marked/src/rules.js

import {
  noopTest,
  edit,
  merge
} from './helpers.js';

/**
 * Block-Level Grammar
 */
export const block = {
  newline: /^(?: *(?:\n|$))+/,
  code: /^( {4}[^\n]+(?:\n(?: *(?:\n|$))*)?)+/,
  fences: /^ {0,3}(`{3,}(?=[^`\n]*\n)|~{3,})([^\n]*)\n(?:|([\s\S]*?)\n)(?: {0,3}\1[~`]* *(?=\n|$)|$)/,
  hr: /^ {0,3}((?:- *){3,}|(?:_ *){3,}|(?:\* *){3,})(?:\n+|$)/,
  heading: /^ {0,3}(#{1,6})(?=\s|$)(.*)(?:\n+|$)/,
  blockquote: /^( {0,3}> ?(paragraph|[^\n]*)(?:\n|$))+/,
  list: /^( {0,3}bull)( [^\n]+?)?(?:\n|$)/,
  html: '^ {0,3}(?:' // optional indentation
    + '<(script|pre|style|textarea)[\\s>][\\s\\S]*?(?:</\\1>[^\\n]*\\n+|$)' // (1)
    + '|comment[^\\n]*(\\n+|$)' // (2)
    + '|<\\?[\\s\\S]*?(?:\\?>\\n*|$)' // (3)
    + '|<![A-Z][\\s\\S]*?(?:>\\n*|$)' // (4)
    + '|<!\\[CDATA\\[[\\s\\S]*?(?:\\]\\]>\\n*|$)' // (5)
    + '|</?(tag)(?: +|\\n|/?>)[\\s\\S]*?(?:(?:\\n *)+\\n|$)' // (6)
    + '|<(?!script|pre|style|textarea)([a-z][\\w-]*)(?:attribute)*? */?>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n *)+\\n|$)' // (7) open tag
    + '|</(?!script|pre|style|textarea)[a-z][\\w-]*\\s*>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:(?:\\n *)+\\n|$)' // (7) closing tag
    + ')',
  def: /^ {0,3}\[(label)\]: *(?:\n *)?<?([^\s>]+)>?(?:(?: +(?:\n *)?| *\n *)(title))? *(?:\n+|$)/,
  table: noopTest,
  lheading: /^([^\n]+)\n {0,3}(=+|-+) *(?:\n+|$)/,
  // regex template, placeholders will be replaced according to different paragraph
  // interruption rules of commonmark and the original markdown spec:
  _paragraph: /^([^\n]+(?:\n(?!hr|heading|lheading|blockquote|fences|list|html|table| +\n)[^\n]+)*)/,
  text: /^[^\n]+/
};

block._label = /(?!\s*\])(?:\\.|[^\[\]\\])+/;
block._title = /(?:"(?:\\"?|[^"\\])*"|'[^'\n]*(?:\n[^'\n]+)*\n?'|\([^()]*\))/;
block.def = edit(block.def)
  .replace('label', block._label)
  .replace('title', block._title)
  .getRegex();

block.bullet = /(?:[*+-]|\d{1,9}[.)])/;
block.listItemStart = edit(/^( *)(bull) */)
  .replace('bull', block.bullet)
  .getRegex();

block.list = edit(block.list)
  .replace(/bull/g, block.bullet)
  .replace('hr', '\\n+(?=\\1?(?:(?:- *){3,}|(?:_ *){3,}|(?:\\* *){3,})(?:\\n+|$))')
  .replace('def', '\\n+(?=' + block.def.source + ')')
  .getRegex();

block._tag = 'address|article|aside|base|basefont|blockquote|body|caption'
  + '|center|col|colgroup|dd|details|dialog|dir|div|dl|dt|fieldset|figcaption'
  + '|figure|footer|form|frame|frameset|h[1-6]|head|header|hr|html|iframe'
  + '|legend|li|link|main|menu|menuitem|meta|nav|noframes|ol|optgroup|option'
  + '|p|param|section|source|summary|table|tbody|td|tfoot|th|thead|title|tr'
  + '|track|ul';
block._comment = /<!--(?!-?>)[\s\S]*?(?:-->|$)/;
block.html = edit(block.html, 'i')
  .replace('comment', block._comment)
  .replace('tag', block._tag)
  .replace('attribute', / +[a-zA-Z:_][\w.:-]*(?: *= *"[^"\n]*"| *= *'[^'\n]*'| *= *[^\s"'=<>`]+)?/)
  .getRegex();

