From fb71f4c6705e3410153196ab0c250a9e4913457e Mon Sep 17 00:00:00 2001 From: Nate Prewitt Date: Fri, 24 May 2024 04:03:13 -0700 Subject: [PATCH] Remove vendored charset_normalizer (#12703) * Upgrade to Requests 2.32.0 * Remove charset_normalizer from vendored dependencies --- news/charset_normalizer.vendor.rst | 5 + news/requests.vendor.rst | 1 + pyproject.toml | 2 - src/pip/_vendor/charset_normalizer/LICENSE | 21 - .../_vendor/charset_normalizer/__init__.py | 46 - .../_vendor/charset_normalizer/__main__.py | 4 - src/pip/_vendor/charset_normalizer/api.py | 626 ------ src/pip/_vendor/charset_normalizer/cd.py | 395 ---- .../charset_normalizer/cli/__init__.py | 6 - .../charset_normalizer/cli/__main__.py | 296 --- .../_vendor/charset_normalizer/constant.py | 1995 ----------------- src/pip/_vendor/charset_normalizer/legacy.py | 54 - src/pip/_vendor/charset_normalizer/md.py | 615 ----- src/pip/_vendor/charset_normalizer/models.py | 340 --- src/pip/_vendor/charset_normalizer/py.typed | 0 src/pip/_vendor/charset_normalizer/utils.py | 421 ---- src/pip/_vendor/charset_normalizer/version.py | 6 - src/pip/_vendor/requests/__init__.py | 9 +- src/pip/_vendor/requests/__version__.py | 6 +- src/pip/_vendor/requests/adapters.py | 114 +- src/pip/_vendor/requests/api.py | 2 +- src/pip/_vendor/requests/auth.py | 1 - src/pip/_vendor/requests/compat.py | 15 +- src/pip/_vendor/requests/cookies.py | 16 +- src/pip/_vendor/requests/exceptions.py | 10 + src/pip/_vendor/requests/help.py | 6 +- src/pip/_vendor/requests/models.py | 13 +- src/pip/_vendor/requests/packages.py | 13 +- src/pip/_vendor/requests/sessions.py | 12 +- src/pip/_vendor/requests/status_codes.py | 10 +- src/pip/_vendor/requests/utils.py | 16 +- src/pip/_vendor/vendor.txt | 3 +- tools/vendoring/patches/requests.patch | 144 +- 33 files changed, 273 insertions(+), 4950 deletions(-) create mode 100644 news/charset_normalizer.vendor.rst create mode 100644 news/requests.vendor.rst delete mode 100644 src/pip/_vendor/charset_normalizer/LICENSE delete mode 100644 src/pip/_vendor/charset_normalizer/__init__.py delete mode 100644 src/pip/_vendor/charset_normalizer/__main__.py delete mode 100644 src/pip/_vendor/charset_normalizer/api.py delete mode 100644 src/pip/_vendor/charset_normalizer/cd.py delete mode 100644 src/pip/_vendor/charset_normalizer/cli/__init__.py delete mode 100644 src/pip/_vendor/charset_normalizer/cli/__main__.py delete mode 100644 src/pip/_vendor/charset_normalizer/constant.py delete mode 100644 src/pip/_vendor/charset_normalizer/legacy.py delete mode 100644 src/pip/_vendor/charset_normalizer/md.py delete mode 100644 src/pip/_vendor/charset_normalizer/models.py delete mode 100644 src/pip/_vendor/charset_normalizer/py.typed delete mode 100644 src/pip/_vendor/charset_normalizer/utils.py delete mode 100644 src/pip/_vendor/charset_normalizer/version.py diff --git a/news/charset_normalizer.vendor.rst b/news/charset_normalizer.vendor.rst new file mode 100644 index 00000000000..b4a64c7c10f --- /dev/null +++ b/news/charset_normalizer.vendor.rst @@ -0,0 +1,5 @@ +Remove vendored charset_normalizer. + +Requests provides optional character detection support on some APIs +when processing ambiguous bytes. This isn't relevant for pip to function +and we're able to remove it due to recent upstream changes. diff --git a/news/requests.vendor.rst b/news/requests.vendor.rst new file mode 100644 index 00000000000..edae29fdbc9 --- /dev/null +++ b/news/requests.vendor.rst @@ -0,0 +1 @@ +Upgrade Requests to 2.32.0 diff --git a/pyproject.toml b/pyproject.toml index 7af2982838a..8cbf9c9f4c3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -122,8 +122,6 @@ drop = [ "bin/", # interpreter and OS specific msgpack libs "msgpack/*.so", - # interpreter and OS specific charset-normalizer libs - "charset_normalizer/*.so", # unneeded parts of setuptools "easy_install.py", "setuptools", diff --git a/src/pip/_vendor/charset_normalizer/LICENSE b/src/pip/_vendor/charset_normalizer/LICENSE deleted file mode 100644 index ad82355b802..00000000000 --- a/src/pip/_vendor/charset_normalizer/LICENSE +++ /dev/null @@ -1,21 +0,0 @@ -MIT License - -Copyright (c) 2019 TAHRI Ahmed R. - -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to deal -in the Software without restriction, including without limitation the rights -to use, copy, modify, merge, publish, distribute, sublicense, and/or sell -copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in all -copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, -OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE -SOFTWARE. \ No newline at end of file diff --git a/src/pip/_vendor/charset_normalizer/__init__.py b/src/pip/_vendor/charset_normalizer/__init__.py deleted file mode 100644 index 55991fc3806..00000000000 --- a/src/pip/_vendor/charset_normalizer/__init__.py +++ /dev/null @@ -1,46 +0,0 @@ -# -*- coding: utf-8 -*- -""" -Charset-Normalizer -~~~~~~~~~~~~~~ -The Real First Universal Charset Detector. -A library that helps you read text from an unknown charset encoding. -Motivated by chardet, This package is trying to resolve the issue by taking a new approach. -All IANA character set names for which the Python core library provides codecs are supported. - -Basic usage: - >>> from charset_normalizer import from_bytes - >>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8')) - >>> best_guess = results.best() - >>> str(best_guess) - 'Bсеки човек има право на образование. Oбразованието!' - -Others methods and usages are available - see the full documentation -at . -:copyright: (c) 2021 by Ahmed TAHRI -:license: MIT, see LICENSE for more details. -""" -import logging - -from .api import from_bytes, from_fp, from_path, is_binary -from .legacy import detect -from .models import CharsetMatch, CharsetMatches -from .utils import set_logging_handler -from .version import VERSION, __version__ - -__all__ = ( - "from_fp", - "from_path", - "from_bytes", - "is_binary", - "detect", - "CharsetMatch", - "CharsetMatches", - "__version__", - "VERSION", - "set_logging_handler", -) - -# Attach a NullHandler to the top level logger by default -# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library - -logging.getLogger("charset_normalizer").addHandler(logging.NullHandler()) diff --git a/src/pip/_vendor/charset_normalizer/__main__.py b/src/pip/_vendor/charset_normalizer/__main__.py deleted file mode 100644 index beae2ef7749..00000000000 --- a/src/pip/_vendor/charset_normalizer/__main__.py +++ /dev/null @@ -1,4 +0,0 @@ -from .cli import cli_detect - -if __name__ == "__main__": - cli_detect() diff --git a/src/pip/_vendor/charset_normalizer/api.py b/src/pip/_vendor/charset_normalizer/api.py deleted file mode 100644 index 0ba08e3a50b..00000000000 --- a/src/pip/_vendor/charset_normalizer/api.py +++ /dev/null @@ -1,626 +0,0 @@ -import logging -from os import PathLike -from typing import BinaryIO, List, Optional, Set, Union - -from .cd import ( - coherence_ratio, - encoding_languages, - mb_encoding_languages, - merge_coherence_ratios, -) -from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE -from .md import mess_ratio -from .models import CharsetMatch, CharsetMatches -from .utils import ( - any_specified_encoding, - cut_sequence_chunks, - iana_name, - identify_sig_or_bom, - is_cp_similar, - is_multi_byte_encoding, - should_strip_sig_or_bom, -) - -# Will most likely be controversial -# logging.addLevelName(TRACE, "TRACE") -logger = logging.getLogger("charset_normalizer") -explain_handler = logging.StreamHandler() -explain_handler.setFormatter( - logging.Formatter("%(asctime)s | %(levelname)s | %(message)s") -) - - -def from_bytes( - sequences: Union[bytes, bytearray], - steps: int = 5, - chunk_size: int = 512, - threshold: float = 0.2, - cp_isolation: Optional[List[str]] = None, - cp_exclusion: Optional[List[str]] = None, - preemptive_behaviour: bool = True, - explain: bool = False, - language_threshold: float = 0.1, - enable_fallback: bool = True, -) -> CharsetMatches: - """ - Given a raw bytes sequence, return the best possibles charset usable to render str objects. - If there is no results, it is a strong indicator that the source is binary/not text. - By default, the process will extract 5 blocks of 512o each to assess the mess and coherence of a given sequence. - And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will. - - The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page - but never take it for granted. Can improve the performance. - - You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that - purpose. - - This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32. - By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain' - toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging. - Custom logging format and handler can be set manually. - """ - - if not isinstance(sequences, (bytearray, bytes)): - raise TypeError( - "Expected object of type bytes or bytearray, got: {0}".format( - type(sequences) - ) - ) - - if explain: - previous_logger_level: int = logger.level - logger.addHandler(explain_handler) - logger.setLevel(TRACE) - - length: int = len(sequences) - - if length == 0: - logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.") - if explain: - logger.removeHandler(explain_handler) - logger.setLevel(previous_logger_level or logging.WARNING) - return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")]) - - if cp_isolation is not None: - logger.log( - TRACE, - "cp_isolation is set. use this flag for debugging purpose. " - "limited list of encoding allowed : %s.", - ", ".join(cp_isolation), - ) - cp_isolation = [iana_name(cp, False) for cp in cp_isolation] - else: - cp_isolation = [] - - if cp_exclusion is not None: - logger.log( - TRACE, - "cp_exclusion is set. use this flag for debugging purpose. " - "limited list of encoding excluded : %s.", - ", ".join(cp_exclusion), - ) - cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion] - else: - cp_exclusion = [] - - if length <= (chunk_size * steps): - logger.log( - TRACE, - "override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.", - steps, - chunk_size, - length, - ) - steps = 1 - chunk_size = length - - if steps > 1 and length / steps < chunk_size: - chunk_size = int(length / steps) - - is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE - is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE - - if is_too_small_sequence: - logger.log( - TRACE, - "Trying to detect encoding from a tiny portion of ({}) byte(s).".format( - length - ), - ) - elif is_too_large_sequence: - logger.log( - TRACE, - "Using lazy str decoding because the payload is quite large, ({}) byte(s).".format( - length - ), - ) - - prioritized_encodings: List[str] = [] - - specified_encoding: Optional[str] = ( - any_specified_encoding(sequences) if preemptive_behaviour else None - ) - - if specified_encoding is not None: - prioritized_encodings.append(specified_encoding) - logger.log( - TRACE, - "Detected declarative mark in sequence. Priority +1 given for %s.", - specified_encoding, - ) - - tested: Set[str] = set() - tested_but_hard_failure: List[str] = [] - tested_but_soft_failure: List[str] = [] - - fallback_ascii: Optional[CharsetMatch] = None - fallback_u8: Optional[CharsetMatch] = None - fallback_specified: Optional[CharsetMatch] = None - - results: CharsetMatches = CharsetMatches() - - sig_encoding, sig_payload = identify_sig_or_bom(sequences) - - if sig_encoding is not None: - prioritized_encodings.append(sig_encoding) - logger.log( - TRACE, - "Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.", - len(sig_payload), - sig_encoding, - ) - - prioritized_encodings.append("ascii") - - if "utf_8" not in prioritized_encodings: - prioritized_encodings.append("utf_8") - - for encoding_iana in prioritized_encodings + IANA_SUPPORTED: - if cp_isolation and encoding_iana not in cp_isolation: - continue - - if cp_exclusion and encoding_iana in cp_exclusion: - continue - - if encoding_iana in tested: - continue - - tested.add(encoding_iana) - - decoded_payload: Optional[str] = None - bom_or_sig_available: bool = sig_encoding == encoding_iana - strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom( - encoding_iana - ) - - if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available: - logger.log( - TRACE, - "Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.", - encoding_iana, - ) - continue - if encoding_iana in {"utf_7"} and not bom_or_sig_available: - logger.log( - TRACE, - "Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.", - encoding_iana, - ) - continue - - try: - is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana) - except (ModuleNotFoundError, ImportError): - logger.log( - TRACE, - "Encoding %s does not provide an IncrementalDecoder", - encoding_iana, - ) - continue - - try: - if is_too_large_sequence and is_multi_byte_decoder is False: - str( - sequences[: int(50e4)] - if strip_sig_or_bom is False - else sequences[len(sig_payload) : int(50e4)], - encoding=encoding_iana, - ) - else: - decoded_payload = str( - sequences - if strip_sig_or_bom is False - else sequences[len(sig_payload) :], - encoding=encoding_iana, - ) - except (UnicodeDecodeError, LookupError) as e: - if not isinstance(e, LookupError): - logger.log( - TRACE, - "Code page %s does not fit given bytes sequence at ALL. %s", - encoding_iana, - str(e), - ) - tested_but_hard_failure.append(encoding_iana) - continue - - similar_soft_failure_test: bool = False - - for encoding_soft_failed in tested_but_soft_failure: - if is_cp_similar(encoding_iana, encoding_soft_failed): - similar_soft_failure_test = True - break - - if similar_soft_failure_test: - logger.log( - TRACE, - "%s is deemed too similar to code page %s and was consider unsuited already. Continuing!", - encoding_iana, - encoding_soft_failed, - ) - continue - - r_ = range( - 0 if not bom_or_sig_available else len(sig_payload), - length, - int(length / steps), - ) - - multi_byte_bonus: bool = ( - is_multi_byte_decoder - and decoded_payload is not None - and len(decoded_payload) < length - ) - - if multi_byte_bonus: - logger.log( - TRACE, - "Code page %s is a multi byte encoding table and it appear that at least one character " - "was encoded using n-bytes.", - encoding_iana, - ) - - max_chunk_gave_up: int = int(len(r_) / 4) - - max_chunk_gave_up = max(max_chunk_gave_up, 2) - early_stop_count: int = 0 - lazy_str_hard_failure = False - - md_chunks: List[str] = [] - md_ratios = [] - - try: - for chunk in cut_sequence_chunks( - sequences, - encoding_iana, - r_, - chunk_size, - bom_or_sig_available, - strip_sig_or_bom, - sig_payload, - is_multi_byte_decoder, - decoded_payload, - ): - md_chunks.append(chunk) - - md_ratios.append( - mess_ratio( - chunk, - threshold, - explain is True and 1 <= len(cp_isolation) <= 2, - ) - ) - - if md_ratios[-1] >= threshold: - early_stop_count += 1 - - if (early_stop_count >= max_chunk_gave_up) or ( - bom_or_sig_available and strip_sig_or_bom is False - ): - break - except ( - UnicodeDecodeError - ) as e: # Lazy str loading may have missed something there - logger.log( - TRACE, - "LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s", - encoding_iana, - str(e), - ) - early_stop_count = max_chunk_gave_up - lazy_str_hard_failure = True - - # We might want to check the sequence again with the whole content - # Only if initial MD tests passes - if ( - not lazy_str_hard_failure - and is_too_large_sequence - and not is_multi_byte_decoder - ): - try: - sequences[int(50e3) :].decode(encoding_iana, errors="strict") - except UnicodeDecodeError as e: - logger.log( - TRACE, - "LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s", - encoding_iana, - str(e), - ) - tested_but_hard_failure.append(encoding_iana) - continue - - mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0 - if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up: - tested_but_soft_failure.append(encoding_iana) - logger.log( - TRACE, - "%s was excluded because of initial chaos probing. Gave up %i time(s). " - "Computed mean chaos is %f %%.", - encoding_iana, - early_stop_count, - round(mean_mess_ratio * 100, ndigits=3), - ) - # Preparing those fallbacks in case we got nothing. - if ( - enable_fallback - and encoding_iana in ["ascii", "utf_8", specified_encoding] - and not lazy_str_hard_failure - ): - fallback_entry = CharsetMatch( - sequences, encoding_iana, threshold, False, [], decoded_payload - ) - if encoding_iana == specified_encoding: - fallback_specified = fallback_entry - elif encoding_iana == "ascii": - fallback_ascii = fallback_entry - else: - fallback_u8 = fallback_entry - continue - - logger.log( - TRACE, - "%s passed initial chaos probing. Mean measured chaos is %f %%", - encoding_iana, - round(mean_mess_ratio * 100, ndigits=3), - ) - - if not is_multi_byte_decoder: - target_languages: List[str] = encoding_languages(encoding_iana) - else: - target_languages = mb_encoding_languages(encoding_iana) - - if target_languages: - logger.log( - TRACE, - "{} should target any language(s) of {}".format( - encoding_iana, str(target_languages) - ), - ) - - cd_ratios = [] - - # We shall skip the CD when its about ASCII - # Most of the time its not relevant to run "language-detection" on it. - if encoding_iana != "ascii": - for chunk in md_chunks: - chunk_languages = coherence_ratio( - chunk, - language_threshold, - ",".join(target_languages) if target_languages else