html-minifier 1.1.1 → 1.4.0

package/src/htmlparser.js

@@ -28,533 +28,500 @@
 
  /* global ActiveXObject, DOMDocument */
 
-(function(global) {
-  'use strict';
-
-  // Regular Expressions for parsing tags and attributes
-  var singleAttrIdentifier = /([\w:\.-]+)/,
-      singleAttrAssign = /=/,
-      singleAttrAssigns = [ singleAttrAssign ],
-      singleAttrValues = [
-        /"((?:\\.|[^"])*)"/.source, // attr value double quotes
-        /'((?:\\.|[^'])*)'/.source, // attr value, single quotes
-        /([^>\s]+)/.source          // attr value, no quotes
-      ],
-      startTagOpen = /^<([\w:-]+)/,
-      startTagClose = /\s*(\/?)>/,
-      endTag = /^<\/([\w:-]+)[^>]*>/,
-      endingSlash = /\/>$/,
-      doctype = /^<!DOCTYPE [^>]+>/i;
-
-  var IS_REGEX_CAPTURING_BROKEN = false;
-  'x'.replace(/x(.)?/g, function(m, g) {
-    IS_REGEX_CAPTURING_BROKEN = g === '';
-  });
-
-  // Empty Elements - HTML 4.01
-  var empty = makeMap('area,base,basefont,br,col,frame,hr,img,input,isindex,link,meta,param,embed,wbr');
-
-  // Block Elements - HTML 4.01
-  // var block = makeMap('address,applet,blockquote,button,center,dd,del,dir,div,dl,dt,fieldset,form,frameset,hr,iframe,ins,isindex,li,map,menu,noframes,noscript,object,ol,p,pre,script,table,tbody,td,tfoot,th,thead,tr,ul');
-
-  // Inline Elements - HTML 4.01
-  var inline = makeMap('a,abbr,acronym,applet,b,basefont,bdo,big,br,button,cite,code,del,dfn,em,font,i,iframe,img,input,ins,kbd,label,map,noscript,object,q,s,samp,script,select,small,span,strike,strong,sub,sup,svg,textarea,tt,u,var');
-
-  // Elements that you can, intentionally, leave open
-  // (and which close themselves)
-  var closeSelf = makeMap('colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr,source');
-
-  // Attributes that have their values filled in disabled='disabled'
-  var fillAttrs = makeMap('checked,compact,declare,defer,disabled,ismap,multiple,nohref,noresize,noshade,nowrap,readonly,selected');
-
-  // Special Elements (can contain anything)
-  var special = makeMap('script,style');
-
-  var reCache = {}, stackedTag, reStackedTag, tagMatch;
-
-  function startTagForHandler( handler ) {
-    var customStartTagAttrs;
-
-    var startTagAttrs = new RegExp(
-        '(?:\\s*[\\w:\\.-]+'
-      +   '(?:\\s*'
-      +     '(?:' + joinSingleAttrAssigns(handler) + ')'
-      +     '\\s*(?:(?:"[^"]*")|(?:\'[^\']*\')|[^>\\s]+)'
-      +   ')?'
-      + ')*'
-    );
-
-    if ( handler.customAttrSurround ) {
-      var attrClauses = [];
-
-      for ( var i = handler.customAttrSurround.length - 1; i >= 0; i-- ) {
-        // Capture the custom attribute opening and closing markup surrounding the standard attribute rules
-        attrClauses[i] = '(?:\\s*'
-          + handler.customAttrSurround[i][0].source
-          + startTagAttrs.source
-          + handler.customAttrSurround[i][1].source
-          + ')';
-      }
-      attrClauses.unshift(startTagAttrs.source);
-
-      customStartTagAttrs = new RegExp(
-        '((?:' + attrClauses.join('|') + ')*)'
-      );
-    }
-    else {
-      // No custom attribute wrappers specified, so just capture the standard attribute rules
-      customStartTagAttrs = new RegExp('(' + startTagAttrs.source + ')');
+'use strict';
+
+var createMapFromString = require('./utils').createMapFromString;
+
+function makeMap(values) {
+  return createMapFromString(values, true);
+}
+
+// Regular Expressions for parsing tags and attributes
+var singleAttrIdentifier = /([^\s"'<>\/=]+)/,
+    singleAttrAssign = /=/,
+    singleAttrAssigns = [ singleAttrAssign ],
+    singleAttrValues = [
+      // attr value double quotes
+      /"([^"]*)"+/.source,
+      // attr value, single quotes
+      /'([^']*)'+/.source,
+      // attr value, no quotes
+      /([^\s"'=<>`]+)/.source
+    ],
+    // https://www.w3.org/TR/1999/REC-xml-names-19990114/#NT-QName
+    qnameCapture = (function() {
+      var ncname = require('ncname').source.slice(1, -1);
+      return '((?:' + ncname + '\\:)?' + ncname + ')';
+    })(),
+    startTagOpen = new RegExp('^<' + qnameCapture),
+    startTagClose = /^\s*(\/?)>/,
+    endTag = new RegExp('^<\\/' + qnameCapture + '[^>]*>'),
+    doctype = /^<!DOCTYPE [^>]+>/i;
+
+var IS_REGEX_CAPTURING_BROKEN = false;
+'x'.replace(/x(.)?/g, function(m, g) {
+  IS_REGEX_CAPTURING_BROKEN = g === '';
+});
+
+// Empty Elements
