resolve_parameter_set_ids( + argnames, ids, parametersets, nodeid=self.definition.nodeid + ) + + # Store used (possibly generated) ids with parametrize Marks. + if _param_mark and _param_mark._param_ids_from and generated_ids is None: + object.__setattr__(_param_mark._param_ids_from, "_param_ids_generated", ids) + + # Add funcargs as fixturedefs to fixtureinfo.arg2fixturedefs by registering + # artificial "pseudo" FixtureDef's so that later at test execution time we can + # rely on a proper FixtureDef to exist for fixture setup. + node = None + # If we have a scope that is higher than function, we need + # to make sure we only ever create an according fixturedef on + # a per-scope basis. We thus store and cache the fixturedef on the + # node related to the scope. + if scope_ is not Scope.Function: + collector = self.definition.parent + assert collector is not None + node = get_scope_node(collector, scope_) + if node is None: + # If used class scope and there is no class, use module-level + # collector (for now). + if scope_ is Scope.Class: + assert isinstance(collector, Module) + node = collector + # If used package scope and there is no package, use session + # (for now). + elif scope_ is Scope.Package: + node = collector.session + else: + assert False, f"Unhandled missing scope: {scope}" + if node is None: + name2pseudofixturedef = None + else: + default: dict[str, FixtureDef[Any]] = {} + name2pseudofixturedef = node.stash.setdefault( + name2pseudofixturedef_key, default + ) + arg_directness = self._resolve_args_directness(argnames, indirect) + for argname in argnames: + if arg_directness[argname] == "indirect": + continue + if name2pseudofixturedef is not None and argname in name2pseudofixturedef: + fixturedef = name2pseudofixturedef[argname] + else: + fixturedef = FixtureDef( + config=self.config, + baseid="", + argname=argname, + func=get_direct_param_fixture_func, + scope=scope_, + params=None, + ids=None, + _ispytest=True, + ) + if name2pseudofixturedef is not None: + name2pseudofixturedef[argname] = fixturedef + self._arg2fixturedefs[argname] = [fixturedef] + + # Create the new calls: if we are parametrize() multiple times (by applying the decorator + # more than once) then we accumulate those calls generating the cartesian product + # of all calls. + newcalls = [] + for callspec in self._calls or [CallSpec2()]: + for param_index, (param_id, param_set) in enumerate( + zip(ids, parametersets) + ): + newcallspec = callspec.setmulti( + argnames=argnames, + valset=param_set.values, + id=param_id, + marks=param_set.marks, + scope=scope_, + param_index=param_index, + ) + newcalls.append(newcallspec) + self._calls = newcalls + + def _resolve_parameter_set_ids( + self, + argnames: Sequence[str], + ids: Iterable[object | None] | Callable[[Any], object | None] | None, + parametersets: Sequence[ParameterSet], + nodeid: str, + ) -> list[str]: + """Resolve the actual ids for the given parameter sets. + + :param argnames: + Argument names passed to ``parametrize()``. + :param ids: + The `ids` parameter of the ``parametrize()`` call (see docs). + :param parametersets: + The parameter sets, each containing a set of values corresponding + to ``argnames``. + :param nodeid str: + The nodeid of the definition item that generated this + parametrization. + :returns: + List with ids for each parameter set given. + """ + if ids is None: + idfn = None + ids_ = None + elif callable(ids): + idfn = ids + ids_ = None + else: + idfn = None + ids_ = self._validate_ids(ids, parametersets, self.function.__name__) + id_maker = IdMaker( + argnames, + parametersets, + idfn, + ids_, + self.config, + nodeid=nodeid, + func_name=self.function.__name__, + ) + return id_maker.make_unique_parameterset_ids() + + def _validate_ids( + self, + ids: Iterable[object | None], + parametersets: Sequence[ParameterSet], + func_name: str, + ) -> list[object | None]: + try: + num_ids = len(ids) # type: ignore[arg-type] + except TypeError: + try: + iter(ids) + except TypeError as e: + raise TypeError("ids must be a callable or an iterable") from e + num_ids = len(parametersets) + + # num_ids == 0 is a special case: https://github.com/pytest-dev/pytest/issues/1849 + if num_ids != len(parametersets) and num_ids != 0: + msg = "In {}: {} parameter sets specified, with different number of ids: {}" + fail(msg.format(func_name, len(parametersets), num_ids), pytrace=False) + + return list(itertools.islice(ids, num_ids)) + + def _resolve_args_directness( + self, + argnames: Sequence[str], + indirect: bool | Sequence[str], + ) -> dict[str, Literal["indirect", "direct"]]: + """Resolve if each parametrized argument must be considered an indirect + parameter to a fixture of the same name, or a direct parameter to the + parametrized function, based on the ``indirect`` parameter of the + parametrized() call. + + :param argnames: + List of argument names passed to ``parametrize()``. + :param indirect: + Same as the ``indirect`` parameter of ``parametrize()``. + :returns + A dict mapping each arg name to either "indirect" or "direct". + """ + arg_directness: dict[str, Literal["indirect", "direct"]] + if isinstance(indirect, bool): + arg_directness = dict.fromkeys( + argnames, "indirect" if indirect else "direct" + ) + elif isinstance(indirect, Sequence): + arg_directness = dict.fromkeys(argnames, "direct") + for arg in indirect: + if arg not in argnames: + fail( + f"In {self.function.__name__}: indirect fixture '{arg}' doesn't exist", + pytrace=False, + ) + arg_directness[arg] = "indirect" + else: + fail( + f"In {self.function.__name__}: expected Sequence or boolean" + f" for indirect, got {type(indirect).__name__}", + pytrace=False, + ) + return arg_directness + + def _validate_if_using_arg_names( + self, + argnames: Sequence[str], + indirect: bool | Sequence[str], + ) -> None: + """Check if all argnames are being used, by default values, or directly/indirectly. + + :param List[str] argnames: List of argument names passed to ``parametrize()``. + :param indirect: Same as the ``indirect`` parameter of ``parametrize()``. + :raises ValueError: If validation fails. + """ + default_arg_names = set(get_default_arg_names(self.function)) + func_name = self.function.__name__ + for arg in argnames: + if arg not in self.fixturenames: + if arg in default_arg_names: + fail( + f"In {func_name}: function already takes an argument '{arg}' with a default value", + pytrace=False, + ) + else: + if isinstance(indirect, Sequence): + name = "fixture" if arg in indirect else "argument" + else: + name = "fixture" if indirect else "argument" + fail( + f"In {func_name}: function uses no {name} '{arg}'", + pytrace=False, + ) + + +def _find_parametrized_scope( + argnames: Sequence[str], + arg2fixturedefs: Mapping[str, Sequence[fixtures.FixtureDef[object]]], + indirect: bool | Sequence[str], +) -> Scope: + """Find the most appropriate scope for a parametrized call based on its arguments. + + When there's at least one direct argument, always use "function" scope. + + When a test function is parametrized and all its arguments are indirect + (e.g. fixtures), return the most narrow scope based on the fixtures used. + + Related to issue #1832, based on code posted by @Kingdread. + """ + if isinstance(indirect, Sequence): + all_arguments_are_fixtures = len(indirect) == len(argnames) + else: + all_arguments_are_fixtures = bool(indirect) + + if all_arguments_are_fixtures: + fixturedefs = arg2fixturedefs or {} + used_scopes = [ + fixturedef[-1]._scope + for name, fixturedef in fixturedefs.items() + if name in argnames + ] + # Takes the most narrow scope from used fixtures. + return min(used_scopes, default=Scope.Function) + + return Scope.Function + + +def _ascii_escaped_by_config(val: str | bytes, config: Config | None) -> str: + if config is None: + escape_option = False + else: + escape_option = config.getini( + "disable_test_id_escaping_and_forfeit_all_rights_to_community_support" + ) + # TODO: If escaping is turned off and the user passes bytes, + # will return a bytes. For now we ignore this but the + # code *probably* doesn't handle this case. + return val if escape_option else ascii_escaped(val) # type: ignore + + +class Function(PyobjMixin, nodes.Item): + """Item responsible for setting up and executing a Python test function. + + :param name: + The full function name, including any decorations like those + added by parametrization (``my_func[my_param]``). + :param parent: + The parent Node. + :param config: + The pytest Config object. + :param callspec: + If given, this function has been parametrized and the callspec contains + meta information about the parametrization. + :param callobj: + If given, the object which will be called when the Function is invoked, + otherwise the callobj will be obtained from ``parent`` using ``originalname``. + :param keywords: + Keywords bound to the function object for "-k" matching. + :param session: + The pytest Session object. + :param fixtureinfo: + Fixture information already resolved at this fixture node.. + :param originalname: + The attribute name to use for accessing the underlying function object. + Defaults to ``name``. Set this if name is different from the original name, + for example when it contains decorations like those added by parametrization + (``my_func[my_param]``). + """ + + # Disable since functions handle it themselves. + _ALLOW_MARKERS = False + + def __init__( + self, + name: str, + parent, + config: Config | None = None, + callspec: CallSpec2 | None = None, + callobj=NOTSET, + keywords: Mapping[str, Any] | None = None, + session: Session | None = None, + fixtureinfo: FuncFixtureInfo | None = None, + originalname: str | None = None, + ) -> None: + super().__init__(name, parent, config=config, session=session) + + if callobj is not NOTSET: + self._obj = callobj + self._instance = getattr(callobj, "__self__", None) + + #: Original function name, without any decorations (for example + #: parametrization adds a ``"[...]"`` suffix to function names), used to access + #: the underlying function object from ``parent`` (in case ``callobj`` is not given + #: explicitly). + #: + #: .. versionadded:: 3.0 + self.originalname = originalname or name + + # Note: when FunctionDefinition is introduced, we should change ``originalname`` + # to a readonly property that returns FunctionDefinition.name. + + self.own_markers.extend(get_unpacked_marks(self.obj)) + if callspec: + self.callspec = callspec + self.own_markers.extend(callspec.marks) + + # todo: this is a hell of a hack + # https://github.com/pytest-dev/pytest/issues/4569 + # Note: the order of the updates is important here; indicates what + # takes priority (ctor argument over function attributes over markers). + # Take own_markers only; NodeKeywords handles parent traversal on its own. + self.keywords.update((mark.name, mark) for mark in self.own_markers) + self.keywords.update(self.obj.__dict__) + if keywords: + self.keywords.update(keywords) + + if fixtureinfo is None: + fm = self.session._fixturemanager + fixtureinfo = fm.getfixtureinfo(self, self.obj, self.cls) + self._fixtureinfo: FuncFixtureInfo = fixtureinfo + self.fixturenames = fixtureinfo.names_closure + self._initrequest() + + # todo: determine sound type limitations + @classmethod + def from_parent(cls, parent, **kw) -> Self: + """The public constructor.""" + return super().from_parent(parent=parent, **kw) + + def _initrequest(self) -> None: + self.funcargs: dict[str, object] = {} + self._request = fixtures.TopRequest(self, _ispytest=True) + + @property + def function(self): + """Underlying python 'function' object.""" + return getimfunc(self.obj) + + @property + def instance(self): + try: + return self._instance + except AttributeError: + if isinstance(self.parent, Class): + # Each Function gets a fresh class instance. + self._instance = self._getinstance() + else: + self._instance = None + return self._instance + + def _getinstance(self): + if isinstance(self.parent, Class): + # Each Function gets a fresh class instance. + return self.parent.newinstance() + else: + return None + + def _getobj(self): + instance = self.instance + if instance is not None: + parent_obj = instance + else: + assert self.parent is not None + parent_obj = self.parent.obj # type: ignore[attr-defined] + return getattr(parent_obj, self.originalname) + + @property + def _pyfuncitem(self): + """(compatonly) for code expecting pytest-2.2 style request objects.""" + return self + + def runtest(self) -> None: + """Execute the underlying test function.""" + self.ihook.pytest_pyfunc_call(pyfuncitem=self) + + def setup(self) -> None: + self._request._fillfixtures() + + def _traceback_filter(self, excinfo: ExceptionInfo[BaseException]) -> Traceback: + if hasattr(self, "_obj") and not self.config.getoption("fulltrace", False): + code = _pytest._code.Code.from_function(get_real_func(self.obj)) + path, firstlineno = code.path, code.firstlineno + traceback = excinfo.traceback + ntraceback = traceback.cut(path=path, firstlineno=firstlineno) + if ntraceback == traceback: + ntraceback = ntraceback.cut(path=path) + if ntraceback == traceback: + ntraceback = ntraceback.filter(filter_traceback) + if not ntraceback: + ntraceback = traceback + ntraceback = ntraceback.filter(excinfo) + + # issue364: mark all but first and last frames to + # only show a single-line message for each frame. + if self.config.getoption("tbstyle", "auto") == "auto": + if len(ntraceback) > 2: + ntraceback = Traceback( + ( + ntraceback[0], + *(t.with_repr_style("short") for t in ntraceback[1:-1]), + ntraceback[-1], + ) + ) + + return ntraceback + return excinfo.traceback + + # TODO: Type ignored -- breaks Liskov Substitution. + def repr_failure( # type: ignore[override] + self, + excinfo: ExceptionInfo[BaseException], + ) -> str | TerminalRepr: + style = self.config.getoption("tbstyle", "auto") + if style == "auto": + style = "long" + return self._repr_failure_py(excinfo, style=style) + + +class FunctionDefinition(Function): + """This class is a stop gap solution until we evolve to have actual function + definition nodes and manage to get rid of ``metafunc``.""" + + def runtest(self) -> None: + raise RuntimeError("function definitions are not supposed to be run as tests") + + setup = runtest diff --git a/.venv/lib/python3.11/site-packages/_pytest/python_api.py b/.venv/lib/python3.11/site-packages/_pytest/python_api.py new file mode 100644 index 0000000000000000000000000000000000000000..f0035f0c393a29e89243546a89a4cf62fba2348a --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/python_api.py @@ -0,0 +1,1028 @@ +# mypy: allow-untyped-defs +from __future__ import annotations + +from collections.abc import Collection +from collections.abc import Sized +from decimal import Decimal +import math +from numbers import Complex +import pprint +import re +from types import TracebackType +from typing import Any +from typing import Callable +from typing import cast +from typing import ContextManager +from typing import final +from typing import Mapping +from typing import overload +from typing import Pattern +from typing import Sequence +from typing import Tuple +from typing import Type +from typing import TYPE_CHECKING +from typing import TypeVar + +import _pytest._code +from _pytest.outcomes import fail + + +if TYPE_CHECKING: + from numpy import ndarray + + +def _compare_approx( + full_object: object, + message_data: Sequence[tuple[str, str, str]], + number_of_elements: int, + different_ids: Sequence[object], + max_abs_diff: float, + max_rel_diff: float, +) -> list[str]: + message_list = list(message_data) + message_list.insert(0, ("Index", "Obtained", "Expected")) + max_sizes = [0, 0, 0] + for index, obtained, expected in message_list: + max_sizes[0] = max(max_sizes[0], len(index)) + max_sizes[1] = max(max_sizes[1], len(obtained)) + max_sizes[2] = max(max_sizes[2], len(expected)) + explanation = [ + f"comparison failed. Mismatched elements: {len(different_ids)} / {number_of_elements}:", + f"Max absolute difference: {max_abs_diff}", + f"Max relative difference: {max_rel_diff}", + ] + [ + f"{indexes:<{max_sizes[0]}} | {obtained:<{max_sizes[1]}} | {expected:<{max_sizes[2]}}" + for indexes, obtained, expected in message_list + ] + return explanation + + +# builtin pytest.approx helper + + +class ApproxBase: + """Provide shared utilities for making approximate comparisons between + numbers or sequences of numbers.""" + + # Tell numpy to use our `__eq__` operator instead of its. + __array_ufunc__ = None + __array_priority__ = 100 + + def __init__(self, expected, rel=None, abs=None, nan_ok: bool = False) -> None: + __tracebackhide__ = True + self.expected = expected + self.abs = abs + self.rel = rel + self.nan_ok = nan_ok + self._check_type() + + def __repr__(self) -> str: + raise NotImplementedError + + def _repr_compare(self, other_side: Any) -> list[str]: + return [ + "comparison failed", + f"Obtained: {other_side}", + f"Expected: {self}", + ] + + def __eq__(self, actual) -> bool: + return all( + a == self._approx_scalar(x) for a, x in self._yield_comparisons(actual) + ) + + def __bool__(self): + __tracebackhide__ = True + raise AssertionError( + "approx() is not supported in a boolean context.\nDid you mean: `assert a == approx(b)`?" + ) + + # Ignore type because of https://github.com/python/mypy/issues/4266. + __hash__ = None # type: ignore + + def __ne__(self, actual) -> bool: + return not (actual == self) + + def _approx_scalar(self, x) -> ApproxScalar: + if isinstance(x, Decimal): + return ApproxDecimal(x, rel=self.rel, abs=self.abs, nan_ok=self.nan_ok) + return ApproxScalar(x, rel=self.rel, abs=self.abs, nan_ok=self.nan_ok) + + def _yield_comparisons(self, actual): + """Yield all the pairs of numbers to be compared. + + This is used to implement the `__eq__` method. + """ + raise NotImplementedError + + def _check_type(self) -> None: + """Raise a TypeError if the expected value is not a valid type.""" + # This is only a concern if the expected value is a sequence. In every + # other case, the approx() function ensures that the expected value has + # a numeric type. For this reason, the default is to do nothing. The + # classes that deal with sequences should reimplement this method to + # raise if there are any non-numeric elements in the sequence. + + +def _recursive_sequence_map(f, x): + """Recursively map a function over a sequence of arbitrary depth""" + if isinstance(x, (list, tuple)): + seq_type = type(x) + return seq_type(_recursive_sequence_map(f, xi) for xi in x) + elif _is_sequence_like(x): + return [_recursive_sequence_map(f, xi) for xi in x] + else: + return f(x) + + +class ApproxNumpy(ApproxBase): + """Perform approximate comparisons where the expected value is numpy array.""" + + def __repr__(self) -> str: + list_scalars = _recursive_sequence_map( + self._approx_scalar, self.expected.tolist() + ) + return f"approx({list_scalars!r})" + + def _repr_compare(self, other_side: ndarray | list[Any]) -> list[str]: + import itertools + import math + + def get_value_from_nested_list( + nested_list: list[Any], nd_index: tuple[Any, ...] + ) -> Any: + """ + Helper function to get the value out of a nested list, given an n-dimensional index. + This mimics numpy's indexing, but for raw nested python lists. + """ + value: Any = nested_list + for i in nd_index: + value = value[i] + return value + + np_array_shape = self.expected.shape + approx_side_as_seq = _recursive_sequence_map( + self._approx_scalar, self.expected.tolist() + ) + + # convert other_side to numpy array to ensure shape attribute is available + other_side_as_array = _as_numpy_array(other_side) + assert other_side_as_array is not None + + if np_array_shape != other_side_as_array.shape: + return [ + "Impossible to compare arrays with different shapes.", + f"Shapes: {np_array_shape} and {other_side_as_array.shape}", + ] + + number_of_elements = self.expected.size + max_abs_diff = -math.inf + max_rel_diff = -math.inf + different_ids = [] + for index in itertools.product(*(range(i) for i in np_array_shape)): + approx_value = get_value_from_nested_list(approx_side_as_seq, index) + other_value = get_value_from_nested_list(other_side_as_array, index) + if approx_value != other_value: + abs_diff = abs(approx_value.expected - other_value) + max_abs_diff = max(max_abs_diff, abs_diff) + if other_value == 0.0: + max_rel_diff = math.inf + else: + max_rel_diff = max(max_rel_diff, abs_diff / abs(other_value)) + different_ids.append(index) + + message_data = [ + ( + str(index), + str(get_value_from_nested_list(other_side_as_array, index)), + str(get_value_from_nested_list(approx_side_as_seq, index)), + ) + for index in different_ids + ] + return _compare_approx( + self.expected, + message_data, + number_of_elements, + different_ids, + max_abs_diff, + max_rel_diff, + ) + + def __eq__(self, actual) -> bool: + import numpy as np + + # self.expected is supposed to always be an array here. + + if not np.isscalar(actual): + try: + actual = np.asarray(actual) + except Exception as e: + raise TypeError(f"cannot compare '{actual}' to numpy.ndarray") from e + + if not np.isscalar(actual) and actual.shape != self.expected.shape: + return False + + return super().__eq__(actual) + + def _yield_comparisons(self, actual): + import numpy as np + + # `actual` can either be a numpy array or a scalar, it is treated in + # `__eq__` before being passed to `ApproxBase.__eq__`, which is the + # only method that calls this one. + + if np.isscalar(actual): + for i in np.ndindex(self.expected.shape): + yield actual, self.expected[i].item() + else: + for i in np.ndindex(self.expected.shape): + yield actual[i].item(), self.expected[i].item() + + +class ApproxMapping(ApproxBase): + """Perform approximate comparisons where the expected value is a mapping + with numeric values (the keys can be anything).""" + + def __repr__(self) -> str: + return f"approx({({k: self._approx_scalar(v) for k, v in self.expected.items()})!r})" + + def _repr_compare(self, other_side: Mapping[object, float]) -> list[str]: + import math + + approx_side_as_map = { + k: self._approx_scalar(v) for k, v in self.expected.items() + } + + number_of_elements = len(approx_side_as_map) + max_abs_diff = -math.inf + max_rel_diff = -math.inf + different_ids = [] + for (approx_key, approx_value), other_value in zip( + approx_side_as_map.items(), other_side.values() + ): + if approx_value != other_value: + if approx_value.expected is not None and other_value is not None: + try: + max_abs_diff = max( + max_abs_diff, abs(approx_value.expected - other_value) + ) + if approx_value.expected == 0.0: + max_rel_diff = math.inf + else: + max_rel_diff = max( + max_rel_diff, + abs( + (approx_value.expected - other_value) + / approx_value.expected + ), + ) + except ZeroDivisionError: + pass + different_ids.append(approx_key) + + message_data = [ + (str(key), str(other_side[key]), str(approx_side_as_map[key])) + for key in different_ids + ] + + return _compare_approx( + self.expected, + message_data, + number_of_elements, + different_ids, + max_abs_diff, + max_rel_diff, + ) + + def __eq__(self, actual) -> bool: + try: + if set(actual.keys()) != set(self.expected.keys()): + return False + except AttributeError: + return False + + return super().__eq__(actual) + + def _yield_comparisons(self, actual): + for k in self.expected.keys(): + yield actual[k], self.expected[k] + + def _check_type(self) -> None: + __tracebackhide__ = True + for key, value in self.expected.items(): + if isinstance(value, type(self.expected)): + msg = "pytest.approx() does not support nested dictionaries: key={!r} value={!r}\n full mapping={}" + raise TypeError(msg.format(key, value, pprint.pformat(self.expected))) + + +class ApproxSequenceLike(ApproxBase): + """Perform approximate comparisons where the expected value is a sequence of numbers.""" + + def __repr__(self) -> str: + seq_type = type(self.expected) + if seq_type not in (tuple, list): + seq_type = list + return f"approx({seq_type(self._approx_scalar(x) for x in self.expected)!r})" + + def _repr_compare(self, other_side: Sequence[float]) -> list[str]: + import math + + if len(self.expected) != len(other_side): + return [ + "Impossible to compare lists with different sizes.", + f"Lengths: {len(self.expected)} and {len(other_side)}", + ] + + approx_side_as_map = _recursive_sequence_map(self._approx_scalar, self.expected) + + number_of_elements = len(approx_side_as_map) + max_abs_diff = -math.inf + max_rel_diff = -math.inf + different_ids = [] + for i, (approx_value, other_value) in enumerate( + zip(approx_side_as_map, other_side) + ): + if approx_value != other_value: + abs_diff = abs(approx_value.expected - other_value) + max_abs_diff = max(max_abs_diff, abs_diff) + if other_value == 0.0: + max_rel_diff = math.inf + else: + max_rel_diff = max(max_rel_diff, abs_diff / abs(other_value)) + different_ids.append(i) + + message_data = [ + (str(i), str(other_side[i]), str(approx_side_as_map[i])) + for i in different_ids + ] + + return _compare_approx( + self.expected, + message_data, + number_of_elements, + different_ids, + max_abs_diff, + max_rel_diff, + ) + + def __eq__(self, actual) -> bool: + try: + if len(actual) != len(self.expected): + return False + except TypeError: + return False + return super().__eq__(actual) + + def _yield_comparisons(self, actual): + return zip(actual, self.expected) + + def _check_type(self) -> None: + __tracebackhide__ = True + for index, x in enumerate(self.expected): + if isinstance(x, type(self.expected)): + msg = "pytest.approx() does not support nested data structures: {!r} at index {}\n full sequence: {}" + raise TypeError(msg.format(x, index, pprint.pformat(self.expected))) + + +class ApproxScalar(ApproxBase): + """Perform approximate comparisons where the expected value is a single number.""" + + # Using Real should be better than this Union, but not possible yet: + # https://github.com/python/typeshed/pull/3108 + DEFAULT_ABSOLUTE_TOLERANCE: float | Decimal = 1e-12 + DEFAULT_RELATIVE_TOLERANCE: float | Decimal = 1e-6 + + def __repr__(self) -> str: + """Return a string communicating both the expected value and the + tolerance for the comparison being made. + + For example, ``1.0 ± 1e-6``, ``(3+4j) ± 5e-6 ∠ ±180°``. + """ + # Don't show a tolerance for values that aren't compared using + # tolerances, i.e. non-numerics and infinities. Need to call abs to + # handle complex numbers, e.g. (inf + 1j). + if ( + isinstance(self.expected, bool) + or (not isinstance(self.expected, (Complex, Decimal))) + or math.isinf(abs(self.expected) or isinstance(self.expected, bool)) + ): + return str(self.expected) + + # If a sensible tolerance can't be calculated, self.tolerance will + # raise a ValueError. In this case, display '???'. + try: + vetted_tolerance = f"{self.tolerance:.1e}" + if ( + isinstance(self.expected, Complex) + and self.expected.imag + and not math.isinf(self.tolerance) + ): + vetted_tolerance += " ∠ ±180°" + except ValueError: + vetted_tolerance = "???" + + return f"{self.expected} ± {vetted_tolerance}" + + def __eq__(self, actual) -> bool: + """Return whether the given value is equal to the expected value + within the pre-specified tolerance.""" + asarray = _as_numpy_array(actual) + if asarray is not None: + # Call ``__eq__()`` manually to prevent infinite-recursion with + # numpy<1.13. See #3748. + return all(self.__eq__(a) for a in asarray.flat) + + # Short-circuit exact equality, except for bool + if isinstance(self.expected, bool) and not isinstance(actual, bool): + return False + elif actual == self.expected: + return True + + # If either type is non-numeric, fall back to strict equality. + # NB: we need Complex, rather than just Number, to ensure that __abs__, + # __sub__, and __float__ are defined. Also, consider bool to be + # nonnumeric, even though it has the required arithmetic. + if isinstance(self.expected, bool) or not ( + isinstance(self.expected, (Complex, Decimal)) + and isinstance(actual, (Complex, Decimal)) + ): + return False + + # Allow the user to control whether NaNs are considered equal to each + # other or not. The abs() calls are for compatibility with complex + # numbers. + if math.isnan(abs(self.expected)): + return self.nan_ok and math.isnan(abs(actual)) + + # Infinity shouldn't be approximately equal to anything but itself, but + # if there's a relative tolerance, it will be infinite and infinity + # will seem approximately equal to everything. The equal-to-itself + # case would have been short circuited above, so here we can just + # return false if the expected value is infinite. The abs() call is + # for compatibility with complex numbers. + if math.isinf(abs(self.expected)): + return False + + # Return true if the two numbers are within the tolerance. + result: bool = abs(self.expected - actual) <= self.tolerance + return result + + # Ignore type because of https://github.com/python/mypy/issues/4266. + __hash__ = None # type: ignore + + @property + def tolerance(self): + """Return the tolerance for the comparison. + + This could be either an absolute tolerance or a relative tolerance, + depending on what the user specified or which would be larger. + """ + + def set_default(x, default): + return x if x is not None else default + + # Figure out what the absolute tolerance should be. ``self.abs`` is + # either None or a value specified by the user. + absolute_tolerance = set_default(self.abs, self.DEFAULT_ABSOLUTE_TOLERANCE) + + if absolute_tolerance < 0: + raise ValueError( + f"absolute tolerance can't be negative: {absolute_tolerance}" + ) + if math.isnan(absolute_tolerance): + raise ValueError("absolute tolerance can't be NaN.") + + # If the user specified an absolute tolerance but not a relative one, + # just return the absolute tolerance. + if self.rel is None: + if self.abs is not None: + return absolute_tolerance + + # Figure out what the relative tolerance should be. ``self.rel`` is + # either None or a value specified by the user. This is done after + # we've made sure the user didn't ask for an absolute tolerance only, + # because we don't want to raise errors about the relative tolerance if + # we aren't even going to use it. + relative_tolerance = set_default( + self.rel, self.DEFAULT_RELATIVE_TOLERANCE + ) * abs(self.expected) + + if relative_tolerance < 0: + raise ValueError( + f"relative tolerance can't be negative: {relative_tolerance}" + ) + if math.isnan(relative_tolerance): + raise ValueError("relative tolerance can't be NaN.") + + # Return the larger of the relative and absolute tolerances. + return max(relative_tolerance, absolute_tolerance) + + +class ApproxDecimal(ApproxScalar): + """Perform approximate comparisons where the expected value is a Decimal.""" + + DEFAULT_ABSOLUTE_TOLERANCE = Decimal("1e-12") + DEFAULT_RELATIVE_TOLERANCE = Decimal("1e-6") + + +def approx(expected, rel=None, abs=None, nan_ok: bool = False) -> ApproxBase: + """Assert that two numbers (or two ordered sequences of numbers) are equal to each other + within some tolerance. + + Due to the :doc:`python:tutorial/floatingpoint`, numbers that we + would intuitively expect to be equal are not always so:: + + >>> 0.1 + 0.2 == 0.3 + False + + This problem is commonly encountered when writing tests, e.g. when making + sure that floating-point values are what you expect them to be. One way to + deal with this problem is to assert that two floating-point numbers are + equal to within some appropriate tolerance:: + + >>> abs((0.1 + 0.2) - 0.3) < 1e-6 + True + + However, comparisons like this are tedious to write and difficult to + understand. Furthermore, absolute comparisons like the one above are + usually discouraged because there's no tolerance that works well for all + situations. ``1e-6`` is good for numbers around ``1``, but too small for + very big numbers and too big for very small ones. It's better to express + the tolerance as a fraction of the expected value, but relative comparisons + like that are even more difficult to write correctly and concisely. + + The ``approx`` class performs floating-point comparisons using a syntax + that's as intuitive as possible:: + + >>> from pytest import approx + >>> 0.1 + 0.2 == approx(0.3) + True + + The same syntax also works for ordered sequences of numbers:: + + >>> (0.1 + 0.2, 0.2 + 0.4) == approx((0.3, 0.6)) + True + + ``numpy`` arrays:: + + >>> import numpy as np # doctest: +SKIP + >>> np.array([0.1, 0.2]) + np.array([0.2, 0.4]) == approx(np.array([0.3, 0.6])) # doctest: +SKIP + True + + And for a ``numpy`` array against a scalar:: + + >>> import numpy as np # doctest: +SKIP + >>> np.array([0.1, 0.2]) + np.array([0.2, 0.1]) == approx(0.3) # doctest: +SKIP + True + + Only ordered sequences are supported, because ``approx`` needs + to infer the relative position of the sequences without ambiguity. This means + ``sets`` and other unordered sequences are not supported. + + Finally, dictionary *values* can also be compared:: + + >>> {'a': 0.1 + 0.2, 'b': 0.2 + 0.4} == approx({'a': 0.3, 'b': 0.6}) + True + + The comparison will be true if both mappings have the same keys and their + respective values match the expected tolerances. + + **Tolerances** + + By default, ``approx`` considers numbers within a relative tolerance of + ``1e-6`` (i.e. one part in a million) of its expected value to be equal. + This treatment would lead to surprising results if the expected value was + ``0.0``, because nothing but ``0.0`` itself is relatively close to ``0.0``. + To handle this case less surprisingly, ``approx`` also considers numbers + within an absolute tolerance of ``1e-12`` of its expected value to be + equal. Infinity and NaN are special cases. Infinity is only considered + equal to itself, regardless of the relative tolerance. NaN is not + considered equal to anything by default, but you can make it be equal to + itself by setting the ``nan_ok`` argument to True. (This is meant to + facilitate comparing arrays that use NaN to mean "no data".) + + Both the relative and absolute tolerances can be changed by passing + arguments to the ``approx`` constructor:: + + >>> 1.0001 == approx(1) + False + >>> 1.0001 == approx(1, rel=1e-3) + True + >>> 1.0001 == approx(1, abs=1e-3) + True + + If you specify ``abs`` but not ``rel``, the comparison will not consider + the relative tolerance at all. In other words, two numbers that are within + the default relative tolerance of ``1e-6`` will still be considered unequal + if they exceed the specified absolute tolerance. If you specify both + ``abs`` and ``rel``, the numbers will be considered equal if either + tolerance is met:: + + >>> 1 + 1e-8 == approx(1) + True + >>> 1 + 1e-8 == approx(1, abs=1e-12) + False + >>> 1 + 1e-8 == approx(1, rel=1e-6, abs=1e-12) + True + + You can also use ``approx`` to compare nonnumeric types, or dicts and + sequences containing nonnumeric types, in which case it falls back to + strict equality. This can be useful for comparing dicts and sequences that + can contain optional values:: + + >>> {"required": 1.0000005, "optional": None} == approx({"required": 1, "optional": None}) + True + >>> [None, 1.0000005] == approx([None,1]) + True + >>> ["foo", 1.0000005] == approx([None,1]) + False + + If you're thinking about using ``approx``, then you might want to know how + it compares to other good ways of comparing floating-point numbers. All of + these algorithms are based on relative and absolute tolerances and should + agree for the most part, but they do have meaningful differences: + + - ``math.isclose(a, b, rel_tol=1e-9, abs_tol=0.0)``: True if the relative + tolerance is met w.r.t. either ``a`` or ``b`` or if the absolute + tolerance is met. Because the relative tolerance is calculated w.r.t. + both ``a`` and ``b``, this test is symmetric (i.e. neither ``a`` nor + ``b`` is a "reference value"). You have to specify an absolute tolerance + if you want to compare to ``0.0`` because there is no tolerance by + default. More information: :py:func:`math.isclose`. + + - ``numpy.isclose(a, b, rtol=1e-5, atol=1e-8)``: True if the difference + between ``a`` and ``b`` is less that the sum of the relative tolerance + w.r.t. ``b`` and the absolute tolerance. Because the relative tolerance + is only calculated w.r.t. ``b``, this test is asymmetric and you can + think of ``b`` as the reference value. Support for comparing sequences + is provided by :py:func:`numpy.allclose`. More information: + :std:doc:`numpy:reference/generated/numpy.isclose`. + + - ``unittest.TestCase.assertAlmostEqual(a, b)``: True if ``a`` and ``b`` + are within an absolute tolerance of ``1e-7``. No relative tolerance is + considered , so this function is not appropriate for very large or very + small numbers. Also, it's only available in subclasses of ``unittest.TestCase`` + and it's ugly because it doesn't follow PEP8. More information: + :py:meth:`unittest.TestCase.assertAlmostEqual`. + + - ``a == pytest.approx(b, rel=1e-6, abs=1e-12)``: True if the relative + tolerance is met w.r.t. ``b`` or if the absolute tolerance is met. + Because the relative tolerance is only calculated w.r.t. ``b``, this test + is asymmetric and you can think of ``b`` as the reference value. In the + special case that you explicitly specify an absolute tolerance but not a + relative tolerance, only the absolute tolerance is considered. + + .. note:: + + ``approx`` can handle numpy arrays, but we recommend the + specialised test helpers in :std:doc:`numpy:reference/routines.testing` + if you need support for comparisons, NaNs, or ULP-based tolerances. + + To match strings using regex, you can use + `Matches `_ + from the + `re_assert package `_. + + .. warning:: + + .. versionchanged:: 3.2 + + In order to avoid inconsistent behavior, :py:exc:`TypeError` is + raised for ``>``, ``>=``, ``<`` and ``<=`` comparisons. + The example below illustrates the problem:: + + assert approx(0.1) > 0.1 + 1e-10 # calls approx(0.1).__gt__(0.1 + 1e-10) + assert 0.1 + 1e-10 > approx(0.1) # calls approx(0.1).__lt__(0.1 + 1e-10) + + In the second example one expects ``approx(0.1).__le__(0.1 + 1e-10)`` + to be called. But instead, ``approx(0.1).__lt__(0.1 + 1e-10)`` is used to + comparison. This is because the call hierarchy of rich comparisons + follows a fixed behavior. More information: :py:meth:`object.__ge__` + + .. versionchanged:: 3.7.1 + ``approx`` raises ``TypeError`` when it encounters a dict value or + sequence element of nonnumeric type. + + .. versionchanged:: 6.1.0 + ``approx`` falls back to strict equality for nonnumeric types instead + of raising ``TypeError``. + """ + # Delegate the comparison to a class that knows how to deal with the type + # of the expected value (e.g. int, float, list, dict, numpy.array, etc). + # + # The primary responsibility of these classes is to implement ``__eq__()`` + # and ``__repr__()``. The former is used to actually check if some + # "actual" value is equivalent to the given expected value within the + # allowed tolerance. The latter is used to show the user the expected + # value and tolerance, in the case that a test failed. + # + # The actual logic for making approximate comparisons can be found in + # ApproxScalar, which is used to compare individual numbers. All of the + # other Approx classes eventually delegate to this class. The ApproxBase + # class provides some convenient methods and overloads, but isn't really + # essential. + + __tracebackhide__ = True + + if isinstance(expected, Decimal): + cls: type[ApproxBase] = ApproxDecimal + elif isinstance(expected, Mapping): + cls = ApproxMapping + elif _is_numpy_array(expected): + expected = _as_numpy_array(expected) + cls = ApproxNumpy + elif _is_sequence_like(expected): + cls = ApproxSequenceLike + elif isinstance(expected, Collection) and not isinstance(expected, (str, bytes)): + msg = f"pytest.approx() only supports ordered sequences, but got: {expected!r}" + raise TypeError(msg) + else: + cls = ApproxScalar + + return cls(expected, rel, abs, nan_ok) + + +def _is_sequence_like(expected: object) -> bool: + return ( + hasattr(expected, "__getitem__") + and isinstance(expected, Sized) + and not isinstance(expected, (str, bytes)) + ) + + +def _is_numpy_array(obj: object) -> bool: + """ + Return true if the given object is implicitly convertible to ndarray, + and numpy is already imported. + """ + return _as_numpy_array(obj) is not None + + +def _as_numpy_array(obj: object) -> ndarray | None: + """ + Return an ndarray if the given object is implicitly convertible to ndarray, + and numpy is already imported, otherwise None. + """ + import sys + + np: Any = sys.modules.get("numpy") + if np is not None: + # avoid infinite recursion on numpy scalars, which have __array__ + if np.isscalar(obj): + return None + elif isinstance(obj, np.ndarray): + return obj + elif hasattr(obj, "__array__") or hasattr("obj", "__array_interface__"): + return np.asarray(obj) + return None + + +# builtin pytest.raises helper + +E = TypeVar("E", bound=BaseException) + + +@overload +def raises( + expected_exception: type[E] | tuple[type[E], ...], + *, + match: str | Pattern[str] | None = ..., +) -> RaisesContext[E]: ... + + +@overload +def raises( + expected_exception: type[E] | tuple[type[E], ...], + func: Callable[..., Any], + *args: Any, + **kwargs: Any, +) -> _pytest._code.ExceptionInfo[E]: ... + + +def raises( + expected_exception: type[E] | tuple[type[E], ...], *args: Any, **kwargs: Any +) -> RaisesContext[E] | _pytest._code.ExceptionInfo[E]: + r"""Assert that a code block/function call raises an exception type, or one of its subclasses. + + :param expected_exception: + The expected exception type, or a tuple if one of multiple possible + exception types are expected. Note that subclasses of the passed exceptions + will also match. + + :kwparam str | re.Pattern[str] | None match: + If specified, a string containing a regular expression, + or a regular expression object, that is tested against the string + representation of the exception and its :pep:`678` `__notes__` + using :func:`re.search`. + + To match a literal string that may contain :ref:`special characters + `, the pattern can first be escaped with :func:`re.escape`. + + (This is only used when ``pytest.raises`` is used as a context manager, + and passed through to the function otherwise. + When using ``pytest.raises`` as a function, you can use: + ``pytest.raises(Exc, func, match="passed on").match("my pattern")``.) + + Use ``pytest.raises`` as a context manager, which will capture the exception of the given + type, or any of its subclasses:: + + >>> import pytest + >>> with pytest.raises(ZeroDivisionError): + ... 1/0 + + If the code block does not raise the expected exception (:class:`ZeroDivisionError` in the example + above), or no exception at all, the check will fail instead. + + You can also use the keyword argument ``match`` to assert that the + exception matches a text or regex:: + + >>> with pytest.raises(ValueError, match='must be 0 or None'): + ... raise ValueError("value must be 0 or None") + + >>> with pytest.raises(ValueError, match=r'must be \d+$'): + ... raise ValueError("value must be 42") + + The ``match`` argument searches the formatted exception string, which includes any + `PEP-678 `__ ``__notes__``: + + >>> with pytest.raises(ValueError, match=r"had a note added"): # doctest: +SKIP + ... e = ValueError("value must be 42") + ... e.add_note("had a note added") + ... raise e + + The context manager produces an :class:`ExceptionInfo` object which can be used to inspect the + details of the captured exception:: + + >>> with pytest.raises(ValueError) as exc_info: + ... raise ValueError("value must be 42") + >>> assert exc_info.type is ValueError + >>> assert exc_info.value.args[0] == "value must be 42" + + .. warning:: + + Given that ``pytest.raises`` matches subclasses, be wary of using it to match :class:`Exception` like this:: + + with pytest.raises(Exception): # Careful, this will catch ANY exception raised. + some_function() + + Because :class:`Exception` is the base class of almost all exceptions, it is easy for this to hide + real bugs, where the user wrote this expecting a specific exception, but some other exception is being + raised due to a bug introduced during a refactoring. + + Avoid using ``pytest.raises`` to catch :class:`Exception` unless certain that you really want to catch + **any** exception raised. + + .. note:: + + When using ``pytest.raises`` as a context manager, it's worthwhile to + note that normal context manager rules apply and that the exception + raised *must* be the final line in the scope of the context manager. + Lines of code after that, within the scope of the context manager will + not be executed. For example:: + + >>> value = 15 + >>> with pytest.raises(ValueError) as exc_info: + ... if value > 10: + ... raise ValueError("value must be <= 10") + ... assert exc_info.type is ValueError # This will not execute. + + Instead, the following approach must be taken (note the difference in + scope):: + + >>> with pytest.raises(ValueError) as exc_info: + ... if value > 10: + ... raise ValueError("value must be <= 10") + ... + >>> assert exc_info.type is ValueError + + **Using with** ``pytest.mark.parametrize`` + + When using :ref:`pytest.mark.parametrize ref` + it is possible to parametrize tests such that + some runs raise an exception and others do not. + + See :ref:`parametrizing_conditional_raising` for an example. + + .. seealso:: + + :ref:`assertraises` for more examples and detailed discussion. + + **Legacy form** + + It is possible to specify a callable by passing a to-be-called lambda:: + + >>> raises(ZeroDivisionError, lambda: 1/0) + + + or you can specify an arbitrary callable with arguments:: + + >>> def f(x): return 1/x + ... + >>> raises(ZeroDivisionError, f, 0) + + >>> raises(ZeroDivisionError, f, x=0) + + + The form above is fully supported but discouraged for new code because the + context manager form is regarded as more readable and less error-prone. + + .. note:: + Similar to caught exception objects in Python, explicitly clearing + local references to returned ``ExceptionInfo`` objects can + help the Python interpreter speed up its garbage collection. + + Clearing those references breaks a reference cycle + (``ExceptionInfo`` --> caught exception --> frame stack raising + the exception --> current frame stack --> local variables --> + ``ExceptionInfo``) which makes Python keep all objects referenced + from that cycle (including all local variables in the current + frame) alive until the next cyclic garbage collection run. + More detailed information can be found in the official Python + documentation for :ref:`the try statement `. + """ + __tracebackhide__ = True + + if not expected_exception: + raise ValueError( + f"Expected an exception type or a tuple of exception types, but got `{expected_exception!r}`. " + f"Raising exceptions is already understood as failing the test, so you don't need " + f"any special code to say 'this should never raise an exception'." + ) + if isinstance(expected_exception, type): + expected_exceptions: tuple[type[E], ...] = (expected_exception,) + else: + expected_exceptions = expected_exception + for exc in expected_exceptions: + if not isinstance(exc, type) or not issubclass(exc, BaseException): + msg = "expected exception must be a BaseException type, not {}" # type: ignore[unreachable] + not_a = exc.__name__ if isinstance(exc, type) else type(exc).__name__ + raise TypeError(msg.format(not_a)) + + message = f"DID NOT RAISE {expected_exception}" + + if not args: + match: str | Pattern[str] | None = kwargs.pop("match", None) + if kwargs: + msg = "Unexpected keyword arguments passed to pytest.raises: " + msg += ", ".join(sorted(kwargs)) + msg += "\nUse context-manager form instead?" + raise TypeError(msg) + return RaisesContext(expected_exception, message, match) + else: + func = args[0] + if not callable(func): + raise TypeError(f"{func!r} object (type: {type(func)}) must be callable") + try: + func(*args[1:], **kwargs) + except expected_exception as e: + return _pytest._code.ExceptionInfo.from_exception(e) + fail(message) + + +# This doesn't work with mypy for now. Use fail.Exception instead. +raises.Exception = fail.Exception # type: ignore + + +@final +class RaisesContext(ContextManager[_pytest._code.ExceptionInfo[E]]): + def __init__( + self, + expected_exception: type[E] | tuple[type[E], ...], + message: str, + match_expr: str | Pattern[str] | None = None, + ) -> None: + self.expected_exception = expected_exception + self.message = message + self.match_expr = match_expr + self.excinfo: _pytest._code.ExceptionInfo[E] | None = None + if self.match_expr is not None: + re_error = None + try: + re.compile(self.match_expr) + except re.error as e: + re_error = e + if re_error is not None: + fail(f"Invalid regex pattern provided to 'match': {re_error}") + + def __enter__(self) -> _pytest._code.ExceptionInfo[E]: + self.excinfo = _pytest._code.ExceptionInfo.for_later() + return self.excinfo + + def __exit__( + self, + exc_type: type[BaseException] | None, + exc_val: BaseException | None, + exc_tb: TracebackType | None, + ) -> bool: + __tracebackhide__ = True + if exc_type is None: + fail(self.message) + assert self.excinfo is not None + if not issubclass(exc_type, self.expected_exception): + return False + # Cast to narrow the exception type now that it's verified. + exc_info = cast(Tuple[Type[E], E, TracebackType], (exc_type, exc_val, exc_tb)) + self.excinfo.fill_unfilled(exc_info) + if self.match_expr is not None: + self.excinfo.match(self.match_expr) + return True diff --git a/.venv/lib/python3.11/site-packages/_pytest/recwarn.py b/.venv/lib/python3.11/site-packages/_pytest/recwarn.py new file mode 100644 index 0000000000000000000000000000000000000000..0dc002edd9410b9120a518e31972b978e54b57b1 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/recwarn.py @@ -0,0 +1,364 @@ +# mypy: allow-untyped-defs +"""Record warnings during test function execution.""" + +from __future__ import annotations + +from pprint import pformat +import re +from types import TracebackType +from typing import Any +from typing import Callable +from typing import final +from typing import Generator +from typing import Iterator +from typing import overload +from typing import Pattern +from typing import TYPE_CHECKING +from typing import TypeVar + + +if TYPE_CHECKING: + from typing_extensions import Self + +import warnings + +from _pytest.deprecated import check_ispytest +from _pytest.fixtures import fixture +from _pytest.outcomes import Exit +from _pytest.outcomes import fail + + +T = TypeVar("T") + + +@fixture +def recwarn() -> Generator[WarningsRecorder]: + """Return a :class:`WarningsRecorder` instance that records all warnings emitted by test functions. + + See :ref:`warnings` for information on warning categories. + """ + wrec = WarningsRecorder(_ispytest=True) + with wrec: + warnings.simplefilter("default") + yield wrec + + +@overload +def deprecated_call(*, match: str | Pattern[str] | None = ...) -> WarningsRecorder: ... + + +@overload +def deprecated_call(func: Callable[..., T], *args: Any, **kwargs: Any) -> T: ... + + +def deprecated_call( + func: Callable[..., Any] | None = None, *args: Any, **kwargs: Any +) -> WarningsRecorder | Any: + """Assert that code produces a ``DeprecationWarning`` or ``PendingDeprecationWarning`` or ``FutureWarning``. + + This function can be used as a context manager:: + + >>> import warnings + >>> def api_call_v2(): + ... warnings.warn('use v3 of this api', DeprecationWarning) + ... return 200 + + >>> import pytest + >>> with pytest.deprecated_call(): + ... assert api_call_v2() == 200 + + It can also be used by passing a function and ``*args`` and ``**kwargs``, + in which case it will ensure calling ``func(*args, **kwargs)`` produces one of + the warnings types above. The return value is the return value of the function. + + In the context manager form you may use the keyword argument ``match`` to assert + that the warning matches a text or regex. + + The context manager produces a list of :class:`warnings.WarningMessage` objects, + one for each warning raised. + """ + __tracebackhide__ = True + if func is not None: + args = (func, *args) + return warns( + (DeprecationWarning, PendingDeprecationWarning, FutureWarning), *args, **kwargs + ) + + +@overload +def warns( + expected_warning: type[Warning] | tuple[type[Warning], ...] = ..., + *, + match: str | Pattern[str] | None = ..., +) -> WarningsChecker: ... + + +@overload +def warns( + expected_warning: type[Warning] | tuple[type[Warning], ...], + func: Callable[..., T], + *args: Any, + **kwargs: Any, +) -> T: ... + + +def warns( + expected_warning: type[Warning] | tuple[type[Warning], ...] = Warning, + *args: Any, + match: str | Pattern[str] | None = None, + **kwargs: Any, +) -> WarningsChecker | Any: + r"""Assert that code raises a particular class of warning. + + Specifically, the parameter ``expected_warning`` can be a warning class or tuple + of warning classes, and the code inside the ``with`` block must issue at least one + warning of that class or classes. + + This helper produces a list of :class:`warnings.WarningMessage` objects, one for + each warning emitted (regardless of whether it is an ``expected_warning`` or not). + Since pytest 8.0, unmatched warnings are also re-emitted when the context closes. + + This function can be used as a context manager:: + + >>> import pytest + >>> with pytest.warns(RuntimeWarning): + ... warnings.warn("my warning", RuntimeWarning) + + In the context manager form you may use the keyword argument ``match`` to assert + that the warning matches a text or regex:: + + >>> with pytest.warns(UserWarning, match='must be 0 or None'): + ... warnings.warn("value must be 0 or None", UserWarning) + + >>> with pytest.warns(UserWarning, match=r'must be \d+$'): + ... warnings.warn("value must be 42", UserWarning) + + >>> with pytest.warns(UserWarning): # catch re-emitted warning + ... with pytest.warns(UserWarning, match=r'must be \d+$'): + ... warnings.warn("this is not here", UserWarning) + Traceback (most recent call last): + ... + Failed: DID NOT WARN. No warnings of type ...UserWarning... were emitted... + + **Using with** ``pytest.mark.parametrize`` + + When using :ref:`pytest.mark.parametrize ref` it is possible to parametrize tests + such that some runs raise a warning and others do not. + + This could be achieved in the same way as with exceptions, see + :ref:`parametrizing_conditional_raising` for an example. + + """ + __tracebackhide__ = True + if not args: + if kwargs: + argnames = ", ".join(sorted(kwargs)) + raise TypeError( + f"Unexpected keyword arguments passed to pytest.warns: {argnames}" + "\nUse context-manager form instead?" + ) + return WarningsChecker(expected_warning, match_expr=match, _ispytest=True) + else: + func = args[0] + if not callable(func): + raise TypeError(f"{func!r} object (type: {type(func)}) must be callable") + with WarningsChecker(expected_warning, _ispytest=True): + return func(*args[1:], **kwargs) + + +class WarningsRecorder(warnings.catch_warnings): # type:ignore[type-arg] + """A context manager to record raised warnings. + + Each recorded warning is an instance of :class:`warnings.WarningMessage`. + + Adapted from `warnings.catch_warnings`. + + .. note:: + ``DeprecationWarning`` and ``PendingDeprecationWarning`` are treated + differently; see :ref:`ensuring_function_triggers`. + + """ + + def __init__(self, *, _ispytest: bool = False) -> None: + check_ispytest(_ispytest) + super().