None, - ) - - cd_ratios.append(chunk_languages) - - cd_ratios_merged = merge_coherence_ratios(cd_ratios) - - if cd_ratios_merged: - logger.log( - TRACE, - "We detected language {} using {}".format( - cd_ratios_merged, encoding_iana - ), - ) - - results.append( - CharsetMatch( - sequences, - encoding_iana, - mean_mess_ratio, - bom_or_sig_available, - cd_ratios_merged, - decoded_payload, - ) - ) - - if ( - encoding_iana in [specified_encoding, "ascii", "utf_8"] - and mean_mess_ratio < 0.1 - ): - logger.debug( - "Encoding detection: %s is most likely the one.", encoding_iana - ) - if explain: - logger.removeHandler(explain_handler) - logger.setLevel(previous_logger_level) - return CharsetMatches([results[encoding_iana]]) - - if encoding_iana == sig_encoding: - logger.debug( - "Encoding detection: %s is most likely the one as we detected a BOM or SIG within " - "the beginning of the sequence.", - encoding_iana, - ) - if explain: - logger.removeHandler(explain_handler) - logger.setLevel(previous_logger_level) - return CharsetMatches([results[encoding_iana]]) - - if len(results) == 0: - if fallback_u8 or fallback_ascii or fallback_specified: - logger.log( - TRACE, - "Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.", - ) - - if fallback_specified: - logger.debug( - "Encoding detection: %s will be used as a fallback match", - fallback_specified.encoding, - ) - results.append(fallback_specified) - elif ( - (fallback_u8 and fallback_ascii is None) - or ( - fallback_u8 - and fallback_ascii - and fallback_u8.fingerprint != fallback_ascii.fingerprint - ) - or (fallback_u8 is not None) - ): - logger.debug("Encoding detection: utf_8 will be used as a fallback match") - results.append(fallback_u8) - elif fallback_ascii: - logger.debug("Encoding detection: ascii will be used as a fallback match") - results.append(fallback_ascii) - - if results: - logger.debug( - "Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.", - results.best().encoding, # type: ignore - len(results) - 1, - ) - else: - logger.debug("Encoding detection: Unable to determine any suitable charset.") - - if explain: - logger.removeHandler(explain_handler) - logger.setLevel(previous_logger_level) - - return results - - -def from_fp( - fp: BinaryIO, - steps: int = 5, - chunk_size: int = 512, - threshold: float = 0.20, - cp_isolation: Optional[List[str]] = None, - cp_exclusion: Optional[List[str]] = None, - preemptive_behaviour: bool = True, - explain: bool = False, - language_threshold: float = 0.1, - enable_fallback: bool = True, -) -> CharsetMatches: - """ - Same thing than the function from_bytes but using a file pointer that is already ready. - Will not close the file pointer. - """ - return from_bytes( - fp.read(), - steps, - chunk_size, - threshold, - cp_isolation, - cp_exclusion, - preemptive_behaviour, - explain, - language_threshold, - enable_fallback, - ) - - -def from_path( - path: Union[str, bytes, PathLike], # type: ignore[type-arg] - steps: int = 5, - chunk_size: int = 512, - threshold: float = 0.20, - cp_isolation: Optional[List[str]] = None, - cp_exclusion: Optional[List[str]] = None, - preemptive_behaviour: bool = True, - explain: bool = False, - language_threshold: float = 0.1, - enable_fallback: bool = True, -) -> CharsetMatches: - """ - Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode. - Can raise IOError. - """ - with open(path, "rb") as fp: - return from_fp( - fp, - steps, - chunk_size, - threshold, - cp_isolation, - cp_exclusion, - preemptive_behaviour, - explain, - language_threshold, - enable_fallback, - ) - - -def is_binary( - fp_or_path_or_payload: Union[PathLike, str, BinaryIO, bytes], # type: ignore[type-arg] - steps: int = 5, - chunk_size: int = 512, - threshold: float = 0.20, - cp_isolation: Optional[List[str]] = None, - cp_exclusion: Optional[List[str]] = None, - preemptive_behaviour: bool = True, - explain: bool = False, - language_threshold: float = 0.1, - enable_fallback: bool = False, -) -> bool: - """ - Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string. - Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match - are disabled to be stricter around ASCII-compatible but unlikely to be a string. - """ - if isinstance(fp_or_path_or_payload, (str, PathLike)): - guesses = from_path( - fp_or_path_or_payload, - steps=steps, - chunk_size=chunk_size, - threshold=threshold, - cp_isolation=cp_isolation, - cp_exclusion=cp_exclusion, - preemptive_behaviour=preemptive_behaviour, - explain=explain, - language_threshold=language_threshold, - enable_fallback=enable_fallback, - ) - elif isinstance( - fp_or_path_or_payload, - ( - bytes, - bytearray, - ), - ): - guesses = from_bytes( - fp_or_path_or_payload, - steps=steps, - chunk_size=chunk_size, - threshold=threshold, - cp_isolation=cp_isolation, - cp_exclusion=cp_exclusion, - preemptive_behaviour=preemptive_behaviour, - explain=explain, - language_threshold=language_threshold, - enable_fallback=enable_fallback, - ) - else: - guesses = from_fp( - fp_or_path_or_payload, - steps=steps, - chunk_size=chunk_size, - threshold=threshold, - cp_isolation=cp_isolation, - cp_exclusion=cp_exclusion, - preemptive_behaviour=preemptive_behaviour, - explain=explain, - language_threshold=language_threshold, - enable_fallback=enable_fallback, - ) - - return not guesses diff --git a/src/pip/_vendor/charset_normalizer/cd.py b/src/pip/_vendor/charset_normalizer/cd.py deleted file mode 100644 index 4ea6760c45b..00000000000 --- a/src/pip/_vendor/charset_normalizer/cd.py +++ /dev/null @@ -1,395 +0,0 @@ -import importlib -from codecs import IncrementalDecoder -from collections import Counter -from functools import lru_cache -from typing import Counter as TypeCounter, Dict, List, Optional, Tuple - -from .constant import ( - FREQUENCIES, - KO_NAMES, - LANGUAGE_SUPPORTED_COUNT, - TOO_SMALL_SEQUENCE, - ZH_NAMES, -) -from .md import is_suspiciously_successive_range -from .models import CoherenceMatches -from .utils import ( - is_accentuated, - is_latin, - is_multi_byte_encoding, - is_unicode_range_secondary, - unicode_range, -) - - -def encoding_unicode_range(iana_name: str) -> List[str]: - """ - Return associated unicode ranges in a single byte code page. - """ - if is_multi_byte_encoding(iana_name): - raise IOError("Function not supported on multi-byte code page") - - decoder = importlib.import_module( - "encodings.{}".format(iana_name) - ).IncrementalDecoder - - p: IncrementalDecoder = decoder(errors="ignore") - seen_ranges: Dict[str, int] = {} - character_count: int = 0 - - for i in range(0x40, 0xFF): - chunk: str = p.decode(bytes([i])) - - if chunk: - character_range: Optional[str] = unicode_range(chunk) - - if character_range is None: - continue - - if is_unicode_range_secondary(character_range) is False: - if character_range not in seen_ranges: - seen_ranges[character_range] = 0 - seen_ranges[character_range] += 1 - character_count += 1 - - return sorted( - [ - character_range - for character_range in seen_ranges - if seen_ranges[character_range] / character_count >= 0.15 - ] - ) - - -def unicode_range_languages(primary_range: str) -> List[str]: - """ - Return inferred languages used with a unicode range. - """ - languages: List[str] = [] - - for language, characters in FREQUENCIES.items(): - for character in characters: - if unicode_range(character) == primary_range: - languages.append(language) - break - - return languages - - -@lru_cache() -def encoding_languages(iana_name: str) -> List[str]: - """ - Single-byte encoding language association. Some code page are heavily linked to particular language(s). - This function does the correspondence. - """ - unicode_ranges: List[str] = encoding_unicode_range(iana_name) - primary_range: Optional[str] = None - - for specified_range in unicode_ranges: - if "Latin" not in specified_range: - primary_range = specified_range - break - - if primary_range is None: - return ["Latin Based"] - - return unicode_range_languages(primary_range) - - -@lru_cache() -def mb_encoding_languages(iana_name: str) -> List[str]: - """ - Multi-byte encoding language association. Some code page are heavily linked to particular language(s). - This function does the correspondence. - """ - if ( - iana_name.startswith("shift_") - or iana_name.startswith("iso2022_jp") - or iana_name.startswith("euc_j") - or iana_name == "cp932" - ): - return ["Japanese"] - if iana_name.startswith("gb") or iana_name in ZH_NAMES: - return ["Chinese"] - if iana_name.startswith("iso2022_kr") or iana_name in KO_NAMES: - return ["Korean"] - - return [] - - -@lru_cache(maxsize=LANGUAGE_SUPPORTED_COUNT) -def get_target_features(language: str) -> Tuple[bool, bool]: - """ - Determine main aspects from a supported language if it contains accents and if is pure Latin. - """ - target_have_accents: bool = False - target_pure_latin: bool = True - - for character in FREQUENCIES[language]: - if not target_have_accents and is_accentuated(character): - target_have_accents = True - if target_pure_latin and is_latin(character) is False: - target_pure_latin = False - - return target_have_accents, target_pure_latin - - -def alphabet_languages( - characters: List[str], ignore_non_latin: bool = False -) -> List[str]: - """ - Return associated languages associated to given characters. - """ - languages: List[Tuple[str, float]] = [] - - source_have_accents = any(is_accentuated(character) for character in characters) - - for language, language_characters in FREQUENCIES.items(): - target_have_accents, target_pure_latin = get_target_features(language) - - if ignore_non_latin and target_pure_latin is False: - continue - - if target_have_accents is False and source_have_accents: - continue - - character_count: int = len(language_characters) - - character_match_count: int = len( - [c for c in language_characters if c in characters] - ) - - ratio: float = character_match_count / character_count - - if ratio >= 0.2: - languages.append((language, ratio)) - - languages = sorted(languages, key=lambda x: x[1], reverse=True) - - return [compatible_language[0] for compatible_language in languages] - - -def characters_popularity_compare( - language: str, ordered_characters: List[str] -) -> float: - """ - Determine if a ordered characters list (by occurrence from most appearance to rarest) match a particular language. - The result is a ratio between 0. (absolutely no correspondence) and 1. (near perfect fit). - Beware that is function is not strict on the match in order to ease the detection. (Meaning close match is 1.) - """ - if language not in FREQUENCIES: - raise ValueError("{} not available".format(language)) - - character_approved_count: int = 0 - FREQUENCIES_language_set = set(FREQUENCIES[language]) - - ordered_characters_count: int = len(ordered_characters) - target_language_characters_count: int = len(FREQUENCIES[language]) - - large_alphabet: bool = target_language_characters_count > 26 - - for character, character_rank in zip( - ordered_characters, range(0, ordered_characters_count) - ): - if character not in FREQUENCIES_language_set: - continue - - character_rank_in_language: int = FREQUENCIES[language].index(character) - expected_projection_ratio: float = ( - target_language_characters_count / ordered_characters_count - ) - character_rank_projection: int = int(character_rank * expected_projection_ratio) - - if ( - large_alphabet is False - and abs(character_rank_projection - character_rank_in_language) > 4 - ): - continue - - if ( - large_alphabet is True - and abs(character_rank_projection - character_rank_in_language) - < target_language_characters_count / 3 - ): - character_approved_count += 1 - continue - - characters_before_source: List[str] = FREQUENCIES[language][ - 0:character_rank_in_language - ] - characters_after_source: List[str] = FREQUENCIES[language][ - character_rank_in_language: - ] - characters_before: List[str] = ordered_characters[0:character_rank] - characters_after: List[str] = ordered_characters[character_rank:] - - before_match_count: int = len( - set(characters_before) & set(characters_before_source) - ) - - after_match_count: int = len( - set(characters_after) & set(characters_after_source) - ) - - if len(characters_before_source) == 0 and before_match_count <= 4: - character_approved_count += 1 - continue - - if len(characters_after_source) == 0 and after_match_count <= 4: - character_approved_count += 1 - continue - - if ( - before_match_count / len(characters_before_source) >= 0.4 - or after_match_count / len(characters_after_source) >= 0.4 - ): - character_approved_count += 1 - continue - - return character_approved_count / len(ordered_characters) - - -def alpha_unicode_split(decoded_sequence: str) -> List[str]: - """ - Given a decoded text sequence, return a list of str. Unicode range / alphabet separation. - Ex. a text containing English/Latin with a bit a Hebrew will return two items in the resulting list; - One containing the latin letters and the other hebrew. - """ - layers: Dict[str, str] = {} - - for character in decoded_sequence: - if character.isalpha() is False: - continue - - character_range: Optional[str] = unicode_range(character) - - if character_range is None: - continue - - layer_target_range: Optional[str] = None - - for discovered_range in layers: - if ( - is_suspiciously_successive_range(discovered_range, character_range) - is False - ): - layer_target_range = discovered_range - break - - if layer_target_range is None: - layer_target_range = character_range - - if layer_target_range not in layers: - layers[layer_target_range] = character.lower() - continue - - layers[layer_target_range] += character.lower() - - return list(layers.values()) - - -def merge_coherence_ratios(results: List[CoherenceMatches]) -> CoherenceMatches: - """ - This function merge results previously given by the function coherence_ratio. - The return type is the same as coherence_ratio. - """ - per_language_ratios: Dict[str, List[float]] = {} - for result in results: - for sub_result in result: - language, ratio = sub_result - if language not in per_language_ratios: - per_language_ratios[language] = [ratio] - continue - per_language_ratios[language].append(ratio) - - merge = [ - ( - language, - round( - sum(per_language_ratios[language]) / len(per_language_ratios[language]), - 4, - ), - ) - for language in per_language_ratios - ] - - return sorted(merge, key=lambda x: x[1], reverse=True) - - -def filter_alt_coherence_matches(results: CoherenceMatches) -> CoherenceMatches: - """ - We shall NOT return "English—" in CoherenceMatches because it is an alternative - of "English". This function only keeps the best match and remove the em-dash in it. - """ - index_results: Dict[str, List[float]] = dict() - - for result in results: - language, ratio = result - no_em_name: str = language.replace("—", "") - - if no_em_name not in index_results: - index_results[no_em_name] = [] - - index_results[no_em_name].append(ratio) - - if any(len(index_results[e]) > 1 for e in index_results): - filtered_results: CoherenceMatches = [] - - for language in index_results: - filtered_results.append((language, max(index_results[language]))) - - return filtered_results - - return results - - -@lru_cache(maxsize=2048) -def coherence_ratio( - decoded_sequence: str, threshold: float = 0.1, lg_inclusion: Optional[str] = None -) -> CoherenceMatches: - """ - Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers. - A layer = Character extraction by alphabets/ranges. - """ - - results: List[Tuple[str, float]] = [] - ignore_non_latin: bool = False - - sufficient_match_count: int = 0 - - lg_inclusion_list = lg_inclusion.split(",") if lg_inclusion is not None else [] - if "Latin Based" in lg_inclusion_list: - ignore_non_latin = True - lg_inclusion_list.remove("Latin Based") - - for layer in alpha_unicode_split(decoded_sequence): - sequence_frequencies: TypeCounter[str] = Counter(layer) - most_common = sequence_frequencies.most_common() - - character_count: int = sum(o for c, o in most_common) - - if character_count <= TOO_SMALL_SEQUENCE: - continue - - popular_character_ordered: List[str] = [c for c, o in most_common] - - for language in lg_inclusion_list or alphabet_languages( - popular_character_ordered, ignore_non_latin - ): - ratio: float = characters_popularity_compare( - language, popular_character_ordered - ) - - if ratio < threshold: - continue - elif ratio >= 0.8: - sufficient_match_count += 1 - - results.append((language, round(ratio, 4))) - - if sufficient_match_count >= 3: - break - - return sorted( - filter_alt_coherence_matches(results), key=lambda x: x[1], reverse=True - ) diff --git a/src/pip/_vendor/charset_normalizer/cli/__init__.py b/src/pip/_vendor/charset_normalizer/cli/__init__.py deleted file mode 100644 index d95fedfe572..00000000000 --- a/src/pip/_vendor/charset_normalizer/cli/__init__.py +++ /dev/null @@ -1,6 +0,0 @@ -from .