marked/src/Lexer.js

import { Tokenizer } from './Tokenizer.js';
import { defaults } from './defaults.js';
import { block, inline } from './rules.js';
import { repeatString } from './helpers.js';

/**
 * smartypants text replacement
 * @param {string} text
 */
function smartypants(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 email addresses
 * @param {string} text
 */
function mangle(text) {
  let out = '',
    i,
    ch;

  const l = text.length;
  for (i = 0; i < l; i++) {
    ch = text.charCodeAt(i);
    if (Math.random() > 0.5) {
      ch = 'x' + ch.toString(16);
    }
    out += '&#' + ch + ';';
  }

  return out;
}

/**
 * Block Lexer
 */
export class Lexer {
  constructor(options) {
    this.tokens = [];
    this.tokens.links = Object.create(null);
    this.options = options || defaults;
    this.options.tokenizer = this.options.tokenizer || new Tokenizer();
    this.tokenizer = this.options.tokenizer;
    this.tokenizer.options = this.options;
    this.tokenizer.lexer = this;
    this.inlineQueue = [];
    this.state = {
      inLink: false,
      inRawBlock: false,
      top: true
    };

    const rules = {
      block: block.normal,
      inline: inline.normal
    };

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

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

  /**
   * Static Lex Method
   */
  static lex(src, options) {
    const lexer = new Lexer(options);
    return lexer.lex(src);
  }

  /**
   * Static Lex Inline Method
   */
  static lexInline(src, options) {
    const lexer = new Lexer(options);
    return lexer.inlineTokens(src);
  }

  /**
   * Preprocessing
   */
  lex(src) {
    src = src
      .replace(/\r\n|\r/g, '\n');

    this.blockTokens(src, this.tokens);

    let next;
    while (next = this.inlineQueue.shift()) {
      this.inlineTokens(next.src, next.tokens);
    }

    return this.tokens;
  }

  /**
   * Lexing
   */
  blockTokens(src, tokens = []) {
    if (this.options.pedantic) {
      src = src.replace(/\t/g, '    ').replace(/^ +$/gm, '');
    } else {
      src = src.replace(/^( *)(\t+)/gm, (_, leading, tabs) => {
        return leading + '    '.repeat(tabs.length);
      });
    }

    let token, lastToken, cutSrc, lastParagraphClipped;

    while (src) {
      if (this.options.extensions
        && this.options.extensions.block
        && this.options.extensions.block.some((extTokenizer) => {
          if (token = extTokenizer.call({ lexer: this }, src, tokens)) {
            src = src.substring(token.raw.length);
            tokens.push(token);
            return true;
          }
          return false;
        })) {
        continue;
      }

      // newline
      if (token = this.tokenizer.space(src)) {
        src = src.substring(token.raw.length);
        if (token.raw.length === 1 && tokens.length > 0) {
          // if there's a single \n as a spacer, it's terminating the last line,
          // so move it there so that we don't get unecessary paragraph tags
          tokens[tokens.length - 1].raw += '\n';
        } else {
          tokens.push(token);
        }
        continue;
      }

      // code
      if (token = this.tokenizer.code(src)) {
        src = src.substring(token.raw.length);
        lastToken = tokens[tokens.length - 1];
        // An indented code block cannot interrupt a paragraph.
        if (lastToken && (lastToken.type === 'paragraph' || lastToken.type === 'text')) {
          lastToken.raw += '\n' + token.raw;
          lastToken.text += '\n' + token.text;
          this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text;
        } else {
          tokens.push(token);
        }
        continue;
      }

      // fences
      if (token = this.tokenizer.fences(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // heading
      if (token = this.tokenizer.heading(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // hr
      if (token = this.tokenizer.hr(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // blockquote
      if (token = this.tokenizer.blockquote(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // list
      if (token = this.tokenizer.list(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // html
      if (token = this.tokenizer.html(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // def
      if (token = this.tokenizer.def(src)) {
        src = src.substring(token.raw.length);
        lastToken = tokens[tokens.length - 1];
        if (lastToken && (lastToken.type === 'paragraph' || lastToken.type === 'text')) {
          lastToken.raw += '\n' + token.raw;
          lastToken.text += '\n' + token.raw;
          this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text;
        } else if (!this.tokens.links[token.tag]) {
          this.tokens.links[token.tag] = {
            href: token.href,
            title: token.title
          };
        }
        continue;
      }

      // table (gfm)
      if (token = this.tokenizer.table(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // lheading
      if (token = this.tokenizer.lheading(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // top-level paragraph
      // prevent paragraph consuming extensions by clipping 'src' to extension start
      cutSrc = src;
      if (this.options.extensions && this.options.extensions.startBlock) {
        let startIndex = Infinity;
        const tempSrc = src.slice(1);
        let tempStart;
        this.options.extensions.startBlock.forEach(function(getStartIndex) {
          tempStart = getStartIndex.call({ lexer: this }, tempSrc);
          if (typeof tempStart === 'number' && tempStart >= 0) { startIndex = Math.min(startIndex, tempStart); }
        });
        if (startIndex < Infinity && startIndex >= 0) {
          cutSrc = src.substring(0, startIndex + 1);
        }
      }
      if (this.state.top && (token = this.tokenizer.paragraph(cutSrc))) {
        lastToken = tokens[tokens.length - 1];
        if (lastParagraphClipped && lastToken.type === 'paragraph') {
          lastToken.raw += '\n' + token.raw;
          lastToken.text += '\n' + token.text;
          this.inlineQueue.pop();
          this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text;
        } else {
          tokens.push(token);
        }
        lastParagraphClipped = (cutSrc.length !== src.length);
        src = src.substring(token.raw.length);
        continue;
      }