__init__(record=True) + self._entered = False + self._list: list[warnings.WarningMessage] = [] + + @property + def list(self) -> list[warnings.WarningMessage]: + """The list of recorded warnings.""" + return self._list + + def __getitem__(self, i: int) -> warnings.WarningMessage: + """Get a recorded warning by index.""" + return self._list[i] + + def __iter__(self) -> Iterator[warnings.WarningMessage]: + """Iterate through the recorded warnings.""" + return iter(self._list) + + def __len__(self) -> int: + """The number of recorded warnings.""" + return len(self._list) + + def pop(self, cls: type[Warning] = Warning) -> warnings.WarningMessage: + """Pop the first recorded warning which is an instance of ``cls``, + but not an instance of a child class of any other match. + Raises ``AssertionError`` if there is no match. + """ + best_idx: int | None = None + for i, w in enumerate(self._list): + if w.category == cls: + return self._list.pop(i) # exact match, stop looking + if issubclass(w.category, cls) and ( + best_idx is None + or not issubclass(w.category, self._list[best_idx].category) + ): + best_idx = i + if best_idx is not None: + return self._list.pop(best_idx) + __tracebackhide__ = True + raise AssertionError(f"{cls!r} not found in warning list") + + def clear(self) -> None: + """Clear the list of recorded warnings.""" + self._list[:] = [] + + def __enter__(self) -> Self: + if self._entered: + __tracebackhide__ = True + raise RuntimeError(f"Cannot enter {self!r} twice") + _list = super().__enter__() + # record=True means it's None. + assert _list is not None + self._list = _list + warnings.simplefilter("always") + return self + + def __exit__( + self, + exc_type: type[BaseException] | None, + exc_val: BaseException | None, + exc_tb: TracebackType | None, + ) -> None: + if not self._entered: + __tracebackhide__ = True + raise RuntimeError(f"Cannot exit {self!r} without entering first") + + super().__exit__(exc_type, exc_val, exc_tb) + + # Built-in catch_warnings does not reset entered state so we do it + # manually here for this context manager to become reusable. + self._entered = False + + +@final +class WarningsChecker(WarningsRecorder): + def __init__( + self, + expected_warning: type[Warning] | tuple[type[Warning], ...] = Warning, + match_expr: str | Pattern[str] | None = None, + *, + _ispytest: bool = False, + ) -> None: + check_ispytest(_ispytest) + super().__init__(_ispytest=True) + + msg = "exceptions must be derived from Warning, not %s" + if isinstance(expected_warning, tuple): + for exc in expected_warning: + if not issubclass(exc, Warning): + raise TypeError(msg % type(exc)) + expected_warning_tup = expected_warning + elif isinstance(expected_warning, type) and issubclass( + expected_warning, Warning + ): + expected_warning_tup = (expected_warning,) + else: + raise TypeError(msg % type(expected_warning)) + + self.expected_warning = expected_warning_tup + self.match_expr = match_expr + + def matches(self, warning: warnings.WarningMessage) -> bool: + assert self.expected_warning is not None + return issubclass(warning.category, self.expected_warning) and bool( + self.match_expr is None or re.search(self.match_expr, str(warning.message)) + ) + + def __exit__( + self, + exc_type: type[BaseException] | None, + exc_val: BaseException | None, + exc_tb: TracebackType | None, + ) -> None: + super().__exit__(exc_type, exc_val, exc_tb) + + __tracebackhide__ = True + + # BaseExceptions like pytest.{skip,fail,xfail,exit} or Ctrl-C within + # pytest.warns should *not* trigger "DID NOT WARN" and get suppressed + # when the warning doesn't happen. Control-flow exceptions should always + # propagate. + if exc_val is not None and ( + not isinstance(exc_val, Exception) + # Exit is an Exception, not a BaseException, for some reason. + or isinstance(exc_val, Exit) + ): + return + + def found_str() -> str: + return pformat([record.message for record in self], indent=2) + + try: + if not any(issubclass(w.category, self.expected_warning) for w in self): + fail( + f"DID NOT WARN. No warnings of type {self.expected_warning} were emitted.\n" + f" Emitted warnings: {found_str()}." + ) + elif not any(self.matches(w) for w in self): + fail( + f"DID NOT WARN. No warnings of type {self.expected_warning} matching the regex were emitted.\n" + f" Regex: {self.match_expr}\n" + f" Emitted warnings: {found_str()}." + ) + finally: + # Whether or not any warnings matched, we want to re-emit all unmatched warnings. + for w in self: + if not self.matches(w): + warnings.warn_explicit( + message=w.message, + category=w.category, + filename=w.filename, + lineno=w.lineno, + module=w.__module__, + source=w.source, + ) + + # Currently in Python it is possible to pass other types than an + # `str` message when creating `Warning` instances, however this + # causes an exception when :func:`warnings.filterwarnings` is used + # to filter those warnings. See + # https://github.com/python/cpython/issues/103577 for a discussion. + # While this can be considered a bug in CPython, we put guards in + # pytest as the error message produced without this check in place + # is confusing (#10865). + for w in self: + if type(w.message) is not UserWarning: + # If the warning was of an incorrect type then `warnings.warn()` + # creates a UserWarning. Any other warning must have been specified + # explicitly. + continue + if not w.message.args: + # UserWarning() without arguments must have been specified explicitly. + continue + msg = w.message.args[0] + if isinstance(msg, str): + continue + # It's possible that UserWarning was explicitly specified, and + # its first argument was not a string. But that case can't be + # distinguished from an invalid type. + raise TypeError( + f"Warning must be str or Warning, got {msg!r} (type {type(msg).__name__})" + ) diff --git a/.venv/lib/python3.11/site-packages/_pytest/tmpdir.py b/.venv/lib/python3.11/site-packages/_pytest/tmpdir.py new file mode 100644 index 0000000000000000000000000000000000000000..1731a4b8d0df259f3768730d5506714c2460e89e --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/tmpdir.py @@ -0,0 +1,314 @@ +# mypy: allow-untyped-defs +"""Support for providing temporary directories to test functions.""" + +from __future__ import annotations + +import dataclasses +import os +from pathlib import Path +import re +from shutil import rmtree +import tempfile +from typing import Any +from typing import Dict +from typing import final +from typing import Generator +from typing import Literal + +from .pathlib import cleanup_dead_symlinks +from .pathlib import LOCK_TIMEOUT +from .pathlib import make_numbered_dir +from .pathlib import make_numbered_dir_with_cleanup +from .pathlib import rm_rf +from _pytest.compat import get_user_id +from _pytest.config import Config +from _pytest.config import ExitCode +from _pytest.config import hookimpl +from _pytest.config.argparsing import Parser +from _pytest.deprecated import check_ispytest +from _pytest.fixtures import fixture +from _pytest.fixtures import FixtureRequest +from _pytest.monkeypatch import MonkeyPatch +from _pytest.nodes import Item +from _pytest.reports import TestReport +from _pytest.stash import StashKey + + +tmppath_result_key = StashKey[Dict[str, bool]]() +RetentionType = Literal["all", "failed", "none"] + + +@final +@dataclasses.dataclass +class TempPathFactory: + """Factory for temporary directories under the common base temp directory, + as discussed at :ref:`temporary directory location and retention`. + """ + + _given_basetemp: Path | None + # pluggy TagTracerSub, not currently exposed, so Any. + _trace: Any + _basetemp: Path | None + _retention_count: int + _retention_policy: RetentionType + + def __init__( + self, + given_basetemp: Path | None, + retention_count: int, + retention_policy: RetentionType, + trace, + basetemp: Path | None = None, + *, + _ispytest: bool = False, + ) -> None: + check_ispytest(_ispytest) + if given_basetemp is None: + self._given_basetemp = None + else: + # Use os.path.abspath() to get absolute path instead of resolve() as it + # does not work the same in all platforms (see #4427). + # Path.absolute() exists, but it is not public (see https://bugs.python.org/issue25012). + self._given_basetemp = Path(os.path.abspath(str(given_basetemp))) + self._trace = trace + self._retention_count = retention_count + self._retention_policy = retention_policy + self._basetemp = basetemp + + @classmethod + def from_config( + cls, + config: Config, + *, + _ispytest: bool = False, + ) -> TempPathFactory: + """Create a factory according to pytest configuration. + + :meta private: + """ + check_ispytest(_ispytest) + count = int(config.getini("tmp_path_retention_count")) + if count < 0: + raise ValueError( + f"tmp_path_retention_count must be >= 0. Current input: {count}." + ) + + policy = config.getini("tmp_path_retention_policy") + if policy not in ("all", "failed", "none"): + raise ValueError( + f"tmp_path_retention_policy must be either all, failed, none. Current input: {policy}." + ) + + return cls( + given_basetemp=config.option.basetemp, + trace=config.trace.get("tmpdir"), + retention_count=count, + retention_policy=policy, + _ispytest=True, + ) + + def _ensure_relative_to_basetemp(self, basename: str) -> str: + basename = os.path.normpath(basename) + if (self.getbasetemp() / basename).resolve().parent != self.getbasetemp(): + raise ValueError(f"{basename} is not a normalized and relative path") + return basename + + def mktemp(self, basename: str, numbered: bool = True) -> Path: + """Create a new temporary directory managed by the factory. + + :param basename: + Directory base name, must be a relative path. + + :param numbered: + If ``True``, ensure the directory is unique by adding a numbered + suffix greater than any existing one: ``basename="foo-"`` and ``numbered=True`` + means that this function will create directories named ``"foo-0"``, + ``"foo-1"``, ``"foo-2"`` and so on. + + :returns: + The path to the new directory. + """ + basename = self._ensure_relative_to_basetemp(basename) + if not numbered: + p = self.getbasetemp().joinpath(basename) + p.mkdir(mode=0o700) + else: + p = make_numbered_dir(root=self.getbasetemp(), prefix=basename, mode=0o700) + self._trace("mktemp", p) + return p + + def getbasetemp(self) -> Path: + """Return the base temporary directory, creating it if needed. + + :returns: + The base temporary directory. + """ + if self._basetemp is not None: + return self._basetemp + + if self._given_basetemp is not None: + basetemp = self._given_basetemp + if basetemp.exists(): + rm_rf(basetemp) + basetemp.mkdir(mode=0o700) + basetemp = basetemp.resolve() + else: + from_env = os.environ.get("PYTEST_DEBUG_TEMPROOT") + temproot = Path(from_env or tempfile.gettempdir()).resolve() + user = get_user() or "unknown" + # use a sub-directory in the temproot to speed-up + # make_numbered_dir() call + rootdir = temproot.joinpath(f"pytest-of-{user}") + try: + rootdir.mkdir(mode=0o700, exist_ok=True) + except OSError: + # getuser() likely returned illegal characters for the platform, use unknown back off mechanism + rootdir = temproot.joinpath("pytest-of-unknown") + rootdir.mkdir(mode=0o700, exist_ok=True) + # Because we use exist_ok=True with a predictable name, make sure + # we are the owners, to prevent any funny business (on unix, where + # temproot is usually shared). + # Also, to keep things private, fixup any world-readable temp + # rootdir's permissions. Historically 0o755 was used, so we can't + # just error out on this, at least for a while. + uid = get_user_id() + if uid is not None: + rootdir_stat = rootdir.stat() + if rootdir_stat.st_uid != uid: + raise OSError( + f"The temporary directory {rootdir} is not owned by the current user. " + "Fix this and try again." + ) + if (rootdir_stat.st_mode & 0o077) != 0: + os.chmod(rootdir, rootdir_stat.st_mode & ~0o077) + keep = self._retention_count + if self._retention_policy == "none": + keep = 0 + basetemp = make_numbered_dir_with_cleanup( + prefix="pytest-", + root=rootdir, + keep=keep, + lock_timeout=LOCK_TIMEOUT, + mode=0o700, + ) + assert basetemp is not None, basetemp + self._basetemp = basetemp + self._trace("new basetemp", basetemp) + return basetemp + + +def get_user() -> str | None: + """Return the current user name, or None if getuser() does not work + in the current environment (see #1010).""" + try: + # In some exotic environments, getpass may not be importable. + import getpass + + return getpass.getuser() + except (ImportError, OSError, KeyError): + return None + + +def pytest_configure(config: Config) -> None: + """Create a TempPathFactory and attach it to the config object. + + This is to comply with existing plugins which expect the handler to be + available at pytest_configure time, but ideally should be moved entirely + to the tmp_path_factory session fixture. + """ + mp = MonkeyPatch() + config.add_cleanup(mp.undo) + _tmp_path_factory = TempPathFactory.from_config(config, _ispytest=True) + mp.setattr(config, "_tmp_path_factory", _tmp_path_factory, raising=False) + + +def pytest_addoption(parser: Parser) -> None: + parser.addini( + "tmp_path_retention_count", + help="How many sessions should we keep the `tmp_path` directories, according to `tmp_path_retention_policy`.", + default=3, + ) + + parser.addini( + "tmp_path_retention_policy", + help="Controls which directories created by the `tmp_path` fixture are kept around, based on test outcome. " + "(all/failed/none)", + default="all", + ) + + +@fixture(scope="session") +def tmp_path_factory(request: FixtureRequest) -> TempPathFactory: + """Return a :class:`pytest.TempPathFactory` instance for the test session.""" + # Set dynamically by pytest_configure() above. + return request.config._tmp_path_factory # type: ignore + + +def _mk_tmp(request: FixtureRequest, factory: TempPathFactory) -> Path: + name = request.node.name + name = re.sub(r"[\W]", "_", name) + MAXVAL = 30 + name = name[:MAXVAL] + return factory.mktemp(name, numbered=True) + + +@fixture +def tmp_path( + request: FixtureRequest, tmp_path_factory: TempPathFactory +) -> Generator[Path]: + """Return a temporary directory (as :class:`pathlib.Path` object) + which is unique to each test function invocation. + The temporary directory is created as a subdirectory + of the base temporary directory, with configurable retention, + as discussed in :ref:`temporary directory location and retention`. + """ + path = _mk_tmp(request, tmp_path_factory) + yield path + + # Remove the tmpdir if the policy is "failed" and the test passed. + tmp_path_factory: TempPathFactory = request.session.config._tmp_path_factory # type: ignore + policy = tmp_path_factory._retention_policy + result_dict = request.node.stash[tmppath_result_key] + + if policy == "failed" and result_dict.get("call", True): + # We do a "best effort" to remove files, but it might not be possible due to some leaked resource, + # permissions, etc, in which case we ignore it. + rmtree(path, ignore_errors=True) + + del request.node.stash[tmppath_result_key] + + +def pytest_sessionfinish(session, exitstatus: int | ExitCode): + """After each session, remove base directory if all the tests passed, + the policy is "failed", and the basetemp is not specified by a user. + """ + tmp_path_factory: TempPathFactory = session.config._tmp_path_factory + basetemp = tmp_path_factory._basetemp + if basetemp is None: + return + + policy = tmp_path_factory._retention_policy + if ( + exitstatus == 0 + and policy == "failed" + and tmp_path_factory._given_basetemp is None + ): + if basetemp.is_dir(): + # We do a "best effort" to remove files, but it might not be possible due to some leaked resource, + # permissions, etc, in which case we ignore it. + rmtree(basetemp, ignore_errors=True) + + # Remove dead symlinks. + if basetemp.is_dir(): + cleanup_dead_symlinks(basetemp) + + +@hookimpl(wrapper=True, tryfirst=True) +def pytest_runtest_makereport( + item: Item, call +) -> Generator[None, TestReport, TestReport]: + rep = yield + assert rep.when is not None + empty: dict[str, bool] = {} + item.stash.setdefault(tmppath_result_key, empty)[rep.when] = rep.passed + return rep diff --git a/.venv/lib/python3.11/site-packages/_pytest/unittest.py b/.venv/lib/python3.11/site-packages/_pytest/unittest.py new file mode 100644 index 0000000000000000000000000000000000000000..8cecd4f93398819912b35309d5ad44f61a3f7270 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/_pytest/unittest.py @@ -0,0 +1,435 @@ +# mypy: allow-untyped-defs +"""Discover and run std-library "unittest" style tests.""" + +from __future__ import annotations + +import inspect +import sys +import traceback +import types +from typing import Any +from typing import Callable +from typing import Generator +from typing import Iterable +from typing import Tuple +from typing import Type +from typing import TYPE_CHECKING +from typing import Union + +import _pytest._code +from _pytest.compat import is_async_function +from _pytest.config import hookimpl +from _pytest.fixtures import FixtureRequest +from _pytest.nodes import Collector +from _pytest.nodes import Item +from _pytest.outcomes import exit +from _pytest.outcomes import fail +from _pytest.outcomes import skip +from _pytest.outcomes import xfail +from _pytest.python import Class +from _pytest.python import Function +from _pytest.python import Module +from _pytest.runner import CallInfo +import pytest + + +if sys.version_info[:2] < (3, 11): + from exceptiongroup import ExceptionGroup + +if TYPE_CHECKING: + import unittest + + import twisted.trial.unittest + + +_SysExcInfoType = Union[ + Tuple[Type[BaseException], BaseException, types.TracebackType], + Tuple[None, None, None], +] + + +def pytest_pycollect_makeitem( + collector: Module | Class, name: str, obj: object +) -> UnitTestCase | None: + try: + # Has unittest been imported? + ut = sys.modules["unittest"] + # Is obj a subclass of unittest.TestCase? + # Type ignored because `ut` is an opaque module. + if not issubclass(obj, ut.TestCase): # type: ignore + return None + except Exception: + return None + # Is obj a concrete class? + # Abstract classes can't be instantiated so no point collecting them. + if inspect.isabstract(obj): + return None + # Yes, so let's collect it. + return UnitTestCase.from_parent(collector, name=name, obj=obj) + + +class UnitTestCase(Class): + # Marker for fixturemanger.getfixtureinfo() + # to declare that our children do not support funcargs. + nofuncargs = True + + def newinstance(self): + # TestCase __init__ takes the method (test) name. The TestCase + # constructor treats the name "runTest" as a special no-op, so it can be + # used when a dummy instance is needed. While unittest.TestCase has a + # default, some subclasses omit the default (#9610), so always supply + # it. + return self.obj("runTest") + + def collect(self) -> Iterable[Item | Collector]: + from unittest import TestLoader + + cls = self.obj + if not getattr(cls, "__test__", True): + return + + skipped = _is_skipped(cls) + if not skipped: + self._register_unittest_setup_method_fixture(cls) + self._register_unittest_setup_class_fixture(cls) + self._register_setup_class_fixture() + + self.session._fixturemanager.parsefactories(self.newinstance(), self.nodeid) + + loader = TestLoader() + foundsomething = False + for name in loader.getTestCaseNames(self.obj): + x = getattr(self.obj, name) + if not getattr(x, "__test__", True): + continue + yield TestCaseFunction.from_parent(self, name=name) + foundsomething = True + + if not foundsomething: + runtest = getattr(self.obj, "runTest", None) + if runtest is not None: + ut = sys.modules.get("twisted.trial.unittest", None) + if ut is None or runtest != ut.TestCase.runTest: + yield TestCaseFunction.from_parent(self, name="runTest") + + def _register_unittest_setup_class_fixture(self, cls: type) -> None: + """Register an auto-use fixture to invoke setUpClass and + tearDownClass (#517).""" + setup = getattr(cls, "setUpClass", None) + teardown = getattr(cls, "tearDownClass", None) + if setup is None and teardown is None: + return None + cleanup = getattr(cls, "doClassCleanups", lambda: None) + + def process_teardown_exceptions() -> None: + # tearDown_exceptions is a list set in the class containing exc_infos for errors during + # teardown for the class. + exc_infos = getattr(cls, "tearDown_exceptions", None) + if not exc_infos: + return + exceptions = [exc for (_, exc, _) in exc_infos] + # If a single exception, raise it directly as this provides a more readable + # error (hopefully this will improve in #12255). + if len(exceptions) == 1: + raise exceptions[0] + else: + raise ExceptionGroup("Unittest class cleanup errors", exceptions) + + def unittest_setup_class_fixture( + request: FixtureRequest, + ) -> Generator[None]: + cls = request.cls + if _is_skipped(cls): + reason = cls.__unittest_skip_why__ + raise pytest.skip.Exception(reason, _use_item_location=True) + if setup is not None: + try: + setup() + # unittest does not call the cleanup function for every BaseException, so we + # follow this here. + except Exception: + cleanup() + process_teardown_exceptions() + raise + yield + try: + if teardown is not None: + teardown() + finally: + cleanup() + process_teardown_exceptions() + + self.session._fixturemanager._register_fixture( + # Use a unique name to speed up lookup. + name=f"_unittest_setUpClass_fixture_{cls.__qualname__}", + func=unittest_setup_class_fixture, + nodeid=self.nodeid, + scope="class", + autouse=True, + ) + + def _register_unittest_setup_method_fixture(self, cls: type) -> None: + """Register an auto-use fixture to invoke setup_method and + teardown_method (#517).""" + setup = getattr(cls, "setup_method", None) + teardown = getattr(cls, "teardown_method", None) + if setup is None and teardown is None: + return None + + def unittest_setup_method_fixture( + request: FixtureRequest, + ) -> Generator[None]: + self = request.instance + if _is_skipped(self): + reason = self.__unittest_skip_why__ + raise pytest.skip.Exception(reason, _use_item_location=True) + if setup is not None: + setup(self, request.function) + yield + if teardown is not None: + teardown(self, request.function) + + self.session._fixturemanager._register_fixture( + # Use a unique name to speed up lookup. + name=f"_unittest_setup_method_fixture_{cls.__qualname__}", + func=unittest_setup_method_fixture, + nodeid=self.nodeid, + scope="function", + autouse=True, + ) + + +class TestCaseFunction(Function): + nofuncargs = True + _excinfo: list[_pytest._code.ExceptionInfo[BaseException]] | None = None + + def _getinstance(self): + assert isinstance(self.parent, UnitTestCase) + return self.parent.obj(self.name) + + # Backward compat for pytest-django; can be removed after pytest-django + # updates + some slack. + @property + def _testcase(self): + return self.instance + + def setup(self) -> None: + # A bound method to be called during teardown() if set (see 'runtest()'). + self._explicit_tearDown: Callable[[], None] | None = None + super().setup() + + def teardown(self) -> None: + if self._explicit_tearDown is not None: + self._explicit_tearDown() + self._explicit_tearDown = None + self._obj = None + del self._instance + super().teardown() + + def startTest(self, testcase: unittest.TestCase) -> None: + pass + + def _addexcinfo(self, rawexcinfo: _SysExcInfoType) -> None: + # Unwrap potential exception info (see twisted trial support below). + rawexcinfo = getattr(rawexcinfo, "_rawexcinfo", rawexcinfo) + try: + excinfo = _pytest._code.ExceptionInfo[BaseException].from_exc_info( + rawexcinfo # type: ignore[arg-type] + ) + # Invoke the attributes to trigger storing the traceback + # trial causes some issue there. + _ = excinfo.value + _ = excinfo.traceback + except TypeError: + try: + try: + values = traceback.format_exception(*rawexcinfo) + values.insert( + 0, + "NOTE: Incompatible Exception Representation, " + "displaying natively:\n\n", + ) + fail("".join(values), pytrace=False) + except (fail.Exception, KeyboardInterrupt): + raise + except BaseException: + fail( + "ERROR: Unknown Incompatible Exception " + f"representation:\n{rawexcinfo!r}", + pytrace=False, + ) + except KeyboardInterrupt: + raise + except fail.Exception: + excinfo = _pytest._code.ExceptionInfo.from_current() + self.__dict__.setdefault("_excinfo", []).append(excinfo) + + def addError( + self, testcase: unittest.TestCase, rawexcinfo: _SysExcInfoType + ) -> None: + try: + if isinstance(rawexcinfo[1], exit.Exception): + exit(rawexcinfo[1].msg) + except TypeError: + pass + self._addexcinfo(rawexcinfo) + + def addFailure( + self, testcase: unittest.TestCase, rawexcinfo: _SysExcInfoType + ) -> None: + self._addexcinfo(rawexcinfo) + + def addSkip(self, testcase: unittest.TestCase, reason: str) -> None: + try: + raise pytest.skip.Exception(reason, _use_item_location=True) + except skip.Exception: + self._addexcinfo(sys.exc_info()) + + def addExpectedFailure( + self, + testcase: unittest.TestCase, + rawexcinfo: _SysExcInfoType, + reason: str = "", + ) -> None: + try: + xfail(str(reason)) + except xfail.Exception: + self._addexcinfo(sys.exc_info()) + + def addUnexpectedSuccess( + self, + testcase: unittest.TestCase, + reason: twisted.trial.unittest.Todo | None = None, + ) -> None: + msg = "Unexpected success" + if reason: + msg += f": {reason.reason}" + # Preserve unittest behaviour - fail the test. Explicitly not an XPASS. + try: + fail(msg, pytrace=False) + except fail.Exception: + self._addexcinfo(sys.exc_info()) + + def addSuccess(self, testcase: unittest.TestCase) -> None: + pass + + def stopTest(self, testcase: unittest.TestCase) -> None: + pass + + def addDuration(self, testcase: unittest.TestCase, elapsed: float) -> None: + pass + + def runtest(self) -> None: + from _pytest.debugging import maybe_wrap_pytest_function_for_tracing + + testcase = self.instance + assert testcase is not None + + maybe_wrap_pytest_function_for_tracing(self) + + # Let the unittest framework handle async functions. + if is_async_function(self.obj): + testcase(result=self) + else: + # When --pdb is given, we want to postpone calling tearDown() otherwise + # when entering the pdb prompt, tearDown() would have probably cleaned up + # instance variables, which makes it difficult to debug. + # Arguably we could always postpone tearDown(), but this changes the moment where the + # TestCase instance interacts with the results object, so better to only do it + # when absolutely needed. + # We need to consider if the test itself is skipped, or the whole class. + assert isinstance(self.parent, UnitTestCase) + skipped = _is_skipped(self.obj) or _is_skipped(self.parent.obj) + if self.config.getoption("usepdb") and not skipped: + self._explicit_tearDown = testcase.tearDown + setattr(testcase, "tearDown", lambda *args: None) + + # We need to update the actual bound method with self.obj, because + # wrap_pytest_function_for_tracing replaces self.obj by a wrapper. + setattr(testcase, self.name, self.obj) + try: + testcase(result=self) + finally: + delattr(testcase, self.name) + + def _traceback_filter( + self, excinfo: _pytest._code.ExceptionInfo[BaseException] + ) -> _pytest._code.Traceback: + traceback = super()._traceback_filter(excinfo) + ntraceback = traceback.filter( + lambda x: not x.frame.f_globals.get("__unittest"), + ) + if not ntraceback: + ntraceback = traceback + return ntraceback + + +@hookimpl(tryfirst=True) +def pytest_runtest_makereport(item: Item, call: CallInfo[None]) -> None: + if isinstance(item, TestCaseFunction): + if item._excinfo: + call.excinfo = item._excinfo.pop(0) + try: + del call.result + except AttributeError: + pass + + # Convert unittest.SkipTest to pytest.skip. + # This is actually only needed for nose, which reuses unittest.SkipTest for + # its own nose.SkipTest. For unittest TestCases, SkipTest is already + # handled internally, and doesn't reach here. + unittest = sys.modules.get("unittest") + if unittest and call.excinfo and isinstance(call.excinfo.value, unittest.SkipTest): + excinfo = call.excinfo + call2 = CallInfo[None].from_call( + lambda: pytest.skip(str(excinfo.value)), call.when + ) + call.excinfo = call2.excinfo + + +# Twisted trial support. +classImplements_has_run = False + + +@hookimpl(wrapper=True) +def pytest_runtest_protocol(item: Item) -> Generator[None, object, object]: + if isinstance(item, TestCaseFunction) and "twisted.trial.unittest" in sys.modules: + ut: Any = sys.modules["twisted.python.failure"] + global classImplements_has_run + Failure__init__ = ut.Failure.__init__ + if not classImplements_has_run: + from twisted.trial.itrial import IReporter + from zope.interface import classImplements + + classImplements(TestCaseFunction, IReporter) + classImplements_has_run = True + + def excstore( + self, exc_value=None, exc_type=None, exc_tb=None, captureVars=None + ): + if exc_value is None: + self._rawexcinfo = sys.exc_info() + else: + if exc_type is None: + exc_type = type(exc_value) + self._rawexcinfo = (exc_type, exc_value, exc_tb) + try: + Failure__init__( + self, exc_value, exc_type, exc_tb, captureVars=captureVars + ) + except TypeError: + Failure__init__(self, exc_value, exc_type, exc_tb) + + ut.Failure.__init__ = excstore + try: + res = yield + finally: + ut.Failure.__init__ = Failure__init__ + else: + res = yield + return res + + +def _is_skipped(obj) -> bool: + """Return True if the given object has been marked with @unittest.skip.""" + return bool(getattr(obj, "__unittest_skip__", False)) diff --git a/.venv/lib/python3.11/site-packages/cpuinfo/__init__.py b/.venv/lib/python3.11/site-packages/cpuinfo/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..f0ae1cedef2202096faadc3ff0dd0614f8adf394 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/cpuinfo/__init__.py @@ -0,0 +1,5 @@ + +import sys +from cpuinfo.cpuinfo import * + + diff --git a/.venv/lib/python3.11/site-packages/cpuinfo/__pycache__/__init__.cpython-311.pyc b/.venv/lib/python3.11/site-packages/cpuinfo/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ccaa075dcbf6fdcc815380c5544030afb83f612c Binary files /dev/null and b/.venv/lib/python3.11/site-packages/cpuinfo/__pycache__/__init__.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/cpuinfo/__pycache__/__main__.cpython-311.pyc b/.venv/lib/python3.11/site-packages/cpuinfo/__pycache__/__main__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..529d35f810889fa65d1e9f2c93384149c0991e7f Binary files /dev/null and b/.venv/lib/python3.11/site-packages/cpuinfo/__pycache__/__main__.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/INSTALLER b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/INSTALLER new file mode 100644 index 0000000000000000000000000000000000000000..a1b589e38a32041e49332e5e81c2d363dc418d68 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/INSTALLER @@ -0,0 +1 @@ +pip diff --git a/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/LICENSE b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/LICENSE new file mode 100644 index 0000000000000000000000000000000000000000..cac50cdfa9f73d7329854bd5528c6c8c3c0eb5d4 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright 2023- The Outlines developers + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/METADATA b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/METADATA new file mode 100644 index 0000000000000000000000000000000000000000..a2ad72b6a38e84ed8c5df5d64c78fdaa08d03c4b --- /dev/null +++ b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/METADATA @@ -0,0 +1,124 @@ +Metadata-Version: 2.1 +Name: outlines_core +Version: 0.1.26 +Summary: Structured Text Generation in Rust +Author: Outlines Developers +License: Apache-2.0 +Project-URL: homepage, https://github.com/dottxt-ai/outlines-core +Project-URL: documentation, https://dottxt-ai.github.io/outlines-core/ +Project-URL: repository, https://github.com/dottxt-ai/outlines-core +Keywords: machine learning,deep learning,language models,structured generation +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: Intended Audience :: Information Technology +Classifier: Intended Audience :: Science/Research +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python :: 3 +Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence +Requires-Python: >=3.8 +Description-Content-Type: text/markdown +License-File: LICENSE +Requires-Dist: interegular +Requires-Dist: jsonschema +Provides-Extra: test +Requires-Dist: pre-commit; extra == "test" +Requires-Dist: pydantic; extra == "test" +Requires-Dist: pytest; extra == "test" +Requires-Dist: pytest-benchmark; extra == "test" +Requires-Dist: pytest-cov; extra == "test" +Requires-Dist: pytest-mock; extra == "test" +Requires-Dist: coverage[toml]>=5.1; extra == "test" +Requires-Dist: diff-cover; extra == "test" +Requires-Dist: accelerate; extra == "test" +Requires-Dist: beartype<0.16.0; extra == "test" +Requires-Dist: huggingface_hub; extra == "test" +Requires-Dist: torch; extra == "test" +Requires-Dist: numpy; extra == "test" +Requires-Dist: scipy; extra == "test" +Requires-Dist: transformers; extra == "test" +Requires-Dist: datasets; extra == "test" +Requires-Dist: pillow; extra == "test" +Requires-Dist: asv; extra == "test" +Requires-Dist: psutil; extra == "test" +Requires-Dist: setuptools-rust; extra == "test" + +
+ +Outlines-core Logo + +[![Contributors][contributors-badge]][contributors] + +*Structured generation (in Rust).* +
+ +This package provides the core functionality for structured generation, formerly implemented in [Outlines][outlines], with a focus on performance and portability. + +# Install + +We provide bindings to the following languages: +- [Rust][rust-implementation] (Original implementation) +- [Python][python-bindings] + +The latest release of the Python bindings is available on PyPi using `pip`: + +``` python +pip install outlines-core +``` + +The current development branch of `outlines-core` can be installed from GitHub, also using `pip`: + +``` shell +pip install git+https://github.com/outlines-dev/outlines-core +``` + +Or install in a rust project with cargo: +``` bash +cargo add outlines-core +``` + +# How to contribute? + +## Setup + +First, fork the repository on GitHub and clone the fork locally: + +```bash +git clone git@github.com/YourUserName/outlines-core.git +cd outlines-core +``` + +Create a new virtual environment: + +``` bash +python -m venv .venv +source .venv/bin/activate +``` + +Then install the dependencies in editable mode, and install the pre-commit hooks: + +``` bash +pip install -e ".[test]" +pre-commit install +``` + +## Before pushing your code + +Run the tests: + + +``` bash +pytest +``` + +And run the code style checks: + +``` bash +pre-commit run --all-files +``` + + +[outlines]: https://github.com/dottxt-ai/outlines +[contributors]: https://github.com/outlines-dev/outlines-core/graphs/contributors +[contributors-badge]: https://img.shields.io/github/contributors/outlines-dev/outlines-core?style=flat-square&logo=github&logoColor=white&color=ECEFF4 +[rust-implementation]: https://github.com/outlines-dev/outlines-core/tree/readme/src +[python-bindings]: https://github.com/outlines-dev/outlines-core/tree/readme/python/outlines_core diff --git a/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/RECORD b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/RECORD new file mode 100644 index 0000000000000000000000000000000000000000..2f41759b2823fa824ddb7a9600e489d448ced7ce --- /dev/null +++ b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/RECORD @@ -0,0 +1,21 @@ +outlines_core-0.1.26.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +outlines_core-0.1.26.dist-info/LICENSE,sha256=9xB47oqqPVZwSIdW8Zk7neOuZMlUagIy67vdWVxTddc,11354 +outlines_core-0.1.26.dist-info/METADATA,sha256=YNmRZrAWCy_JWcTTuWsTzD9qZu-Wdm5J8JTTolLRigM,3761 +outlines_core-0.1.26.dist-info/RECORD,, +outlines_core-0.1.26.dist-info/WHEEL,sha256=9BFfIe-Zq441iQ0ehutX65O5faGDpmB1Uw3WaQGk4f0,151 +outlines_core-0.1.26.dist-info/top_level.txt,sha256=45vDiTQKP-oMzuyEv9_QNERQrpBud0CXZ1BDiFJjyV4,14 +outlines_core/__init__.py,sha256=U-Sz4BgH-fmII5vv_AL_qSp2a2mLd6g6aHbEfnUPmKU,208 +outlines_core/__pycache__/__init__.cpython-311.pyc,, +outlines_core/__pycache__/_version.cpython-311.pyc,, +outlines_core/_version.py,sha256=pHptU6h1OxA8-tsynXa5Rz3N6XELevZ_27Ye-N1R-ds,413 +outlines_core/fsm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +outlines_core/fsm/__pycache__/__init__.cpython-311.pyc,, +outlines_core/fsm/__pycache__/guide.cpython-311.pyc,, +outlines_core/fsm/__pycache__/json_schema.cpython-311.pyc,, +outlines_core/fsm/__pycache__/regex.cpython-311.pyc,, +outlines_core/fsm/guide.py,sha256=PujEqMU_UgYHBfOmWsAvVbdEb1HeniffGHQj61ZtCBE,9584 +outlines_core/fsm/json_schema.py,sha256=nXgIMF6uVI7sYqy9b1kJOChFfNutvbmvwmOgFbHcnl0,230 +outlines_core/fsm/outlines_core_rs.cpython-311-x86_64-linux-gnu.so,sha256=O3cV_9q1Ah16BFzf7g2xbNTxx7H8P6gbW8P9yt8QQ98,686792 +outlines_core/fsm/outlines_core_rs.pyi,sha256=1pvCFg3KDIDySgwhyzC4-r7tljU-DoWVr-AWs5KuhM0,2917 +outlines_core/fsm/regex.py,sha256=jw4pOwLhXXVlErnN6QUN56F6_nmPp8ATIDN-e3cl1y8,17243 +outlines_core/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 diff --git a/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/WHEEL b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/WHEEL new file mode 100644 index 0000000000000000000000000000000000000000..8b0363604372a86351ec451bb3c5afa26234e6f0 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/WHEEL @@ -0,0 +1,6 @@ +Wheel-Version: 1.0 +Generator: setuptools (75.6.0) +Root-Is-Purelib: false +Tag: cp311-cp311-manylinux_2_17_x86_64 +Tag: cp311-cp311-manylinux2014_x86_64 + diff --git a/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/top_level.txt b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/top_level.txt new file mode 100644 index 0000000000000000000000000000000000000000..44737cc8a2c5439560c6d7f59de74e020d0b23a0 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/outlines_core-0.1.26.dist-info/top_level.txt @@ -0,0 +1 @@ +outlines_core diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/__init__.py b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..d8dcab5b6866f24bc054e981fa40e83d23f14a28 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__init__.py @@ -0,0 +1,47 @@ +from __future__ import absolute_import + +import os +from pickle import PicklingError + +from ray.cloudpickle.cloudpickle import * # noqa +from ray.cloudpickle.cloudpickle_fast import CloudPickler, dumps, dump # noqa + + +# Conform to the convention used by python serialization libraries, which +# expose their Pickler subclass at top-level under the "Pickler" name. +Pickler = CloudPickler + +__version__ = '2.0.0' + + +def _warn_msg(obj, method, exc): + return ( + f"{method}({str(obj)}) failed." + "\nTo check which non-serializable variables are captured " + "in scope, re-run the ray script with 'RAY_PICKLE_VERBOSE_DEBUG=1'.") + + +def dump_debug(obj, *args, **kwargs): + try: + return dump(obj, *args, **kwargs) + except (TypeError, PicklingError) as exc: + if os.environ.get("RAY_PICKLE_VERBOSE_DEBUG"): + from ray.util.check_serialize import inspect_serializability + inspect_serializability(obj) + raise + else: + msg = _warn_msg(obj, "ray.cloudpickle.dump", exc) + raise type(exc)(msg) + + +def dumps_debug(obj, *args, **kwargs): + try: + return dumps(obj, *args, **kwargs) + except (TypeError, PicklingError) as exc: + if os.environ.get("RAY_PICKLE_VERBOSE_DEBUG"): + from ray.util.check_serialize import inspect_serializability + inspect_serializability(obj) + raise + else: + msg = _warn_msg(obj, "ray.cloudpickle.dumps", exc) + raise type(exc)(msg) diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/__init__.cpython-311.pyc b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..cc21ab6f1ccd643b0bb292f982fabd4fec3fb399 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/__init__.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/cloudpickle.cpython-311.pyc b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/cloudpickle.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..251b5e2a45d78b605e11684bafe84c5d5e2eb9ed Binary files /dev/null and b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/cloudpickle.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/cloudpickle_fast.cpython-311.pyc b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/cloudpickle_fast.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ff0d0500b5fff0f6e3287c86fb9ee4ea64d7ef9f Binary files /dev/null and b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/cloudpickle_fast.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/compat.cpython-311.pyc b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/compat.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c33fea7febeee4af417c870d45942e909ceea2be Binary files /dev/null and b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/compat.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/py_pickle.cpython-311.pyc b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/py_pickle.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..d0178c8948c84ae82e3b8cff634de6075f55c820 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/ray/cloudpickle/__pycache__/py_pickle.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/cloudpickle.py b/.venv/lib/python3.11/site-packages/ray/cloudpickle/cloudpickle.py new file mode 100644 index 0000000000000000000000000000000000000000..8f00b5f3f9769f8c549f25e8affe0198e5a65655 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/cloudpickle/cloudpickle.py @@ -0,0 +1,1487 @@ +"""Pickler class to extend the standard pickle.Pickler functionality + +The main objective is to make it natural to perform distributed computing on +clusters (such as PySpark, Dask, Ray...) with interactively defined code +(functions, classes, ...) written in notebooks or console. + +In particular this pickler adds the following features: +- serialize interactively-defined or locally-defined functions, classes, + enums, typevars, lambdas and nested functions to compiled byte code; +- deal with some other non-serializable objects in an ad-hoc manner where + applicable. + +This pickler is therefore meant to be used for the communication between short +lived Python processes running the same version of Python and libraries. In +particular, it is not meant to be used for long term storage of Python objects. + +It does not include an unpickler, as standard Python unpickling suffices. + +This module was extracted from the `cloud` package, developed by `PiCloud, Inc. +`_. + +Copyright (c) 2012-now, CloudPickle developers and contributors. +Copyright (c) 2012, Regents of the University of California. +Copyright (c) 2009 `PiCloud, Inc. `_. +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in the + documentation and/or other materials provided with the distribution. + * Neither the name of the University of California, Berkeley nor the + names of its contributors may be used to endorse or promote + products derived from this software without specific prior written + permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED +TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +""" + +import _collections_abc +from collections import ChainMap, OrderedDict +import abc +import builtins +import copyreg +import dataclasses +import dis +from enum import Enum +import io +import itertools +import logging +import opcode +import pickle +from pickle import _getattribute +import platform +import struct +import sys +import threading +import types +import typing +import uuid +import warnings +import weakref + +# The following import is required to be imported in the cloudpickle +# namespace to be able to load pickle files generated with older versions of +# cloudpickle. See: tests/test_backward_compat.py +from types import CellType # noqa: F401 + + +# cloudpickle is meant for inter process communication: we expect all +# communicating processes to run the same Python version hence we favor +# communication speed over compatibility: +DEFAULT_PROTOCOL = pickle.HIGHEST_PROTOCOL + +# Names of modules whose resources should be treated as dynamic. +_PICKLE_BY_VALUE_MODULES = set() + +# Track the provenance of reconstructed dynamic classes to make it possible to +# reconstruct instances from the matching singleton class definition when +# appropriate and preserve the usual "isinstance" semantics of Python objects. +_DYNAMIC_CLASS_TRACKER_BY_CLASS = weakref.WeakKeyDictionary() +_DYNAMIC_CLASS_TRACKER_BY_ID = weakref.WeakValueDictionary() +_DYNAMIC_CLASS_TRACKER_LOCK = threading.Lock() + +PYPY = platform.python_implementation() == "PyPy" + +builtin_code_type = None +if PYPY: + # builtin-code objects only exist in pypy + builtin_code_type = type(float.__new__.__code__) + +_extract_code_globals_cache = weakref.WeakKeyDictionary() + + +def _get_or_create_tracker_id(class_def): + with _DYNAMIC_CLASS_TRACKER_LOCK: + class_tracker_id = _DYNAMIC_CLASS_TRACKER_BY_CLASS.get(class_def) + if class_tracker_id is None: + class_tracker_id = uuid.uuid4().hex + _DYNAMIC_CLASS_TRACKER_BY_CLASS[class_def] = class_tracker_id + _DYNAMIC_CLASS_TRACKER_BY_ID[class_tracker_id] = class_def + return class_tracker_id + + +def _lookup_class_or_track(class_tracker_id, class_def): + if class_tracker_id is not None: + with _DYNAMIC_CLASS_TRACKER_LOCK: + class_def = _DYNAMIC_CLASS_TRACKER_BY_ID.setdefault( + class_tracker_id, class_def + ) + _DYNAMIC_CLASS_TRACKER_BY_CLASS[class_def] = class_tracker_id + return class_def + + +def register_pickle_by_value(module): + """Register a module to make it functions and classes picklable by value. + + By default, functions and classes that are attributes of an importable + module are to be pickled by reference, that is relying on re-importing + the attribute from the module at load time. + + If `register_pickle_by_value(module)` is called, all its functions and + classes are subsequently to be pickled by value, meaning that they can + be loaded in Python processes where the module is not importable. + + This is especially useful when developing a module in a distributed + execution environment: restarting the client Python process with the new + source code is enough: there is no need to re-install the new version + of the module on all the worker nodes nor to restart the workers. + + Note: this feature is considered experimental. See the cloudpickle + README.md file for more details and limitations. + """ + if not isinstance(module, types.ModuleType): + raise ValueError(f"Input should be a module object, got {str(module)} instead") + # In the future, cloudpickle may need a way to access any module registered + # for pickling by value in order to introspect relative imports inside + # functions pickled by value. (see + # https://github.com/cloudpipe/cloudpickle/pull/417#issuecomment-873684633). + # This access can be ensured by checking that module is present in + # sys.modules at registering time and assuming that it will still be in + # there when accessed during pickling. Another alternative would be to + # store a weakref to the module. Even though cloudpickle does not implement + # this introspection yet, in order to avoid a possible breaking change + # later, we still enforce the presence of module inside sys.modules. + if module.__name__ not in sys.modules: + raise ValueError( + f"{module} was not imported correctly, have you used an " + "`import` statement to access it?" + ) + _PICKLE_BY_VALUE_MODULES.add(module.__name__) + + +def unregister_pickle_by_value(module): + """Unregister that the input module should be pickled by value.""" + if not isinstance(module, types.ModuleType): + raise ValueError(f"Input should be a module object, got {str(module)} instead") + if module.__name__ not in _PICKLE_BY_VALUE_MODULES: + raise ValueError(f"{module} is not registered for pickle by value") + else: + _PICKLE_BY_VALUE_MODULES.remove(module.__name__) + + +def list_registry_pickle_by_value(): + return _PICKLE_BY_VALUE_MODULES.copy() + + +def _is_registered_pickle_by_value(module): + module_name = module.__name__ + if module_name in _PICKLE_BY_VALUE_MODULES: + return True + while True: + parent_name = module_name.rsplit(".", 1)[0] + if parent_name == module_name: + break + if parent_name in _PICKLE_BY_VALUE_MODULES: + return True + module_name = parent_name + return False + + +def _whichmodule(obj, name): + """Find the module an object belongs to. + + This function differs from ``pickle.whichmodule`` in two ways: + - it does not mangle the cases where obj's module is __main__ and obj was + not found in any module. + - Errors arising during module introspection are ignored, as those errors + are considered unwanted side effects. + """ + module_name = getattr(obj, "__module__", None) + + if module_name is not None: + return module_name + # Protect the iteration by using a copy of sys.modules against dynamic + # modules that trigger imports of other modules upon calls to getattr or + # other threads importing at the same time. + for module_name, module in sys.modules.copy().items(): + # Some modules such as coverage can inject non-module objects inside + # sys.modules + if ( + module_name == "__main__" + or module is None + or not isinstance(module, types.ModuleType) + ): + continue + try: + if _getattribute(module, name)[0] is obj: + return module_name + except Exception: + pass + return None + + +def _should_pickle_by_reference(obj, name=None): + """Test whether an function or a class should be pickled by reference + + Pickling by reference means by that the object (typically a function or a + class) is an attribute of a module that is assumed to be importable in the + target Python environment. Loading will therefore rely on importing the + module and then calling `getattr` on it to access the function or class. + + Pickling by reference is the only option to pickle functions and classes + in the standard library. In cloudpickle the alternative option is to + pickle by value (for instance for interactively or locally defined + functions and classes or for attributes of modules that have been + explicitly registered to be pickled by value. + """ + if isinstance(obj, types.FunctionType) or issubclass(type(obj), type): + module_and_name = _lookup_module_and_qualname(obj, name=name) + if module_and_name is None: + return False + module, name = module_and_name + return not _is_registered_pickle_by_value(module) + + elif isinstance(obj, types.ModuleType): + # We assume that sys.modules is primarily used as a cache mechanism for + # the Python import machinery. Checking if a module has been added in + # is sys.modules therefore a cheap and simple heuristic to tell us + # whether we can assume that a given module could be imported by name + # in another Python process. + if _is_registered_pickle_by_value(obj): + return False + return obj.