markdown.js 4.9 KB
Newer Older
DCloud_JSON's avatar
DCloud_JSON 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241
/*
Language: Markdown
Requires: xml.js
Author: John Crepezzi <john.crepezzi@gmail.com>
Website: https://daringfireball.net/projects/markdown/
Category: common, markup
*/

function markdown(hljs) {
  const regex = hljs.regex;
  const INLINE_HTML = {
    begin: /<\/?[A-Za-z_]/,
    end: '>',
    subLanguage: 'xml',
    relevance: 0
  };
  const HORIZONTAL_RULE = {
    begin: '^[-\\*]{3,}',
    end: '$'
  };
  const CODE = {
    className: 'code',
    variants: [
      // TODO: fix to allow these to work with sublanguage also
      { begin: '(`{3,})[^`](.|\\n)*?\\1`*[ ]*' },
      { begin: '(~{3,})[^~](.|\\n)*?\\1~*[ ]*' },
      // needed to allow markdown as a sublanguage to work
      {
        begin: '```',
        end: '```+[ ]*$'
      },
      {
        begin: '~~~',
        end: '~~~+[ ]*$'
      },
      { begin: '`.+?`' },
      {
        begin: '(?=^( {4}|\\t))',
        // use contains to gobble up multiple lines to allow the block to be whatever size
        // but only have a single open/close tag vs one per line
        contains: [
          {
            begin: '^( {4}|\\t)',
            end: '(\\n)$'
          }
        ],
        relevance: 0
      }
    ]
  };
  const LIST = {
    className: 'bullet',
    begin: '^[ \t]*([*+-]|(\\d+\\.))(?=\\s+)',
    end: '\\s+',
    excludeEnd: true
  };
  const LINK_REFERENCE = {
    begin: /^\[[^\n]+\]:/,
    returnBegin: true,
    contains: [
      {
        className: 'symbol',
        begin: /\[/,
        end: /\]/,
        excludeBegin: true,
        excludeEnd: true
      },
      {
        className: 'link',
        begin: /:\s*/,
        end: /$/,
        excludeBegin: true
      }
    ]
  };
  const URL_SCHEME = /[A-Za-z][A-Za-z0-9+.-]*/;
  const LINK = {
    variants: [
      // too much like nested array access in so many languages
      // to have any real relevance
      {
        begin: /\[.+?\]\[.*?\]/,
        relevance: 0
      },
      // popular internet URLs
      {
        begin: /\[.+?\]\(((data|javascript|mailto):|(?:http|ftp)s?:\/\/).*?\)/,
        relevance: 2
      },
      {
        begin: regex.concat(/\[.+?\]\(/, URL_SCHEME, /:\/\/.*?\)/),
        relevance: 2
      },
      // relative urls
      {
        begin: /\[.+?\]\([./?&#].*?\)/,
        relevance: 1
      },
      // whatever else, lower relevance (might not be a link at all)
      {
        begin: /\[.*?\]\(.*?\)/,
        relevance: 0
      }
    ],
    returnBegin: true,
    contains: [
      {
        // empty strings for alt or link text
        match: /\[(?=\])/ },
      {
        className: 'string',
        relevance: 0,
        begin: '\\[',
        end: '\\]',
        excludeBegin: true,
        returnEnd: true
      },
      {
        className: 'link',
        relevance: 0,
        begin: '\\]\\(',
        end: '\\)',
        excludeBegin: true,
        excludeEnd: true
      },
      {
        className: 'symbol',
        relevance: 0,
        begin: '\\]\\[',
        end: '\\]',
        excludeBegin: true,
        excludeEnd: true
      }
    ]
  };
  const BOLD = {
    className: 'strong',
    contains: [], // defined later
    variants: [
      {
        begin: /_{2}(?!\s)/,
        end: /_{2}/
      },
      {
        begin: /\*{2}(?!\s)/,
        end: /\*{2}/
      }
    ]
  };
  const ITALIC = {
    className: 'emphasis',
    contains: [], // defined later
    variants: [
      {
        begin: /\*(?![*\s])/,
        end: /\*/
      },
      {
        begin: /_(?![_\s])/,
        end: /_/,
        relevance: 0
      }
    ]
  };

  // 3 level deep nesting is not allowed because it would create confusion
  // in cases like `***testing***` because where we don't know if the last
  // `***` is starting a new bold/italic or finishing the last one
  const BOLD_WITHOUT_ITALIC = hljs.inherit(BOLD, { contains: [] });
  const ITALIC_WITHOUT_BOLD = hljs.inherit(ITALIC, { contains: [] });
  BOLD.contains.push(ITALIC_WITHOUT_BOLD);
  ITALIC.contains.push(BOLD_WITHOUT_ITALIC);

  let CONTAINABLE = [
    INLINE_HTML,
    LINK
  ];

  [
    BOLD,
    ITALIC,
    BOLD_WITHOUT_ITALIC,
    ITALIC_WITHOUT_BOLD
  ].forEach(m => {
    m.contains = m.contains.concat(CONTAINABLE);
  });

  CONTAINABLE = CONTAINABLE.concat(BOLD, ITALIC);

  const HEADER = {
    className: 'section',
    variants: [
      {
        begin: '^#{1,6}',
        end: '$',
        contains: CONTAINABLE
      },
      {
        begin: '(?=^.+?\\n[=-]{2,}$)',
        contains: [
          { begin: '^[=-]*$' },
          {
            begin: '^',
            end: "\\n",
            contains: CONTAINABLE
          }
        ]
      }
    ]
  };

  const BLOCKQUOTE = {
    className: 'quote',
    begin: '^>\\s+',
    contains: CONTAINABLE,
    end: '$'
  };

  return {
    name: 'Markdown',
    aliases: [
      'md',
      'mkdown',
      'mkd'
    ],
    contains: [
      HEADER,
      INLINE_HTML,
      LIST,
      BOLD,
      ITALIC,
      BLOCKQUOTE,
      CODE,
      HORIZONTAL_RULE,
      LINK,
      LINK_REFERENCE
    ]
  };
}

export { markdown as default };