marked/src/Tokenizer.js

const { defaults } = require('./defaults.js');
const {
  rtrim,
  splitCells,
  escape,
  findClosingBracket
} = require('./helpers.js');

function outputLink(cap, link, raw) {
  const href = link.href;
  const title = link.title ? escape(link.title) : null;

  if (cap[0].charAt(0) !== '!') {
    return {
      type: 'link',
      raw,
      href,
      title,
      text: cap[1]
    };
  } else {
    return {
      type: 'image',
      raw,
      text: escape(cap[1]),
      href,
      title
    };
  }
}

function indentCodeCompensation(raw, text) {
  const matchIndentToCode = raw.match(/^(\s+)(?:```)/);

  if (matchIndentToCode === null) {
    return text;
  }

  const indentToCode = matchIndentToCode[1];

  return text
    .split('\n')
    .map(node => {
      const matchIndentInNode = node.match(/^\s+/);
      if (matchIndentInNode === null) {
        return node;
      }

      const [indentInNode] = matchIndentInNode;

      if (indentInNode.length >= indentToCode.length) {
        return node.slice(indentToCode.length);
      }

      return node;
    })
    .join('\n');
}

/**
 * Tokenizer
 */
module.exports = class Tokenizer {
  constructor(options) {
    this.options = options || defaults;
  }

  space(src) {
    const cap = this.rules.block.newline.exec(src);
    if (cap) {
      if (cap[0].length > 1) {
        return {
          type: 'space',
          raw: cap[0]
        };
      }
      return { raw: '\n' };
    }
  }

  code(src, tokens) {
    const cap = this.rules.block.code.exec(src);
    if (cap) {
      const lastToken = tokens[tokens.length - 1];
      // An indented code block cannot interrupt a paragraph.
      if (lastToken && lastToken.type === 'paragraph') {
        return {
          raw: cap[0],
          text: cap[0].trimRight()
        };
      }

      const text = cap[0].replace(/^ {4}/gm, '');
      return {
        type: 'code',
        raw: cap[0],
        codeBlockStyle: 'indented',
        text: !this.options.pedantic
          ? rtrim(text, '\n')
          : text
      };
    }
  }

  fences(src) {
    const cap = this.rules.block.fences.exec(src);
    if (cap) {
      const raw = cap[0];
      const text = indentCodeCompensation(raw, cap[3] || '');

      return {
        type: 'code',
        raw,
        lang: cap[2] ? cap[2].trim() : cap[2],
        text
      };
    }
  }

  heading(src) {
    const cap = this.rules.block.heading.exec(src);
    if (cap) {
      return {
        type: 'heading',
        raw: cap[0],
        depth: cap[1].length,
        text: cap[2]
      };
    }
  }

  nptable(src) {
    const cap = this.rules.block.nptable.exec(src);
    if (cap) {
      const item = {
        type: 'table',
        header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),
        align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),
        cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : [],
        raw: cap[0]
      };

      if (item.header.length === item.align.length) {
        let l = item.align.length;
        let i;
        for (i = 0; i < l; i++) {
          if (/^ *-+: *$/.test(item.align[i])) {
            item.align[i] = 'right';
          } else if (/^ *:-+: *$/.test(item.align[i])) {
            item.align[i] = 'center';
          } else if (/^ *:-+ *$/.test(item.align[i])) {
            item.align[i] = 'left';
          } else {
            item.align[i] = null;
          }
        }

        l = item.cells.length;
        for (i = 0; i < l; i++) {
          item.cells[i] = splitCells(item.cells[i], item.header.length);
        }

        return item;
      }
    }
  }

  hr(src) {
    const cap = this.rules.block.hr.exec(src);
    if (cap) {
      return {
        type: 'hr',
        raw: cap[0]
      };
    }
  }

  blockquote(src) {
    const cap = this.rules.block.blockquote.exec(src);
    if (cap) {
      const text = cap[0].replace(/^ *> ?/gm, '');

      return {
        type: 'blockquote',
        raw: cap[0],
        text
      };
    }
  }

  list(src) {
    const cap = this.rules.block.list.exec(src);
    if (cap) {
      let raw = cap[0];
      const bull = cap[2];
      const isordered = bull.length > 1;

      const list = {
        type: 'list',
        raw,
        ordered: isordered,
        start: isordered ? +bull : '',
        loose: false,
        items: []
      };

      // Get each top-level item.
      const itemMatch = cap[0].match(this.rules.block.item);

      let next = false,
        item,
        space,
        b,
        addBack,
        loose,
        istask,
        ischecked;

      const l = itemMatch.length;
      for (let i = 0; i < l; i++) {
        item = itemMatch[i];
        raw = item;

        // Remove the list item's bullet
        // so it is seen as the next token.
        space = item.length;
        item = item.replace(/^ *([*+-]|\d+\.) */, '');

        // Outdent whatever the
        // list item contains. Hacky.
        if (~item.indexOf('\n ')) {
          space -= item.length;
          item = !this.options.pedantic
            ? item.replace(new RegExp('^ {1,' + space + '}', 'gm'), '')
            : item.replace(/^ {1,4}/gm, '');
        }

