marked.js使用杂记

起因

我的博客系统的文章是直接使用gitbook保存的markdown文档，后端使用marked.js来解析markdown文档。

因为gitbook比较优秀，markdown进行了语法扩展，拿gitbook写文章也就更爽了。但是，这样问题就出现了，marked.js无法解析gitbook扩展的语法，所以我们就需要手动去解析这些扩展的markdown语法。

marked.js如何扩展语法?

想要扩展语法，也就需要深入了解marked.js的工作机制。

marked.js的工作机制：

创建Lexer(词法解析器)实例：

const lexer = new marked.Lexer()

lexer将markdown字符串解析成tokens(tokens是官方文档的叫法，按照我的理解应该是markdown节点(node))：

const tokens = lexer.lex(md)

接下来创建Parser(解析器)实例：

const parser = new marked.Parser()

调用parser.parse()来解析tokens，生成html字符串：

const html = parser.parse(tokens)

到这里，marked.js的工作机制就完了。 那么，我们需要修改的部分也就很清晰了，我们需要修改lexer的生成tokens函数、parser的解析函数以及渲染函数。

如何修改Lexer生成token的函数？

我看了marked.js的源码发现，lexer生成token的函数是一个名为token的函数，这个函数的代码是这样的：

marked.Lexer.prototype.token = function (src, top) {
  src = src.replace(/^ +$/gm, '');
  var next,
  // ...;

  while (src) {
    // newline
    if (cap = this.rules.newline.exec(src)) {
      src = src.substring(cap[0].length);
      if (cap[0].length > 1) {
        this.tokens.push({
          type: 'space'
        });
      }
    }
    // ...
  }
  //...
}

也就是，lexer用while循环来使用正则表达式进行判断是否符合语法，如果符合就push到tokens，然后切割字符串进行下次循环。我们就如法炮制一条正则表达式和循环中的代码块：

const customRules = {
  hint: /^<div data-gb-custom-block data-tag="hint" data-style='([a-z]+)'>\n(.*)?(\n</div>)/
}
// 将自定义的rule添加到词法解析器
marked.Lexer.rules = Object.assign(marked.Lexer.rules,customRules)
const lexer = new marked.Lexer();
// 源代码是merge了新的block rules，所以需要在实例上再添加一次
/*
block.normal = merge({}, block);
function Lexer(options) {
  this.tokens = [];
  this.tokens.links = Object.create(null);
  this.options = options || marked.defaults;
  this.rules = block.normal;
}
 */
Object.assign(lexer.rules,customRules)

// 重写词法解析器
marked.Lexer.prototype.token = function (src, top) {
  src = src.replace(/^ +$/gm, '');
  var next,
    //...;

  while (src) {
    // newline
    if (cap = this.rules.newline.exec(src)) {
      src = src.substring(cap[0].length);
      if (cap[0].length > 1) {
        this.tokens.push({
          type: 'space'
        });
      }
    }

    // 我们扩展的hint语法
    // hint
    if (cap = this.rules.hint.exec(src)) {
      var lastToken = this.tokens[this.tokens.length - 1];
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'hint',
        state:cap[1],
        text: cap[2]
      });
      continue;
    }
  }
  //...

这样，词法解析器就修改完成了，接下来我们需要修改Parser的解析函数用来生成对应hint语法的html

如何修改Parser解析？

依然是翻源码，找到parser的解析函数：tok

marked.Parser.prototype.tok = function() {
  switch (this.token.type) {
    case 'space': {
      return '';
    }
    case 'hr': {
      return this.renderer.hr();
    }
    //...
  }
  //...
}

我们需要在switch中增加一个case：

marked.Parser.prototype.tok = function() {
  switch (this.token.type) {
    case 'space': {
      return '';
    }
    case 'hint': {
      return this.renderer.hint(this.token.state, this.token.text);
    }
    case 'hr': {
      return this.renderer.hr();
    }
    //...
  }
  //...
}