__main__ import cli_detect, query_yes_no - -__all__ = ( - "cli_detect", - "query_yes_no", -) diff --git a/src/pip/_vendor/charset_normalizer/cli/__main__.py b/src/pip/_vendor/charset_normalizer/cli/__main__.py deleted file mode 100644 index d939caadb83..00000000000 --- a/src/pip/_vendor/charset_normalizer/cli/__main__.py +++ /dev/null @@ -1,296 +0,0 @@ -import argparse -import sys -from json import dumps -from os.path import abspath, basename, dirname, join, realpath -from platform import python_version -from typing import List, Optional -from unicodedata import unidata_version - -import pip._vendor.charset_normalizer.md as md_module -from pip._vendor.charset_normalizer import from_fp -from pip._vendor.charset_normalizer.models import CliDetectionResult -from pip._vendor.charset_normalizer.version import __version__ - - -def query_yes_no(question: str, default: str = "yes") -> bool: - """Ask a yes/no question via input() and return their answer. - - "question" is a string that is presented to the user. - "default" is the presumed answer if the user just hits . - It must be "yes" (the default), "no" or None (meaning - an answer is required of the user). - - The "answer" return value is True for "yes" or False for "no". - - Credit goes to (c) https://stackoverflow.com/questions/3041986/apt-command-line-interface-like-yes-no-input - """ - valid = {"yes": True, "y": True, "ye": True, "no": False, "n": False} - if default is None: - prompt = " [y/n] " - elif default == "yes": - prompt = " [Y/n] " - elif default == "no": - prompt = " [y/N] " - else: - raise ValueError("invalid default answer: '%s'" % default) - - while True: - sys.stdout.write(question + prompt) - choice = input().lower() - if default is not None and choice == "": - return valid[default] - elif choice in valid: - return valid[choice] - else: - sys.stdout.write("Please respond with 'yes' or 'no' " "(or 'y' or 'n').\n") - - -def cli_detect(argv: Optional[List[str]] = None) -> int: - """ - CLI assistant using ARGV and ArgumentParser - :param argv: - :return: 0 if everything is fine, anything else equal trouble - """ - parser = argparse.ArgumentParser( - description="The Real First Universal Charset Detector. " - "Discover originating encoding used on text file. " - "Normalize text to unicode." - ) - - parser.add_argument( - "files", type=argparse.FileType("rb"), nargs="+", help="File(s) to be analysed" - ) - parser.add_argument( - "-v", - "--verbose", - action="store_true", - default=False, - dest="verbose", - help="Display complementary information about file if any. " - "Stdout will contain logs about the detection process.", - ) - parser.add_argument( - "-a", - "--with-alternative", - action="store_true", - default=False, - dest="alternatives", - help="Output complementary possibilities if any. Top-level JSON WILL be a list.", - ) - parser.add_argument( - "-n", - "--normalize", - action="store_true", - default=False, - dest="normalize", - help="Permit to normalize input file. If not set, program does not write anything.", - ) - parser.add_argument( - "-m", - "--minimal", - action="store_true", - default=False, - dest="minimal", - help="Only output the charset detected to STDOUT. Disabling JSON output.", - ) - parser.add_argument( - "-r", - "--replace", - action="store_true", - default=False, - dest="replace", - help="Replace file when trying to normalize it instead of creating a new one.", - ) - parser.add_argument( - "-f", - "--force", - action="store_true", - default=False, - dest="force", - help="Replace file without asking if you are sure, use this flag with caution.", - ) - parser.add_argument( - "-t", - "--threshold", - action="store", - default=0.2, - type=float, - dest="threshold", - help="Define a custom maximum amount of chaos allowed in decoded content. 0. <= chaos <= 1.", - ) - parser.add_argument( - "--version", - action="version", - version="Charset-Normalizer {} - Python {} - Unicode {} - SpeedUp {}".format( - __version__, - python_version(), - unidata_version, - "OFF" if md_module.__file__.lower().endswith(".py") else "ON", - ), - help="Show version information and exit.", - ) - - args = parser.parse_args(argv) - - if args.replace is True and args.normalize is False: - print("Use --replace in addition of --normalize only.", file=sys.stderr) - return 1 - - if args.force is True and args.replace is False: - print("Use --force in addition of --replace only.", file=sys.stderr) - return 1 - - if args.threshold < 0.0 or args.threshold > 1.0: - print("--threshold VALUE should be between 0. AND 1.", file=sys.stderr) - return 1 - - x_ = [] - - for my_file in args.files: - matches = from_fp(my_file, threshold=args.threshold, explain=args.verbose) - - best_guess = matches.best() - - if best_guess is None: - print( - 'Unable to identify originating encoding for "{}". {}'.format( - my_file.name, - "Maybe try increasing maximum amount of chaos." - if args.threshold < 1.0 - else "", - ), - file=sys.stderr, - ) - x_.append( - CliDetectionResult( - abspath(my_file.name), - None, - [], - [], - "Unknown", - [], - False, - 1.0, - 0.0, - None, - True, - ) - ) - else: - x_.append( - CliDetectionResult( - abspath(my_file.name), - best_guess.encoding, - best_guess.encoding_aliases, - [ - cp - for cp in best_guess.could_be_from_charset - if cp != best_guess.encoding - ], - best_guess.language, - best_guess.alphabets, - best_guess.bom, - best_guess.percent_chaos, - best_guess.percent_coherence, - None, - True, - ) - ) - - if len(matches) > 1 and args.alternatives: - for el in matches: - if el != best_guess: - x_.append( - CliDetectionResult( - abspath(my_file.name), - el.encoding, - el.encoding_aliases, - [ - cp - for cp in el.could_be_from_charset - if cp != el.encoding - ], - el.language, - el.alphabets, - el.bom, - el.percent_chaos, - el.percent_coherence, - None, - False, - ) - ) - - if args.normalize is True: - if best_guess.encoding.startswith("utf") is True: - print( - '"{}" file does not need to be normalized, as it already came from unicode.'.format( - my_file.name - ), - file=sys.stderr, - ) - if my_file.closed is False: - my_file.close() - continue - - dir_path = dirname(realpath(my_file.name)) - file_name = basename(realpath(my_file.name)) - - o_: List[str] = file_name.split(".") - - if args.replace is False: - o_.insert(-1, best_guess.encoding) - if my_file.closed is False: - my_file.close() - elif ( - args.force is False - and query_yes_no( - 'Are you sure to normalize "{}" by replacing it ?'.format( - my_file.name - ), - "no", - ) - is False - ): - if my_file.closed is False: - my_file.close() - continue - - try: - x_[0].unicode_path = join(dir_path, ".".join(o_)) - - with open(x_[0].unicode_path, "w", encoding="utf-8") as fp: - fp.write(str(best_guess)) - except IOError as e: - print(str(e), file=sys.stderr) - if my_file.closed is False: - my_file.close() - return 2 - - if my_file.closed is False: - my_file.close() - - if args.minimal is False: - print( - dumps( - [el.__dict__ for el in x_] if len(x_) > 1 else x_[0].__dict__, - ensure_ascii=True, - indent=4, - ) - ) - else: - for my_file in args.files: - print( - ", ".join( - [ - el.encoding or "undefined" - for el in x_ - if el.path == abspath(my_file.name) - ] - ) - ) - - return 0 - - -if __name__ == "__main__": - cli_detect() diff --git a/src/pip/_vendor/charset_normalizer/constant.py b/src/pip/_vendor/charset_normalizer/constant.py deleted file mode 100644 index 863490461ea..00000000000 --- a/src/pip/_vendor/charset_normalizer/constant.py +++ /dev/null @@ -1,1995 +0,0 @@ -# -*- coding: utf-8 -*- -from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE -from encodings.aliases import aliases -from re import IGNORECASE, compile as re_compile -from typing import Dict, List, Set, Union - -# Contain for each eligible encoding a list of/item bytes SIG/BOM -ENCODING_MARKS: Dict[str, Union[bytes, List[bytes]]] = { - "utf_8": BOM_UTF8, - "utf_7": [ - b"\x2b\x2f\x76\x38", - b"\x2b\x2f\x76\x39", - b"\x2b\x2f\x76\x2b", - b"\x2b\x2f\x76\x2f", - b"\x2b\x2f\x76\x38\x2d", - ], - "gb18030": b"\x84\x31\x95\x33", - "utf_32": [BOM_UTF32_BE, BOM_UTF32_LE], - "utf_16": [BOM_UTF16_BE, BOM_UTF16_LE], -} - -TOO_SMALL_SEQUENCE: int = 32 -TOO_BIG_SEQUENCE: int = int(10e6) - -UTF8_MAXIMAL_ALLOCATION: int = 1_112_064 - -# Up-to-date Unicode ucd/15.0.0 -UNICODE_RANGES_COMBINED: Dict[str, range] = { - "Control character": range(32), - "Basic Latin": range(32, 128), - "Latin-1 Supplement": range(128, 256), - "Latin Extended-A": range(256, 384), - "Latin Extended-B": range(384, 592), - "IPA Extensions": range(592, 688), - "Spacing Modifier Letters": range(688, 768), - "Combining Diacritical Marks": range(768, 880), - "Greek and Coptic": range(880, 1024), - "Cyrillic": range(1024, 1280), - "Cyrillic Supplement": range(1280, 1328), - "Armenian": range(1328, 1424), - "Hebrew": range(1424, 1536), - "Arabic": range(1536, 1792), - "Syriac": range(1792, 1872), - "Arabic Supplement": range(1872, 1920), - "Thaana": range(1920, 1984), - "NKo": range(1984, 2048), - "Samaritan": range(2048, 2112), - "Mandaic": range(2112, 2144), - "Syriac Supplement": range(2144, 2160), - "Arabic Extended-B": range(2160, 2208), - "Arabic Extended-A": range(2208, 2304), - "Devanagari": range(2304, 2432), - "Bengali": range(2432, 2560), - "Gurmukhi": range(2560, 2688), - "Gujarati": range(2688, 2816), - "Oriya": range(2816, 2944), - "Tamil": range(2944, 3072), - "Telugu": range(3072, 3200), - "Kannada": range(3200, 3328), - "Malayalam": range(3328, 3456), - "Sinhala": range(3456, 3584), - "Thai": range(3584, 3712), - "Lao": range(3712, 3840), - "Tibetan": range(3840, 4096), - "Myanmar": range(4096, 4256), - "Georgian": range(4256, 4352), - "Hangul Jamo": range(4352, 4608), - "Ethiopic": range(4608, 4992), - "Ethiopic Supplement": range(4992, 5024), - "Cherokee": range(5024, 5120), - "Unified Canadian Aboriginal Syllabics": range(5120, 5760), - "Ogham": range(5760, 5792), - "Runic": range(5792, 5888), - "Tagalog": range(5888, 5920), - "Hanunoo": range(5920, 5952), - "Buhid": range(5952, 5984), - "Tagbanwa": range(5984, 6016), - "Khmer": range(6016, 6144), - "Mongolian": range(6144, 6320), - "Unified Canadian Aboriginal Syllabics Extended": range(6320, 6400), - "Limbu": range(6400, 6480), - "Tai Le": range(6480, 6528), - "New Tai Lue": range(6528, 6624), - "Khmer Symbols": range(6624, 6656), - "Buginese": range(6656, 6688), - "Tai Tham": range(6688, 6832), - "Combining Diacritical Marks Extended": range(6832, 6912), - "Balinese": range(6912, 7040), - "Sundanese": range(7040, 7104), - "Batak": range(7104, 7168), - "Lepcha": range(7168, 7248), - "Ol Chiki": range(7248, 7296), - "Cyrillic Extended-C": range(7296, 7312), - "Georgian Extended": range(7312, 7360), - "Sundanese Supplement": range(7360, 7376), - "Vedic Extensions": range(7376, 7424), - "Phonetic Extensions": range(7424, 7552), - "Phonetic Extensions Supplement": range(7552, 7616), - "Combining Diacritical Marks Supplement": range(7616, 7680), - "Latin Extended Additional": range(7680, 7936), - "Greek Extended": range(7936, 8192), - "General Punctuation": range(8192, 8304), - "Superscripts and Subscripts": range(8304, 8352), - "Currency Symbols": range(8352, 8400), - "Combining Diacritical Marks for Symbols": range(8400, 8448), - "Letterlike Symbols": range(8448, 8528), - "Number Forms": range(8528, 8592), - "Arrows": range(8592, 8704), - "Mathematical Operators": range(8704, 8960), - "Miscellaneous Technical": range(8960, 9216), - "Control Pictures": range(9216, 9280), - "Optical Character Recognition": range(9280, 9312), - "Enclosed Alphanumerics": range(9312, 9472), - "Box Drawing": range(9472, 9600), - "Block Elements": range(9600, 9632), - "Geometric Shapes": range(9632, 9728), - "Miscellaneous Symbols": range(9728, 9984), - "Dingbats": range(9984, 10176), - "Miscellaneous Mathematical Symbols-A": range(10176, 10224), - "Supplemental Arrows-A": range(10224, 10240), - "Braille Patterns": range(10240, 10496), - "Supplemental Arrows-B": range(10496, 10624), - "Miscellaneous Mathematical Symbols-B": range(10624, 10752), - "Supplemental Mathematical Operators": range(10752, 11008), - "Miscellaneous Symbols and Arrows": range(11008, 11264), - "Glagolitic": range(11264, 11360), - "Latin Extended-C": range(11360, 11392), - "Coptic": range(11392, 11520), - "Georgian Supplement": range(11520, 11568), - "Tifinagh": range(11568, 11648), - "Ethiopic Extended": range(11648, 11744), - "Cyrillic Extended-A": range(11744, 11776), - "Supplemental Punctuation": range(11776, 11904), - "CJK Radicals Supplement": range(11904, 12032), - "Kangxi Radicals": range(12032, 12256), - "Ideographic Description Characters": range(12272, 12288), - "CJK Symbols and Punctuation": range(12288, 12352), - "Hiragana": range(12352, 12448), - "Katakana": range(12448, 12544), - "Bopomofo": range(12544, 12592), - "Hangul Compatibility Jamo": range(12592, 12688), - "Kanbun": range(12688, 12704), - "Bopomofo Extended": range(12704, 12736), - "CJK Strokes": range(12736, 12784), - "Katakana Phonetic Extensions": range(12784, 12800), - "Enclosed CJK Letters and Months": range(12800, 13056), - "CJK Compatibility": range(13056, 13312), - "CJK Unified Ideographs Extension A": range(13312, 19904), - "Yijing Hexagram Symbols": range(19904, 19968), - "CJK Unified Ideographs": range(19968, 40960), - "Yi Syllables": range(40960, 42128), - "Yi Radicals": range(42128, 42192), - "Lisu": range(42192, 42240), - "Vai": range(42240, 42560), - "Cyrillic Extended-B": range(42560, 42656), - "Bamum": range(42656, 42752), - "Modifier Tone Letters": range(42752, 42784), - "Latin Extended-D": range(42784, 43008), - "Syloti Nagri": range(43008, 43056), - "Common Indic Number Forms": range(43056, 43072), - "Phags-pa": range(43072, 43136), - "Saurashtra": range(43136, 43232), - "Devanagari Extended": range(43232, 43264), - "Kayah Li": range(43264, 43312), - "Rejang": range(43312, 43360), - "Hangul Jamo Extended-A": range(43360, 43392), - "Javanese": range(43392, 43488), - "Myanmar Extended-B": range(43488, 43520), - "Cham": range(43520, 43616), - "Myanmar Extended-A": range(43616, 43648), - "Tai Viet": range(43648, 43744), - "Meetei Mayek Extensions": range(43744, 43776), - "Ethiopic Extended-A": range(43776, 43824), - "Latin Extended-E": range(43824, 43888), - "Cherokee Supplement": range(43888, 43968), - "Meetei Mayek": range(43968, 44032), - "Hangul Syllables": range(44032, 55216), - "Hangul Jamo Extended-B": range(55216, 55296), - "High Surrogates": range(55296, 56192), - "High Private Use Surrogates": range(56192, 56320), - "Low Surrogates": range(56320, 57344), - "Private Use Area": range(57344, 63744), - "CJK Compatibility Ideographs": range(63744, 64256), - "Alphabetic Presentation Forms": range(64256, 64336), - "Arabic Presentation Forms-A": range(64336, 65024), - "Variation Selectors": range(65024, 65040), - "Vertical Forms": range(65040, 65056), - "Combining Half Marks": range(65056, 65072), - "CJK Compatibility Forms": range(65072, 65104), - "Small Form Variants": range(65104, 65136), - "Arabic Presentation Forms-B": range(65136, 65280), - "Halfwidth and Fullwidth Forms": range(65280, 65520), - "Specials": range(65520, 65536), - "Linear B Syllabary": range(65536, 65664), - "Linear B Ideograms": range(65664, 65792), - "Aegean Numbers": range(65792, 65856), - "Ancient Greek Numbers": range(65856, 65936), - "Ancient Symbols": range(65936, 66000), - "Phaistos Disc": range(66000, 66048), - "Lycian": range(66176, 66208), - "Carian": range(66208, 66272), - "Coptic Epact Numbers": range(66272, 66304), - "Old Italic": range(66304, 66352), - "Gothic": range(66352, 66384), - "Old Permic": range(66384, 66432), - "Ugaritic": range(66432, 66464), - "Old Persian": range(66464, 66528), - "Deseret": range(66560, 66640), - "Shavian": range(66640, 66688), - "Osmanya": range(66688, 66736), - "Osage": range(66736, 66816), - "Elbasan": range(66816, 66864), - "Caucasian Albanian": range(66864, 66928), - "Vithkuqi": range(66928, 67008), - "Linear A": range(67072, 67456), - "Latin Extended-F": range(67456, 67520), - "Cypriot Syllabary": range(67584, 67648), - "Imperial Aramaic": range(67648, 67680), - "Palmyrene": range(67680, 67712), - "Nabataean": range(67712, 67760), - "Hatran": range(67808, 67840), - "Phoenician": range(67840, 67872), - "Lydian": range(67872, 67904), - "Meroitic Hieroglyphs": range(67968, 68000), - "Meroitic Cursive": range(68000, 68096), - "Kharoshthi": range(68096, 68192), - "Old South Arabian": range(68192, 68224), - "Old North Arabian": range(68224, 68256), - "Manichaean": range(68288, 68352), - "Avestan": range(68352, 68416), - "Inscriptional Parthian": range(68416, 68448), - "Inscriptional Pahlavi": range(68448, 68480), - "Psalter Pahlavi": range(68480, 68528), - "Old Turkic": range(68608, 68688), - "Old Hungarian": range(68736, 68864), - "Hanifi Rohingya": range(68864, 68928), - "Rumi Numeral Symbols": range(69216, 69248), - "Yezidi": range(69248, 69312), - "Arabic Extended-C": range(69312, 69376), - "Old Sogdian": range(69376, 69424), - "Sogdian": range(69424, 69488), - "Old Uyghur": range(69488, 69552), - "Chorasmian": range(69552, 69600), - "Elymaic": range(69600, 69632), - "Brahmi": range(69632, 69760), - "Kaithi": range(69760, 69840), - "Sora Sompeng": range(69840, 69888), - "Chakma": range(69888, 69968), - "Mahajani": range(69968, 70016), - "Sharada": range(70016, 70112), - "Sinhala Archaic Numbers": range(70112, 70144), - "Khojki": range(70144, 70224), - "Multani": range(70272, 70320), - "Khudawadi": range(70320, 70400), - "Grantha": range(70400, 70528), - "Newa": range(70656, 70784), - "Tirhuta": range(70784, 70880), - "Siddham": range(71040, 71168), - "Modi": range(71168, 71264), - "Mongolian Supplement": range(71264, 71296), - "Takri": range(71296, 71376), - "Ahom": range(71424, 71504), - "Dogra": range(71680, 71760), - "Warang Citi": range(71840, 71936), - "Dives Akuru": range(71936, 72032), - "Nandinagari": range(72096, 