o #j8@sUdZddlmZddlZddlmZddlmZddlm Z ide dd hd e d d hd e d hde dhde dhde ddhde ddhde dhde dhde dhde dhde dhde hd d!e d"d#hd$e d%hd&e d hd'e d(he d)he d*he d+he d,he d-he d.he d/d0he d1he d1he d2d3he d4he d4hd5 Z d6e d7<d dd d(d)d*d+d,d-d d.d d8 Z d9e d:<dd?d@ZddAdBZeZidddCdDdEdFddGdddHdddIdJdKd"ddLdMdNd&dOdPdQdRdSdTdUdVdWdXdYdZid[d\d]d^dd_d`d d1dad4dbdcddd)ded dfd+dgd-dhd,didjdkdldmdndodpdqdrdsZd9e dt<ddudvZdwZdxe dy<dzZdxe d{<d|d}fdddZeeZd6e d<dddZiZd6e d<e D] \ZZe epeZe ddeDZeee eBee<qeedd}dZd6e d<dddZ dddZ!e ddhZ"de d<dddZ#dddZ$dS)a$Encoding equivalences and name remapping. This module defines: 1. **Directional supersets** for accuracy evaluation: detecting a superset encoding when the expected encoding is a subset is correct (e.g., detecting UTF-8 when expected is ASCII), but not the reverse. 2. **Bidirectional equivalents**: groups of encodings where detecting any member when another member was expected is considered correct. This includes UTF-16/UTF-32 endian variants (which encode the same text with different byte order) and ISO-2022-JP branch variants (which are compatible extensions of the same base encoding). 3. **Preferred superset mapping** for the ``prefer_superset`` API option: replaces detected ISO/subset encoding names with their Windows/CP superset equivalents that modern software actually uses. 4. **Compatibility names** for the default ``compat_names=True`` mode: maps internal Python codec names to the names chardet 5.x/6.x returned, preserving backward compatibility for callers that compare encoding strings directly. ) annotationsN)Callable) DetectionDictlookup_encodingASCIIzutf-8cp1252zTIS-620 iso8859-11Zcp874z ISO-8859-11ZGB2312gb18030ZGBKZBig5 big5hkscscp950Z Shift_JIScp932shift_jis_2004zShift-JISX0213zEUC-JP euc_jis_2004z EUC-JISX0213zEUC-KRcp949ZCP037cp1140z ISO-2022-JP> iso2022_jp_2iso2022_jp_extiso2022_jp_2004z ISO2022-JP-1rrz ISO2022-JP-3rz ISO-8859-1z ISO-8859-2cp1250cp1251cp1256cp1253cp1255cp1254cp1257z utf-16-lez utf-16-bezutf-16z utf-32-lez utf-32-bezutf-32) ISO-8859-5z ISO-8859-6 ISO-8859-7 ISO-8859-8 ISO-8859-9z ISO-8859-13UTF-16z UTF-16-LEz UTF-16-BEUTF-32z UTF-32-LEz UTF-32-BEdict[str, frozenset[str]] SUPERSETS) asciieuc_kr iso8859-1z iso8859-2 iso8859-5z iso8859-6 iso8859-7 iso8859-8 iso8859-9r z iso8859-13tis-620dict[str, str]PREFERRED_SUPERSETresultrmappingreturncCs(|d}t|tr||||d<|S)zGReplace the encoding name using *mapping*, modifying *result* in-place.encoding)get isinstancestr)r.r/encr6U/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/chardet/equivalences.py_remap_encodingls  r8cC t|tS)a7Replace the encoding name with its preferred Windows/CP superset. Modifies the ``"encoding"`` value in *result* in-place and returns *result* for fluent chaining. :param result: A detection result dict containing an ``"encoding"`` key. :returns: The same *result* dict, modified in-place. )r8r-r.r6r6r7apply_preferred_supersett r;cp855ZIBM855cp866ZIBM866ZCP949r%ZGB18030hzz HZ-GB-2312 iso2022_krz ISO-2022-KRr&r'rr(rr)rr*rjohabZJohabzkoi8-rzKOI8-Rz mac-cyrillicZ MacCyrillicz mac-romanZMacRomanZ SHIFT_JISr+r r!z utf-8-sigz UTF-8-SIGz Windows-1251z Windows-1252z Windows-1253z Windows-1254z Windows-1255kz1048ZKZ1048z mac-greekZMacGreekz mac-icelandZ MacIcelandz mac-latin2Z MacLatin2z mac-turkishZ MacTurkish _COMPAT_NAMEScCr9)a7Convert internal codec names to chardet 5.x/6.x compatible names. Modifies the ``"encoding"`` value in *result* in-place and returns *result* for fluent chaining. :param result: A detection result dict containing an ``"encoding"`` key. :returns: