vue 模板编译原理

我们都知道 vue 写代码是需要按照固定的格式，比如下面这样：

<template>
  <div>{{msg}}</div>
</template>

<script>
export default {
  data () {
    return {
      msg: ''
    }
  }
}
</script>

把 html 的内容写在 template 里面，经过 vue 的处理，首先会把模板转换为 AST 抽象语法树，然后把 AST 转换为可执行的 render 函数，最后才可以生成真是 DOM，那么今天要分析的内容是如何将模板生成 AST 的。

首先要生成的 AST 结构如下：

function createASTElement (
  tag,
  attrs,
  parent
) {
  return {
    type: 1,
    tag: tag,
    attrsList: attrs,
    attrsMap: attrs,
    rawAttrsMap: {},
    parent: parent,
    children: []
  }
}

然后就是把模板的内容都遍历一遍，通过正则去匹配标签的内容。

var unicodeRegExp = /a-zA-Z\u00B7\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u037D\u037F-\u1FFF\u200C-\u200D\u203F-\u2040\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD/;
// Regular Expressions for parsing tags and attributes
var attribute = /^\s*([^\s"'<>\/=]+)(?:\s*(=)\s*(?:"([^"]*)"+|'([^']*)'+|([^\s"'=<>`]+)))?/;
var dynamicArgAttribute = /^\s*((?:v-[\w-]+:|@|:|#)\[[^=]+?\][^\s"'<>\/=]*)(?:\s*(=)\s*(?:"([^"]*)"+|'([^']*)'+|([^\s"'=<>`]+)))?/;
var ncname = "[a-zA-Z_][\\-\\.0-9_a-zA-Z" + (unicodeRegExp.source) + "]*";
var qnameCapture = "((?:" + ncname + "\\:)?" + ncname + ")";
var startTagOpen = new RegExp(("^<" + qnameCapture));
var startTagClose = /^\s*(\/?)>/;
var endTag = new RegExp(("^<\\/" + qnameCapture + "[^>]*>"));
var doctype = /^<!DOCTYPE [^>]+>/i;
// #7298: escape - to avoid being passed as HTML comment when inlined in page
var reCache = {};
var comment = /^<!\--/;
var conditionalComment = /^<!\[/;

这些正则都是源码里面粘贴过来的，包括匹配开始标签，结束标签，注释等等。

function parseHTML(html, options) {
  var stack = [];
  var expectHTML = options.expectHTML;
  var isUnaryTag$$1 = options.isUnaryTag || no;
  var canBeLeftOpenTag$$1 = options.canBeLeftOpenTag || no;
  var index = 0;
  var last, lastTag;
  while (html) {
    last = html;
    // 确保不是 script 或者 style 者 textarea 标签
    if (!lastTag || !isPlainTextElement(lastTag)) {
      var textEnd = html.indexOf('<');
      if (textEnd === 0) {
        // End tag: 匹配结束标签
        var endTagMatch = html.match(endTag);
        if (endTagMatch) {
          var curIndex = index;
          advance(endTagMatch[0].length);
          parseEndTag(endTagMatch[1], curIndex, index);
          continue
        }

        // Start tag: 匹配开始标签
        var startTagMatch = parseStartTag();
        if (startTagMatch) {
          handleStartTag(startTagMatch);
          continue
        }
      }

      var text = (void 0), rest = (void 0), next = (void 0);
      if (textEnd >= 0) {
        rest = html.slice(textEnd);
        while (
          !endTag.test(rest) &&
          !startTagOpen.test(rest)
        ) {
          // 把标签里面的文字提取出来 hello</div> 提取 hello
          next = rest.indexOf('<', 1);
          if (next < 0) { break }
          textEnd += next;
          rest = html.slice(textEnd);
        }
        text = html.substring(0, textEnd);
      }

      if (textEnd < 0) {
        text = html;
      }
      if (text) {
        advance(text.length); // 去除文字 hello 剩下 </div>
      }

      if (options.chars && text) {
        options.chars(text, index - text.length, index);
      }
    } else {
      var endTagLength = 0;
      var stackedTag = lastTag.toLowerCase();
      var reStackedTag = reCache[stackedTag] || (reCache[stackedTag] = new RegExp('([\\s\\S]*?)(</' + stackedTag + '[^>]*>)', 'i'));
      var rest$1 = html.replace(reStackedTag, function (all, text, endTag) {
        endTagLength = endTag.length;
        return ''
      });
      index += html.length - rest$1.length;
      html = rest$1;
      parseEndTag(stackedTag, index - endTagLength, index);
    }
  }