这里的`this.renderer.hint`调用的是渲染器的函数，也就是让marked.js知道怎么渲染hint语法：

// 新建渲染器
const renderer = new marked.Renderer()

const hintState={
  info:`<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="currentColor" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" stroke="none" class="icon-7f6730be--text-3f89f380"><g><path d="M12.2 8.98c.06-.01.12-.03.18-.06.06-.02.12-.05.18-.09l.15-.12c.18-.19.29-.45.29-.71 0-.06-.01-.13-.02-.19a.603.603 0 0 0-.06-.19.757.757 0 0 0-.09-.18c-.03-.05-.08-.1-.12-.15-.28-.27-.72-.37-1.09-.21-.13.05-.23.12-.33.21-.04.05-.09.1-.12.15-.04.06-.07.12-.09.18-.03.06-.05.12-.06.19-.01.06-.02.13-.02.19 0 .26.11.52.29.71.1.09.2.16.33.21.12.05.25.08.38.08.06 0 .13-.01.2-.02M13 16v-4a1 1 0 1 0-2 0v4a1 1 0 1 0 2 0M12 3c-4.962 0-9 4.038-9 9 0 4.963 4.038 9 9 9 4.963 0 9-4.037 9-9 0-4.962-4.037-9-9-9m0 20C5.935 23 1 18.065 1 12S5.935 1 12 1c6.066 0 11 4.935 11 11s-4.934 11-11 11" fill-rule="evenodd"></path></g></svg>`,
  warning: `<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke="currentColor" class="icon-7f6730be--text-3f89f380" style="color: rgb(247, 125, 5);"><g><circle cx="12" cy="12" r="10"></circle><line x1="12" y1="8" x2="12" y2="12"></line><line x1="12" y1="16" x2="12" y2="16"></line></g></svg>`,
  danger: `<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke="currentColor" class="icon-7f6730be--text-3f89f380" style="color: rgb(255, 70, 66);"><g><path d="M10.29 3.86L1.82 18a2 2 0 0 0 1.71 3h16.94a2 2 0 0 0 1.71-3L13.71 3.86a2 2 0 0 0-3.42 0z"></path><line x1="12" y1="9" x2="12" y2="13"></line><line x1="12" y1="17" x2="12" y2="17"></line></g></svg>`,
  success: `<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke="currentColor" class="icon-7f6730be--text-3f89f380" style="color: rgb(38, 203, 124);"><g><path d="M22 11.07V12a10 10 0 1 1-5.93-9.14"></path><polyline points="23 3 12 14 9 11"></polyline></g></svg>`
}

// 自定义语法的渲染函数
renderer.hint = (state, text) => {
  return `<div class="hint ${state}">
    <span class="hint-icon">${hintState[state]}</span>
    <span class="hint-content">${text.replace(/\n/g,'<br/>')}</span>
  </div>`
}

最后，将renderer传递给marked.js：

marked.setOptions({ renderer })

这样，我们就新扩展了markdown的语法啦

例：

const md = `<div data-gb-custom-block data-tag="hint" data-style='info'>

1

</div>

<div data-gb-custom-block data-tag="hint" data-style='warning'>

2

</div>

<div data-gb-custom-block data-tag="hint" data-style='danger'>

3

</div>

<div data-gb-custom-block data-tag="hint" data-style='success'>

4

</div>

`

marked(md)

展示出来就是这个样子：

上面的代码是不完整的，下面贴上完整的代码

import marked from 'marked'
import hljs from 'highlight.js'

const customRules = {
  hint: /^

<div data-gb-custom-block data-tag="hint" data-style='([a-z]+)'>\n(.*)?(\n</div>)/
}

// 将自定义的rule添加到词法解析器
marked.Lexer.rules = Object.assign(marked.Lexer.rules,customRules)
const lexer = new marked.Lexer();
// 源代码是merge了新的block rules，所以需要在实例上再添加一次
/*
block.normal = merge({}, block);
function Lexer(options) {
  this.tokens = [];
  this.tokens.links = Object.create(null);
  this.options = options || marked.defaults;
  this.rules = block.normal;
}
 */
Object.assign(lexer.rules,customRules)

// 重写词法解析器
marked.Lexer.prototype.token = function (src, top) {
  src = src.replace(/^ +$/gm, '');
  var next,
    loose,
    cap,
    bull,
    b,
    item,
    listStart,
    listItems,
    t,
    space,
    i,
    tag,
    l,
    isordered,
    istask,
    ischecked;

  while (src) {
    // newline
    if (cap = this.rules.newline.exec(src)) {
      src = src.substring(cap[0].length);
      if (cap[0].length > 1) {
        this.tokens.push({
          type: 'space'
        });
      }
    }

    // hint
    if (cap = this.rules.hint.exec(src)) {
      var lastToken = this.tokens[this.tokens.length - 1];
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'hint',
        state:cap[1],
        text: cap[2]
      });
      continue;
    }