block.paragraph = edit(block._paragraph)
  .replace('hr', block.hr)
  .replace('heading', ' {0,3}#{1,6} ')
  .replace('|lheading', '') // setex headings don't interrupt commonmark paragraphs
  .replace('|table', '')
  .replace('blockquote', ' {0,3}>')
  .replace('fences', ' {0,3}(?:`{3,}(?=[^`\\n]*\\n)|~{3,})[^\\n]*\\n')
  .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt
  .replace('html', '</?(?:tag)(?: +|\\n|/?>)|<(?:script|pre|style|textarea|!--)')
  .replace('tag', block._tag) // pars can be interrupted by type (6) html blocks
  .getRegex();

block.blockquote = edit(block.blockquote)
  .replace('paragraph', block.paragraph)
  .getRegex();

/**
 * Normal Block Grammar
 */

block.normal = merge({}, block);

/**
 * GFM Block Grammar
 */

block.gfm = merge({}, block.normal, {
  table: '^ *([^\\n ].*\\|.*)\\n' // Header
    + ' {0,3}(?:\\| *)?(:?-+:? *(?:\\| *:?-+:? *)*)(?:\\| *)?' // Align
    + '(?:\\n((?:(?! *\\n|hr|heading|blockquote|code|fences|list|html).*(?:\\n|$))*)\\n*|$)' // Cells
});

block.gfm.table = edit(block.gfm.table)
  .replace('hr', block.hr)
  .replace('heading', ' {0,3}#{1,6} ')
  .replace('blockquote', ' {0,3}>')
  .replace('code', ' {4}[^\\n]')
  .replace('fences', ' {0,3}(?:`{3,}(?=[^`\\n]*\\n)|~{3,})[^\\n]*\\n')
  .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt
  .replace('html', '</?(?:tag)(?: +|\\n|/?>)|<(?:script|pre|style|textarea|!--)')
  .replace('tag', block._tag) // tables can be interrupted by type (6) html blocks
  .getRegex();

block.gfm.paragraph = edit(block._paragraph)
  .replace('hr', block.hr)
  .replace('heading', ' {0,3}#{1,6} ')
  .replace('|lheading', '') // setex headings don't interrupt commonmark paragraphs
  .replace('table', block.gfm.table) // interrupt paragraphs with table
  .replace('blockquote', ' {0,3}>')
  .replace('fences', ' {0,3}(?:`{3,}(?=[^`\\n]*\\n)|~{3,})[^\\n]*\\n')
  .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt
  .replace('html', '</?(?:tag)(?: +|\\n|/?>)|<(?:script|pre|style|textarea|!--)')
  .replace('tag', block._tag) // pars can be interrupted by type (6) html blocks
  .getRegex();
/**
 * Pedantic grammar (original John Gruber's loose markdown specification)
 */

block.pedantic = merge({}, block.normal, {
  html: edit(
    '^ *(?:comment *(?:\\n|\\s*$)'
    + '|<(tag)[\\s\\S]+?</\\1> *(?:\\n{2,}|\\s*$)' // closed tag
    + '|<tag(?:"[^"]*"|\'[^\']*\'|\\s[^\'"/>\\s]*)*?/?> *(?:\\n{2,}|\\s*$))')
    .replace('comment', block._comment)
    .replace(/tag/g, '(?!(?:'
      + 'a|em|strong|small|s|cite|q|dfn|abbr|data|time|code|var|samp|kbd|sub'
      + '|sup|i|b|u|mark|ruby|rt|rp|bdi|bdo|span|br|wbr|ins|del|img)'
      + '\\b)\\w+(?!:|[^\\w\\s@]*@)\\b')
    .getRegex(),
  def: /^ *\[([^\]]+)\]: *<?([^\s>]+)>?(?: +(["(][^\n]+[")]))? *(?:\n+|$)/,
  heading: /^(#{1,6})(.*)(?:\n+|$)/,
  fences: noopTest, // fences not supported
  paragraph: edit(block.normal._paragraph)
    .replace('hr', block.hr)
    .replace('heading', ' *#{1,6} *[^\n]')
    .replace('lheading', block.lheading)
    .replace('blockquote', ' {0,3}>')
    .replace('|fences', '')
    .replace('|list', '')
    .replace('|html', '')
    .getRegex()
});

