i"pdZddlmZddlZddlmZddlmZddlZddlmZd'dZ d(d Z ed Z d)d Z d*d Z d+d Zejdej ZejdZejdej Zd,dZd-dZdZejdezdzZd-dZd.dZejdZd-dZd/dZd0dZhdZd1dZd2dZ hdZ!d3d Z"d-d!Z#ejd"ej #Z$ejd$ej #Z%d4d%Z&d4d&Z'y)5z!Utilities for parsing source text) annotationsN)Match)TypeVar)entitiesc> t||S#t$rYywxYwa  Returns the Unicode value of the character at the specified location. @param - index The zero-based index of the desired character. If there is no character at the specified index, NaN is returned. This was added for compatibility with python N)ord IndexErrorsrcposs m/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/markdown_it/common/utils.py charCodeAtr s'3s8} s  c, ||S#t$rYywxYwr )r r s r charStrAtrs"3x s  _ItemTVc$|d||z||dzdzS)zw Remove element from array and put another array at those position. Useful for some operations with tokens Nr)r r newElementss rarrayReplaceAtr.s$ t9{ "Sq^ 33c|dk\r|dkry|dk\r|dkry|dzdk(s|dzdk(ry|dk\r|d kry|d k(ry|d k\r|d kry|d k\r|dkry|dkD S)NiiFiiiir ircs risValidEntityCoder"8sF{qF{F{qF{ VQZF$:DyQ$YDyDyQ$YDyQ$YH rct|S)zConvert ordinal to unicode. Note, in the original Javascript two string characters were required, for codepoints larger than `0xFFFF`. But Python 3 can represent any unicode codepoint in one character. )chrr s r fromCodePointr%Ns  q6MrzD\\([!"#$%&\'()*+,\-.\/:;<=>?@[\\\]^_`{|}~])|&([a-z#][a-z0-9]{1,31});z #([0-9]{1,8})z#x([a-f0-9]{1,8})c&|tvr t|Sd}tj|x}rt|j dd}n2t j|x}rt|j dd}|t |r t|S|S)z^Convert HTML entity patterns, see https://spec.commonmark.org/0.30/#entity-references Nr )rDIGITAL_ENTITY_BASE10_RE fullmatchintgroupDIGITAL_ENTITY_BASE16_REr"r%)matchnamecodepats rreplaceEntityPatternr2bs x~D&0066s6399Q<$(2248 8 8399Q<$ -d3T"" LrcJdd}d|vrd|vr|Stj||S)Nc|jd}|r|S|jd}t|j|S)Nr)r,r2)r.escapedentitys r replacer_funcz"unescapeAll..replacer_funcvs7++a. NQ#EKKM6::r\&)r.z Match[str]returnstr)UNESCAPE_ALL_REsub)stringr8s r unescapeAllr@us0; 6c/   }f 55rz#\\!"#$%&'()*+,./:;<=>?@\[\]^`{}|_~-z\\([z])c.tjd|S)zStrip escape \ charactersz\1) ESCAPE_CHARr>r?s r stripEscaperDs ??5& ))rc|jdd}|jdd}|jdd}|jdd}|S) zHReplace special characters "&", "<", ">" and '"' to HTML-safe sequences.r:z&z>"z")replace)raws r escapeHtmlrKsI ++c7 #C ++c6 "C ++c6 "C ++c8 $C Jrz[.?*+^$[\]\\(){}|-]c2tjd|}|S)Nz\$&)REGEXP_ESCAPE_REr>rCs rescapeRErNs  ! !&& 1F Mrc |dvS)z(Check if character code is a whitespace.) rr0s risSpacerSs < rc |dvS)z#Check if character is a whitespace.)  rchs r isStrSpacerYs  r> 0/ _ rPr'r rQc(|dk\r|dkry|tvS)z"Zs (unicode class) || [\t\f\v\r\n]i i T) MD_WHITESPACErRs r isWhiteSpacercs v~$&. =  rcJtj|jdS)z.Check if character is a punctuation character.)PS) unicodedatacategory startswithrWs r isPunctCharrjs    # . .z ::r> !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~c|tvS)a9Markdown ASCII punctuation characters. :: !, ", #, $, %, &, ', (, ), *, +, ,, -, ., /, :, ;, <, =, >, ?, @, [, \, ], ^, _, `, {, |, }, or ~ See http://spec.commonmark.org/0.15/#ascii-punctuation-character Don't confuse with unicode punctuation !!! It lacks some chars in ascii range. )MD_ASCII_PUNCTrWs risMdAsciiPunctrs  rctjdd|j}|jj S)z#Helper to unify [reference labels].z\s+rV)rer>striplowerupperrCs rnormalizeReferencers4VVFC 0FX <<>   !!rz^\s])flagsz^c>ttj|SN)bool LINK_OPEN_REsearchrCs r isLinkOpenr4s  ##F+ ,,rc>ttj|Sr)r LINK_CLOSE_RErrCs r isLinkCloser8s  $$V, --r)r r<rr+r; int | None)r r<rr+r; str | None)r list[_ItemTV]rr+rrr;r)r!r+r;r)r!r+r;r<)r.r<r/r<r;r<)r?r<r;r<)rJr<r;r<)r0rr;r)rXrr;r)r0r+r;r)rXr<r;r)rXr+r;r)r?r<r;r)(__doc__ __future__rrrtypingrrgrrrrrr"r%compile IGNORECASEr=r)r-r2r@ ESCAPABLErBrDrKrMrNrSrYrbrcrjrrrrrrrrrrrs['"    ) 4 4 4/<44,"**VMM&2::&67%2::&:BMMJ& 6 7 bjj9,u45 * 2::45   !; !H  0"frzz+R]];  ;bmm< -.r