'Wd)dZddlmZddlZddlmZmZddlmZd'dZd(dZ ed Z d)d Z d*d Z d+d Z ejd ejZejdZejdejZd,dZd-dZdZejdezdzZd-dZd.dZejdZd-dZd/dZd0dZhdZd1dZejdZd2dZ hdZ!d3d Z"d-d!Z#ejd"ej#Z$ejd$ej#Z%d4d%Z&d4d&Z'y)5z"Utilities for parsing source text ) annotationsN)MatchTypeVar)entitiesc> t||S#t$rYywxYwa  Returns the Unicode value of the character at the specified location. @param - index The zero-based index of the desired character. If there is no character at the specified index, NaN is returned. This was added for compatibility with python N)ord IndexErrorsrcposs :/usr/lib/python3/dist-packages/markdown_it/common/utils.py charCodeAtr s'3s8} s  c, ||S#t$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|dkDryy)NiiFiiiir iTrcs risValidEntityCoder"6sF{qF{F{qF{ VQZF$:DyQ$YDyDyQ$YDyQ$Y8| 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~$&. =  rab[!-#%-\*,-\/:;\?@\[-\]_\{\}\xA1\xA7\xAB\xB6\xB7\xBB\xBF\u037E\u0387\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u09FD\u0A76\u0AF0\u0C84\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F14\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1360-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CC0-\u1CC7\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u2308-\u230B\u2329\u232A\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30-\u2E4E\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA8FC\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uAAF0\uAAF1\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]|\uD800[\uDD00-\uDD02\uDF9F\uDFD0]|\uD801\uDD6F|\uD802[\uDC57\uDD1F\uDD3F\uDE50-\uDE58\uDE7F\uDEF0-\uDEF6\uDF39-\uDF3F\uDF99-\uDF9C]|\uD803[\uDF55-\uDF59]|\uD804[\uDC47-\uDC4D\uDCBB\uDCBC\uDCBE-\uDCC1\uDD40-\uDD43\uDD74\uDD75\uDDC5-\uDDC8\uDDCD\uDDDB\uDDDD-\uDDDF\uDE38-\uDE3D\uDEA9]|\uD805[\uDC4B-\uDC4F\uDC5B\uDC5D\uDCC6\uDDC1-\uDDD7\uDE41-\uDE43\uDE60-\uDE6C\uDF3C-\uDF3E]|\uD806[\uDC3B\uDE3F-\uDE46\uDE9A-\uDE9C\uDE9E-\uDEA2]|\uD807[\uDC41-\uDC45\uDC70\uDC71\uDEF7\uDEF8]|\uD809[\uDC70-\uDC74]|\uD81A[\uDE6E\uDE6F\uDEF5\uDF37-\uDF3B\uDF44]|\uD81B[\uDE97-\uDE9A]|\uD82F\uDC9F|\uD836[\uDE87-\uDE8B]|\uD83A[\uDD5E\uDD5F]c0tj|duS)z.Check if character is a punctuation character.N)UNICODE_PUNCT_REsearchrWs r isPunctCharrgs  " "2 &d 22r> !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~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_RErfrCs r isLinkOpenr9s  ##F+ ,,rc>ttj|Sr)r LINK_CLOSE_RErfrCs r isLinkCloser=s  $$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__rrtypingrrrrrrrr"r%compile IGNORECASEr=r)r-r2r@ ESCAPABLErBrDrKrMrNrSrYrbrcrergrrrrrrrrrrrsp" !   ) 4 4 4/<440"**VMM&2::&67%2::&:BMMJ& 6 7 bjj9,u45 * 2::45   !2::j 3 !H  0"frzz+R]];  ;bmm< -.r