72192), - "Zanabazar Square": range(72192, 72272), - "Soyombo": range(72272, 72368), - "Unified Canadian Aboriginal Syllabics Extended-A": range(72368, 72384), - "Pau Cin Hau": range(72384, 72448), - "Devanagari Extended-A": range(72448, 72544), - "Bhaiksuki": range(72704, 72816), - "Marchen": range(72816, 72896), - "Masaram Gondi": range(72960, 73056), - "Gunjala Gondi": range(73056, 73136), - "Makasar": range(73440, 73472), - "Kawi": range(73472, 73568), - "Lisu Supplement": range(73648, 73664), - "Tamil Supplement": range(73664, 73728), - "Cuneiform": range(73728, 74752), - "Cuneiform Numbers and Punctuation": range(74752, 74880), - "Early Dynastic Cuneiform": range(74880, 75088), - "Cypro-Minoan": range(77712, 77824), - "Egyptian Hieroglyphs": range(77824, 78896), - "Egyptian Hieroglyph Format Controls": range(78896, 78944), - "Anatolian Hieroglyphs": range(82944, 83584), - "Bamum Supplement": range(92160, 92736), - "Mro": range(92736, 92784), - "Tangsa": range(92784, 92880), - "Bassa Vah": range(92880, 92928), - "Pahawh Hmong": range(92928, 93072), - "Medefaidrin": range(93760, 93856), - "Miao": range(93952, 94112), - "Ideographic Symbols and Punctuation": range(94176, 94208), - "Tangut": range(94208, 100352), - "Tangut Components": range(100352, 101120), - "Khitan Small Script": range(101120, 101632), - "Tangut Supplement": range(101632, 101760), - "Kana Extended-B": range(110576, 110592), - "Kana Supplement": range(110592, 110848), - "Kana Extended-A": range(110848, 110896), - "Small Kana Extension": range(110896, 110960), - "Nushu": range(110960, 111360), - "Duployan": range(113664, 113824), - "Shorthand Format Controls": range(113824, 113840), - "Znamenny Musical Notation": range(118528, 118736), - "Byzantine Musical Symbols": range(118784, 119040), - "Musical Symbols": range(119040, 119296), - "Ancient Greek Musical Notation": range(119296, 119376), - "Kaktovik Numerals": range(119488, 119520), - "Mayan Numerals": range(119520, 119552), - "Tai Xuan Jing Symbols": range(119552, 119648), - "Counting Rod Numerals": range(119648, 119680), - "Mathematical Alphanumeric Symbols": range(119808, 120832), - "Sutton SignWriting": range(120832, 121520), - "Latin Extended-G": range(122624, 122880), - "Glagolitic Supplement": range(122880, 122928), - "Cyrillic Extended-D": range(122928, 123024), - "Nyiakeng Puachue Hmong": range(123136, 123216), - "Toto": range(123536, 123584), - "Wancho": range(123584, 123648), - "Nag Mundari": range(124112, 124160), - "Ethiopic Extended-B": range(124896, 124928), - "Mende Kikakui": range(124928, 125152), - "Adlam": range(125184, 125280), - "Indic Siyaq Numbers": range(126064, 126144), - "Ottoman Siyaq Numbers": range(126208, 126288), - "Arabic Mathematical Alphabetic Symbols": range(126464, 126720), - "Mahjong Tiles": range(126976, 127024), - "Domino Tiles": range(127024, 127136), - "Playing Cards": range(127136, 127232), - "Enclosed Alphanumeric Supplement": range(127232, 127488), - "Enclosed Ideographic Supplement": range(127488, 127744), - "Miscellaneous Symbols and Pictographs": range(127744, 128512), - "Emoticons range(Emoji)": range(128512, 128592), - "Ornamental Dingbats": range(128592, 128640), - "Transport and Map Symbols": range(128640, 128768), - "Alchemical Symbols": range(128768, 128896), - "Geometric Shapes Extended": range(128896, 129024), - "Supplemental Arrows-C": range(129024, 129280), - "Supplemental Symbols and Pictographs": range(129280, 129536), - "Chess Symbols": range(129536, 129648), - "Symbols and Pictographs Extended-A": range(129648, 129792), - "Symbols for Legacy Computing": range(129792, 130048), - "CJK Unified Ideographs Extension B": range(131072, 173792), - "CJK Unified Ideographs Extension C": range(173824, 177984), - "CJK Unified Ideographs Extension D": range(177984, 178208), - "CJK Unified Ideographs Extension E": range(178208, 183984), - "CJK Unified Ideographs Extension F": range(183984, 191472), - "CJK Compatibility Ideographs Supplement": range(194560, 195104), - "CJK Unified Ideographs Extension G": range(196608, 201552), - "CJK Unified Ideographs Extension H": range(201552, 205744), - "Tags": range(917504, 917632), - "Variation Selectors Supplement": range(917760, 918000), - "Supplementary Private Use Area-A": range(983040, 1048576), - "Supplementary Private Use Area-B": range(1048576, 1114112), -} - - -UNICODE_SECONDARY_RANGE_KEYWORD: List[str] = [ - "Supplement", - "Extended", - "Extensions", - "Modifier", - "Marks", - "Punctuation", - "Symbols", - "Forms", - "Operators", - "Miscellaneous", - "Drawing", - "Block", - "Shapes", - "Supplemental", - "Tags", -] - -RE_POSSIBLE_ENCODING_INDICATION = re_compile( - r"(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)", - IGNORECASE, -) - -IANA_NO_ALIASES = [ - "cp720", - "cp737", - "cp856", - "cp874", - "cp875", - "cp1006", - "koi8_r", - "koi8_t", - "koi8_u", -] - -IANA_SUPPORTED: List[str] = sorted( - filter( - lambda x: x.endswith("_codec") is False - and x not in {"rot_13", "tactis", "mbcs"}, - list(set(aliases.values())) + IANA_NO_ALIASES, - ) -) - -IANA_SUPPORTED_COUNT: int = len(IANA_SUPPORTED) - -# pre-computed code page that are similar using the function cp_similarity. -IANA_SUPPORTED_SIMILAR: Dict[str, List[str]] = { - "cp037": ["cp1026", "cp1140", "cp273", "cp500"], - "cp1026": ["cp037", "cp1140", "cp273", "cp500"], - "cp1125": ["cp866"], - "cp1140": ["cp037", "cp1026", "cp273", "cp500"], - "cp1250": ["iso8859_2"], - "cp1251": ["kz1048", "ptcp154"], - "cp1252": ["iso8859_15", "iso8859_9", "latin_1"], - "cp1253": ["iso8859_7"], - "cp1254": ["iso8859_15", "iso8859_9", "latin_1"], - "cp1257": ["iso8859_13"], - "cp273": ["cp037", "cp1026", "cp1140", "cp500"], - "cp437": ["cp850", "cp858", "cp860", "cp861", "cp862", "cp863", "cp865"], - "cp500": ["cp037", "cp1026", "cp1140", "cp273"], - "cp850": ["cp437", "cp857", "cp858", "cp865"], - "cp857": ["cp850", "cp858", "cp865"], - "cp858": ["cp437", "cp850", "cp857", "cp865"], - "cp860": ["cp437", "cp861", "cp862", "cp863", "cp865"], - "cp861": ["cp437", "cp860", "cp862", "cp863", "cp865"], - "cp862": ["cp437", "cp860", "cp861", "cp863", "cp865"], - "cp863": ["cp437", "cp860", "cp861", "cp862", "cp865"], - "cp865": ["cp437", "cp850", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863"], - "cp866": ["cp1125"], - "iso8859_10": ["iso8859_14", "iso8859_15", "iso8859_4", "iso8859_9", "latin_1"], - "iso8859_11": ["tis_620"], - "iso8859_13": ["cp1257"], - "iso8859_14": [ - "iso8859_10", - "iso8859_15", - "iso8859_16", - "iso8859_3", - "iso8859_9", - "latin_1", - ], - "iso8859_15": [ - "cp1252", - "cp1254", - "iso8859_10", - "iso8859_14", - "iso8859_16", - "iso8859_3", - "iso8859_9", - "latin_1", - ], - "iso8859_16": [ - "iso8859_14", - "iso8859_15", - "iso8859_2", - "iso8859_3", - "iso8859_9", - "latin_1", - ], - "iso8859_2": ["cp1250", "iso8859_16", "iso8859_4"], - "iso8859_3": ["iso8859_14", "iso8859_15", "iso8859_16", "iso8859_9", "latin_1"], - "iso8859_4": ["iso8859_10", "iso8859_2", "iso8859_9", "latin_1"], - "iso8859_7": ["cp1253"], - "iso8859_9": [ - "cp1252", - "cp1254", - "cp1258", - "iso8859_10", - "iso8859_14", - "iso8859_15", - "iso8859_16", - "iso8859_3", - "iso8859_4", - "latin_1", - ], - "kz1048": ["cp1251", "ptcp154"], - "latin_1": [ - "cp1252", - "cp1254", - "cp1258", - "iso8859_10", - "iso8859_14", - "iso8859_15", - "iso8859_16", - "iso8859_3", - "iso8859_4", - "iso8859_9", - ], - "mac_iceland": ["mac_roman", "mac_turkish"], - "mac_roman": ["mac_iceland", "mac_turkish"], - "mac_turkish": ["mac_iceland", "mac_roman"], - "ptcp154": ["cp1251", "kz1048"], - "tis_620": ["iso8859_11"], -} - - -CHARDET_CORRESPONDENCE: Dict[str, str] = { - "iso2022_kr": "ISO-2022-KR", - "iso2022_jp": "ISO-2022-JP", - "euc_kr": "EUC-KR", - "tis_620": "TIS-620", - "utf_32": "UTF-32", - "euc_jp": "EUC-JP", - "koi8_r": "KOI8-R", - "iso8859_1": "ISO-8859-1", - "iso8859_2": "ISO-8859-2", - "iso8859_5": "ISO-8859-5", - "iso8859_6": "ISO-8859-6", - "iso8859_7": "ISO-8859-7", - "iso8859_8": "ISO-8859-8", - "utf_16": "UTF-16", - "cp855": "IBM855", - "mac_cyrillic": "MacCyrillic", - "gb2312": "GB2312", - "gb18030": "GB18030", - "cp932": "CP932", - "cp866": "IBM866", - "utf_8": "utf-8", - "utf_8_sig": "UTF-8-SIG", - "shift_jis": "SHIFT_JIS", - "big5": "Big5", - "cp1250": "windows-1250", - "cp1251": "windows-1251", - "cp1252": "Windows-1252", - "cp1253": "windows-1253", - "cp1255": "windows-1255", - "cp1256": "windows-1256", - "cp1254": "Windows-1254", - "cp949": "CP949", -} - - -COMMON_SAFE_ASCII_CHARACTERS: Set[str] = { - "<", - ">", - "=", - ":", - "/", - "&", - ";", - "{", - "}", - "[", - "]", - ",", - "|", - '"', - "-", -} - - -KO_NAMES: Set[str] = {"johab", "cp949", "euc_kr"} -ZH_NAMES: Set[str] = {"big5", "cp950", "big5hkscs", "hz"} - -# Logging LEVEL below DEBUG -TRACE: int = 5 - - -# Language label that contain the em dash "—" -# character are to be considered alternative seq to origin -FREQUENCIES: Dict[str, List[str]] = { - "English": [ - "e", - "a", - "t", - "i", - "o", - "n", - "s", - "r", - "h", - "l", - "d", - "c", - "u", - "m", - "f", - "p", - "g", - "w", - "y", - "b", - "v", - "k", - "x", - "j", - "z", - "q", - ], - "English—": [ - "e", - "a", - "t", - "i", - "o", - "n", - "s", - "r", - "h", - "l", - "d", - "c", - "m", - "u", - "f", - "p", - "g", - "w", - "b", - "y", - "v", - "k", - "j", - "x", - "z", - "q", - ], - "German": [ - "e", - "n", - "i", - "r", - "s", - "t", - "a", - "d", - "h", - "u", - "l", - "g", - "o", - "c", - "m", - "b", - "f", - "k", - "w", - "z", - "p", - "v", - "ü", - "ä", - "ö", - "j", - ], - "French": [ - "e", - "a", - "s", - "n", - "i", - "t", - "r", - "l", - "u", - "o", - "d", - "c", - "p", - "m", - "é", - "v", - "g", - "f", - "b", - "h", - "q", - "à", - "x", - "è", - "y", - "j", - ], - "Dutch": [ - "e", - "n", - "a", - "i", - "r", - "t", - "o", - "d", - "s", - "l", - "g", - "h", - "v", - "m", - "u", - "k", - "c", - "p", - "b", - "w", - "j", - "z", - "f", - "y", - "x", - "ë", - ], - "Italian": [ - "e", - "i", - "a", - "o", - "n", - "l", - "t", - "r", - "s", - "c", - "d", - "u", - "p", - "m", - "g", - "v", - "f", - "b", - "z", - "h", - "q", - "è", - "à", - "k", - "y", - "ò", - ], - "Polish": [ - "a", - "i", - "o", - "e", - "n", - "r", - "z", - "w", - "s", - "c", - "t", - "k", - "y", - "d", - "p", - "m", - "u", - "l", - "j", - "ł", - "g", - "b", - "h", - "ą", - "ę", - "ó", - ], - "Spanish": [ - "e", - "a", - "o", - "n", - "s", - "r", - "i", - "l", - "d", - "t", - "c", - "u", - "m", - "p", - "b", - "g", - "v", - "f", - "y", - "ó", - "h", - "q", - "í", - "j", - "z", - "á", - ], - "Russian": [ - "о", - "а", - "е", - "и", - "н", - "с", - "т", - "р", - "в", - "л", - "к", - "м", - "д", - "п", - "у", - "г", - "я", - "ы", - "з", - "б", - "й", - "ь", - "ч", - "х", - "ж", - "ц", - ], - # Jap-Kanji - "Japanese": [ - "人", - "一", - "大", - "亅", - "丁", - "丨", - "竹", - "笑", - "口", - "日", - "今", - "二", - "彳", - "行", - "十", - "土", - "丶", - "寸", - "寺", - "時", - "乙", - "丿", - "乂", - "气", - "気", - "冂", - "巾", - "亠", - "市", - "目", - "儿", - "見", - "八", - "小", - "凵", - "県", - "月", - "彐", - "門", - "間", - "木", - "東", - "山", - "出", - "本", - "中", - "刀", - "分", - "耳", - "又", - "取", - "最", - "言", - "田", - "心", - "思", - "刂", - "前", - "京", - "尹", - "事", - "生", - "厶", - "云", - "会", - "未", - "来", - "白", - "冫", - "楽", - "灬", - "馬", - "尸", - "尺", - "駅", - "明", - "耂", - "者", - "了", - "阝", - "都", - "高", - "卜", - "占", - "厂", - "广", - "店", - "子", - "申", - "奄", - "亻", - "俺", - "上", - "方", - "冖", - "学", - "衣", - "艮", - "食", - "自", - ], - # Jap-Katakana - "Japanese—": [ - "ー", - "ン", - "ス", - "・", - "ル", - "ト", - "リ", - "イ", - "ア", - "ラ", - "ッ", - "ク", - "ド", - "シ", - "レ", - "ジ", - "タ", - "フ", - "ロ", - "カ", - "テ", - "マ", - "ィ", - "グ", - "バ", - "ム", - "プ", - "オ", - "コ", - "デ", - "ニ", - "ウ", - "メ", - "サ", - "ビ", - "ナ", - "ブ", - "ャ", - "エ", - "ュ", - "チ", - "キ", - "ズ", - "ダ", - "パ", - "ミ", - "ェ", - "ョ", - "ハ", - "セ", - "ベ", - "ガ", - "モ", - "ツ", - "ネ", - "ボ", - "ソ", - "ノ", - "ァ", - "ヴ", - "ワ", - "ポ", - "ペ", - "ピ", - "ケ", - "ゴ", - "ギ", - "ザ", - "ホ", - "ゲ", - "ォ", - "ヤ", - "ヒ", - "ユ", - "ヨ", - "ヘ", - "ゼ", - "ヌ", - "ゥ", - "ゾ", - "ヶ", - "ヂ", - "ヲ", - "ヅ", - "ヵ", - "ヱ", - "ヰ", - "ヮ", - "ヽ", - "゠", - "ヾ", - "ヷ", - "ヿ", - "ヸ", - "ヹ", - "ヺ", - ], - # Jap-Hiragana - "Japanese——": [ - "の", - "に", - "る", - "た", - "と", - "は", - "し", - "い", - "を", - "で", - "て", - "が", - "な", - "れ", - "か", - "ら", - "さ", - "っ", - "り", - "す", - "あ", - "も", - "こ", - "ま", - "う", - "く", - "よ", - "き", - "ん", - "め", - "お", - "け", - "そ", - "つ", - "だ", - "や", - "え", - "ど", - "わ", - "ち", - "み", - "せ", - "じ", - "ば", - "へ", - "び", - "ず", - "ろ", - "ほ", - "げ", - "む", - "べ", - "ひ", - "ょ", - "ゆ", - "ぶ", - "ご", - "ゃ", - "ね", - "ふ", - "ぐ", - "ぎ", - "ぼ", - "ゅ", - "づ", - "ざ", - "ぞ", - "ぬ", - "ぜ", - "ぱ", - "ぽ", - "ぷ", - "ぴ", - "ぃ", - "ぁ", - "ぇ", - "ぺ", - "ゞ", - "ぢ", - "ぉ", - "ぅ", - "ゐ", - "ゝ", - "ゑ", - "゛", - "゜", - "ゎ", - "ゔ", - "゚", - "ゟ", - "゙", - "ゕ", - "ゖ", - ], - "Portuguese": [ - "a", - "e", - "o", - "s", - "i", - "r", - "d", - "n", - "t", - "m", - "u", - "c", - "l", - "p", - "g", - "v", - "b", - "f", - "h", - "ã", - "q", - "é", - "ç", - "á", - "z", - "í", - ], - "Swedish": [ - "e", - "a", - "n", - "r", - "t", - "s", - "i", - "l", - "d", - "o", - "m", - "k", - "g", - "v", - "h", - "f", - "u", - "p", - "ä", - "c", - "b", - "ö", - "å", - "y", - "j", - "x", - ], - "Chinese": [ - "的", - "一", - "是", - "不", - "了", - "在", - "人", - "有", - "我", - "他", - "这", - "个", - "们", - "中", - "来", - "上", - "大", - "为", - "和", - "国", - "地", - "到", - "以", - "说", - "时", - "要", - "就", - "出", - "会", - "可", - "也", - "你", - "对", - "生", - "能", - "而", - "子", - "那", - "得", - "于", - "着", - "下", - "自", - "之", - "年", - "过", - "发", - "后", - "作", - "里", - "用", - "道", - "行", - "所", - "然", - "家", - "种", - "事", - "成", - "方", - "多", - "经", - "么", - "去", - "法", - "学", - "如", - "都", - "同", - "现", - "当", - "没", - "动", - "面", - "起", - "看", - "定", - "天", - "分", - "还", - "进", - "好", - "小", - "部", - "其", - "些", - "主", - "样", - "理", - "心", - "她", - "本", - "前", - "开", - "但", - "因", - "只", - "从", - "想", - "实", - ], - "Ukrainian": [ - "о", - "а", - "н", - "і", - "и", - "р", - "в", - "т", - "е", - "с", - "к", - "л", - "у", - "д", - "м", - "п", - "з", - "я", - "ь", - "б", - "г", - "й", - "ч", - "х", - "ц", - "ї", - ], - "Norwegian": [ - "e", - "r", - "n", - "t", - "a", - "s", - "i", - "o", - "l", - "d", - "g", - "k", - "m", - "v", - "f", - "p", - "u", - "b", - "h", - "å", - "y", - "j", - "ø", - "c", - "æ", - "w", - ], - "Finnish": [ - "a", - "i", - "n", - "t", - "e", - "s", - "l", - "o", - "u", - "k", - "ä", - "m", - "r", - "v", - "j", - "h", - "p", - "y", - "d", - "ö", - "g", - "c", - "b", - "f", - "w", - "z", - ], - "Vietnamese": [ - "n", - "h", - "t", - "i", - "c", - "g", - "a", - "o", - "u", - "m", - "l", - "r", - "à", - "đ", - "s", - "e", - "v", - "p", - "b", - "y", - "ư", - "d", - "á", - "k", - "ộ", - "ế", - ], - "Czech": [ - "o", - "e", - "a", - "n", - "t", - "s", - "i", - "l", - "v", - "r", - "k", - "d", - "u", - "m", - "p", - "í", - "c", - "h", - "z", - "á", - "y", - "j", - "b", - "ě", - "é", - "ř", - ], - "Hungarian": [ - "e", - "a", - "t", - "l", - "s", - "n", - "k", - "r", - "i", - "o", - "z", - "á", - "é", - "g", - "m", - "b", - "y", - "v", - "d", - "h", - "u", - "p", - "j", - "ö", - "f", - "c", - ], - "Korean": [ - "이", - "다", - "에", - "의", - "는", - "로", - "하", - "을", - "가", - "고", - "지", - "서", - "한", - "은", - "기", - "으", - "년", - "대", - "사", - "시", - "를", - "리", - "도", - "인", - "스", - "일", - ], - "Indonesian": [ - "a", - "n", - "e", - "i", - "r", - "t", - "u", - "s", - "d", - "k", - "m", - "l", - "g", - "p", - "b", - "o", - "h", - "y", - "j", - "c", - "w", - "f", - "v", - "z", - "x", - "q", - ], - "Turkish": [ - "a", - "e", - "i", - "n", - "r", - "l", - "ı", - "k", - "d", - "t", - "s", - "m", - "y", - "u", - "o", - "b", - "ü", - "ş", - "v", - "g", - "z", - "h", - "c", - "p", - "ç", - "ğ", - ], - "Romanian": [ - "e", - "i", - "a", - "r", - "n", - "t", - "u", - "l", - "o", - "c", - "s", - "d", - "p", - "m", - "ă", - "f", - "v", - "î", - "g", - "b", - "ș", - "ț", - "z", - "h", - "â", - "j", - ], - "Farsi": [ - "ا", - "ی", - "ر", - "د", - "ن", - "ه", - "و", - "م", - "ت", - "ب", - "س", - "ل", - "ک", - "ش", - "ز", - "ف", - "گ", - "ع", - "خ", - "ق", - "ج", - "آ", - "پ", - "ح", - "ط", - "ص", - ], - "Arabic": [ - "ا", - "ل", - "ي", - "م", - "و", - "ن", - "ر", - "ت", - "ب", - "ة", - "ع", - "د", - "س", - "ف", - "ه", - "ك", - "ق", - "أ", - "ح", - "ج", - "ش", - "ط", - "ص", - "ى", - "خ", - "إ", - ], - "Danish": [ - "e", - "r", - "n", - "t", - "a", - "i", - "s", - "d", - "l", - "o", - "g", - "m", - "k", - "f", - "v", - "u", - "b", - "h", - "p", - "å", - "y", - "ø", - "æ", - "c", - "j", - "w", - ], - "Serbian": [ - "а", - "и", - "о", - "е", - "н", - "р", - "с", - "у", - "т", - "к", - "ј", - "в", - "д", - "м", - "п", - "л", - "г", - "з", - "б", - "a", - "i", - "e", - "o", - "n", - "ц", - "ш", - ], - "Lithuanian": [ - "i", - "a", - "s", - "o", - "r", - "e", - "t", - "n", - "u", - "k", - "m", - "l", - "p", - "v", - "d", - "j", - "g", - "ė", - "b", - "y", - "ų", - "š", - "ž", - "c", - "ą", - "į", - ], - "Slovene": [ - "e", - "a", - "i", - "o", - "n", - "r", - "s", - "l", - "t", - "j", - "v", - "k", - "d", - "p", - "m", - "u", - "z", - "b", - "g", - "h", - "č", - "c", - "š", - "ž", - "f", - "y", - ], - "Slovak": [ - "o", - "a", - "e", - "n", - "i", - "r", - "v", - "t", - "s", - "l", - "k", - "d", - "m", - "p", - "u", - "c", - "h", - "j", - "b", - "z", - "á", - "y", - "ý", - "í", - "č", - "é", - ], - "Hebrew": [ - "י", - "ו", - "ה", - "ל", - "ר", - "ב", - "ת", - "מ", - "א", - "ש", - "נ", - "ע", - "ם", - "ד", - "ק", - "ח", - "פ", - "ס", - "כ", - "ג", - "ט", - "צ", - "ן", - "ז", - "ך", - ], - "Bulgarian": [ - "а", - "и", - "о", - "е", - "н", - "т", - "р", - "с", - "в", - "л", - "к", - "д", - "п", - "м", - "з", - "г", - "я", - "ъ", - "у", - "б", - "ч", - "ц", - "й", - "ж", - "щ", - "х", - ], - "Croatian": [ - "a", - "i", - "o", - "e", - "n", - "r", - "j", - "s", - "t", - "u", - "k", - "l", - "v", - "d", - "m", - "p", - "g", - "z", - "b", - "c", - "č", - "h", - "š", - "ž", - "ć", - "f", - ], - "Hindi": [ - "क", - "र", - "स", - "न", - "त", - "म", - "ह", - "प", - "य", - "ल", - "व", - "ज", - "द", - "ग", - "ब", - "श", - "ट", - "अ", - "ए", - "थ", - "भ", - "ड", - "च", - "ध", - "ष", - "इ", - ], - "Estonian": [ - "a", - "i", - "e", - "s", - "t", - "l", - "u", - "n", - "o", - "k", - "r", - "d", - "m", - "v", - "g", - "p", - "j", - "h", - "ä", - "b", - "õ", - "ü", - "f", - "c", - "ö", - "y", - ], - "Thai": [ - "า", - "น", - "ร", - "อ", - "ก", - "เ", - "ง", - "ม", - "ย", - "ล", - "ว", - "ด", - "ท", - "ส", - "ต", - "ะ", - "ป", - "บ", - "ค", - "ห", - "แ", - "จ", - "พ", - "ช", - "ข", - "ใ", - ], - "Greek": [ - "α", - "τ", - "ο", - "ι", - "ε", - "ν", - "ρ", - "σ", - "κ", - "η", - "π", - "ς", - "υ", - "μ", - "λ", - "ί", - "ό", - "ά", - "γ", - "έ", - "δ", - "ή", - "ω", - "χ", - "θ", - "ύ", - ], - "Tamil": [ - "க", - "த", - "ப", - "ட", - "ர", - "ம", - "ல", - "ன", - "வ", - "ற", - "ய", - "ள", - "ச", - "ந", - "இ", - "ண", - "அ", - "ஆ", - "ழ", - "ங", - "எ", - "உ", - "ஒ", - "ஸ", - ], - "Kazakh": [ - "а", - "ы", - "е", - "н", - "т", - "р", - "л", - "і", - "д", - "с", - "м", - "қ", - "к", - "о", - "б", - "и", - "у", - "ғ", - "ж", - "ң", - "з", - "ш", - "й", - "п", - "г", - "ө", - ], -} - -LANGUAGE_SUPPORTED_COUNT: int = len(FREQUENCIES) diff --git a/src/pip/_vendor/charset_normalizer/legacy.py b/src/pip/_vendor/charset_normalizer/legacy.py deleted file mode 100644 index 43aad21a9dd..00000000000 --- a/src/pip/_vendor/charset_normalizer/legacy.py +++ /dev/null @@ -1,54 +0,0 @@ -from typing import Any, Dict, Optional, Union -from warnings import warn - -from .api import from_bytes -from .constant import CHARDET_CORRESPONDENCE - - -def detect( - byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any -) -> Dict[str, Optional[Union[str, float]]]: - """ - chardet legacy method - Detect the encoding of the given byte string. It should be mostly backward-compatible. - Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it) - This function is deprecated and should be used to migrate your project easily, consult the documentation for - further information. Not planned for removal. - - :param byte_str: The byte sequence to examine. - :param should_rename_legacy: Should we rename legacy encodings - to their more modern equivalents? - """ - if len(kwargs): - warn( - f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()" - ) - - if not isinstance(byte_str, (bytearray, bytes)): - raise TypeError( # pragma: nocover - "Expected object of type bytes or bytearray, got: " - "{0}".format(type(byte_str)) - ) - - if isinstance(byte_str, bytearray): - byte_str = bytes(byte_str) - - r = from_bytes(byte_str).best() - - encoding = r.encoding if r is not None else None - language = r.language if r is not None and r.language != "Unknown" else "" - confidence = 1.0 - r.chaos if r is not None else None - - # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process - # but chardet does return 'utf-8-sig' and it is a valid codec name. - if r is not None and encoding == "utf_8" and r.bom: - encoding += "_sig" - - if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE: - encoding = CHARDET_CORRESPONDENCE[encoding] - - return { - "encoding": encoding, - "language": language, - "confidence": confidence, - } diff --git a/src/pip/_vendor/charset_normalizer/md.py b/src/pip/_vendor/charset_normalizer/md.py deleted file mode 100644 index 77897aae4f4..00000000000 --- a/src/pip/_vendor/charset_normalizer/md.py +++ /dev/null @@ -1,615 +0,0 @@ -from functools import lru_cache -from logging import getLogger -from typing import List, Optional - -from .constant import ( - COMMON_SAFE_ASCII_CHARACTERS, - TRACE, - UNICODE_SECONDARY_RANGE_KEYWORD, -) -from .utils import ( - is_accentuated, - is_arabic, - is_arabic_isolated_form, - is_case_variable, - is_cjk, - is_emoticon, - is_hangul, - is_hiragana, - is_katakana, - is_latin, - is_punctuation, - is_separator, - is_symbol, - is_thai, - is_unprintable, - remove_accent, - unicode_range, -) - - -class MessDetectorPlugin: - """ - Base abstract class used for mess detection plugins. - All detectors MUST extend and implement given methods. - """ - - def eligible(self, character: str) -> bool: - """ - Determine if given character should be fed in. - """ - raise NotImplementedError # pragma: nocover - - def feed(self, character: str) -> None: - """ - The main routine to be executed upon character. - Insert the logic in witch the text would be considered chaotic. - """ - raise NotImplementedError # pragma: nocover - - def reset(self) -> None: # pragma: no cover - """ - Permit to reset the plugin to the initial state. - """ - raise NotImplementedError - - @property - def ratio(self) -> float: - """ - Compute the chaos ratio based on what your feed() has seen. - Must NOT be lower than 0.; No restriction gt 0. - """ - raise NotImplementedError # pragma: nocover - - -class TooManySymbolOrPunctuationPlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._punctuation_count: int = 0 - self._symbol_count: int = 0 - self._character_count: int = 0 - - self._last_printable_char: Optional[str] = None - self._frenzy_symbol_in_word: bool = False - - def eligible(self, character: str) -> bool: - return character.isprintable() - - def feed(self, character: str) -> None: - self._character_count += 1 - - if ( - character != self._last_printable_char - and character not in COMMON_SAFE_ASCII_CHARACTERS - ): - if is_punctuation(character): - self._punctuation_count += 1 - elif ( - character.isdigit() is False - and is_symbol(character) - and is_emoticon(character) is False - ): - self._symbol_count += 2 - - self._last_printable_char = character - - def reset(self) -> None: # pragma: no cover - self._punctuation_count = 0 - self._character_count = 0 - self._symbol_count = 0 - - @property - def ratio(self) -> float: - if self._character_count == 0: - return 0.0 - - ratio_of_punctuation: float = ( - self._punctuation_count + self._symbol_count - ) / self._character_count - - return ratio_of_punctuation if ratio_of_punctuation >= 0.3 else 0.0 - - -class TooManyAccentuatedPlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._character_count: int = 0 - self._accentuated_count: int = 0 - - def eligible(self, character: str) -> bool: - return character.isalpha() - - def feed(self, character: str) -> None: - self._character_count += 1 - - if is_accentuated(character): - self._accentuated_count += 1 - - def reset(self) -> None: # pragma: no cover - self._character_count = 0 - self._accentuated_count = 0 - - @property - def ratio(self) -> float: - if self._character_count < 8: - return 0.0 - - ratio_of_accentuation: float = self._accentuated_count / self._character_count - return ratio_of_accentuation if ratio_of_accentuation >= 0.35 else 0.0 - - -class UnprintablePlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._unprintable_count: int = 0 - self._character_count: int = 0 - - def eligible(self, character: str) -> bool: - return True - - def feed(self, character: str) -> None: - if is_unprintable(character): - self._unprintable_count += 1 - self._character_count += 1 - - def reset(self) -> None: # pragma: no cover - self._unprintable_count = 0 - - @property - def ratio(self) -> float: - if self._character_count == 0: - return 0.0 - - return (self._unprintable_count * 8) / self._character_count - - -class SuspiciousDuplicateAccentPlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._successive_count: int = 0 - self._character_count: int = 0 - - self._last_latin_character: Optional[str] = None - - def eligible(self, character: str) -> bool: - return character.isalpha() and is_latin(character) - - def feed(self, character: str) -> None: - self._character_count += 1 - if ( - self._last_latin_character is not None - and is_accentuated(character) - and is_accentuated(self._last_latin_character) - ): - if character.isupper() and self._last_latin_character.isupper(): - self._successive_count += 1 - # Worse if its the same char duplicated with different accent. - if remove_accent(character) == remove_accent(self._last_latin_character): - self._successive_count += 1 - self._last_latin_character = character - - def reset(self) -> None: # pragma: no cover - self._successive_count = 0 - self._character_count = 0 - self._last_latin_character = None - - @property - def ratio(self) -> float: - if self._character_count == 0: - return 0.0 - - return (self._successive_count * 2) / self._character_count - - -class SuspiciousRange(MessDetectorPlugin): - def __init__(self) -> None: - self._suspicious_successive_range_count: int = 0 - self._character_count: int = 0 - self._last_printable_seen: Optional[str] = None - - def eligible(self, character: str) -> bool: - return character.isprintable() - - def feed(self, character: str) -> None: - self._character_count += 1 - - if ( - character.isspace() - or is_punctuation(character) - or character in COMMON_SAFE_ASCII_CHARACTERS - ): - self._last_printable_seen = None - return - - if self._last_printable_seen is None: - self._last_printable_seen = character - return - - unicode_range_a: Optional[str] = unicode_range(self._last_printable_seen) - unicode_range_b: Optional[str] = unicode_range(character) - - if is_suspiciously_successive_range(unicode_range_a, unicode_range_b): - self._suspicious_successive_range_count += 1 - - self._last_printable_seen = character - - def reset(self) -> None: # pragma: no cover - self._character_count = 0 - self._suspicious_successive_range_count = 0 - self._last_printable_seen = None - - @property - def ratio(self) -> float: - if self._character_count <= 24: - return 0.0 - - ratio_of_suspicious_range_usage: float = ( - self._suspicious_successive_range_count * 2 - ) / self._character_count - - return ratio_of_suspicious_range_usage - - -class SuperWeirdWordPlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._word_count: int = 0 - self._bad_word_count: int = 0 - self._foreign_long_count: int = 0 - - self._is_current_word_bad: bool = False - self._foreign_long_watch: bool = False - - self._character_count: int = 0 - self._bad_character_count: int = 0 - - self._buffer: str = "" - self._buffer_accent_count: int = 0 - - def eligible(self, character: str) -> bool: - return True - - def feed(self, character: str) -> None: - if character.isalpha(): - self._buffer += character - if is_accentuated(character): - self._buffer_accent_count += 1 - if ( - self._foreign_long_watch is False - and (is_latin(character) is False or is_accentuated(character)) - and is_cjk(character) is False - and is_hangul(character) is False - and is_katakana(character) is False - and is_hiragana(character) is False - and is_thai(character) is False - ): - self._foreign_long_watch = True - return - if not self._buffer: - return - if ( - character.isspace() or is_punctuation(character) or is_separator(character) - ) and self._buffer: - self._word_count += 1 - buffer_length: int = len(self._buffer) - - self._character_count += buffer_length - - if buffer_length >= 4: - if self._buffer_accent_count / buffer_length > 0.34: - self._is_current_word_bad = True - # Word/Buffer ending with an upper case accentuated letter are so rare, - # that we will consider them all as suspicious. Same weight as foreign_long suspicious. - if ( - is_accentuated(self._buffer[-1]) - and self._buffer[-1].isupper() - and all(_.isupper() for _ in self._buffer) is False - ): - self._foreign_long_count += 1 - self._is_current_word_bad = True - if buffer_length >= 24 and self._foreign_long_watch: - camel_case_dst = [ - i - for c, i in zip(self._buffer, range(0, buffer_length)) - if c.isupper() - ] - probable_camel_cased: bool = False - - if camel_case_dst and (len(camel_case_dst) / buffer_length <= 0.3): - probable_camel_cased = True - - if not probable_camel_cased: - self._foreign_long_count += 1 - self._is_current_word_bad = True - - if self._is_current_word_bad: - self._bad_word_count += 1 - self._bad_character_count += len(self._buffer) - self._is_current_word_bad = False - - self._foreign_long_watch = False - self._buffer = "" - self._buffer_accent_count = 0 - elif ( - character not in {"<", ">", "-", "=", "~", "|", "_"} - and character.isdigit() is False - and is_symbol(character) - ): - self._is_current_word_bad = True - self._buffer += character - - def reset(self) -> None: # pragma: no cover - self._buffer = "" - self._is_current_word_bad = False - self._foreign_long_watch = False - self._bad_word_count = 0 - self._word_count = 0 - self._character_count = 0 - self._bad_character_count = 0 - self._foreign_long_count = 0 - - @property - def ratio(self) -> float: - if self._word_count <= 10 and self._foreign_long_count == 0: - return 0.0 - - return self._bad_character_count / self._character_count - - -class CjkInvalidStopPlugin(MessDetectorPlugin): - """ - GB(Chinese) based encoding often render the stop incorrectly when the content does not fit and - can be easily detected. Searching for the overuse of '丅' and '丄'. - """ - - def __init__(self) -> None: - self._wrong_stop_count: int = 0 - self._cjk_character_count: int = 0 - - def eligible(self, character: str) -> bool: - return True - - def feed(self, character: str) -> None: - if character in {"丅", "丄"}: - self._wrong_stop_count += 1 - return - if is_cjk(character): - self._cjk_character_count += 1 - - def reset(self) -> None: # pragma: no cover - self._wrong_stop_count = 0 - self._cjk_character_count = 0 - - @property - def ratio(self) -> float: - if self._cjk_character_count < 16: - return 0.0 - return self._wrong_stop_count / self._cjk_character_count - - -class ArchaicUpperLowerPlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._buf: bool = False - - self._character_count_since_last_sep: int = 0 - - self._successive_upper_lower_count: int = 0 - self._successive_upper_lower_count_final: int = 0 - - self._character_count: int = 0 - - self._last_alpha_seen: Optional[str] = None - self._current_ascii_only: bool = True - - def eligible(self, character: str) -> bool: - return True - - def feed(self, character: str) -> None: - is_concerned = character.isalpha() and is_case_variable(character) - chunk_sep = is_concerned is False - - if chunk_sep and self._character_count_since_last_sep > 0: - if ( - self._character_count_since_last_sep <= 64 - and character.isdigit() is False - and self._current_ascii_only is False - ): - self._successive_upper_lower_count_final += ( - self._successive_upper_lower_count - ) - - self._successive_upper_lower_count = 0 - self._character_count_since_last_sep = 0 - self._last_alpha_seen = None - self._buf = False - self._character_count += 1 - self._current_ascii_only = True - - return - - if self._current_ascii_only is True and character.isascii() is False: - self._current_ascii_only = False - - if self._last_alpha_seen is not None: - if (character.isupper() and self._last_alpha_seen.islower()) or ( - character.islower() and self._last_alpha_seen.isupper() - ): - if self._buf is True: - self._successive_upper_lower_count += 2 - self._buf = False - else: - self._buf = True - else: - self._buf = False - - self._character_count += 1 - self._character_count_since_last_sep += 1 - self._last_alpha_seen = character - - def reset(self) -> None: # pragma: no cover - self._character_count = 0 - self._character_count_since_last_sep = 0 - self._successive_upper_lower_count = 0 - self._successive_upper_lower_count_final = 0 - self._last_alpha_seen = None - self._buf = False - self._current_ascii_only = True - - @property - def ratio(self) -> float: - if self._character_count == 0: - return 0.0 - - return self._successive_upper_lower_count_final / self._character_count - - -class ArabicIsolatedFormPlugin(MessDetectorPlugin): - def __init__(self) -> None: - self._character_count: int = 0 - self._isolated_form_count: int = 0 - - def reset(self) -> None: # pragma: no cover - self._character_count = 0 - self._isolated_form_count = 0 - - def eligible(self, character: str) -> bool: - return is_arabic(character) - - def feed(self, character: str) -> None: - self._character_count += 1 - - if is_arabic_isolated_form(character): - self._isolated_form_count += 1 - - @property - def ratio(self) -> float: - if self._character_count < 8: - return 0.0 - - isolated_form_usage: float = self._isolated_form_count / self._character_count - - return isolated_form_usage - - -@lru_cache(maxsize=1024) -def is_suspiciously_successive_range( - unicode_range_a: Optional[str], unicode_range_b: Optional[str] -) -> bool: - """ - Determine if two Unicode range seen next to each other can be considered as suspicious. - """ - if unicode_range_a is None or unicode_range_b is None: - return True - - if unicode_range_a == unicode_range_b: - return False - - if "Latin" in unicode_range_a and "Latin" in unicode_range_b: - return False - - if "Emoticons" in unicode_range_a or "Emoticons" in unicode_range_b: - return False - - # Latin characters can be accompanied with a combining diacritical mark - # eg. Vietnamese. - if ("Latin" in unicode_range_a or "Latin" in unicode_range_b) and ( - "Combining" in unicode_range_a or "Combining" in unicode_range_b - ): - return False - - keywords_range_a, keywords_range_b = unicode_range_a.split( - " " - ), unicode_range_b.split(" ") - - for el in keywords_range_a: - if el in UNICODE_SECONDARY_RANGE_KEYWORD: - continue - if el in keywords_range_b: - return False - - # Japanese Exception - range_a_jp_chars, range_b_jp_chars = ( - unicode_range_a - in ( - "Hiragana", - "Katakana", - ), - unicode_range_b in ("Hiragana", "Katakana"), - ) - if (range_a_jp_chars or range_b_jp_chars) and ( - "CJK" in unicode_range_a or "CJK" in unicode_range_b - ): - return False - if range_a_jp_chars and range_b_jp_chars: - return False - - if "Hangul" in unicode_range_a or "Hangul" in unicode_range_b: - if "CJK" in unicode_range_a or "CJK" in unicode_range_b: - return False - if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin": - return False - - # Chinese/Japanese use dedicated range for punctuation and/or separators. - if ("CJK" in unicode_range_a or "CJK" in unicode_range_b) or ( - unicode_range_a in ["Katakana", "Hiragana"] - and unicode_range_b in ["Katakana", "Hiragana"] - ): - if "Punctuation" in unicode_range_a or "Punctuation" in unicode_range_b: - return False - if "Forms" in unicode_range_a or "Forms" in unicode_range_b: - return False - if unicode_range_a == "Basic Latin" or unicode_range_b == "Basic Latin": - return False - - return True - - -@lru_cache(maxsize=2048) -def mess_ratio( - decoded_sequence: str, maximum_threshold: float = 0.2, debug: bool = False -) -> float: - """ - Compute a mess ratio given a decoded bytes sequence. The maximum threshold does stop the computation earlier. - """ - - detectors: List[MessDetectorPlugin] = [ - md_class() for md_class in MessDetectorPlugin.