a SicJ @sddlZddlZddlmZddlmZmZddlmZm Z m Z m Z m Z ddl mZmZmZmZddlmZmZmZmZddlmZdd lmZmZdd lmZmZmZm Z m!Z!m"Z"m#Z#e$d Z%e&Z'e'(e)d de*e+e+e,e e e-e e e-e.e.ed ddZ/d e e+e+e,e e e-e e e-e.e.ed ddZ0d!de+e+e,e e e-e e e-e.e.ed ddZ1d"de+e+e,e e e-e e e-e.edddZ2dS)#N)PathLike)basenamesplitext)AnyBinaryIOListOptionalSet)coherence_ratioencoding_languagesmb_encoding_languagesmerge_coherence_ratios)IANA_SUPPORTEDTOO_BIG_SEQUENCETOO_SMALL_SEQUENCETRACE) mess_ratio) CharsetMatchCharsetMatches)any_specified_encodingcut_sequence_chunks iana_nameidentify_sig_or_bom is_cp_similaris_multi_byte_encodingshould_strip_sig_or_bomcharset_normalizerz)%(asctime)s | %(levelname)s | %(message)s皙?TF) sequencessteps chunk_size threshold cp_isolation cp_exclusionpreemptive_behaviourexplainreturnc- Cst|ttfs tdt||r>tj}tt t t t |} | dkrt d|rvtt t |prtjtt|dddgdgS|durtt d d |d d |D}ng}|durtt d d |dd |D}ng}| ||krtt d||| d}| }|dkr:| ||kr:t| |}t |tk} t |tk} | rltt d| n| rtt d| g} |rt|nd} | dur| | tt d| t}g}g}d}d}d}t}t|\}}|dur| |tt dt ||| dd| vr.| d| tD]}|rP||vrPq6|rd||vrdq6||vrrq6||d}||k}|ot|}|dvr|stt d|q6z t|}Wn,t t!fytt d|Yq6Yn0zr| r<|dur[zfrom_bytes..zacp_exclusion is set. use this flag for debugging purpose. limited list of encoding excluded : %s.cSsg|]}t|dqSr,r-r.r1r1r2r3fr4z^override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.r z>Trying to detect encoding from a tiny portion of ({}) byte(s).zIUsing lazy str decoding because the payload is quite large, ({}) byte(s).z@Detected declarative mark in sequence. Priority +1 given for %s.zIDetected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.ascii>utf_32utf_16z[Encoding %s wont be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.z2Encoding %s does not provide an IncrementalDecodergA)encodingz9Code page %s does not fit given bytes sequence at ALL. %sTzW%s is deemed too similar to code page %s and was consider unsuited already. Continuing!zpCode page %s is a multi byte encoding table and it appear that at least one character was encoded using n-bytes.zaLazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %sgj@strict)errorsz^LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %szc%s was excluded because of initial chaos probing. Gave up %i time(s). Computed mean chaos is %f %%.d)ndigitsz=%s passed initial chaos probing. Mean measured chaos is %f %%z&{} should target any language(s) of {}g?,z We detected language {} using {}z.Encoding detection: %s is most likely the one.zoEncoding detection: %s is most likely the one as we detected a BOM or SIG within the beginning of the sequence.zONothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.z7Encoding detection: %s will be used as a fallback matchz:Encoding detection: utf_8 will be used as a fallback matchz:Encoding detection: ascii will be used as a fallback matchz]Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.z=Encoding detection: Unable to determine any suitable charset.)4 isinstance bytearraybytes TypeErrorformattypeloggerlevel addHandlerexplain_handlersetLevelrlendebug removeHandlerloggingWARNINGrrlogjoinintrrrappendsetrraddrrModuleNotFoundError ImportErrorstrUnicodeDecodeError LookupErrorrrangemaxrrdecodesumroundr r r rr8 fingerprintbest)-r!r"r#r$r%r&r'r(Zprevious_logger_levellengthZis_too_small_sequenceZis_too_large_sequenceZprioritized_encodingsZspecified_encodingZtestedZtested_but_hard_failureZtested_but_soft_failureZfallback_asciiZ fallback_u8Zfallback_specifiedresultsZ sig_encodingZ sig_payloadZ encoding_ianaZdecoded_payloadZbom_or_sig_availableZstrip_sig_or_bomZis_multi_byte_decodereZsimilar_soft_failure_testZencoding_soft_failedZr_Zmulti_byte_bonusZmax_chunk_gave_upZearly_stop_countZlazy_str_hard_failureZ md_chunksZ md_ratioschunkZmean_mess_ratioZfallback_entryZtarget_languagesZ cd_ratiosZchunk_languagesZcd_ratios_mergedr1r1r2 from_bytes#s                      $        $                       rh) fpr"r#r$r%r&r'r(r)c Cst||||||||S)z Same thing than the function from_bytes but using a file pointer that is already ready. Will not close the file pointer. )rhread)rir"r#r$r%r&r'r(r1r1r2from_fpsrkz PathLike[Any]) pathr"r#r$r%r&r'r(r)c CsDt|d&}t||||||||WdS1s60YdS)z Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode. Can raise IOError. rbN)openrk) rlr"r#r$r%r&r'r(rir1r1r2 from_paths ro)rlr"r#r$r%r&r'r)c Cstdtt|||||||}t|}tt|} t|dkrNtd || } | dd| j 7<t d t ||d| d} | | Wdn1s0Y| S) zi Take a (text-based) file path and try to create another file next to it, this time using UTF-8. z2normalize is deprecated and will be removed in 3.0rz;Unable to normalize "{}", no encoding charset seems to fit.-z{}r+wbN)warningswarnDeprecationWarningrorlistrrMIOErrorrFrcr8rnrZreplacerSwriteoutput) rlr"r#r$r%r&r'refilenameZtarget_extensionsresultrir1r1r2 normalizes:    ,r|)rrr NNTF)rrr NNTF)rrr NNTF)rrr NNT)3rPrrosrZos.pathrrtypingrrrrr cdr r r rconstantrrrrmdrmodelsrrutilsrrrrrrr getLoggerrH StreamHandlerrK setFormatter FormatterrDrTfloatrZboolrhrkror|r1r1r1r2s  $    G