        // Determine whether the next list item belongs here.
        // Backpedal if it does not belong in this list.
        if (i !== l - 1) {
          b = this.rules.block.bullet.exec(itemMatch[i + 1])[0];
          if (bull.length > 1 ? b.length === 1
            : (b.length > 1 || (this.options.smartLists && b !== bull))) {
            addBack = itemMatch.slice(i + 1).join('\n');
            list.raw = list.raw.substring(0, list.raw.length - addBack.length);
            i = l - 1;
          }
        }

        // Determine whether item is loose or not.
        // Use: /(^|\n)(?! )[^\n]+\n\n(?!\s*$)/
        // for discount behavior.
        loose = next || /\n\n(?!\s*$)/.test(item);
        if (i !== l - 1) {
          next = item.charAt(item.length - 1) === '\n';
          if (!loose) loose = next;
        }

        if (loose) {
          list.loose = true;
        }

        // Check for task list items
        istask = /^\[[ xX]\] /.test(item);
        ischecked = undefined;
        if (istask) {
          ischecked = item[1] !== ' ';
          item = item.replace(/^\[[ xX]\] +/, '');
        }

        list.items.push({
          type: 'list_item',
          raw,
          task: istask,
          checked: ischecked,
          loose: loose,
          text: item
        });
      }

      return list;
    }
  }

  html(src) {
    const cap = this.rules.block.html.exec(src);
    if (cap) {
      return {
        type: this.options.sanitize
          ? 'paragraph'
          : 'html',
        raw: cap[0],
        pre: !this.options.sanitizer
          && (cap[1] === 'pre' || cap[1] === 'script' || cap[1] === 'style'),
        text: this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]
      };
    }
  }

  def(src) {
    const cap = this.rules.block.def.exec(src);
    if (cap) {
      if (cap[3]) cap[3] = cap[3].substring(1, cap[3].length - 1);
      const tag = cap[1].toLowerCase().replace(/\s+/g, ' ');
      return {
        tag,
        raw: cap[0],
        href: cap[2],
        title: cap[3]
      };
    }
  }

  table(src) {
    const cap = this.rules.block.table.exec(src);
    if (cap) {
      const item = {
        type: 'table',
        header: splitCells(cap[1].replace(/^ *| *\| *$/g, '')),
        align: cap[2].replace(/^ *|\| *$/g, '').split(/ *\| */),
        cells: cap[3] ? cap[3].replace(/\n$/, '').split('\n') : []
      };

      if (item.header.length === item.align.length) {
        item.raw = cap[0];

        let l = item.align.length;
        let i;
        for (i = 0; i < l; i++) {
          if (/^ *-+: *$/.test(item.align[i])) {
            item.align[i] = 'right';
          } else if (/^ *:-+: *$/.test(item.align[i])) {
            item.align[i] = 'center';
          } else if (/^ *:-+ *$/.test(item.align[i])) {
            item.align[i] = 'left';
          } else {
            item.align[i] = null;
          }
        }

        l = item.cells.length;
        for (i = 0; i < l; i++) {
          item.cells[i] = splitCells(
            item.cells[i].replace(/^ *\| *| *\| *$/g, ''),
            item.header.length);
        }

        return item;
      }
    }
  }

  lheading(src) {
    const cap = this.rules.block.lheading.exec(src);
    if (cap) {
      return {
        type: 'heading',
        raw: cap[0],
        depth: cap[2].charAt(0) === '=' ? 1 : 2,
        text: cap[1]
      };
    }
  }

  paragraph(src) {
    const cap = this.rules.block.paragraph.exec(src);
    if (cap) {
      return {
        type: 'paragraph',
        raw: cap[0],
        text: cap[1].charAt(cap[1].length - 1) === '\n'
          ? cap[1].slice(0, -1)
          : cap[1]
      };
    }
  }

  text(src, tokens) {
    const cap = this.rules.block.text.exec(src);
    if (cap) {
      const lastToken = tokens[tokens.length - 1];
      if (lastToken && lastToken.type === 'text') {
        return {
          raw: cap[0],
          text: cap[0]
        };
      }

      return {
        type: 'text',
        raw: cap[0],
        text: cap[0]
      };
    }
  }

  escape(src) {
    const cap = this.rules.inline.escape.exec(src);
    if (cap) {
      return {
        type: 'escape',
        raw: cap[0],
        text: escape(cap[1])
      };
    }
  }

  tag(src, inLink, inRawBlock) {
    const cap = this.rules.inline.tag.exec(src);
    if (cap) {
      if (!inLink && /^<a /i.test(cap[0])) {
        inLink = true;
      } else if (inLink && /^<\/a>/i.test(cap[0])) {
        inLink = false;
      }
      if (!inRawBlock && /^<(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {
        inRawBlock = true;
      } else if (inRawBlock && /^<\/(pre|code|kbd|script)(\s|>)/i.test(cap[0])) {
        inRawBlock = false;
      }

