marked 0.6.1 → 0.8.0

package/src/Parser.js

@@ -0,0 +1,206 @@
+const Renderer = require('./Renderer.js');
+const Slugger = require('./Slugger.js');
+const InlineLexer = require('./InlineLexer.js');
+const TextRenderer = require('./TextRenderer.js');
+const { defaults } = require('./defaults.js');
+const {
+  merge,
+  unescape
+} = require('./helpers.js');
+
+/**
+ * Parsing & Compiling
+ */
+module.exports = class Parser {
+  constructor(options) {
+    this.tokens = [];
+    this.token = null;
+    this.options = options || defaults;
+    this.options.renderer = this.options.renderer || new Renderer();
+    this.renderer = this.options.renderer;
+    this.renderer.options = this.options;
+    this.slugger = new Slugger();
+  }
+
+  /**
+   * Static Parse Method
+   */
+  static parse(tokens, options) {
+    const parser = new Parser(options);
+    return parser.parse(tokens);
+  };
+
+  /**
+   * Parse Loop
+   */
+  parse(tokens) {
+    this.inline = new InlineLexer(tokens.links, this.options);
+    // use an InlineLexer with a TextRenderer to extract pure text
+    this.inlineText = new InlineLexer(
+      tokens.links,
+      merge({}, this.options, { renderer: new TextRenderer() })
+    );
+    this.tokens = tokens.reverse();
+
+    let out = '';
+    while (this.next()) {
+      out += this.tok();
+    }
+
+    return out;
+  };
+
+  /**
+   * Next Token
+   */
+  next() {
+    this.token = this.tokens.pop();
+    return this.token;
+  };
+
+  /**
+   * Preview Next Token
+   */
+  peek() {
+    return this.tokens[this.tokens.length - 1] || 0;
+  };
+
+  /**
+   * Parse Text Tokens
+   */
+  parseText() {
+    let body = this.token.text;
+
+    while (this.peek().type === 'text') {
+      body += '\n' + this.next().text;
+    }
+
+    return this.inline.output(body);
+  };
+
+  /**
+   * Parse Current Token
+   */
+  tok() {
+    let body = '';
+    switch (this.token.type) {
+      case 'space': {
+        return '';
+      }
+      case 'hr': {
+        return this.renderer.hr();
+      }
+      case 'heading': {
+        return this.renderer.heading(
+          this.inline.output(this.token.text),
+          this.token.depth,
+          unescape(this.inlineText.output(this.token.text)),
+          this.slugger);
+      }
+      case 'code': {
+        return this.renderer.code(this.token.text,
+          this.token.lang,
+          this.token.escaped);
+      }
+      case 'table': {
+        let header = '',
+          i,
+          row,
+          cell,
+          j;
+
+        // header
+        cell = '';
+        for (i = 0; i < this.token.header.length; i++) {
+          cell += this.renderer.tablecell(
+            this.inline.output(this.token.header[i]),
+            { header: true, align: this.token.align[i] }
+          );
+        }
+        header += this.renderer.tablerow(cell);
+
+        for (i = 0; i < this.token.cells.length; i++) {
+          row = this.token.cells[i];
+
+          cell = '';
+          for (j = 0; j < row.length; j++) {
+            cell += this.renderer.tablecell(
+              this.inline.output(row[j]),
+              { header: false, align: this.token.align[j] }
+            );
+          }
+
+          body += this.renderer.tablerow(cell);
+        }
+        return this.renderer.table(header, body);
+      }
+      case 'blockquote_start': {
+        body = '';
+
+        while (this.next().type !== 'blockquote_end') {
+          body += this.tok();
+        }
+
+        return this.renderer.blockquote(body);
+      }
+      case 'list_start': {
+        body = '';
+        const ordered = this.token.ordered,
+          start = this.token.start;
+
+        while (this.next().type !== 'list_end') {
+          body += this.tok();
+        }
+
+        return this.renderer.list(body, ordered, start);
+      }
+      case 'list_item_start': {
+        body = '';
+        const loose = this.token.loose;
+        const checked = this.token.checked;
+        const task = this.token.task;
+
+        if (this.token.task) {
+          if (loose) {
+            if (this.peek().type === 'text') {
+              const nextToken = this.peek();
+              nextToken.text = this.renderer.checkbox(checked) + ' ' + nextToken.text;
+            } else {
+              this.tokens.push({
+                type: 'text',
+                text: this.renderer.checkbox(checked)
+              });
+            }
+          } else {
+            body += this.renderer.checkbox(checked);
+          }
+        }
+
+        while (this.next().type !== 'list_item_end') {
+          body += !loose && this.token.type === 'text'
+            ? this.parseText()
+            : this.tok();
+        }
+        return this.renderer.listitem(body, task, checked);
+      }
+      case 'html': {
+        // TODO parse inline content if parameter markdown=1
+        return this.renderer.html(this.token.text);
+      }
+      case 'paragraph': {
+        return this.renderer.paragraph(this.inline.output(this.token.text));
+      }
+      case 'text': {
+        return this.renderer.paragraph(this.parseText());
+      }
+      default: {
+        const errMsg = 'Token with "' + this.token.type + '" type was not found.';
+        if (this.options.silent) {
+          console.log(errMsg);
+        } else {
+          throw new Error(errMsg);
+        }
+      }
+    }
+  };
+};

