1.0.0

components/u-parse/libs/htmlparser.js

@@ -0,0 +1,156 @@
+/**
+ *
+ * htmlParser改造自: https://github.com/blowsie/Pure-JavaScript-HTML5-Parser
+ *
+ * author: Di (微信小程序开发工程师)
+ * organization: WeAppDev(微信小程序开发论坛)(http://weappdev.com)
+ *               垂直微信小程序开发交流社区
+ *
+ * github地址: https://github.com/icindy/wxParse
+ *
+ * for: 微信小程序富文本解析
+ * detail : http://weappdev.com/t/wxparse-alpha0-1-html-markdown/184
+ */
+// Regular Expressions for parsing tags and attributes
+
+const startTag = /^<([-A-Za-z0-9_]+)((?:\s+[a-zA-Z0-9_:][-a-zA-Z0-9_:.]*(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/;
+const endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/;
+const attr = /([a-zA-Z0-9_:][-a-zA-Z0-9_:.]*)(?:\s*=\s*(?:(?:"((?:\\.|[^"])*)")|(?:'((?:\\.|[^'])*)')|([^>\s]+)))?/g;
+
+function makeMap(str) {
+  const obj = {};
+  const items = str.split(',');
+  for (let i = 0; i < items.length; i += 1) obj[items[i]] = true;
+  return obj;
+}
+
+// Empty Elements - HTML 5
+const empty = makeMap('area,base,basefont,br,col,frame,hr,img,input,link,meta,param,embed,command,keygen,source,track,wbr');
+
+// Block Elements - HTML 5
+const block = makeMap('address,code,article,applet,aside,audio,blockquote,button,canvas,center,dd,del,dir,div,dl,dt,fieldset,figcaption,figure,footer,form,frameset,h1,h2,h3,h4,h5,h6,header,hgroup,hr,iframe,ins,isindex,li,map,menu,noframes,noscript,object,ol,output,p,pre,section,script,table,tbody,td,tfoot,th,thead,tr,ul,video');
+
+// Inline Elements - HTML 5
+const inline = makeMap('a,abbr,acronym,applet,b,basefont,bdo,big,br,button,cite,del,dfn,em,font,i,iframe,img,input,ins,kbd,label,map,object,q,s,samp,script,select,small,span,strike,strong,sub,sup,textarea,tt,u,var');
+
+// Elements that you can, intentionally, leave open
+// (and which close themselves)
+const closeSelf = makeMap('colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr');
+
+// Attributes that have their values filled in disabled="disabled"
+const fillAttrs = makeMap('checked,compact,declare,defer,disabled,ismap,multiple,nohref,noresize,noshade,nowrap,readonly,selected');
+
+function HTMLParser(html, handler) {
+  let index;
+  let chars;
+  let match;
+  let last = html;
+  const stack = [];
+
+  stack.last = () => stack[stack.length - 1];
+
+  function parseEndTag(tag, tagName) {
+    // If no tag name is provided, clean shop
+    let pos;
+    if (!tagName) {
+      pos = 0;
+    } else {
+      // Find the closest opened tag of the same type
+      tagName = tagName.toLowerCase();
+      for (pos = stack.length - 1; pos >= 0; pos -= 1) {
+        if (stack[pos] === tagName) break;
+      }
+    }
+    if (pos >= 0) {
+      // Close all the open elements, up the stack
+      for (let i = stack.length - 1; i >= pos; i -= 1) {
+        if (handler.end) handler.end(stack[i]);
+      }
+
+      // Remove the open elements from the stack
+      stack.length = pos;
+    }
+  }
+
+  function parseStartTag(tag, tagName, rest, unary) {
+    tagName = tagName.toLowerCase();
+
+    if (block[tagName]) {
+      while (stack.last() && inline[stack.last()]) {
+        parseEndTag('', stack.last());
+      }
+    }
+
+    if (closeSelf[tagName] && stack.last() === tagName) {
+      parseEndTag('', tagName);
+    }
+
+    unary = empty[tagName] || !!unary;
+
+    if (!unary) stack.push(tagName);
+
+    if (handler.start) {
+      const attrs = [];
+
+      rest.replace(attr, function genAttr(matches, name) {
+        const value = arguments[2] || arguments[3] || arguments[4] || (fillAttrs[name] ? name : '');
+
+        attrs.push({
+          name,
+          value,
+          escaped: value.replace(/(^|[^\\])"/g, '$1\\"'), // "
+        });
+      });
+
+      if (handler.start) {
+        handler.start(tagName, attrs, unary);
+      }
+    }
+  }
+
+  while (html) {
+    chars = true;
+
+    if (html.indexOf('</') === 0) {
+      match = html.match(endTag);
+
+      if (match) {
+        html = html.substring(match[0].length);
+        match[0].replace(endTag, parseEndTag);
+        chars = false;
+      }
+
+      // start tag
+    } else if (html.indexOf('<') === 0) {
+      match = html.match(startTag);
+
+      if (match) {
+        html = html.substring(match[0].length);
+        match[0].replace(startTag, parseStartTag);
+        chars = false;
+      }
+    }
+
+    if (chars) {
+      index = html.indexOf('<');
+      let text = '';
+      while (index === 0) {
+        text += '<';
+        html = html.substring(1);
+        index = html.indexOf('<');
+      }
+      text += index < 0 ? html : html.substring(0, index);
+      html = index < 0 ? '' : html.substring(index);
+
+      if (handler.chars) handler.chars(text);
+    }
+
+    if (html === last) throw new Error(`Parse Error: ${html}`);
+    last = html;
+  }
+
+  // Clean up any remaining tags
+  parseEndTag();
+}
+
+export default HTMLParser;