      // text
      if (token = this.tokenizer.text(src)) {
        src = src.substring(token.raw.length);
        lastToken = tokens[tokens.length - 1];
        if (lastToken && lastToken.type === 'text') {
          lastToken.raw += '\n' + token.raw;
          lastToken.text += '\n' + token.text;
          this.inlineQueue.pop();
          this.inlineQueue[this.inlineQueue.length - 1].src = lastToken.text;
        } else {
          tokens.push(token);
        }
        continue;
      }

      if (src) {
        const errMsg = 'Infinite loop on byte: ' + src.charCodeAt(0);
        if (this.options.silent) {
          console.error(errMsg);
          break;
        } else {
          throw new Error(errMsg);
        }
      }
    }

    this.state.top = true;
    return tokens;
  }

  inline(src, tokens = []) {
    this.inlineQueue.push({ src, tokens });
    return tokens;
  }

  /**
   * Lexing/Compiling
   */
  inlineTokens(src, tokens = []) {
    let token, lastToken, cutSrc;

    // String with links masked to avoid interference with em and strong
    let maskedSrc = src;
    let match;
    let keepPrevChar, prevChar;

    // Mask out reflinks
    if (this.tokens.links) {
      const links = Object.keys(this.tokens.links);
      if (links.length > 0) {
        while ((match = this.tokenizer.rules.inline.reflinkSearch.exec(maskedSrc)) != null) {
          if (links.includes(match[0].slice(match[0].lastIndexOf('[') + 1, -1))) {
            maskedSrc = maskedSrc.slice(0, match.index) + '[' + repeatString('a', match[0].length - 2) + ']' + maskedSrc.slice(this.tokenizer.rules.inline.reflinkSearch.lastIndex);
          }
        }
      }
    }
    // Mask out other blocks
    while ((match = this.tokenizer.rules.inline.blockSkip.exec(maskedSrc)) != null) {
      maskedSrc = maskedSrc.slice(0, match.index) + '[' + repeatString('a', match[0].length - 2) + ']' + maskedSrc.slice(this.tokenizer.rules.inline.blockSkip.lastIndex);
    }

    // Mask out escaped em & strong delimiters
    while ((match = this.tokenizer.rules.inline.escapedEmSt.exec(maskedSrc)) != null) {
      maskedSrc = maskedSrc.slice(0, match.index) + '++' + maskedSrc.slice(this.tokenizer.rules.inline.escapedEmSt.lastIndex);
    }

    while (src) {
      if (!keepPrevChar) {
        prevChar = '';
      }
      keepPrevChar = false;

      // extensions
      if (this.options.extensions
        && this.options.extensions.inline
        && this.options.extensions.inline.some((extTokenizer) => {
          if (token = extTokenizer.call({ lexer: this }, src, tokens)) {
            src = src.substring(token.raw.length);
            tokens.push(token);
            return true;
          }
          return false;
        })) {
        continue;
      }

      // escape
      if (token = this.tokenizer.escape(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // tag
      if (token = this.tokenizer.tag(src)) {
        src = src.substring(token.raw.length);
        lastToken = tokens[tokens.length - 1];
        if (lastToken && token.type === 'text' && lastToken.type === 'text') {
          lastToken.raw += token.raw;
          lastToken.text += token.text;
        } else {
          tokens.push(token);
        }
        continue;
      }

      // link
      if (token = this.tokenizer.link(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // reflink, nolink
      if (token = this.tokenizer.reflink(src, this.tokens.links)) {
        src = src.substring(token.raw.length);
        lastToken = tokens[tokens.length - 1];
        if (lastToken && token.type === 'text' && lastToken.type === 'text') {
          lastToken.raw += token.raw;
          lastToken.text += token.text;
        } else {
          tokens.push(token);
        }
        continue;
      }

      // em & strong
      if (token = this.tokenizer.emStrong(src, maskedSrc, prevChar)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // code
      if (token = this.tokenizer.codespan(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // br
      if (token = this.tokenizer.br(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // del (gfm)
      if (token = this.tokenizer.del(src)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // autolink
      if (token = this.tokenizer.autolink(src, mangle)) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // url (gfm)
      if (!this.state.inLink && (token = this.tokenizer.url(src, mangle))) {
        src = src.substring(token.raw.length);
        tokens.push(token);
        continue;
      }

      // text
      // prevent inlineText consuming extensions by clipping 'src' to extension start
      cutSrc = src;
      if (this.options.extensions && this.options.extensions.startInline) {
        let startIndex = Infinity;
        const tempSrc = src.slice(1);
        let tempStart;
        this.options.extensions.startInline.forEach(function(getStartIndex) {
          tempStart = getStartIndex.call({ lexer: this }, tempSrc);
          if (typeof tempStart === 'number' && tempStart >= 0) { startIndex = Math.min(startIndex, tempStart); }
        });
        if (startIndex < Infinity && startIndex >= 0) {
          cutSrc = src.substring(0, startIndex + 1);
        }
      }
      if (token = this.tokenizer.inlineText(cutSrc, smartypants)) {
        src = src.substring(token.raw.length);
        if (token.raw.slice(-1) !== '_') { // Track prevChar before string of ____ started
          prevChar = token.raw.slice(-1);
        }
        keepPrevChar = true;
        lastToken = tokens[tokens.length - 1];
        if (lastToken && lastToken.type === 'text') {
          lastToken.raw += token.raw;
          lastToken.text += token.text;
        } else {
          tokens.push(token);
        }
        continue;
      }

      if (src) {
        const errMsg = 'Infinite loop on byte: ' + src.charCodeAt(0);
        if (this.options.silent) {
          console.error(errMsg);
          break;
        } else {
          throw new Error(errMsg);
        }
      }
    }

    return tokens;
  }
}