package/src/Renderer.js

@@ -0,0 +1,164 @@
+const { defaults } = require('./defaults.js');
+const {
+  cleanUrl,
+  escape
+} = require('./helpers.js');
+
+/**
+ * Renderer
+ */
+module.exports = class Renderer {
+  constructor(options) {
+    this.options = options || defaults;
+  }
+
+  code(code, infostring, escaped) {
+    const lang = (infostring || '').match(/\S*/)[0];
+    if (this.options.highlight) {
+      const out = this.options.highlight(code, lang);
+      if (out != null && out !== code) {
+        escaped = true;
+        code = out;
+      }
+    }
+
+    if (!lang) {
+      return '<pre><code>'
+        + (escaped ? code : escape(code, true))
+        + '</code></pre>';
+    }
+
+    return '<pre><code class="'
+      + this.options.langPrefix
+      + escape(lang, true)
+      + '">'
+      + (escaped ? code : escape(code, true))
+      + '</code></pre>\n';
+  };
+
+  blockquote(quote) {
+    return '<blockquote>\n' + quote + '</blockquote>\n';
+  };
+
+  html(html) {
+    return html;
+  };
+
+  heading(text, level, raw, slugger) {
+    if (this.options.headerIds) {
+      return '<h'
+        + level
+        + ' id="'
+        + this.options.headerPrefix
+        + slugger.slug(raw)
+        + '">'
+        + text
+        + '</h'
+        + level
+        + '>\n';
+    }
+    // ignore IDs
+    return '<h' + level + '>' + text + '</h' + level + '>\n';
+  };
+
+  hr() {
+    return this.options.xhtml ? '<hr/>\n' : '<hr>\n';
+  };
+
+  list(body, ordered, start) {
+    const type = ordered ? 'ol' : 'ul',
+      startatt = (ordered && start !== 1) ? (' start="' + start + '"') : '';
+    return '<' + type + startatt + '>\n' + body + '</' + type + '>\n';
+  };
+
+  listitem(text) {
+    return '<li>' + text + '</li>\n';
+  };
+
+  checkbox(checked) {
+    return '<input '
+      + (checked ? 'checked="" ' : '')
+      + 'disabled="" type="checkbox"'
+      + (this.options.xhtml ? ' /' : '')
+      + '> ';
+  };
+
+  paragraph(text) {
+    return '<p>' + text + '</p>\n';
+  };
+
+  table(header, body) {
+    if (body) body = '<tbody>' + body + '</tbody>';
+
+    return '<table>\n'
+      + '<thead>\n'
+      + header
+      + '</thead>\n'
+      + body
+      + '</table>\n';
+  };
+
+  tablerow(content) {
+    return '<tr>\n' + content + '</tr>\n';
+  };
+
+  tablecell(content, flags) {
+    const type = flags.header ? 'th' : 'td';
+    const tag = flags.align
+      ? '<' + type + ' align="' + flags.align + '">'
+      : '<' + type + '>';
+    return tag + content + '</' + type + '>\n';
+  };
+
+  // span level renderer
+  strong(text) {
+    return '<strong>' + text + '</strong>';
+  };
+
+  em(text) {
+    return '<em>' + text + '</em>';
+  };
+
+  codespan(text) {
+    return '<code>' + text + '</code>';
+  };
+
+  br() {
+    return this.options.xhtml ? '<br/>' : '<br>';
+  };
+
+  del(text) {
+    return '<del>' + text + '</del>';
+  };
+
+  link(href, title, text) {
+    href = cleanUrl(this.options.sanitize, this.options.baseUrl, href);
+    if (href === null) {
+      return text;
+    }
+    let out = '<a href="' + escape(href) + '"';
+    if (title) {
+      out += ' title="' + title + '"';
+    }
+    out += '>' + text + '</a>';
+    return out;
+  };
+
+  image(href, title, text) {
+    href = cleanUrl(this.options.sanitize, this.options.baseUrl, href);
+    if (href === null) {
+      return text;
+    }
+
+    let out = '<img src="' + href + '" alt="' + text + '"';
+    if (title) {
+      out += ' title="' + title + '"';
+    }
+    out += this.options.xhtml ? '/>' : '>';
+    return out;
+  };
+
+  text(text) {
+    return text;
+  };
+};

