+
    LV-jF;  ã                  ó†  € ^ RI Ht ^ RIt^ RIHt ^ RIHt ^ RIHt ^ RI	Ht
 ^RIHtHtHtHtHtHtHt ^RIHt ^RIHt ^R	IHtHtHtHtHt R
 R ltR R lt]! 4       R R l4       t]! 4       R R l4       t ]! ]R7      R R l4       t!R"R R llt"R R lt#R R lt$R R lt%R R lt&]! RR7      R#R  R! ll4       t'R# )$é    )ÚannotationsN)ÚIncrementalDecoder)ÚCounter)Ú	lru_cache)ÚFREQUENCIESÚKO_NAMESÚLANGUAGE_SUPPORTED_COUNTÚTOO_SMALL_SEQUENCEÚZH_NAMESÚ_FREQUENCIES_SETÚ_FREQUENCIES_RANK)Ú is_suspiciously_successive_range)ÚCoherenceMatches)Úis_accentuatedÚis_latinÚis_multi_byte_encodingÚis_unicode_range_secondaryÚunicode_rangec               ó    € V ^8„  d   QhRRRR/# ©é   Ú	iana_nameÚstrÚreturnú	list[str]© )Úformats   "Úf/Volumes/fast/ai/experiments/ui-tars-smoke/.venv/lib/python3.14/site-packages/charset_normalizer/cd.pyÚ__annotate__r      s   € ÷ $ñ $ cð $¨iñ $ó    c                ó  € \        V 4      '       d   \        R4      h\        P                  ! RV  24      P                  pV! RR7      p/ p^ p\        ^@^ÿ4       Fq  pVP                  \        V.4      4      pV'       g   K(  \        V4      pVf   K9  \        V4      RJ g   KJ  Ws9  d   ^ W7&   W7;;,          ^,          uu&   V^,          pKs  	  \        V Uu. uF  pW7,          V,          R8¼  g   K  VNK  	  up4      # u upi )z>
Return associated unicode ranges in a single byte code page.
z.Function not supported on multi-byte code pagez
encodings.Úignore)ÚerrorsFg333333Ã?)r   ÚOSErrorÚ	importlibÚimport_moduler   ÚrangeÚdecodeÚbytesr   r   Úsorted)r   ÚdecoderÚpÚseen_rangesÚcharacter_countÚiÚchunkÚcharacter_ranges   &       r   Úencoding_unicode_ranger2      s  € ô ˜i×(Ò(ÜØ<ó
ð 	
ô ×%Ò%¨
°9°+Ð&>Ó?×RÑR€Gá#¨8Ô4€AØ"$€KØ€Oä�4˜ÖˆØ—X‘Xœe Q C›jÓ)ˆç‰5Ü*7¸Ó*>ˆOàÒ&Ùä)¨/Ó:¸eÕCØ"Ô5Ø34�KÑ0Ø×,°Õ1Ó,Ø 1Õ$’ñ ô ñ $/ó	
á#.�ØÕ+¨oÕ=ÀÑE÷ ˆOÙ#.ñ	
óð ùò	
s   ÃC?Ã2C?c               ó    € V ^8„  d   QhRRRR/# )r   Úprimary_ranger   r   r   r   )r   s   "r   r   r   D   s   € ÷ ñ ¨3ð °9ñ r    c                ó    € . p\         P                  ! 4        F2  w  r#V F'  p\        V4      V 8X  g   K  VP                  V4        K0  	  K4  	  V# )z6
Return inferred languages used with a unicode range.
)r   Úitemsr   Úappend)r4   Ú	languagesÚlanguageÚ
charactersÚ	characters   &    r   Úunicode_range_languagesr<   D   sO   € ð €Iä +× 1Ò 1Ö 3ÑˆÛ#ˆIÜ˜YÓ'¨=Ö8Ø× Ñ  Ô*Úó $ñ !4ð Ðr    c               ó    € V ^8„  d   QhRRRR/# r   r   )r   s   "r   r   r   T   s   € ÷ 2ñ 2 #ð 2¨)ñ 2r    c                óh   € \        V 4      pRpV F  pRV9  g   K  Tp M	  Vf   R.# \        V4      # )z�
Single-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
NÚLatinúLatin Based)r2   r<   )r   Úunicode_rangesr4   Úspecified_ranges   &   r   Úencoding_languagesrC   S   sH   € ô !7°yÓ A€NØ $€Mã)ˆØ˜/Ö)Ø+ˆMÙñ *ð
 ÒØˆÐä" =Ó1Ð1r    c               ó    € V ^8„  d   QhRRRR/# r   r   )r   s   "r   r   r   h   s   € ÷ ñ  Sð ¨Yñ r    c                ó8  € V P                  R4      '       g6   V P                  R4      '       g   V P                  R4      '       g   V R8X  d   R.# V P                  R4      '       g   V \        9   d   R.# V P                  R4      '       g   V \        9   d   R	.# . # )
z�
Multi-byte encoding language association. Some code page are heavily linked to particular language(s).