/**
 * Inline-Level Grammar
 */
export const inline = {
  escape: /^\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/,
  autolink: /^<(scheme:[^\s\x00-\x1f<>]*|email)>/,
  url: noopTest,
  tag: '^comment'
    + '|^</[a-zA-Z][\\w:-]*\\s*>' // self-closing tag
    + '|^<[a-zA-Z][\\w-]*(?:attribute)*?\\s*/?>' // open tag
    + '|^<\\?[\\s\\S]*?\\?>' // processing instruction, e.g. <?php ?>
    + '|^<![a-zA-Z]+\\s[\\s\\S]*?>' // declaration, e.g. <!DOCTYPE html>
    + '|^<!\\[CDATA\\[[\\s\\S]*?\\]\\]>', // CDATA section
  link: /^!?\[(label)\]\(\s*(href)(?:\s+(title))?\s*\)/,
  reflink: /^!?\[(label)\]\[(ref)\]/,
  nolink: /^!?\[(ref)\](?:\[\])?/,
  reflinkSearch: 'reflink|nolink(?!\\()',
  emStrong: {
    lDelim: /^(?:\*+(?:([punct_])|[^\s*]))|^_+(?:([punct*])|([^\s_]))/,
    //        (1) and (2) can only be a Right Delimiter. (3) and (4) can only be Left.  (5) and (6) can be either Left or Right.
    //        () Skip orphan delim inside strong    (1) #***                (2) a***#, a***                   (3) #***a, ***a                 (4) ***#              (5) #***#                 (6) a***a
    rDelimAst: /^[^_*]*?\_\_[^_*]*?\*[^_*]*?(?=\_\_)|[punct_](\*+)(?=[\s]|$)|[^punct*_\s](\*+)(?=[punct_\s]|$)|[punct_\s](\*+)(?=[^punct*_\s])|[\s](\*+)(?=[punct_])|[punct_](\*+)(?=[punct_])|[^punct*_\s](\*+)(?=[^punct*_\s])/,
    rDelimUnd: /^[^_*]*?\*\*[^_*]*?\_[^_*]*?(?=\*\*)|[punct*](\_+)(?=[\s]|$)|[^punct*_\s](\_+)(?=[punct*\s]|$)|[punct*\s](\_+)(?=[^punct*_\s])|[\s](\_+)(?=[punct*])|[punct*](\_+)(?=[punct*])/ // ^- Not allowed for _
  },
  code: /^(`+)([^`]|[^`][\s\S]*?[^`])\1(?!`)/,
  br: /^( {2,}|\\)\n(?!\s*$)/,
  del: noopTest,
  text: /^(`+|[^`])(?:(?= {2,}\n)|[\s\S]*?(?:(?=[\\<!\[`*_]|\b_|$)|[^ ](?= {2,}\n)))/,
  punctuation: /^([\spunctuation])/
};

// list of punctuation marks from CommonMark spec
// without * and _ to handle the different emphasis markers * and _
inline._punctuation = '!"#$%&\'()+\\-.,/:;<=>?@\\[\\]`^{|}~';
inline.punctuation = edit(inline.punctuation).replace(/punctuation/g, inline._punctuation).getRegex();

// sequences em should skip over [title](link), `code`, <html>
inline.blockSkip = /\[[^\]]*?\]\([^\)]*?\)|`[^`]*?`|<[^>]*?>/g;
inline.escapedEmSt = /\\\*|\\_/g;

inline._comment = edit(block._comment).replace('(?:-->|$)', '-->').getRegex();

inline.emStrong.lDelim = edit(inline.emStrong.lDelim)
  .replace(/punct/g, inline._punctuation)
  .getRegex();

inline.emStrong.rDelimAst = edit(inline.emStrong.rDelimAst, 'g')
  .replace(/punct/g, inline._punctuation)
  .getRegex();

inline.emStrong.rDelimUnd = edit(inline.emStrong.rDelimUnd, 'g')
  .replace(/punct/g, inline._punctuation)
  .getRegex();

inline._escapes = /\\([!"#$%&'()*+,\-./:;<=>?@\[\]\\^_`{|}~])/g;