__subclasses__() - ] - - length: int = len(decoded_sequence) + 1 - - mean_mess_ratio: float = 0.0 - - if length < 512: - intermediary_mean_mess_ratio_calc: int = 32 - elif length <= 1024: - intermediary_mean_mess_ratio_calc = 64 - else: - intermediary_mean_mess_ratio_calc = 128 - - for character, index in zip(decoded_sequence + "\n", range(length)): - for detector in detectors: - if detector.eligible(character): - detector.feed(character) - - if ( - index > 0 and index % intermediary_mean_mess_ratio_calc == 0 - ) or index == length - 1: - mean_mess_ratio = sum(dt.ratio for dt in detectors) - - if mean_mess_ratio >= maximum_threshold: - break - - if debug: - logger = getLogger("charset_normalizer") - - logger.log( - TRACE, - "Mess-detector extended-analysis start. " - f"intermediary_mean_mess_ratio_calc={intermediary_mean_mess_ratio_calc} mean_mess_ratio={mean_mess_ratio} " - f"maximum_threshold={maximum_threshold}", - ) - - if len(decoded_sequence) > 16: - logger.log(TRACE, f"Starting with: {decoded_sequence[:16]}") - logger.log(TRACE, f"Ending with: {decoded_sequence[-16::]}") - - for dt in detectors: # pragma: nocover - logger.log(TRACE, f"{dt.__class__}: {dt.ratio}") - - return round(mean_mess_ratio, 3) diff --git a/src/pip/_vendor/charset_normalizer/models.py b/src/pip/_vendor/charset_normalizer/models.py deleted file mode 100644 index 751775d5c33..00000000000 --- a/src/pip/_vendor/charset_normalizer/models.py +++ /dev/null @@ -1,340 +0,0 @@ -from encodings.aliases import aliases -from hashlib import sha256 -from json import dumps -from typing import Any, Dict, Iterator, List, Optional, Tuple, Union - -from .constant import TOO_BIG_SEQUENCE -from .utils import iana_name, is_multi_byte_encoding, unicode_range - - -class CharsetMatch: - def __init__( - self, - payload: bytes, - guessed_encoding: str, - mean_mess_ratio: float, - has_sig_or_bom: bool, - languages: "CoherenceMatches", - decoded_payload: Optional[str] = None, - ): - self._payload: bytes = payload - - self._encoding: str = guessed_encoding - self._mean_mess_ratio: float = mean_mess_ratio - self._languages: CoherenceMatches = languages - self._has_sig_or_bom: bool = has_sig_or_bom - self._unicode_ranges: Optional[List[str]] = None - - self._leaves: List[CharsetMatch] = [] - self._mean_coherence_ratio: float = 0.0 - - self._output_payload: Optional[bytes] = None - self._output_encoding: Optional[str] = None - - self._string: Optional[str] = decoded_payload - - def __eq__(self, other: object) -> bool: - if not isinstance(other, CharsetMatch): - raise TypeError( - "__eq__ cannot be invoked on {} and {}.".format( - str(other.__class__), str(self.__class__) - ) - ) - return self.encoding == other.encoding and self.fingerprint == other.fingerprint - - def __lt__(self, other: object) -> bool: - """ - Implemented to make sorted available upon CharsetMatches items. - """ - if not isinstance(other, CharsetMatch): - raise ValueError - - chaos_difference: float = abs(self.chaos - other.chaos) - coherence_difference: float = abs(self.coherence - other.coherence) - - # Below 1% difference --> Use Coherence - if chaos_difference < 0.01 and coherence_difference > 0.02: - return self.coherence > other.coherence - elif chaos_difference < 0.01 and coherence_difference <= 0.02: - # When having a difficult decision, use the result that decoded as many multi-byte as possible. - # preserve RAM usage! - if len(self._payload) >= TOO_BIG_SEQUENCE: - return self.chaos < other.chaos - return self.multi_byte_usage > other.multi_byte_usage - - return self.chaos < other.chaos - - @property - def multi_byte_usage(self) -> float: - return 1.0 - (len(str(self)) / len(self.raw)) - - def __str__(self) -> str: - # Lazy Str Loading - if self._string is None: - self._string = str(self._payload, self._encoding, "strict") - return self._string - - def __repr__(self) -> str: - return "".format(self.encoding, self.fingerprint) - - def add_submatch(self, other: "CharsetMatch") -> None: - if not isinstance(other, CharsetMatch) or other == self: - raise ValueError( - "Unable to add instance <{}> as a submatch of a CharsetMatch".format( - other.__class__ - ) - ) - - other._string = None # Unload RAM usage; dirty trick. - self._leaves.append(other) - - @property - def encoding(self) -> str: - return self._encoding - - @property - def encoding_aliases(self) -> List[str]: - """ - Encoding name are known by many name, using this could help when searching for IBM855 when it's listed as CP855. - """ - also_known_as: List[str] = [] - for u, p in aliases.items(): - if self.encoding == u: - also_known_as.append(p) - elif self.encoding == p: - also_known_as.append(u) - return also_known_as - - @property - def bom(self) -> bool: - return self._has_sig_or_bom - - @property - def byte_order_mark(self) -> bool: - return self._has_sig_or_bom - - @property - def languages(self) -> List[str]: - """ - Return the complete list of possible languages found in decoded sequence. - Usually not really useful. Returned list may be empty even if 'language' property return something != 'Unknown'. - """ - return [e[0] for e in self._languages] - - @property - def language(self) -> str: - """ - Most probable language found in decoded sequence. If none were detected or inferred, the property will return - "Unknown". - """ - if not self._languages: - # Trying to infer the language based on the given encoding - # Its either English or we should not pronounce ourselves in certain cases. - if "ascii" in self.could_be_from_charset: - return "English" - - # doing it there to avoid circular import - from pip._vendor.charset_normalizer.cd import encoding_languages, mb_encoding_languages - - languages = ( - mb_encoding_languages(self.encoding) - if is_multi_byte_encoding(self.encoding) - else encoding_languages(self.encoding) - ) - - if len(languages) == 0 or "Latin Based" in languages: - return "Unknown" - - return languages[0] - - return self._languages[0][0] - - @property - def chaos(self) -> float: - return self._mean_mess_ratio - - @property - def coherence(self) -> float: - if not self._languages: - return 0.0 - return self._languages[0][1] - - @property - def percent_chaos(self) -> float: - return round(self.chaos * 100, ndigits=3) - - @property - def percent_coherence(self) -> float: - return round(self.coherence * 100, ndigits=3) - - @property - def raw(self) -> bytes: - """ - Original untouched bytes. - """ - return self._payload - - @property - def submatch(self) -> List["CharsetMatch"]: - return self._leaves - - @property - def has_submatch(self) -> bool: - return len(self._leaves) > 0 - - @property - def alphabets(self) -> List[str]: - if self._unicode_ranges is not None: - return self._unicode_ranges - # list detected ranges - detected_ranges: List[Optional[str]] = [ - unicode_range(char) for char in str(self) - ] - # filter and sort - self._unicode_ranges = sorted(list({r for r in detected_ranges if r})) - return self._unicode_ranges - - @property - def could_be_from_charset(self) -> List[str]: - """ - The complete list of encoding that output the exact SAME str result and therefore could be the originating - encoding. - This list does include the encoding available in property 'encoding'. - """ - return [self._encoding] + [m.encoding for m in self._leaves] - - def output(self, encoding: str = "utf_8") -> bytes: - """ - Method to get re-encoded bytes payload using given target encoding. Default to UTF-8. - Any errors will be simply ignored by the encoder NOT replaced. - """ - if self._output_encoding is None or self._output_encoding != encoding: - self._output_encoding = encoding - self._output_payload = str(self).encode(encoding, "replace") - - return self._output_payload # type: ignore - - @property - def fingerprint(self) -> str: - """ - Retrieve the unique SHA256 computed using the transformed (re-encoded) payload. Not the original one. - """ - return sha256(self.output()).hexdigest() - - -class CharsetMatches: - """ - Container with every CharsetMatch items ordered by default from most probable to the less one. - Act like a list(iterable) but does not implements all related methods. - """ - - def __init__(self, results: Optional[List[CharsetMatch]] = None): - self._results: List[CharsetMatch] = sorted(results) if results else [] - - def __iter__(self) -> Iterator[CharsetMatch]: - yield from self._results - - def __getitem__(self, item: Union[int, str]) -> CharsetMatch: - """ - Retrieve a single item either by its position or encoding name (alias may be used here). - Raise KeyError upon invalid index or encoding not present in results. - """ - if isinstance(item, int): - return self._results[item] - if isinstance(item, str): - item = iana_name(item, False) - for result in self._results: - if item in result.could_be_from_charset: - return result - raise KeyError - - def __len__(self) -> int: - return len(self._results) - - def __bool__(self) -> bool: - return len(self._results) > 0 - - def append(self, item: CharsetMatch) -> None: - """ - Insert a single match. Will be inserted accordingly to preserve sort. - Can be inserted as a submatch. - """ - if not isinstance(item, CharsetMatch): - raise ValueError( - "Cannot append instance '{}' to CharsetMatches".format( - str(item.__class__) - ) - ) - # We should disable the submatch factoring when the input file is too heavy (conserve RAM usage) - if len(item.raw) <= TOO_BIG_SEQUENCE: - for match in self._results: - if match.fingerprint == item.fingerprint and match.chaos == item.chaos: - match.add_submatch(item) - return - self._results.append(item) - self._results = sorted(self._results) - - def best(self) -> Optional["CharsetMatch"]: - """ - Simply return the first match. Strict equivalent to matches[0]. - """ - if not self._results: - return None - return self._results[0] - - def first(self) -> Optional["CharsetMatch"]: - """ - Redundant method, call the method best(). Kept for BC reasons. - """ - return self.best() - - -CoherenceMatch = Tuple[str, float] -CoherenceMatches = List[CoherenceMatch] - - -class CliDetectionResult: - def __init__( - self, - path: str, - encoding: Optional[str], - encoding_aliases: List[str], - alternative_encodings: List[str], - language: str, - alphabets: List[str], - has_sig_or_bom: bool, - chaos: float, - coherence: float, - unicode_path: Optional[str], - is_preferred: bool, - ): - self.path: str = path - self.unicode_path: Optional[str] = unicode_path - self.encoding: Optional[str] = encoding - self.encoding_aliases: List[str] = encoding_aliases - self.alternative_encodings: List[str] = alternative_encodings - self.language: str = language - self.alphabets: List[str] = alphabets - self.has_sig_or_bom: bool = has_sig_or_bom - self.chaos: float = chaos - self.coherence: float = coherence - self.is_preferred: bool = is_preferred - - @property - def __dict__(self) -> Dict[str, Any]: # type: ignore - return { - "path": self.path, - "encoding": self.encoding, - "encoding_aliases": self.encoding_aliases, - "alternative_encodings": self.alternative_encodings, - "language": self.language, - "alphabets": self.alphabets, - "has_sig_or_bom": self.has_sig_or_bom, - "chaos": self.chaos, - "coherence": self.coherence, - "unicode_path": self.unicode_path, - "is_preferred": self.is_preferred, - } - - def to_json(self) -> str: - return dumps(self.__dict__, ensure_ascii=True, indent=4) diff --git a/src/pip/_vendor/charset_normalizer/py.typed b/src/pip/_vendor/charset_normalizer/py.typed deleted file mode 100644 index e69de29bb2d..00000000000 diff --git a/src/pip/_vendor/charset_normalizer/utils.py b/src/pip/_vendor/charset_normalizer/utils.py deleted file mode 100644 index e5cbbf4c0dd..00000000000 --- a/src/pip/_vendor/charset_normalizer/utils.py +++ /dev/null @@ -1,421 +0,0 @@ -import importlib -import logging -import unicodedata -from codecs import IncrementalDecoder -from encodings.aliases import aliases -from functools import lru_cache -from re import findall -from typing import Generator, List, Optional, Set, Tuple, Union - -from _multibytecodec import MultibyteIncrementalDecoder - -from .constant import ( - ENCODING_MARKS, - IANA_SUPPORTED_SIMILAR, - RE_POSSIBLE_ENCODING_INDICATION, - UNICODE_RANGES_COMBINED, - UNICODE_SECONDARY_RANGE_KEYWORD, - UTF8_MAXIMAL_ALLOCATION, -) - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_accentuated(character: str) -> bool: - try: - description: str = unicodedata.name(character) - except ValueError: - return False - return ( - "WITH GRAVE" in description - or "WITH ACUTE" in description - or "WITH CEDILLA" in description - or "WITH DIAERESIS" in description - or "WITH CIRCUMFLEX" in description - or "WITH TILDE" in description - or "WITH MACRON" in description - or "WITH RING ABOVE" in description - ) - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def remove_accent(character: str) -> str: - decomposed: str = unicodedata.decomposition(character) - if not decomposed: - return character - - codes: List[str] = decomposed.split(" ") - - return chr(int(codes[0], 16)) - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def unicode_range(character: str) -> Optional[str]: - """ - Retrieve the Unicode range official name from a single character. - """ - character_ord: int = ord(character) - - for range_name, ord_range in UNICODE_RANGES_COMBINED.items(): - if character_ord in ord_range: - return range_name - - return None - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_latin(character: str) -> bool: - try: - description: str = unicodedata.name(character) - except ValueError: - return False - return "LATIN" in description - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_punctuation(character: str) -> bool: - character_category: str = unicodedata.category(character) - - if "P" in character_category: - return True - - character_range: Optional[str] = unicode_range(character) - - if character_range is None: - return False - - return "Punctuation" in character_range - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_symbol(character: str) -> bool: - character_category: str = unicodedata.category(character) - - if "S" in character_category or "N" in character_category: - return True - - character_range: Optional[str] = unicode_range(character) - - if character_range is None: - return False - - return "Forms" in character_range and character_category != "Lo" - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_emoticon(character: str) -> bool: - character_range: Optional[str] = unicode_range(character) - - if character_range is None: - return False - - return "Emoticons" in character_range or "Pictographs" in character_range - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_separator(character: str) -> bool: - if character.isspace() or character in {"｜", "+", "<", ">"}: - return True - - character_category: str = unicodedata.category(character) - - return "Z" in character_category or character_category in {"Po", "Pd", "Pc"} - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_case_variable(character: str) -> bool: - return character.islower() != character.isupper() - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_cjk(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "CJK" in character_name - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_hiragana(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "HIRAGANA" in