This function does the correspondence.
Úshift_Ú
iso2022_jpÚeuc_jÚcp932ÚJapaneseÚgbÚChineseÚ
iso2022_krÚKorean)Ú
startswithr   r   )r   s   &r   Úmb_encoding_languagesrP   g   sŒ   € ð 	×Ñ˜X×&Ò&Ø×Ñ ×-Ò-Ø×Ñ ×(Ò(Ø˜Ôàˆ|ÐØ×Ñ˜D×!Ò! Y´(Ô%:Øˆ{ÐØ×Ñ˜L×)Ò)¨Y¼(Ô-BØˆzÐà€Ir    )Úmaxsizec               ó    € V ^8„  d   QhRRRR/# )r   r9   r   r   ztuple[bool, bool]r   )r   s   "r   r   r   }   s   € ÷ 2ñ 2 #ð 2Ð*;ñ 2r    c                ó¨   € RpRp\         V ,           F;  pV'       g   \        V4      '       d   RpV'       g   K(  \        V4      RJ g   K9  RpK=  	  W3# )z_
Determine main aspects from a supported language if it contains accents and if is pure Latin.
FT)r   r   r   )r9   Útarget_have_accentsÚtarget_pure_latinr;   s   &   r   Úget_target_featuresrV   |   sX   € ð
 !&ÐØ"Ðä  ×*Ð*ˆ	ß"¤~°i×'@Ò'@Ø"&ÐßÑ¤¨)Ó!4¸Õ!=Ø %Òñ	 +ð Ð1Ð1r    c               ó$   € V ^8„  d   QhRRRRRR/# )r   r:   r   Úignore_non_latinÚboolr   r   )r   s   "r   r   r   �   s)   € ÷ Iñ IØðIØ-1ðIàñIr    c                ó  € . p\        V 4      p\        ;QJ d    R V  4       F  '       g   K   RM	  RM! R V  4       4      p\        P                  ! 4        F}  w  rV\	        V4      w  rxV'       d	   VRJ d   K"  VRJ d   V'       d   K2  \        V4      p	\        \        V,          V,          4      p
W©,          pVR8¼  g   Kk  VP                  W[34       K  	  \        VR RR7      pV Uu. uF  qÌ^ ,          NK  	  up# u upi )z=
Return associated languages associated to given characters.
c              3  ó8   "  € T F  p\        V4      x € K  	  R # 5i)N)r   )Ú.0r;   s   & r   Ú	<genexpr>Ú%alphabet_languages.<locals>.<genexpr>–   s   é € ÐTÉ¸Iœn¨Y×7Ð7Ëùs   ‚TFgš™™™™™É?c                ó   € V ^,          # ©é   r   ©Úxs   &r   Ú<lambda>Ú$alphabet_languages.<locals>.<lambda>ª   s   € °°!¶r    ©ÚkeyÚreverse)	Ú	frozensetÚanyr   r6   rV   Úlenr   r7   r*   )r:   rX   r8   Úcharacters_setÚsource_have_accentsr9   Úlanguage_charactersrT   rU   r.   Úcharacter_match_countÚratioÚcompatible_languages   &&           r   Úalphabet_languagesrr   �   sä   € ð *,€Iä%.¨zÓ%:€Nß›#ÑTÉÓTŸ#Ÿ#š#ÑTÉÓTÓTÐä)4×):Ò):Ö)<Ñ%ˆÜ1DÀXÓ1NÑ.ÐçÐ 1°UÓ :Ùà %Ó'×,?Ùä"Ð#6Ó7ˆä%(Ô)9¸(Õ)CÀnÕ)TÓ%UÐà,Õ>ˆà�CŽ<Ø×Ñ˜hÐ.Ö/ñ! *=ô$ �y¡n¸dÔC€Iá>GÓH¹iÐ': ×"Ð"¹iÑHÐHùÒHs   Ã+C?c               ó$   € V ^8„  d   QhRRRRRR/# )r   r9   r   Úordered_charactersr   r   Úfloatr   )r   s   "r   r   r   ¯   s)   € ÷ b>ñ b>Øðb>Ø'0ðb>à
ñb>r    c                óì  € V \         9  d   \        V  R24      h^ p\        V ,          p\        V ,          p\	        V4      p\	        \         V ,          4      pV^8„  pWe,          p\        V4       U	U