package/src/Slugger.js

@@ -0,0 +1,30 @@
+/**
+ * Slugger generates header id
+ */
+module.exports = class Slugger {
+  constructor() {
+    this.seen = {};
+  }
+
+  /**
+   * Convert string to unique id
+   */
+  slug(value) {
+    let slug = value
+      .toLowerCase()
+      .trim()
+      .replace(/[\u2000-\u206F\u2E00-\u2E7F\\'!"#$%&()*+,./:;<=>?@[\]^`{|}~]/g, '')
+      .replace(/\s/g, '-');
+
+    if (this.seen.hasOwnProperty(slug)) {
+      const originalSlug = slug;
+      do {
+        this.seen[originalSlug]++;
+        slug = originalSlug + '-' + this.seen[originalSlug];
+      } while (this.seen.hasOwnProperty(slug));
+    }
+    this.seen[slug] = 0;
+
+    return slug;
+  };
+};

package/src/TextRenderer.js

@@ -0,0 +1,38 @@
+/**
+ * TextRenderer
+ * returns only the textual part of the token
+ */
+module.exports = class TextRenderer {
+  // no need for block level renderers
+  strong(text) {
+    return text;
+  }
+
+  em(text) {
+    return text;
+  }
+
+  codespan(text) {
+    return text;
+  }
+
+  del(text) {
+    return text;
+  }
+
+  text(text) {
+    return text;
+  }
+
+  link(href, title, text) {
+    return '' + text;
+  }
+
+  image(href, title, text) {
+    return '' + text;
+  }
+
+  br() {
+    return '';
+  }
+};

package/src/defaults.js

@@ -0,0 +1,30 @@
+function getDefaults() {
+  return {
+    baseUrl: null,
+    breaks: false,
+    gfm: true,
+    headerIds: true,
+    headerPrefix: '',
+    highlight: null,
+    langPrefix: 'language-',
+    mangle: true,
+    pedantic: false,
+    renderer: null,
+    sanitize: false,
+    sanitizer: null,
+    silent: false,
+    smartLists: false,
+    smartypants: false,
+    xhtml: false
+  };
+}
+
+function changeDefaults(newDefaults) {
+  module.exports.defaults = newDefaults;
+}
+
+module.exports = {
+  defaults: getDefaults(),
+  getDefaults,
+  changeDefaults
+};

