o j]4@svdZddlmZddlmZddlmZddlmZm Z m Z ddl m Z ddl mZmZmZmZmZmZmZmZmZmZmZmZmZmZerLdd lmZd ZGd d d eZed dd9ddZ ed dd:ddZ!ed dd:ddZ"ed dd:ddZ#ed dd:ddZ$Gddde Z%ed dd;d"d#Z&dd0d1Z(d?d3d4Z)d@d5d6Z*  *d=d>d7d8Z+d*S)Az Grapheme cluster segmentation following Unicode Standard Annex #29. This module provides pure-Python implementation of the grapheme cluster boundary algorithm as defined in UAX #29: Unicode Text Segmentation. https://www.unicode.org/reports/tr29/ ) annotations)IntEnum) lru_cache) TYPE_CHECKINGOptional NamedTuple)bisearch) GRAPHEME_L GRAPHEME_T GRAPHEME_V GRAPHEME_LV INCB_EXTEND INCB_LINKER GRAPHEME_LVTINCB_CONSONANTGRAPHEME_EXTENDGRAPHEME_CONTROLGRAPHEME_PREPENDGRAPHEME_SPACINGMARKEXTENDED_PICTOGRAPHICGRAPHEME_REGIONAL_INDICATOR)Iterator c@sHeZdZdZdZdZdZdZdZdZ dZ d Z d Z d Z d Zd ZdZdZdS)GCBz'Grapheme Cluster Break property values.rr N)__name__ __module__ __qualname____doc__OTHERCRLFCONTROLEXTENDZWJREGIONAL_INDICATORPREPEND SPACING_MARKLVTLVLVTr9r9Q/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/wcwidth/grapheme.pyr,s ri)maxsizeucsintreturncCs|dkrtjS|dkrtjS|dkrtjSt|trtjSt|tr%tjSt|t r-tj St|t r5tj St|t r=tjSt|trEtjSt|trMtjSt|trUtjSt|tr]tjSt|tretjStjS)z;Return the Grapheme_Cluster_Break property for a codepoint.r&r#i )rr,r-r0 _bisearchrr.rr/rr1rr2rr3r r4r r5r r6r r7rr8r+r<r9r9r:_grapheme_cluster_breakBs6          rAboolcCtt|tS)z6Check if codepoint has Extended_Pictographic property.)rBr?rr@r9r9r:_is_extended_pictographicerDcCrC)z,Check if codepoint has InCB=Linker property.)rBr?rr@r9r9r:_is_incb_linkerkrErFcCrC)z/Check if codepoint has InCB=Consonant property.)rBr?rr@r9r9r:_is_incb_consonantqrErGcCrC)z,Check if codepoint has InCB=Extend property.)rBr?rr@r9r9r:_is_incb_extendwrErHc@s"eZdZUdZded<ded<dS) BreakResultz*Result of grapheme cluster break decision.rB should_breakr=ri_countN)r'r(r)r*__annotations__r9r9r9r:rI}s  rIprev_gcbcurr_gcbOptional[BreakResult]cCs&|tjkr|tjkrtdddS|tjtjtjfvr tdddS|tjtjtjfvr0tdddS|tjkrG|tjtjtjtjfvrGtdddS|tjtjfvr]|tjtj fvr]tdddS|tjtj fvrp|tj krptdddS|tj kr{tdddS|tj krtdddS|tj krtdddSdS)z Check simple GCB-pair-based break rules (cacheable). Returns BreakResult for rules that can be determined from GCB properties alone, or None if complex lookback rules (GB9c, GB11) need to be checked. FrrJrKTN) rr,r-rIr.r4r5r7r8r6r/r3r2)rMrNr9r9r:_simple_break_checks&   "          rQtextstrcurr_idxrKc Csnt||}|dur |S|tjkrtdddSt||}t|rVd}|d}|dkrVt||} t| r;d}|d8}nt| rD|d8}nt| rQ|rPtdddSnn|dks*|tjkrt|r|d}|dkrt||} t | } | tj kr{|d8}n t| rtdddSn|dksg|tj kr|tj kr|ddkrtd|ddStdddS|tj krdnd}td|dS)z Determine if there should be a grapheme cluster break between prev and curr. Implements UAX #29 grapheme cluster boundary rules. NFrrPrTr) rQrr0rIordrGrFrHrDrAr/r1) rMrNrRrTrKresultZcurr_ucsZ has_linkeriZprev_ucsZ prev_propr9r9r: _should_breaksN               rXNunistrstartend Optional[int] Iterator[str]c