      return {
        type: this.options.sanitize
          ? 'text'
          : 'html',
        raw: cap[0],
        inLink,
        inRawBlock,
        text: this.options.sanitize
          ? (this.options.sanitizer
            ? this.options.sanitizer(cap[0])
            : escape(cap[0]))
          : cap[0]
      };
    }
  }

  link(src) {
    const cap = this.rules.inline.link.exec(src);
    if (cap) {
      const lastParenIndex = findClosingBracket(cap[2], '()');
      if (lastParenIndex > -1) {
        const start = cap[0].indexOf('!') === 0 ? 5 : 4;
        const linkLen = start + cap[1].length + lastParenIndex;
        cap[2] = cap[2].substring(0, lastParenIndex);
        cap[0] = cap[0].substring(0, linkLen).trim();
        cap[3] = '';
      }
      let href = cap[2];
      let title = '';
      if (this.options.pedantic) {
        const link = /^([^'"]*[^\s])\s+(['"])(.*)\2/.exec(href);

        if (link) {
          href = link[1];
          title = link[3];
        } else {
          title = '';
        }
      } else {
        title = cap[3] ? cap[3].slice(1, -1) : '';
      }
      href = href.trim().replace(/^<([\s\S]*)>$/, '$1');
      const token = outputLink(cap, {
        href: href ? href.replace(this.rules.inline._escapes, '$1') : href,
        title: title ? title.replace(this.rules.inline._escapes, '$1') : title
      }, cap[0]);
      return token;
    }
  }

  reflink(src, links) {
    let cap;
    if ((cap = this.rules.inline.reflink.exec(src))
        || (cap = this.rules.inline.nolink.exec(src))) {
      let link = (cap[2] || cap[1]).replace(/\s+/g, ' ');
      link = links[link.toLowerCase()];
      if (!link || !link.href) {
        const text = cap[0].charAt(0);
        return {
          type: 'text',
          raw: text,
          text
        };
      }
      const token = outputLink(cap, link, cap[0]);
      return token;
    }
  }

  strong(src) {
    const cap = this.rules.inline.strong.exec(src);
    if (cap) {
      return {
        type: 'strong',
        raw: cap[0],
        text: cap[4] || cap[3] || cap[2] || cap[1]
      };
    }
  }

  em(src) {
    const cap = this.rules.inline.em.exec(src);
    if (cap) {
      return {
        type: 'em',
        raw: cap[0],
        text: cap[6] || cap[5] || cap[4] || cap[3] || cap[2] || cap[1]
      };
    }
  }

  codespan(src) {
    const cap = this.rules.inline.code.exec(src);
    if (cap) {
      let text = cap[2].replace(/\n/g, ' ');
      const hasNonSpaceChars = /[^ ]/.test(text);
      const hasSpaceCharsOnBothEnds = text.startsWith(' ') && text.endsWith(' ');
      if (hasNonSpaceChars && hasSpaceCharsOnBothEnds) {
        text = text.substring(1, text.length - 1);
      }
      text = escape(text, true);
      return {
        type: 'codespan',
        raw: cap[0],
        text
      };
    }
  }

  br(src) {
    const cap = this.rules.inline.br.exec(src);
    if (cap) {
      return {
        type: 'br',
        raw: cap[0]
      };
    }
  }

  del(src) {
    const cap = this.rules.inline.del.exec(src);
    if (cap) {
      return {
        type: 'del',
        raw: cap[0],
        text: cap[1]
      };
    }
  }

  autolink(src, mangle) {
    const cap = this.rules.inline.autolink.exec(src);
    if (cap) {
      let text, href;
      if (cap[2] === '@') {
        text = escape(this.options.mangle ? mangle(cap[1]) : cap[1]);
        href = 'mailto:' + text;
      } else {
        text = escape(cap[1]);
        href = text;
      }

      return {
        type: 'link',
        raw: cap[0],
        text,
        href,
        tokens: [
          {
            type: 'text',
            raw: text,
            text
          }
        ]
      };
    }
  }

  url(src, mangle) {
    let cap;
    if (cap = this.rules.inline.url.exec(src)) {
      let text, href;
      if (cap[2] === '@') {
        text = escape(this.options.mangle ? mangle(cap[0]) : cap[0]);
        href = 'mailto:' + text;
      } else {
        // do extended autolink path validation
        let prevCapZero;
        do {
          prevCapZero = cap[0];
          cap[0] = this.rules.inline._backpedal.exec(cap[0])[0];
        } while (prevCapZero !== cap[0]);
        text = escape(cap[0]);
        if (cap[1] === 'www.') {
          href = 'http://' + text;
        } else {
          href = text;
        }
      }
      return {
        type: 'link',
        raw: cap[0],
        text,
        href,
        tokens: [
          {
            type: 'text',
            raw: text,
            text
          }
        ]
      };
    }
  }

  inlineText(src, inRawBlock, smartypants) {
    const cap = this.rules.inline.text.exec(src);
    if (cap) {
      let text;
      if (inRawBlock) {
        text = this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0];
      } else {
        text = escape(this.options.smartypants ? smartypants(cap[0]) : cap[0]);
      }
      return {
        type: 'text',
        raw: cap[0],
        text
      };
    }
  }
};