character_name - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_katakana(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "KATAKANA" in character_name - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_hangul(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "HANGUL" in character_name - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_thai(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "THAI" in character_name - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_arabic(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "ARABIC" in character_name - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_arabic_isolated_form(character: str) -> bool: - try: - character_name = unicodedata.name(character) - except ValueError: - return False - - return "ARABIC" in character_name and "ISOLATED FORM" in character_name - - -@lru_cache(maxsize=len(UNICODE_RANGES_COMBINED)) -def is_unicode_range_secondary(range_name: str) -> bool: - return any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD) - - -@lru_cache(maxsize=UTF8_MAXIMAL_ALLOCATION) -def is_unprintable(character: str) -> bool: - return ( - character.isspace() is False # includes \n \t \r \v - and character.isprintable() is False - and character != "\x1A" # Why? Its the ASCII substitute character. - and character != "\ufeff" # bug discovered in Python, - # Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space. - ) - - -def any_specified_encoding(sequence: bytes, search_zone: int = 8192) -> Optional[str]: - """ - Extract using ASCII-only decoder any specified encoding in the first n-bytes. - """ - if not isinstance(sequence, bytes): - raise TypeError - - seq_len: int = len(sequence) - - results: List[str] = findall( - RE_POSSIBLE_ENCODING_INDICATION, - sequence[: min(seq_len, search_zone)].decode("ascii", errors="ignore"), - ) - - if len(results) == 0: - return None - - for specified_encoding in results: - specified_encoding = specified_encoding.lower().replace("-", "_") - - encoding_alias: str - encoding_iana: str - - for encoding_alias, encoding_iana in aliases.items(): - if encoding_alias == specified_encoding: - return encoding_iana - if encoding_iana == specified_encoding: - return encoding_iana - - return None - - -@lru_cache(maxsize=128) -def is_multi_byte_encoding(name: str) -> bool: - """ - Verify is a specific encoding is a multi byte one based on it IANA name - """ - return name in { - "utf_8", - "utf_8_sig", - "utf_16", - "utf_16_be", - "utf_16_le", - "utf_32", - "utf_32_le", - "utf_32_be", - "utf_7", - } or issubclass( - importlib.import_module("encodings.{}".format(name)).IncrementalDecoder, - MultibyteIncrementalDecoder, - ) - - -def identify_sig_or_bom(sequence: bytes) -> Tuple[Optional[str], bytes]: - """ - Identify and extract SIG/BOM in given sequence. - """ - - for iana_encoding in ENCODING_MARKS: - marks: Union[bytes, List[bytes]] = ENCODING_MARKS[iana_encoding] - - if isinstance(marks, bytes): - marks = [marks] - - for mark in marks: - if sequence.startswith(mark): - return iana_encoding, mark - - return None, b"" - - -def should_strip_sig_or_bom(iana_encoding: str) -> bool: - return iana_encoding not in {"utf_16", "utf_32"} - - -def iana_name(cp_name: str, strict: bool = True) -> str: - cp_name = cp_name.lower().replace("-", "_") - - encoding_alias: str - encoding_iana: str - - for encoding_alias, encoding_iana in aliases.items(): - if cp_name in [encoding_alias, encoding_iana]: - return encoding_iana - - if strict: - raise ValueError("Unable to retrieve IANA for '{}'".format(cp_name)) - - return cp_name - - -def range_scan(decoded_sequence: str) -> List[str]: - ranges: Set[str] = set() - - for character in decoded_sequence: - character_range: Optional[str] = unicode_range(character) - - if character_range is None: - continue - - ranges.add(character_range) - - return list(ranges) - - -def cp_similarity(iana_name_a: str, iana_name_b: str) -> float: - if is_multi_byte_encoding(iana_name_a) or is_multi_byte_encoding(iana_name_b): - return 0.0 - - decoder_a = importlib.import_module( - "encodings.{}".format(iana_name_a) - ).IncrementalDecoder - decoder_b = importlib.import_module( - "encodings.{}".format(iana_name_b) - ).IncrementalDecoder - - id_a: IncrementalDecoder = decoder_a(errors="ignore") - id_b: IncrementalDecoder = decoder_b(errors="ignore") - - character_match_count: int = 0 - - for i in range(255): - to_be_decoded: bytes = bytes([i]) - if id_a.decode(to_be_decoded) == id_b.decode(to_be_decoded): - character_match_count += 1 - - return character_match_count / 254 - - -def is_cp_similar(iana_name_a: str, iana_name_b: str) -> bool: - """ - Determine if two code page are at least 80% similar. IANA_SUPPORTED_SIMILAR dict was generated using - the function cp_similarity. - """ - return ( - iana_name_a in IANA_SUPPORTED_SIMILAR - and iana_name_b in IANA_SUPPORTED_SIMILAR[iana_name_a] - ) - - -def set_logging_handler( - name: str = "charset_normalizer", - level: int = logging.INFO, - format_string: str = "%(asctime)s | %(levelname)s | %(message)s", -) -> None: - logger = logging.getLogger(name) - logger.setLevel(level) - - handler = logging.StreamHandler() - handler.setFormatter(logging.Formatter(format_string)) - logger.addHandler(handler) - - -def cut_sequence_chunks( - sequences: bytes, - encoding_iana: str, - offsets: range, - chunk_size: int, - bom_or_sig_available: bool, - strip_sig_or_bom: bool, - sig_payload: bytes, - is_multi_byte_decoder: bool, - decoded_payload: Optional[str] = None, -) -> Generator[str, None, None]: - if decoded_payload and is_multi_byte_decoder is False: - for i in offsets: - chunk = decoded_payload[i : i + chunk_size] - if not chunk: - break - yield chunk - else: - for i in offsets: - chunk_end = i + chunk_size - if chunk_end > len(sequences) + 8: - continue - - cut_sequence = sequences[i : i + chunk_size] - - if bom_or_sig_available and strip_sig_or_bom is False: - cut_sequence = sig_payload + cut_sequence - - chunk = cut_sequence.decode( - encoding_iana, - errors="ignore" if is_multi_byte_decoder else "strict", - ) - - # multi-byte bad cutting detector and adjustment - # not the cleanest way to perform that fix but clever enough for now. - if is_multi_byte_decoder and i > 0: - chunk_partial_size_chk: int = min(chunk_size, 16) - - if ( - decoded_payload - and chunk[:chunk_partial_size_chk] not in decoded_payload - ): - for j in range(i, i - 4, -1): - cut_sequence = sequences[j:chunk_end] - - if bom_or_sig_available and strip_sig_or_bom is False: - cut_sequence = sig_payload + cut_sequence - - chunk = cut_sequence.decode(encoding_iana, errors="ignore") - - if chunk[:chunk_partial_size_chk] in decoded_payload: - break - - yield chunk diff --git a/src/pip/_vendor/charset_normalizer/version.py b/src/pip/_vendor/charset_normalizer/version.py deleted file mode 100644 index 5a4da4ff49b..00000000000 --- a/src/pip/_vendor/charset_normalizer/version.py +++ /dev/null @@ -1,6 +0,0 @@ -""" -Expose version -""" - -__version__ = "3.3.2" -VERSION = __version__.split(".") diff --git a/src/pip/_vendor/requests/__init__.py b/src/pip/_vendor/requests/__init__.py index 9d4e72c60d4..04230fc8d9a 100644 --- a/src/pip/_vendor/requests/__init__.py +++ b/src/pip/_vendor/requests/__init__.py @@ -44,11 +44,7 @@ from .exceptions import RequestsDependencyWarning -try: - from pip._vendor.charset_normalizer import __version__ as charset_normalizer_version -except ImportError: - charset_normalizer_version = None - +charset_normalizer_version = None chardet_version = None @@ -80,7 +76,8 @@ def check_compatibility(urllib3_version, chardet_version, charset_normalizer_ver # charset_normalizer >= 2.0.0 < 4.0.0 assert (2, 0, 0) <= (major, minor, patch) < (4, 0, 0) else: - raise Exception("You need either charset_normalizer or chardet installed") + # pip does not need or use character detection + pass def _check_cryptography(cryptography_version): diff --git a/src/pip/_vendor/requests/__version__.py b/src/pip/_vendor/requests/__version__.py index 5063c3f8ee7..1ac168734ee 100644 --- a/src/pip/_vendor/requests/__version__.py +++ b/src/pip/_vendor/requests/__version__.py @@ -5,10 +5,10 @@ __title__ = "requests" __description__ = "Python HTTP for Humans." __url__ = "https://requests.readthedocs.io" -__version__ = "2.31.0" -__build__ = 0x023100 +__version__ = "2.32.0" +__build__ = 0x023200 __author__ = "Kenneth Reitz" __author_email__ = "me@kennethreitz.org" -__license__ = "Apache 2.0" +__license__ = "Apache-2.0" __copyright__ = "Copyright Kenneth Reitz" __cake__ = "\u2728 \U0001f370 \u2728" diff --git a/src/pip/_vendor/requests/adapters.py b/src/pip/_vendor/requests/adapters.py index 10c176790b6..4d9d9c63067 100644 --- a/src/pip/_vendor/requests/adapters.py +++ b/src/pip/_vendor/requests/adapters.py @@ -8,6 +8,7 @@ import os.path import socket # noqa: F401 +import typing from pip._vendor.urllib3.exceptions import ClosedPoolError, ConnectTimeoutError from pip._vendor.urllib3.exceptions import HTTPError as _HTTPError @@ -25,6 +26,7 @@ from pip._vendor.urllib3.util import Timeout as TimeoutSauce from pip._vendor.urllib3.util import parse_url from pip._vendor.urllib3.util.retry import Retry +from pip._vendor.urllib3.util.ssl_ import create_urllib3_context from .auth import _basic_auth_str from .compat import basestring, urlparse @@ -61,11 +63,57 @@ def SOCKSProxyManager(*args, **kwargs): raise InvalidSchema("Missing dependencies for SOCKS support.") +if typing.TYPE_CHECKING: + from .models import PreparedRequest + + DEFAULT_POOLBLOCK = False DEFAULT_POOLSIZE = 10 DEFAULT_RETRIES = 0 DEFAULT_POOL_TIMEOUT = None +_preloaded_ssl_context = create_urllib3_context() +_preloaded_ssl_context.load_verify_locations( + extract_zipped_paths(DEFAULT_CA_BUNDLE_PATH) +) + + +def _urllib3_request_context( + request: "PreparedRequest", + verify: "bool | str | None", + client_cert: "typing.Tuple[str, str] | str | None", +) -> "(typing.Dict[str, typing.Any], typing.Dict[str, typing.Any])": + host_params = {} + pool_kwargs = {} + parsed_request_url = urlparse(request.url) + scheme = parsed_request_url.scheme.lower() + port = parsed_request_url.port + cert_reqs = "CERT_REQUIRED" + if verify is False: + cert_reqs = "CERT_NONE" + elif verify is True: + pool_kwargs["ssl_context"] = _preloaded_ssl_context + elif isinstance(verify, str): + if not os.path.isdir(verify): + pool_kwargs["ca_certs"] = verify + else: + pool_kwargs["ca_cert_dir"] = verify + pool_kwargs["cert_reqs"] = cert_reqs + if client_cert is not None: + if isinstance(client_cert, tuple) and len(client_cert) == 2: + pool_kwargs["cert_file"] = client_cert[0] + pool_kwargs["key_file"] = client_cert[1] + else: + # According to our docs, we allow users to specify just the client + # cert path + pool_kwargs["cert_file"] = client_cert + host_params = { + "scheme": scheme, + "host": parsed_request_url.hostname, + "port": port, + } + return host_params, pool_kwargs + class BaseAdapter: """The Base Transport Adapter""" @@ -247,28 +295,26 @@ def cert_verify(self, conn, url, verify, cert): :param cert: The SSL certificate to verify. """ if url.lower().startswith("https") and verify: + conn.cert_reqs = "CERT_REQUIRED" - cert_loc = None - - # Allow self-specified cert location. + # Only load the CA certificates if 'verify' is a string indicating the CA bundle to use. + # Otherwise, if verify is a boolean, we don't load anything since + # the connection will be using a context with the default certificates already loaded, + # and this avoids a call to the slow load_verify_locations() if verify is not True: + # `verify` must be a str with a path then cert_loc = verify - if not cert_loc: - cert_loc = extract_zipped_paths(DEFAULT_CA_BUNDLE_PATH) + if not os.path.exists(cert_loc): + raise OSError( + f"Could not find a suitable TLS CA certificate bundle, " + f"invalid path: {cert_loc}" + ) - if not cert_loc or not os.path.exists(cert_loc): - raise OSError( - f"Could not find a suitable TLS CA certificate bundle, " - f"invalid path: {cert_loc}" - ) - - conn.cert_reqs = "CERT_REQUIRED" - - if not os.path.isdir(cert_loc): - conn.ca_certs = cert_loc - else: - conn.ca_cert_dir = cert_loc + if not os.path.isdir(cert_loc): + conn.ca_certs = cert_loc + else: + conn.ca_cert_dir = cert_loc else: conn.cert_reqs = "CERT_NONE" conn.ca_certs = None @@ -328,6 +374,35 @@ def build_response(self, req, resp): return response + def _get_connection(self, request, verify, proxies=None, cert=None): + # Replace the existing get_connection without breaking things and + # ensure that TLS settings are considered when we interact with + # urllib3 HTTP Pools + proxy = select_proxy(request.url, proxies) + try: + host_params, pool_kwargs = _urllib3_request_context(request, verify, cert) + except ValueError as e: + raise InvalidURL(e, request=request) + if proxy: + proxy = prepend_scheme_if_needed(proxy, "http") + proxy_url = parse_url(proxy) + if not proxy_url.host: + raise InvalidProxyURL( + "Please check proxy URL. It is malformed " + "and could be missing the host." + ) + proxy_manager = self.proxy_manager_for(proxy) + conn = proxy_manager.connection_from_host( + **host_params, pool_kwargs=pool_kwargs + ) + else: + # Only scheme should be lower case + conn = self.poolmanager.connection_from_host( + **host_params, pool_kwargs=pool_kwargs + ) + + return conn + def get_connection(self, url, proxies=None): """Returns a urllib3 connection for the given URL. This should not be called from user code, and is only exposed for use when subclassing the @@ -391,6 +466,9 @@ def request_url(self, request, proxies): using_socks_proxy = proxy_scheme.startswith("socks") url = request.path_url + if url.startswith("//"): # Don't confuse urllib3 + url = f"/{url.lstrip('/')}" + if is_proxied_http_request and not using_socks_proxy: url = urldefragauth(request.url) @@ -451,7 +529,7 @@ def send( """ try: - conn = self.get_connection(request.url, proxies) + conn = self._get_connection(request, verify, proxies=proxies, cert=cert) except LocationValueError as e: raise InvalidURL(e, request=request) diff --git a/src/pip/_vendor/requests/api.py b/src/pip/_vendor/requests/api.py index cd0b3eeac3e..5960744552e 100644 --- a/src/pip/_vendor/requests/api.py +++ b/src/pip/_vendor/requests/api.py @@ -25,7 +25,7 @@ def request(method, url, **kwargs): :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload. ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')`` - or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string + or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content_type'`` is a string defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers to add for the file. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. diff --git a/src/pip/_vendor/requests/auth.py b/src/pip/_vendor/requests/auth.py index 9733686ddb3..4a7ce6dc146 100644 --- a/src/pip/_vendor/requests/auth.py +++ b/src/pip/_vendor/requests/auth.py @@ -258,7 +258,6 @@ def handle_401(self, r, **kwargs): s_auth = r.headers.get("www-authenticate", "") if "digest" in s_auth.lower() and self._thread_local.num_401_calls < 2: - self._thread_local.num_401_calls += 1 pat = re.compile(r"digest ", flags=re.IGNORECASE) self._thread_local.chal = parse_dict_header(pat.sub("", s_auth, count=1)) diff --git a/src/pip/_vendor/requests/compat.py b/src/pip/_vendor/requests/compat.py index 33525c52f0c..7081da756ac 100644 --- a/src/pip/_vendor/requests/compat.py +++ b/src/pip/_vendor/requests/compat.py @@ -7,10 +7,21 @@ compatibility until the next major version. """ -from pip._vendor import charset_normalizer as chardet - import sys +# ------------------- +# Character Detection +# ------------------- + + +def _resolve_char_detection(): + """Find supported character detection libraries.""" + chardet = None + return chardet + + +chardet = _resolve_char_detection() + # ------- # Pythons # ------- diff --git a/src/pip/_vendor/requests/cookies.py b/src/pip/_vendor/requests/cookies.py index bf54ab237e4..f69d0cda9e1 100644 --- a/src/pip/_vendor/requests/cookies.py +++ b/src/pip/_vendor/requests/cookies.py @@ -2,7 +2,7 @@ requests.cookies ~~~~~~~~~~~~~~~~ -Compatibility code to be able to use `cookielib.CookieJar` with requests. +Compatibility code to be able to use `http.cookiejar.CookieJar` with requests. requests.utils imports from here, so be careful with imports. """ @@ -23,7 +23,7 @@ class MockRequest: """Wraps a `requests.Request` to mimic a `urllib2.Request`. - The code in `cookielib.CookieJar` expects this interface in order to correctly + The code in `http.cookiejar.CookieJar` expects this interface in order to correctly manage cookie policies, i.e., determine whether a cookie can be set, given the domains of the request and the cookie. @@ -76,7 +76,7 @@ def get_header(self, name, default=None): return self._r.headers.get(name, self._new_headers.get(name, default)) def add_header(self, key, val): - """cookielib has no legitimate use for this method; add it back if you find one.""" + """cookiejar has no legitimate use for this method; add it back if you find one.""" raise NotImplementedError( "Cookie headers should be added with add_unredirected_header()" ) @@ -104,11 +104,11 @@ class MockResponse: """Wraps a `httplib.HTTPMessage` to mimic a `urllib.addinfourl`. ...what? Basically, expose the parsed HTTP headers from the server response - the way `cookielib` expects to see them. + the way `http.cookiejar` expects to see them. """ def __init__(self, headers): - """Make a MockResponse for `cookielib` to read. + """Make a MockResponse for `cookiejar` to read. :param headers: a httplib.HTTPMessage or analogous carrying the headers """ @@ -124,7 +124,7 @@ def getheaders(self, name): def extract_cookies_to_jar(jar, request, response): """Extract the cookies from the response into a CookieJar. - :param jar: cookielib.CookieJar (not necessarily a RequestsCookieJar) + :param jar: http.cookiejar.CookieJar (not necessarily a RequestsCookieJar) :param request: our own requests.Request object :param response: urllib3.HTTPResponse object """ @@ -174,7 +174,7 @@ class CookieConflictError(RuntimeError): class RequestsCookieJar(cookielib.CookieJar, MutableMapping): - """Compatibility class; is a cookielib.CookieJar, but exposes a dict + """Compatibility class; is a http.cookiejar.CookieJar, but exposes a dict interface. This is the CookieJar we create by default for requests and sessions that @@ -341,7 +341,7 @@ def __setitem__(self, name, value): self.set(name, value) def __delitem__(self, name): - """Deletes a cookie given a name. Wraps ``cookielib.CookieJar``'s + """Deletes a cookie given a name. Wraps ``http.cookiejar.CookieJar``'s ``remove_cookie_by_name()``. """ remove_cookie_by_name(self, name) diff --git a/src/pip/_vendor/requests/exceptions.py b/src/pip/_vendor/requests/exceptions.py index 168d07390df..7f3660f00d9 100644 --- a/src/pip/_vendor/requests/exceptions.py +++ b/src/pip/_vendor/requests/exceptions.py @@ -41,6 +41,16 @@ def __init__(self, *args, **kwargs): CompatJSONDecodeError.