The same *result* dict, modified in-place. )r8rCr:r6r6r7apply_compat_namesr<rD))rrrtuple[tuple[str, ...], ...]BIDIRECTIONAL_GROUPS))skcs)ukrubgbe)msid)nodasvLANGUAGE_EQUIVALENCEScCs|SNr6)xr6r6r7srUgroups normalizeCallable[[str], str]cs>i}|D]}tfdd|D}|D]}|||<qq|S)zJBuild a lookup: key -> frozenset of all equivalent keys in the same group.c3s|]}|VqdSrSr6).0nrWr6r7 sz%_build_group_index..) frozenset)rVrWr.groupZnormednamer6r[r7_build_group_indexsr`_LANGUAGE_EQUIVexpectedr4detectedboolcCs&||krdSt|}|duo||vS)aCheck whether *detected* is an acceptable language for *expected*. Returns ``True`` when *expected* and *detected* are the same ISO 639-1 code, or belong to the same equivalence group in :data:`LANGUAGE_EQUIVALENCES`. :param expected: Expected ISO 639-1 language code. :param detected: Detected ISO 639-1 language code. :returns: ``True`` if the languages are equivalent. TN)rar2)rbrcr^r6r6r7is_language_equivalents  re_NORMALIZED_SUPERSETSccs|] }t|p |VqdSrSr)rYsr6r6r7r\ sr\cCs t|p|SrSr)rZr6r6r7rUs r[_NORMALIZED_BIDIR str | NonecCst|dur|duS|durdSt|p|}t|p|}||kr$dS|tvr0|t|vr0dS|tvo9|t|vS)aCheck whether *detected* is an acceptable answer for *expected*. Acceptable means: 1. Exact match (after normalization), OR 2. Both belong to the same bidirectional byte-order group, OR 3. *detected* is a known superset of *expected*. :param expected: The expected encoding name, or ``None`` for binary files. :param detected: The detected encoding name, or ``None``. :returns: ``True`` if the detection is acceptable. NFT)rlowerrhrf)rbrcnorm_expnorm_detr6r6r7 is_corrects  rmtextcCs td|}ddd|DS)z4NFKD-normalize *text* and strip all combining marks.ZNFKDcss|] }t|s|VqdSrS) unicodedata combining)rYcr6r6r7r\8z#_strip_combining..)rprWjoin)rnZnfkdr6r6r7_strip_combining5s ru)¤€)rwrvzfrozenset[tuple[str, str]]_EQUIVALENT_SYMBOL_PAIRSabcCs,||krdS||ftvrdSt|t|kS)uReturn True if characters *a* and *b* are functionally equivalent. Equivalent means: - Same character, OR - Same base letter after stripping combining marks, OR - An explicitly listed symbol equivalence (e.g. ¤ ↔ €) T)rxru)ryrzr6r6r7_chars_equivalentEs  r{databytesc Cs|dur|duS|durdSt|p|}t|p|}||kr$dSz ||}||}Wn ttfy<YdSw||krCdSt|t|krMdStddt||ddDS)uCheck whether *detected* produces functionally identical text to *expected*. Returns ``True`` when: 1. *detected* is not ``None`` and both encoding names normalize to the same codec, OR 2. Decoding *data* with both encodings yields identical strings, OR 3. Every differing character pair is functionally equivalent: same base letter after stripping combining marks, or an explicitly listed symbol equivalence (e.g. ¤ ↔ €). Returns ``False`` if *detected* is ``None``, either encoding is unknown, or either encoding cannot decode *data*. :param data: The raw byte data that was detected. :param expected: The expected encoding name, or ``None`` for binary files. :param detected: The detected encoding name, or ``None``. :returns: ``True`` if decoding with *detected* yields functionally identical text to decoding with *expected*. NFTcss|] \}}t||VqdSrS)r{)rYryrzr6r6r7r\rsz*is_equivalent_detection..)strict)rrjdecodeUnicodeDecodeError LookupErrorlenallzip)r|rbrcrkrlZtext_expZtext_detr6r6r7is_equivalent_detectionUs& r)r.rr/r,r0r)r.rr0r)rVrErWrXr0r")rbr4rcr4r0rd)rbrircrir0rd)rnr4r0r4)ryr4rzr4r0rd)r|r}rbrircrir0rd)%__doc__ __future__rrpcollections.abcrZchardet.pipelinerZchardet.registryrr]r#__annotations__r-r8r;Zapply_legacy_renamerCrDrFrRr`rarerfitemsZ_subsetZ _supersets_keyZ_normedr2rhrmrurxr{rr6r6r6r7sF                       3        !"#$ (       #