u/ uF  w  ršW©bK	  	  pp	p
VP                  4        UUu. uF  w  rÍWË9   g   K  WÛV,          3NK  	  ppp\	        V4      pV Uu. uF  pV^ ,          NK  	  ppV Uu. uF  pV^,          NK  	  pp\        V\        ^ V4      4       EFC  w  ppVV9  d   K  VV,          p\        VV,          4      pVRJ d   \        VV,
          4      ^8”  d   KJ  VRJ d*   \        VV,
          4      V^,          8  d   V^,          pKy  ^ p^ p\        V4       FB  pVV,          pVV,          pVV8  d   VV8  d   V^,          pK.  K0  VV8¼  g   K9  V^,          pKD  	  VV,
          pV^ 8X  d   V^8:  d   V^,          pKð  V^ 8X  d   V^8:  d   V^,          pEK
  V^ 8”  d   VV,          R8¼  g   V^ 8”  g   EK)  VV,          R8¼  g   EK:  V^,          pEKF  	  V\	        V4      ,          # u up
p	i u uppi u upi u upi )a>  
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.)
z not availableFTgš™™™™™Ù?)r   Ú
ValueErrorr   r   rk   Ú	enumerater6   Úzipr'   ÚintÚabs)r9   rt   Úcharacter_approved_countÚfrequencies_language_setÚ	lang_rankÚordered_characters_countÚ target_language_characters_countÚlarge_alphabetÚexpected_projection_ratioÚrankÚcharÚordered_rankÚcÚlrÚcommon_charsÚcommon_countr,   Ú	common_lrÚ
common_orrr;   Úcharacter_rankÚcharacter_rank_in_languageÚcharacter_rank_projectionÚbefore_match_countÚafter_match_countr/   Úlr_iÚorr_iÚ	after_lens   &&                           r   Úcharacters_popularity_comparer”   ¯   s½  € ð ”{Ô"Ü˜H˜: ^Ð4Ó5Ð5à$%ÐÜ/?ÀÕ/IÐÜ 1°(Õ ;€Iä$'Ð(:Ó$;ÐÜ,/´¸HÕ0EÓ,FÐ$à;¸bÑ@€Nð 	)ÕCð ô &/Ð/AÔ%Bô$Ù%B‘z�tˆŠ
Ñ%Bð ñ $ð ,5¯?©?Ô+<ô+Ù+<¡% !ÀÑ@QÔˆ˜!�_ÓÑ+<ð ñ +ô ˜LÓ)€LÙ*6Ó7©, Q˜A˜aŸD˜D©,€IÐ7Ù+7Ó8©< a˜Q˜qŸT˜T©<€JÐ8ä%(ØœE !Ð%=Ó>÷&Ñ!ˆ	�>ð Ð4Ô4Ùà*3°IÕ*>Ð"Ü),¨^Ð>WÕ-WÓ)XÐ!ð ˜eÓ#ÜÐ-Ð0JÕJÓKÈaÔOáð ˜dÓ"ÜÐ-Ð0JÕJÓKØ.°Õ2ô3ð %¨Õ)Ð$Ùð #$ÐØ!"ÐÜ�|Ö$ˆAØ! !�ˆDØ# A�ˆEØÐ0Ô0Ø˜>Ô)Ø&¨!Õ+Ò&ñ *ð ˜NÖ*Ø%¨Õ*Ò%ñ %ð :Ð<VÕVˆ	à%¨Ô*Ð/AÀQÔ/FØ$¨Õ)Ð$Ùà˜Œ>Ð/°1Ô4Ø$¨Õ)Ð$Úð '¨Ô*Ø"Ð%?Õ?À3ÔFØ˜!�mÐ 1°IÕ =À× DØ$¨Õ)Ð$Úñm&ðp $¤cÐ*<Ó&=Õ=Ð=ùóS$ùó+ùò 8ùÚ8s   Á2I Â
I&Â$I&ÃI,ÃI1c               ó    € V ^8„  d   QhRRRR/# )r   Údecoded_sequencer   r   r   r   )r   s   "r   r   r     s"   € ÷ GAñ GA¨#ð GA°)ñ GAr    c                óJ  € / pRpRpRpRpV  FÒ  pVP                  4       RJ d   K  \        V4      pV^€8  d   RpM\        V4      pVf   K?  W„8X  d   Ve   W,          P                  V4       Kb  Rp	V'       d   V F  p
\	        W¨4      RJ g   K  T
p	 M	  MVe   \	        W(4      RJ d   Tp	V	f   Tp	W‘9  d   . W&   Vf   T	pMRpW,          P                  V4       TpT	pKÔ  	  VP                  4        Uu. uF"  pRP                  V4      P                  4       NK$  	  up# u upi )z÷
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.