__name__ in sys.modules + else: + raise TypeError( + "cannot check importability of {} instances".format(type(obj).__name__) + ) + + +def _lookup_module_and_qualname(obj, name=None): + if name is None: + name = getattr(obj, "__qualname__", None) + if name is None: # pragma: no cover + # This used to be needed for Python 2.7 support but is probably not + # needed anymore. However we keep the __name__ introspection in case + # users of cloudpickle rely on this old behavior for unknown reasons. + name = getattr(obj, "__name__", None) + + module_name = _whichmodule(obj, name) + + if module_name is None: + # In this case, obj.__module__ is None AND obj was not found in any + # imported module. obj is thus treated as dynamic. + return None + + if module_name == "__main__": + return None + + # Note: if module_name is in sys.modules, the corresponding module is + # assumed importable at unpickling time. See #357 + module = sys.modules.get(module_name, None) + if module is None: + # The main reason why obj's module would not be imported is that this + # module has been dynamically created, using for example + # types.ModuleType. The other possibility is that module was removed + # from sys.modules after obj was created/imported. But this case is not + # supported, as the standard pickle does not support it either. + return None + + try: + obj2, parent = _getattribute(module, name) + except AttributeError: + # obj was not found inside the module it points to + return None + if obj2 is not obj: + return None + return module, name + + +def _extract_code_globals(co): + """Find all globals names read or written to by codeblock co.""" + out_names = _extract_code_globals_cache.get(co) + if out_names is None: + # We use a dict with None values instead of a set to get a + # deterministic order and avoid introducing non-deterministic pickle + # bytes as a results. + out_names = {name: None for name in _walk_global_ops(co)} + + # Declaring a function inside another one using the "def ..." syntax + # generates a constant code object corresponding to the one of the + # nested function's As the nested function may itself need global + # variables, we need to introspect its code, extract its globals, (look + # for code object in it's co_consts attribute..) and add the result to + # code_globals + if co.co_consts: + for const in co.co_consts: + if isinstance(const, types.CodeType): + out_names.update(_extract_code_globals(const)) + + _extract_code_globals_cache[co] = out_names + + return out_names + + +def _find_imported_submodules(code, top_level_dependencies): + """Find currently imported submodules used by a function. + + Submodules used by a function need to be detected and referenced for the + function to work correctly at depickling time. Because submodules can be + referenced as attribute of their parent package (``package.submodule``), we + need a special introspection technique that does not rely on GLOBAL-related + opcodes to find references of them in a code object. + + Example: + ``` + import concurrent.futures + import cloudpickle + def func(): + x = concurrent.futures.ThreadPoolExecutor + if __name__ == '__main__': + cloudpickle.dumps(func) + ``` + The globals extracted by cloudpickle in the function's state include the + concurrent package, but not its submodule (here, concurrent.futures), which + is the module used by func. Find_imported_submodules will detect the usage + of concurrent.futures. Saving this module alongside with func will ensure + that calling func once depickled does not fail due to concurrent.futures + not being imported + """ + + subimports = [] + # check if any known dependency is an imported package + for x in top_level_dependencies: + if ( + isinstance(x, types.ModuleType) + and hasattr(x, "__package__") + and x.__package__ + ): + # check if the package has any currently loaded sub-imports + prefix = x.__name__ + "." + # A concurrent thread could mutate sys.modules, + # make sure we iterate over a copy to avoid exceptions + for name in list(sys.modules): + # Older versions of pytest will add a "None" module to + # sys.modules. + if name is not None and name.startswith(prefix): + # check whether the function can address the sub-module + tokens = set(name[len(prefix) :].split(".")) + if not tokens - set(code.co_names): + subimports.append(sys.modules[name]) + return subimports + + +# relevant opcodes +STORE_GLOBAL = opcode.opmap["STORE_GLOBAL"] +DELETE_GLOBAL = opcode.opmap["DELETE_GLOBAL"] +LOAD_GLOBAL = opcode.opmap["LOAD_GLOBAL"] +GLOBAL_OPS = (STORE_GLOBAL, DELETE_GLOBAL, LOAD_GLOBAL) +HAVE_ARGUMENT = dis.HAVE_ARGUMENT +EXTENDED_ARG = dis.EXTENDED_ARG + + +_BUILTIN_TYPE_NAMES = {} +for k, v in types.__dict__.items(): + if type(v) is type: + _BUILTIN_TYPE_NAMES[v] = k + + +def _builtin_type(name): + if name == "ClassType": # pragma: no cover + # Backward compat to load pickle files generated with cloudpickle + # < 1.3 even if loading pickle files from older versions is not + # officially supported. + return type + return getattr(types, name) + + +def _walk_global_ops(code): + """Yield referenced name for global-referencing instructions in code.""" + for instr in dis.get_instructions(code): + op = instr.opcode + if op in GLOBAL_OPS: + yield instr.argval + + +def _extract_class_dict(cls): + """Retrieve a copy of the dict of a class without the inherited method.""" + clsdict = dict(cls.__dict__) # copy dict proxy to a dict + if len(cls.__bases__) == 1: + inherited_dict = cls.__bases__[0].__dict__ + else: + inherited_dict = {} + for base in reversed(cls.__bases__): + inherited_dict.update(base.__dict__) + to_remove = [] + for name, value in clsdict.items(): + try: + base_value = inherited_dict[name] + if value is base_value: + to_remove.append(name) + except KeyError: + pass + for name in to_remove: + clsdict.pop(name) + return clsdict + + +def is_tornado_coroutine(func): + """Return whether `func` is a Tornado coroutine function. + + Running coroutines are not supported. + """ + warnings.warn( + "is_tornado_coroutine is deprecated in cloudpickle 3.0 and will be " + "removed in cloudpickle 4.0. Use tornado.gen.is_coroutine_function " + "directly instead.", + category=DeprecationWarning, + ) + if "tornado.gen" not in sys.modules: + return False + gen = sys.modules["tornado.gen"] + if not hasattr(gen, "is_coroutine_function"): + # Tornado version is too old + return False + return gen.is_coroutine_function(func) + + +def subimport(name): + # We cannot do simply: `return __import__(name)`: Indeed, if ``name`` is + # the name of a submodule, __import__ will return the top-level root module + # of this submodule. For instance, __import__('os.path') returns the `os` + # module. + __import__(name) + return sys.modules[name] + + +def dynamic_subimport(name, vars): + mod = types.ModuleType(name) + mod.__dict__.update(vars) + mod.__dict__["__builtins__"] = builtins.__dict__ + return mod + + +def _get_cell_contents(cell): + try: + return cell.cell_contents + except ValueError: + # Handle empty cells explicitly with a sentinel value. + return _empty_cell_value + + +def instance(cls): + """Create a new instance of a class. + + Parameters + ---------- + cls : type + The class to create an instance of. + + Returns + ------- + instance : cls + A new instance of ``cls``. + """ + return cls() + + +@instance +class _empty_cell_value: + """Sentinel for empty closures.""" + + @classmethod + def __reduce__(cls): + return cls.__name__ + + +def _make_function(code, globals, name, argdefs, closure): + # Setting __builtins__ in globals is needed for nogil CPython. + globals["__builtins__"] = __builtins__ + return types.FunctionType(code, globals, name, argdefs, closure) + + +def _make_empty_cell(): + if False: + # trick the compiler into creating an empty cell in our lambda + cell = None + raise AssertionError("this route should not be executed") + + return (lambda: cell).__closure__[0] + + +def _make_cell(value=_empty_cell_value): + cell = _make_empty_cell() + if value is not _empty_cell_value: + cell.cell_contents = value + return cell + + +def _make_skeleton_class( + type_constructor, name, bases, type_kwargs, class_tracker_id, extra +): + """Build dynamic class with an empty __dict__ to be filled once memoized + + If class_tracker_id is not None, try to lookup an existing class definition + matching that id. If none is found, track a newly reconstructed class + definition under that id so that other instances stemming from the same + class id will also reuse this class definition. + + The "extra" variable is meant to be a dict (or None) that can be used for + forward compatibility shall the need arise. + """ + skeleton_class = types.new_class( + name, bases, {"metaclass": type_constructor}, lambda ns: ns.update(type_kwargs) + ) + return _lookup_class_or_track(class_tracker_id, skeleton_class) + + +def _make_skeleton_enum( + bases, name, qualname, members, module, class_tracker_id, extra +): + """Build dynamic enum with an empty __dict__ to be filled once memoized + + The creation of the enum class is inspired by the code of + EnumMeta._create_. + + If class_tracker_id is not None, try to lookup an existing enum definition + matching that id. If none is found, track a newly reconstructed enum + definition under that id so that other instances stemming from the same + class id will also reuse this enum definition. + + The "extra" variable is meant to be a dict (or None) that can be used for + forward compatibility shall the need arise. + """ + # enums always inherit from their base Enum class at the last position in + # the list of base classes: + enum_base = bases[-1] + metacls = enum_base.__class__ + classdict = metacls.__prepare__(name, bases) + + for member_name, member_value in members.items(): + classdict[member_name] = member_value + enum_class = metacls.__new__(metacls, name, bases, classdict) + enum_class.__module__ = module + enum_class.__qualname__ = qualname + + return _lookup_class_or_track(class_tracker_id, enum_class) + + +def _make_typevar(name, bound, constraints, covariant, contravariant, class_tracker_id): + tv = typing.TypeVar( + name, + *constraints, + bound=bound, + covariant=covariant, + contravariant=contravariant, + ) + return _lookup_class_or_track(class_tracker_id, tv) + + +def _decompose_typevar(obj): + return ( + obj.__name__, + obj.__bound__, + obj.__constraints__, + obj.__covariant__, + obj.__contravariant__, + _get_or_create_tracker_id(obj), + ) + + +def _typevar_reduce(obj): + # TypeVar instances require the module information hence why we + # are not using the _should_pickle_by_reference directly + module_and_name = _lookup_module_and_qualname(obj, name=obj.__name__) + + if module_and_name is None: + return (_make_typevar, _decompose_typevar(obj)) + elif _is_registered_pickle_by_value(module_and_name[0]): + return (_make_typevar, _decompose_typevar(obj)) + + return (getattr, module_and_name) + + +def _get_bases(typ): + if "__orig_bases__" in getattr(typ, "__dict__", {}): + # For generic types (see PEP 560) + # Note that simply checking `hasattr(typ, '__orig_bases__')` is not + # correct. Subclasses of a fully-parameterized generic class does not + # have `__orig_bases__` defined, but `hasattr(typ, '__orig_bases__')` + # will return True because it's defined in the base class. + bases_attr = "__orig_bases__" + else: + # For regular class objects + bases_attr = "__bases__" + return getattr(typ, bases_attr) + + +def _make_dict_keys(obj, is_ordered=False): + if is_ordered: + return OrderedDict.fromkeys(obj).keys() + else: + return dict.fromkeys(obj).keys() + + +def _make_dict_values(obj, is_ordered=False): + if is_ordered: + return OrderedDict((i, _) for i, _ in enumerate(obj)).values() + else: + return {i: _ for i, _ in enumerate(obj)}.values() + + +def _make_dict_items(obj, is_ordered=False): + if is_ordered: + return OrderedDict(obj).items() + else: + return obj.items() + + +# COLLECTION OF OBJECTS __getnewargs__-LIKE METHODS +# ------------------------------------------------- + + +def _class_getnewargs(obj): + type_kwargs = {} + if "__module__" in obj.__dict__: + type_kwargs["__module__"] = obj.__module__ + + __dict__ = obj.__dict__.get("__dict__", None) + if isinstance(__dict__, property): + type_kwargs["__dict__"] = __dict__ + + return ( + type(obj), + obj.__name__, + _get_bases(obj), + type_kwargs, + _get_or_create_tracker_id(obj), + None, + ) + + +def _enum_getnewargs(obj): + members = {e.name: e.value for e in obj} + return ( + obj.__bases__, + obj.__name__, + obj.__qualname__, + members, + obj.__module__, + _get_or_create_tracker_id(obj), + None, + ) + + +# COLLECTION OF OBJECTS RECONSTRUCTORS +# ------------------------------------ +def _file_reconstructor(retval): + return retval + + +# COLLECTION OF OBJECTS STATE GETTERS +# ----------------------------------- + + +def _function_getstate(func): + # - Put func's dynamic attributes (stored in func.__dict__) in state. These + # attributes will be restored at unpickling time using + # f.__dict__.update(state) + # - Put func's members into slotstate. Such attributes will be restored at + # unpickling time by iterating over slotstate and calling setattr(func, + # slotname, slotvalue) + slotstate = { + "__name__": func.__name__, + "__qualname__": func.__qualname__, + "__annotations__": func.__annotations__, + "__kwdefaults__": func.__kwdefaults__, + "__defaults__": func.__defaults__, + "__module__": func.__module__, + "__doc__": func.__doc__, + "__closure__": func.__closure__, + } + + f_globals_ref = _extract_code_globals(func.__code__) + f_globals = {k: func.__globals__[k] for k in f_globals_ref if k in func.__globals__} + + if func.__closure__ is not None: + closure_values = list(map(_get_cell_contents, func.__closure__)) + else: + closure_values = () + + # Extract currently-imported submodules used by func. Storing these modules + # in a smoke _cloudpickle_subimports attribute of the object's state will + # trigger the side effect of importing these modules at unpickling time + # (which is necessary for func to work correctly once depickled) + slotstate["_cloudpickle_submodules"] = _find_imported_submodules( + func.__code__, itertools.chain(f_globals.values(), closure_values) + ) + slotstate["__globals__"] = f_globals + + state = func.__dict__ + return state, slotstate + + +def _class_getstate(obj): + clsdict = _extract_class_dict(obj) + clsdict.pop("__weakref__", None) + + if issubclass(type(obj), abc.ABCMeta): + # If obj is an instance of an ABCMeta subclass, don't pickle the + # cache/negative caches populated during isinstance/issubclass + # checks, but pickle the list of registered subclasses of obj. + clsdict.pop("_abc_cache", None) + clsdict.pop("_abc_negative_cache", None) + clsdict.pop("_abc_negative_cache_version", None) + registry = clsdict.pop("_abc_registry", None) + if registry is None: + # The abc caches and registered subclasses of a + # class are bundled into the single _abc_impl attribute + clsdict.pop("_abc_impl", None) + (registry, _, _, _) = abc._get_dump(obj) + + clsdict["_abc_impl"] = [subclass_weakref() for subclass_weakref in registry] + else: + # In the above if clause, registry is a set of weakrefs -- in + # this case, registry is a WeakSet + clsdict["_abc_impl"] = [type_ for type_ in registry] + + if "__slots__" in clsdict: + # pickle string length optimization: member descriptors of obj are + # created automatically from obj's __slots__ attribute, no need to + # save them in obj's state + if isinstance(obj.__slots__, str): + clsdict.pop(obj.__slots__) + else: + for k in obj.__slots__: + clsdict.pop(k, None) + + clsdict.pop("__dict__", None) # unpicklable property object + + return (clsdict, {}) + + +def _enum_getstate(obj): + clsdict, slotstate = _class_getstate(obj) + + members = {e.name: e.value for e in obj} + # Cleanup the clsdict that will be passed to _make_skeleton_enum: + # Those attributes are already handled by the metaclass. + for attrname in [ + "_generate_next_value_", + "_member_names_", + "_member_map_", + "_member_type_", + "_value2member_map_", + ]: + clsdict.pop(attrname, None) + for member in members: + clsdict.pop(member) + # Special handling of Enum subclasses + return clsdict, slotstate + + +# COLLECTIONS OF OBJECTS REDUCERS +# ------------------------------- +# A reducer is a function taking a single argument (obj), and that returns a +# tuple with all the necessary data to re-construct obj. Apart from a few +# exceptions (list, dict, bytes, int, etc.), a reducer is necessary to +# correctly pickle an object. +# While many built-in objects (Exceptions objects, instances of the "object" +# class, etc), are shipped with their own built-in reducer (invoked using +# obj.__reduce__), some do not. The following methods were created to "fill +# these holes". + + +def _code_reduce(obj): + """code object reducer.""" + # If you are not sure about the order of arguments, take a look at help + # of the specific type from types, for example: + # >>> from types import CodeType + # >>> help(CodeType) + if hasattr(obj, "co_exceptiontable"): + # Python 3.11 and later: there are some new attributes + # related to the enhanced exceptions. + args = ( + obj.co_argcount, + obj.co_posonlyargcount, + obj.co_kwonlyargcount, + obj.co_nlocals, + obj.co_stacksize, + obj.co_flags, + obj.co_code, + obj.co_consts, + obj.co_names, + obj.co_varnames, + obj.co_filename, + obj.co_name, + obj.co_qualname, + obj.co_firstlineno, + obj.co_linetable, + obj.co_exceptiontable, + obj.co_freevars, + obj.co_cellvars, + ) + elif hasattr(obj, "co_linetable"): + # Python 3.10 and later: obj.co_lnotab is deprecated and constructor + # expects obj.co_linetable instead. + args = ( + obj.co_argcount, + obj.co_posonlyargcount, + obj.co_kwonlyargcount, + obj.co_nlocals, + obj.co_stacksize, + obj.co_flags, + obj.co_code, + obj.co_consts, + obj.co_names, + obj.co_varnames, + obj.co_filename, + obj.co_name, + obj.co_firstlineno, + obj.co_linetable, + obj.co_freevars, + obj.co_cellvars, + ) + elif hasattr(obj, "co_nmeta"): # pragma: no cover + # "nogil" Python: modified attributes from 3.9 + args = ( + obj.co_argcount, + obj.co_posonlyargcount, + obj.co_kwonlyargcount, + obj.co_nlocals, + obj.co_framesize, + obj.co_ndefaultargs, + obj.co_nmeta, + obj.co_flags, + obj.co_code, + obj.co_consts, + obj.co_varnames, + obj.co_filename, + obj.co_name, + obj.co_firstlineno, + obj.co_lnotab, + obj.co_exc_handlers, + obj.co_jump_table, + obj.co_freevars, + obj.co_cellvars, + obj.co_free2reg, + obj.co_cell2reg, + ) + else: + # Backward compat for 3.8 and 3.9 + args = ( + obj.co_argcount, + obj.co_posonlyargcount, + obj.co_kwonlyargcount, + obj.co_nlocals, + obj.co_stacksize, + obj.co_flags, + obj.co_code, + obj.co_consts, + obj.co_names, + obj.co_varnames, + obj.co_filename, + obj.co_name, + obj.co_firstlineno, + obj.co_lnotab, + obj.co_freevars, + obj.co_cellvars, + ) + return types.CodeType, args + + +def _cell_reduce(obj): + """Cell (containing values of a function's free variables) reducer.""" + try: + obj.cell_contents + except ValueError: # cell is empty + return _make_empty_cell, () + else: + return _make_cell, (obj.cell_contents,) + + +def _classmethod_reduce(obj): + orig_func = obj.__func__ + return type(obj), (orig_func,) + + +def _file_reduce(obj): + """Save a file.""" + import io + + if not hasattr(obj, "name") or not hasattr(obj, "mode"): + raise pickle.PicklingError( + "Cannot pickle files that do not map to an actual file" + ) + if obj is sys.stdout: + return getattr, (sys, "stdout") + if obj is sys.stderr: + return getattr, (sys, "stderr") + if obj is sys.stdin: + raise pickle.PicklingError("Cannot pickle standard input") + if obj.closed: + raise pickle.PicklingError("Cannot pickle closed files") + if hasattr(obj, "isatty") and obj.isatty(): + raise pickle.PicklingError("Cannot pickle files that map to tty objects") + if "r" not in obj.mode and "+" not in obj.mode: + raise pickle.PicklingError( + "Cannot pickle files that are not opened for reading: %s" % obj.mode + ) + + name = obj.name + + retval = io.StringIO() + + try: + # Read the whole file + curloc = obj.tell() + obj.seek(0) + contents = obj.read() + obj.seek(curloc) + except OSError as e: + raise pickle.PicklingError( + "Cannot pickle file %s as it cannot be read" % name + ) from e + retval.write(contents) + retval.seek(curloc) + + retval.name = name + return _file_reconstructor, (retval,) + + +def _getset_descriptor_reduce(obj): + return getattr, (obj.__objclass__, obj.__name__) + + +def _mappingproxy_reduce(obj): + return types.MappingProxyType, (dict(obj),) + + +def _memoryview_reduce(obj): + return bytes, (obj.tobytes(),) + + +def _module_reduce(obj): + if _should_pickle_by_reference(obj): + return subimport, (obj.__name__,) + else: + # Some external libraries can populate the "__builtins__" entry of a + # module's `__dict__` with unpicklable objects (see #316). For that + # reason, we do not attempt to pickle the "__builtins__" entry, and + # restore a default value for it at unpickling time. + state = obj.__dict__.copy() + state.pop("__builtins__", None) + return dynamic_subimport, (obj.__name__, state) + + +def _method_reduce(obj): + return (types.MethodType, (obj.__func__, obj.__self__)) + + +def _logger_reduce(obj): + return logging.getLogger, (obj.name,) + + +def _root_logger_reduce(obj): + return logging.getLogger, () + + +def _property_reduce(obj): + return property, (obj.fget, obj.fset, obj.fdel, obj.__doc__) + + +def _weakset_reduce(obj): + return weakref.WeakSet, (list(obj),) + + +def _dynamic_class_reduce(obj): + """Save a class that can't be referenced as a module attribute. + + This method is used to serialize classes that are defined inside + functions, or that otherwise can't be serialized as attribute lookups + from importable modules. + """ + if Enum is not None and issubclass(obj, Enum): + return ( + _make_skeleton_enum, + _enum_getnewargs(obj), + _enum_getstate(obj), + None, + None, + _class_setstate, + ) + else: + return ( + _make_skeleton_class, + _class_getnewargs(obj), + _class_getstate(obj), + None, + None, + _class_setstate, + ) + + +def _class_reduce(obj): + """Select the reducer depending on the dynamic nature of the class obj.""" + if obj is type(None): # noqa + return type, (None,) + elif obj is type(Ellipsis): + return type, (Ellipsis,) + elif obj is type(NotImplemented): + return type, (NotImplemented,) + elif obj in _BUILTIN_TYPE_NAMES: + return _builtin_type, (_BUILTIN_TYPE_NAMES[obj],) + elif not _should_pickle_by_reference(obj): + return _dynamic_class_reduce(obj) + return NotImplemented + + +def _dict_keys_reduce(obj): + # Safer not to ship the full dict as sending the rest might + # be unintended and could potentially cause leaking of + # sensitive information + return _make_dict_keys, (list(obj),) + + +def _dict_values_reduce(obj): + # Safer not to ship the full dict as sending the rest might + # be unintended and could potentially cause leaking of + # sensitive information + return _make_dict_values, (list(obj),) + + +def _dict_items_reduce(obj): + return _make_dict_items, (dict(obj),) + + +def _odict_keys_reduce(obj): + # Safer not to ship the full dict as sending the rest might + # be unintended and could potentially cause leaking of + # sensitive information + return _make_dict_keys, (list(obj), True) + + +def _odict_values_reduce(obj): + # Safer not to ship the full dict as sending the rest might + # be unintended and could potentially cause leaking of + # sensitive information + return _make_dict_values, (list(obj), True) + + +def _odict_items_reduce(obj): + return _make_dict_items, (dict(obj), True) + + +def _dataclass_field_base_reduce(obj): + return _get_dataclass_field_type_sentinel, (obj.name,) + + +# COLLECTIONS OF OBJECTS STATE SETTERS +# ------------------------------------ +# state setters are called at unpickling time, once the object is created and +# it has to be updated to how it was at unpickling time. + + +def _function_setstate(obj, state): + """Update the state of a dynamic function. + + As __closure__ and __globals__ are readonly attributes of a function, we + cannot rely on the native setstate routine of pickle.load_build, that calls + setattr on items of the slotstate. Instead, we have to modify them inplace. + """ + state, slotstate = state + obj.__dict__.update(state) + + obj_globals = slotstate.pop("__globals__") + obj_closure = slotstate.pop("__closure__") + # _cloudpickle_subimports is a set of submodules that must be loaded for + # the pickled function to work correctly at unpickling time. Now that these + # submodules are depickled (hence imported), they can be removed from the + # object's state (the object state only served as a reference holder to + # these submodules) + slotstate.pop("_cloudpickle_submodules") + + obj.__globals__.update(obj_globals) + obj.__globals__["__builtins__"] = __builtins__ + + if obj_closure is not None: + for i, cell in enumerate(obj_closure): + try: + value = cell.cell_contents + except ValueError: # cell is empty + continue + obj.__closure__[i].cell_contents = value + + for k, v in slotstate.items(): + setattr(obj, k, v) + + +def _class_setstate(obj, state): + state, slotstate = state + registry = None + for attrname, attr in state.items(): + if attrname == "_abc_impl": + registry = attr + else: + setattr(obj, attrname, attr) + if registry is not None: + for subclass in registry: + obj.register(subclass) + + return obj + + +# COLLECTION OF DATACLASS UTILITIES +# --------------------------------- +# There are some internal sentinel values whose identity must be preserved when +# unpickling dataclass fields. Each sentinel value has a unique name that we can +# use to retrieve its identity at unpickling time. + + +_DATACLASSE_FIELD_TYPE_SENTINELS = { + dataclasses._FIELD.name: dataclasses._FIELD, + dataclasses._FIELD_CLASSVAR.name: dataclasses._FIELD_CLASSVAR, + dataclasses._FIELD_INITVAR.name: dataclasses._FIELD_INITVAR, +} + + +def _get_dataclass_field_type_sentinel(name): + return _DATACLASSE_FIELD_TYPE_SENTINELS[name] + + +class Pickler(pickle.Pickler): + # set of reducers defined and used by cloudpickle (private) + _dispatch_table = {} + _dispatch_table[classmethod] = _classmethod_reduce + _dispatch_table[io.TextIOWrapper] = _file_reduce + _dispatch_table[logging.Logger] = _logger_reduce + _dispatch_table[logging.RootLogger] = _root_logger_reduce + _dispatch_table[memoryview] = _memoryview_reduce + _dispatch_table[property] = _property_reduce + _dispatch_table[staticmethod] = _classmethod_reduce + _dispatch_table[CellType] = _cell_reduce + _dispatch_table[types.CodeType] = _code_reduce + _dispatch_table[types.GetSetDescriptorType] = _getset_descriptor_reduce + _dispatch_table[types.ModuleType] = _module_reduce + _dispatch_table[types.MethodType] = _method_reduce + _dispatch_table[types.MappingProxyType] = _mappingproxy_reduce + _dispatch_table[weakref.WeakSet] = _weakset_reduce + _dispatch_table[typing.TypeVar] = _typevar_reduce + _dispatch_table[_collections_abc.dict_keys] = _dict_keys_reduce + _dispatch_table[_collections_abc.dict_values] = _dict_values_reduce + _dispatch_table[_collections_abc.dict_items] = _dict_items_reduce + _dispatch_table[type(OrderedDict().keys())] = _odict_keys_reduce + _dispatch_table[type(OrderedDict().values())] = _odict_values_reduce + _dispatch_table[type(OrderedDict().items())] = _odict_items_reduce + _dispatch_table[abc.abstractmethod] = _classmethod_reduce + _dispatch_table[abc.abstractclassmethod] = _classmethod_reduce + _dispatch_table[abc.abstractstaticmethod] = _classmethod_reduce + _dispatch_table[abc.abstractproperty] = _property_reduce + _dispatch_table[dataclasses._FIELD_BASE] = _dataclass_field_base_reduce + + dispatch_table = ChainMap(_dispatch_table, copyreg.dispatch_table) + + # function reducers are defined as instance methods of cloudpickle.Pickler + # objects, as they rely on a cloudpickle.Pickler attribute (globals_ref) + def _dynamic_function_reduce(self, func): + """Reduce a function that is not pickleable via attribute lookup.""" + newargs = self._function_getnewargs(func) + state = _function_getstate(func) + return (_make_function, newargs, state, None, None, _function_setstate) + + def _function_reduce(self, obj): + """Reducer for function objects. + + If obj is a top-level attribute of a file-backed module, this reducer + returns NotImplemented, making the cloudpickle.Pickler fall back to + traditional pickle.Pickler routines to save obj. Otherwise, it reduces + obj using a custom cloudpickle reducer designed specifically to handle + dynamic functions. + """ + if _should_pickle_by_reference(obj): + return NotImplemented + else: + return self._dynamic_function_reduce(obj) + + def _function_getnewargs(self, func): + code = func.__code__ + + # base_globals represents the future global namespace of func at + # unpickling time. Looking it up and storing it in + # cloudpickle.Pickler.globals_ref allow functions sharing the same + # globals at pickling time to also share them once unpickled, at one + # condition: since globals_ref is an attribute of a cloudpickle.Pickler + # instance, and that a new cloudpickle.Pickler is created each time + # cloudpickle.dump or cloudpickle.dumps is called, functions also need + # to be saved within the same invocation of + # cloudpickle.dump/cloudpickle.dumps (for example: + # cloudpickle.dumps([f1, f2])). There is no such limitation when using + # cloudpickle.Pickler.dump, as long as the multiple invocations are + # bound to the same cloudpickle.Pickler instance. + base_globals = self.globals_ref.setdefault(id(func.__globals__), {}) + + if base_globals == {}: + # Add module attributes used to resolve relative imports + # instructions inside func. + for k in ["__package__", "__name__", "__path__", "__file__"]: + if k in func.__globals__: + base_globals[k] = func.__globals__[k] + + # Do not bind the free variables before the function is created to + # avoid infinite recursion. + if func.__closure__ is None: + closure = None + else: + closure = tuple(_make_empty_cell() for _ in range(len(code.co_freevars))) + + return code, base_globals, None, None, closure + + def dump(self, obj): + try: + return super().dump(obj) + except RuntimeError as e: + if len(e.args) > 0 and "recursion" in e.args[0]: + msg = "Could not pickle object as excessively deep recursion required." + raise pickle.PicklingError(msg) from e + else: + raise + + def __init__(self, file, protocol=None, buffer_callback=None): + if protocol is None: + protocol = DEFAULT_PROTOCOL + super().__init__(file, protocol=protocol, buffer_callback=buffer_callback) + # map functions __globals__ attribute ids, to ensure that functions + # sharing the same global namespace at pickling time also share + # their global namespace at unpickling time. + self.globals_ref = {} + self.proto = int(protocol) + + if not PYPY: + # pickle.Pickler is the C implementation of the CPython pickler and + # therefore we rely on reduce_override method to customize the pickler + # behavior. + + # `cloudpickle.Pickler.dispatch` is only left for backward + # compatibility - note that when using protocol 5, + # `cloudpickle.Pickler.dispatch` is not an extension of + # `pickle._Pickler.dispatch` dictionary, because `cloudpickle.Pickler` + # subclasses the C-implemented `pickle.Pickler`, which does not expose + # a `dispatch` attribute. Earlier versions of `cloudpickle.Pickler` + # used `cloudpickle.Pickler.dispatch` as a class-level attribute + # storing all reducers implemented by cloudpickle, but the attribute + # name was not a great choice given because it would collide with a + # similarly named attribute in the pure-Python `pickle._Pickler` + # implementation in the standard library. + dispatch = dispatch_table + + # Implementation of the reducer_override callback, in order to + # efficiently serialize dynamic functions and classes by subclassing + # the C-implemented `pickle.Pickler`. + # TODO: decorrelate reducer_override (which is tied to CPython's + # implementation - would it make sense to backport it to pypy? - and + # pickle's protocol 5 which is implementation agnostic. Currently, the + # availability of both notions coincide on CPython's pickle, but it may + # not be the case anymore when pypy implements protocol 5. + + def reducer_override(self, obj): + """Type-agnostic reducing callback for function and classes. + + For performance reasons, subclasses of the C `pickle.Pickler` class + cannot register custom reducers for functions and classes in the + dispatch_table attribute. Reducers for such types must instead + implemented via the special `reducer_override` method. + + Note that this method will be called for any object except a few + builtin-types (int, lists, dicts etc.), which differs from reducers + in the Pickler's dispatch_table, each of them being invoked for + objects of a specific type only. + + This property comes in handy for classes: although most classes are + instances of the ``type`` metaclass, some of them can be instances + of other custom metaclasses (such as enum.EnumMeta for example). In + particular, the metaclass will likely not be known in advance, and + thus cannot be special-cased using an entry in the dispatch_table. + reducer_override, among other things, allows us to register a + reducer that will be called for any class, independently of its + type. + + Notes: + + * reducer_override has the priority over dispatch_table-registered + reducers. + * reducer_override can be used to fix other limitations of + cloudpickle for other types that suffered from type-specific + reducers, such as Exceptions. See + https://github.com/cloudpipe/cloudpickle/issues/248 + """ + t = type(obj) + try: + is_anyclass = issubclass(t, type) + except TypeError: # t is not a class (old Boost; see SF #502085) + is_anyclass = False + + if is_anyclass: + return _class_reduce(obj) + elif isinstance(obj, types.FunctionType): + return self._function_reduce(obj) + else: + # fallback to save_global, including the Pickler's + # dispatch_table + return NotImplemented + + else: + # When reducer_override is not available, hack the pure-Python + # Pickler's types.FunctionType and type savers. Note: the type saver + # must override Pickler.save_global, because pickle.py contains a + # hard-coded call to save_global when pickling meta-classes. + dispatch = pickle.Pickler.dispatch.copy() + + def _save_reduce_pickle5( + self, + func, + args, + state=None, + listitems=None, + dictitems=None, + state_setter=None, + obj=None, + ): + save = self.save + write = self.write + self.save_reduce( + func, + args, + state=None, + listitems=listitems, + dictitems=dictitems, + obj=obj, + ) + # backport of the Python 3.8 state_setter pickle operations + save(state_setter) + save(obj) # simple BINGET opcode as obj is already memoized. + save(state) + write(pickle.TUPLE2) + # Trigger a state_setter(obj, state) function call. + write(pickle.REDUCE) + # The purpose of state_setter is to carry-out an + # inplace modification of obj. We do not care about what the + # method might return, so its output is eventually removed from + # the stack. + write(pickle.POP) + + def save_global(self, obj, name=None, pack=struct.pack): + """Main dispatch method. + + The name of this method is somewhat misleading: all types get + dispatched here. + """ + if obj is type(None): # noqa + return self.save_reduce(type, (None,), obj=obj) + elif obj is type(Ellipsis): + return self.save_reduce(type, (Ellipsis,), obj=obj) + elif obj is type(NotImplemented): + return self.save_reduce(type, (NotImplemented,), obj=obj) + elif obj in _BUILTIN_TYPE_NAMES: + return self.save_reduce( + _builtin_type, (_BUILTIN_TYPE_NAMES[obj],), obj=obj + ) + + if name is not None: + super().save_global(obj, name=name) + elif not _should_pickle_by_reference(obj, name=name): + self._save_reduce_pickle5(*_dynamic_class_reduce(obj), obj=obj) + else: + super().save_global(obj, name=name) + + dispatch[type] = save_global + + def save_function(self, obj, name=None): + """Registered with the dispatch to handle all function types. + + Determines what kind of function obj is (e.g. lambda, defined at + interactive prompt, etc) and handles the pickling appropriately. + """ + if _should_pickle_by_reference(obj, name=name): + return super().save_global(obj, name=name) + elif PYPY and isinstance(obj.__code__, builtin_code_type): + return self.save_pypy_builtin_func(obj) + else: + return self._save_reduce_pickle5( + *self._dynamic_function_reduce(obj), obj=obj + ) + + def save_pypy_builtin_func(self, obj): + """Save pypy equivalent of builtin functions. + + PyPy does not have the concept of builtin-functions. Instead, + builtin-functions are simple function instances, but with a + builtin-code attribute. + Most of the time, builtin functions should be pickled by attribute. + But PyPy has flaky support for __qualname__, so some builtin + functions such as float.__new__ will be classified as dynamic. For + this reason only, we created this special routine. Because + builtin-functions are not expected to have closure or globals, + there is no additional hack (compared the one already implemented + in pickle) to protect ourselves from reference cycles. A simple + (reconstructor, newargs, obj.__dict__) tuple is save_reduced. Note + also that PyPy improved their support for __qualname__ in v3.6, so + this routing should be removed when cloudpickle supports only PyPy + 3.6 and later. + """ + rv = ( + types.FunctionType, + (obj.__code__, {}, obj.__name__, obj.__defaults__, obj.__closure__), + obj.__dict__, + ) + self.save_reduce(*rv, obj=obj) + + dispatch[types.FunctionType] = save_function + + +# Shorthands similar to pickle.dump/pickle.dumps + + +def dump(obj, file, protocol=None, buffer_callback=None): + """Serialize obj as bytes streamed into file + + protocol defaults to cloudpickle.DEFAULT_PROTOCOL which is an alias to + pickle.HIGHEST_PROTOCOL. This setting favors maximum communication + speed between processes running the same Python version. + + Set protocol=pickle.DEFAULT_PROTOCOL instead if you need to ensure + compatibility with older versions of Python (although this is not always + guaranteed to work because cloudpickle relies on some internal + implementation details that can change from one Python version to the + next). + """ + Pickler(file, protocol=protocol, buffer_callback=buffer_callback).dump(obj) + + +def dumps(obj, protocol=None, buffer_callback=None): + """Serialize obj as a string of bytes allocated in memory + + protocol defaults to cloudpickle.DEFAULT_PROTOCOL which is an alias to + pickle.HIGHEST_PROTOCOL. This setting favors maximum communication + speed between processes running the same Python version. + + Set protocol=pickle.DEFAULT_PROTOCOL instead if you need to ensure + compatibility with older versions of Python (although this is not always + guaranteed to work because cloudpickle relies on some internal + implementation details that can change from one Python version to the + next). + """ + with io.BytesIO() as file: + cp = Pickler(file, protocol=protocol, buffer_callback=buffer_callback) + cp.dump(obj) + return file.getvalue() + + +# Include pickles unloading functions in this namespace for convenience. +load, loads = pickle.load, pickle.loads + +# Backward compat alias. +CloudPickler = Pickler \ No newline at end of file diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/cloudpickle_fast.py b/.venv/lib/python3.11/site-packages/ray/cloudpickle/cloudpickle_fast.py new file mode 100644 index 0000000000000000000000000000000000000000..52d6732e44ebcc0053b24969943f7c3b742268bb --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/cloudpickle/cloudpickle_fast.py @@ -0,0 +1,13 @@ +"""Compatibility module. + +It can be necessary to load files generated by previous versions of cloudpickle +that rely on symbols being defined under the `cloudpickle.cloudpickle_fast` +namespace. + +See: tests/test_backward_compat.py +""" +from . import cloudpickle + + +def __getattr__(name): + return getattr(cloudpickle, name) diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/compat.py b/.venv/lib/python3.11/site-packages/ray/cloudpickle/compat.py new file mode 100644 index 0000000000000000000000000000000000000000..a2eb12e5080b1dd9e0bb7e16e079fbb262678215 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/cloudpickle/compat.py @@ -0,0 +1,19 @@ +import logging +import os + +logger = logging.getLogger(__name__) + +RAY_PICKLE_VERBOSE_DEBUG = os.environ.get("RAY_PICKLE_VERBOSE_DEBUG") +verbose_level = int(RAY_PICKLE_VERBOSE_DEBUG) if RAY_PICKLE_VERBOSE_DEBUG else 0 + +if verbose_level > 1: + logger.warning( + "Environmental variable RAY_PICKLE_VERBOSE_DEBUG is set to " + f"'{verbose_level}', this enabled python-based serialization backend " + f"instead of C-Pickle. Serialization would be very slow." + ) + from ray.cloudpickle import py_pickle as pickle + from ray.cloudpickle.py_pickle import Pickler +else: + import pickle # noqa: F401 + from _pickle import Pickler # noqa: F401 diff --git a/.venv/lib/python3.11/site-packages/ray/cloudpickle/py_pickle.py b/.venv/lib/python3.11/site-packages/ray/cloudpickle/py_pickle.py new file mode 100644 index 0000000000000000000000000000000000000000..b21840702a5167b38a0ff167eccacc8377453677 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/cloudpickle/py_pickle.py @@ -0,0 +1,30 @@ +from pickle import ( + _Pickler, + _Unpickler as Unpickler, + _loads as loads, + _load as load, + PickleError, + PicklingError, + UnpicklingError, + HIGHEST_PROTOCOL, +) + +__all__ = [ + "PickleError", + "PicklingError", + "UnpicklingError", + "Pickler", + "Unpickler", + "load", + "loads", + "HIGHEST_PROTOCOL", +] + + +class Pickler(_Pickler): + def __init__(self, file, protocol=None, *, fix_imports=True, buffer_callback=None): + super().__init__( + file, protocol, fix_imports=fix_imports, buffer_callback=buffer_callback + ) + # avoid being overrided by cloudpickle + self.dispatch = _Pickler.dispatch.copy() diff --git a/.venv/lib/python3.11/site-packages/ray/scripts/__init__.py b/.venv/lib/python3.11/site-packages/ray/scripts/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/.venv/lib/python3.11/site-packages/ray/scripts/__pycache__/__init__.cpython-311.pyc b/.venv/lib/python3.11/site-packages/ray/scripts/__pycache__/__init__.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c381c26c02100ecd26097e283774c37b08612a3e Binary files /dev/null and b/.venv/lib/python3.11/site-packages/ray/scripts/__pycache__/__init__.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/ray/scripts/scripts.py b/.venv/lib/python3.11/site-packages/ray/scripts/scripts.py new file mode 100644 index 0000000000000000000000000000000000000000..1bb2e536bd137bff31de0d4f84cd152998330f11 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/scripts/scripts.py @@ -0,0 +1,2695 @@ +import copy +import json +import logging +import os +import platform +import signal +import subprocess +import sys +import time +import urllib +import urllib.parse +import warnings +import shutil +from datetime import datetime +from typing import Optional, Set, List, Tuple +from ray.dashboard.modules.metrics import install_and_start_prometheus +from ray.util.check_open_ports import check_open_ports +import requests + +import click +import colorama +import psutil +import yaml + +import ray +import ray._private.ray_constants as ray_constants +import ray._private.services as services +from ray._private.utils import ( + check_ray_client_dependencies_installed, + parse_resources_json, + parse_node_labels_json, +) +from ray._private.internal_api import memory_summary +from ray._private.storage import _load_class +from ray._private.usage import usage_lib +from ray.autoscaler._private.cli_logger import add_click_logging_options, cf, cli_logger +from ray.autoscaler._private.commands import ( + RUN_ENV_TYPES, + attach_cluster, + create_or_update_cluster, + debug_status, + exec_cluster, + get_cluster_dump_archive, + get_head_node_ip, + get_local_dump_archive, + get_worker_node_ips, + kill_node, + monitor_cluster, + rsync, + teardown_cluster, +) +from ray.autoscaler._private.constants import RAY_PROCESSES +from ray.autoscaler._private.fake_multi_node.node_provider import FAKE_HEAD_NODE_ID +from ray.util.annotations import PublicAPI +from ray.core.generated import autoscaler_pb2 + + +logger = logging.getLogger(__name__) + + +def _check_ray_version(gcs_client): + import ray._private.usage.usage_lib as ray_usage_lib + + cluster_metadata = ray_usage_lib.get_cluster_metadata(gcs_client) + if cluster_metadata and cluster_metadata["ray_version"] != ray.__version__: + raise RuntimeError( + "Ray version mismatch: cluster has Ray version " + f'{cluster_metadata["ray_version"]} ' + f"but local Ray version is {ray.__version__}" + ) + + +@click.group() +@click.option( + "--logging-level", + required=False, + default=ray_constants.LOGGER_LEVEL, + type=str, + help=ray_constants.LOGGER_LEVEL_HELP, +) +@click.option( + "--logging-format", + required=False, + default=ray_constants.LOGGER_FORMAT, + type=str, + help=ray_constants.LOGGER_FORMAT_HELP, +) +@click.version_option() +def cli(logging_level, logging_format): + level = logging.getLevelName(logging_level.upper()) + ray._private.ray_logging.setup_logger(level, logging_format) + cli_logger.set_format(format_tmpl=logging_format) + + +@click.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--port", + "-p", + required=False, + type=int, + default=ray_constants.DEFAULT_DASHBOARD_PORT, + help="The local port to forward to the dashboard", +) +@click.option( + "--remote-port", + required=False, + type=int, + default=ray_constants.DEFAULT_DASHBOARD_PORT, + help="The remote port your dashboard runs on", +) +@click.option( + "--no-config-cache", + is_flag=True, + default=False, + help="Disable the local cluster config cache.", +) +@PublicAPI +def dashboard(cluster_config_file, cluster_name, port, remote_port, no_config_cache): + """Port-forward a Ray cluster's dashboard to the local machine.""" + # Sleeping in a loop is preferable to `sleep infinity` because the latter + # only works on linux. + # Find the first open port sequentially from `remote_port`. + try: + port_forward = [ + (port, remote_port), + ] + click.echo( + "Attempting to establish dashboard locally at" + " http://localhost:{}/ connected to" + " remote port {}".format(port, remote_port) + ) + # We want to probe with a no-op that returns quickly to avoid + # exceptions caused by network errors. + exec_cluster( + cluster_config_file, + override_cluster_name=cluster_name, + port_forward=port_forward, + no_config_cache=no_config_cache, + ) + click.echo("Successfully established connection.") + except Exception as e: + raise click.ClickException( + "Failed to forward dashboard from remote port {1} to local port " + "{0}. There are a couple possibilities: \n 1. The remote port is " + "incorrectly specified \n 2. The local port {0} is already in " + "use.\n The exception is: {2}".format(port, remote_port, e) + ) from None + + +def continue_debug_session(live_jobs: Set[str]): + """Continue active debugging session. + + This function will connect 'ray debug' to the right debugger + when a user is stepping between Ray tasks. + """ + active_sessions = ray.experimental.internal_kv._internal_kv_list( + "RAY_PDB_", namespace=ray_constants.KV_NAMESPACE_PDB + ) + + for active_session in active_sessions: + if active_session.startswith(b"RAY_PDB_CONTINUE"): + # Check to see that the relevant job is still alive. + data = ray.experimental.internal_kv._internal_kv_get( + active_session, namespace=ray_constants.KV_NAMESPACE_PDB + ) + if json.loads(data)["job_id"] not in live_jobs: + ray.experimental.internal_kv._internal_kv_del( + active_session, namespace=ray_constants.KV_NAMESPACE_PDB + ) + continue + + print("Continuing pdb session in different process...") + key = b"RAY_PDB_" + active_session[len("RAY_PDB_CONTINUE_") :] + while True: + data = ray.experimental.internal_kv._internal_kv_get( + key, namespace=ray_constants.KV_NAMESPACE_PDB + ) + if data: + session = json.loads(data) + if "exit_debugger" in session or session["job_id"] not in live_jobs: + ray.experimental.internal_kv._internal_kv_del( + key, namespace=ray_constants.KV_NAMESPACE_PDB + ) + return + host, port = session["pdb_address"].split(":") + ray.util.rpdb._connect_pdb_client(host, int(port)) + ray.experimental.internal_kv._internal_kv_del( + key, namespace=ray_constants.KV_NAMESPACE_PDB + ) + continue_debug_session(live_jobs) + return + time.sleep(1.0) + + +def none_to_empty(s): + if s is None: + return "" + return s + + +def format_table(table): + """Format a table as a list of lines with aligned columns.""" + result = [] + col_width = [max(len(x) for x in col) for col in zip(*table)] + for line in table: + result.append( + " | ".join("{0:{1}}".format(x, col_width[i]) for i, x in enumerate(line)) + ) + return result + + +@cli.command() +@click.option( + "--address", required=False, type=str, help="Override the address to connect to." +) +@click.option( + "-v", + "--verbose", + required=False, + is_flag=True, + help="Shows additional fields in breakpoint selection page.", +) +def debug(address: str, verbose: bool): + """Show all active breakpoints and exceptions in the Ray debugger.""" + address = services.canonicalize_bootstrap_address_or_die(address) + logger.info(f"Connecting to Ray instance at {address}.") + ray.init(address=address, log_to_driver=False) + if os.environ.get("RAY_DEBUG", "1") != "legacy": + print( + f"{colorama.Fore.YELLOW}NOTE: The distributed debugger " + "https://docs.ray.io/en/latest/ray-observability" + "/ray-distributed-debugger.html is now the default " + "due to better interactive debugging support. If you want " + "to keep using 'ray debug' please set RAY_DEBUG=legacy " + f"in your cluster (e.g. via runtime environment).