U
    Sh)                      @  s8  d Z ddlmZ ddlZddlmZmZ ddlmZ ddd	d
ddZdddd
ddZ	edZ
dddddddZdddddZdddddZedejZedZedejZdddddd Zddd!d"d#Zd$Zed%e d& Zddd!d'd(Zddd)d*d+Zed,Zddd!d-d.Zd	dd/d0d1Zddd2d3d4Zd5d6d7d8d9d:d;d<d=d>d?hZddd/d@dAZedBZddd2dCdDZ dEdFdGdHdIdJdKdLdMdNdOdPdQdRdSdTdUdVdWdXdYdZd[d\d]d^d_d`dadbdcddh Z!ddd2dedfZ"ddd!dgdhZ#ejdiejdjZ$ejdkejdjZ%ddd!dldmZ&ddd!dndoZ'dS )pz"Utilities for parsing source text
    )annotationsN)MatchTypeVar   )entitiesstrintz
int | None)srcposreturnc                 C  s*   zt | | W S  tk
r$   Y dS X dS a
  
    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
IndexErrorr	   r
    r   K/root/rtd-docs/venv/lib/python3.8/site-packages/markdown_it/common/utils.py
charCodeAt   s    	r   z
str | Nonec                 C  s&   z
| | W S  t k
r    Y dS X dS r   )r   r   r   r   r   	charStrAt   s    	
r   _ItemTVzlist[_ItemTV])r	   r
   newElementsr   c                 C  s    | d| | | |d d  S )zw
    Remove element from array and put another array at those position.
    Useful for some operations with tokens
    Nr   r   )r	   r
   r   r   r   r   arrayReplaceAt,   s    r   bool)cr   c                 C  s   | dkr| dkrdS | dkr(| dkr(dS | d@ dks@| d@ dkrDdS | dkrX| d	krXdS | d
krddS | dkrx| dkrxdS | dkr| dkrdS | dkrdS dS )Ni   i  Fi  i  i  i  r                     i Tr   r   r   r   r   isValidEntityCode6   s"    r    c                 C  s   t | 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   r   r   r   fromCodePointN   s    r"   zD\\([!"#$%&\'()*+,\-.\/:;<=>?@[\\\]^_`{|}~])|&([a-z#][a-z0-9]{1,31});z#([0-9]{1,8})z#x([a-f0-9]{1,8}))matchnamer   c                 C  sn   |t krt | S d}t| }r4t|dd}nt| }rRt|dd}|dk	rjt|rjt|S | S )z^Convert HTML entity patterns,
    see https://spec.commonmark.org/0.30/#entity-references
    Nr   
      )r   DIGITAL_ENTITY_BASE10_RE	fullmatchr   groupDIGITAL_ENTITY_BASE16_REr    r"   )r#   r$   codepatr   r   r   replaceEntityPatternb   s    r-   )stringr   c                 C  s0   ddddd}d| kr$d| kr$| S t || S )Nz
Match[str]r   )r#   r   c                 S  s*   |  d}|r|S |  d}t|   |S )Nr      )r)   r-   )r#   escapedentityr   r   r   replacer_funcv   s
    

z"unescapeAll.<locals>.replacer_func\&)UNESCAPE_ALL_REsub)r.   r2   r   r   r   unescapeAllu   s    r7   z#\\!"#$%&'()*+,./:;<=>?@\[\]^`{}|_~-z\\([z])c                 C  s   t d| S )zStrip escape \ charactersz\1)ESCAPE_CHARr6   r.   r   r   r   stripEscape   s    r:   )rawr   c                 C  s4   |  dd} |  dd} |  dd} |  dd} | S )	zHReplace special characters "&", "<", ">" and '"' to HTML-safe sequences.r4   z&amp;<z&lt;>z&gt;"z&quot;)replace)r;   r   r   r   
escapeHtml   s
    r@   z[.?*+^$[\]\\(){}|-]c                 C  s   t d| } | S )Nz\$&)REGEXP_ESCAPE_REr6   r9   r   r   r   escapeRE   s    rB   )r+   r   c                 C  s   | dkS )z(Check if character code is a whitespace.)	       r   r+   r   r   r   isSpace   s    rF   )chr   c                 C  s   | dkS )z#Check if character is a whitespace.)	 r   rG   r   r   r   
isStrSpace   s    rK   rC   r%   r         rD      i  i/   i_   i 0  c                 C  s   | dkr| dkrdS | t kS )z"Zs (unicode class) || [\t\f\v\r\n]i    i
   T)MD_WHITESPACErE   r   r   r   isWhiteSpace   s    rP   ab  [!-#%-\*,-\/:;\?@\[-\]_\{\}\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]c                 C  s   t | dk	S )z.Check if character is a punctuation character.N)UNICODE_PUNCT_REsearchrJ   r   r   r   isPunctChar   s    rS   !   "   #   $   %   &   '   (   )   *   +   ,   -   .   /   :   ;   <   =   >   ?   @   [   \   ]   ^   _   `   {   |   }   ~   c                 C  s   | t kS )a9  Markdown 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_PUNCTrJ   r   r   r   isMdAsciiPunct   s    ru   c                 C  s   t dd|  } |   S )z#Helper to unify [reference labels].z\s+rI   )rer6   striplowerupperr9   r   r   r   normalizeReference  s    ,rz   z^<a[>\s])flagsz^</a\s*>c                 C  s   t t| S N)r   LINK_OPEN_RErR   r9   r   r   r   
isLinkOpen9  s    r~   c                 C  s   t t| S r|   )r   LINK_CLOSE_RErR   r9   r   r   r   isLinkClose=  s    r   )(__doc__
__future__r   rv   typingr   r   r   r   r   r   r   r    r"   compile
IGNORECASEr5   r'   r*   r-   r7   Z	ESCAPABLEr8   r:   r@   rA   rB   rF   rK   rO   rP   rQ   rS   rt   ru   rz   r}   r   r~   r   r   r   r   r   <module>   s   


	$3