    // code
    if (cap = this.rules.code.exec(src)) {
      var lastToken = this.tokens[this.tokens.length - 1];
      src = src.substring(cap[0].length);
      // An indented code block cannot interrupt a paragraph.
      if (lastToken && lastToken.type === 'paragraph') {
        lastToken.text += '\n' + cap[0].trimRight();
      } else {
        cap = cap[0].replace(/^ {4}/gm, '');
        this.tokens.push({
          type: 'code',
          codeBlockStyle: 'indented',
          text: !this.options.pedantic
            ? rtrim(cap, '\n')
            : cap
        });
      }
      continue;
    }

    // fences
    if (cap = this.rules.fences.exec(src)) {
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'code',
        lang: cap[2] ? cap[2].trim() : cap[2],
        text: cap[3] || ''
      });
      continue;
    }

    // heading
    if (cap = this.rules.heading.exec(src)) {
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'heading',
        depth: cap[1].length,
        text: cap[2]
      });
      continue;
    }

    // table no leading pipe (gfm)
    if (cap = this.rules.nptable.exec(src)) {
      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) {
        src = src.substring(cap[0].length);

        for (i = 0; i < item.align.length; 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;
          }
        }

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

        this.tokens.push(item);

        continue;
      }
    }

    // hr
    if (cap = this.rules.hr.exec(src)) {
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'hr'
      });
      continue;
    }

    // blockquote
    if (cap = this.rules.blockquote.exec(src)) {
      src = src.substring(cap[0].length);

      this.tokens.push({
        type: 'blockquote_start'
      });

      cap = cap[0].replace(/^ *> ?/gm, '');

      // Pass `top` to keep the current
      // "toplevel" state. This is exactly
      // how markdown.pl works.
      this.token(cap, top);

      this.tokens.push({
        type: 'blockquote_end'
      });

      continue;
    }

    // list
    if (cap = this.rules.list.exec(src)) {
      src = src.substring(cap[0].length);
      bull = cap[2];
      isordered = bull.length > 1;

      listStart = {
        type: 'list_start',
        ordered: isordered,
        start: isordered ? +bull : '',
        loose: false
      };

      this.tokens.push(listStart);

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

      listItems = [];
      next = false;
      l = cap.length;
      i = 0;

      for (; i < l; i++) {
        item = cap[i];

        // 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.bullet.exec(cap[i + 1])[0];
          if (bull.length > 1 ? b.length === 1
            : (b.length > 1 || (this.options.smartLists && b !== bull))) {
            src = cap.slice(i + 1).join('\n') + src;
            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) {
          listStart.loose = true;
        }

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

        t = {
          type: 'list_item_start',
          task: istask,
          checked: ischecked,
          loose: loose
        };

        listItems.push(t);
        this.tokens.push(t);

        // Recurse.
        this.token(item, false);

        this.tokens.push({
          type: 'list_item_end'
        });
      }

      if (listStart.loose) {
        l = listItems.length;
        i = 0;
        for (; i < l; i++) {
          listItems[i].loose = true;
        }
      }

      this.tokens.push({
        type: 'list_end'
      });

      continue;
    }

    // html
    if (cap = this.rules.html.exec(src)) {
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: this.options.sanitize
          ? 'paragraph'
          : 'html',
        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]
      });
      continue;
    }

    // def
    if (top && (cap = this.rules.def.exec(src))) {
      src = src.substring(cap[0].length);
      if (cap[3]) cap[3] = cap[3].substring(1, cap[3].length - 1);
      tag = cap[1].toLowerCase().replace(/\s+/g, ' ');
      if (!this.tokens.links[tag]) {
        this.tokens.links[tag] = {
          href: cap[2],
          title: cap[3]
        };
      }
      continue;
    }

    // table (gfm)
    if (cap = this.rules.table.exec(src)) {
      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) {
        src = src.substring(cap[0].length);

        for (i = 0; i < item.align.length; 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;
          }
        }

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

        this.tokens.push(item);

        continue;
      }
    }

    // lheading
    if (cap = this.rules.lheading.exec(src)) {
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'heading',
        depth: cap[2].charAt(0) === '=' ? 1 : 2,
        text: cap[1]
      });
      continue;
    }

    // top-level paragraph
    if (top && (cap = this.rules.paragraph.exec(src))) {
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'paragraph',
        text: cap[1].charAt(cap[1].length - 1) === '\n'
          ? cap[1].slice(0, -1)
          : cap[1]
      });
      continue;
    }