package/src/helpers.js

@@ -0,0 +1,243 @@
+/**
+ * Helpers
+ */
+const escapeTest = /[&<>"']/;
+const escapeReplace = /[&<>"']/g;
+const escapeTestNoEncode = /[<>"']|&(?!#?\w+;)/;
+const escapeReplaceNoEncode = /[<>"']|&(?!#?\w+;)/g;
+const escapeReplacements = {
+  '&': '&amp;',
+  '<': '&lt;',
+  '>': '&gt;',
+  '"': '&quot;',
+  "'": '&#39;'
+};
+const getEscapeReplacement = (ch) => escapeReplacements[ch];
+function escape(html, encode) {
+  if (encode) {
+    if (escapeTest.test(html)) {
+      return html.replace(escapeReplace, getEscapeReplacement);
+    }
+  } else {
+    if (escapeTestNoEncode.test(html)) {
+      return html.replace(escapeReplaceNoEncode, getEscapeReplacement);
+    }
+  }
+
+  return html;
+}
+
+const unescapeTest = /&(#(?:\d+)|(?:#x[0-9A-Fa-f]+)|(?:\w+));?/ig;
+
+function unescape(html) {
+  // explicitly match decimal, hex, and named HTML entities
+  return html.replace(unescapeTest, (_, n) => {
+    n = n.toLowerCase();
+    if (n === 'colon') return ':';
+    if (n.charAt(0) === '#') {
+      return n.charAt(1) === 'x'
+        ? String.fromCharCode(parseInt(n.substring(2), 16))
+        : String.fromCharCode(+n.substring(1));
+    }
+    return '';
+  });
+}
+
+const caret = /(^|[^\[])\^/g;
+function edit(regex, opt) {
+  regex = regex.source || regex;
+  opt = opt || '';
+  const obj = {
+    replace: (name, val) => {
+      val = val.source || val;
+      val = val.replace(caret, '$1');
+      regex = regex.replace(name, val);
+      return obj;
+    },
+    getRegex: () => {
+      return new RegExp(regex, opt);
+    }
+  };
+  return obj;
+}
+
+const nonWordAndColonTest = /[^\w:]/g;
+const originIndependentUrl = /^$|^[a-z][a-z0-9+.-]*:|^[?#]/i;
+function cleanUrl(sanitize, base, href) {
+  if (sanitize) {
+    let prot;
+    try {
+      prot = decodeURIComponent(unescape(href))
+        .replace(nonWordAndColonTest, '')
+        .toLowerCase();
+    } catch (e) {
+      return null;
+    }
+    if (prot.indexOf('javascript:') === 0 || prot.indexOf('vbscript:') === 0 || prot.indexOf('data:') === 0) {
+      return null;
+    }
+  }
+  if (base && !originIndependentUrl.test(href)) {
+    href = resolveUrl(base, href);
+  }
+  try {
+    href = encodeURI(href).replace(/%25/g, '%');
+  } catch (e) {
+    return null;
+  }
+  return href;
+}
+
+const baseUrls = {};
+const justDomain = /^[^:]+:\/*[^/]*$/;
+const protocol = /^([^:]+:)[\s\S]*$/;
+const domain = /^([^:]+:\/*[^/]*)[\s\S]*$/;
+
+function resolveUrl(base, href) {
+  if (!baseUrls[' ' + base]) {
+    // we can ignore everything in base after the last slash of its path component,
+    // but we might need to add _that_
+    // https://tools.ietf.org/html/rfc3986#section-3
+    if (justDomain.test(base)) {
+      baseUrls[' ' + base] = base + '/';
+    } else {
+      baseUrls[' ' + base] = rtrim(base, '/', true);
+    }
+  }
+  base = baseUrls[' ' + base];
+  const relativeBase = base.indexOf(':') === -1;
+
+  if (href.substring(0, 2) === '//') {
+    if (relativeBase) {
+      return href;
+    }