NFzBasic LatinTÚ )ÚisalphaÚordr   r7   r   ÚvaluesÚjoinÚlower)r–   ÚlayersÚsingle_layer_keyÚmulti_layerÚprev_character_rangeÚprev_layer_targetr;   Úcharacter_ordr1   Úlayer_target_rangeÚdiscovered_rangeÚcharss   &           r   Úalpha_unicode_splitr§     s]  € ð $&€Fð $(ÐØ€Kð (,ÐØ$(Ðã%ˆ	Ø×ÑÓ %Ó'Ùô ! ›^ˆØ˜3ÔØ*7‰Oä+¨IÓ6ˆOàÒ"Ùð Ô2Ø Ò,ØÕ)×0Ñ0°Ô;Ùà)-ÐçÛ$*Ð ä4Ð5EÓWØõð *:Ð&Ùò %+ð Ò)ä0Ð1AÓSØóð &6Ð"àÒ%Ø!0ÐàÔ+Ø)+ˆFÑ&ØÒ'Ø#5Ñ à"�àÕ"×)Ñ)¨)Ô4ð  /ÐØ.Òñi &ðl 17·±´Ó@± uˆB�G‰G�E‹N× Ñ Ö"±Ñ@Ð@ùÒ@s   Ã5(D c               ó    € V ^8„  d   QhRRRR/# )r   Úresultszlist[CoherenceMatches]r   r   r   )r   s   "r   r   r   ^  s   € ÷ ;ñ ;Ð$:ð ;Ð?Oñ ;r    c                ó&  € / pV  F4  pV F+  pVw  rEWA9  d   V.W&   K  W,          P                  V4       K-  	  K6  	  V Uu. uF6  pV\        \        W,          4      \        W,          4      ,          ^4      3NK8  	  pp\	        VR RR7      # u upi )z
This function merge results previously given by the function coherence_ratio.
The return type is the same as coherence_ratio.
c                ó   € V ^,          # r`   r   rb   s   &r   rd   Ú(merge_coherence_ratios.<locals>.<lambda>w  s   €  q¨¦tr    Trf   )r7   ÚroundÚsumrk   r*   )r©   Úper_language_ratiosÚresultÚ
sub_resultr9   rp   Úmerges   &      r   Úmerge_coherence_ratiosr³   ^  s°   € ð
 35ÐÛˆÛ ˆJØ(‰OˆHØÔ2Ø16°Ð#Ñ-ÙØÕ)×0Ñ0°Ö7ó !ñ ñ  ,ó	ñ ,ˆHð ÜÜÐ'Õ1Ó2´SÐ9LÕ9VÓ5WÕWØóó	
ñ ,ð 
ð 	ô �%™^°TÔ:Ð:ùò	s   Á<Bc               ó    € V ^8„  d   QhRRRR/# )r   r©   r   r   r   )r   s   "r   r   r   z  s   € ÷ ñ Ð*:ð Ð?Oñ r    c                ó‚  a€ \        4       oV  F=  pVw  r#VP                  RR4      pVS9  d   . SV&   SV,          P                  V4       K?  	  \        ;QJ d    V3R lS 4       F  '       g   K   RM	  RM! V3R lS 4       4      '       d1   . pS F&  pVP                  V\	        SV,          4      34       K(  	  V# V # )u§   
We shall NOT return "Englishâ€”" in CoherenceMatches because it is an alternative
of "English". This function only keeps the best match and remove the em-dash in it.
