marked/src/rules.js

const {
  noopTest,
  edit,
  merge
} = require('./helpers.js');

/**
 * Block-Level Grammar
 */
const block = {
  newline: /^\n+/,
  code: /^( {4}[^\n]+\n*)+/,
  fences: /^ {0,3}(`{3,}|~{3,})([^`~\n]*)\n(?:|([\s\S]*?)\n)(?: {0,3}\1[~`]* *(?:\n+|$)|$)/,
  hr: /^ {0,3}((?:- *){3,}|(?:_ *){3,}|(?:\* *){3,})(?:\n+|$)/,
  heading: /^ {0,3}(#{1,6}) +([^\n]*?)(?: +#+)? *(?:\n+|$)/,
  blockquote: /^( {0,3}> ?(paragraph|[^\n]*)(?:\n|$))+/,
  list: /^( {0,3})(bull) [\s\S]+?(?:hr|def|\n{2,}(?! )(?!\1bull )\n*|\s*$)/,
  html: '^ {0,3}(?:' // optional indentation
    + '<(script|pre|style)[\\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{2,}|$)' // (6)
    + '|<(?!script|pre|style)([a-z][\\w-]*)(?:attribute)*? */?>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:\\n{2,}|$)' // (7) open tag
    + '|</(?!script|pre|style)[a-z][\\w-]*\\s*>(?=[ \\t]*(?:\\n|$))[\\s\\S]*?(?:\\n{2,}|$)' // (7) closing tag
    + ')',
  def: /^ {0,3}\[(label)\]: *\n? *<?([^\s>]+)>?(?:(?: +\n? *| *\n *)(title))? *(?:\n+|$)/,
  nptable: noopTest,
  table: noopTest,
  lheading: /^([^\n]+)\n {0,3}(=+|-+) *(?:\n+|$)/,
  // 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)[^\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.item = /^( *)(bull) ?[^\n]*(?:\n(?!\1bull ?)[^\n]*)*/;
block.item = edit(block.item, 'gm')
  .replace(/bull/g, 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('blockquote', ' {0,3}>')
  .replace('fences', ' {0,3}(?:`{3,}|~{3,})[^`\\n]*\\n')
  .replace('list', ' {0,3}(?:[*+-]|1[.)]) ') // only lists starting from 1 can interrupt
  .replace('html', '</?(?:tag)(?: +|\\n|/?>)|<(?:script|pre|style|!--)')
  .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, {
  nptable: /^ *([^|\n ].*\|.*)\n *([-:]+ *\|[-| :]*)(?:\n((?:.*[^>\n ].*(?:\n|$))*)\n*|$)/,
  table: /^ *\|(.+)\n *\|?( *[-:]+[-| :]*)(?:\n((?: *[^>\n ].*(?:\n|$))*)\n*|$)/
});

/**
 * 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+|$)/,
  heading: /^ *(#{1,6}) *([^\n]+?) *(?:#+ *)?(?:\n+|$)/,
  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
 */
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: /^!?\[(label)\]\[(?!\s*\])((?:\\[\[\]]?|[^\[\]\\])+)\]/,
  nolink: /^!?\[(?!\s*\])((?:\[[^\[\]]*\]|\\[\[\]]|[^\[\]])*)\](?:\[\])?/,
  strong: /^__([^\s_])__(?!_)|^\*\*([^\s*])\*\*(?!\*)|^__([^\s][\s\S]*?[^\s])__(?!_)|^\*\*([^\s][\s\S]*?[^\s])\*\*(?!\*)/,
  em: /^_([^\s_])_(?!_)|^\*([^\s*<\[])\*(?!\*)|^_([^\s<][\s\S]*?[^\s_])_(?!_|[^\spunctuation])|^_([^\s_<][\s\S]*?[^\s])_(?!_|[^\spunctuation])|^\*([^\s<"][\s\S]*?[^\s\*])\*(?!\*|[^\spunctuation])|^\*([^\s*"<\[][\s\S]*?[^\s])\*(?!\*)/,
  code: /^(`+)([^`]|[^`][\s\S]*?[^`])\1(?!`)/,
  br: /^( {2,}|\\)\n(?!\s*$)/,
  del: noopTest,
  text: /^(`+|[^`])(?:[\s\S]*?(?:(?=[\\<!\[`*]|\b_|$)|[^ ](?= {2,}\n))|(?= {2,}\n))/
};

// list of punctuation marks from common mark spec
// without ` and ] to workaround Rule 17 (inline code blocks/links)
inline._punctuation = '!"#$%&\'()*+,\\-./:;<=>?@\\[^_{|}~';
inline.em = edit(inline.em).replace(/punctuation/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', block._comment)
  .replace('attribute', inline._attribute)
  .getRegex();

inline._label = /(?:\[[^\[\]]*\]|\\.|`[^`]*`|[^\[\]\\`])*?/;
inline._href = /<(?:\\[<>]?|[^\s<>\\])*>|[^\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)
  .getRegex();

/**
 * Normal Inline Grammar
 */

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

/**
 * Pedantic Inline Grammar
 */

inline.pedantic = merge({}, inline.normal, {
  strong: /^__(?=\S)([\s\S]*?\S)__(?!_)|^\*\*(?=\S)([\s\S]*?\S)\*\*(?!\*)/,
  em: /^_(?=\S)([\s\S]*?\S)_(?!_)|^\*(?=\S)([\s\S]*?\S)\*(?!\*)/,
  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)~+/,
  text: /^(`+|[^`])(?:[\s\S]*?(?:(?=[\\<!\[`*~]|\b_|https?:\/\/|ftp:\/\/|www\.|$)|[^ ](?= {2,}\n)|[^a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-](?=[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@))|(?= {2,}\n|[a-zA-Z0-9.!#$%&'*+\/=?_`{\|}~-]+@))/
});

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()
});

module.exports = {
  block,
  inline
};