__init__(self, *args) InvalidJSONError.__init__(self, *self.args, **kwargs) + def __reduce__(self): + """ + The __reduce__ method called when pickling the object must + be the one from the JSONDecodeError (be it json/simplejson) + as it expects all the arguments for instantiation, not just + one like the IOError, and the MRO would by default call the + __reduce__ method from the IOError due to the inheritance order. + """ + return CompatJSONDecodeError.__reduce__(self) + class HTTPError(RequestException): """An HTTP error occurred.""" diff --git a/src/pip/_vendor/requests/help.py b/src/pip/_vendor/requests/help.py index 17ca75eda7d..ddbb6150d64 100644 --- a/src/pip/_vendor/requests/help.py +++ b/src/pip/_vendor/requests/help.py @@ -10,11 +10,7 @@ from . import __version__ as requests_version -try: - from pip._vendor import charset_normalizer -except ImportError: - charset_normalizer = None - +charset_normalizer = None chardet = None try: diff --git a/src/pip/_vendor/requests/models.py b/src/pip/_vendor/requests/models.py index 76e6f199c00..85a008cfb56 100644 --- a/src/pip/_vendor/requests/models.py +++ b/src/pip/_vendor/requests/models.py @@ -170,7 +170,7 @@ def _encode_files(files, data): ) ) - for (k, v) in files: + for k, v in files: # support for explicit filename ft = None fh = None @@ -268,7 +268,6 @@ def __init__( hooks=None, json=None, ): - # Default empty dicts for dict params. data = [] if data is None else data files = [] if files is None else files @@ -277,7 +276,7 @@ def __init__( hooks = {} if hooks is None else hooks self.hooks = default_hooks() - for (k, v) in list(hooks.items()): + for k, v in list(hooks.items()): self.register_hook(event=k, hook=v) self.method = method @@ -790,7 +789,12 @@ def next(self): @property def apparent_encoding(self): """The apparent encoding, provided by the charset_normalizer or chardet libraries.""" - return chardet.detect(self.content)["encoding"] + if chardet is not None: + return chardet.detect(self.content)["encoding"] + else: + # If no character detection library is available, we'll fall back + # to a standard Python utf-8 str. + return "utf-8" def iter_content(self, chunk_size=1, decode_unicode=False): """Iterates over the response data. When stream=True is set on the @@ -865,7 +869,6 @@ def iter_lines( for chunk in self.iter_content( chunk_size=chunk_size, decode_unicode=decode_unicode ): - if pending is not None: chunk = pending + chunk diff --git a/src/pip/_vendor/requests/packages.py b/src/pip/_vendor/requests/packages.py index 45787bfbe54..200c38287f4 100644 --- a/src/pip/_vendor/requests/packages.py +++ b/src/pip/_vendor/requests/packages.py @@ -1,9 +1,11 @@ import sys +from .compat import chardet + # This code exists for backwards compatibility reasons. # I don't like it either. Just look the other way. :) -for package in ('urllib3', 'idna', 'charset_normalizer'): +for package in ("urllib3", "idna"): vendored_package = "pip._vendor." + package locals()[package] = __import__(vendored_package) # This traversal is apparently necessary such that the identities are @@ -13,4 +15,11 @@ unprefixed_mod = mod[len("pip._vendor."):] sys.modules['pip._vendor.requests.packages.' + unprefixed_mod] = sys.modules[mod] -# Kinda cool, though, right? +if chardet is not None: + target = chardet.__name__ + for mod in list(sys.modules): + if mod == target or mod.startswith(f"{target}."): + imported_mod = sys.modules[mod] + sys.modules[f"requests.packages.{mod}"] = imported_mod + mod = mod.replace(target, "chardet") + sys.modules[f"requests.packages.{mod}"] = imported_mod diff --git a/src/pip/_vendor/requests/sessions.py b/src/pip/_vendor/requests/sessions.py index dbcf2a7b0ee..b387bc36df7 100644 --- a/src/pip/_vendor/requests/sessions.py +++ b/src/pip/_vendor/requests/sessions.py @@ -262,7 +262,6 @@ def resolve_redirects( if yield_requests: yield req else: - resp = self.send( req, stream=stream, @@ -326,7 +325,7 @@ def rebuild_proxies(self, prepared_request, proxies): # urllib3 handles proxy authorization for us in the standard adapter. # Avoid appending this to TLS tunneled requests where it may be leaked. - if not scheme.startswith('https') and username and password: + if not scheme.startswith("https") and username and password: headers["Proxy-Authorization"] = _basic_auth_str(username, password) return new_proxies @@ -389,7 +388,6 @@ class Session(SessionRedirectMixin): ] def __init__(self): - #: A case-insensitive dictionary of headers to be sent on each #: :class:`Request ` sent from this #: :class:`Session `. @@ -545,6 +543,8 @@ def request( :type allow_redirects: bool :param proxies: (optional) Dictionary mapping protocol or protocol and hostname to the URL of the proxy. + :param hooks: (optional) Dictionary mapping hook name to one event or + list of events, event must be callable. :param stream: (optional) whether to immediately download the response content. Defaults to ``False``. :param verify: (optional) Either a boolean, in which case it controls whether we verify @@ -711,7 +711,6 @@ def send(self, request, **kwargs): # Persist cookies if r.history: - # If the hooks create history then we want those cookies too for resp in r.history: extract_cookies_to_jar(self.cookies, resp.request, resp.raw) @@ -759,7 +758,7 @@ def merge_environment_settings(self, url, proxies, stream, verify, cert): # Set environment's proxies. no_proxy = proxies.get("no_proxy") if proxies is not None else None env_proxies = get_environ_proxies(url, no_proxy=no_proxy) - for (k, v) in env_proxies.items(): + for k, v in env_proxies.items(): proxies.setdefault(k, v) # Look for requests environment configuration @@ -785,8 +784,7 @@ def get_adapter(self, url): :rtype: requests.adapters.BaseAdapter """ - for (prefix, adapter) in self.adapters.items(): - + for prefix, adapter in self.adapters.items(): if url.lower().startswith(prefix.lower()): return adapter diff --git a/src/pip/_vendor/requests/status_codes.py b/src/pip/_vendor/requests/status_codes.py index 4bd072be976..c7945a2f068 100644 --- a/src/pip/_vendor/requests/status_codes.py +++ b/src/pip/_vendor/requests/status_codes.py @@ -24,7 +24,7 @@ # Informational. 100: ("continue",), 101: ("switching_protocols",), - 102: ("processing",), + 102: ("processing", "early-hints"), 103: ("checkpoint",), 122: ("uri_too_long", "request_uri_too_long"), 200: ("ok", "okay", "all_ok", "all_okay", "all_good", "\\o/", "✓"), @@ -65,8 +65,8 @@ 410: ("gone",), 411: ("length_required",), 412: ("precondition_failed", "precondition"), - 413: ("request_entity_too_large",), - 414: ("request_uri_too_large",), + 413: ("request_entity_too_large", "content_too_large"), + 414: ("request_uri_too_large", "uri_too_long"), 415: ("unsupported_media_type", "unsupported_media", "media_type"), 416: ( "requested_range_not_satisfiable", @@ -76,10 +76,10 @@ 417: ("expectation_failed",), 418: ("im_a_teapot", "teapot", "i_am_a_teapot"), 421: ("misdirected_request",), - 422: ("unprocessable_entity", "unprocessable"), + 422: ("unprocessable_entity", "unprocessable", "unprocessable_content"), 423: ("locked",), 424: ("failed_dependency", "dependency"), - 425: ("unordered_collection", "unordered"), + 425: ("unordered_collection", "unordered", "too_early"), 426: ("upgrade_required", "upgrade"), 428: ("precondition_required", "precondition"), 429: ("too_many_requests", "too_many"), diff --git a/src/pip/_vendor/requests/utils.py b/src/pip/_vendor/requests/utils.py index 36607eda2ec..a35ce478667 100644 --- a/src/pip/_vendor/requests/utils.py +++ b/src/pip/_vendor/requests/utils.py @@ -97,6 +97,8 @@ def proxy_bypass_registry(host): # '' string by the localhost entry and the corresponding # canonical entry. proxyOverride = proxyOverride.split(";") + # filter out empty strings to avoid re.match return true in the following code. + proxyOverride = filter(None, proxyOverride) # now check if we match one of the registry values. for test in proxyOverride: if test == "": @@ -134,6 +136,9 @@ def super_len(o): total_length = None current_position = 0 + if isinstance(o, str): + o = o.encode("utf-8") + if hasattr(o, "__len__"): total_length = len(o) @@ -466,11 +471,7 @@ def dict_from_cookiejar(cj): :rtype: dict """ - cookie_dict = {} - - for cookie in cj: - cookie_dict[cookie.name] = cookie.value - + cookie_dict = {cookie.name: cookie.value for cookie in cj} return cookie_dict @@ -767,6 +768,7 @@ def should_bypass_proxies(url, no_proxy): :rtype: bool """ + # Prioritize lowercase environment variables over uppercase # to keep a consistent behaviour with other http projects (curl, wget). def get_proxy(key): @@ -862,7 +864,7 @@ def select_proxy(url, proxies): def resolve_proxies(request, proxies, trust_env=True): """This method takes proxy information from a request and configuration input to resolve a mapping of target proxies. This will consider settings - such a NO_PROXY to strip proxy configurations. + such as NO_PROXY to strip proxy configurations. :param request: Request or PreparedRequest :param proxies: A dictionary of schemes or schemes and hosts to proxy URLs @@ -1054,7 +1056,7 @@ def _validate_header_part(header, header_part, header_validator_index): if not validator.match(header_part): header_kind = "name" if header_validator_index == 0 else "value" raise InvalidHeader( - f"Invalid leading whitespace, reserved character(s), or return" + f"Invalid leading whitespace, reserved character(s), or return " f"character(s) in header {header_kind}: {header_part!r}" ) diff --git a/src/pip/_vendor/vendor.txt b/src/pip/_vendor/vendor.txt index 2643da721fc..00d81549cb6 100644 --- a/src/pip/_vendor/vendor.txt +++ b/src/pip/_vendor/vendor.txt @@ -5,9 +5,8 @@ msgpack==1.0.8 packaging==24.0 platformdirs==4.2.1 pyproject-hooks==1.0.0 -requests==2.31.0 +requests==2.32.0 certifi==2024.2.2 - charset-normalizer==3.3.2 idna==3.7 urllib3==1.26.18 rich==13.7.1 diff --git a/tools/vendoring/patches/requests.patch b/tools/vendoring/patches/requests.patch index d02eb31fbcf..c205250eeb1 100644 --- a/tools/vendoring/patches/requests.patch +++ b/tools/vendoring/patches/requests.patch @@ -1,42 +1,3 @@ -diff --git a/src/pip/_vendor/requests/packages.py b/src/pip/_vendor/requests/packages.py -index 77c45c9e..45787bfb 100644 ---- a/src/pip/_vendor/requests/packages.py -+++ b/src/pip/_vendor/requests/packages.py -@@ -1,28 +1,16 @@ - import sys - --try: -- import chardet --except ImportError: -- import warnings -- -- import charset_normalizer as chardet -- -- warnings.filterwarnings("ignore", "Trying to detect", module="charset_normalizer") -- - # This code exists for backwards compatibility reasons. - # I don't like it either. Just look the other way. :) - --for package in ("urllib3", "idna"): -- locals()[package] = __import__(package) -+for package in ('urllib3', 'idna', 'charset_normalizer'): -+ vendored_package = "pip._vendor." + package -+ locals()[package] = __import__(vendored_package) - # This traversal is apparently necessary such that the identities are - # preserved (requests.packages.urllib3.* is urllib3.*) - for mod in list(sys.modules): -- if mod == package or mod.startswith(f"{package}."): -- sys.modules[f"requests.packages.{mod}"] = sys.modules[mod] -+ if mod == vendored_package or mod.startswith(vendored_package + '.'): -+ unprefixed_mod = mod[len("pip._vendor."):] -+ sys.modules['pip._vendor.requests.packages.' + unprefixed_mod] = sys.modules[mod] - --target = chardet.__name__ --for mod in list(sys.modules): -- if mod == target or mod.startswith(f"{target}."): -- target = target.replace(target, "chardet") -- sys.modules[f"requests.packages.{target}"] = sys.modules[mod] - # Kinda cool, though, right? diff --git a/src/pip/_vendor/requests/__init__.py b/src/pip/_vendor/requests/__init__.py index 300a16c5..a66f6024 100644 --- a/src/pip/_vendor/requests/__init__.py @@ -53,6 +14,20 @@ index 300a16c5..a66f6024 100644 def check_compatibility(urllib3_version, chardet_version, charset_normalizer_version): +@@ -76,11 +76,8 @@ def check_compatibility(urllib3_version, chardet_version, charset_normalizer_ver + # charset_normalizer >= 2.0.0 < 4.0.0 + assert (2, 0, 0) <= (major, minor, patch) < (4, 0, 0) + else: +- warnings.warn( +- "Unable to find acceptable character detection dependency " +- "(chardet or charset_normalizer).", +- RequestsDependencyWarning, +- ) ++ # pip does not need or use character detection ++ pass + + + def _check_cryptography(cryptography_version): @@ -118,6 +115,11 @@ except (AssertionError, ValueError): # if the standard library doesn't support SNI or the # 'ssl' library isn't available. @@ -69,18 +44,6 @@ diff --git a/src/pip/_vendor/requests/compat.py b/src/pip/_vendor/requests/compa index 6776163c..7819bb99 100644 --- a/src/pip/_vendor/requests/compat.py +++ b/src/pip/_vendor/requests/compat.py -@@ -7,10 +7,7 @@ between Python 2 and Python 3. It remains for backwards - compatibility until the next major version. - """ - --try: -- import chardet --except ImportError: -- import charset_normalizer as chardet -+import charset_normalizer as chardet - - import sys - @@ -27,19 +24,10 @@ is_py2 = _ver[0] == 2 #: Python 3.x? is_py3 = _ver[0] == 3 @@ -141,3 +104,82 @@ index be422c3e..3daf06f6 100644 if __name__ == "__main__": print(where()) +diff --git a/src/pip/_vendor/requests/__init__.py b/src/pip/_vendor/requests/__init__.py +index 9d4e72c60..04230fc8d 100644 +--- a/src/pip/_vendor/requests/__init__.py ++++ b/src/pip/_vendor/requests/__init__.py +@@ -44,11 +44,7 @@ from pip._vendor import urllib3 + + from .exceptions import RequestsDependencyWarning + +-try: +- from charset_normalizer import __version__ as charset_normalizer_version +-except ImportError: +- charset_normalizer_version = None +- ++charset_normalizer_version = None + chardet_version = None + + +diff --git a/src/pip/_vendor/requests/help.py b/src/pip/_vendor/requests/help.py +index 17ca75eda..ddbb6150d 100644 +--- a/src/pip/_vendor/requests/help.py ++++ b/src/pip/_vendor/requests/help.py +@@ -10,11 +10,7 @@ from pip._vendor import urllib3 + + from . import __version__ as requests_version + +-try: +- import charset_normalizer +-except ImportError: +- charset_normalizer = None +- ++charset_normalizer = None + chardet = None + + try: +--- a/src/pip/_vendor/requests/compat.py ++++ b/src/pip/_vendor/requests/compat.py +@@ -7,7 +7,6 @@ between Python 2 and Python 3. It remains for backwards + compatibility until the next major version. + """ + +-import importlib + import sys + + # ------------------- +@@ -18,12 +17,6 @@ import sys + def _resolve_char_detection(): + """Find supported character detection libraries.""" + chardet = None +- for lib in ("chardet", "charset_normalizer"): +- if chardet is None: +- try: +- chardet = importlib.import_module(lib) +- except ImportError: +- pass + return chardet + + +diff --git a/src/pip/_vendor/requests/packages.py b/src/pip/_vendor/requests/packages.py +index 5ab3d8e25..200c38287 100644 +--- a/src/pip/_vendor/requests/packages.py ++++ b/src/pip/_vendor/requests/packages.py +@@ -6,12 +6,14 @@ from .compat import chardet + # I don't like it either. Just look the other way. :) + + for package in ("urllib3", "idna"): +- locals()[package] = __import__(package) ++ vendored_package = "pip._vendor." + package ++ locals()[package] = __import__(vendored_package) + # This traversal is apparently necessary such that the identities are + # preserved (requests.packages.urllib3.* is urllib3.*) + for mod in list(sys.modules): +- if mod == package or mod.startswith(f"{package}."): +- sys.modules[f"requests.packages.{mod}"] = sys.modules[mod] ++ if mod == vendored_package or mod.startswith(vendored_package + '.'): ++ unprefixed_mod = mod[len("pip._vendor."):] ++ sys.modules['pip._vendor.requests.packages.' + unprefixed_mod] = sys.modules[mod] + + if chardet is not None: + target = chardet.__name__