{colorama.Fore.RESET}" + ) + while True: + # Used to filter out and clean up entries from dead jobs. + live_jobs = { + job["JobID"] for job in ray._private.state.jobs() if not job["IsDead"] + } + continue_debug_session(live_jobs) + + active_sessions = ray.experimental.internal_kv._internal_kv_list( + "RAY_PDB_", namespace=ray_constants.KV_NAMESPACE_PDB + ) + print("Active breakpoints:") + sessions_data = [] + for active_session in active_sessions: + data = json.loads( + ray.experimental.internal_kv._internal_kv_get( + active_session, namespace=ray_constants.KV_NAMESPACE_PDB + ) + ) + # Check that the relevant job is alive, else clean up the entry. + if data["job_id"] in live_jobs: + sessions_data.append(data) + else: + ray.experimental.internal_kv._internal_kv_del( + active_session, namespace=ray_constants.KV_NAMESPACE_PDB + ) + sessions_data = sorted( + sessions_data, key=lambda data: data["timestamp"], reverse=True + ) + if verbose: + table = [ + [ + "index", + "timestamp", + "Ray task", + "filename:lineno", + "Task ID", + "Worker ID", + "Actor ID", + "Node ID", + ] + ] + for i, data in enumerate(sessions_data): + date = datetime.utcfromtimestamp(data["timestamp"]).strftime( + "%Y-%m-%d %H:%M:%S" + ) + table.append( + [ + str(i), + date, + data["proctitle"], + data["filename"] + ":" + str(data["lineno"]), + data["task_id"], + data["worker_id"], + none_to_empty(data["actor_id"]), + data["node_id"], + ] + ) + else: + # Non verbose mode: no IDs. + table = [["index", "timestamp", "Ray task", "filename:lineno"]] + for i, data in enumerate(sessions_data): + date = datetime.utcfromtimestamp(data["timestamp"]).strftime( + "%Y-%m-%d %H:%M:%S" + ) + table.append( + [ + str(i), + date, + data["proctitle"], + data["filename"] + ":" + str(data["lineno"]), + ] + ) + for i, line in enumerate(format_table(table)): + print(line) + if i >= 1 and not sessions_data[i - 1]["traceback"].startswith( + "NoneType: None" + ): + print(sessions_data[i - 1]["traceback"]) + inp = input("Enter breakpoint index or press enter to refresh: ") + if inp == "": + print() + continue + else: + index = int(inp) + session = json.loads( + ray.experimental.internal_kv._internal_kv_get( + active_sessions[index], namespace=ray_constants.KV_NAMESPACE_PDB + ) + ) + host, port = session["pdb_address"].split(":") + ray.util.rpdb._connect_pdb_client(host, int(port)) + + +@cli.command() +@click.option( + "--node-ip-address", required=False, type=str, help="the IP address of this node" +) +@click.option("--address", required=False, type=str, help="the address to use for Ray") +@click.option( + "--port", + type=int, + required=False, + help=f"the port of the head ray process. If not provided, defaults to " + f"{ray_constants.DEFAULT_PORT}; if port is set to 0, we will" + f" allocate an available port.", +) +@click.option( + "--node-name", + required=False, + hidden=True, + type=str, + help="the user-provided identifier or name for this node. " + "Defaults to the node's ip_address", +) +@click.option( + "--redis-username", + required=False, + hidden=True, + type=str, + default=ray_constants.REDIS_DEFAULT_USERNAME, + help="If provided, secure Redis ports with this username", +) +@click.option( + "--redis-password", + required=False, + hidden=True, + type=str, + default=ray_constants.REDIS_DEFAULT_PASSWORD, + help="If provided, secure Redis ports with this password", +) +@click.option( + "--redis-shard-ports", + required=False, + hidden=True, + type=str, + help="the port to use for the Redis shards other than the primary Redis shard", +) +@click.option( + "--object-manager-port", + required=False, + type=int, + help="the port to use for starting the object manager", +) +@click.option( + "--node-manager-port", + required=False, + type=int, + default=0, + help="the port to use for starting the node manager", +) +@click.option( + "--gcs-server-port", + required=False, + type=int, + help="Port number for the GCS server.", +) +@click.option( + "--min-worker-port", + required=False, + type=int, + default=10002, + help="the lowest port number that workers will bind on. If not set, " + "random ports will be chosen.", +) +@click.option( + "--max-worker-port", + required=False, + type=int, + default=19999, + help="the highest port number that workers will bind on. If set, " + "'--min-worker-port' must also be set.", +) +@click.option( + "--worker-port-list", + required=False, + help="a comma-separated list of open ports for workers to bind on. " + "Overrides '--min-worker-port' and '--max-worker-port'.", +) +@click.option( + "--ray-client-server-port", + required=False, + type=int, + default=None, + help="the port number the ray client server binds on, default to 10001, " + "or None if ray[client] is not installed.", +) +@click.option( + "--memory", + required=False, + hidden=True, + type=int, + help="The amount of memory (in bytes) to make available to workers. " + "By default, this is set to the available memory on the node.", +) +@click.option( + "--object-store-memory", + required=False, + type=int, + help="The amount of memory (in bytes) to start the object store with. " + "By default, this is 30% (ray_constants.DEFAULT_OBJECT_STORE_MEMORY_PROPORTION) " + "of available system memory capped by " + "the shm size and 200G (ray_constants.DEFAULT_OBJECT_STORE_MAX_MEMORY_BYTES) " + "but can be set higher.", +) +@click.option( + "--redis-max-memory", + required=False, + hidden=True, + type=int, + help="The max amount of memory (in bytes) to allow redis to use. Once the " + "limit is exceeded, redis will start LRU eviction of entries. This only " + "applies to the sharded redis tables (task, object, and profile tables). " + "By default this is capped at 10GB but can be set higher.", +) +@click.option( + "--num-cpus", required=False, type=int, help="the number of CPUs on this node" +) +@click.option( + "--num-gpus", required=False, type=int, help="the number of GPUs on this node" +) +@click.option( + "--resources", + required=False, + default="{}", + type=str, + help="A JSON serialized dictionary mapping resource name to resource quantity." + + ( + r""" + +Windows command prompt users must ensure to double quote command line arguments. Because +JSON requires the use of double quotes you must escape these arguments as well, for +example: + + ray start --head --resources="{\"special_hardware\":1, \"custom_label\":1}" + +Windows powershell users need additional escaping: + + ray start --head --resources="{\""special_hardware\"":1, \""custom_label\"":1}" +""" + if platform.system() == "Windows" + else "" + ), +) +@click.option( + "--head", + is_flag=True, + default=False, + help="provide this argument for the head node", +) +@click.option( + "--include-dashboard", + default=None, + type=bool, + help="provide this argument to start the Ray dashboard GUI", +) +@click.option( + "--dashboard-host", + required=False, + default=ray_constants.DEFAULT_DASHBOARD_IP, + help="the host to bind the dashboard server to, either localhost " + "(127.0.0.1) or 0.0.0.0 (available from all interfaces). By default, this " + "is 127.0.0.1", +) +@click.option( + "--dashboard-port", + required=False, + type=int, + default=ray_constants.DEFAULT_DASHBOARD_PORT, + help="the port to bind the dashboard server to--defaults to {}".format( + ray_constants.DEFAULT_DASHBOARD_PORT + ), +) +@click.option( + "--dashboard-agent-listen-port", + type=int, + default=ray_constants.DEFAULT_DASHBOARD_AGENT_LISTEN_PORT, + help="the port for dashboard agents to listen for http on.", +) +@click.option( + "--dashboard-agent-grpc-port", + type=int, + default=None, + help="the port for dashboard agents to listen for grpc on.", +) +@click.option( + "--dashboard-grpc-port", + type=int, + default=None, + help="The port for the dashboard head to listen for grpc on.", +) +@click.option( + "--runtime-env-agent-port", + type=int, + default=None, + help="The port for the runtime enviroment agents to listen for http on.", +) +@click.option( + "--block", + is_flag=True, + default=False, + help="provide this argument to block forever in this command", +) +@click.option( + "--plasma-directory", + required=False, + type=str, + help="object store directory for memory mapped files", +) +@click.option( + "--autoscaling-config", + required=False, + type=str, + help="the file that contains the autoscaling config", +) +@click.option( + "--no-redirect-output", + is_flag=True, + default=False, + help="do not redirect non-worker stdout and stderr to files", +) +@click.option( + "--plasma-store-socket-name", + default=None, + help="manually specify the socket name of the plasma store", +) +@click.option( + "--raylet-socket-name", + default=None, + help="manually specify the socket path of the raylet process", +) +@click.option( + "--temp-dir", + default=None, + help="manually specify the root temporary dir of the Ray process, only " + "works when --head is specified", +) +@click.option( + "--storage", + default=None, + help="the persistent storage URI for the cluster. Experimental.", +) +@click.option( + "--system-config", + default=None, + hidden=True, + type=json.loads, + help="Override system configuration defaults.", +) +@click.option( + "--enable-object-reconstruction", + is_flag=True, + default=False, + hidden=True, + help="Specify whether object reconstruction will be used for this cluster.", +) +@click.option( + "--metrics-export-port", + type=int, + default=None, + help="the port to use to expose Ray metrics through a Prometheus endpoint.", +) +@click.option( + "--no-monitor", + is_flag=True, + hidden=True, + default=False, + help="If True, the ray autoscaler monitor for this cluster will not be started.", +) +@click.option( + "--tracing-startup-hook", + type=str, + hidden=True, + default=None, + help="The function that sets up tracing with a tracing provider, remote " + "span processor, and additional instruments. See docs.ray.io/tracing.html " + "for more info.", +) +@click.option( + "--ray-debugger-external", + is_flag=True, + default=False, + help="Make the Ray debugger available externally to the node. This is only " + "safe to activate if the node is behind a firewall.", +) +@click.option( + "--disable-usage-stats", + is_flag=True, + default=False, + help="If True, the usage stats collection will be disabled.", +) +@click.option( + "--labels", + required=False, + hidden=True, + default="{}", + type=str, + help="a JSON serialized dictionary mapping label name to label value.", +) +@click.option( + "--include-log-monitor", + default=None, + type=bool, + help="If set to True or left unset, a log monitor will start monitoring " + "the log files of all processes on this node and push their contents to GCS. " + "Only one log monitor should be started per physical host to avoid log " + "duplication on the driver process.", +) +@add_click_logging_options +@PublicAPI +def start( + node_ip_address, + address, + port, + node_name, + redis_username, + redis_password, + redis_shard_ports, + object_manager_port, + node_manager_port, + gcs_server_port, + min_worker_port, + max_worker_port, + worker_port_list, + ray_client_server_port, + memory, + object_store_memory, + redis_max_memory, + num_cpus, + num_gpus, + resources, + head, + include_dashboard, + dashboard_host, + dashboard_port, + dashboard_agent_listen_port, + dashboard_agent_grpc_port, + dashboard_grpc_port, + runtime_env_agent_port, + block, + plasma_directory, + autoscaling_config, + no_redirect_output, + plasma_store_socket_name, + raylet_socket_name, + temp_dir, + storage, + system_config, + enable_object_reconstruction, + metrics_export_port, + no_monitor, + tracing_startup_hook, + ray_debugger_external, + disable_usage_stats, + labels, + include_log_monitor, +): + """Start Ray processes manually on the local machine.""" + # TODO(hjiang): Expose physical mode interface to ray cluster start command after + # all features implemented. + + if gcs_server_port is not None: + cli_logger.error( + "`{}` is deprecated and ignored. Use {} to specify " + "GCS server port on head node.", + cf.bold("--gcs-server-port"), + cf.bold("--port"), + ) + # Whether the original arguments include node_ip_address. + include_node_ip_address = False + if node_ip_address is not None: + include_node_ip_address = True + node_ip_address = services.resolve_ip_for_localhost(node_ip_address) + + resources = parse_resources_json(resources, cli_logger, cf) + labels_dict = parse_node_labels_json(labels, cli_logger, cf) + + if plasma_store_socket_name is not None: + warnings.warn( + "plasma_store_socket_name is deprecated and will be removed. You are not " + "supposed to specify this parameter as it's internal.", + DeprecationWarning, + stacklevel=2, + ) + if raylet_socket_name is not None: + warnings.warn( + "raylet_socket_name is deprecated and will be removed. You are not " + "supposed to specify this parameter as it's internal.", + DeprecationWarning, + stacklevel=2, + ) + if temp_dir and not head: + cli_logger.warning( + f"`--temp-dir={temp_dir}` option will be ignored. " + "`--head` is a required flag to use `--temp-dir`. " + "temp_dir is only configurable from a head node. " + "All the worker nodes will use the same temp_dir as a head node. " + ) + temp_dir = None + + redirect_output = None if not no_redirect_output else True + + # no client, no port -> ok + # no port, has client -> default to 10001 + # has port, no client -> value error + # has port, has client -> ok, check port validity + has_ray_client = check_ray_client_dependencies_installed() + if has_ray_client and ray_client_server_port is None: + ray_client_server_port = 10001 + + ray_params = ray._private.parameter.RayParams( + node_ip_address=node_ip_address, + node_name=node_name if node_name else node_ip_address, + min_worker_port=min_worker_port, + max_worker_port=max_worker_port, + worker_port_list=worker_port_list, + ray_client_server_port=ray_client_server_port, + object_manager_port=object_manager_port, + node_manager_port=node_manager_port, + memory=memory, + object_store_memory=object_store_memory, + redis_username=redis_username, + redis_password=redis_password, + redirect_output=redirect_output, + num_cpus=num_cpus, + num_gpus=num_gpus, + resources=resources, + labels=labels_dict, + autoscaling_config=autoscaling_config, + plasma_directory=plasma_directory, + huge_pages=False, + plasma_store_socket_name=plasma_store_socket_name, + raylet_socket_name=raylet_socket_name, + temp_dir=temp_dir, + storage=storage, + include_dashboard=include_dashboard, + dashboard_host=dashboard_host, + dashboard_port=dashboard_port, + dashboard_agent_listen_port=dashboard_agent_listen_port, + metrics_agent_port=dashboard_agent_grpc_port, + dashboard_grpc_port=dashboard_grpc_port, + runtime_env_agent_port=runtime_env_agent_port, + _system_config=system_config, + enable_object_reconstruction=enable_object_reconstruction, + metrics_export_port=metrics_export_port, + no_monitor=no_monitor, + tracing_startup_hook=tracing_startup_hook, + ray_debugger_external=ray_debugger_external, + enable_physical_mode=False, + include_log_monitor=include_log_monitor, + ) + + if ray_constants.RAY_START_HOOK in os.environ: + _load_class(os.environ[ray_constants.RAY_START_HOOK])(ray_params, head) + + if head: + # Start head node. + + if disable_usage_stats: + usage_lib.set_usage_stats_enabled_via_env_var(False) + usage_lib.show_usage_stats_prompt(cli=True) + cli_logger.newline() + + if port is None: + port = ray_constants.DEFAULT_PORT + + # Set bootstrap port. + assert ray_params.redis_port is None + assert ray_params.gcs_server_port is None + ray_params.gcs_server_port = port + + if os.environ.get("RAY_FAKE_CLUSTER"): + ray_params.env_vars = { + "RAY_OVERRIDE_NODE_ID_FOR_TESTING": FAKE_HEAD_NODE_ID + } + + num_redis_shards = None + # Start Ray on the head node. + if redis_shard_ports is not None and address is None: + redis_shard_ports = redis_shard_ports.split(",") + # Infer the number of Redis shards from the ports if the number is + # not provided. + num_redis_shards = len(redis_shard_ports) + + # This logic is deprecated and will be removed later. + if address is not None: + cli_logger.warning( + "Specifying {} for external Redis address is deprecated. " + "Please specify environment variable {}={} instead.", + cf.bold("--address"), + cf.bold("RAY_REDIS_ADDRESS"), + address, + ) + external_addresses = address.split(",") + + # We reuse primary redis as sharding when there's only one + # instance provided. + if len(external_addresses) == 1: + external_addresses.append(external_addresses[0]) + + ray_params.update_if_absent(external_addresses=external_addresses) + num_redis_shards = len(external_addresses) - 1 + if redis_username == ray_constants.REDIS_DEFAULT_USERNAME: + cli_logger.warning( + "`{}` should not be specified as empty string if " + "external Redis server(s) `{}` points to requires " + "username.", + cf.bold("--redis-username"), + cf.bold("--address"), + ) + if redis_password == ray_constants.REDIS_DEFAULT_PASSWORD: + cli_logger.warning( + "`{}` should not be specified as empty string if " + "external redis server(s) `{}` points to requires " + "password.", + cf.bold("--redis-password"), + cf.bold("--address"), + ) + + # Get the node IP address if one is not provided. + ray_params.update_if_absent(node_ip_address=services.get_node_ip_address()) + cli_logger.labeled_value("Local node IP", ray_params.node_ip_address) + + # Initialize Redis settings. + ray_params.update_if_absent( + redis_shard_ports=redis_shard_ports, + redis_max_memory=redis_max_memory, + num_redis_shards=num_redis_shards, + redis_max_clients=None, + ) + + # Fail early when starting a new cluster when one is already running + if address is None: + default_address = f"{ray_params.node_ip_address}:{port}" + bootstrap_address = services.find_bootstrap_address(temp_dir) + if ( + default_address == bootstrap_address + and bootstrap_address in services.find_gcs_addresses() + ): + # The default address is already in use by a local running GCS + # instance. + raise ConnectionError( + f"Ray is trying to start at {default_address}, " + f"but is already running at {bootstrap_address}. " + "Please specify a different port using the `--port`" + " flag of `ray start` command." + ) + + node = ray._private.node.Node( + ray_params, head=True, shutdown_at_exit=block, spawn_reaper=block + ) + + bootstrap_address = node.address + + # this is a noop if new-style is not set, so the old logger calls + # are still in place + cli_logger.newline() + startup_msg = "Ray runtime started." + cli_logger.success("-" * len(startup_msg)) + cli_logger.success(startup_msg) + cli_logger.success("-" * len(startup_msg)) + cli_logger.newline() + with cli_logger.group("Next steps"): + dashboard_url = node.address_info["webui_url"] + if ray_constants.ENABLE_RAY_CLUSTER: + cli_logger.print("To add another node to this Ray cluster, run") + # NOTE(kfstorm): Java driver rely on this line to get the address + # of the cluster. Please be careful when updating this line. + cli_logger.print( + cf.bold(" {} ray start --address='{}'"), + f" {ray_constants.ENABLE_RAY_CLUSTERS_ENV_VAR}=1" + if ray_constants.IS_WINDOWS_OR_OSX + else "", + bootstrap_address, + ) + + cli_logger.newline() + cli_logger.print("To connect to this Ray cluster:") + with cli_logger.indented(): + cli_logger.print("{} ray", cf.magenta("import")) + cli_logger.print( + "ray{}init({})", + cf.magenta("."), + "_node_ip_address{}{}".format( + cf.magenta("="), cf.yellow("'" + node_ip_address + "'") + ) + if include_node_ip_address + else "", + ) + + if dashboard_url: + cli_logger.newline() + cli_logger.print("To submit a Ray job using the Ray Jobs CLI:") + cli_logger.print( + cf.bold( + " RAY_ADDRESS='http://{}' ray job submit " + "--working-dir . " + "-- python my_script.py" + ), + dashboard_url, + ) + cli_logger.newline() + cli_logger.print( + "See https://docs.ray.io/en/latest/cluster/running-applications" + "/job-submission/index.html " + ) + cli_logger.print( + "for more information on submitting Ray jobs to the Ray cluster." + ) + + cli_logger.newline() + cli_logger.print("To terminate the Ray runtime, run") + cli_logger.print(cf.bold(" ray stop")) + + cli_logger.newline() + cli_logger.print("To view the status of the cluster, use") + cli_logger.print(" {}".format(cf.bold("ray status"))) + + if dashboard_url: + cli_logger.newline() + cli_logger.print("To monitor and debug Ray, view the dashboard at ") + cli_logger.print( + " {}".format( + cf.bold(dashboard_url), + ) + ) + + cli_logger.newline() + cli_logger.print( + cf.underlined( + "If connection to the dashboard fails, check your " + "firewall settings and " + "network configuration." + ) + ) + ray_params.gcs_address = bootstrap_address + else: + # Start worker node. + if not ray_constants.ENABLE_RAY_CLUSTER: + cli_logger.abort( + "Multi-node Ray clusters are not supported on Windows and OSX. " + "Restart the Ray cluster with the environment variable `{}=1` " + "to proceed anyway.", + cf.bold(ray_constants.ENABLE_RAY_CLUSTERS_ENV_VAR), + ) + raise Exception( + "Multi-node Ray clusters are not supported on Windows and OSX. " + "Restart the Ray cluster with the environment variable " + f"`{ray_constants.ENABLE_RAY_CLUSTERS_ENV_VAR}=1` to proceed " + "anyway.", + ) + + # Ensure `--address` flag is specified. + if address is None: + cli_logger.abort( + "`{}` is a required flag unless starting a head node with `{}`.", + cf.bold("--address"), + cf.bold("--head"), + ) + raise Exception( + "`--address` is a required flag unless starting a " + "head node with `--head`." + ) + + # Raise error if any head-only flag are specified. + head_only_flags = { + "--port": port, + "--redis-shard-ports": redis_shard_ports, + "--include-dashboard": include_dashboard, + } + for flag, val in head_only_flags.items(): + if val is None: + continue + cli_logger.abort( + "`{}` should only be specified when starting head node with `{}`.", + cf.bold(flag), + cf.bold("--head"), + ) + raise ValueError( + f"{flag} should only be specified when starting head node " + "with `--head`." + ) + + # Start Ray on a non-head node. + bootstrap_address = services.canonicalize_bootstrap_address( + address, temp_dir=temp_dir + ) + + if bootstrap_address is None: + cli_logger.abort( + "Cannot canonicalize address `{}={}`.", + cf.bold("--address"), + cf.bold(address), + ) + raise Exception("Cannot canonicalize address " f"`--address={address}`.") + + ray_params.gcs_address = bootstrap_address + + # Get the node IP address if one is not provided. + ray_params.update_if_absent( + node_ip_address=services.get_node_ip_address(bootstrap_address) + ) + + cli_logger.labeled_value("Local node IP", ray_params.node_ip_address) + + node = ray._private.node.Node( + ray_params, head=False, shutdown_at_exit=block, spawn_reaper=block + ) + temp_dir = node.get_temp_dir_path() + + # TODO(hjiang): Validate whether specified resource is true for physical + # resource. + + # Ray and Python versions should probably be checked before + # initializing Node. + node.check_version_info() + + cli_logger.newline() + startup_msg = "Ray runtime started." + cli_logger.success("-" * len(startup_msg)) + cli_logger.success(startup_msg) + cli_logger.success("-" * len(startup_msg)) + cli_logger.newline() + cli_logger.print("To terminate the Ray runtime, run") + cli_logger.print(cf.bold(" ray stop")) + cli_logger.flush() + + assert ray_params.gcs_address is not None + ray._private.utils.write_ray_address(ray_params.gcs_address, temp_dir) + + if block: + cli_logger.newline() + with cli_logger.group(cf.bold("--block")): + cli_logger.print( + "This command will now block forever until terminated by a signal." + ) + cli_logger.print( + "Running subprocesses are monitored and a message will be " + "printed if any of them terminate unexpectedly. Subprocesses " + "exit with SIGTERM will be treated as graceful, thus NOT reported." + ) + cli_logger.flush() + + while True: + time.sleep(1) + deceased = node.dead_processes() + + # Report unexpected exits of subprocesses with unexpected return codes. + # We are explicitly expecting SIGTERM because this is how `ray stop` sends + # shutdown signal to subprocesses, i.e. log_monitor, raylet... + # NOTE(rickyyx): We are treating 128+15 as an expected return code since + # this is what autoscaler/_private/monitor.py does upon SIGTERM + # handling. + expected_return_codes = [ + 0, + signal.SIGTERM, + -1 * signal.SIGTERM, + 128 + signal.SIGTERM, + ] + unexpected_deceased = [ + (process_type, process) + for process_type, process in deceased + if process.returncode not in expected_return_codes + ] + if len(unexpected_deceased) > 0: + cli_logger.newline() + cli_logger.error("Some Ray subprocesses exited unexpectedly:") + + with cli_logger.indented(): + for process_type, process in unexpected_deceased: + cli_logger.error( + "{}", + cf.bold(str(process_type)), + _tags={"exit code": str(process.returncode)}, + ) + + cli_logger.newline() + cli_logger.error("Remaining processes will be killed.") + # explicitly kill all processes since atexit handlers + # will not exit with errors. + node.kill_all_processes(check_alive=False, allow_graceful=False) + os._exit(1) + # not-reachable + + +@cli.command() +@click.option( + "-f", + "--force", + is_flag=True, + help="If set, ray will send SIGKILL instead of SIGTERM.", +) +@click.option( + "-g", + "--grace-period", + default=16, + help=( + "The time in seconds ray waits for processes to be properly terminated. " + "If processes are not terminated within the grace period, " + "they are forcefully terminated after the grace period. " + ), +) +@add_click_logging_options +@PublicAPI +def stop(force: bool, grace_period: int): + """Stop Ray processes manually on the local machine.""" + is_linux = sys.platform.startswith("linux") + total_procs_found = 0 + total_procs_stopped = 0 + procs_not_gracefully_killed = [] + + def kill_procs( + force: bool, grace_period: int, processes_to_kill: List[str] + ) -> Tuple[int, int, List[psutil.Process]]: + """Find all processes from `processes_to_kill` and terminate them. + + Unless `force` is specified, it gracefully kills processes. If + processes are not cleaned within `grace_period`, it force kill all + remaining processes. + + Returns: + total_procs_found: Total number of processes found from + `processes_to_kill` is added. + total_procs_stopped: Total number of processes gracefully + stopped from `processes_to_kill` is added. + procs_not_gracefully_killed: If processes are not killed + gracefully, they are added here. + """ + process_infos = [] + for proc in psutil.process_iter(["name", "cmdline"]): + try: + process_infos.append((proc, proc.name(), proc.cmdline())) + except psutil.Error: + pass + + stopped = [] + for keyword, filter_by_cmd in processes_to_kill: + if filter_by_cmd and is_linux and len(keyword) > 15: + # getting here is an internal bug, so we do not use cli_logger + msg = ( + "The filter string should not be more than {} " + "characters. Actual length: {}. Filter: {}" + ).format(15, len(keyword), keyword) + raise ValueError(msg) + + found = [] + for candidate in process_infos: + proc, proc_cmd, proc_args = candidate + corpus = ( + proc_cmd if filter_by_cmd else subprocess.list2cmdline(proc_args) + ) + if keyword in corpus: + found.append(candidate) + for proc, proc_cmd, proc_args in found: + proc_string = str(subprocess.list2cmdline(proc_args)) + try: + if force: + proc.kill() + else: + # TODO(mehrdadn): On Windows, this is forceful termination. + # We don't want CTRL_BREAK_EVENT, because that would + # terminate the entire process group. What to do? + proc.terminate() + + if force: + cli_logger.verbose( + "Killed `{}` {} ", + cf.bold(proc_string), + cf.dimmed("(via SIGKILL)"), + ) + else: + cli_logger.verbose( + "Send termination request to `{}` {}", + cf.bold(proc_string), + cf.dimmed("(via SIGTERM)"), + ) + + stopped.append(proc) + except psutil.NoSuchProcess: + cli_logger.verbose( + "Attempted to stop `{}`, but process was already dead.", + cf.bold(proc_string), + ) + except (psutil.Error, OSError) as ex: + cli_logger.error( + "Could not terminate `{}` due to {}", + cf.bold(proc_string), + str(ex), + ) + + # Wait for the processes to actually stop. + # Dedup processes. + stopped, alive = psutil.wait_procs(stopped, timeout=0) + procs_to_kill = stopped + alive + total_found = len(procs_to_kill) + + # Wait for grace period to terminate processes. + gone_procs = set() + + def on_terminate(proc): + gone_procs.add(proc) + cli_logger.print(f"{len(gone_procs)}/{total_found} stopped.", end="\r") + + stopped, alive = psutil.wait_procs( + procs_to_kill, timeout=grace_period, callback=on_terminate + ) + total_stopped = len(stopped) + + # For processes that are not killed within the grace period, + # we send force termination signals. + for proc in alive: + proc.kill() + # Wait a little bit to make sure processes are killed forcefully. + psutil.wait_procs(alive, timeout=2) + return total_found, total_stopped, alive + + # Process killing procedure: we put processes into 3 buckets. + # Bucket 1: raylet + # Bucket 2: all other processes, e.g. dashboard, runtime env agents + # Bucket 3: gcs_server. + # + # For each bucket, we send sigterm to all processes, then wait for 30s, then if + # they are still alive, send sigkill. + processes_to_kill = RAY_PROCESSES + # Raylet should exit before all other processes exit. + # Otherwise, fate-sharing agents will complain and exit. + assert processes_to_kill[0][0] == "raylet" + + # GCS should exit after all other processes exit. + # Otherwise, some of processes may exit with an unexpected + # exit code which breaks ray start --block. + assert processes_to_kill[-1][0] == "gcs_server" + + buckets = [[processes_to_kill[0]], processes_to_kill[1:-1], [processes_to_kill[-1]]] + + for bucket in buckets: + found, stopped, alive = kill_procs(force, grace_period / len(buckets), bucket) + total_procs_found += found + total_procs_stopped += stopped + procs_not_gracefully_killed.extend(alive) + + # Print the termination result. + if total_procs_found == 0: + cli_logger.print("Did not find any active Ray processes.") + else: + if total_procs_stopped == total_procs_found: + cli_logger.success("Stopped all {} Ray processes.", total_procs_stopped) + else: + cli_logger.warning( + f"Stopped only {total_procs_stopped} out of {total_procs_found} " + f"Ray processes within the grace period {grace_period} seconds. " + f"Set `{cf.bold('-v')}` to see more details. " + f"Remaining processes {procs_not_gracefully_killed} " + "will be forcefully terminated.", + ) + cli_logger.warning( + f"You can also use `{cf.bold('--force')}` to forcefully terminate " + "processes or set higher `--grace-period` to wait longer time for " + "proper termination." + ) + + # NOTE(swang): This will not reset the cluster address for a user-defined + # temp_dir. This is fine since it will get overwritten the next time we + # call `ray start`. + ray._private.utils.reset_ray_address() + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--min-workers", + required=False, + type=int, + help="Override the configured min worker node count for the cluster.", +) +@click.option( + "--max-workers", + required=False, + type=int, + help="Override the configured max worker node count for the cluster.", +) +@click.option( + "--no-restart", + is_flag=True, + default=False, + help=( + "Whether to skip restarting Ray services during the update. " + "This avoids interrupting running jobs." + ), +) +@click.option( + "--restart-only", + is_flag=True, + default=False, + help=( + "Whether to skip running setup commands and only restart Ray. " + "This cannot be used with 'no-restart'." + ), +) +@click.option( + "--yes", "-y", is_flag=True, default=False, help="Don't ask for confirmation." +) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--no-config-cache", + is_flag=True, + default=False, + help="Disable the local cluster config cache.", +) +@click.option( + "--redirect-command-output", + is_flag=True, + default=False, + help="Whether to redirect command output to a file.", +) +@click.option( + "--use-login-shells/--use-normal-shells", + is_flag=True, + default=True, + help=( + "Ray uses login shells (bash --login -i) to run cluster commands " + "by default. If your workflow is compatible with normal shells, " + "this can be disabled for a better user experience." + ), +) +@click.option( + "--disable-usage-stats", + is_flag=True, + default=False, + help="If True, the usage stats collection will be disabled.", +) +@add_click_logging_options +@PublicAPI +def up( + cluster_config_file, + min_workers, + max_workers, + no_restart, + restart_only, + yes, + cluster_name, + no_config_cache, + redirect_command_output, + use_login_shells, + disable_usage_stats, +): + """Create or update a Ray cluster.""" + if disable_usage_stats: + usage_lib.set_usage_stats_enabled_via_env_var(False) + + if restart_only or no_restart: + cli_logger.doassert( + restart_only != no_restart, + "`{}` is incompatible with `{}`.", + cf.bold("--restart-only"), + cf.bold("--no-restart"), + ) + assert ( + restart_only != no_restart + ), "Cannot set both 'restart_only' and 'no_restart' at the same time!" + + if urllib.parse.urlparse(cluster_config_file).scheme in ("http", "https"): + try: + response = urllib.request.urlopen(cluster_config_file, timeout=5) + content = response.read() + file_name = cluster_config_file.split("/")[-1] + with open(file_name, "wb") as f: + f.write(content) + cluster_config_file = file_name + except urllib.error.HTTPError as e: + cli_logger.warning("{}", str(e)) + cli_logger.warning("Could not download remote cluster configuration file.") + create_or_update_cluster( + config_file=cluster_config_file, + override_min_workers=min_workers, + override_max_workers=max_workers, + no_restart=no_restart, + restart_only=restart_only, + yes=yes, + override_cluster_name=cluster_name, + no_config_cache=no_config_cache, + redirect_command_output=redirect_command_output, + use_login_shells=use_login_shells, + ) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--yes", "-y", is_flag=True, default=False, help="Don't ask for confirmation." +) +@click.option( + "--workers-only", is_flag=True, default=False, help="Only destroy the workers." +) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--keep-min-workers", + is_flag=True, + default=False, + help="Retain the minimal amount of workers specified in the config.", +) +@add_click_logging_options +@PublicAPI +def down(cluster_config_file, yes, workers_only, cluster_name, keep_min_workers): + """Tear down a Ray cluster.""" + teardown_cluster( + cluster_config_file, yes, workers_only, cluster_name, keep_min_workers + ) + + +@cli.command(hidden=True) +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--yes", "-y", is_flag=True, default=False, help="Don't ask for confirmation." +) +@click.option( + "--hard", + is_flag=True, + default=False, + help="Terminates the node via node provider (defaults to a 'soft kill'" + " which terminates Ray but does not actually delete the instances).", +) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +def kill_random_node(cluster_config_file, yes, hard, cluster_name): + """Kills a random Ray node. For testing purposes only.""" + click.echo( + "Killed node with IP " + kill_node(cluster_config_file, yes, hard, cluster_name) + ) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--lines", required=False, default=100, type=int, help="Number of lines to tail." +) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@add_click_logging_options +def monitor(cluster_config_file, lines, cluster_name): + """Tails the autoscaler logs of a Ray cluster.""" + monitor_cluster(cluster_config_file, lines, cluster_name) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--start", is_flag=True, default=False, help="Start the cluster if needed." +) +@click.option( + "--screen", is_flag=True, default=False, help="Run the command in screen." +) +@click.option("--tmux", is_flag=True, default=False, help="Run the command in tmux.") +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--no-config-cache", + is_flag=True, + default=False, + help="Disable the local cluster config cache.", +) +@click.option("--new", "-N", is_flag=True, help="Force creation of a new screen.") +@click.option( + "--port-forward", + "-p", + required=False, + multiple=True, + type=int, + help="Port to forward. Use this multiple times to forward multiple ports.", +) +@add_click_logging_options +@PublicAPI +def attach( + cluster_config_file, + start, + screen, + tmux, + cluster_name, + no_config_cache, + new, + port_forward, +): + """Create or attach to a SSH session to a Ray cluster.""" + port_forward = [(port, port) for port in list(port_forward)] + attach_cluster( + cluster_config_file, + start, + screen, + tmux, + cluster_name, + no_config_cache=no_config_cache, + new=new, + port_forward=port_forward, + ) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.argument("source", required=False, type=str) +@click.argument("target", required=False, type=str) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@add_click_logging_options +def rsync_down(cluster_config_file, source, target, cluster_name): + """Download specific files from a Ray cluster.""" + rsync(cluster_config_file, source, target, cluster_name, down=True) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.argument("source", required=False, type=str) +@click.argument("target", required=False, type=str) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--all-nodes", + "-A", + is_flag=True, + required=False, + help="Upload to all nodes (workers and head).", +) +@add_click_logging_options +def rsync_up(cluster_config_file, source, target, cluster_name, all_nodes): + """Upload specific files to a Ray cluster.""" + if all_nodes: + cli_logger.warning( + "WARNING: the `all_nodes` option is deprecated and will be " + "removed in the future. " + "Rsync to worker nodes is not reliable since workers may be " + "added during autoscaling. Please use the `file_mounts` " + "feature instead for consistent file sync in autoscaling clusters" + ) + + rsync( + cluster_config_file, + source, + target, + cluster_name, + down=False, + all_nodes=all_nodes, + ) + + +@cli.command(context_settings={"ignore_unknown_options": True}) +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--stop", + is_flag=True, + default=False, + help="Stop the cluster after the command finishes running.", +) +@click.option( + "--start", is_flag=True, default=False, help="Start the cluster if needed." +) +@click.option( + "--screen", is_flag=True, default=False, help="Run the command in a screen." +) +@click.option("--tmux", is_flag=True, default=False, help="Run the command in tmux.") +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--no-config-cache", + is_flag=True, + default=False, + help="Disable the local cluster config cache.", +) +@click.option( + "--port-forward", + "-p", + required=False, + multiple=True, + type=int, + help="Port to forward. Use this multiple times to forward multiple ports.", +) +@click.argument("script", required=True, type=str) +@click.option( + "--args", + required=False, + type=str, + help="(deprecated) Use '-- --arg1 --arg2' for script args.", +) +@click.argument("script_args", nargs=-1) +@click.option( + "--disable-usage-stats", + is_flag=True, + default=False, + help="If True, the usage stats collection will be disabled.", +) +@click.option( + "--extra-screen-args", + default=None, + help="if screen is enabled, add the provided args to it. A useful example " + "usage scenario is passing --extra-screen-args='-Logfile /full/path/blah_log.txt'" + " as it redirects screen output also to a custom file", +) +@add_click_logging_options +def submit( + cluster_config_file, + screen, + tmux, + stop, + start, + cluster_name, + no_config_cache, + port_forward, + script, + args, + script_args, + disable_usage_stats, + extra_screen_args: Optional[str] = None, +): + """Uploads and runs a script on the specified cluster. + + The script is automatically synced to the following location: + + os.path.join("~", os.path.basename(script)) + + Example: + ray submit [CLUSTER.YAML] experiment.py -- --smoke-test + """ + cli_logger.doassert( + not (screen and tmux), + "`{}` and `{}` are incompatible.", + cf.bold("--screen"), + cf.bold("--tmux"), + ) + cli_logger.doassert( + not (script_args and args), + "`{0}` and `{1}` are incompatible. Use only `{1}`.\nExample: `{2}`", + cf.bold("--args"), + cf.bold("-- "), + cf.bold("ray submit script.py -- --arg=123 --flag"), + ) + + assert not (screen and tmux), "Can specify only one of `screen` or `tmux`." + assert not (script_args and args), "Use -- --arg1 --arg2 for script args." + + if (extra_screen_args is not None) and (not screen): + cli_logger.abort( + "To use extra_screen_args, it is required to use the --screen flag" + ) + + if args: + cli_logger.warning( + "`{}` is deprecated and will be removed in the future.", cf.bold("--args") + ) + cli_logger.warning( + "Use `{}` instead. Example: `{}`.", + cf.bold("-- "), + cf.bold("ray submit script.py -- --arg=123 --flag"), + ) + cli_logger.newline() + + if start: + if disable_usage_stats: + usage_lib.set_usage_stats_enabled_via_env_var(False) + + create_or_update_cluster( + config_file=cluster_config_file, + override_min_workers=None, + override_max_workers=None, + no_restart=False, + restart_only=False, + yes=True, + override_cluster_name=cluster_name, + no_config_cache=no_config_cache, + redirect_command_output=False, + use_login_shells=True, + ) + target = os.path.basename(script) + target = os.path.join("~", target) + rsync( + cluster_config_file, + script, + target, + cluster_name, + no_config_cache=no_config_cache, + down=False, + ) + + command_parts = ["python", target] + if script_args: + command_parts += list(script_args) + elif args is not None: + command_parts += [args] + + port_forward = [(port, port) for port in list(port_forward)] + cmd = " ".join(command_parts) + exec_cluster( + cluster_config_file, + cmd=cmd, + run_env="docker", + screen=screen, + tmux=tmux, + stop=stop, + start=False, + override_cluster_name=cluster_name, + no_config_cache=no_config_cache, + port_forward=port_forward, + extra_screen_args=extra_screen_args, + ) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.argument("cmd", required=True, type=str) +@click.option( + "--run-env", + required=False, + type=click.Choice(RUN_ENV_TYPES), + default="auto", + help="Choose whether to execute this command in a container or directly on" + " the cluster head. Only applies when docker is configured in the YAML.", +) +@click.option( + "--stop", + is_flag=True, + default=False, + help="Stop the cluster after the command finishes running.", +) +@click.option( + "--start", is_flag=True, default=False, help="Start the cluster if needed." +) +@click.option( + "--screen", is_flag=True, default=False, help="Run the command in a screen." +) +@click.option("--tmux", is_flag=True, default=False, help="Run the command in tmux.") +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +@click.option( + "--no-config-cache", + is_flag=True, + default=False, + help="Disable the local cluster config cache.", +) +@click.option( + "--port-forward", + "-p", + required=False, + multiple=True, + type=int, + help="Port to forward. Use this multiple times to forward multiple ports.", +) +@click.option( + "--disable-usage-stats", + is_flag=True, + default=False, + help="If True, the usage stats collection will be disabled.", +) +@add_click_logging_options +def exec( + cluster_config_file, + cmd, + run_env, + screen, + tmux, + stop, + start, + cluster_name, + no_config_cache, + port_forward, + disable_usage_stats, +): + """Execute a command via SSH on a Ray cluster.""" + port_forward = [(port, port) for port in list(port_forward)] + + if start: + if disable_usage_stats: + usage_lib.set_usage_stats_enabled_via_env_var(False) + + exec_cluster( + cluster_config_file, + cmd=cmd, + run_env=run_env, + screen=screen, + tmux=tmux, + stop=stop, + start=start, + override_cluster_name=cluster_name, + no_config_cache=no_config_cache, + port_forward=port_forward, + _allow_uninitialized_state=True, + ) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +def get_head_ip(cluster_config_file, cluster_name): + """Return the head node IP of a Ray cluster.""" + click.echo(get_head_node_ip(cluster_config_file, cluster_name)) + + +@cli.command() +@click.argument("cluster_config_file", required=True, type=str) +@click.option( + "--cluster-name", + "-n", + required=False, + type=str, + help="Override the configured cluster name.", +) +def get_worker_ips(cluster_config_file, cluster_name): + """Return the list of worker IPs of a Ray cluster.""" + worker_ips = get_worker_node_ips(cluster_config_file, cluster_name) + click.echo("\n".join(worker_ips)) + + +@cli.command() +def disable_usage_stats(): + """Disable usage stats collection. + + This will not affect the current running clusters + but clusters launched in the future. + """ + usage_lib.set_usage_stats_enabled_via_config(enabled=False) + print( + "Usage stats disabled for future clusters. " + "Restart any current running clusters for this to take effect." + ) + + +@cli.command() +def enable_usage_stats(): + """Enable usage stats collection. + + This will not affect the current running clusters + but clusters launched in the future. + """ + usage_lib.set_usage_stats_enabled_via_config(enabled=True) + print( + "Usage stats enabled for future clusters. " + "Restart any current running clusters for this to take effect." + ) + + +@cli.command() +def stack(): + """Take a stack dump of all Python workers on the local machine.""" + COMMAND = """ +pyspy=`which py-spy` +if [ ! -e "$pyspy" ]; then + echo "ERROR: Please 'pip install py-spy'" \ + "or 'pip install ray[default]' first." + exit 1 +fi +# Set IFS to iterate over lines instead of over words. +export IFS=" +" +# Call sudo to prompt for password before anything has been printed. +sudo true +workers=$( + ps aux | grep -E ' ray::|default_worker.py' | grep -v raylet | grep -v grep +) +for worker in $workers; do + echo "Stack dump for $worker"; + pid=`echo $worker | awk '{print $2}'`; + case "$(uname -s)" in + Linux*) native=--native;; + *) native=;; + esac + sudo $pyspy dump --pid $pid $native; + echo; +done + """ + subprocess.call(COMMAND, shell=True) + + +@cli.command() +def microbenchmark(): + """Run a local Ray microbenchmark on the current machine.""" + from ray._private.ray_perf import main + + main() + + +@cli.command() +@click.option( + "--address", + required=False, + type=str, + help="Override the Ray address to connect to.", +) +def timeline(address): + """Take a Chrome tracing timeline for a Ray cluster.""" + address = services.canonicalize_bootstrap_address_or_die(address) + logger.info(f"Connecting to Ray instance at {address}.") + ray.init(address=address) + time = datetime.today().strftime("%Y-%m-%d_%H-%M-%S") + filename = os.path.join( + ray._private.utils.get_user_temp_dir(), f"ray-timeline-{time}.json" + ) + ray.timeline(filename=filename) + size = os.path.getsize(filename) + logger.info(f"Trace file written to {filename} ({size} bytes).") + logger.info("You can open this with chrome://tracing in the Chrome browser.") + + +@cli.command() +@click.option( + "--address", required=False, type=str, help="Override the address to connect to." +) +@click.option( + "--group-by", + type=click.Choice(["NODE_ADDRESS", "STACK_TRACE"]), + default="NODE_ADDRESS", + help="Group object references by a GroupByType \ +(e.g. NODE_ADDRESS or STACK_TRACE).", +) +@click.option( + "--sort-by", + type=click.Choice(["PID", "OBJECT_SIZE", "REFERENCE_TYPE"]), + default="OBJECT_SIZE", + help="Sort object references in ascending order by a SortingType \ +(e.g. PID, OBJECT_SIZE, or REFERENCE_TYPE).", +) +@click.option( + "--units", + type=click.Choice(["B", "KB", "MB", "GB"]), + default="B", + help="Specify unit metrics for displaying object sizes \ +(e.g. B, KB, MB, GB).", +) +@click.option( + "--no-format", + is_flag=True, + type=bool, + default=True, + help="Display unformatted results. Defaults to true when \ +terminal width is less than 137 characters.", +) +@click.option( + "--stats-only", is_flag=True, default=False, help="Display plasma store stats only." +) +@click.option( + "--num-entries", + "--n", + type=int, + default=None, + help="Specify number of sorted entries per group.", +) +def memory( + address, + group_by, + sort_by, + units, + no_format, + stats_only, + num_entries, +): + """Print object references held in a Ray cluster.""" + address = services.canonicalize_bootstrap_address_or_die(address) + gcs_client = ray._raylet.GcsClient(address=address) + _check_ray_version(gcs_client) + time = datetime.now() + header = "=" * 8 + f" Object references status: {time} " + "=" * 8 + mem_stats = memory_summary( + address, + group_by, + sort_by, + units, + no_format, + stats_only, + num_entries, + ) + print(f"{header}\n{mem_stats}") + + +@cli.command() +@click.option( + "--address", required=False, type=str, help="Override the address to connect to." +) +@click.option( + "-v", + "--verbose", + required=False, + is_flag=True, + hidden=True, + help="Experimental: Display additional debuggging information.", +) +@PublicAPI +def status(address: str, verbose: bool): + """Print cluster status, including autoscaling info.""" + address = services.canonicalize_bootstrap_address_or_die(address) + gcs_client = ray._raylet.GcsClient(address=address) + _check_ray_version(gcs_client) + ray.experimental.internal_kv._initialize_internal_kv(gcs_client) + status = gcs_client.internal_kv_get(ray_constants.DEBUG_AUTOSCALING_STATUS.encode()) + error = gcs_client.internal_kv_get(ray_constants.DEBUG_AUTOSCALING_ERROR.encode()) + print(debug_status(status, error, verbose=verbose, address=address)) + + +@cli.command(hidden=True) +@click.option( + "--stream", + "-S", + required=False, + type=bool, + is_flag=True, + default=False, + help="If True, will stream the binary archive contents to stdout", +) +@click.option( + "--output", "-o", required=False, type=str, default=None, help="Output file." +) +@click.option( + "--logs/--no-logs", + is_flag=True, + default=True, + help="Collect logs from ray session dir", +) +@click.option( + "--debug-state/--no-debug-state", + is_flag=True, + default=True, + help="Collect debug_state.txt from ray session dir", +) +@click.option( + "--pip/--no-pip", is_flag=True, default=True, help="Collect installed pip packages" +) +@click.option( + "--processes/--no-processes", + is_flag=True, + default=True, + help="Collect info on running processes", +) +@click.option( + "--processes-verbose/--no-processes-verbose", + is_flag=True, + default=True, + help="Increase process information verbosity", +) +@click.option( + "--tempfile", + "-T", + required=False, + type=str, + default=None, + help="Temporary file to use", +) +def local_dump( + stream: bool = False, + output: Optional[str] = None, + logs: bool = True, + debug_state: bool = True, + pip: bool = True, + processes: bool = True, + processes_verbose: bool = False, + tempfile: Optional[str] = None, +): + """Collect local data and package into an archive. + + Usage: + + ray local-dump [--stream/--output file] + + This script is called on remote nodes to fetch their data. + """ + # This may stream data to stdout, so no printing here + get_local_dump_archive( + stream=stream, + output=output, + logs=logs, + debug_state=debug_state, + pip=pip, + processes=processes, + processes_verbose=processes_verbose, + tempfile=tempfile, + ) + + +@cli.command() +@click.argument("cluster_config_file", required=False, type=str) +@click.option( + "--host", + "-h", + required=False, + type=str, + help="Single or list of hosts, separated by comma.", +) +@click.option( + "--ssh-user", + "-U", + required=False, + type=str, + default=None, + help="Username of the SSH user.", +) +@click.option( + "--ssh-key", + "-K", + required=False, + type=str, + default=None, + help="Path to the SSH key file.", +) +@click.option( + "--docker", + "-d", + required=False, + type=str, + default=None, + help="Name of the docker container, if applicable.", +) +@click.option( + "--local", + "-L", + required=False, + type=bool, + is_flag=True, + default=None, + help="Also include information about the local node.", +) +@click.option( + "--output", "-o", required=False, type=str, default=None, help="Output file." +) +@click.option( + "--logs/--no-logs", + is_flag=True, + default=True, + help="Collect logs from ray session dir", +) +@click.option( + "--debug-state/--no-debug-state", + is_flag=True, + default=True, + help="Collect debug_state.txt from ray log dir", +) +@click.option( + "--pip/--no-pip", is_flag=True, default=True, help="Collect installed pip packages" +) +@click.option( + "--processes/--no-processes", + is_flag=True, + default=True, + help="Collect info on running processes", +) +@click.option( + "--processes-verbose/--no-processes-verbose", + is_flag=True, + default=True, + help="Increase process information verbosity", +) +@click.option( + "--tempfile", + "-T", + required=False, + type=str, + default=None, + help="Temporary file to use", +) +def cluster_dump( + cluster_config_file: Optional[str] = None, + host: Optional[str] = None, + ssh_user: Optional[str] = None, + ssh_key: Optional[str] = None, + docker: Optional[str] = None, + local: Optional[bool] = None, + output: Optional[str] = None, + logs: bool = True, + debug_state: bool = True, + pip: bool = True, + processes: bool = True, + processes_verbose: bool = False, + tempfile: Optional[str] = None, +): + """Get log data from one or more nodes. + + Best used with Ray cluster configs: + + ray cluster-dump [cluster.yaml] + + Include the --local flag to also collect and include data from the + local node. + + Missing fields will be tried to be auto-filled. + + You can also manually specify a list of hosts using the + ``--host `` parameter. + """ + archive_path = get_cluster_dump_archive( + cluster_config_file=cluster_config_file, + host=host, + ssh_user=ssh_user, + ssh_key=ssh_key, + docker=docker, + local=local, + output=output, + logs=logs, + debug_state=debug_state, + pip=pip, + processes=processes, + processes_verbose=processes_verbose, + tempfile=tempfile, + ) + if archive_path: + click.echo(f"Created archive: {archive_path}") + else: + click.echo("Could not create archive.") + + +@cli.command(hidden=True) +@click.option( + "--address", required=False, type=str, help="Override the address to connect to." +) +def global_gc(address): + """Trigger Python garbage collection on all cluster workers.""" + ray.init(address=address) + ray._private.internal_api.global_gc() + print("Triggered gc.collect() on all workers.") + + +@cli.command(hidden=True) +@click.option( + "--address", required=False, type=str, help="Override the address to connect to." +) +@click.option( + "--node-id", + required=True, + type=str, + help="Hex ID of the worker node to be drained.", +) +@click.option( + "--reason", + required=True, + type=click.Choice( + [ + item[0] + for item in autoscaler_pb2.DrainNodeReason.items() + if item[1] != autoscaler_pb2.DRAIN_NODE_REASON_UNSPECIFIED + ] + ), + help="The reason why the node will be drained.", +) +@click.option( + "--reason-message", + required=True, + type=str, + help="The detailed drain reason message.", +) +@click.option( + "--deadline-remaining-seconds", + required=False, + type=int, + default=None, + help="Inform GCS that the node to be drained will be force killed " + "after this many of seconds. " + "Default is None which means there is no deadline. " + "Note: This command doesn't actually force kill the node after the deadline, " + "it's the caller's responsibility to do that.", +) +def drain_node( + address: str, + node_id: str, + reason: str, + reason_message: str, + deadline_remaining_seconds: int, +): + """ + This is NOT a public API. + + Manually drain a worker node. + """ + deadline_timestamp_ms = 0 + if deadline_remaining_seconds is not None: + if deadline_remaining_seconds < 0: + raise click.BadParameter( + "--deadline-remaining-seconds cannot be negative, " + f"got {deadline_remaining_seconds}" + ) + deadline_timestamp_ms = (time.time_ns() // 1000000) + ( + deadline_remaining_seconds * 1000 + ) + + if ray.NodeID.from_hex(node_id) == ray.NodeID.nil(): + raise click.BadParameter(f"Invalid hex ID of a Ray node, got {node_id}") + + address = services.canonicalize_bootstrap_address_or_die(address) + + gcs_client = ray._raylet.GcsClient(address=address) + _check_ray_version(gcs_client) + is_accepted, rejection_error_message = gcs_client.drain_node( + node_id, + autoscaler_pb2.DrainNodeReason.Value(reason), + reason_message, + deadline_timestamp_ms, + ) + + if not is_accepted: + raise click.ClickException( + f"The drain request is not accepted: {rejection_error_message}" + ) + + +@cli.command(name="kuberay-autoscaler", hidden=True) +@click.option( + "--cluster-name", + required=True, + type=str, + help="The name of the Ray Cluster.