o aĎiF4@srdZddlmZddlmZddlmZddlmZm Z ddl m Z ddl m Z mZmZmZmZmZmZmZmZmZmZmZmZmZerJdd lmZd ZGd d d eZed dd9ddZed 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_CHECKING 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_MARKLVTLVLVTr8r8L/home/jeff/fluffinator/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,r/ _bisearchrr-rr.rr0rr1rr2r r3r r4r r5r r6rr7r*r;r8r8r9_grapheme_cluster_breakBs6          r@boolcCtt|tS)z6Check if codepoint has Extended_Pictographic property.)rAr>rr?r8r8r9_is_extended_pictographicerCcCrB)z,Check if codepoint has InCB=Linker property.)rAr>rr?r8r8r9_is_incb_linkerkrDrEcCrB)z/Check if codepoint has InCB=Consonant property.)rAr>rr?r8r8r9_is_incb_consonantqrDrFcCrB)z,Check if codepoint has InCB=Extend property.)rAr>r r?r8r8r9_is_incb_extendwrDrGc@s"eZdZUdZded<ded<dS) BreakResultz*Result of grapheme cluster break decision.rA should_breakr<ri_countN)r&r'r(r)__annotations__r8r8r8r9rH}s  rHprev_gcbcurr_gcbBreakResult | NonecCs&|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. FrrIrJTN) rr+r,rHr-r3r4r6r7r5r.r2r1)rLrMr8r8r9_simple_break_checks&   "          rPtextstrcurr_idxrJc 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. NFrrOrTr) rPrr/rHordrFrErGrCr@r.r0) rLrMrQrSrJresultcurr_ucs has_linkeriprev_ucs prev_propr8r8r9 _should_breaksN               r[Nunistrstartend int | None Iterator[str]c cs|sdSt|}|dur|}||ks||krdSt||}|}d}tt||}|tjkr1d}t|d|D]#}tt||}t|||||} | j}| j rY|||V|}|}q8|||VdS)aP 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('\U0001F468\u200D\U0001F469\u200D\U0001F467')) ['o', 'k', '\U0001F468\u200D\U0001F469\u200D\U0001F467'] >>> list(iter_graphemes('\U0001F1FA\U0001F1F8')) ['o', 'k', '\U0001F1FA\U0001F1F8'] .. versionadded:: 0.3.0 Nrr) lenminr@rTrr0ranger[rJrI) r\r]r^length cluster_startrJrLidxrMrUr8r8r9iter_graphemess.  rgposc 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) rTr@rr1_find_cluster_startMAX_GRAPHEME_SCANr-r0rcr[rJrI) rQrh target_cpprev_cp safe_startcpreleft_gcbrJrX right_gcbrUr8r8r9rk<s:   rkcCs |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)rkrbra)r\rhr8r8r9grapheme_boundary_beforepsrsccs|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)rarbmaxrk)r\r]r^rdrhrer8r8r9iter_graphemes_reverses   ru)r;r<r=r)r;r<r=rA)rLrrMrr=rN) rLrrMrrQrRrSr<rJr<r=rH)rN)r\rRr]r<r^r_r=r`)rQrRrhr<r=r<)r\rRrhr<r=r<)+r) __future__renumr functoolsrtypingrrrr>table_graphemer r r r r rrrrrrrrrcollections.abcrrlrr@rCrErFrGrHrPr[rgrkrsrur8r8r8r9sB   @  "      0E D 4