  // Clean up any remaining tags
  parseEndTag();

  function advance(n) {
    index += n;
    html = html.substring(n);
  }

  function parseStartTag() {
    var start = html.match(startTagOpen);
    // [ '<div', 'div', index: 0, input: '<div id="1" bg="2">hello</div>', groups: undefined ]
    if (start) {
      var match = {
        tagName: start[1],
        attrs: [],
        start: index
      };
      advance(start[0].length); // 去除 <div，剩下 id="1" bg="2">hello</div>
      var end, attr;
      // 把属性都存储起来 id="1" bg="2" 去除属性之后剩下 >hello</div>
      while (!(end = html.match(startTagClose)) && (attr = html.match(dynamicArgAttribute) || html.match(attribute))) {
        attr.start = index;
        advance(attr[0].length);
        attr.end = index;
        match.attrs.push(attr);
      }
      if (end) {
        match.unarySlash = end[1];
        advance(end[0].length); // 把>或者/>去除剩下 hello</div>
        match.end = index;
        return match
      }
    }
  }

  function handleStartTag(match) {
    var tagName = match.tagName;
    var unarySlash = match.unarySlash; // 自闭合标签为/ 双标签为‘’空

    var unary = !!unarySlash;

    var l = match.attrs.length;
    var attrs = new Array(l);
    for (var i = 0; i < l; i++) {
      var args = match.attrs[i];
      var value = args[3] || args[4] || args[5] || '';
      attrs[i] = {
        name: args[1],
        value: value
      };
      // 按照{ name: value } 的形式保存起来，{ id: 1 }
      if (options.outputSourceRange) {
        attrs[i].start = args.start + args[0].match(/^\s*/).length;
        attrs[i].end = args.end;
      }
    }
    // 双标签
    if (!unary) {
      stack.push({ tag: tagName, lowerCasedTag: tagName.toLowerCase(), attrs: attrs, start: match.start, end: match.end });
      lastTag = tagName;
    }
    if (options.start) {
      options.start(tagName, attrs, unary, match.start, match.end);
    }
  }
  // stackedTag, index - endTagLength, index
  function parseEndTag(tagName, start, end) {
    var pos, lowerCasedTagName;
    if (start == null) { start = index; }
    if (end == null) { end = index; }

    // Find the closest opened tag of the same type
    if (tagName) {
      lowerCasedTagName = tagName.toLowerCase();
      for (pos = stack.length - 1; pos >= 0; pos--) {
        if (stack[pos].lowerCasedTag === lowerCasedTagName) {
          break
        }
      }
    } else {
      // If no tag name is provided, clean shop
      pos = 0;
    }
    if (pos >= 0) {
      // Close all the open elements, up the stack
      for (var i = stack.length - 1; i >= pos; i--) {
        if (options.end) {
          options.end(stack[i].tag, start, end);
        }
      }
      // Remove the open elements from the stack
      stack.length = pos;
      lastTag = pos && stack[pos - 1].tag;
    }
  }
}

上面是把所有的标签进行处理，按照顺序遍历之后就可以生成 AST 了。

var currentParent;
var stack = [];
var root;

function end(tag, start) {
  var element = stack[stack.length - 1];
  // pop stack 出栈
  stack.length -= 1;
  currentParent = stack[stack.length - 1];
  closeElement(element);
}

function start(tag, attrs, unary, start, end) {
  var element = createASTElement(tag, attrs, currentParent);
  if (!root) {
    root = element;
  }
  if (!unary) {
    currentParent = element;
    // push stack 入栈
    stack.push(element);
  }
}

function chars(text, start, end) {
  var children = currentParent.children;
  if (text) {
    var child;
    child = {
      type: 2,
      expression: '',
      tokens: '',
      text: text
    };
    if (child) {
      children.push(child);
    }
  }
}

function closeElement (element) {
  if (currentParent && !element.forbidden) {
    currentParent.children.push(element);
    element.parent = currentParent;
  }
  element.children = element.children.filter(function (c) { return !(c).slotScope; });
}

function createASTElement (
  tag,
  attrs,
  parent
) {
  return {
    type: 1,
    tag: tag,
    attrsList: attrs,
    attrsMap: attrs,
    rawAttrsMap: {},
    parent: parent,
    children: []
  }
}

const content = '<template><div bg="1">hello<span>11</span></div></template>'

parseHTML(content, {
  start: start,
  end: end,
  chars: chars
});

console.log(root) // ast