\n" + "Should coincide with the `metadata.name` of the RayCluster CR.", +) +@click.option( + "--cluster-namespace", + required=True, + type=str, + help="The Kubernetes namespace the Ray Cluster lives in.\n" + "Should coincide with the `metadata.namespace` of the RayCluster CR.", +) +def kuberay_autoscaler(cluster_name: str, cluster_namespace: str) -> None: + """Runs the autoscaler for a Ray cluster managed by the KubeRay operator. + + `ray kuberay-autoscaler` is meant to be used as an entry point in + KubeRay cluster configs. + `ray kuberay-autoscaler` is NOT a public CLI. + """ + # Delay import to avoid introducing Ray core dependency on the Python Kubernetes + # client. + from ray.autoscaler._private.kuberay.run_autoscaler import run_kuberay_autoscaler + + run_kuberay_autoscaler(cluster_name, cluster_namespace) + + +@cli.command(name="health-check", hidden=True) +@click.option( + "--address", required=False, type=str, help="Override the address to connect to." +) +@click.option( + "--component", + required=False, + type=str, + help="Health check for a specific component. Currently supports: " + "[ray_client_server]", +) +@click.option( + "--skip-version-check", + is_flag=True, + default=False, + help="Skip comparison of GCS version with local Ray version.", +) +def healthcheck(address, component, skip_version_check): + """ + This is NOT a public API. + + Health check a Ray or a specific component. Exit code 0 is healthy. + """ + + address = services.canonicalize_bootstrap_address_or_die(address) + gcs_client = ray._raylet.GcsClient(address=address) + if not skip_version_check: + _check_ray_version(gcs_client) + + if not component: + sys.exit(0) + + report_str = gcs_client.internal_kv_get( + component.encode(), namespace=ray_constants.KV_NAMESPACE_HEALTHCHECK + ) + if not report_str: + # Status was never updated + sys.exit(1) + + report = json.loads(report_str) + + # TODO (Alex): We probably shouldn't rely on time here, but cloud providers + # have very well synchronized NTP servers, so this should be fine in + # practice. + cur_time = time.time() + report_time = float(report["time"]) + + # If the status is too old, the service has probably already died. + delta = cur_time - report_time + time_ok = delta < ray._private.ray_constants.HEALTHCHECK_EXPIRATION_S + + if time_ok: + sys.exit(0) + else: + sys.exit(1) + + +@cli.command() +@click.option("-v", "--verbose", is_flag=True) +@click.option( + "--dryrun", + is_flag=True, + help="Identifies the wheel but does not execute the installation.", +) +def install_nightly(verbose, dryrun): + """Install the latest wheels for Ray. + + This uses the same python environment as the one that Ray is currently + installed in. Make sure that there is no Ray processes on this + machine (ray stop) when running this command. + """ + raydir = os.path.abspath(os.path.dirname(ray.__file__)) + all_wheels_path = os.path.join(raydir, "nightly-wheels.yaml") + + wheels = None + if os.path.exists(all_wheels_path): + with open(all_wheels_path) as f: + wheels = yaml.safe_load(f) + + if not wheels: + raise click.ClickException( + f"Wheels not found in '{all_wheels_path}'! " + "Please visit https://docs.ray.io/en/master/installation.html to " + "obtain the latest wheels." + ) + + platform = sys.platform + py_version = "{0}.{1}".format(*sys.version_info[:2]) + + matching_wheel = None + for target_platform, wheel_map in wheels.items(): + if verbose: + print(f"Evaluating os={target_platform}, python={list(wheel_map)}") + if platform.startswith(target_platform): + if py_version in wheel_map: + matching_wheel = wheel_map[py_version] + break + if verbose: + print("Not matched.") + + if matching_wheel is None: + raise click.ClickException( + "Unable to identify a matching platform. " + "Please visit https://docs.ray.io/en/master/installation.html to " + "obtain the latest wheels." + ) + if dryrun: + print(f"Found wheel: {matching_wheel}") + else: + cmd = [sys.executable, "-m", "pip", "install", "-U", matching_wheel] + print(f"Running: {' '.join(cmd)}.") + subprocess.check_call(cmd) + + +@cli.command() +@click.option( + "--show-library-path", + "-show", + required=False, + is_flag=True, + help="Show the cpp include path and library path, if provided.", +) +@click.option( + "--generate-bazel-project-template-to", + "-gen", + required=False, + type=str, + help="The directory to generate the bazel project template to, if provided.", +) +@add_click_logging_options +def cpp(show_library_path, generate_bazel_project_template_to): + """Show the cpp library path and generate the bazel project template.""" + if sys.platform == "win32": + cli_logger.error("Ray C++ API is not supported on Windows currently.") + sys.exit(1) + if not show_library_path and not generate_bazel_project_template_to: + raise ValueError( + "Please input at least one option of '--show-library-path'" + " and '--generate-bazel-project-template-to'." + ) + raydir = os.path.abspath(os.path.dirname(ray.__file__)) + cpp_dir = os.path.join(raydir, "cpp") + cpp_templete_dir = os.path.join(cpp_dir, "example") + include_dir = os.path.join(cpp_dir, "include") + lib_dir = os.path.join(cpp_dir, "lib") + if not os.path.isdir(cpp_dir): + raise ValueError('Please install ray with C++ API by "pip install ray[cpp]".') + if show_library_path: + cli_logger.print("Ray C++ include path {} ", cf.bold(f"{include_dir}")) + cli_logger.print("Ray C++ library path {} ", cf.bold(f"{lib_dir}")) + if generate_bazel_project_template_to: + # copytree expects that the dst dir doesn't exist + # so we manually delete it if it exists. + if os.path.exists(generate_bazel_project_template_to): + shutil.rmtree(generate_bazel_project_template_to) + shutil.copytree(cpp_templete_dir, generate_bazel_project_template_to) + out_include_dir = os.path.join( + generate_bazel_project_template_to, "thirdparty/include" + ) + if os.path.exists(out_include_dir): + shutil.rmtree(out_include_dir) + shutil.copytree(include_dir, out_include_dir) + out_lib_dir = os.path.join(generate_bazel_project_template_to, "thirdparty/lib") + if os.path.exists(out_lib_dir): + shutil.rmtree(out_lib_dir) + shutil.copytree(lib_dir, out_lib_dir) + + cli_logger.print( + "Project template generated to {}", + cf.bold(f"{os.path.abspath(generate_bazel_project_template_to)}"), + ) + cli_logger.print("To build and run this template, run") + cli_logger.print( + cf.bold( + f" cd {os.path.abspath(generate_bazel_project_template_to)}" + " && bash run.sh" + ) + ) + + +@click.group(name="metrics") +def metrics_group(): + pass + + +@metrics_group.command(name="launch-prometheus") +def launch_prometheus(): + install_and_start_prometheus.main() + + +@metrics_group.command(name="shutdown-prometheus") +def shutdown_prometheus(): + try: + requests.post("http://localhost:9090/-/quit") + except requests.exceptions.RequestException as e: + print(f"An error occurred: {e}") + sys.exit(1) + + +def add_command_alias(command, name, hidden): + new_command = copy.deepcopy(command) + new_command.hidden = hidden + cli.add_command(new_command, name=name) + + +cli.add_command(dashboard) +cli.add_command(debug) +cli.add_command(start) +cli.add_command(stop) +cli.add_command(up) +add_command_alias(up, name="create_or_update", hidden=True) +cli.add_command(attach) +cli.add_command(exec) +add_command_alias(exec, name="exec_cmd", hidden=True) +add_command_alias(rsync_down, name="rsync_down", hidden=True) +add_command_alias(rsync_up, name="rsync_up", hidden=True) +cli.add_command(submit) +cli.add_command(down) +add_command_alias(down, name="teardown", hidden=True) +cli.add_command(kill_random_node) +add_command_alias(get_head_ip, name="get_head_ip", hidden=True) +cli.add_command(get_worker_ips) +cli.add_command(microbenchmark) +cli.add_command(stack) +cli.add_command(status) +cli.add_command(memory) +cli.add_command(local_dump) +cli.add_command(cluster_dump) +cli.add_command(global_gc) +cli.add_command(timeline) +cli.add_command(install_nightly) +cli.add_command(cpp) +cli.add_command(disable_usage_stats) +cli.add_command(enable_usage_stats) +cli.add_command(metrics_group) +cli.add_command(drain_node) +cli.add_command(check_open_ports) + +try: + from ray.util.state.state_cli import ( + ray_get, + ray_list, + logs_state_cli_group, + summary_state_cli_group, + ) + + cli.add_command(ray_list, name="list") + cli.add_command(ray_get, name="get") + add_command_alias(summary_state_cli_group, name="summary", hidden=False) + add_command_alias(logs_state_cli_group, name="logs", hidden=False) +except ImportError as e: + logger.debug(f"Integrating ray state command line tool failed: {e}") + + +try: + from ray.dashboard.modules.job.cli import job_cli_group + + add_command_alias(job_cli_group, name="job", hidden=False) +except Exception as e: + logger.debug(f"Integrating ray jobs command line tool failed with {e}") + + +try: + from ray.serve.scripts import serve_cli + + cli.add_command(serve_cli) +except Exception as e: + logger.debug(f"Integrating ray serve command line tool failed with {e}") + + +def main(): + return cli() + + +if __name__ == "__main__": + main() diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/METADATA b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/METADATA new file mode 100644 index 0000000000000000000000000000000000000000..a1b5c57543005b310ac2efb02243a6b6ab6d8932 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/METADATA @@ -0,0 +1,441 @@ +Metadata-Version: 2.1 +Name: colorama +Version: 0.4.6 +Summary: Cross-platform colored terminal text. +Project-URL: Homepage, https://github.com/tartley/colorama +Author-email: Jonathan Hartley +License-File: LICENSE.txt +Keywords: ansi,color,colour,crossplatform,terminal,text,windows,xplatform +Classifier: Development Status :: 5 - Production/Stable +Classifier: Environment :: Console +Classifier: Intended Audience :: Developers +Classifier: License :: OSI Approved :: BSD License +Classifier: Operating System :: OS Independent +Classifier: Programming Language :: Python +Classifier: Programming Language :: Python :: 2 +Classifier: Programming Language :: Python :: 2.7 +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Programming Language :: Python :: 3.10 +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Topic :: Terminals +Requires-Python: !=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7 +Description-Content-Type: text/x-rst + +.. image:: https://img.shields.io/pypi/v/colorama.svg + :target: https://pypi.org/project/colorama/ + :alt: Latest Version + +.. image:: https://img.shields.io/pypi/pyversions/colorama.svg + :target: https://pypi.org/project/colorama/ + :alt: Supported Python versions + +.. image:: https://github.com/tartley/colorama/actions/workflows/test.yml/badge.svg + :target: https://github.com/tartley/colorama/actions/workflows/test.yml + :alt: Build Status + +Colorama +======== + +Makes ANSI escape character sequences (for producing colored terminal text and +cursor positioning) work under MS Windows. + +.. |donate| image:: https://www.paypalobjects.com/en_US/i/btn/btn_donate_SM.gif + :target: https://www.paypal.com/cgi-bin/webscr?cmd=_donations&business=2MZ9D2GMLYCUJ&item_name=Colorama¤cy_code=USD + :alt: Donate with Paypal + +`PyPI for releases `_ | +`Github for source `_ | +`Colorama for enterprise on Tidelift `_ + +If you find Colorama useful, please |donate| to the authors. Thank you! + +Installation +------------ + +Tested on CPython 2.7, 3.7, 3.8, 3.9 and 3.10 and Pypy 2.7 and 3.8. + +No requirements other than the standard library. + +.. code-block:: bash + + pip install colorama + # or + conda install -c anaconda colorama + +Description +----------- + +ANSI escape character sequences have long been used to produce colored terminal +text and cursor positioning on Unix and Macs. Colorama makes this work on +Windows, too, by wrapping ``stdout``, stripping ANSI sequences it finds (which +would appear as gobbledygook in the output), and converting them into the +appropriate win32 calls to modify the state of the terminal. On other platforms, +Colorama does nothing. + +This has the upshot of providing a simple cross-platform API for printing +colored terminal text from Python, and has the happy side-effect that existing +applications or libraries which use ANSI sequences to produce colored output on +Linux or Macs can now also work on Windows, simply by calling +``colorama.just_fix_windows_console()`` (since v0.4.6) or ``colorama.init()`` +(all versions, but may have other side-effects – see below). + +An alternative approach is to install ``ansi.sys`` on Windows machines, which +provides the same behaviour for all applications running in terminals. Colorama +is intended for situations where that isn't easy (e.g., maybe your app doesn't +have an installer.) + +Demo scripts in the source code repository print some colored text using +ANSI sequences. Compare their output under Gnome-terminal's built in ANSI +handling, versus on Windows Command-Prompt using Colorama: + +.. image:: https://github.com/tartley/colorama/raw/master/screenshots/ubuntu-demo.png + :width: 661 + :height: 357 + :alt: ANSI sequences on Ubuntu under gnome-terminal. + +.. image:: https://github.com/tartley/colorama/raw/master/screenshots/windows-demo.png + :width: 668 + :height: 325 + :alt: Same ANSI sequences on Windows, using Colorama. + +These screenshots show that, on Windows, Colorama does not support ANSI 'dim +text'; it looks the same as 'normal text'. + +Usage +----- + +Initialisation +.............. + +If the only thing you want from Colorama is to get ANSI escapes to work on +Windows, then run: + +.. code-block:: python + + from colorama import just_fix_windows_console + just_fix_windows_console() + +If you're on a recent version of Windows 10 or better, and your stdout/stderr +are pointing to a Windows console, then this will flip the magic configuration +switch to enable Windows' built-in ANSI support. + +If you're on an older version of Windows, and your stdout/stderr are pointing to +a Windows console, then this will wrap ``sys.stdout`` and/or ``sys.stderr`` in a +magic file object that intercepts ANSI escape sequences and issues the +appropriate Win32 calls to emulate them. + +In all other circumstances, it does nothing whatsoever. Basically the idea is +that this makes Windows act like Unix with respect to ANSI escape handling. + +It's safe to call this function multiple times. It's safe to call this function +on non-Windows platforms, but it won't do anything. It's safe to call this +function when one or both of your stdout/stderr are redirected to a file – it +won't do anything to those streams. + +Alternatively, you can use the older interface with more features (but also more +potential footguns): + +.. code-block:: python + + from colorama import init + init() + +This does the same thing as ``just_fix_windows_console``, except for the +following differences: + +- It's not safe to call ``init`` multiple times; you can end up with multiple + layers of wrapping and broken ANSI support. + +- Colorama will apply a heuristic to guess whether stdout/stderr support ANSI, + and if it thinks they don't, then it will wrap ``sys.stdout`` and + ``sys.stderr`` in a magic file object that strips out ANSI escape sequences + before printing them. This happens on all platforms, and can be convenient if + you want to write your code to emit ANSI escape sequences unconditionally, and + let Colorama decide whether they should actually be output. But note that + Colorama's heuristic is not particularly clever. + +- ``init`` also accepts explicit keyword args to enable/disable various + functionality – see below. + +To stop using Colorama before your program exits, simply call ``deinit()``. +This will restore ``stdout`` and ``stderr`` to their original values, so that +Colorama is disabled. To resume using Colorama again, call ``reinit()``; it is +cheaper than calling ``init()`` again (but does the same thing). + +Most users should depend on ``colorama >= 0.4.6``, and use +``just_fix_windows_console``. The old ``init`` interface will be supported +indefinitely for backwards compatibility, but we don't plan to fix any issues +with it, also for backwards compatibility. + +Colored Output +.............. + +Cross-platform printing of colored text can then be done using Colorama's +constant shorthand for ANSI escape sequences. These are deliberately +rudimentary, see below. + +.. code-block:: python + + from colorama import Fore, Back, Style + print(Fore.RED + 'some red text') + print(Back.GREEN + 'and with a green background') + print(Style.DIM + 'and in dim text') + print(Style.RESET_ALL) + print('back to normal now') + +...or simply by manually printing ANSI sequences from your own code: + +.. code-block:: python + + print('\033[31m' + 'some red text') + print('\033[39m') # and reset to default color + +...or, Colorama can be used in conjunction with existing ANSI libraries +such as the venerable `Termcolor `_ +the fabulous `Blessings `_, +or the incredible `_Rich `_. + +If you wish Colorama's Fore, Back and Style constants were more capable, +then consider using one of the above highly capable libraries to generate +colors, etc, and use Colorama just for its primary purpose: to convert +those ANSI sequences to also work on Windows: + +SIMILARLY, do not send PRs adding the generation of new ANSI types to Colorama. +We are only interested in converting ANSI codes to win32 API calls, not +shortcuts like the above to generate ANSI characters. + +.. code-block:: python + + from colorama import just_fix_windows_console + from termcolor import colored + + # use Colorama to make Termcolor work on Windows too + just_fix_windows_console() + + # then use Termcolor for all colored text output + print(colored('Hello, World!', 'green', 'on_red')) + +Available formatting constants are:: + + Fore: BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE, RESET. + Back: BLACK, RED, GREEN, YELLOW, BLUE, MAGENTA, CYAN, WHITE, RESET. + Style: DIM, NORMAL, BRIGHT, RESET_ALL + +``Style.RESET_ALL`` resets foreground, background, and brightness. Colorama will +perform this reset automatically on program exit. + +These are fairly well supported, but not part of the standard:: + + Fore: LIGHTBLACK_EX, LIGHTRED_EX, LIGHTGREEN_EX, LIGHTYELLOW_EX, LIGHTBLUE_EX, LIGHTMAGENTA_EX, LIGHTCYAN_EX, LIGHTWHITE_EX + Back: LIGHTBLACK_EX, LIGHTRED_EX, LIGHTGREEN_EX, LIGHTYELLOW_EX, LIGHTBLUE_EX, LIGHTMAGENTA_EX, LIGHTCYAN_EX, LIGHTWHITE_EX + +Cursor Positioning +.................. + +ANSI codes to reposition the cursor are supported. See ``demos/demo06.py`` for +an example of how to generate them. + +Init Keyword Args +................. + +``init()`` accepts some ``**kwargs`` to override default behaviour. + +init(autoreset=False): + If you find yourself repeatedly sending reset sequences to turn off color + changes at the end of every print, then ``init(autoreset=True)`` will + automate that: + + .. code-block:: python + + from colorama import init + init(autoreset=True) + print(Fore.RED + 'some red text') + print('automatically back to default color again') + +init(strip=None): + Pass ``True`` or ``False`` to override whether ANSI codes should be + stripped from the output. The default behaviour is to strip if on Windows + or if output is redirected (not a tty). + +init(convert=None): + Pass ``True`` or ``False`` to override whether to convert ANSI codes in the + output into win32 calls. The default behaviour is to convert if on Windows + and output is to a tty (terminal). + +init(wrap=True): + On Windows, Colorama works by replacing ``sys.stdout`` and ``sys.stderr`` + with proxy objects, which override the ``.write()`` method to do their work. + If this wrapping causes you problems, then this can be disabled by passing + ``init(wrap=False)``. The default behaviour is to wrap if ``autoreset`` or + ``strip`` or ``convert`` are True. + + When wrapping is disabled, colored printing on non-Windows platforms will + continue to work as normal. To do cross-platform colored output, you can + use Colorama's ``AnsiToWin32`` proxy directly: + + .. code-block:: python + + import sys + from colorama import init, AnsiToWin32 + init(wrap=False) + stream = AnsiToWin32(sys.stderr).stream + + # Python 2 + print >>stream, Fore.BLUE + 'blue text on stderr' + + # Python 3 + print(Fore.BLUE + 'blue text on stderr', file=stream) + +Recognised ANSI Sequences +......................... + +ANSI sequences generally take the form:: + + ESC [ ; ... + +Where ```` is an integer, and ```` is a single letter. Zero or +more params are passed to a ````. If no params are passed, it is +generally synonymous with passing a single zero. No spaces exist in the +sequence; they have been inserted here simply to read more easily. + +The only ANSI sequences that Colorama converts into win32 calls are:: + + ESC [ 0 m # reset all (colors and brightness) + ESC [ 1 m # bright + ESC [ 2 m # dim (looks same as normal brightness) + ESC [ 22 m # normal brightness + + # FOREGROUND: + ESC [ 30 m # black + ESC [ 31 m # red + ESC [ 32 m # green + ESC [ 33 m # yellow + ESC [ 34 m # blue + ESC [ 35 m # magenta + ESC [ 36 m # cyan + ESC [ 37 m # white + ESC [ 39 m # reset + + # BACKGROUND + ESC [ 40 m # black + ESC [ 41 m # red + ESC [ 42 m # green + ESC [ 43 m # yellow + ESC [ 44 m # blue + ESC [ 45 m # magenta + ESC [ 46 m # cyan + ESC [ 47 m # white + ESC [ 49 m # reset + + # cursor positioning + ESC [ y;x H # position cursor at x across, y down + ESC [ y;x f # position cursor at x across, y down + ESC [ n A # move cursor n lines up + ESC [ n B # move cursor n lines down + ESC [ n C # move cursor n characters forward + ESC [ n D # move cursor n characters backward + + # clear the screen + ESC [ mode J # clear the screen + + # clear the line + ESC [ mode K # clear the line + +Multiple numeric params to the ``'m'`` command can be combined into a single +sequence:: + + ESC [ 36 ; 45 ; 1 m # bright cyan text on magenta background + +All other ANSI sequences of the form ``ESC [ ; ... `` +are silently stripped from the output on Windows. + +Any other form of ANSI sequence, such as single-character codes or alternative +initial characters, are not recognised or stripped. It would be cool to add +them though. Let me know if it would be useful for you, via the Issues on +GitHub. + +Status & Known Problems +----------------------- + +I've personally only tested it on Windows XP (CMD, Console2), Ubuntu +(gnome-terminal, xterm), and OS X. + +Some valid ANSI sequences aren't recognised. + +If you're hacking on the code, see `README-hacking.md`_. ESPECIALLY, see the +explanation there of why we do not want PRs that allow Colorama to generate new +types of ANSI codes. + +See outstanding issues and wish-list: +https://github.com/tartley/colorama/issues + +If anything doesn't work for you, or doesn't do what you expected or hoped for, +I'd love to hear about it on that issues list, would be delighted by patches, +and would be happy to grant commit access to anyone who submits a working patch +or two. + +.. _README-hacking.md: README-hacking.md + +License +------- + +Copyright Jonathan Hartley & Arnon Yaari, 2013-2020. BSD 3-Clause license; see +LICENSE file. + +Professional support +-------------------- + +.. |tideliftlogo| image:: https://cdn2.hubspot.net/hubfs/4008838/website/logos/logos_for_download/Tidelift_primary-shorthand-logo.png + :alt: Tidelift + :target: https://tidelift.com/subscription/pkg/pypi-colorama?utm_source=pypi-colorama&utm_medium=referral&utm_campaign=readme + +.. list-table:: + :widths: 10 100 + + * - |tideliftlogo| + - Professional support for colorama is available as part of the + `Tidelift Subscription`_. + Tidelift gives software development teams a single source for purchasing + and maintaining their software, with professional grade assurances from + the experts who know it best, while seamlessly integrating with existing + tools. + +.. _Tidelift Subscription: https://tidelift.com/subscription/pkg/pypi-colorama?utm_source=pypi-colorama&utm_medium=referral&utm_campaign=readme + +Thanks +------ + +See the CHANGELOG for more thanks! + +* Marc Schlaich (schlamar) for a ``setup.py`` fix for Python2.5. +* Marc Abramowitz, reported & fixed a crash on exit with closed ``stdout``, + providing a solution to issue #7's setuptools/distutils debate, + and other fixes. +* User 'eryksun', for guidance on correctly instantiating ``ctypes.windll``. +* Matthew McCormick for politely pointing out a longstanding crash on non-Win. +* Ben Hoyt, for a magnificent fix under 64-bit Windows. +* Jesse at Empty Square for submitting a fix for examples in the README. +* User 'jamessp', an observant documentation fix for cursor positioning. +* User 'vaal1239', Dave Mckee & Lackner Kristof for a tiny but much-needed Win7 + fix. +* Julien Stuyck, for wisely suggesting Python3 compatible updates to README. +* Daniel Griffith for multiple fabulous patches. +* Oscar Lesta for a valuable fix to stop ANSI chars being sent to non-tty + output. +* Roger Binns, for many suggestions, valuable feedback, & bug reports. +* Tim Golden for thought and much appreciated feedback on the initial idea. +* User 'Zearin' for updates to the README file. +* John Szakmeister for adding support for light colors +* Charles Merriam for adding documentation to demos +* Jurko for a fix on 64-bit Windows CPython2.5 w/o ctypes +* Florian Bruhin for a fix when stdout or stderr are None +* Thomas Weininger for fixing ValueError on Windows +* Remi Rampin for better Github integration and fixes to the README file +* Simeon Visser for closing a file handle using 'with' and updating classifiers + to include Python 3.3 and 3.4 +* Andy Neff for fixing RESET of LIGHT_EX colors. +* Jonathan Hartley for the initial idea and implementation. diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/RECORD b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/RECORD new file mode 100644 index 0000000000000000000000000000000000000000..0e0eb308fe9ae79f7f3de19b5143488afef67f46 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/RECORD @@ -0,0 +1,32 @@ +colorama-0.4.6.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +colorama-0.4.6.dist-info/METADATA,sha256=e67SnrUMOym9sz_4TjF3vxvAV4T3aF7NyqRHHH3YEMw,17158 +colorama-0.4.6.dist-info/RECORD,, +colorama-0.4.6.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +colorama-0.4.6.dist-info/WHEEL,sha256=cdcF4Fbd0FPtw2EMIOwH-3rSOTUdTCeOSXRMD1iLUb8,105 +colorama-0.4.6.dist-info/licenses/LICENSE.txt,sha256=ysNcAmhuXQSlpxQL-zs25zrtSWZW6JEQLkKIhteTAxg,1491 +colorama/__init__.py,sha256=wePQA4U20tKgYARySLEC047ucNX-g8pRLpYBuiHlLb8,266 +colorama/__pycache__/__init__.cpython-311.pyc,, +colorama/__pycache__/ansi.cpython-311.pyc,, +colorama/__pycache__/ansitowin32.cpython-311.pyc,, +colorama/__pycache__/initialise.cpython-311.pyc,, +colorama/__pycache__/win32.cpython-311.pyc,, +colorama/__pycache__/winterm.cpython-311.pyc,, +colorama/ansi.py,sha256=Top4EeEuaQdBWdteKMEcGOTeKeF19Q-Wo_6_Cj5kOzQ,2522 +colorama/ansitowin32.py,sha256=vPNYa3OZbxjbuFyaVo0Tmhmy1FZ1lKMWCnT7odXpItk,11128 +colorama/initialise.py,sha256=-hIny86ClXo39ixh5iSCfUIa2f_h_bgKRDW7gqs-KLU,3325 +colorama/tests/__init__.py,sha256=MkgPAEzGQd-Rq0w0PZXSX2LadRWhUECcisJY8lSrm4Q,75 +colorama/tests/__pycache__/__init__.cpython-311.pyc,, +colorama/tests/__pycache__/ansi_test.cpython-311.pyc,, +colorama/tests/__pycache__/ansitowin32_test.cpython-311.pyc,, +colorama/tests/__pycache__/initialise_test.cpython-311.pyc,, +colorama/tests/__pycache__/isatty_test.cpython-311.pyc,, +colorama/tests/__pycache__/utils.cpython-311.pyc,, +colorama/tests/__pycache__/winterm_test.cpython-311.pyc,, +colorama/tests/ansi_test.py,sha256=FeViDrUINIZcr505PAxvU4AjXz1asEiALs9GXMhwRaE,2839 +colorama/tests/ansitowin32_test.py,sha256=RN7AIhMJ5EqDsYaCjVo-o4u8JzDD4ukJbmevWKS70rY,10678 +colorama/tests/initialise_test.py,sha256=BbPy-XfyHwJ6zKozuQOvNvQZzsx9vdb_0bYXn7hsBTc,6741 +colorama/tests/isatty_test.py,sha256=Pg26LRpv0yQDB5Ac-sxgVXG7hsA1NYvapFgApZfYzZg,1866 +colorama/tests/utils.py,sha256=1IIRylG39z5-dzq09R_ngufxyPZxgldNbrxKxUGwGKE,1079 +colorama/tests/winterm_test.py,sha256=qoWFPEjym5gm2RuMwpf3pOis3a5r_PJZFCzK254JL8A,3709 +colorama/win32.py,sha256=YQOKwMTwtGBbsY4dL5HYTvwTeP9wIQra5MvPNddpxZs,6181 +colorama/winterm.py,sha256=XCQFDHjPi6AHYNdZwy0tA02H-Jh48Jp-HvCjeLeLp3U,7134 diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/REQUESTED b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/REQUESTED new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/WHEEL b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/WHEEL new file mode 100644 index 0000000000000000000000000000000000000000..d79189fda3251187de18c3998f23ae6fec11b20f --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/WHEEL @@ -0,0 +1,5 @@ +Wheel-Version: 1.0 +Generator: hatchling 1.11.1 +Root-Is-Purelib: true +Tag: py2-none-any +Tag: py3-none-any diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/licenses/LICENSE.txt b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/licenses/LICENSE.txt new file mode 100644 index 0000000000000000000000000000000000000000..3105888ec149d10cad51c11d332779e94b548661 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/colorama-0.4.6.dist-info/licenses/LICENSE.txt @@ -0,0 +1,27 @@ +Copyright (c) 2010 Jonathan Hartley +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +* Redistributions of source code must retain the above copyright notice, this + list of conditions and the following disclaimer. + +* Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +* Neither the name of the copyright holders, nor those of its contributors + may be used to endorse or promote products derived from this software without + specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND +ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED +WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE +FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, +OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/psutil/_psutil_linux.abi3.so b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/psutil/_psutil_linux.abi3.so new file mode 100644 index 0000000000000000000000000000000000000000..d977371504986c5f9cebb780c26a4b2eceab56c2 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/psutil/_psutil_linux.abi3.so @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d76b01666546f2806089d6f4ef08f005db0bb410d893a54d463a7b0f8b727e2 +size 115336 diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/setproctitle-1.2.2.dist-info/METADATA b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/setproctitle-1.2.2.dist-info/METADATA new file mode 100644 index 0000000000000000000000000000000000000000..05351c6fb0ccb4bc948afbad7db08239434aa0d2 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/setproctitle-1.2.2.dist-info/METADATA @@ -0,0 +1,327 @@ +Metadata-Version: 2.2 +Name: setproctitle +Version: 1.2.2 +Summary: A Python module to customize the process title +Home-page: https://github.com/dvarrazzo/py-setproctitle +Download-URL: http://pypi.python.org/pypi/setproctitle/ +Author: Daniele Varrazzo +Author-email: daniele.varrazzo@gmail.com +License: BSD +Platform: GNU/Linux +Platform: BSD +Platform: MacOS X +Platform: Windows +Classifier: Development Status :: 5 - Production/Stable +Classifier: Intended Audience :: Developers +Classifier: License :: OSI Approved :: BSD License +Classifier: Programming Language :: C +Classifier: Programming Language :: Python :: 3 +Classifier: Programming Language :: Python :: 3.6 +Classifier: Programming Language :: Python :: 3.7 +Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 +Classifier: Operating System :: POSIX :: Linux +Classifier: Operating System :: POSIX :: BSD +Classifier: Operating System :: MacOS :: MacOS X +Classifier: Operating System :: Microsoft :: Windows +Classifier: Topic :: Software Development +Requires-Python: >=3.6 +Description-Content-Type: text/x-rst +Provides-Extra: test +Requires-Dist: pytest<6.2,>=6.1; extra == "test" +Dynamic: author +Dynamic: author-email +Dynamic: classifier +Dynamic: description +Dynamic: description-content-type +Dynamic: download-url +Dynamic: home-page +Dynamic: license +Dynamic: platform +Dynamic: provides-extra +Dynamic: requires-python +Dynamic: summary + +A Python module to customize the process title +============================================== + +.. image:: https://github.com/dvarrazzo/py-setproctitle/workflows/Tests/badge.svg + :target: https://github.com/dvarrazzo/py-setproctitle/actions?query=workflow%3ATests + :alt: Tests + +:author: Daniele Varrazzo + +The ``setproctitle`` module allows a process to change its title (as displayed +by system tools such as ``ps`` and ``top``). + +Changing the title is mostly useful in multi-process systems, for example +when a master process is forked: changing the children's title allows to +identify the task each process is busy with. The technique is used by +PostgreSQL_ and the `OpenSSH Server`_ for example. + +The procedure is hardly portable across different systems. PostgreSQL provides +a good `multi-platform implementation`__: this module is a Python wrapper +around PostgreSQL code. + +- `Homepage `__ +- `Download `__ +- `Bug tracker `__ + + +.. _PostgreSQL: http://www.postgresql.org +.. _OpenSSH Server: http://www.openssh.com/ +.. __: http://doxygen.postgresql.org/ps__status_8c_source.html + + +Installation +------------ + +``setproctitle`` is a C extension: in order to build it you will need a C +compiler and the Python development support (the ``python-dev`` or +``python3-dev`` package in most Linux distributions). No further external +dependencies are required. + +You can use ``pip`` to install the module:: + + pip install setproctitle + +You can use ``pip -t`` or ``virtualenv`` for local installations, ``sudo pip`` +for a system-wide one... the usual stuff. Read pip_ or virtualenv_ docs for +all the details. + +.. _pip: https://pip.readthedocs.org/ +.. _virtualenv: https://virtualenv.readthedocs.org/ + + +Usage +----- + +.. note:: + You should import and use the module (even just calling ``getproctitle()``) + pretty early in your program lifetime: code writing env vars `may + interfere`__ with the module initialisation. + + .. __: https://github.com/dvarrazzo/py-setproctitle/issues/42 + + +The ``setproctitle`` module exports the following functions: + +``setproctitle(title)`` + Set *title* as the title for the current process. + +``getproctitle()`` + Return the current process title. + +The process title is usually visible in files such as ``/proc/PID/cmdline``, +``/proc/PID/status``, ``/proc/PID/comm``, depending on the operating system +and kernel version. These information are used by user-space tools such as +``ps`` and ``top``. + + +``setthreadtitle(title)`` + Set *title* as the title for the current thread. + +``getthreadtitle()`` + Get the current thread title. + +The thread title is exposed by some operating systems as the file +``/proc/PID/task/TID/comm``, which is used by certain tools such as ``htop``. + + +Environment variables +~~~~~~~~~~~~~~~~~~~~~ + +A few environment variables can be used to customize the module behavior: + +``SPT_NOENV`` + Avoid clobbering ``/proc/PID/environ``. + + On many platforms, setting the process title will clobber the + ``environ`` memory area. ``os.environ`` will work as expected from within + the Python process, but the content of the file ``/proc/PID/environ`` will + be overwritten. If you require this file not to be broken you can set the + ``SPT_NOENV`` environment variable to any non-empty value: in this case + the maximum length for the title will be limited to the length of the + command line. + +``SPT_DEBUG`` + Print debug information on ``stderr``. + + If the module doesn't work as expected you can set this variable to a + non-empty value to generate information useful for debugging. Note that + the most useful information is printed when the module is imported, not + when the functions are called. + + +Module status +------------- + +The module can be currently compiled and effectively used on the following +platforms: + +- GNU/Linux +- BSD +- MacOS X +- Windows + +Note that on Windows there is no way to change the process string: +what the module does is to create a *Named Object* whose value can be read +using a tool such as `Process Explorer`_ (contribution of a more useful tool +to be used together with ``setproctitle`` would be well accepted). + +The module can probably work on HP-UX, but I haven't found any to test with. +It is unlikely that it can work on Solaris instead. + +.. _Process Explorer: http://technet.microsoft.com/en-us/sysinternals/bb896653.aspx + +Releases history +---------------- + +Version 1.2.2 +------------- + +- Fixed Windows build (issues #89, #90). +- Added wheel packages for Windows (issues #47, #90). +- Added wheel packages for aarch64 (issues #95). + + +Version 1.2.1 +------------- + +- Fixed segfault after ``os.environ.clear()`` (issue #88). + + +Version 1.2 +~~~~~~~~~~~ + +- added ``getthreadtitle()`` and ``setthreadtitle()``. +- Initialisation of the module moved to the first usage: importing the module + doesn't cause side effects. +- Manage much longer command lines (#52) +- Improved build on BSD, dropped ancient versions (issue #67). +- Fixed build for Python 3.8 (#66, #72) +- Added support for Python 3.9 +- Dropped support for Python < 3.6 + + +Version 1.1.10 +~~~~~~~~~~~~~~ + +- Fixed building with certain ``prctl.h`` implementations (issue #44). +- Use ``setuptools`` if available (issue #48). + + +Version 1.1.9 +~~~~~~~~~~~~~ + +- Fixed build on VC (issues #20, #33). +- Added ``MANIFEST.in`` to the source distribution to help with RPM building + (issue #30). + + +Version 1.1.8 +~~~~~~~~~~~~~ + +- Added support for Python "diehard" 2.4 (pull request #3). +- Fixed build on Mac OS X 10.9 Maverick (issue #27). + + +Version 1.1.7 +~~~~~~~~~~~~~ + +- Added PyPy support, courtesy of Ozan Turksever - http://www.logsign.net + (pull request #2). + + +Version 1.1.6 +~~~~~~~~~~~~~ + +- The module can be compiled again on Windows (issue #21). + + +Version 1.1.5 +~~~~~~~~~~~~~ + +- No module bug, but a packaging issue: files ``README`` and ``HISTORY`` + added back into the distribution. + + +Version 1.1.4 +~~~~~~~~~~~~~ + +- The module works correctly in embedded Python. +- ``setproctitle()`` accepts a keyword argument. +- Debug output support always compiled in: the variable ``SPT_DEBUG`` can be + used to emit debug log. + + +Version 1.1.3 +~~~~~~~~~~~~~ + +- Don't clobber environ if the variable ``SPT_NOENV`` is set (issue #16). + + +Version 1.1.2 +~~~~~~~~~~~~~ + +- Find the setproctitle include file on OpenBSD (issue #11). +- Skip test with unicode if the file system encoding wouldn't make it pass + (issue #13). + + +Version 1.1.1 +~~~~~~~~~~~~~ + +- Fixed segfault when the module is imported under mod_wsgi (issue #9). + + +Version 1.1 +~~~~~~~~~~~ + +- The module works correctly with Python 3. + + +Version 1.0.1 +~~~~~~~~~~~~~ + +- ``setproctitle()`` works even when Python messes up with argv, e.g. when run + with the -m option (issue #8). + + +Version 1.0 +~~~~~~~~~~~ + +No major change since the previous version. The module has been heavily used +in production environment without any problem reported, so it's time to declare +it stable. + + +Version 0.4 +~~~~~~~~~~~ + +- Module works on BSD (tested on FreeBSD 7.2). + +- Module works on Windows. Many thanks to `Develer`_ for providing a neat `GCC + package for Windows with Python integration`__ that made the Windows porting + painless. + + .. _Develer: http://www.develer.com/ + .. __: http://www.develer.com/oss/GccWinBinaries + + +Version 0.3 +~~~~~~~~~~~ + +- Module works on Mac OS X 10.2. Reported working on OS X 10.6 too. + + +Version 0.2 +~~~~~~~~~~~ + +- Added ``prctl()`` call on Linux >= 2.6.9 to update ``/proc/self/status``. + + +Version 0.1 +~~~~~~~~~~~ + +- Initial public release. diff --git a/.venv/lib/python3.11/site-packages/ray/thirdparty_files/setproctitle-1.2.2.dist-info/RECORD b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/setproctitle-1.2.2.dist-info/RECORD new file mode 100644 index 0000000000000000000000000000000000000000..9ea1e6cd89b06a213e39d7b8c5585acaea1692ef --- /dev/null +++ b/.venv/lib/python3.11/site-packages/ray/thirdparty_files/setproctitle-1.2.2.dist-info/RECORD @@ -0,0 +1,7 @@ +setproctitle-1.2.2.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4 +setproctitle-1.2.2.dist-info/METADATA,sha256=FFhJMjb-VT6QB94FksWKoQkg-sZy52OTBXC_KG3_hf8,9051 +setproctitle-1.2.2.dist-info/RECORD,, +setproctitle-1.2.2.dist-info/REQUESTED,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0 +setproctitle-1.2.2.dist-info/WHEEL,sha256=HDBMQ19ZtMFARwRc3ZGC21o8Tu11IBK6tQtXGgqOICs,104 +setproctitle-1.2.2.dist-info/top_level.txt,sha256=khlu2SuNEK2Ct594XhMTT62ll8p0oFza-4dmzUFTBhQ,13 +setproctitle.cpython-311-x86_64-linux-gnu.so,sha256=sOhOZH3jZQWd3CIHW_KKe8qLZZm-YPo86kISUM-MZkM,69120 diff --git a/.venv/lib/python3.11/site-packages/yaml/__init__.py b/.venv/lib/python3.11/site-packages/yaml/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..2ec4f203c7e12941ff807c9def9e35b9ae1ab2bd --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/__init__.py @@ -0,0 +1,390 @@ + +from .error import * + +from .tokens import * +from .events import * +from .nodes import * + +from .loader import * +from .dumper import * + +__version__ = '6.0.2' +try: + from .cyaml import * + __with_libyaml__ = True +except ImportError: + __with_libyaml__ = False + +import io + +#------------------------------------------------------------------------------ +# XXX "Warnings control" is now deprecated. Leaving in the API function to not +# break code that uses it. +#------------------------------------------------------------------------------ +def warnings(settings=None): + if settings is None: + return {} + +#------------------------------------------------------------------------------ +def scan(stream, Loader=Loader): + """ + Scan a YAML stream and produce scanning tokens. + """ + loader = Loader(stream) + try: + while loader.check_token(): + yield loader.get_token() + finally: + loader.dispose() + +def parse(stream, Loader=Loader): + """ + Parse a YAML stream and produce parsing events. + """ + loader = Loader(stream) + try: + while loader.check_event(): + yield loader.get_event() + finally: + loader.dispose() + +def compose(stream, Loader=Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding representation tree. + """ + loader = Loader(stream) + try: + return loader.get_single_node() + finally: + loader.dispose() + +def compose_all(stream, Loader=Loader): + """ + Parse all YAML documents in a stream + and produce corresponding representation trees. + """ + loader = Loader(stream) + try: + while loader.check_node(): + yield loader.get_node() + finally: + loader.dispose() + +def load(stream, Loader): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + """ + loader = Loader(stream) + try: + return loader.get_single_data() + finally: + loader.dispose() + +def load_all(stream, Loader): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + """ + loader = Loader(stream) + try: + while loader.check_data(): + yield loader.get_data() + finally: + loader.dispose() + +def full_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve all tags except those known to be + unsafe on untrusted input. + """ + return load(stream, FullLoader) + +def full_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve all tags except those known to be + unsafe on untrusted input. + """ + return load_all(stream, FullLoader) + +def safe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve only basic YAML tags. This is known + to be safe for untrusted input. + """ + return load(stream, SafeLoader) + +def safe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve only basic YAML tags. This is known + to be safe for untrusted input. + """ + return load_all(stream, SafeLoader) + +def unsafe_load(stream): + """ + Parse the first YAML document in a stream + and produce the corresponding Python object. + + Resolve all tags, even those known to be + unsafe on untrusted input. + """ + return load(stream, UnsafeLoader) + +def unsafe_load_all(stream): + """ + Parse all YAML documents in a stream + and produce corresponding Python objects. + + Resolve all tags, even those known to be + unsafe on untrusted input. + """ + return load_all(stream, UnsafeLoader) + +def emit(events, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + """ + Emit YAML parsing events into a stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + stream = io.StringIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + try: + for event in events: + dumper.emit(event) + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize_all(nodes, stream=None, Dumper=Dumper, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None): + """ + Serialize a sequence of representation trees into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + stream = io.StringIO() + else: + stream = io.BytesIO() + getvalue = stream.getvalue + dumper = Dumper(stream, canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end) + try: + dumper.open() + for node in nodes: + dumper.serialize(node) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def serialize(node, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a representation tree into a YAML stream. + If stream is None, return the produced string instead. + """ + return serialize_all([node], stream, Dumper=Dumper, **kwds) + +def dump_all(documents, stream=None, Dumper=Dumper, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + """ + Serialize a sequence of Python objects into a YAML stream. + If stream is None, return the produced string instead. + """ + getvalue = None + if stream is None: + if encoding is None: + stream = io.StringIO() + else: + stream = io.BytesIO() + getvalue = stream.getvalue + dumper = Dumper(stream, default_style=default_style, + default_flow_style=default_flow_style, + canonical=canonical, indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break, + encoding=encoding, version=version, tags=tags, + explicit_start=explicit_start, explicit_end=explicit_end, sort_keys=sort_keys) + try: + dumper.open() + for data in documents: + dumper.represent(data) + dumper.close() + finally: + dumper.dispose() + if getvalue: + return getvalue() + +def dump(data, stream=None, Dumper=Dumper, **kwds): + """ + Serialize a Python object into a YAML stream. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=Dumper, **kwds) + +def safe_dump_all(documents, stream=None, **kwds): + """ + Serialize a sequence of Python objects into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all(documents, stream, Dumper=SafeDumper, **kwds) + +def safe_dump(data, stream=None, **kwds): + """ + Serialize a Python object into a YAML stream. + Produce only basic YAML tags. + If stream is None, return the produced string instead. + """ + return dump_all([data], stream, Dumper=SafeDumper, **kwds) + +def add_implicit_resolver(tag, regexp, first=None, + Loader=None, Dumper=Dumper): + """ + Add an implicit scalar detector. + If an implicit scalar value matches the given regexp, + the corresponding tag is assigned to the scalar. + first is a sequence of possible initial characters or None. + """ + if Loader is None: + loader.Loader.add_implicit_resolver(tag, regexp, first) + loader.FullLoader.add_implicit_resolver(tag, regexp, first) + loader.UnsafeLoader.add_implicit_resolver(tag, regexp, first) + else: + Loader.add_implicit_resolver(tag, regexp, first) + Dumper.add_implicit_resolver(tag, regexp, first) + +def add_path_resolver(tag, path, kind=None, Loader=None, Dumper=Dumper): + """ + Add a path based resolver for the given tag. + A path is a list of keys that forms a path + to a node in the representation tree. + Keys can be string values, integers, or None. + """ + if Loader is None: + loader.Loader.add_path_resolver(tag, path, kind) + loader.FullLoader.add_path_resolver(tag, path, kind) + loader.UnsafeLoader.add_path_resolver(tag, path, kind) + else: + Loader.add_path_resolver(tag, path, kind) + Dumper.add_path_resolver(tag, path, kind) + +def add_constructor(tag, constructor, Loader=None): + """ + Add a constructor for the given tag. + Constructor is a function that accepts a Loader instance + and a node object and produces the corresponding Python object. + """ + if Loader is None: + loader.Loader.add_constructor(tag, constructor) + loader.FullLoader.add_constructor(tag, constructor) + loader.UnsafeLoader.add_constructor(tag, constructor) + else: + Loader.add_constructor(tag, constructor) + +def add_multi_constructor(tag_prefix, multi_constructor, Loader=None): + """ + Add a multi-constructor for the given tag prefix. + Multi-constructor is called for a node if its tag starts with tag_prefix. + Multi-constructor accepts a Loader instance, a tag suffix, + and a node object and produces the corresponding Python object. + """ + if Loader is None: + loader.Loader.add_multi_constructor(tag_prefix, multi_constructor) + loader.FullLoader.add_multi_constructor(tag_prefix, multi_constructor) + loader.UnsafeLoader.add_multi_constructor(tag_prefix, multi_constructor) + else: + Loader.add_multi_constructor(tag_prefix, multi_constructor) + +def add_representer(data_type, representer, Dumper=Dumper): + """ + Add a representer for the given type. + Representer is a function accepting a Dumper instance + and an instance of the given data type + and producing the corresponding representation node. + """ + Dumper.add_representer(data_type, representer) + +def add_multi_representer(data_type, multi_representer, Dumper=Dumper): + """ + Add a representer for the given type. + Multi-representer is a function accepting a Dumper instance + and an instance of the given data type or subtype + and producing the corresponding representation node. + """ + Dumper.add_multi_representer(data_type, multi_representer) + +class YAMLObjectMetaclass(type): + """ + The metaclass for YAMLObject. + """ + def __init__(cls, name, bases, kwds): + super(YAMLObjectMetaclass, cls).