inline._scheme = /[a-zA-Z][a-zA-Z0-9+.-]{1,31}/;
inline._email = /[a-zA-Z0-9.!#$%&'*+/=?^_`{|}~-]+(@)[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)+(?![-_])/;
inline.autolink = edit(inline.autolink)
  .replace('scheme', inline._scheme)
  .replace('email', inline._email)
  .getRegex();

inline._attribute = /\s+[a-zA-Z:_][\w.:-]*(?:\s*=\s*"[^"]*"|\s*=\s*'[^']*'|\s*=\s*[^\s"'=<>`]+)?/;

inline.tag = edit(inline.tag)
  .replace('comment', inline._comment)
  .replace('attribute', inline._attribute)
  .getRegex();

inline._label = /(?:\[(?:\\.|[^\[\]\\])*\]|\\.|`[^`]*`|[^\[\]\\`])*?/;
inline._href = /<(?:\\.|[^\n<>\\])+>|[^\s\x00-\x1f]*/;
inline._title = /"(?:\\"?|[^"\\])*"|'(?:\\'?|[^'\\])*'|\((?:\\\)?|[^)\\])*\)/;

inline.link = edit(inline.link)
  .replace('label', inline._label)
  .replace('href', inline._href)
  .replace('title', inline._title)
  .getRegex();

inline.reflink = edit(inline.reflink)
  .replace('label', inline._label)
  .replace('ref', block._label)
  .getRegex();

inline.nolink = edit(inline.nolink)
  .replace('ref', block._label)
  .getRegex();

inline.reflinkSearch = edit(inline.reflinkSearch, 'g')
  .replace('reflink', inline.reflink)
  .replace('nolink', inline.nolink)
  .getRegex();

/**
 * Normal Inline Grammar
 */

inline.normal = merge({}, inline);

/**
 * Pedantic Inline Grammar
 */

inline.pedantic = merge({}, inline.normal, {
  strong: {
    start: /^__|\*\*/,
    middle: /^__(?=\S)([\s\S]*?\S)__(?!_)|^\*\*(?=\S)([\s\S]*?\S)\*\*(?!\*)/,
    endAst: /\*\*(?!\*)/g,
    endUnd: /__(?!_)/g
  },
  em: {
    start: /^_|\*/,
    middle: /^()\*(?=\S)([\s\S]*?\S)\*(?!\*)|^_(?=\S)([\s\S]*?\S)_(?!_)/,
    endAst: /\*(?!\*)/g,
    endUnd: /_(?!_)/g
  },
  link: edit(/^!?\[(label)\]\((.*?)\)/)
    .replace('label', inline._label)
    .getRegex(),
  reflink: edit(/^!?\[(label)\]\s*\[([^\]]*)\]/)
    .replace('label', inline._label)
    .getRegex()
});

/**
 * GFM Inline Grammar
 */

inline.gfm = merge({}, inline.normal, {
  escape: edit(inline.escape).replace('])', '~|])').getRegex(),
  _extended_email: /[A-Za-z0-9._+-]+(@)[a-zA-Z0-9-_]+(?:\.[a-zA-Z0-9-_]*[a-zA-Z0-9])+(?![-_])/,
  url: /^((?:ftp|https?):\/\/|www\.)(?:[a-zA-Z0-9\-]+\.?)+[^\s<]*|^email/,
  _backpedal: /(?:[^?!.,:;*_~()&]+|\([^)]*\)|&(?![a-zA-Z0-9]+;$)|[?!.,:;*_~)]+(?!$))+/,
  del: /^(~~?)(?=[^\s~])([\s\S]*?[^\s~])\1(?=[^~]|$)/,
  text: /^([`~]+|[^`~])(?:(?= {2,}\n)|(?=[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@)|[\s\S]*?(?:(?=[\\<!\[`*~_]|\b_|https?:\/\/|ftp:\/\/|www\.|$)|[^ ](?= {2,}\n)|[^a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-](?=[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@)))/
});

inline.gfm.url = edit(inline.gfm.url, 'i')
  .replace('email', inline.gfm._extended_email)
  .getRegex();
/**
 * GFM + Line Breaks Inline Grammar
 */

inline.breaks = merge({}, inline.gfm, {
  br: edit(inline.br).replace('{2,}', '*').getRegex(),
  text: edit(inline.gfm.text)
    .replace('\\b_', '\\b_| {2,}\\n')
    .replace(/\{2,\}/g, '*')
    .getRegex()
});