marked/src/InlineLexer.js

const Renderer = require('./Renderer.js');
const { defaults } = require('./defaults.js');
const { inline } = require('./rules.js');
const {
  findClosingBracket,
  escape
} = require('./helpers.js');

/**
 * Inline Lexer & Compiler
 */
module.exports = class InlineLexer {
  constructor(links, options) {
    this.options = options || defaults;
    this.links = links;
    this.rules = inline.normal;
    this.options.renderer = this.options.renderer || new Renderer();
    this.renderer = this.options.renderer;
    this.renderer.options = this.options;

    if (!this.links) {
      throw new Error('Tokens array requires a `links` property.');
    }

    if (this.options.pedantic) {
      this.rules = inline.pedantic;
    } else if (this.options.gfm) {
      if (this.options.breaks) {
        this.rules = inline.breaks;
      } else {
        this.rules = inline.gfm;
      }
    }
  }

  /**
   * Expose Inline Rules
   */
  static get rules() {
    return inline;
  }

  /**
   * Static Lexing/Compiling Method
   */
  static output(src, links, options) {
    const inline = new InlineLexer(links, options);
    return inline.output(src);
  }

  /**
   * Lexing/Compiling
   */
  output(src) {
    let out = '',
      link,
      text,
      href,
      title,
      cap,
      prevCapZero;

    while (src) {
      // escape
      if (cap = this.rules.escape.exec(src)) {
        src = src.substring(cap[0].length);
        out += escape(cap[1]);
        continue;
      }

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

        src = src.substring(cap[0].length);
        out += this.options.sanitize
          ? this.options.sanitizer
            ? this.options.sanitizer(cap[0])
            : escape(cap[0])
          : cap[0];
        continue;
      }

      // link
      if (cap = this.rules.link.exec(src)) {
        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] = '';
        }
        src = src.substring(cap[0].length);
        this.inLink = true;
        href = cap[2];
        if (this.options.pedantic) {
          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');
        out += this.outputLink(cap, {
          href: InlineLexer.escapes(href),
          title: InlineLexer.escapes(title)
        });
        this.inLink = false;
        continue;
      }

      // reflink, nolink
      if ((cap = this.rules.reflink.exec(src))
          || (cap = this.rules.nolink.exec(src))) {
        src = src.substring(cap[0].length);
        link = (cap[2] || cap[1]).replace(/\s+/g, ' ');
        link = this.links[link.toLowerCase()];
        if (!link || !link.href) {
          out += cap[0].charAt(0);
          src = cap[0].substring(1) + src;
          continue;
        }
        this.inLink = true;
        out += this.outputLink(cap, link);
        this.inLink = false;
        continue;
      }

      // strong
      if (cap = this.rules.strong.exec(src)) {
        src = src.substring(cap[0].length);
        out += this.renderer.strong(this.output(cap[4] || cap[3] || cap[2] || cap[1]));
        continue;
      }

      // em
      if (cap = this.rules.em.exec(src)) {
        src = src.substring(cap[0].length);
        out += this.renderer.em(this.output(cap[6] || cap[5] || cap[4] || cap[3] || cap[2] || cap[1]));
        continue;
      }

      // code
      if (cap = this.rules.code.exec(src)) {
        src = src.substring(cap[0].length);
        out += this.renderer.codespan(escape(cap[2].trim(), true));
        continue;
      }

      // br
      if (cap = this.rules.br.exec(src)) {
        src = src.substring(cap[0].length);
        out += this.renderer.br();
        continue;
      }

      // del (gfm)
      if (cap = this.rules.del.exec(src)) {
        src = src.substring(cap[0].length);
        out += this.renderer.del(this.output(cap[1]));
        continue;
      }

      // autolink
      if (cap = this.rules.autolink.exec(src)) {
        src = src.substring(cap[0].length);
        if (cap[2] === '@') {
          text = escape(this.mangle(cap[1]));
          href = 'mailto:' + text;
        } else {
          text = escape(cap[1]);
          href = text;
        }
        out += this.renderer.link(href, null, text);
        continue;
      }

      // url (gfm)
      if (!this.inLink && (cap = this.rules.url.exec(src))) {
        if (cap[2] === '@') {
          text = escape(cap[0]);
          href = 'mailto:' + text;
        } else {
          // do extended autolink path validation
          do {
            prevCapZero = cap[0];
            cap[0] = this.rules._backpedal.exec(cap[0])[0];
          } while (prevCapZero !== cap[0]);
          text = escape(cap[0]);
          if (cap[1] === 'www.') {
            href = 'http://' + text;
          } else {
            href = text;
          }
        }
        src = src.substring(cap[0].length);
        out += this.renderer.link(href, null, text);
        continue;
      }

      // text
      if (cap = this.rules.text.exec(src)) {
        src = src.substring(cap[0].length);
        if (this.inRawBlock) {
          out += this.renderer.text(this.options.sanitize ? (this.options.sanitizer ? this.options.sanitizer(cap[0]) : escape(cap[0])) : cap[0]);
        } else {
          out += this.renderer.text(escape(this.smartypants(cap[0])));
        }
        continue;
      }

      if (src) {
        throw new Error('Infinite loop on byte: ' + src.charCodeAt(0));
      }
    }

    return out;
  }

  static escapes(text) {
    return text ? text.replace(InlineLexer.rules._escapes, '$1') : text;
  }

  /**
   * Compile Link
   */
  outputLink(cap, link) {
    const href = link.href,
      title = link.title ? escape(link.title) : null;

    return cap[0].charAt(0) !== '!'
      ? this.renderer.link(href, title, this.output(cap[1]))
      : this.renderer.image(href, title, escape(cap[1]));
  }

  /**
   * Smartypants Transformations
   */
  smartypants(text) {
    if (!this.options.smartypants) return text;
    return text
      // em-dashes
      .replace(/---/g, '\u2014')
      // en-dashes
      .replace(/--/g, '\u2013')
      // opening singles
      .replace(/(^|[-\u2014/(\[{"\s])'/g, '$1\u2018')
      // closing singles & apostrophes
      .replace(/'/g, '\u2019')
      // opening doubles
      .replace(/(^|[-\u2014/(\[{\u2018\s])"/g, '$1\u201c')
      // closing doubles
      .replace(/"/g, '\u201d')
      // ellipses
      .replace(/\.{3}/g, '\u2026');
  }

  /**
   * Mangle Links
   */
  mangle(text) {
    if (!this.options.mangle) return text;
    const l = text.length;
    let out = '',
      i = 0,
      ch;

    for (; i < l; i++) {
      ch = text.charCodeAt(i);
      if (Math.random() > 0.5) {
        ch = 'x' + ch.toString(16);
      }
      out += '&#' + ch + ';';
    }

    return out;
  }
};