__init__(name, bases, kwds) + if 'yaml_tag' in kwds and kwds['yaml_tag'] is not None: + if isinstance(cls.yaml_loader, list): + for loader in cls.yaml_loader: + loader.add_constructor(cls.yaml_tag, cls.from_yaml) + else: + cls.yaml_loader.add_constructor(cls.yaml_tag, cls.from_yaml) + + cls.yaml_dumper.add_representer(cls, cls.to_yaml) + +class YAMLObject(metaclass=YAMLObjectMetaclass): + """ + An object that can dump itself to a YAML stream + and load itself from a YAML stream. + """ + + __slots__ = () # no direct instantiation, so allow immutable subclasses + + yaml_loader = [Loader, FullLoader, UnsafeLoader] + yaml_dumper = Dumper + + yaml_tag = None + yaml_flow_style = None + + @classmethod + def from_yaml(cls, loader, node): + """ + Convert a representation node to a Python object. + """ + return loader.construct_yaml_object(node, cls) + + @classmethod + def to_yaml(cls, dumper, data): + """ + Convert a Python object to a representation node. + """ + return dumper.represent_yaml_object(cls.yaml_tag, data, cls, + flow_style=cls.yaml_flow_style) + diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/composer.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/composer.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ca743b9281f2426b85c98b687e21f3418224034e Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/composer.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/constructor.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/constructor.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..1fe88f5d152fce56218149e6faaf829398c62361 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/constructor.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/cyaml.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/cyaml.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..7382cbd193f6e1a3714283c97175a5a44be644d1 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/cyaml.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/dumper.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/dumper.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..ae756a5ebbaa88543df421e550cae7876607f8be Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/dumper.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/emitter.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/emitter.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..85bc7ca6c64b008cd60adaa527fc237d547e72c3 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/emitter.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/error.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/error.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b4d3672855638645eda774ba0f9966f0477dfe69 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/error.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/events.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/events.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..c67e140151699e7853c1de1df96f486bd972b2b3 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/events.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/loader.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/loader.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..a0d0f16e24735a131661573c43598e231efcea7f Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/loader.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/parser.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/parser.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..fb9d3c3aa905772ec90ac944f2e429efa8ed5a65 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/parser.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/reader.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/reader.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..42979b26cd08d15d79ed86bd3028e8014bfd2ae3 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/reader.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/representer.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/representer.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..09c0ec66f6ddbf14d50bd0becf0d4c77b673c0ae Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/representer.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/resolver.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/resolver.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..78b9e79547f7498881f9c650169348460e111eb9 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/resolver.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/scanner.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/scanner.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..b4e3100622aa9424c09b561063a6b74008ff3894 Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/scanner.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/serializer.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/serializer.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..8239ef65de857d424ec4b176f8d9fa32aaae494e Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/serializer.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/__pycache__/tokens.cpython-311.pyc b/.venv/lib/python3.11/site-packages/yaml/__pycache__/tokens.cpython-311.pyc new file mode 100644 index 0000000000000000000000000000000000000000..2e17349f145229a8fa924ebd06dc7cd304bf3baf Binary files /dev/null and b/.venv/lib/python3.11/site-packages/yaml/__pycache__/tokens.cpython-311.pyc differ diff --git a/.venv/lib/python3.11/site-packages/yaml/composer.py b/.venv/lib/python3.11/site-packages/yaml/composer.py new file mode 100644 index 0000000000000000000000000000000000000000..6d15cb40e3b4198819c91c6f8d8b32807fcf53b2 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/composer.py @@ -0,0 +1,139 @@ + +__all__ = ['Composer', 'ComposerError'] + +from .error import MarkedYAMLError +from .events import * +from .nodes import * + +class ComposerError(MarkedYAMLError): + pass + +class Composer: + + def __init__(self): + self.anchors = {} + + def check_node(self): + # Drop the STREAM-START event. + if self.check_event(StreamStartEvent): + self.get_event() + + # If there are more documents available? + return not self.check_event(StreamEndEvent) + + def get_node(self): + # Get the root node of the next document. + if not self.check_event(StreamEndEvent): + return self.compose_document() + + def get_single_node(self): + # Drop the STREAM-START event. + self.get_event() + + # Compose a document if the stream is not empty. + document = None + if not self.check_event(StreamEndEvent): + document = self.compose_document() + + # Ensure that the stream contains no more documents. + if not self.check_event(StreamEndEvent): + event = self.get_event() + raise ComposerError("expected a single document in the stream", + document.start_mark, "but found another document", + event.start_mark) + + # Drop the STREAM-END event. + self.get_event() + + return document + + def compose_document(self): + # Drop the DOCUMENT-START event. + self.get_event() + + # Compose the root node. + node = self.compose_node(None, None) + + # Drop the DOCUMENT-END event. + self.get_event() + + self.anchors = {} + return node + + def compose_node(self, parent, index): + if self.check_event(AliasEvent): + event = self.get_event() + anchor = event.anchor + if anchor not in self.anchors: + raise ComposerError(None, None, "found undefined alias %r" + % anchor, event.start_mark) + return self.anchors[anchor] + event = self.peek_event() + anchor = event.anchor + if anchor is not None: + if anchor in self.anchors: + raise ComposerError("found duplicate anchor %r; first occurrence" + % anchor, self.anchors[anchor].start_mark, + "second occurrence", event.start_mark) + self.descend_resolver(parent, index) + if self.check_event(ScalarEvent): + node = self.compose_scalar_node(anchor) + elif self.check_event(SequenceStartEvent): + node = self.compose_sequence_node(anchor) + elif self.check_event(MappingStartEvent): + node = self.compose_mapping_node(anchor) + self.ascend_resolver() + return node + + def compose_scalar_node(self, anchor): + event = self.get_event() + tag = event.tag + if tag is None or tag == '!': + tag = self.resolve(ScalarNode, event.value, event.implicit) + node = ScalarNode(tag, event.value, + event.start_mark, event.end_mark, style=event.style) + if anchor is not None: + self.anchors[anchor] = node + return node + + def compose_sequence_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == '!': + tag = self.resolve(SequenceNode, None, start_event.implicit) + node = SequenceNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + index = 0 + while not self.check_event(SequenceEndEvent): + node.value.append(self.compose_node(node, index)) + index += 1 + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + + def compose_mapping_node(self, anchor): + start_event = self.get_event() + tag = start_event.tag + if tag is None or tag == '!': + tag = self.resolve(MappingNode, None, start_event.implicit) + node = MappingNode(tag, [], + start_event.start_mark, None, + flow_style=start_event.flow_style) + if anchor is not None: + self.anchors[anchor] = node + while not self.check_event(MappingEndEvent): + #key_event = self.peek_event() + item_key = self.compose_node(node, None) + #if item_key in node.value: + # raise ComposerError("while composing a mapping", start_event.start_mark, + # "found duplicate key", key_event.start_mark) + item_value = self.compose_node(node, item_key) + #node.value[item_key] = item_value + node.value.append((item_key, item_value)) + end_event = self.get_event() + node.end_mark = end_event.end_mark + return node + diff --git a/.venv/lib/python3.11/site-packages/yaml/constructor.py b/.venv/lib/python3.11/site-packages/yaml/constructor.py new file mode 100644 index 0000000000000000000000000000000000000000..619acd3070a4845c653fcf22a626e05158035bc2 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/constructor.py @@ -0,0 +1,748 @@ + +__all__ = [ + 'BaseConstructor', + 'SafeConstructor', + 'FullConstructor', + 'UnsafeConstructor', + 'Constructor', + 'ConstructorError' +] + +from .error import * +from .nodes import * + +import collections.abc, datetime, base64, binascii, re, sys, types + +class ConstructorError(MarkedYAMLError): + pass + +class BaseConstructor: + + yaml_constructors = {} + yaml_multi_constructors = {} + + def __init__(self): + self.constructed_objects = {} + self.recursive_objects = {} + self.state_generators = [] + self.deep_construct = False + + def check_data(self): + # If there are more documents available? + return self.check_node() + + def check_state_key(self, key): + """Block special attributes/methods from being set in a newly created + object, to prevent user-controlled methods from being called during + deserialization""" + if self.get_state_keys_blacklist_regexp().match(key): + raise ConstructorError(None, None, + "blacklisted key '%s' in instance state found" % (key,), None) + + def get_data(self): + # Construct and return the next document. + if self.check_node(): + return self.construct_document(self.get_node()) + + def get_single_data(self): + # Ensure that the stream contains a single document and construct it. + node = self.get_single_node() + if node is not None: + return self.construct_document(node) + return None + + def construct_document(self, node): + data = self.construct_object(node) + while self.state_generators: + state_generators = self.state_generators + self.state_generators = [] + for generator in state_generators: + for dummy in generator: + pass + self.constructed_objects = {} + self.recursive_objects = {} + self.deep_construct = False + return data + + def construct_object(self, node, deep=False): + if node in self.constructed_objects: + return self.constructed_objects[node] + if deep: + old_deep = self.deep_construct + self.deep_construct = True + if node in self.recursive_objects: + raise ConstructorError(None, None, + "found unconstructable recursive node", node.start_mark) + self.recursive_objects[node] = None + constructor = None + tag_suffix = None + if node.tag in self.yaml_constructors: + constructor = self.yaml_constructors[node.tag] + else: + for tag_prefix in self.yaml_multi_constructors: + if tag_prefix is not None and node.tag.startswith(tag_prefix): + tag_suffix = node.tag[len(tag_prefix):] + constructor = self.yaml_multi_constructors[tag_prefix] + break + else: + if None in self.yaml_multi_constructors: + tag_suffix = node.tag + constructor = self.yaml_multi_constructors[None] + elif None in self.yaml_constructors: + constructor = self.yaml_constructors[None] + elif isinstance(node, ScalarNode): + constructor = self.__class__.construct_scalar + elif isinstance(node, SequenceNode): + constructor = self.__class__.construct_sequence + elif isinstance(node, MappingNode): + constructor = self.__class__.construct_mapping + if tag_suffix is None: + data = constructor(self, node) + else: + data = constructor(self, tag_suffix, node) + if isinstance(data, types.GeneratorType): + generator = data + data = next(generator) + if self.deep_construct: + for dummy in generator: + pass + else: + self.state_generators.append(generator) + self.constructed_objects[node] = data + del self.recursive_objects[node] + if deep: + self.deep_construct = old_deep + return data + + def construct_scalar(self, node): + if not isinstance(node, ScalarNode): + raise ConstructorError(None, None, + "expected a scalar node, but found %s" % node.id, + node.start_mark) + return node.value + + def construct_sequence(self, node, deep=False): + if not isinstance(node, SequenceNode): + raise ConstructorError(None, None, + "expected a sequence node, but found %s" % node.id, + node.start_mark) + return [self.construct_object(child, deep=deep) + for child in node.value] + + def construct_mapping(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + mapping = {} + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + if not isinstance(key, collections.abc.Hashable): + raise ConstructorError("while constructing a mapping", node.start_mark, + "found unhashable key", key_node.start_mark) + value = self.construct_object(value_node, deep=deep) + mapping[key] = value + return mapping + + def construct_pairs(self, node, deep=False): + if not isinstance(node, MappingNode): + raise ConstructorError(None, None, + "expected a mapping node, but found %s" % node.id, + node.start_mark) + pairs = [] + for key_node, value_node in node.value: + key = self.construct_object(key_node, deep=deep) + value = self.construct_object(value_node, deep=deep) + pairs.append((key, value)) + return pairs + + @classmethod + def add_constructor(cls, tag, constructor): + if not 'yaml_constructors' in cls.__dict__: + cls.yaml_constructors = cls.yaml_constructors.copy() + cls.yaml_constructors[tag] = constructor + + @classmethod + def add_multi_constructor(cls, tag_prefix, multi_constructor): + if not 'yaml_multi_constructors' in cls.__dict__: + cls.yaml_multi_constructors = cls.yaml_multi_constructors.copy() + cls.yaml_multi_constructors[tag_prefix] = multi_constructor + +class SafeConstructor(BaseConstructor): + + def construct_scalar(self, node): + if isinstance(node, MappingNode): + for key_node, value_node in node.value: + if key_node.tag == 'tag:yaml.org,2002:value': + return self.construct_scalar(value_node) + return super().construct_scalar(node) + + def flatten_mapping(self, node): + merge = [] + index = 0 + while index < len(node.value): + key_node, value_node = node.value[index] + if key_node.tag == 'tag:yaml.org,2002:merge': + del node.value[index] + if isinstance(value_node, MappingNode): + self.flatten_mapping(value_node) + merge.extend(value_node.value) + elif isinstance(value_node, SequenceNode): + submerge = [] + for subnode in value_node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing a mapping", + node.start_mark, + "expected a mapping for merging, but found %s" + % subnode.id, subnode.start_mark) + self.flatten_mapping(subnode) + submerge.append(subnode.value) + submerge.reverse() + for value in submerge: + merge.extend(value) + else: + raise ConstructorError("while constructing a mapping", node.start_mark, + "expected a mapping or list of mappings for merging, but found %s" + % value_node.id, value_node.start_mark) + elif key_node.tag == 'tag:yaml.org,2002:value': + key_node.tag = 'tag:yaml.org,2002:str' + index += 1 + else: + index += 1 + if merge: + node.value = merge + node.value + + def construct_mapping(self, node, deep=False): + if isinstance(node, MappingNode): + self.flatten_mapping(node) + return super().construct_mapping(node, deep=deep) + + def construct_yaml_null(self, node): + self.construct_scalar(node) + return None + + bool_values = { + 'yes': True, + 'no': False, + 'true': True, + 'false': False, + 'on': True, + 'off': False, + } + + def construct_yaml_bool(self, node): + value = self.construct_scalar(node) + return self.bool_values[value.lower()] + + def construct_yaml_int(self, node): + value = self.construct_scalar(node) + value = value.replace('_', '') + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '0': + return 0 + elif value.startswith('0b'): + return sign*int(value[2:], 2) + elif value.startswith('0x'): + return sign*int(value[2:], 16) + elif value[0] == '0': + return sign*int(value, 8) + elif ':' in value: + digits = [int(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*int(value) + + inf_value = 1e300 + while inf_value != inf_value*inf_value: + inf_value *= inf_value + nan_value = -inf_value/inf_value # Trying to make a quiet NaN (like C99). + + def construct_yaml_float(self, node): + value = self.construct_scalar(node) + value = value.replace('_', '').lower() + sign = +1 + if value[0] == '-': + sign = -1 + if value[0] in '+-': + value = value[1:] + if value == '.inf': + return sign*self.inf_value + elif value == '.nan': + return self.nan_value + elif ':' in value: + digits = [float(part) for part in value.split(':')] + digits.reverse() + base = 1 + value = 0.0 + for digit in digits: + value += digit*base + base *= 60 + return sign*value + else: + return sign*float(value) + + def construct_yaml_binary(self, node): + try: + value = self.construct_scalar(node).encode('ascii') + except UnicodeEncodeError as exc: + raise ConstructorError(None, None, + "failed to convert base64 data into ascii: %s" % exc, + node.start_mark) + try: + if hasattr(base64, 'decodebytes'): + return base64.decodebytes(value) + else: + return base64.decodestring(value) + except binascii.Error as exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + timestamp_regexp = re.compile( + r'''^(?P[0-9][0-9][0-9][0-9]) + -(?P[0-9][0-9]?) + -(?P[0-9][0-9]?) + (?:(?:[Tt]|[ \t]+) + (?P[0-9][0-9]?) + :(?P[0-9][0-9]) + :(?P[0-9][0-9]) + (?:\.(?P[0-9]*))? + (?:[ \t]*(?PZ|(?P[-+])(?P[0-9][0-9]?) + (?::(?P[0-9][0-9]))?))?)?$''', re.X) + + def construct_yaml_timestamp(self, node): + value = self.construct_scalar(node) + match = self.timestamp_regexp.match(node.value) + values = match.groupdict() + year = int(values['year']) + month = int(values['month']) + day = int(values['day']) + if not values['hour']: + return datetime.date(year, month, day) + hour = int(values['hour']) + minute = int(values['minute']) + second = int(values['second']) + fraction = 0 + tzinfo = None + if values['fraction']: + fraction = values['fraction'][:6] + while len(fraction) < 6: + fraction += '0' + fraction = int(fraction) + if values['tz_sign']: + tz_hour = int(values['tz_hour']) + tz_minute = int(values['tz_minute'] or 0) + delta = datetime.timedelta(hours=tz_hour, minutes=tz_minute) + if values['tz_sign'] == '-': + delta = -delta + tzinfo = datetime.timezone(delta) + elif values['tz']: + tzinfo = datetime.timezone.utc + return datetime.datetime(year, month, day, hour, minute, second, fraction, + tzinfo=tzinfo) + + def construct_yaml_omap(self, node): + # Note: we do not check for duplicate keys, because it's too + # CPU-expensive. + omap = [] + yield omap + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing an ordered map", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + omap.append((key, value)) + + def construct_yaml_pairs(self, node): + # Note: the same code as `construct_yaml_omap`. + pairs = [] + yield pairs + if not isinstance(node, SequenceNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a sequence, but found %s" % node.id, node.start_mark) + for subnode in node.value: + if not isinstance(subnode, MappingNode): + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a mapping of length 1, but found %s" % subnode.id, + subnode.start_mark) + if len(subnode.value) != 1: + raise ConstructorError("while constructing pairs", node.start_mark, + "expected a single mapping item, but found %d items" % len(subnode.value), + subnode.start_mark) + key_node, value_node = subnode.value[0] + key = self.construct_object(key_node) + value = self.construct_object(value_node) + pairs.append((key, value)) + + def construct_yaml_set(self, node): + data = set() + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_str(self, node): + return self.construct_scalar(node) + + def construct_yaml_seq(self, node): + data = [] + yield data + data.extend(self.construct_sequence(node)) + + def construct_yaml_map(self, node): + data = {} + yield data + value = self.construct_mapping(node) + data.update(value) + + def construct_yaml_object(self, node, cls): + data = cls.__new__(cls) + yield data + if hasattr(data, '__setstate__'): + state = self.construct_mapping(node, deep=True) + data.__setstate__(state) + else: + state = self.construct_mapping(node) + data.__dict__.update(state) + + def construct_undefined(self, node): + raise ConstructorError(None, None, + "could not determine a constructor for the tag %r" % node.tag, + node.start_mark) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:null', + SafeConstructor.construct_yaml_null) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:bool', + SafeConstructor.construct_yaml_bool) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:int', + SafeConstructor.construct_yaml_int) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:float', + SafeConstructor.construct_yaml_float) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:binary', + SafeConstructor.construct_yaml_binary) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:timestamp', + SafeConstructor.construct_yaml_timestamp) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:omap', + SafeConstructor.construct_yaml_omap) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:pairs', + SafeConstructor.construct_yaml_pairs) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:set', + SafeConstructor.construct_yaml_set) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:str', + SafeConstructor.construct_yaml_str) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:seq', + SafeConstructor.construct_yaml_seq) + +SafeConstructor.add_constructor( + 'tag:yaml.org,2002:map', + SafeConstructor.construct_yaml_map) + +SafeConstructor.add_constructor(None, + SafeConstructor.construct_undefined) + +class FullConstructor(SafeConstructor): + # 'extend' is blacklisted because it is used by + # construct_python_object_apply to add `listitems` to a newly generate + # python instance + def get_state_keys_blacklist(self): + return ['^extend$', '^__.*__$'] + + def get_state_keys_blacklist_regexp(self): + if not hasattr(self, 'state_keys_blacklist_regexp'): + self.state_keys_blacklist_regexp = re.compile('(' + '|'.join(self.get_state_keys_blacklist()) + ')') + return self.state_keys_blacklist_regexp + + def construct_python_str(self, node): + return self.construct_scalar(node) + + def construct_python_unicode(self, node): + return self.construct_scalar(node) + + def construct_python_bytes(self, node): + try: + value = self.construct_scalar(node).encode('ascii') + except UnicodeEncodeError as exc: + raise ConstructorError(None, None, + "failed to convert base64 data into ascii: %s" % exc, + node.start_mark) + try: + if hasattr(base64, 'decodebytes'): + return base64.decodebytes(value) + else: + return base64.decodestring(value) + except binascii.Error as exc: + raise ConstructorError(None, None, + "failed to decode base64 data: %s" % exc, node.start_mark) + + def construct_python_long(self, node): + return self.construct_yaml_int(node) + + def construct_python_complex(self, node): + return complex(self.construct_scalar(node)) + + def construct_python_tuple(self, node): + return tuple(self.construct_sequence(node)) + + def find_python_module(self, name, mark, unsafe=False): + if not name: + raise ConstructorError("while constructing a Python module", mark, + "expected non-empty name appended to the tag", mark) + if unsafe: + try: + __import__(name) + except ImportError as exc: + raise ConstructorError("while constructing a Python module", mark, + "cannot find module %r (%s)" % (name, exc), mark) + if name not in sys.modules: + raise ConstructorError("while constructing a Python module", mark, + "module %r is not imported" % name, mark) + return sys.modules[name] + + def find_python_name(self, name, mark, unsafe=False): + if not name: + raise ConstructorError("while constructing a Python object", mark, + "expected non-empty name appended to the tag", mark) + if '.' in name: + module_name, object_name = name.rsplit('.', 1) + else: + module_name = 'builtins' + object_name = name + if unsafe: + try: + __import__(module_name) + except ImportError as exc: + raise ConstructorError("while constructing a Python object", mark, + "cannot find module %r (%s)" % (module_name, exc), mark) + if module_name not in sys.modules: + raise ConstructorError("while constructing a Python object", mark, + "module %r is not imported" % module_name, mark) + module = sys.modules[module_name] + if not hasattr(module, object_name): + raise ConstructorError("while constructing a Python object", mark, + "cannot find %r in the module %r" + % (object_name, module.__name__), mark) + return getattr(module, object_name) + + def construct_python_name(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python name", node.start_mark, + "expected the empty value, but found %r" % value, node.start_mark) + return self.find_python_name(suffix, node.start_mark) + + def construct_python_module(self, suffix, node): + value = self.construct_scalar(node) + if value: + raise ConstructorError("while constructing a Python module", node.start_mark, + "expected the empty value, but found %r" % value, node.start_mark) + return self.find_python_module(suffix, node.start_mark) + + def make_python_instance(self, suffix, node, + args=None, kwds=None, newobj=False, unsafe=False): + if not args: + args = [] + if not kwds: + kwds = {} + cls = self.find_python_name(suffix, node.start_mark) + if not (unsafe or isinstance(cls, type)): + raise ConstructorError("while constructing a Python instance", node.start_mark, + "expected a class, but found %r" % type(cls), + node.start_mark) + if newobj and isinstance(cls, type): + return cls.__new__(cls, *args, **kwds) + else: + return cls(*args, **kwds) + + def set_python_instance_state(self, instance, state, unsafe=False): + if hasattr(instance, '__setstate__'): + instance.__setstate__(state) + else: + slotstate = {} + if isinstance(state, tuple) and len(state) == 2: + state, slotstate = state + if hasattr(instance, '__dict__'): + if not unsafe and state: + for key in state.keys(): + self.check_state_key(key) + instance.__dict__.update(state) + elif state: + slotstate.update(state) + for key, value in slotstate.items(): + if not unsafe: + self.check_state_key(key) + setattr(instance, key, value) + + def construct_python_object(self, suffix, node): + # Format: + # !!python/object:module.name { ... state ... } + instance = self.make_python_instance(suffix, node, newobj=True) + yield instance + deep = hasattr(instance, '__setstate__') + state = self.construct_mapping(node, deep=deep) + self.set_python_instance_state(instance, state) + + def construct_python_object_apply(self, suffix, node, newobj=False): + # Format: + # !!python/object/apply # (or !!python/object/new) + # args: [ ... arguments ... ] + # kwds: { ... keywords ... } + # state: ... state ... + # listitems: [ ... listitems ... ] + # dictitems: { ... dictitems ... } + # or short format: + # !!python/object/apply [ ... arguments ... ] + # The difference between !!python/object/apply and !!python/object/new + # is how an object is created, check make_python_instance for details. + if isinstance(node, SequenceNode): + args = self.construct_sequence(node, deep=True) + kwds = {} + state = {} + listitems = [] + dictitems = {} + else: + value = self.construct_mapping(node, deep=True) + args = value.get('args', []) + kwds = value.get('kwds', {}) + state = value.get('state', {}) + listitems = value.get('listitems', []) + dictitems = value.get('dictitems', {}) + instance = self.make_python_instance(suffix, node, args, kwds, newobj) + if state: + self.set_python_instance_state(instance, state) + if listitems: + instance.extend(listitems) + if dictitems: + for key in dictitems: + instance[key] = dictitems[key] + return instance + + def construct_python_object_new(self, suffix, node): + return self.construct_python_object_apply(suffix, node, newobj=True) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/none', + FullConstructor.construct_yaml_null) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/bool', + FullConstructor.construct_yaml_bool) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/str', + FullConstructor.construct_python_str) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/unicode', + FullConstructor.construct_python_unicode) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/bytes', + FullConstructor.construct_python_bytes) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/int', + FullConstructor.construct_yaml_int) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/long', + FullConstructor.construct_python_long) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/float', + FullConstructor.construct_yaml_float) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/complex', + FullConstructor.construct_python_complex) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/list', + FullConstructor.construct_yaml_seq) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/tuple', + FullConstructor.construct_python_tuple) + +FullConstructor.add_constructor( + 'tag:yaml.org,2002:python/dict', + FullConstructor.construct_yaml_map) + +FullConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/name:', + FullConstructor.construct_python_name) + +class UnsafeConstructor(FullConstructor): + + def find_python_module(self, name, mark): + return super(UnsafeConstructor, self).find_python_module(name, mark, unsafe=True) + + def find_python_name(self, name, mark): + return super(UnsafeConstructor, self).find_python_name(name, mark, unsafe=True) + + def make_python_instance(self, suffix, node, args=None, kwds=None, newobj=False): + return super(UnsafeConstructor, self).make_python_instance( + suffix, node, args, kwds, newobj, unsafe=True) + + def set_python_instance_state(self, instance, state): + return super(UnsafeConstructor, self).set_python_instance_state( + instance, state, unsafe=True) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/module:', + UnsafeConstructor.construct_python_module) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object:', + UnsafeConstructor.construct_python_object) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object/new:', + UnsafeConstructor.construct_python_object_new) + +UnsafeConstructor.add_multi_constructor( + 'tag:yaml.org,2002:python/object/apply:', + UnsafeConstructor.construct_python_object_apply) + +# Constructor is same as UnsafeConstructor. Need to leave this in place in case +# people have extended it directly. +class Constructor(UnsafeConstructor): + pass diff --git a/.venv/lib/python3.11/site-packages/yaml/cyaml.py b/.venv/lib/python3.11/site-packages/yaml/cyaml.py new file mode 100644 index 0000000000000000000000000000000000000000..0c21345879b298bb8668201bebe7d289586b17f9 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/cyaml.py @@ -0,0 +1,101 @@ + +__all__ = [ + 'CBaseLoader', 'CSafeLoader', 'CFullLoader', 'CUnsafeLoader', 'CLoader', + 'CBaseDumper', 'CSafeDumper', 'CDumper' +] + +from yaml._yaml import CParser, CEmitter + +from .constructor import * + +from .serializer import * +from .representer import * + +from .resolver import * + +class CBaseLoader(CParser, BaseConstructor, BaseResolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class CSafeLoader(CParser, SafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class CFullLoader(CParser, FullConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + FullConstructor.__init__(self) + Resolver.__init__(self) + +class CUnsafeLoader(CParser, UnsafeConstructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + UnsafeConstructor.__init__(self) + Resolver.__init__(self) + +class CLoader(CParser, Constructor, Resolver): + + def __init__(self, stream): + CParser.__init__(self, stream) + Constructor.__init__(self) + Resolver.__init__(self) + +class CBaseDumper(CEmitter, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class CSafeDumper(CEmitter, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class CDumper(CEmitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + CEmitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, encoding=encoding, + allow_unicode=allow_unicode, line_break=line_break, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + diff --git a/.venv/lib/python3.11/site-packages/yaml/dumper.py b/.venv/lib/python3.11/site-packages/yaml/dumper.py new file mode 100644 index 0000000000000000000000000000000000000000..6aadba551f3836b02f4752277f4b3027073defad --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/dumper.py @@ -0,0 +1,62 @@ + +__all__ = ['BaseDumper', 'SafeDumper', 'Dumper'] + +from .emitter import * +from .serializer import * +from .representer import * +from .resolver import * + +class BaseDumper(Emitter, Serializer, BaseRepresenter, BaseResolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class SafeDumper(Emitter, Serializer, SafeRepresenter, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + SafeRepresenter.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + +class Dumper(Emitter, Serializer, Representer, Resolver): + + def __init__(self, stream, + default_style=None, default_flow_style=False, + canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None, + encoding=None, explicit_start=None, explicit_end=None, + version=None, tags=None, sort_keys=True): + Emitter.__init__(self, stream, canonical=canonical, + indent=indent, width=width, + allow_unicode=allow_unicode, line_break=line_break) + Serializer.__init__(self, encoding=encoding, + explicit_start=explicit_start, explicit_end=explicit_end, + version=version, tags=tags) + Representer.__init__(self, default_style=default_style, + default_flow_style=default_flow_style, sort_keys=sort_keys) + Resolver.__init__(self) + diff --git a/.venv/lib/python3.11/site-packages/yaml/emitter.py b/.venv/lib/python3.11/site-packages/yaml/emitter.py new file mode 100644 index 0000000000000000000000000000000000000000..a664d011162af69184df2f8e59ab7feec818f7c7 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/emitter.py @@ -0,0 +1,1137 @@ + +# Emitter expects events obeying the following grammar: +# stream ::= STREAM-START document* STREAM-END +# document ::= DOCUMENT-START node DOCUMENT-END +# node ::= SCALAR | sequence | mapping +# sequence ::= SEQUENCE-START node* SEQUENCE-END +# mapping ::= MAPPING-START (node node)* MAPPING-END + +__all__ = ['Emitter', 'EmitterError'] + +from .error import YAMLError +from .events import * + +class EmitterError(YAMLError): + pass + +class ScalarAnalysis: + def __init__(self, scalar, empty, multiline, + allow_flow_plain, allow_block_plain, + allow_single_quoted, allow_double_quoted, + allow_block): + self.scalar = scalar + self.empty = empty + self.multiline = multiline + self.allow_flow_plain = allow_flow_plain + self.allow_block_plain = allow_block_plain + self.allow_single_quoted = allow_single_quoted + self.allow_double_quoted = allow_double_quoted + self.allow_block = allow_block + +class Emitter: + + DEFAULT_TAG_PREFIXES = { + '!' : '!', + 'tag:yaml.org,2002:' : '!!', + } + + def __init__(self, stream, canonical=None, indent=None, width=None, + allow_unicode=None, line_break=None): + + # The stream should have the methods `write` and possibly `flush`. + self.stream = stream + + # Encoding can be overridden by STREAM-START. + self.encoding = None + + # Emitter is a state machine with a stack of states to handle nested + # structures. + self.states = [] + self.state = self.expect_stream_start + + # Current event and the event queue. + self.events = [] + self.event = None + + # The current indentation level and the stack of previous indents. + self.indents = [] + self.indent = None + + # Flow level. + self.flow_level = 0 + + # Contexts. + self.root_context = False + self.sequence_context = False + self.mapping_context = False + self.simple_key_context = False + + # Characteristics of the last emitted character: + # - current position. + # - is it a whitespace? + # - is it an indention character + # (indentation space, '-', '?', or ':')? + self.line = 0 + self.column = 0 + self.whitespace = True + self.indention = True + + # Whether the document requires an explicit document indicator + self.open_ended = False + + # Formatting details. + self.canonical = canonical + self.allow_unicode = allow_unicode + self.best_indent = 2 + if indent and 1 < indent < 10: + self.best_indent = indent + self.best_width = 80 + if width and width > self.best_indent*2: + self.best_width = width + self.best_line_break = '\n' + if line_break in ['\r', '\n', '\r\n']: + self.best_line_break = line_break + + # Tag prefixes. + self.tag_prefixes = None + + # Prepared anchor and tag. + self.prepared_anchor = None + self.prepared_tag = None + + # Scalar analysis and style. + self.analysis = None + self.style = None + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def emit(self, event): + self.events.append(event) + while not self.need_more_events(): + self.event = self.events.pop(0) + self.state() + self.event = None + + # In some cases, we wait for a few next events before emitting. + + def need_more_events(self): + if not self.events: + return True + event = self.events[0] + if isinstance(event, DocumentStartEvent): + return self.need_events(1) + elif isinstance(event, SequenceStartEvent): + return self.need_events(2) + elif isinstance(event, MappingStartEvent): + return self.need_events(3) + else: + return False + + def need_events(self, count): + level = 0 + for event in self.events[1:]: + if isinstance(event, (DocumentStartEvent, CollectionStartEvent)): + level += 1 + elif isinstance(event, (DocumentEndEvent, CollectionEndEvent)): + level -= 1 + elif isinstance(event, StreamEndEvent): + level = -1 + if level < 0: + return False + return (len(self.events) < count+1) + + def increase_indent(self, flow=False, indentless=False): + self.indents.append(self.indent) + if self.indent is None: + if flow: + self.indent = self.best_indent + else: + self.indent = 0 + elif not indentless: + self.indent += self.best_indent + + # States. + + # Stream handlers. + + def expect_stream_start(self): + if isinstance(self.event, StreamStartEvent): + if self.event.encoding and not hasattr(self.stream, 'encoding'): + self.encoding = self.event.encoding + self.write_stream_start() + self.state = self.expect_first_document_start + else: + raise EmitterError("expected StreamStartEvent, but got %s" + % self.event) + + def expect_nothing(self): + raise EmitterError("expected nothing, but got %s" % self.event) + + # Document handlers. + + def expect_first_document_start(self): + return self.expect_document_start(first=True) + + def expect_document_start(self, first=False): + if isinstance(self.event, DocumentStartEvent): + if (self.event.version or self.event.tags) and self.open_ended: + self.write_indicator('...', True) + self.write_indent() + if self.event.version: + version_text = self.prepare_version(self.event.version) + self.write_version_directive(version_text) + self.tag_prefixes = self.DEFAULT_TAG_PREFIXES.copy() + if self.event.tags: + handles = sorted(self.event.tags.keys()) + for handle in handles: + prefix = self.event.tags[handle] + self.tag_prefixes[prefix] = handle + handle_text = self.prepare_tag_handle(handle) + prefix_text = self.prepare_tag_prefix(prefix) + self.write_tag_directive(handle_text, prefix_text) + implicit = (first and not self.event.explicit and not self.canonical + and not self.event.version and not self.event.tags + and not self.check_empty_document()) + if not implicit: + self.write_indent() + self.write_indicator('---', True) + if self.canonical: + self.write_indent() + self.state = self.expect_document_root + elif isinstance(self.event, StreamEndEvent): + if self.open_ended: + self.write_indicator('...', True) + self.write_indent() + self.write_stream_end() + self.state = self.expect_nothing + else: + raise EmitterError("expected DocumentStartEvent, but got %s" + % self.event) + + def expect_document_end(self): + if isinstance(self.event, DocumentEndEvent): + self.write_indent() + if self.event.explicit: + self.write_indicator('...', True) + self.write_indent() + self.flush_stream() + self.state = self.expect_document_start + else: + raise EmitterError("expected DocumentEndEvent, but got %s" + % self.event) + + def expect_document_root(self): + self.states.append(self.expect_document_end) + self.expect_node(root=True) + + # Node handlers. + + def expect_node(self, root=False, sequence=False, mapping=False, + simple_key=False): + self.root_context = root + self.sequence_context = sequence + self.mapping_context = mapping + self.simple_key_context = simple_key + if isinstance(self.event, AliasEvent): + self.expect_alias() + elif isinstance(self.event, (ScalarEvent, CollectionStartEvent)): + self.process_anchor('&') + self.process_tag() + if isinstance(self.event, ScalarEvent): + self.expect_scalar() + elif isinstance(self.event, SequenceStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_sequence(): + self.expect_flow_sequence() + else: + self.expect_block_sequence() + elif isinstance(self.event, MappingStartEvent): + if self.flow_level or self.canonical or self.event.flow_style \ + or self.check_empty_mapping(): + self.expect_flow_mapping() + else: + self.expect_block_mapping() + else: + raise EmitterError("expected NodeEvent, but got %s" % self.event) + + def expect_alias(self): + if self.event.anchor is None: + raise EmitterError("anchor is not specified for alias") + self.process_anchor('*') + self.state = self.states.pop() + + def expect_scalar(self): + self.increase_indent(flow=True) + self.process_scalar() + self.indent = self.indents.pop() + self.state = self.states.pop() + + # Flow sequence handlers. + + def expect_flow_sequence(self): + self.write_indicator('[', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_sequence_item + + def expect_first_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator(']', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + def expect_flow_sequence_item(self): + if isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(',', False) + self.write_indent() + self.write_indicator(']', False) + self.state = self.states.pop() + else: + self.write_indicator(',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + self.states.append(self.expect_flow_sequence_item) + self.expect_node(sequence=True) + + # Flow mapping handlers. + + def expect_flow_mapping(self): + self.write_indicator('{', True, whitespace=True) + self.flow_level += 1 + self.increase_indent(flow=True) + self.state = self.expect_first_flow_mapping_key + + def expect_first_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + self.write_indicator('}', False) + self.state = self.states.pop() + else: + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_key(self): + if isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.flow_level -= 1 + if self.canonical: + self.write_indicator(',', False) + self.write_indent() + self.write_indicator('}', False) + self.state = self.states.pop() + else: + self.write_indicator(',', False) + if self.canonical or self.column > self.best_width: + self.write_indent() + if not self.canonical and self.check_simple_key(): + self.states.append(self.expect_flow_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True) + self.states.append(self.expect_flow_mapping_value) + self.expect_node(mapping=True) + + def expect_flow_mapping_simple_value(self): + self.write_indicator(':', False) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + def expect_flow_mapping_value(self): + if self.canonical or self.column > self.best_width: + self.write_indent() + self.write_indicator(':', True) + self.states.append(self.expect_flow_mapping_key) + self.expect_node(mapping=True) + + # Block sequence handlers. + + def expect_block_sequence(self): + indentless = (self.mapping_context and not self.indention) + self.increase_indent(flow=False, indentless=indentless) + self.state = self.expect_first_block_sequence_item + + def expect_first_block_sequence_item(self): + return self.expect_block_sequence_item(first=True) + + def expect_block_sequence_item(self, first=False): + if not first and isinstance(self.event, SequenceEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + self.write_indicator('-', True, indention=True) + self.states.append(self.expect_block_sequence_item) + self.expect_node(sequence=True) + + # Block mapping handlers. + + def expect_block_mapping(self): + self.increase_indent(flow=False) + self.state = self.expect_first_block_mapping_key + + def expect_first_block_mapping_key(self): + return self.expect_block_mapping_key(first=True) + + def expect_block_mapping_key(self, first=False): + if not first and isinstance(self.event, MappingEndEvent): + self.indent = self.indents.pop() + self.state = self.states.pop() + else: + self.write_indent() + if self.check_simple_key(): + self.states.append(self.expect_block_mapping_simple_value) + self.expect_node(mapping=True, simple_key=True) + else: + self.write_indicator('?', True, indention=True) + self.states.append(self.expect_block_mapping_value) + self.expect_node(mapping=True) + + def expect_block_mapping_simple_value(self): + self.write_indicator(':', False) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + def expect_block_mapping_value(self): + self.write_indent() + self.write_indicator(':', True, indention=True) + self.states.append(self.expect_block_mapping_key) + self.expect_node(mapping=True) + + # Checkers. + + def check_empty_sequence(self): + return (isinstance(self.event, SequenceStartEvent) and self.events + and isinstance(self.events[0], SequenceEndEvent)) + + def check_empty_mapping(self): + return (isinstance(self.event, MappingStartEvent) and self.events + and isinstance(self.events[0], MappingEndEvent)) + + def check_empty_document(self): + if not isinstance(self.event, DocumentStartEvent) or not self.events: + return False + event = self.events[0] + return (isinstance(event, ScalarEvent) and event.anchor is None + and event.tag is None and event.implicit and event.value == '') + + def check_simple_key(self): + length = 0 + if isinstance(self.event, NodeEvent) and self.event.anchor is not None: + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + length += len(self.prepared_anchor) + if isinstance(self.event, (ScalarEvent, CollectionStartEvent)) \ + and self.event.tag is not None: + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(self.event.tag) + length += len(self.prepared_tag) + if isinstance(self.event, ScalarEvent): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + length += len(self.analysis.scalar) + return (length < 128 and (isinstance(self.event, AliasEvent) + or (isinstance(self.event, ScalarEvent) + and not self.analysis.empty and not self.analysis.multiline) + or self.check_empty_sequence() or self.check_empty_mapping())) + + # Anchor, Tag, and Scalar processors. + + def process_anchor(self, indicator): + if self.event.anchor is None: + self.prepared_anchor = None + return + if self.prepared_anchor is None: + self.prepared_anchor = self.prepare_anchor(self.event.anchor) + if self.prepared_anchor: + self.write_indicator(indicator+self.prepared_anchor, True) + self.prepared_anchor = None + + def process_tag(self): + tag = self.event.tag + if isinstance(self.event, ScalarEvent): + if self.style is None: + self.style = self.choose_scalar_style() + if ((not self.canonical or tag is None) and + ((self.style == '' and self.event.implicit[0]) + or (self.style != '' and self.event.implicit[1]))): + self.prepared_tag = None + return + if self.event.implicit[0] and tag is None: + tag = '!' + self.prepared_tag = None + else: + if (not self.canonical or tag is None) and self.event.implicit: + self.prepared_tag = None + return + if tag is None: + raise EmitterError("tag is not specified") + if self.prepared_tag is None: + self.prepared_tag = self.prepare_tag(tag) + if self.prepared_tag: + self.write_indicator(self.prepared_tag, True) + self.prepared_tag = None + + def choose_scalar_style(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.event.style == '"' or self.canonical: + return '"' + if not self.event.style and self.event.implicit[0]: + if (not (self.simple_key_context and + (self.analysis.empty or self.analysis.multiline)) + and (self.flow_level and self.analysis.allow_flow_plain + or (not self.flow_level and self.analysis.allow_block_plain))): + return '' + if self.event.style and self.event.style in '|>': + if (not self.flow_level and not self.simple_key_context + and self.analysis.allow_block): + return self.event.style + if not self.event.style or self.event.style == '\'': + if (self.analysis.allow_single_quoted and + not (self.simple_key_context and self.analysis.multiline)): + return '\'' + return '"' + + def process_scalar(self): + if self.analysis is None: + self.analysis = self.analyze_scalar(self.event.value) + if self.style is None: + self.style = self.choose_scalar_style() + split = (not self.simple_key_context) + #if self.analysis.multiline and split \ + # and (not self.style or self.style in '\'\"'): + # self.write_indent() + if self.style == '"': + self.write_double_quoted(self.analysis.scalar, split) + elif self.style == '\'': + self.write_single_quoted(self.analysis.scalar, split) + elif self.style == '>': + self.write_folded(self.analysis.scalar) + elif self.style == '|': + self.write_literal(self.analysis.scalar) + else: + self.write_plain(self.analysis.scalar, split) + self.analysis = None + self.style = None + + # Analyzers. + + def prepare_version(self, version): + major, minor = version + if major != 1: + raise EmitterError("unsupported YAML version: %d.%d" % (major, minor)) + return '%d.%d' % (major, minor) + + def prepare_tag_handle(self, handle): + if not handle: + raise EmitterError("tag handle must not be empty") + if handle[0] != '!' or handle[-1] != '!': + raise EmitterError("tag handle must start and end with '!': %r" % handle) + for ch in handle[1:-1]: + if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_'): + raise EmitterError("invalid character %r in the tag handle: %r" + % (ch, handle)) + return handle + + def prepare_tag_prefix(self, prefix): + if not prefix: + raise EmitterError("tag prefix must not be empty") + chunks = [] + start = end = 0 + if prefix[0] == '!': + end = 1 + while end < len(prefix): + ch = prefix[end] + if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?!:@&=+$,_.~*\'()[]': + end += 1 + else: + if start < end: + chunks.append(prefix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append('%%%02X' % ord(ch)) + if start < end: + chunks.append(prefix[start:end]) + return ''.join(chunks) + + def prepare_tag(self, tag): + if not tag: + raise EmitterError("tag must not be empty") + if tag == '!': + return tag + handle = None + suffix = tag + prefixes = sorted(self.tag_prefixes.keys()) + for prefix in prefixes: + if tag.startswith(prefix) \ + and (prefix == '!' or len(prefix) < len(tag)): + handle = self.tag_prefixes[prefix] + suffix = tag[len(prefix):] + chunks = [] + start = end = 0 + while end < len(suffix): + ch = suffix[end] + if '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?:@&=+$,_.~*\'()[]' \ + or (ch == '!' and handle != '!'): + end += 1 + else: + if start < end: + chunks.append(suffix[start:end]) + start = end = end+1 + data = ch.encode('utf-8') + for ch in data: + chunks.append('%%%02X' % ch) + if start < end: + chunks.append(suffix[start:end]) + suffix_text = ''.join(chunks) + if handle: + return '%s%s' % (handle, suffix_text) + else: + return '!