    // text
    if (cap = this.rules.text.exec(src)) {
      // Top-level should never reach here.
      src = src.substring(cap[0].length);
      this.tokens.push({
        type: 'text',
        text: cap[0]
      });
      continue;
    }

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

// 重写解析器
marked.Parser.prototype.tok = function() {
  switch (this.token.type) {
    case 'space': {
      return '';
    }
    case 'hint': {
      return this.renderer.hint(this.token.state, this.token.text);
    }
    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': {
      var header = '',
          body = '',
          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 = '';
      var 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 = '';
      var loose = this.token.loose;
      var checked = this.token.checked;
      var task = this.token.task;

      if (this.token.task) {
        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: {
      var errMsg = 'Token with "' + this.token.type + '" type was not found.';
      if (this.options.silent) {
        console.log(errMsg);
      } else {
        throw new Error(errMsg);
      }
    }
  }
};


// 新建渲染器
const renderer = new marked.Renderer()

const hintState={
  info:`<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="currentColor" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" stroke="none" class="icon-7f6730be--text-3f89f380"><g><path d="M12.2 8.98c.06-.01.12-.03.18-.06.06-.02.12-.05.18-.09l.15-.12c.18-.19.29-.45.29-.71 0-.06-.01-.13-.02-.19a.603.603 0 0 0-.06-.19.757.757 0 0 0-.09-.18c-.03-.05-.08-.1-.12-.15-.28-.27-.72-.37-1.09-.21-.13.05-.23.12-.33.21-.04.05-.09.1-.12.15-.04.06-.07.12-.09.18-.03.06-.05.12-.06.19-.01.06-.02.13-.02.19 0 .26.11.52.29.71.1.09.2.16.33.21.12.05.25.08.38.08.06 0 .13-.01.2-.02M13 16v-4a1 1 0 1 0-2 0v4a1 1 0 1 0 2 0M12 3c-4.962 0-9 4.038-9 9 0 4.963 4.038 9 9 9 4.963 0 9-4.037 9-9 0-4.962-4.037-9-9-9m0 20C5.935 23 1 18.065 1 12S5.935 1 12 1c6.066 0 11 4.935 11 11s-4.934 11-11 11" fill-rule="evenodd"></path></g></svg>`,
  warning: `<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke="currentColor" class="icon-7f6730be--text-3f89f380" style="color: rgb(247, 125, 5);"><g><circle cx="12" cy="12" r="10"></circle><line x1="12" y1="8" x2="12" y2="12"></line><line x1="12" y1="16" x2="12" y2="16"></line></g></svg>`,
  danger: `<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke="currentColor" class="icon-7f6730be--text-3f89f380" style="color: rgb(255, 70, 66);"><g><path d="M10.29 3.86L1.82 18a2 2 0 0 0 1.71 3h16.94a2 2 0 0 0 1.71-3L13.71 3.86a2 2 0 0 0-3.42 0z"></path><line x1="12" y1="9" x2="12" y2="13"></line><line x1="12" y1="17" x2="12" y2="17"></line></g></svg>`,
  success: `<svg preserveAspectRatio="xMidYMid meet" height="1em" width="1em" fill="none" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" stroke="currentColor" class="icon-7f6730be--text-3f89f380" style="color: rgb(38, 203, 124);"><g><path d="M22 11.07V12a10 10 0 1 1-5.93-9.14"></path><polyline points="23 3 12 14 9 11"></polyline></g></svg>`
}

// 自定义语法的渲染函数
renderer.hint = (state, text) => {
  return `<div class="hint ${state}">
    <span class="hint-icon">${hintState[state]}</span>
    <span class="hint-content">${text.replace(/\n/g,'<br/>')}</span>
  </div>`
}

// code高亮
renderer.code = (code, language, isEscaped) => {
  const isMarkup = language === 'markup'
  let hled
  if (isMarkup) {
    hled = hljs.highlightAuto(code).value;
  } else {
    hled = hljs.highlight(language, code).value
  }
  return `<pre class="hljs"><code class="${language}">${hled}</code></pre>`
}
renderer.listitem = (body, task, checked) => {
  let className = ''
  if(task){
    className = 'task-item'
  }
  return `<li class="${className}">${body}</li>\n`;
}
marked.setOptions({ renderer })
export default marked