u   â€”r˜   c              3  óN   <"  € T F  p\        SV,          4      ^8„  x € K  	  R# 5i)ra   N)rk   )r\   ÚeÚindex_resultss   & €r   r]   Ú/filter_alt_coherence_matches.<locals>.<genexpr>Š  s    øé € Ð
<©m¨Œ3ˆ}˜QÕÓ  1Ö$«mùs   ƒ"%TF)ÚdictÚreplacer7   rj   Úmax)r©   r°   r9   rp   Ú
no_em_nameÚfiltered_resultsr¸   s   &     @r   Úfilter_alt_coherence_matchesr¿   z  s±   ø€ ô
 -1«F€MãˆØ ‰ˆØ"×*Ñ*¨5°"Ó5ˆ
à˜]Ô*Ø(*ˆM˜*Ñ%à�jÕ!×(Ñ(¨Ö/ñ ÷ ƒsÔ
<©mÓ
<‡s‡s‚sÔ
<©mÓ
<×<Ò<Ø-/Ðã%ˆHØ×#Ñ# X¬s°=ÀÕ3JÓ/KÐ$LÖMñ &ð  Ðà€Nr    i   c               ó(   € V ^8„  d   QhRRRRRRRR/# )	r   r–   r   Ú	thresholdru   Úlg_inclusionz
str | Noner   r   r   )r   s   "r   r   r   –  s,   € ÷ 0ñ 0Øð0Ø&+ð0ØAKð0àñ0r    c           	     ó,  € . pRp^ pVe   VP                  R4      M. pRV9   d   RpVP                  R4       \        V 4       F±  p\        V4      pVP	                  4       p	\        V4      p
V
\        8:  d   K6  V	 UUu. uF  w  r¼VNK	  	  pppT;'       g    \        WÔ4       FM  p\        Wí4      pWñ8  d   K  VR8¼  d
   V^,          pVP                  V\        V^4      34       V^8¼  g   KL   K¯  	  K³  	  \        \        V4      R RR7      # u uppi )zœ
Detect ANY language that can be identified in given sequence. The sequence will be analysed by layers.
A layer = Character extraction by alphabets/ranges.
FÚ,r@   Tgš™™™™™é?c                ó   € V ^,          # r`   r   rb   s   &r   rd   Ú!coherence_ratio.<locals>.<lambda>Å  s   € ¸Q¸q¾Tr    rf   )ÚsplitÚremover§   r   Úmost_commonrk   r
   rr   r”   r7   r­   r*   r¿   )r–   rÁ   rÂ   r©   rX   Úsufficient_match_countÚlg_inclusion_listÚlayerÚsequence_frequenciesrÉ   r.   r†   ÚoÚpopular_character_orderedr9   rp   s   &&&             r   Úcoherence_ratiorÐ   •  s2  € ð (*€GØ"Ðà"#Ðà3?Ò3K˜×*Ñ*¨3Ô/ÐQSÐØÐ)Ô)ØÐØ× Ñ  Ô/ä$Ð%5Ö6ˆÜ18¸³ÐØ*×6Ñ6Ó8ˆä" 5›zˆàÔ0Ô0Ùá>IÔ/J¹k±d°a³¹kÐ!Ñ/Jà)÷ 
ð 
Ô-?Ø%ó.
ò 
ˆHô 9ØóˆEð Ô ÙØ˜#”Ø&¨!Õ+Ð&à�N‰N˜H¤e¨E°1£oÐ6Ô7à%¨Ö*Úó
ñ 7ô8 Ü$ WÓ-±>È4ôð ùó' 0Ks   Á>D)F)gš™™™™™¹?N)(Ú
__future__r   r%   Úcodecsr   Úcollectionsr   Ú	functoolsr   ÚtypingÚTypeCounterÚconstantr   r   r	   r
   r   r   r   Úmdr   Úmodelsr   Úutilsr   r   r   r   r   r2   r<   rC   rP   rV   rr   r”   r§   r³   r¿   rÐ   r   r    r   Ú<module>rÛ      sÂ   ðÝ "ã Ý %Ý Ý Ý )÷÷ ñ õ 1Ý $÷õ õ$õNñ ƒô2ó ð2ñ& ƒôó ðñ( Ð+Ô,ô2ó -ð2÷ IõDb>õJGAõT;õ8ñ6 �4Ôö0ó ò0r    