<%s>' % suffix_text + + def prepare_anchor(self, anchor): + if not anchor: + raise EmitterError("anchor must not be empty") + for ch in anchor: + if not ('0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_'): + raise EmitterError("invalid character %r in the anchor: %r" + % (ch, anchor)) + return anchor + + def analyze_scalar(self, scalar): + + # Empty scalar is a special case. + if not scalar: + return ScalarAnalysis(scalar=scalar, empty=True, multiline=False, + allow_flow_plain=False, allow_block_plain=True, + allow_single_quoted=True, allow_double_quoted=True, + allow_block=False) + + # Indicators and special characters. + block_indicators = False + flow_indicators = False + line_breaks = False + special_characters = False + + # Important whitespace combinations. + leading_space = False + leading_break = False + trailing_space = False + trailing_break = False + break_space = False + space_break = False + + # Check document indicators. + if scalar.startswith('---') or scalar.startswith('...'): + block_indicators = True + flow_indicators = True + + # First character or preceded by a whitespace. + preceded_by_whitespace = True + + # Last character or followed by a whitespace. + followed_by_whitespace = (len(scalar) == 1 or + scalar[1] in '\0 \t\r\n\x85\u2028\u2029') + + # The previous character is a space. + previous_space = False + + # The previous character is a break. + previous_break = False + + index = 0 + while index < len(scalar): + ch = scalar[index] + + # Check for indicators. + if index == 0: + # Leading indicators are special characters. + if ch in '#,[]{}&*!|>\'\"%@`': + flow_indicators = True + block_indicators = True + if ch in '?:': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == '-' and followed_by_whitespace: + flow_indicators = True + block_indicators = True + else: + # Some indicators cannot appear within a scalar as well. + if ch in ',?[]{}': + flow_indicators = True + if ch == ':': + flow_indicators = True + if followed_by_whitespace: + block_indicators = True + if ch == '#' and preceded_by_whitespace: + flow_indicators = True + block_indicators = True + + # Check for line breaks, special, and unicode characters. + if ch in '\n\x85\u2028\u2029': + line_breaks = True + if not (ch == '\n' or '\x20' <= ch <= '\x7E'): + if (ch == '\x85' or '\xA0' <= ch <= '\uD7FF' + or '\uE000' <= ch <= '\uFFFD' + or '\U00010000' <= ch < '\U0010ffff') and ch != '\uFEFF': + unicode_characters = True + if not self.allow_unicode: + special_characters = True + else: + special_characters = True + + # Detect important whitespace combinations. + if ch == ' ': + if index == 0: + leading_space = True + if index == len(scalar)-1: + trailing_space = True + if previous_break: + break_space = True + previous_space = True + previous_break = False + elif ch in '\n\x85\u2028\u2029': + if index == 0: + leading_break = True + if index == len(scalar)-1: + trailing_break = True + if previous_space: + space_break = True + previous_space = False + previous_break = True + else: + previous_space = False + previous_break = False + + # Prepare for the next character. + index += 1 + preceded_by_whitespace = (ch in '\0 \t\r\n\x85\u2028\u2029') + followed_by_whitespace = (index+1 >= len(scalar) or + scalar[index+1] in '\0 \t\r\n\x85\u2028\u2029') + + # Let's decide what styles are allowed. + allow_flow_plain = True + allow_block_plain = True + allow_single_quoted = True + allow_double_quoted = True + allow_block = True + + # Leading and trailing whitespaces are bad for plain scalars. + if (leading_space or leading_break + or trailing_space or trailing_break): + allow_flow_plain = allow_block_plain = False + + # We do not permit trailing spaces for block scalars. + if trailing_space: + allow_block = False + + # Spaces at the beginning of a new line are only acceptable for block + # scalars. + if break_space: + allow_flow_plain = allow_block_plain = allow_single_quoted = False + + # Spaces followed by breaks, as well as special character are only + # allowed for double quoted scalars. + if space_break or special_characters: + allow_flow_plain = allow_block_plain = \ + allow_single_quoted = allow_block = False + + # Although the plain scalar writer supports breaks, we never emit + # multiline plain scalars. + if line_breaks: + allow_flow_plain = allow_block_plain = False + + # Flow indicators are forbidden for flow plain scalars. + if flow_indicators: + allow_flow_plain = False + + # Block indicators are forbidden for block plain scalars. + if block_indicators: + allow_block_plain = False + + return ScalarAnalysis(scalar=scalar, + empty=False, multiline=line_breaks, + allow_flow_plain=allow_flow_plain, + allow_block_plain=allow_block_plain, + allow_single_quoted=allow_single_quoted, + allow_double_quoted=allow_double_quoted, + allow_block=allow_block) + + # Writers. + + def flush_stream(self): + if hasattr(self.stream, 'flush'): + self.stream.flush() + + def write_stream_start(self): + # Write BOM if needed. + if self.encoding and self.encoding.startswith('utf-16'): + self.stream.write('\uFEFF'.encode(self.encoding)) + + def write_stream_end(self): + self.flush_stream() + + def write_indicator(self, indicator, need_whitespace, + whitespace=False, indention=False): + if self.whitespace or not need_whitespace: + data = indicator + else: + data = ' '+indicator + self.whitespace = whitespace + self.indention = self.indention and indention + self.column += len(data) + self.open_ended = False + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_indent(self): + indent = self.indent or 0 + if not self.indention or self.column > indent \ + or (self.column == indent and not self.whitespace): + self.write_line_break() + if self.column < indent: + self.whitespace = True + data = ' '*(indent-self.column) + self.column = indent + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_line_break(self, data=None): + if data is None: + data = self.best_line_break + self.whitespace = True + self.indention = True + self.line += 1 + self.column = 0 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + + def write_version_directive(self, version_text): + data = '%%YAML %s' % version_text + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + def write_tag_directive(self, handle_text, prefix_text): + data = '%%TAG %s %s' % (handle_text, prefix_text) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_line_break() + + # Scalar streams. + + def write_single_quoted(self, text, split=True): + self.write_indicator('\'', True) + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch is None or ch != ' ': + if start+1 == end and self.column > self.best_width and split \ + and start != 0 and end != len(text): + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + if text[start] == '\n': + self.write_line_break() + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029' or ch == '\'': + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch == '\'': + data = '\'\'' + self.column += 2 + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + 1 + if ch is not None: + spaces = (ch == ' ') + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + self.write_indicator('\'', False) + + ESCAPE_REPLACEMENTS = { + '\0': '0', + '\x07': 'a', + '\x08': 'b', + '\x09': 't', + '\x0A': 'n', + '\x0B': 'v', + '\x0C': 'f', + '\x0D': 'r', + '\x1B': 'e', + '\"': '\"', + '\\': '\\', + '\x85': 'N', + '\xA0': '_', + '\u2028': 'L', + '\u2029': 'P', + } + + def write_double_quoted(self, text, split=True): + self.write_indicator('"', True) + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if ch is None or ch in '"\\\x85\u2028\u2029\uFEFF' \ + or not ('\x20' <= ch <= '\x7E' + or (self.allow_unicode + and ('\xA0' <= ch <= '\uD7FF' + or '\uE000' <= ch <= '\uFFFD'))): + if start < end: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + if ch in self.ESCAPE_REPLACEMENTS: + data = '\\'+self.ESCAPE_REPLACEMENTS[ch] + elif ch <= '\xFF': + data = '\\x%02X' % ord(ch) + elif ch <= '\uFFFF': + data = '\\u%04X' % ord(ch) + else: + data = '\\U%08X' % ord(ch) + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end+1 + if 0 < end < len(text)-1 and (ch == ' ' or start >= end) \ + and self.column+(end-start) > self.best_width and split: + data = text[start:end]+'\\' + if start < end: + start = end + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.write_indent() + self.whitespace = False + self.indention = False + if text[start] == ' ': + data = '\\' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + end += 1 + self.write_indicator('"', False) + + def determine_block_hints(self, text): + hints = '' + if text: + if text[0] in ' \n\x85\u2028\u2029': + hints += str(self.best_indent) + if text[-1] not in '\n\x85\u2028\u2029': + hints += '-' + elif len(text) == 1 or text[-2] in '\n\x85\u2028\u2029': + hints += '+' + return hints + + def write_folded(self, text): + hints = self.determine_block_hints(text) + self.write_indicator('>'+hints, True) + if hints[-1:] == '+': + self.open_ended = True + self.write_line_break() + leading_space = True + spaces = False + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + if not leading_space and ch is not None and ch != ' ' \ + and text[start] == '\n': + self.write_line_break() + leading_space = (ch == ' ') + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + elif spaces: + if ch != ' ': + if start+1 == end and self.column > self.best_width: + self.write_indent() + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in '\n\x85\u2028\u2029') + spaces = (ch == ' ') + end += 1 + + def write_literal(self, text): + hints = self.determine_block_hints(text) + self.write_indicator('|'+hints, True) + if hints[-1:] == '+': + self.open_ended = True + self.write_line_break() + breaks = True + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if breaks: + if ch is None or ch not in '\n\x85\u2028\u2029': + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + if ch is not None: + self.write_indent() + start = end + else: + if ch is None or ch in '\n\x85\u2028\u2029': + data = text[start:end] + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + if ch is None: + self.write_line_break() + start = end + if ch is not None: + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 + + def write_plain(self, text, split=True): + if self.root_context: + self.open_ended = True + if not text: + return + if not self.whitespace: + data = ' ' + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + self.whitespace = False + self.indention = False + spaces = False + breaks = False + start = end = 0 + while end <= len(text): + ch = None + if end < len(text): + ch = text[end] + if spaces: + if ch != ' ': + if start+1 == end and self.column > self.best_width and split: + self.write_indent() + self.whitespace = False + self.indention = False + else: + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + elif breaks: + if ch not in '\n\x85\u2028\u2029': + if text[start] == '\n': + self.write_line_break() + for br in text[start:end]: + if br == '\n': + self.write_line_break() + else: + self.write_line_break(br) + self.write_indent() + self.whitespace = False + self.indention = False + start = end + else: + if ch is None or ch in ' \n\x85\u2028\u2029': + data = text[start:end] + self.column += len(data) + if self.encoding: + data = data.encode(self.encoding) + self.stream.write(data) + start = end + if ch is not None: + spaces = (ch == ' ') + breaks = (ch in '\n\x85\u2028\u2029') + end += 1 diff --git a/.venv/lib/python3.11/site-packages/yaml/error.py b/.venv/lib/python3.11/site-packages/yaml/error.py new file mode 100644 index 0000000000000000000000000000000000000000..b796b4dc519512c4825ff539a2e6aa20f4d370d0 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/error.py @@ -0,0 +1,75 @@ + +__all__ = ['Mark', 'YAMLError', 'MarkedYAMLError'] + +class Mark: + + def __init__(self, name, index, line, column, buffer, pointer): + self.name = name + self.index = index + self.line = line + self.column = column + self.buffer = buffer + self.pointer = pointer + + def get_snippet(self, indent=4, max_length=75): + if self.buffer is None: + return None + head = '' + start = self.pointer + while start > 0 and self.buffer[start-1] not in '\0\r\n\x85\u2028\u2029': + start -= 1 + if self.pointer-start > max_length/2-1: + head = ' ... ' + start += 5 + break + tail = '' + end = self.pointer + while end < len(self.buffer) and self.buffer[end] not in '\0\r\n\x85\u2028\u2029': + end += 1 + if end-self.pointer > max_length/2-1: + tail = ' ... ' + end -= 5 + break + snippet = self.buffer[start:end] + return ' '*indent + head + snippet + tail + '\n' \ + + ' '*(indent+self.pointer-start+len(head)) + '^' + + def __str__(self): + snippet = self.get_snippet() + where = " in \"%s\", line %d, column %d" \ + % (self.name, self.line+1, self.column+1) + if snippet is not None: + where += ":\n"+snippet + return where + +class YAMLError(Exception): + pass + +class MarkedYAMLError(YAMLError): + + def __init__(self, context=None, context_mark=None, + problem=None, problem_mark=None, note=None): + self.context = context + self.context_mark = context_mark + self.problem = problem + self.problem_mark = problem_mark + self.note = note + + def __str__(self): + lines = [] + if self.context is not None: + lines.append(self.context) + if self.context_mark is not None \ + and (self.problem is None or self.problem_mark is None + or self.context_mark.name != self.problem_mark.name + or self.context_mark.line != self.problem_mark.line + or self.context_mark.column != self.problem_mark.column): + lines.append(str(self.context_mark)) + if self.problem is not None: + lines.append(self.problem) + if self.problem_mark is not None: + lines.append(str(self.problem_mark)) + if self.note is not None: + lines.append(self.note) + return '\n'.join(lines) + diff --git a/.venv/lib/python3.11/site-packages/yaml/events.py b/.venv/lib/python3.11/site-packages/yaml/events.py new file mode 100644 index 0000000000000000000000000000000000000000..f79ad389cb6c9517e391dcd25534866bc9ccd36a --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/events.py @@ -0,0 +1,86 @@ + +# Abstract classes. + +class Event(object): + def __init__(self, start_mark=None, end_mark=None): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in ['anchor', 'tag', 'implicit', 'value'] + if hasattr(self, key)] + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +class NodeEvent(Event): + def __init__(self, anchor, start_mark=None, end_mark=None): + self.anchor = anchor + self.start_mark = start_mark + self.end_mark = end_mark + +class CollectionStartEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, start_mark=None, end_mark=None, + flow_style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class CollectionEndEvent(Event): + pass + +# Implementations. + +class StreamStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndEvent(Event): + pass + +class DocumentStartEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None, version=None, tags=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + self.version = version + self.tags = tags + +class DocumentEndEvent(Event): + def __init__(self, start_mark=None, end_mark=None, + explicit=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.explicit = explicit + +class AliasEvent(NodeEvent): + pass + +class ScalarEvent(NodeEvent): + def __init__(self, anchor, tag, implicit, value, + start_mark=None, end_mark=None, style=None): + self.anchor = anchor + self.tag = tag + self.implicit = implicit + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class SequenceStartEvent(CollectionStartEvent): + pass + +class SequenceEndEvent(CollectionEndEvent): + pass + +class MappingStartEvent(CollectionStartEvent): + pass + +class MappingEndEvent(CollectionEndEvent): + pass + diff --git a/.venv/lib/python3.11/site-packages/yaml/loader.py b/.venv/lib/python3.11/site-packages/yaml/loader.py new file mode 100644 index 0000000000000000000000000000000000000000..e90c11224c38e559cdf0cb205f0692ebd4fb8681 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/loader.py @@ -0,0 +1,63 @@ + +__all__ = ['BaseLoader', 'FullLoader', 'SafeLoader', 'Loader', 'UnsafeLoader'] + +from .reader import * +from .scanner import * +from .parser import * +from .composer import * +from .constructor import * +from .resolver import * + +class BaseLoader(Reader, Scanner, Parser, Composer, BaseConstructor, BaseResolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + BaseConstructor.__init__(self) + BaseResolver.__init__(self) + +class FullLoader(Reader, Scanner, Parser, Composer, FullConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + FullConstructor.__init__(self) + Resolver.__init__(self) + +class SafeLoader(Reader, Scanner, Parser, Composer, SafeConstructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + SafeConstructor.__init__(self) + Resolver.__init__(self) + +class Loader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) + +# UnsafeLoader is the same as Loader (which is and was always unsafe on +# untrusted input). Use of either Loader or UnsafeLoader should be rare, since +# FullLoad should be able to load almost all YAML safely. Loader is left intact +# to ensure backwards compatibility. +class UnsafeLoader(Reader, Scanner, Parser, Composer, Constructor, Resolver): + + def __init__(self, stream): + Reader.__init__(self, stream) + Scanner.__init__(self) + Parser.__init__(self) + Composer.__init__(self) + Constructor.__init__(self) + Resolver.__init__(self) diff --git a/.venv/lib/python3.11/site-packages/yaml/nodes.py b/.venv/lib/python3.11/site-packages/yaml/nodes.py new file mode 100644 index 0000000000000000000000000000000000000000..c4f070c41e1fb1bc01af27d69329e92dded38908 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/nodes.py @@ -0,0 +1,49 @@ + +class Node(object): + def __init__(self, tag, value, start_mark, end_mark): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + value = self.value + #if isinstance(value, list): + # if len(value) == 0: + # value = '' + # elif len(value) == 1: + # value = '<1 item>' + # else: + # value = '<%d items>' % len(value) + #else: + # if len(value) > 75: + # value = repr(value[:70]+u' ... ') + # else: + # value = repr(value) + value = repr(value) + return '%s(tag=%r, value=%s)' % (self.__class__.__name__, self.tag, value) + +class ScalarNode(Node): + id = 'scalar' + def __init__(self, tag, value, + start_mark=None, end_mark=None, style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style + +class CollectionNode(Node): + def __init__(self, tag, value, + start_mark=None, end_mark=None, flow_style=None): + self.tag = tag + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + self.flow_style = flow_style + +class SequenceNode(CollectionNode): + id = 'sequence' + +class MappingNode(CollectionNode): + id = 'mapping' + diff --git a/.venv/lib/python3.11/site-packages/yaml/parser.py b/.venv/lib/python3.11/site-packages/yaml/parser.py new file mode 100644 index 0000000000000000000000000000000000000000..13a5995d292045d0f865a99abf692bd35dc87814 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/parser.py @@ -0,0 +1,589 @@ + +# The following YAML grammar is LL(1) and is parsed by a recursive descent +# parser. +# +# stream ::= STREAM-START implicit_document? explicit_document* STREAM-END +# implicit_document ::= block_node DOCUMENT-END* +# explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* +# block_node_or_indentless_sequence ::= +# ALIAS +# | properties (block_content | indentless_block_sequence)? +# | block_content +# | indentless_block_sequence +# block_node ::= ALIAS +# | properties block_content? +# | block_content +# flow_node ::= ALIAS +# | properties flow_content? +# | flow_content +# properties ::= TAG ANCHOR? | ANCHOR TAG? +# block_content ::= block_collection | flow_collection | SCALAR +# flow_content ::= flow_collection | SCALAR +# block_collection ::= block_sequence | block_mapping +# flow_collection ::= flow_sequence | flow_mapping +# block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END +# indentless_sequence ::= (BLOCK-ENTRY block_node?)+ +# block_mapping ::= BLOCK-MAPPING_START +# ((KEY block_node_or_indentless_sequence?)? +# (VALUE block_node_or_indentless_sequence?)?)* +# BLOCK-END +# flow_sequence ::= FLOW-SEQUENCE-START +# (flow_sequence_entry FLOW-ENTRY)* +# flow_sequence_entry? +# FLOW-SEQUENCE-END +# flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# flow_mapping ::= FLOW-MAPPING-START +# (flow_mapping_entry FLOW-ENTRY)* +# flow_mapping_entry? +# FLOW-MAPPING-END +# flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? +# +# FIRST sets: +# +# stream: { STREAM-START } +# explicit_document: { DIRECTIVE DOCUMENT-START } +# implicit_document: FIRST(block_node) +# block_node: { ALIAS TAG ANCHOR SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_node: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_content: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# flow_content: { FLOW-SEQUENCE-START FLOW-MAPPING-START SCALAR } +# block_collection: { BLOCK-SEQUENCE-START BLOCK-MAPPING-START } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# block_sequence: { BLOCK-SEQUENCE-START } +# block_mapping: { BLOCK-MAPPING-START } +# block_node_or_indentless_sequence: { ALIAS ANCHOR TAG SCALAR BLOCK-SEQUENCE-START BLOCK-MAPPING-START FLOW-SEQUENCE-START FLOW-MAPPING-START BLOCK-ENTRY } +# indentless_sequence: { ENTRY } +# flow_collection: { FLOW-SEQUENCE-START FLOW-MAPPING-START } +# flow_sequence: { FLOW-SEQUENCE-START } +# flow_mapping: { FLOW-MAPPING-START } +# flow_sequence_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } +# flow_mapping_entry: { ALIAS ANCHOR TAG SCALAR FLOW-SEQUENCE-START FLOW-MAPPING-START KEY } + +__all__ = ['Parser', 'ParserError'] + +from .error import MarkedYAMLError +from .tokens import * +from .events import * +from .scanner import * + +class ParserError(MarkedYAMLError): + pass + +class Parser: + # Since writing a recursive-descendant parser is a straightforward task, we + # do not give many comments here. + + DEFAULT_TAGS = { + '!': '!', + '!!': 'tag:yaml.org,2002:', + } + + def __init__(self): + self.current_event = None + self.yaml_version = None + self.tag_handles = {} + self.states = [] + self.marks = [] + self.state = self.parse_stream_start + + def dispose(self): + # Reset the state attributes (to clear self-references) + self.states = [] + self.state = None + + def check_event(self, *choices): + # Check the type of the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + if self.current_event is not None: + if not choices: + return True + for choice in choices: + if isinstance(self.current_event, choice): + return True + return False + + def peek_event(self): + # Get the next event. + if self.current_event is None: + if self.state: + self.current_event = self.state() + return self.current_event + + def get_event(self): + # Get the next event and proceed further. + if self.current_event is None: + if self.state: + self.current_event = self.state() + value = self.current_event + self.current_event = None + return value + + # stream ::= STREAM-START implicit_document? explicit_document* STREAM-END + # implicit_document ::= block_node DOCUMENT-END* + # explicit_document ::= DIRECTIVE* DOCUMENT-START block_node? DOCUMENT-END* + + def parse_stream_start(self): + + # Parse the stream start. + token = self.get_token() + event = StreamStartEvent(token.start_mark, token.end_mark, + encoding=token.encoding) + + # Prepare the next state. + self.state = self.parse_implicit_document_start + + return event + + def parse_implicit_document_start(self): + + # Parse an implicit document. + if not self.check_token(DirectiveToken, DocumentStartToken, + StreamEndToken): + self.tag_handles = self.DEFAULT_TAGS + token = self.peek_token() + start_mark = end_mark = token.start_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=False) + + # Prepare the next state. + self.states.append(self.parse_document_end) + self.state = self.parse_block_node + + return event + + else: + return self.parse_document_start() + + def parse_document_start(self): + + # Parse any extra document end indicators. + while self.check_token(DocumentEndToken): + self.get_token() + + # Parse an explicit document. + if not self.check_token(StreamEndToken): + token = self.peek_token() + start_mark = token.start_mark + version, tags = self.process_directives() + if not self.check_token(DocumentStartToken): + raise ParserError(None, None, + "expected '', but found %r" + % self.peek_token().id, + self.peek_token().start_mark) + token = self.get_token() + end_mark = token.end_mark + event = DocumentStartEvent(start_mark, end_mark, + explicit=True, version=version, tags=tags) + self.states.append(self.parse_document_end) + self.state = self.parse_document_content + else: + # Parse the end of the stream. + token = self.get_token() + event = StreamEndEvent(token.start_mark, token.end_mark) + assert not self.states + assert not self.marks + self.state = None + return event + + def parse_document_end(self): + + # Parse the document end. + token = self.peek_token() + start_mark = end_mark = token.start_mark + explicit = False + if self.check_token(DocumentEndToken): + token = self.get_token() + end_mark = token.end_mark + explicit = True + event = DocumentEndEvent(start_mark, end_mark, + explicit=explicit) + + # Prepare the next state. + self.state = self.parse_document_start + + return event + + def parse_document_content(self): + if self.check_token(DirectiveToken, + DocumentStartToken, DocumentEndToken, StreamEndToken): + event = self.process_empty_scalar(self.peek_token().start_mark) + self.state = self.states.pop() + return event + else: + return self.parse_block_node() + + def process_directives(self): + self.yaml_version = None + self.tag_handles = {} + while self.check_token(DirectiveToken): + token = self.get_token() + if token.name == 'YAML': + if self.yaml_version is not None: + raise ParserError(None, None, + "found duplicate YAML directive", token.start_mark) + major, minor = token.value + if major != 1: + raise ParserError(None, None, + "found incompatible YAML document (version 1.* is required)", + token.start_mark) + self.yaml_version = token.value + elif token.name == 'TAG': + handle, prefix = token.value + if handle in self.tag_handles: + raise ParserError(None, None, + "duplicate tag handle %r" % handle, + token.start_mark) + self.tag_handles[handle] = prefix + if self.tag_handles: + value = self.yaml_version, self.tag_handles.copy() + else: + value = self.yaml_version, None + for key in self.DEFAULT_TAGS: + if key not in self.tag_handles: + self.tag_handles[key] = self.DEFAULT_TAGS[key] + return value + + # block_node_or_indentless_sequence ::= ALIAS + # | properties (block_content | indentless_block_sequence)? + # | block_content + # | indentless_block_sequence + # block_node ::= ALIAS + # | properties block_content? + # | block_content + # flow_node ::= ALIAS + # | properties flow_content? + # | flow_content + # properties ::= TAG ANCHOR? | ANCHOR TAG? + # block_content ::= block_collection | flow_collection | SCALAR + # flow_content ::= flow_collection | SCALAR + # block_collection ::= block_sequence | block_mapping + # flow_collection ::= flow_sequence | flow_mapping + + def parse_block_node(self): + return self.parse_node(block=True) + + def parse_flow_node(self): + return self.parse_node() + + def parse_block_node_or_indentless_sequence(self): + return self.parse_node(block=True, indentless_sequence=True) + + def parse_node(self, block=False, indentless_sequence=False): + if self.check_token(AliasToken): + token = self.get_token() + event = AliasEvent(token.value, token.start_mark, token.end_mark) + self.state = self.states.pop() + else: + anchor = None + tag = None + start_mark = end_mark = tag_mark = None + if self.check_token(AnchorToken): + token = self.get_token() + start_mark = token.start_mark + end_mark = token.end_mark + anchor = token.value + if self.check_token(TagToken): + token = self.get_token() + tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + elif self.check_token(TagToken): + token = self.get_token() + start_mark = tag_mark = token.start_mark + end_mark = token.end_mark + tag = token.value + if self.check_token(AnchorToken): + token = self.get_token() + end_mark = token.end_mark + anchor = token.value + if tag is not None: + handle, suffix = tag + if handle is not None: + if handle not in self.tag_handles: + raise ParserError("while parsing a node", start_mark, + "found undefined tag handle %r" % handle, + tag_mark) + tag = self.tag_handles[handle]+suffix + else: + tag = suffix + #if tag == '!': + # raise ParserError("while parsing a node", start_mark, + # "found non-specific tag '!'", tag_mark, + # "Please check 'http://pyyaml.org/wiki/YAMLNonSpecificTag' and share your opinion.") + if start_mark is None: + start_mark = end_mark = self.peek_token().start_mark + event = None + implicit = (tag is None or tag == '!') + if indentless_sequence and self.check_token(BlockEntryToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark) + self.state = self.parse_indentless_sequence_entry + else: + if self.check_token(ScalarToken): + token = self.get_token() + end_mark = token.end_mark + if (token.plain and tag is None) or tag == '!': + implicit = (True, False) + elif tag is None: + implicit = (False, True) + else: + implicit = (False, False) + event = ScalarEvent(anchor, tag, implicit, token.value, + start_mark, end_mark, style=token.style) + self.state = self.states.pop() + elif self.check_token(FlowSequenceStartToken): + end_mark = self.peek_token().end_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_sequence_first_entry + elif self.check_token(FlowMappingStartToken): + end_mark = self.peek_token().end_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=True) + self.state = self.parse_flow_mapping_first_key + elif block and self.check_token(BlockSequenceStartToken): + end_mark = self.peek_token().start_mark + event = SequenceStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_sequence_first_entry + elif block and self.check_token(BlockMappingStartToken): + end_mark = self.peek_token().start_mark + event = MappingStartEvent(anchor, tag, implicit, + start_mark, end_mark, flow_style=False) + self.state = self.parse_block_mapping_first_key + elif anchor is not None or tag is not None: + # Empty scalars are allowed even if a tag or an anchor is + # specified. + event = ScalarEvent(anchor, tag, (implicit, False), '', + start_mark, end_mark) + self.state = self.states.pop() + else: + if block: + node = 'block' + else: + node = 'flow' + token = self.peek_token() + raise ParserError("while parsing a %s node" % node, start_mark, + "expected the node content, but found %r" % token.id, + token.start_mark) + return event + + # block_sequence ::= BLOCK-SEQUENCE-START (BLOCK-ENTRY block_node?)* BLOCK-END + + def parse_block_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_sequence_entry() + + def parse_block_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, BlockEndToken): + self.states.append(self.parse_block_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_block_sequence_entry + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block collection", self.marks[-1], + "expected , but found %r" % token.id, token.start_mark) + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + # indentless_sequence ::= (BLOCK-ENTRY block_node?)+ + + def parse_indentless_sequence_entry(self): + if self.check_token(BlockEntryToken): + token = self.get_token() + if not self.check_token(BlockEntryToken, + KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_indentless_sequence_entry) + return self.parse_block_node() + else: + self.state = self.parse_indentless_sequence_entry + return self.process_empty_scalar(token.end_mark) + token = self.peek_token() + event = SequenceEndEvent(token.start_mark, token.start_mark) + self.state = self.states.pop() + return event + + # block_mapping ::= BLOCK-MAPPING_START + # ((KEY block_node_or_indentless_sequence?)? + # (VALUE block_node_or_indentless_sequence?)?)* + # BLOCK-END + + def parse_block_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_block_mapping_key() + + def parse_block_mapping_key(self): + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_value) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_value + return self.process_empty_scalar(token.end_mark) + if not self.check_token(BlockEndToken): + token = self.peek_token() + raise ParserError("while parsing a block mapping", self.marks[-1], + "expected , but found %r" % token.id, token.start_mark) + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_block_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(KeyToken, ValueToken, BlockEndToken): + self.states.append(self.parse_block_mapping_key) + return self.parse_block_node_or_indentless_sequence() + else: + self.state = self.parse_block_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_block_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + # flow_sequence ::= FLOW-SEQUENCE-START + # (flow_sequence_entry FLOW-ENTRY)* + # flow_sequence_entry? + # FLOW-SEQUENCE-END + # flow_sequence_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + # + # Note that while production rules for both flow_sequence_entry and + # flow_mapping_entry are equal, their interpretations are different. + # For `flow_sequence_entry`, the part `KEY flow_node? (VALUE flow_node?)?` + # generate an inline mapping (set syntax). + + def parse_flow_sequence_first_entry(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_sequence_entry(first=True) + + def parse_flow_sequence_entry(self, first=False): + if not self.check_token(FlowSequenceEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow sequence", self.marks[-1], + "expected ',' or ']', but got %r" % token.id, token.start_mark) + + if self.check_token(KeyToken): + token = self.peek_token() + event = MappingStartEvent(None, None, True, + token.start_mark, token.end_mark, + flow_style=True) + self.state = self.parse_flow_sequence_entry_mapping_key + return event + elif not self.check_token(FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry) + return self.parse_flow_node() + token = self.get_token() + event = SequenceEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_sequence_entry_mapping_key(self): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_value + return self.process_empty_scalar(token.end_mark) + + def parse_flow_sequence_entry_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowSequenceEndToken): + self.states.append(self.parse_flow_sequence_entry_mapping_end) + return self.parse_flow_node() + else: + self.state = self.parse_flow_sequence_entry_mapping_end + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_sequence_entry_mapping_end + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_sequence_entry_mapping_end(self): + self.state = self.parse_flow_sequence_entry + token = self.peek_token() + return MappingEndEvent(token.start_mark, token.start_mark) + + # flow_mapping ::= FLOW-MAPPING-START + # (flow_mapping_entry FLOW-ENTRY)* + # flow_mapping_entry? + # FLOW-MAPPING-END + # flow_mapping_entry ::= flow_node | KEY flow_node? (VALUE flow_node?)? + + def parse_flow_mapping_first_key(self): + token = self.get_token() + self.marks.append(token.start_mark) + return self.parse_flow_mapping_key(first=True) + + def parse_flow_mapping_key(self, first=False): + if not self.check_token(FlowMappingEndToken): + if not first: + if self.check_token(FlowEntryToken): + self.get_token() + else: + token = self.peek_token() + raise ParserError("while parsing a flow mapping", self.marks[-1], + "expected ',' or '}', but got %r" % token.id, token.start_mark) + if self.check_token(KeyToken): + token = self.get_token() + if not self.check_token(ValueToken, + FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_value) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_value + return self.process_empty_scalar(token.end_mark) + elif not self.check_token(FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_empty_value) + return self.parse_flow_node() + token = self.get_token() + event = MappingEndEvent(token.start_mark, token.end_mark) + self.state = self.states.pop() + self.marks.pop() + return event + + def parse_flow_mapping_value(self): + if self.check_token(ValueToken): + token = self.get_token() + if not self.check_token(FlowEntryToken, FlowMappingEndToken): + self.states.append(self.parse_flow_mapping_key) + return self.parse_flow_node() + else: + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(token.end_mark) + else: + self.state = self.parse_flow_mapping_key + token = self.peek_token() + return self.process_empty_scalar(token.start_mark) + + def parse_flow_mapping_empty_value(self): + self.state = self.parse_flow_mapping_key + return self.process_empty_scalar(self.peek_token().start_mark) + + def process_empty_scalar(self, mark): + return ScalarEvent(None, None, (True, False), '', mark, mark) + diff --git a/.venv/lib/python3.11/site-packages/yaml/reader.py b/.venv/lib/python3.11/site-packages/yaml/reader.py new file mode 100644 index 0000000000000000000000000000000000000000..774b0219b5932a0ee1c27e637371de5ba8d9cb16 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/reader.py @@ -0,0 +1,185 @@ +# This module contains abstractions for the input stream. You don't have to +# looks further, there are no pretty code. +# +# We define two classes here. +# +# Mark(source, line, column) +# It's just a record and its only use is producing nice error messages. +# Parser does not use it for any other purposes. +# +# Reader(source, data) +# Reader determines the encoding of `data` and converts it to unicode. +# Reader provides the following methods and attributes: +# reader.peek(length=1) - return the next `length` characters +# reader.forward(length=1) - move the current position to `length` characters. +# reader.index - the number of the current character. +# reader.line, stream.column - the line and the column of the current character. + +__all__ = ['Reader', 'ReaderError'] + +from .error import YAMLError, Mark + +import codecs, re + +class ReaderError(YAMLError): + + def __init__(self, name, position, character, encoding, reason): + self.name = name + self.character = character + self.position = position + self.encoding = encoding + self.reason = reason + + def __str__(self): + if isinstance(self.character, bytes): + return "'%s' codec can't decode byte #x%02x: %s\n" \ + " in \"%s\", position %d" \ + % (self.encoding, ord(self.character), self.reason, + self.name, self.position) + else: + return "unacceptable character #x%04x: %s\n" \ + " in \"%s\", position %d" \ + % (self.character, self.reason, + self.name, self.position) + +class Reader(object): + # Reader: + # - determines the data encoding and converts it to a unicode string, + # - checks if characters are in allowed range, + # - adds '\0' to the end. + + # Reader accepts + # - a `bytes` object, + # - a `str` object, + # - a file-like object with its `read` method returning `str`, + # - a file-like object with its `read` method returning `unicode`. + + # Yeah, it's ugly and slow. + + def __init__(self, stream): + self.name = None + self.stream = None + self.stream_pointer = 0 + self.eof = True + self.buffer = '' + self.pointer = 0 + self.raw_buffer = None + self.raw_decode = None + self.encoding = None + self.index = 0 + self.line = 0 + self.column = 0 + if isinstance(stream, str): + self.name = "" + self.check_printable(stream) + self.buffer = stream+'\0' + elif isinstance(stream, bytes): + self.name = "" + self.raw_buffer = stream + self.determine_encoding() + else: + self.stream = stream + self.name = getattr(stream, 'name', "") + self.eof = False + self.raw_buffer = None + self.determine_encoding() + + def peek(self, index=0): + try: + return self.buffer[self.pointer+index] + except IndexError: + self.update(index+1) + return self.buffer[self.pointer+index] + + def prefix(self, length=1): + if self.pointer+length >= len(self.buffer): + self.update(length) + return self.buffer[self.pointer:self.pointer+length] + + def forward(self, length=1): + if self.pointer+length+1 >= len(self.buffer): + self.update(length+1) + while length: + ch = self.buffer[self.pointer] + self.pointer += 1 + self.index += 1 + if ch in '\n\x85\u2028\u2029' \ + or (ch == '\r' and self.buffer[self.pointer] != '\n'): + self.line += 1 + self.column = 0 + elif ch != '\uFEFF': + self.column += 1 + length -= 1 + + def get_mark(self): + if self.stream is None: + return Mark(self.name, self.index, self.line, self.column, + self.buffer, self.pointer) + else: + return Mark(self.name, self.index, self.line, self.column, + None, None) + + def determine_encoding(self): + while not self.eof and (self.raw_buffer is None or len(self.raw_buffer) < 2): + self.update_raw() + if isinstance(self.raw_buffer, bytes): + if self.raw_buffer.startswith(codecs.BOM_UTF16_LE): + self.raw_decode = codecs.utf_16_le_decode + self.encoding = 'utf-16-le' + elif self.raw_buffer.startswith(codecs.BOM_UTF16_BE): + self.raw_decode = codecs.utf_16_be_decode + self.encoding = 'utf-16-be' + else: + self.raw_decode = codecs.utf_8_decode + self.encoding = 'utf-8' + self.update(1) + + NON_PRINTABLE = re.compile('[^\x09\x0A\x0D\x20-\x7E\x85\xA0-\uD7FF\uE000-\uFFFD\U00010000-\U0010ffff]') + def check_printable(self, data): + match = self.NON_PRINTABLE.search(data) + if match: + character = match.group() + position = self.index+(len(self.buffer)-self.pointer)+match.start() + raise ReaderError(self.name, position, ord(character), + 'unicode', "special characters are not allowed") + + def update(self, length): + if self.raw_buffer is None: + return + self.buffer = self.buffer[self.pointer:] + self.pointer = 0 + while len(self.buffer) < length: + if not self.eof: + self.update_raw() + if self.raw_decode is not None: + try: + data, converted = self.raw_decode(self.raw_buffer, + 'strict', self.eof) + except UnicodeDecodeError as exc: + character = self.raw_buffer[exc.start] + if self.stream is not None: + position = self.stream_pointer-len(self.raw_buffer)+exc.start + else: + position = exc.start + raise ReaderError(self.name, position, character, + exc.encoding, exc.reason) + else: + data = self.raw_buffer + converted = len(data) + self.check_printable(data) + self.buffer += data + self.raw_buffer = self.raw_buffer[converted:] + if self.eof: + self.buffer += '\0' + self.raw_buffer = None + break + + def update_raw(self, size=4096): + data = self.stream.read(size) + if self.raw_buffer is None: + self.raw_buffer = data + else: + self.raw_buffer += data + self.stream_pointer += len(data) + if not data: + self.eof = True diff --git a/.venv/lib/python3.11/site-packages/yaml/representer.py b/.venv/lib/python3.11/site-packages/yaml/representer.py new file mode 100644 index 0000000000000000000000000000000000000000..808ca06dfbd60c9a23eb079151b74a82ef688749 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/representer.py @@ -0,0 +1,389 @@ + +__all__ = ['BaseRepresenter', 'SafeRepresenter', 'Representer', + 'RepresenterError'] + +from .error import * +from .nodes import * + +import datetime, copyreg, types, base64, collections + +class RepresenterError(YAMLError): + pass + +class BaseRepresenter: + + yaml_representers = {} + yaml_multi_representers = {} + + def __init__(self, default_style=None, default_flow_style=False, sort_keys=True): + self.default_style = default_style + self.sort_keys = sort_keys + self.default_flow_style = default_flow_style + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent(self, data): + node = self.represent_data(data) + self.serialize(node) + self.represented_objects = {} + self.object_keeper = [] + self.alias_key = None + + def represent_data(self, data): + if self.ignore_aliases(data): + self.alias_key = None + else: + self.alias_key = id(data) + if self.alias_key is not None: + if self.alias_key in self.represented_objects: + node = self.represented_objects[self.alias_key] + #if node is None: + # raise RepresenterError("recursive objects are not allowed: %r" % data) + return node + #self.represented_objects[alias_key] = None + self.object_keeper.append(data) + data_types = type(data).__mro__ + if data_types[0] in self.yaml_representers: + node = self.yaml_representers[data_types[0]](self, data) + else: + for data_type in data_types: + if data_type in self.yaml_multi_representers: + node = self.yaml_multi_representers[data_type](self, data) + break + else: + if None in self.yaml_multi_representers: + node = self.yaml_multi_representers[None](self, data) + elif None in self.yaml_representers: + node = self.yaml_representers[None](self, data) + else: + node = ScalarNode(None, str(data)) + #if alias_key is not None: + # self.represented_objects[alias_key] = node + return node + + @classmethod + def add_representer(cls, data_type, representer): + if not 'yaml_representers' in cls.__dict__: + cls.yaml_representers = cls.yaml_representers.copy() + cls.yaml_representers[data_type] = representer + + @classmethod + def add_multi_representer(cls, data_type, representer): + if not 'yaml_multi_representers' in cls.__dict__: + cls.yaml_multi_representers = cls.yaml_multi_representers.copy() + cls.yaml_multi_representers[data_type] = representer + + def represent_scalar(self, tag, value, style=None): + if style is None: + style = self.default_style + node = ScalarNode(tag, value, style=style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + return node + + def represent_sequence(self, tag, sequence, flow_style=None): + value = [] + node = SequenceNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + for item in sequence: + node_item = self.represent_data(item) + if not (isinstance(node_item, ScalarNode) and not node_item.style): + best_style = False + value.append(node_item) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def represent_mapping(self, tag, mapping, flow_style=None): + value = [] + node = MappingNode(tag, value, flow_style=flow_style) + if self.alias_key is not None: + self.represented_objects[self.alias_key] = node + best_style = True + if hasattr(mapping, 'items'): + mapping = list(mapping.items()) + if self.sort_keys: + try: + mapping = sorted(mapping) + except TypeError: + pass + for item_key, item_value in mapping: + node_key = self.represent_data(item_key) + node_value = self.represent_data(item_value) + if not (isinstance(node_key, ScalarNode) and not node_key.style): + best_style = False + if not (isinstance(node_value, ScalarNode) and not node_value.style): + best_style = False + value.append((node_key, node_value)) + if flow_style is None: + if self.default_flow_style is not None: + node.flow_style = self.default_flow_style + else: + node.flow_style = best_style + return node + + def ignore_aliases(self, data): + return False + +class SafeRepresenter(BaseRepresenter): + + def ignore_aliases(self, data): + if data is None: + return True + if isinstance(data, tuple) and data == (): + return True + if isinstance(data, (str, bytes, bool, int, float)): + return True + + def represent_none(self, data): + return self.represent_scalar('tag:yaml.org,2002:null', 'null') + + def represent_str(self, data): + return self.represent_scalar('tag:yaml.org,2002:str', data) + + def represent_binary(self, data): + if hasattr(base64, 'encodebytes'): + data = base64.encodebytes(data).decode('ascii') + else: + data = base64.encodestring(data).decode('ascii') + return self.represent_scalar('tag:yaml.org,2002:binary', data, style='|') + + def represent_bool(self, data): + if data: + value = 'true' + else: + value = 'false' + return self.represent_scalar('tag:yaml.org,2002:bool', value) + + def represent_int(self, data): + return self.represent_scalar('tag:yaml.org,2002:int', str(data)) + + inf_value = 1e300 + while repr(inf_value) != repr(inf_value*inf_value): + inf_value *= inf_value + + def represent_float(self, data): + if data != data or (data == 0.0 and data == 1.0): + value = '.nan' + elif data == self.inf_value: + value = '.inf' + elif data == -self.inf_value: + value = '-.inf' + else: + value = repr(data).lower() + # Note that in some cases `repr(data)` represents a float number + # without the decimal parts. For instance: + # >>> repr(1e17) + # '1e17' + # Unfortunately, this is not a valid float representation according + # to the definition of the `!!float` tag. We fix this by adding + # '.0' before the 'e' symbol. + if '.' not in value and 'e' in value: + value = value.replace('e', '.0e', 1) + return self.represent_scalar('tag:yaml.org,2002:float', value) + + def represent_list(self, data): + #pairs = (len(data) > 0 and isinstance(data, list)) + #if pairs: + # for item in data: + # if not isinstance(item, tuple) or len(item) != 2: + # pairs = False + # break + #if not pairs: + return self.represent_sequence('tag:yaml.org,2002:seq', data) + #value = [] + #for item_key, item_value in data: + # value.append(self.represent_mapping(u'tag:yaml.org,2002:map', + # [(item_key, item_value)])) + #return SequenceNode(u'tag:yaml.org,2002:pairs', value) + + def represent_dict(self, data): + return self.represent_mapping('tag:yaml.org,2002:map', data) + + def represent_set(self, data): + value = {} + for key in data: + value[key] = None + return self.represent_mapping('tag:yaml.org,2002:set', value) + + def represent_date(self, data): + value = data.isoformat() + return self.represent_scalar('tag:yaml.org,2002:timestamp', value) + + def represent_datetime(self, data): + value = data.isoformat(' ') + return self.represent_scalar('tag:yaml.org,2002:timestamp', value) + + def represent_yaml_object(self, tag, data, cls, flow_style=None): + if hasattr(data, '__getstate__'): + state = data.__getstate__() + else: + state = data.__dict__.copy() + return self.represent_mapping(tag, state, flow_style=flow_style) + + def represent_undefined(self, data): + raise RepresenterError("cannot represent an object", data) + +SafeRepresenter.add_representer(type(None), + SafeRepresenter.represent_none) + +SafeRepresenter.add_representer(str, + SafeRepresenter.represent_str) + +SafeRepresenter.add_representer(bytes, + SafeRepresenter.represent_binary) + +SafeRepresenter.add_representer(bool, + SafeRepresenter.represent_bool) + +SafeRepresenter.add_representer(int, + SafeRepresenter.represent_int) + +SafeRepresenter.add_representer(float, + SafeRepresenter.represent_float) + +SafeRepresenter.add_representer(list, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(tuple, + SafeRepresenter.represent_list) + +SafeRepresenter.add_representer(dict, + SafeRepresenter.represent_dict) + +SafeRepresenter.add_representer(set, + SafeRepresenter.represent_set) + +SafeRepresenter.add_representer(datetime.date, + SafeRepresenter.represent_date) + +SafeRepresenter.add_representer(datetime.datetime, + SafeRepresenter.represent_datetime) + +SafeRepresenter.add_representer(None, + SafeRepresenter.represent_undefined) + +class Representer(SafeRepresenter): + + def represent_complex(self, data): + if data.imag == 0.0: + data = '%r' % data.real + elif data.real == 0.0: + data = '%rj' % data.imag + elif data.imag > 0: + data = '%r+%rj' % (data.real, data.imag) + else: + data = '%r%rj' % (data.real, data.imag) + return self.represent_scalar('tag:yaml.org,2002:python/complex', data) + + def represent_tuple(self, data): + return self.represent_sequence('tag:yaml.org,2002:python/tuple', data) + + def represent_name(self, data): + name = '%s.%s' % (data.__module__, data.__name__) + return self.represent_scalar('tag:yaml.org,2002:python/name:'+name, '') + + def represent_module(self, data): + return self.represent_scalar( + 'tag:yaml.org,2002:python/module:'+data.__name__, '') + + def represent_object(self, data): + # We use __reduce__ API to save the data. data.__reduce__ returns + # a tuple of length 2-5: + # (function, args, state, listitems, dictitems) + + # For reconstructing, we calls function(*args), then set its state, + # listitems, and dictitems if they are not None. + + # A special case is when function.__name__ == '__newobj__'. In this + # case we create the object with args[0].__new__(*args). + + # Another special case is when __reduce__ returns a string - we don't + # support it. + + # We produce a !!python/object, !!python/object/new or + # !!python/object/apply node. + + cls = type(data) + if cls in copyreg.dispatch_table: + reduce = copyreg.dispatch_table[cls](data) + elif hasattr(data, '__reduce_ex__'): + reduce = data.__reduce_ex__(2) + elif hasattr(data, '__reduce__'): + reduce = data.__reduce__() + else: + raise RepresenterError("cannot represent an object", data) + reduce = (list(reduce)+[None]*5)[:5] + function, args, state, listitems, dictitems = reduce + args = list(args) + if state is None: + state = {} + if listitems is not None: + listitems = list(listitems) + if dictitems is not None: + dictitems = dict(dictitems) + if function.__name__ == '__newobj__': + function = args[0] + args = args[1:] + tag = 'tag:yaml.org,2002:python/object/new:' + newobj = True + else: + tag = 'tag:yaml.org,2002:python/object/apply:' + newobj = False + function_name = '%s.%s' % (function.__module__, function.