+    return base.replace(protocol, '$1') + href;
+  } else if (href.charAt(0) === '/') {
+    if (relativeBase) {
+      return href;
+    }
+    return base.replace(domain, '$1') + href;
+  } else {
+    return base + href;
+  }
+}
+
+const noopTest = { exec: function noopTest() {} };
+
+function merge(obj) {
+  let i = 1,
+    target,
+    key;
+
+  for (; i < arguments.length; i++) {
+    target = arguments[i];
+    for (key in target) {
+      if (Object.prototype.hasOwnProperty.call(target, key)) {
+        obj[key] = target[key];
+      }
+    }
+  }
+
+  return obj;
+}
+
+function splitCells(tableRow, count) {
+  // ensure that every cell-delimiting pipe has a space
+  // before it to distinguish it from an escaped pipe
+  const row = tableRow.replace(/\|/g, (match, offset, str) => {
+      let escaped = false,
+        curr = offset;
+      while (--curr >= 0 && str[curr] === '\\') escaped = !escaped;
+      if (escaped) {
+        // odd number of slashes means | is escaped
+        // so we leave it alone
+        return '|';
+      } else {
+        // add space before unescaped |
+        return ' |';
+      }
+    }),
+    cells = row.split(/ \|/);
+  let i = 0;
+
+  if (cells.length > count) {
+    cells.splice(count);
+  } else {
+    while (cells.length < count) cells.push('');
+  }
+
+  for (; i < cells.length; i++) {
+    // leading or trailing whitespace is ignored per the gfm spec
+    cells[i] = cells[i].trim().replace(/\\\|/g, '|');
+  }
+  return cells;
+}
+
+// Remove trailing 'c's. Equivalent to str.replace(/c*$/, '').
+// /c*$/ is vulnerable to REDOS.
+// invert: Remove suffix of non-c chars instead. Default falsey.
+function rtrim(str, c, invert) {
+  const l = str.length;
+  if (l === 0) {
+    return '';
+  }
+
+  // Length of suffix matching the invert condition.
+  let suffLen = 0;
+
+  // Step left until we fail to match the invert condition.
+  while (suffLen < l) {
+    const currChar = str.charAt(l - suffLen - 1);
+    if (currChar === c && !invert) {
+      suffLen++;
+    } else if (currChar !== c && invert) {
+      suffLen++;
+    } else {
+      break;
+    }
+  }
+
+  return str.substr(0, l - suffLen);
+}
+
+function findClosingBracket(str, b) {
+  if (str.indexOf(b[1]) === -1) {
+    return -1;
+  }
+  const l = str.length;
+  let level = 0,
+    i = 0;
+  for (; i < l; i++) {
+    if (str[i] === '\\') {
+      i++;
+    } else if (str[i] === b[0]) {
+      level++;
+    } else if (str[i] === b[1]) {
+      level--;
+      if (level < 0) {
+        return i;
+      }
+    }
+  }
+  return -1;
+}
+
+function checkSanitizeDeprecation(opt) {
+  if (opt && opt.sanitize && !opt.silent) {
+    console.warn('marked(): sanitize and sanitizer parameters are deprecated since version 0.7.0, should not be used and will be removed in the future. Read more here: https://marked.js.org/#/USING_ADVANCED.md#options');
+  }
+}
+
+module.exports = {
+  escape,
+  unescape,
+  edit,
+  cleanUrl,
+  resolveUrl,
+  noopTest,
+  merge,
+  splitCells,
+  rtrim,
+  findClosingBracket,
+  checkSanitizeDeprecation
+};