cs|sdSt|}|dur|}||ks||krdSt||}|}d}tt||}|tjkr1d}t|d|D]#}tt||}t|||||} | j}| j rY|||V|}|}q8|||VdS)aT Iterate over grapheme clusters in a Unicode string. Grapheme clusters are "user-perceived characters" - what a user would consider a single character, which may consist of multiple Unicode codepoints (e.g., a base character with combining marks, emoji sequences). :param unistr: The Unicode string to segment. :param start: Starting index (default 0). :param end: Ending index (default len(unistr)). :yields: Grapheme cluster substrings. Example:: >>> list(iter_graphemes('cafe\u0301')) ['c', 'a', 'f', 'e\u0301'] >>> list(iter_graphemes('ok\U0001F468\u200D\U0001F469\u200D\U0001F467')) ['o', 'k', '\U0001F468\u200D\U0001F469\u200D\U0001F467'] >>> list(iter_graphemes('ok\U0001F1FA\U0001F1F8')) ['o', 'k', '\U0001F1FA\U0001F1F8'] .. versionadded:: 0.3.0 Nrr) lenminrArUrr1rangerXrKrJ) rYrZr[length cluster_startrKrMidxrNrVr9r9r:iter_graphemess.  rdposc Cslt||d}|dkr|dkr||ddkr|dS|dkrF|dkrB|dkrBt||d}|dkrBt|tjkrBt||dS|dS|d}|dkr}||tkr}t||}d|krddkrgnnnt|tjkron|d8}|dkr}||tksT|}tt||}|tjkrdnd}t|d|D]} tt|| } t || || |} | j }| j r| }| }q|S)a Find the start of the grapheme cluster containing the character before pos. Scans backwards from pos to find a safe starting point, then iterates forward using standard break rules to find the actual cluster boundary. :param text: The Unicode string. :param pos: Position to search before (exclusive). :returns: Start position of the grapheme cluster. rr#r rr) rUrArr2_find_cluster_startMAX_GRAPHEME_SCANr.r1r`rXrKrJ) rRreZ target_cpZprev_cpZ safe_startcprbZleft_gcbrKrWZ right_gcbrVr9r9r:rh<s:   rhcCs |dkrdSt|t|t|S)a Find the grapheme cluster boundary immediately before a position. :param unistr: The Unicode string to search. :param pos: Position in the string (0 < pos <= len(unistr)). :returns: Start index of the grapheme cluster containing the character at pos-1. Example:: >>> grapheme_boundary_before('Hello \U0001F44B\U0001F3FB', 8) 6 >>> grapheme_boundary_before('a\r\nb', 3) 1 .. versionadded:: 0.3.6 r)rhr_r^)rYrer9r9r:grapheme_boundary_beforepsrkccs|sdSt|}|dur|nt||}t|d}||ks!||kr#dS|}||krCt||}||kr4dS|||V|}||ks)dSdS)a Iterate over grapheme clusters in reverse order (last to first). :param unistr: The Unicode string to segment. :param start: Starting index (default 0). :param end: Ending index (default len(unistr)). :yields: Grapheme cluster substrings in reverse order. Example:: >>> list(iter_graphemes_reverse('cafe\u0301')) ['e\u0301', 'f', 'a', 'c'] .. versionadded:: 0.3.6 Nr)r^r_maxrh)rYrZr[rarerbr9r9r:iter_graphemes_reverses   rm)r<r=r>r)r<r=r>rB)rMrrNrr>rO) rMrrNrrRrSrTr=rKr=r>rI)rN)rYrSrZr=r[r\r>r])rRrSrer=r>r=)rYrSrer=r>r=),r* __future__renumr functoolsrtypingrrrr r?Ztable_graphemer r r r rrrrrrrrrrcollections.abcrrirrArDrFrGrHrIrQrXrdrhrkrmr9r9r9r:sB   @  "      0E D 4