__name__) + if not args and not listitems and not dictitems \ + and isinstance(state, dict) and newobj: + return self.represent_mapping( + 'tag:yaml.org,2002:python/object:'+function_name, state) + if not listitems and not dictitems \ + and isinstance(state, dict) and not state: + return self.represent_sequence(tag+function_name, args) + value = {} + if args: + value['args'] = args + if state or not isinstance(state, dict): + value['state'] = state + if listitems: + value['listitems'] = listitems + if dictitems: + value['dictitems'] = dictitems + return self.represent_mapping(tag+function_name, value) + + def represent_ordered_dict(self, data): + # Provide uniform representation across different Python versions. + data_type = type(data) + tag = 'tag:yaml.org,2002:python/object/apply:%s.%s' \ + % (data_type.__module__, data_type.__name__) + items = [[key, value] for key, value in data.items()] + return self.represent_sequence(tag, [items]) + +Representer.add_representer(complex, + Representer.represent_complex) + +Representer.add_representer(tuple, + Representer.represent_tuple) + +Representer.add_multi_representer(type, + Representer.represent_name) + +Representer.add_representer(collections.OrderedDict, + Representer.represent_ordered_dict) + +Representer.add_representer(types.FunctionType, + Representer.represent_name) + +Representer.add_representer(types.BuiltinFunctionType, + Representer.represent_name) + +Representer.add_representer(types.ModuleType, + Representer.represent_module) + +Representer.add_multi_representer(object, + Representer.represent_object) + diff --git a/.venv/lib/python3.11/site-packages/yaml/resolver.py b/.venv/lib/python3.11/site-packages/yaml/resolver.py new file mode 100644 index 0000000000000000000000000000000000000000..3522bdaaf6358110b608f4e6503b9d314c82d887 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/resolver.py @@ -0,0 +1,227 @@ + +__all__ = ['BaseResolver', 'Resolver'] + +from .error import * +from .nodes import * + +import re + +class ResolverError(YAMLError): + pass + +class BaseResolver: + + DEFAULT_SCALAR_TAG = 'tag:yaml.org,2002:str' + DEFAULT_SEQUENCE_TAG = 'tag:yaml.org,2002:seq' + DEFAULT_MAPPING_TAG = 'tag:yaml.org,2002:map' + + yaml_implicit_resolvers = {} + yaml_path_resolvers = {} + + def __init__(self): + self.resolver_exact_paths = [] + self.resolver_prefix_paths = [] + + @classmethod + def add_implicit_resolver(cls, tag, regexp, first): + if not 'yaml_implicit_resolvers' in cls.__dict__: + implicit_resolvers = {} + for key in cls.yaml_implicit_resolvers: + implicit_resolvers[key] = cls.yaml_implicit_resolvers[key][:] + cls.yaml_implicit_resolvers = implicit_resolvers + if first is None: + first = [None] + for ch in first: + cls.yaml_implicit_resolvers.setdefault(ch, []).append((tag, regexp)) + + @classmethod + def add_path_resolver(cls, tag, path, kind=None): + # Note: `add_path_resolver` is experimental. The API could be changed. + # `new_path` is a pattern that is matched against the path from the + # root to the node that is being considered. `node_path` elements are + # tuples `(node_check, index_check)`. `node_check` is a node class: + # `ScalarNode`, `SequenceNode`, `MappingNode` or `None`. `None` + # matches any kind of a node. `index_check` could be `None`, a boolean + # value, a string value, or a number. `None` and `False` match against + # any _value_ of sequence and mapping nodes. `True` matches against + # any _key_ of a mapping node. A string `index_check` matches against + # a mapping value that corresponds to a scalar key which content is + # equal to the `index_check` value. An integer `index_check` matches + # against a sequence value with the index equal to `index_check`. + if not 'yaml_path_resolvers' in cls.__dict__: + cls.yaml_path_resolvers = cls.yaml_path_resolvers.copy() + new_path = [] + for element in path: + if isinstance(element, (list, tuple)): + if len(element) == 2: + node_check, index_check = element + elif len(element) == 1: + node_check = element[0] + index_check = True + else: + raise ResolverError("Invalid path element: %s" % element) + else: + node_check = None + index_check = element + if node_check is str: + node_check = ScalarNode + elif node_check is list: + node_check = SequenceNode + elif node_check is dict: + node_check = MappingNode + elif node_check not in [ScalarNode, SequenceNode, MappingNode] \ + and not isinstance(node_check, str) \ + and node_check is not None: + raise ResolverError("Invalid node checker: %s" % node_check) + if not isinstance(index_check, (str, int)) \ + and index_check is not None: + raise ResolverError("Invalid index checker: %s" % index_check) + new_path.append((node_check, index_check)) + if kind is str: + kind = ScalarNode + elif kind is list: + kind = SequenceNode + elif kind is dict: + kind = MappingNode + elif kind not in [ScalarNode, SequenceNode, MappingNode] \ + and kind is not None: + raise ResolverError("Invalid node kind: %s" % kind) + cls.yaml_path_resolvers[tuple(new_path), kind] = tag + + def descend_resolver(self, current_node, current_index): + if not self.yaml_path_resolvers: + return + exact_paths = {} + prefix_paths = [] + if current_node: + depth = len(self.resolver_prefix_paths) + for path, kind in self.resolver_prefix_paths[-1]: + if self.check_resolver_prefix(depth, path, kind, + current_node, current_index): + if len(path) > depth: + prefix_paths.append((path, kind)) + else: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + for path, kind in self.yaml_path_resolvers: + if not path: + exact_paths[kind] = self.yaml_path_resolvers[path, kind] + else: + prefix_paths.append((path, kind)) + self.resolver_exact_paths.append(exact_paths) + self.resolver_prefix_paths.append(prefix_paths) + + def ascend_resolver(self): + if not self.yaml_path_resolvers: + return + self.resolver_exact_paths.pop() + self.resolver_prefix_paths.pop() + + def check_resolver_prefix(self, depth, path, kind, + current_node, current_index): + node_check, index_check = path[depth-1] + if isinstance(node_check, str): + if current_node.tag != node_check: + return + elif node_check is not None: + if not isinstance(current_node, node_check): + return + if index_check is True and current_index is not None: + return + if (index_check is False or index_check is None) \ + and current_index is None: + return + if isinstance(index_check, str): + if not (isinstance(current_index, ScalarNode) + and index_check == current_index.value): + return + elif isinstance(index_check, int) and not isinstance(index_check, bool): + if index_check != current_index: + return + return True + + def resolve(self, kind, value, implicit): + if kind is ScalarNode and implicit[0]: + if value == '': + resolvers = self.yaml_implicit_resolvers.get('', []) + else: + resolvers = self.yaml_implicit_resolvers.get(value[0], []) + wildcard_resolvers = self.yaml_implicit_resolvers.get(None, []) + for tag, regexp in resolvers + wildcard_resolvers: + if regexp.match(value): + return tag + implicit = implicit[1] + if self.yaml_path_resolvers: + exact_paths = self.resolver_exact_paths[-1] + if kind in exact_paths: + return exact_paths[kind] + if None in exact_paths: + return exact_paths[None] + if kind is ScalarNode: + return self.DEFAULT_SCALAR_TAG + elif kind is SequenceNode: + return self.DEFAULT_SEQUENCE_TAG + elif kind is MappingNode: + return self.DEFAULT_MAPPING_TAG + +class Resolver(BaseResolver): + pass + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:bool', + re.compile(r'''^(?:yes|Yes|YES|no|No|NO + |true|True|TRUE|false|False|FALSE + |on|On|ON|off|Off|OFF)$''', re.X), + list('yYnNtTfFoO')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:float', + re.compile(r'''^(?:[-+]?(?:[0-9][0-9_]*)\.[0-9_]*(?:[eE][-+][0-9]+)? + |\.[0-9][0-9_]*(?:[eE][-+][0-9]+)? + |[-+]?[0-9][0-9_]*(?::[0-5]?[0-9])+\.[0-9_]* + |[-+]?\.(?:inf|Inf|INF) + |\.(?:nan|NaN|NAN))$''', re.X), + list('-+0123456789.')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:int', + re.compile(r'''^(?:[-+]?0b[0-1_]+ + |[-+]?0[0-7_]+ + |[-+]?(?:0|[1-9][0-9_]*) + |[-+]?0x[0-9a-fA-F_]+ + |[-+]?[1-9][0-9_]*(?::[0-5]?[0-9])+)$''', re.X), + list('-+0123456789')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:merge', + re.compile(r'^(?:<<)$'), + ['<']) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:null', + re.compile(r'''^(?: ~ + |null|Null|NULL + | )$''', re.X), + ['~', 'n', 'N', '']) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:timestamp', + re.compile(r'''^(?:[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9] + |[0-9][0-9][0-9][0-9] -[0-9][0-9]? -[0-9][0-9]? + (?:[Tt]|[ \t]+)[0-9][0-9]? + :[0-9][0-9] :[0-9][0-9] (?:\.[0-9]*)? + (?:[ \t]*(?:Z|[-+][0-9][0-9]?(?::[0-9][0-9])?))?)$''', re.X), + list('0123456789')) + +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:value', + re.compile(r'^(?:=)$'), + ['=']) + +# The following resolver is only for documentation purposes. It cannot work +# because plain scalars cannot start with '!', '&', or '*'. +Resolver.add_implicit_resolver( + 'tag:yaml.org,2002:yaml', + re.compile(r'^(?:!|&|\*)$'), + list('!&*')) + diff --git a/.venv/lib/python3.11/site-packages/yaml/scanner.py b/.venv/lib/python3.11/site-packages/yaml/scanner.py new file mode 100644 index 0000000000000000000000000000000000000000..de925b07f1eaec33c9c305a8a69f9eb7ac5983c5 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/scanner.py @@ -0,0 +1,1435 @@ + +# Scanner produces tokens of the following types: +# STREAM-START +# STREAM-END +# DIRECTIVE(name, value) +# DOCUMENT-START +# DOCUMENT-END +# BLOCK-SEQUENCE-START +# BLOCK-MAPPING-START +# BLOCK-END +# FLOW-SEQUENCE-START +# FLOW-MAPPING-START +# FLOW-SEQUENCE-END +# FLOW-MAPPING-END +# BLOCK-ENTRY +# FLOW-ENTRY +# KEY +# VALUE +# ALIAS(value) +# ANCHOR(value) +# TAG(value) +# SCALAR(value, plain, style) +# +# Read comments in the Scanner code for more details. +# + +__all__ = ['Scanner', 'ScannerError'] + +from .error import MarkedYAMLError +from .tokens import * + +class ScannerError(MarkedYAMLError): + pass + +class SimpleKey: + # See below simple keys treatment. + + def __init__(self, token_number, required, index, line, column, mark): + self.token_number = token_number + self.required = required + self.index = index + self.line = line + self.column = column + self.mark = mark + +class Scanner: + + def __init__(self): + """Initialize the scanner.""" + # It is assumed that Scanner and Reader will have a common descendant. + # Reader do the dirty work of checking for BOM and converting the + # input data to Unicode. It also adds NUL to the end. + # + # Reader supports the following methods + # self.peek(i=0) # peek the next i-th character + # self.prefix(l=1) # peek the next l characters + # self.forward(l=1) # read the next l characters and move the pointer. + + # Had we reached the end of the stream? + self.done = False + + # The number of unclosed '{' and '['. `flow_level == 0` means block + # context. + self.flow_level = 0 + + # List of processed tokens that are not yet emitted. + self.tokens = [] + + # Add the STREAM-START token. + self.fetch_stream_start() + + # Number of tokens that were emitted through the `get_token` method. + self.tokens_taken = 0 + + # The current indentation level. + self.indent = -1 + + # Past indentation levels. + self.indents = [] + + # Variables related to simple keys treatment. + + # A simple key is a key that is not denoted by the '?' indicator. + # Example of simple keys: + # --- + # block simple key: value + # ? not a simple key: + # : { flow simple key: value } + # We emit the KEY token before all keys, so when we find a potential + # simple key, we try to locate the corresponding ':' indicator. + # Simple keys should be limited to a single line and 1024 characters. + + # Can a simple key start at the current position? A simple key may + # start: + # - at the beginning of the line, not counting indentation spaces + # (in block context), + # - after '{', '[', ',' (in the flow context), + # - after '?', ':', '-' (in the block context). + # In the block context, this flag also signifies if a block collection + # may start at the current position. + self.allow_simple_key = True + + # Keep track of possible simple keys. This is a dictionary. The key + # is `flow_level`; there can be no more that one possible simple key + # for each level. The value is a SimpleKey record: + # (token_number, required, index, line, column, mark) + # A simple key may start with ALIAS, ANCHOR, TAG, SCALAR(flow), + # '[', or '{' tokens. + self.possible_simple_keys = {} + + # Public methods. + + def check_token(self, *choices): + # Check if the next token is one of the given types. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + if not choices: + return True + for choice in choices: + if isinstance(self.tokens[0], choice): + return True + return False + + def peek_token(self): + # Return the next token, but do not delete if from the queue. + # Return None if no more tokens. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + return self.tokens[0] + else: + return None + + def get_token(self): + # Return the next token. + while self.need_more_tokens(): + self.fetch_more_tokens() + if self.tokens: + self.tokens_taken += 1 + return self.tokens.pop(0) + + # Private methods. + + def need_more_tokens(self): + if self.done: + return False + if not self.tokens: + return True + # The current token may be a potential simple key, so we + # need to look further. + self.stale_possible_simple_keys() + if self.next_possible_simple_key() == self.tokens_taken: + return True + + def fetch_more_tokens(self): + + # Eat whitespaces and comments until we reach the next token. + self.scan_to_next_token() + + # Remove obsolete possible simple keys. + self.stale_possible_simple_keys() + + # Compare the current indentation and column. It may add some tokens + # and decrease the current indentation level. + self.unwind_indent(self.column) + + # Peek the next character. + ch = self.peek() + + # Is it the end of stream? + if ch == '\0': + return self.fetch_stream_end() + + # Is it a directive? + if ch == '%' and self.check_directive(): + return self.fetch_directive() + + # Is it the document start? + if ch == '-' and self.check_document_start(): + return self.fetch_document_start() + + # Is it the document end? + if ch == '.' and self.check_document_end(): + return self.fetch_document_end() + + # TODO: support for BOM within a stream. + #if ch == '\uFEFF': + # return self.fetch_bom() <-- issue BOMToken + + # Note: the order of the following checks is NOT significant. + + # Is it the flow sequence start indicator? + if ch == '[': + return self.fetch_flow_sequence_start() + + # Is it the flow mapping start indicator? + if ch == '{': + return self.fetch_flow_mapping_start() + + # Is it the flow sequence end indicator? + if ch == ']': + return self.fetch_flow_sequence_end() + + # Is it the flow mapping end indicator? + if ch == '}': + return self.fetch_flow_mapping_end() + + # Is it the flow entry indicator? + if ch == ',': + return self.fetch_flow_entry() + + # Is it the block entry indicator? + if ch == '-' and self.check_block_entry(): + return self.fetch_block_entry() + + # Is it the key indicator? + if ch == '?' and self.check_key(): + return self.fetch_key() + + # Is it the value indicator? + if ch == ':' and self.check_value(): + return self.fetch_value() + + # Is it an alias? + if ch == '*': + return self.fetch_alias() + + # Is it an anchor? + if ch == '&': + return self.fetch_anchor() + + # Is it a tag? + if ch == '!': + return self.fetch_tag() + + # Is it a literal scalar? + if ch == '|' and not self.flow_level: + return self.fetch_literal() + + # Is it a folded scalar? + if ch == '>' and not self.flow_level: + return self.fetch_folded() + + # Is it a single quoted scalar? + if ch == '\'': + return self.fetch_single() + + # Is it a double quoted scalar? + if ch == '\"': + return self.fetch_double() + + # It must be a plain scalar then. + if self.check_plain(): + return self.fetch_plain() + + # No? It's an error. Let's produce a nice error message. + raise ScannerError("while scanning for the next token", None, + "found character %r that cannot start any token" % ch, + self.get_mark()) + + # Simple keys treatment. + + def next_possible_simple_key(self): + # Return the number of the nearest possible simple key. Actually we + # don't need to loop through the whole dictionary. We may replace it + # with the following code: + # if not self.possible_simple_keys: + # return None + # return self.possible_simple_keys[ + # min(self.possible_simple_keys.keys())].token_number + min_token_number = None + for level in self.possible_simple_keys: + key = self.possible_simple_keys[level] + if min_token_number is None or key.token_number < min_token_number: + min_token_number = key.token_number + return min_token_number + + def stale_possible_simple_keys(self): + # Remove entries that are no longer possible simple keys. According to + # the YAML specification, simple keys + # - should be limited to a single line, + # - should be no longer than 1024 characters. + # Disabling this procedure will allow simple keys of any length and + # height (may cause problems if indentation is broken though). + for level in list(self.possible_simple_keys): + key = self.possible_simple_keys[level] + if key.line != self.line \ + or self.index-key.index > 1024: + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not find expected ':'", self.get_mark()) + del self.possible_simple_keys[level] + + def save_possible_simple_key(self): + # The next token may start a simple key. We check if it's possible + # and save its position. This function is called for + # ALIAS, ANCHOR, TAG, SCALAR(flow), '[', and '{'. + + # Check if a simple key is required at the current position. + required = not self.flow_level and self.indent == self.column + + # The next token might be a simple key. Let's save it's number and + # position. + if self.allow_simple_key: + self.remove_possible_simple_key() + token_number = self.tokens_taken+len(self.tokens) + key = SimpleKey(token_number, required, + self.index, self.line, self.column, self.get_mark()) + self.possible_simple_keys[self.flow_level] = key + + def remove_possible_simple_key(self): + # Remove the saved possible key position at the current flow level. + if self.flow_level in self.possible_simple_keys: + key = self.possible_simple_keys[self.flow_level] + + if key.required: + raise ScannerError("while scanning a simple key", key.mark, + "could not find expected ':'", self.get_mark()) + + del self.possible_simple_keys[self.flow_level] + + # Indentation functions. + + def unwind_indent(self, column): + + ## In flow context, tokens should respect indentation. + ## Actually the condition should be `self.indent >= column` according to + ## the spec. But this condition will prohibit intuitively correct + ## constructions such as + ## key : { + ## } + #if self.flow_level and self.indent > column: + # raise ScannerError(None, None, + # "invalid indentation or unclosed '[' or '{'", + # self.get_mark()) + + # In the flow context, indentation is ignored. We make the scanner less + # restrictive then specification requires. + if self.flow_level: + return + + # In block context, we may need to issue the BLOCK-END tokens. + while self.indent > column: + mark = self.get_mark() + self.indent = self.indents.pop() + self.tokens.append(BlockEndToken(mark, mark)) + + def add_indent(self, column): + # Check if we need to increase indentation. + if self.indent < column: + self.indents.append(self.indent) + self.indent = column + return True + return False + + # Fetchers. + + def fetch_stream_start(self): + # We always add STREAM-START as the first token and STREAM-END as the + # last token. + + # Read the token. + mark = self.get_mark() + + # Add STREAM-START. + self.tokens.append(StreamStartToken(mark, mark, + encoding=self.encoding)) + + + def fetch_stream_end(self): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + self.possible_simple_keys = {} + + # Read the token. + mark = self.get_mark() + + # Add STREAM-END. + self.tokens.append(StreamEndToken(mark, mark)) + + # The steam is finished. + self.done = True + + def fetch_directive(self): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Scan and add DIRECTIVE. + self.tokens.append(self.scan_directive()) + + def fetch_document_start(self): + self.fetch_document_indicator(DocumentStartToken) + + def fetch_document_end(self): + self.fetch_document_indicator(DocumentEndToken) + + def fetch_document_indicator(self, TokenClass): + + # Set the current indentation to -1. + self.unwind_indent(-1) + + # Reset simple keys. Note that there could not be a block collection + # after '---'. + self.remove_possible_simple_key() + self.allow_simple_key = False + + # Add DOCUMENT-START or DOCUMENT-END. + start_mark = self.get_mark() + self.forward(3) + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_start(self): + self.fetch_flow_collection_start(FlowSequenceStartToken) + + def fetch_flow_mapping_start(self): + self.fetch_flow_collection_start(FlowMappingStartToken) + + def fetch_flow_collection_start(self, TokenClass): + + # '[' and '{' may start a simple key. + self.save_possible_simple_key() + + # Increase the flow level. + self.flow_level += 1 + + # Simple keys are allowed after '[' and '{'. + self.allow_simple_key = True + + # Add FLOW-SEQUENCE-START or FLOW-MAPPING-START. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_sequence_end(self): + self.fetch_flow_collection_end(FlowSequenceEndToken) + + def fetch_flow_mapping_end(self): + self.fetch_flow_collection_end(FlowMappingEndToken) + + def fetch_flow_collection_end(self, TokenClass): + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Decrease the flow level. + self.flow_level -= 1 + + # No simple keys after ']' or '}'. + self.allow_simple_key = False + + # Add FLOW-SEQUENCE-END or FLOW-MAPPING-END. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(TokenClass(start_mark, end_mark)) + + def fetch_flow_entry(self): + + # Simple keys are allowed after ','. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add FLOW-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(FlowEntryToken(start_mark, end_mark)) + + def fetch_block_entry(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a new entry? + if not self.allow_simple_key: + raise ScannerError(None, None, + "sequence entries are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-SEQUENCE-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockSequenceStartToken(mark, mark)) + + # It's an error for the block entry to occur in the flow context, + # but we let the parser detect this. + else: + pass + + # Simple keys are allowed after '-'. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add BLOCK-ENTRY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(BlockEntryToken(start_mark, end_mark)) + + def fetch_key(self): + + # Block context needs additional checks. + if not self.flow_level: + + # Are we allowed to start a key (not necessary a simple)? + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping keys are not allowed here", + self.get_mark()) + + # We may need to add BLOCK-MAPPING-START. + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after '?' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add KEY. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(KeyToken(start_mark, end_mark)) + + def fetch_value(self): + + # Do we determine a simple key? + if self.flow_level in self.possible_simple_keys: + + # Add KEY. + key = self.possible_simple_keys[self.flow_level] + del self.possible_simple_keys[self.flow_level] + self.tokens.insert(key.token_number-self.tokens_taken, + KeyToken(key.mark, key.mark)) + + # If this key starts a new block mapping, we need to add + # BLOCK-MAPPING-START. + if not self.flow_level: + if self.add_indent(key.column): + self.tokens.insert(key.token_number-self.tokens_taken, + BlockMappingStartToken(key.mark, key.mark)) + + # There cannot be two simple keys one after another. + self.allow_simple_key = False + + # It must be a part of a complex key. + else: + + # Block context needs additional checks. + # (Do we really need them? They will be caught by the parser + # anyway.) + if not self.flow_level: + + # We are allowed to start a complex value if and only if + # we can start a simple key. + if not self.allow_simple_key: + raise ScannerError(None, None, + "mapping values are not allowed here", + self.get_mark()) + + # If this value starts a new block mapping, we need to add + # BLOCK-MAPPING-START. It will be detected as an error later by + # the parser. + if not self.flow_level: + if self.add_indent(self.column): + mark = self.get_mark() + self.tokens.append(BlockMappingStartToken(mark, mark)) + + # Simple keys are allowed after ':' in the block context. + self.allow_simple_key = not self.flow_level + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Add VALUE. + start_mark = self.get_mark() + self.forward() + end_mark = self.get_mark() + self.tokens.append(ValueToken(start_mark, end_mark)) + + def fetch_alias(self): + + # ALIAS could be a simple key. + self.save_possible_simple_key() + + # No simple keys after ALIAS. + self.allow_simple_key = False + + # Scan and add ALIAS. + self.tokens.append(self.scan_anchor(AliasToken)) + + def fetch_anchor(self): + + # ANCHOR could start a simple key. + self.save_possible_simple_key() + + # No simple keys after ANCHOR. + self.allow_simple_key = False + + # Scan and add ANCHOR. + self.tokens.append(self.scan_anchor(AnchorToken)) + + def fetch_tag(self): + + # TAG could start a simple key. + self.save_possible_simple_key() + + # No simple keys after TAG. + self.allow_simple_key = False + + # Scan and add TAG. + self.tokens.append(self.scan_tag()) + + def fetch_literal(self): + self.fetch_block_scalar(style='|') + + def fetch_folded(self): + self.fetch_block_scalar(style='>') + + def fetch_block_scalar(self, style): + + # A simple key may follow a block scalar. + self.allow_simple_key = True + + # Reset possible simple key on the current level. + self.remove_possible_simple_key() + + # Scan and add SCALAR. + self.tokens.append(self.scan_block_scalar(style)) + + def fetch_single(self): + self.fetch_flow_scalar(style='\'') + + def fetch_double(self): + self.fetch_flow_scalar(style='"') + + def fetch_flow_scalar(self, style): + + # A flow scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after flow scalars. + self.allow_simple_key = False + + # Scan and add SCALAR. + self.tokens.append(self.scan_flow_scalar(style)) + + def fetch_plain(self): + + # A plain scalar could be a simple key. + self.save_possible_simple_key() + + # No simple keys after plain scalars. But note that `scan_plain` will + # change this flag if the scan is finished at the beginning of the + # line. + self.allow_simple_key = False + + # Scan and add SCALAR. May change `allow_simple_key`. + self.tokens.append(self.scan_plain()) + + # Checkers. + + def check_directive(self): + + # DIRECTIVE: ^ '%' ... + # The '%' indicator is already checked. + if self.column == 0: + return True + + def check_document_start(self): + + # DOCUMENT-START: ^ '---' (' '|'\n') + if self.column == 0: + if self.prefix(3) == '---' \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return True + + def check_document_end(self): + + # DOCUMENT-END: ^ '...' (' '|'\n') + if self.column == 0: + if self.prefix(3) == '...' \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return True + + def check_block_entry(self): + + # BLOCK-ENTRY: '-' (' '|'\n') + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_key(self): + + # KEY(flow context): '?' + if self.flow_level: + return True + + # KEY(block context): '?' (' '|'\n') + else: + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_value(self): + + # VALUE(flow context): ':' + if self.flow_level: + return True + + # VALUE(block context): ':' (' '|'\n') + else: + return self.peek(1) in '\0 \t\r\n\x85\u2028\u2029' + + def check_plain(self): + + # A plain scalar may start with any non-space character except: + # '-', '?', ':', ',', '[', ']', '{', '}', + # '#', '&', '*', '!', '|', '>', '\'', '\"', + # '%', '@', '`'. + # + # It may also start with + # '-', '?', ':' + # if it is followed by a non-space character. + # + # Note that we limit the last rule to the block context (except the + # '-' character) because we want the flow context to be space + # independent. + ch = self.peek() + return ch not in '\0 \t\r\n\x85\u2028\u2029-?:,[]{}#&*!|>\'\"%@`' \ + or (self.peek(1) not in '\0 \t\r\n\x85\u2028\u2029' + and (ch == '-' or (not self.flow_level and ch in '?:'))) + + # Scanners. + + def scan_to_next_token(self): + # We ignore spaces, line breaks and comments. + # If we find a line break in the block context, we set the flag + # `allow_simple_key` on. + # The byte order mark is stripped if it's the first character in the + # stream. We do not yet support BOM inside the stream as the + # specification requires. Any such mark will be considered as a part + # of the document. + # + # TODO: We need to make tab handling rules more sane. A good rule is + # Tabs cannot precede tokens + # BLOCK-SEQUENCE-START, BLOCK-MAPPING-START, BLOCK-END, + # KEY(block), VALUE(block), BLOCK-ENTRY + # So the checking code is + # if : + # self.allow_simple_keys = False + # We also need to add the check for `allow_simple_keys == True` to + # `unwind_indent` before issuing BLOCK-END. + # Scanners for block, flow, and plain scalars need to be modified. + + if self.index == 0 and self.peek() == '\uFEFF': + self.forward() + found = False + while not found: + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + if self.scan_line_break(): + if not self.flow_level: + self.allow_simple_key = True + else: + found = True + + def scan_directive(self): + # See the specification for details. + start_mark = self.get_mark() + self.forward() + name = self.scan_directive_name(start_mark) + value = None + if name == 'YAML': + value = self.scan_yaml_directive_value(start_mark) + end_mark = self.get_mark() + elif name == 'TAG': + value = self.scan_tag_directive_value(start_mark) + end_mark = self.get_mark() + else: + end_mark = self.get_mark() + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + self.scan_directive_ignored_line(start_mark) + return DirectiveToken(name, value, start_mark, end_mark) + + def scan_directive_name(self, start_mark): + # See the specification for details. + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + return value + + def scan_yaml_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + major = self.scan_yaml_directive_number(start_mark) + if self.peek() != '.': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or '.', but found %r" % self.peek(), + self.get_mark()) + self.forward() + minor = self.scan_yaml_directive_number(start_mark) + if self.peek() not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a digit or ' ', but found %r" % self.peek(), + self.get_mark()) + return (major, minor) + + def scan_yaml_directive_number(self, start_mark): + # See the specification for details. + ch = self.peek() + if not ('0' <= ch <= '9'): + raise ScannerError("while scanning a directive", start_mark, + "expected a digit, but found %r" % ch, self.get_mark()) + length = 0 + while '0' <= self.peek(length) <= '9': + length += 1 + value = int(self.prefix(length)) + self.forward(length) + return value + + def scan_tag_directive_value(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + handle = self.scan_tag_directive_handle(start_mark) + while self.peek() == ' ': + self.forward() + prefix = self.scan_tag_directive_prefix(start_mark) + return (handle, prefix) + + def scan_tag_directive_handle(self, start_mark): + # See the specification for details. + value = self.scan_tag_handle('directive', start_mark) + ch = self.peek() + if ch != ' ': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + return value + + def scan_tag_directive_prefix(self, start_mark): + # See the specification for details. + value = self.scan_tag_uri('directive', start_mark) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + return value + + def scan_directive_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in '\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a directive", start_mark, + "expected a comment or a line break, but found %r" + % ch, self.get_mark()) + self.scan_line_break() + + def scan_anchor(self, TokenClass): + # The specification does not restrict characters for anchors and + # aliases. This may lead to problems, for instance, the document: + # [ *alias, value ] + # can be interpreted in two ways, as + # [ "value" ] + # and + # [ *alias , "value" ] + # Therefore we restrict aliases to numbers and ASCII letters. + start_mark = self.get_mark() + indicator = self.peek() + if indicator == '*': + name = 'alias' + else: + name = 'anchor' + self.forward() + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if not length: + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + value = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch not in '\0 \t\r\n\x85\u2028\u2029?:,]}%@`': + raise ScannerError("while scanning an %s" % name, start_mark, + "expected alphabetic or numeric character, but found %r" + % ch, self.get_mark()) + end_mark = self.get_mark() + return TokenClass(value, start_mark, end_mark) + + def scan_tag(self): + # See the specification for details. + start_mark = self.get_mark() + ch = self.peek(1) + if ch == '<': + handle = None + self.forward(2) + suffix = self.scan_tag_uri('tag', start_mark) + if self.peek() != '>': + raise ScannerError("while parsing a tag", start_mark, + "expected '>', but found %r" % self.peek(), + self.get_mark()) + self.forward() + elif ch in '\0 \t\r\n\x85\u2028\u2029': + handle = None + suffix = '!' + self.forward() + else: + length = 1 + use_handle = False + while ch not in '\0 \r\n\x85\u2028\u2029': + if ch == '!': + use_handle = True + break + length += 1 + ch = self.peek(length) + handle = '!' + if use_handle: + handle = self.scan_tag_handle('tag', start_mark) + else: + handle = '!' + self.forward() + suffix = self.scan_tag_uri('tag', start_mark) + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a tag", start_mark, + "expected ' ', but found %r" % ch, self.get_mark()) + value = (handle, suffix) + end_mark = self.get_mark() + return TagToken(value, start_mark, end_mark) + + def scan_block_scalar(self, style): + # See the specification for details. + + if style == '>': + folded = True + else: + folded = False + + chunks = [] + start_mark = self.get_mark() + + # Scan the header. + self.forward() + chomping, increment = self.scan_block_scalar_indicators(start_mark) + self.scan_block_scalar_ignored_line(start_mark) + + # Determine the indentation level and go to the first non-empty line. + min_indent = self.indent+1 + if min_indent < 1: + min_indent = 1 + if increment is None: + breaks, max_indent, end_mark = self.scan_block_scalar_indentation() + indent = max(min_indent, max_indent) + else: + indent = min_indent+increment-1 + breaks, end_mark = self.scan_block_scalar_breaks(indent) + line_break = '' + + # Scan the inner part of the block scalar. + while self.column == indent and self.peek() != '\0': + chunks.extend(breaks) + leading_non_space = self.peek() not in ' \t' + length = 0 + while self.peek(length) not in '\0\r\n\x85\u2028\u2029': + length += 1 + chunks.append(self.prefix(length)) + self.forward(length) + line_break = self.scan_line_break() + breaks, end_mark = self.scan_block_scalar_breaks(indent) + if self.column == indent and self.peek() != '\0': + + # Unfortunately, folding rules are ambiguous. + # + # This is the folding according to the specification: + + if folded and line_break == '\n' \ + and leading_non_space and self.peek() not in ' \t': + if not breaks: + chunks.append(' ') + else: + chunks.append(line_break) + + # This is Clark Evans's interpretation (also in the spec + # examples): + # + #if folded and line_break == '\n': + # if not breaks: + # if self.peek() not in ' \t': + # chunks.append(' ') + # else: + # chunks.append(line_break) + #else: + # chunks.append(line_break) + else: + break + + # Chomp the tail. + if chomping is not False: + chunks.append(line_break) + if chomping is True: + chunks.extend(breaks) + + # We are done. + return ScalarToken(''.join(chunks), False, start_mark, end_mark, + style) + + def scan_block_scalar_indicators(self, start_mark): + # See the specification for details. + chomping = None + increment = None + ch = self.peek() + if ch in '+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch in '0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + elif ch in '0123456789': + increment = int(ch) + if increment == 0: + raise ScannerError("while scanning a block scalar", start_mark, + "expected indentation indicator in the range 1-9, but found 0", + self.get_mark()) + self.forward() + ch = self.peek() + if ch in '+-': + if ch == '+': + chomping = True + else: + chomping = False + self.forward() + ch = self.peek() + if ch not in '\0 \r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected chomping or indentation indicators, but found %r" + % ch, self.get_mark()) + return chomping, increment + + def scan_block_scalar_ignored_line(self, start_mark): + # See the specification for details. + while self.peek() == ' ': + self.forward() + if self.peek() == '#': + while self.peek() not in '\0\r\n\x85\u2028\u2029': + self.forward() + ch = self.peek() + if ch not in '\0\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a block scalar", start_mark, + "expected a comment or a line break, but found %r" % ch, + self.get_mark()) + self.scan_line_break() + + def scan_block_scalar_indentation(self): + # See the specification for details. + chunks = [] + max_indent = 0 + end_mark = self.get_mark() + while self.peek() in ' \r\n\x85\u2028\u2029': + if self.peek() != ' ': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + else: + self.forward() + if self.column > max_indent: + max_indent = self.column + return chunks, max_indent, end_mark + + def scan_block_scalar_breaks(self, indent): + # See the specification for details. + chunks = [] + end_mark = self.get_mark() + while self.column < indent and self.peek() == ' ': + self.forward() + while self.peek() in '\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + end_mark = self.get_mark() + while self.column < indent and self.peek() == ' ': + self.forward() + return chunks, end_mark + + def scan_flow_scalar(self, style): + # See the specification for details. + # Note that we loose indentation rules for quoted scalars. Quoted + # scalars don't need to adhere indentation because " and ' clearly + # mark the beginning and the end of them. Therefore we are less + # restrictive then the specification requires. We only need to check + # that document separators are not included in scalars. + if style == '"': + double = True + else: + double = False + chunks = [] + start_mark = self.get_mark() + quote = self.peek() + self.forward() + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + while self.peek() != quote: + chunks.extend(self.scan_flow_scalar_spaces(double, start_mark)) + chunks.extend(self.scan_flow_scalar_non_spaces(double, start_mark)) + self.forward() + end_mark = self.get_mark() + return ScalarToken(''.join(chunks), False, start_mark, end_mark, + style) + + ESCAPE_REPLACEMENTS = { + '0': '\0', + 'a': '\x07', + 'b': '\x08', + 't': '\x09', + '\t': '\x09', + 'n': '\x0A', + 'v': '\x0B', + 'f': '\x0C', + 'r': '\x0D', + 'e': '\x1B', + ' ': '\x20', + '\"': '\"', + '\\': '\\', + '/': '/', + 'N': '\x85', + '_': '\xA0', + 'L': '\u2028', + 'P': '\u2029', + } + + ESCAPE_CODES = { + 'x': 2, + 'u': 4, + 'U': 8, + } + + def scan_flow_scalar_non_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + length = 0 + while self.peek(length) not in '\'\"\\\0 \t\r\n\x85\u2028\u2029': + length += 1 + if length: + chunks.append(self.prefix(length)) + self.forward(length) + ch = self.peek() + if not double and ch == '\'' and self.peek(1) == '\'': + chunks.append('\'') + self.forward(2) + elif (double and ch == '\'') or (not double and ch in '\"\\'): + chunks.append(ch) + self.forward() + elif double and ch == '\\': + self.forward() + ch = self.peek() + if ch in self.ESCAPE_REPLACEMENTS: + chunks.append(self.ESCAPE_REPLACEMENTS[ch]) + self.forward() + elif ch in self.ESCAPE_CODES: + length = self.ESCAPE_CODES[ch] + self.forward() + for k in range(length): + if self.peek(k) not in '0123456789ABCDEFabcdef': + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "expected escape sequence of %d hexadecimal numbers, but found %r" % + (length, self.peek(k)), self.get_mark()) + code = int(self.prefix(length), 16) + chunks.append(chr(code)) + self.forward(length) + elif ch in '\r\n\x85\u2028\u2029': + self.scan_line_break() + chunks.extend(self.scan_flow_scalar_breaks(double, start_mark)) + else: + raise ScannerError("while scanning a double-quoted scalar", start_mark, + "found unknown escape character %r" % ch, self.get_mark()) + else: + return chunks + + def scan_flow_scalar_spaces(self, double, start_mark): + # See the specification for details. + chunks = [] + length = 0 + while self.peek(length) in ' \t': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch == '\0': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected end of stream", self.get_mark()) + elif ch in '\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + breaks = self.scan_flow_scalar_breaks(double, start_mark) + if line_break != '\n': + chunks.append(line_break) + elif not breaks: + chunks.append(' ') + chunks.extend(breaks) + else: + chunks.append(whitespaces) + return chunks + + def scan_flow_scalar_breaks(self, double, start_mark): + # See the specification for details. + chunks = [] + while True: + # Instead of checking indentation, we check for document + # separators. + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + raise ScannerError("while scanning a quoted scalar", start_mark, + "found unexpected document separator", self.get_mark()) + while self.peek() in ' \t': + self.forward() + if self.peek() in '\r\n\x85\u2028\u2029': + chunks.append(self.scan_line_break()) + else: + return chunks + + def scan_plain(self): + # See the specification for details. + # We add an additional restriction for the flow context: + # plain scalars in the flow context cannot contain ',' or '?'. + # We also keep track of the `allow_simple_key` flag here. + # Indentation rules are loosed for the flow context. + chunks = [] + start_mark = self.get_mark() + end_mark = start_mark + indent = self.indent+1 + # We allow zero indentation for scalars, but then we need to check for + # document separators at the beginning of the line. + #if indent == 0: + # indent = 1 + spaces = [] + while True: + length = 0 + if self.peek() == '#': + break + while True: + ch = self.peek(length) + if ch in '\0 \t\r\n\x85\u2028\u2029' \ + or (ch == ':' and + self.peek(length+1) in '\0 \t\r\n\x85\u2028\u2029' + + (u',[]{}' if self.flow_level else u''))\ + or (self.flow_level and ch in ',?[]{}'): + break + length += 1 + if length == 0: + break + self.allow_simple_key = False + chunks.extend(spaces) + chunks.append(self.prefix(length)) + self.forward(length) + end_mark = self.get_mark() + spaces = self.scan_plain_spaces(indent, start_mark) + if not spaces or self.peek() == '#' \ + or (not self.flow_level and self.column < indent): + break + return ScalarToken(''.join(chunks), True, start_mark, end_mark) + + def scan_plain_spaces(self, indent, start_mark): + # See the specification for details. + # The specification is really confusing about tabs in plain scalars. + # We just forbid them completely. Do not use tabs in YAML! + chunks = [] + length = 0 + while self.peek(length) in ' ': + length += 1 + whitespaces = self.prefix(length) + self.forward(length) + ch = self.peek() + if ch in '\r\n\x85\u2028\u2029': + line_break = self.scan_line_break() + self.allow_simple_key = True + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return + breaks = [] + while self.peek() in ' \r\n\x85\u2028\u2029': + if self.peek() == ' ': + self.forward() + else: + breaks.append(self.scan_line_break()) + prefix = self.prefix(3) + if (prefix == '---' or prefix == '...') \ + and self.peek(3) in '\0 \t\r\n\x85\u2028\u2029': + return + if line_break != '\n': + chunks.append(line_break) + elif not breaks: + chunks.append(' ') + chunks.extend(breaks) + elif whitespaces: + chunks.append(whitespaces) + return chunks + + def scan_tag_handle(self, name, start_mark): + # See the specification for details. + # For some strange reasons, the specification does not allow '_' in + # tag handles. I have allowed it anyway. + ch = self.peek() + if ch != '!': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch, self.get_mark()) + length = 1 + ch = self.peek(length) + if ch != ' ': + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-_': + length += 1 + ch = self.peek(length) + if ch != '!': + self.forward(length) + raise ScannerError("while scanning a %s" % name, start_mark, + "expected '!', but found %r" % ch, self.get_mark()) + length += 1 + value = self.prefix(length) + self.forward(length) + return value + + def scan_tag_uri(self, name, start_mark): + # See the specification for details. + # Note: we do not check if URI is well-formed. + chunks = [] + length = 0 + ch = self.peek(length) + while '0' <= ch <= '9' or 'A' <= ch <= 'Z' or 'a' <= ch <= 'z' \ + or ch in '-;/?:@&=+$,_.!~*\'()[]%': + if ch == '%': + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + chunks.append(self.scan_uri_escapes(name, start_mark)) + else: + length += 1 + ch = self.peek(length) + if length: + chunks.append(self.prefix(length)) + self.forward(length) + length = 0 + if not chunks: + raise ScannerError("while parsing a %s" % name, start_mark, + "expected URI, but found %r" % ch, self.get_mark()) + return ''.join(chunks) + + def scan_uri_escapes(self, name, start_mark): + # See the specification for details. + codes = [] + mark = self.get_mark() + while self.peek() == '%': + self.forward() + for k in range(2): + if self.peek(k) not in '0123456789ABCDEFabcdef': + raise ScannerError("while scanning a %s" % name, start_mark, + "expected URI escape sequence of 2 hexadecimal numbers, but found %r" + % self.peek(k), self.get_mark()) + codes.append(int(self.prefix(2), 16)) + self.forward(2) + try: + value = bytes(codes).decode('utf-8') + except UnicodeDecodeError as exc: + raise ScannerError("while scanning a %s" % name, start_mark, str(exc), mark) + return value + + def scan_line_break(self): + # Transforms: + # '\r\n' : '\n' + # '\r' : '\n' + # '\n' : '\n' + # '\x85' : '\n' + # '\u2028' : '\u2028' + # '\u2029 : '\u2029' + # default : '' + ch = self.peek() + if ch in '\r\n\x85': + if self.prefix(2) == '\r\n': + self.forward(2) + else: + self.forward() + return '\n' + elif ch in '\u2028\u2029': + self.forward() + return ch + return '' diff --git a/.venv/lib/python3.11/site-packages/yaml/serializer.py b/.venv/lib/python3.11/site-packages/yaml/serializer.py new file mode 100644 index 0000000000000000000000000000000000000000..fe911e67ae7a739abb491fbbc6834b9c37bbda4b --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/serializer.py @@ -0,0 +1,111 @@ + +__all__ = ['Serializer', 'SerializerError'] + +from .error import YAMLError +from .events import * +from .nodes import * + +class SerializerError(YAMLError): + pass + +class Serializer: + + ANCHOR_TEMPLATE = 'id%03d' + + def __init__(self, encoding=None, + explicit_start=None, explicit_end=None, version=None, tags=None): + self.use_encoding = encoding + self.use_explicit_start = explicit_start + self.use_explicit_end = explicit_end + self.use_version = version + self.use_tags = tags + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + self.closed = None + + def open(self): + if self.closed is None: + self.emit(StreamStartEvent(encoding=self.use_encoding)) + self.closed = False + elif self.closed: + raise SerializerError("serializer is closed") + else: + raise SerializerError("serializer is already opened") + + def close(self): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif not self.closed: + self.emit(StreamEndEvent()) + self.closed = True + + #def __del__(self): + # self.close() + + def serialize(self, node): + if self.closed is None: + raise SerializerError("serializer is not opened") + elif self.closed: + raise SerializerError("serializer is closed") + self.emit(DocumentStartEvent(explicit=self.use_explicit_start, + version=self.use_version, tags=self.use_tags)) + self.anchor_node(node) + self.serialize_node(node, None, None) + self.emit(DocumentEndEvent(explicit=self.use_explicit_end)) + self.serialized_nodes = {} + self.anchors = {} + self.last_anchor_id = 0 + + def anchor_node(self, node): + if node in self.anchors: + if self.anchors[node] is None: + self.anchors[node] = self.generate_anchor(node) + else: + self.anchors[node] = None + if isinstance(node, SequenceNode): + for item in node.value: + self.anchor_node(item) + elif isinstance(node, MappingNode): + for key, value in node.value: + self.anchor_node(key) + self.anchor_node(value) + + def generate_anchor(self, node): + self.last_anchor_id += 1 + return self.ANCHOR_TEMPLATE % self.last_anchor_id + + def serialize_node(self, node, parent, index): + alias = self.anchors[node] + if node in self.serialized_nodes: + self.emit(AliasEvent(alias)) + else: + self.serialized_nodes[node] = True + self.descend_resolver(parent, index) + if isinstance(node, ScalarNode): + detected_tag = self.resolve(ScalarNode, node.value, (True, False)) + default_tag = self.resolve(ScalarNode, node.value, (False, True)) + implicit = (node.tag == detected_tag), (node.tag == default_tag) + self.emit(ScalarEvent(alias, node.tag, implicit, node.value, + style=node.style)) + elif isinstance(node, SequenceNode): + implicit = (node.tag + == self.resolve(SequenceNode, node.value, True)) + self.emit(SequenceStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + index = 0 + for item in node.value: + self.serialize_node(item, node, index) + index += 1 + self.emit(SequenceEndEvent()) + elif isinstance(node, MappingNode): + implicit = (node.tag + == self.resolve(MappingNode, node.value, True)) + self.emit(MappingStartEvent(alias, node.tag, implicit, + flow_style=node.flow_style)) + for key, value in node.value: + self.serialize_node(key, node, None) + self.serialize_node(value, node, key) + self.emit(MappingEndEvent()) + self.ascend_resolver() + diff --git a/.venv/lib/python3.11/site-packages/yaml/tokens.py b/.venv/lib/python3.11/site-packages/yaml/tokens.py new file mode 100644 index 0000000000000000000000000000000000000000..4d0b48a394ac8c019b401516a12f688df361cf90 --- /dev/null +++ b/.venv/lib/python3.11/site-packages/yaml/tokens.py @@ -0,0 +1,104 @@ + +class Token(object): + def __init__(self, start_mark, end_mark): + self.start_mark = start_mark + self.end_mark = end_mark + def __repr__(self): + attributes = [key for key in self.__dict__ + if not key.endswith('_mark')] + attributes.sort() + arguments = ', '.join(['%s=%r' % (key, getattr(self, key)) + for key in attributes]) + return '%s(%s)' % (self.__class__.__name__, arguments) + +#class BOMToken(Token): +# id = '' + +class DirectiveToken(Token): + id = '' + def __init__(self, name, value, start_mark, end_mark): + self.name = name + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class DocumentStartToken(Token): + id = '' + +class DocumentEndToken(Token): + id = '' + +class StreamStartToken(Token): + id = '' + def __init__(self, start_mark=None, end_mark=None, + encoding=None): + self.start_mark = start_mark + self.end_mark = end_mark + self.encoding = encoding + +class StreamEndToken(Token): + id = '' + +class BlockSequenceStartToken(Token): + id = '' + +class BlockMappingStartToken(Token): + id = '' + +class BlockEndToken(Token): + id = '' + +class FlowSequenceStartToken(Token): + id = '[' + +class FlowMappingStartToken(Token): + id = '{' + +class FlowSequenceEndToken(Token): + id = ']' + +class FlowMappingEndToken(Token): + id = '}' + +class KeyToken(Token): + id = '?' + +class ValueToken(Token): + id = ':' + +class BlockEntryToken(Token): + id = '-' + +class FlowEntryToken(Token): + id = ',' + +class AliasToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class AnchorToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class TagToken(Token): + id = '' + def __init__(self, value, start_mark, end_mark): + self.value = value + self.start_mark = start_mark + self.end_mark = end_mark + +class ScalarToken(Token): + id = '' + def __init__(self, value, plain, start_mark, end_mark, style=None): + self.value = value + self.plain = plain + self.start_mark = start_mark + self.end_mark = end_mark + self.style = style +