+var empty = makeMap('area,base,basefont,br,col,embed,frame,hr,img,input,isindex,keygen,link,meta,param,source,track,wbr');
+
+// Inline Elements
+var inline = makeMap('a,abbr,acronym,applet,b,basefont,bdo,big,br,button,cite,code,del,dfn,em,font,i,iframe,img,input,ins,kbd,label,map,noscript,object,q,s,samp,script,select,small,span,strike,strong,sub,sup,svg,textarea,tt,u,var');
+
+// Elements that you can, intentionally, leave open
+// (and which close themselves)
+var closeSelf = makeMap('colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr,source');
+
+// Attributes that have their values filled in disabled='disabled'
+var fillAttrs = makeMap('checked,compact,declare,defer,disabled,ismap,multiple,nohref,noresize,noshade,nowrap,readonly,selected');
+
+// Special Elements (can contain anything)
+var special = makeMap('script,style');
+
+// HTML5 tags https://html.spec.whatwg.org/multipage/indices.html#elements-3
+// Phrasing Content https://html.spec.whatwg.org/multipage/dom.html#phrasing-content
+var nonPhrasing = makeMap('address,article,aside,base,blockquote,body,caption,col,colgroup,dd,details,dialog,div,dl,dt,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,head,header,hgroup,hr,html,legend,li,menuitem,meta,optgroup,option,param,rp,rt,source,style,summary,tbody,td,tfoot,th,thead,title,tr,track');
+
+var reCache = {};
+
+function attrForHandler(handler) {
+  var pattern = singleAttrIdentifier.source
+    + '(?:\\s*(' + joinSingleAttrAssigns(handler) + ')'
+    + '\\s*(?:' + singleAttrValues.join('|') + '))?';
+  if (handler.customAttrSurround) {
+    var attrClauses = [];
+    for ( var i = handler.customAttrSurround.length - 1; i >= 0; i-- ) {
+      attrClauses[i] = '(?:'
+        + '(' + handler.customAttrSurround[i][0].source + ')\\s*'
+        + pattern
+        + '\\s*(' + handler.customAttrSurround[i][1].source + ')'
+        + ')';
     }
-
-    return new RegExp(startTagOpen.source + customStartTagAttrs.source + startTagClose.source);
+    attrClauses.push('(?:' + pattern + ')');
+    pattern = '(?:' + attrClauses.join('|') + ')';
   }
-
-  function attrForHandler( handler ) {
-    var singleAttr = new RegExp(
-      singleAttrIdentifier.source
-      + '(?:\\s*'
-      + '(' + joinSingleAttrAssigns( handler ) + ')'
-      + '\\s*'
-      + '(?:'
-      + singleAttrValues.join('|')
-      + ')'
-      + ')?'
-    );
-
-    if ( handler.customAttrSurround ) {
-      var attrClauses = [];
-      for ( var i = handler.customAttrSurround.length - 1; i >= 0; i-- ) {
-        attrClauses[i] = '(?:'
-          + '(' + handler.customAttrSurround[i][0].source + ')'
-          + singleAttr.source
-          + '(' + handler.customAttrSurround[i][1].source + ')'
-          + ')';
-      }
-      attrClauses.unshift('(?:' + singleAttr.source + ')');
-
-      return new RegExp(attrClauses.join('|'), 'g');
-    }
-    else {
-      return new RegExp(singleAttr.source, 'g');
-    }
-  }
-
-  function joinSingleAttrAssigns( handler ) {
-    return singleAttrAssigns.concat(
-      handler.customAttrAssign || []
-    ).map(function (assign) {
-      return '(?:' + assign.source + ')';
-    }).join('|');
-  }
-
-  var HTMLParser = global.HTMLParser = function( html, handler ) {
-    var index, chars, match, stack = [], last = html, prevTag, nextTag;
-    stack.last = function() {
-      var last = this[ this.length - 1 ];
-      return last && last.tag;
-    };
-
-    var startTag = startTagForHandler(handler);
-    var attr = attrForHandler(handler);
-
-    while ( html ) {
-      chars = true;
-
-      // Make sure we're not in a script or style element
-      if ( !stack.last() || !special[ stack.last() ] ) {
-
+  return new RegExp('^\\s*' + pattern);
+}
+
+function joinSingleAttrAssigns( handler ) {
+  return singleAttrAssigns.concat(
+    handler.customAttrAssign || []
+  ).map(function (assign) {
+    return '(?:' + assign.source + ')';
+  }).join('|');
+}
+
+function HTMLParser( html, handler ) {
+  var stack = [], lastTag;
+  var attribute = attrForHandler(handler);
+  var last, prevTag, nextTag;
+  while ( html ) {
+    last = html;
+    // Make sure we're not in a script or style element
+    if ( !lastTag || !special(lastTag) ) {
+      var textEnd = html.indexOf('<');
+      if (textEnd === 0) {
         // Comment:
         if ( /^<!--/.test( html ) ) {
-          index = html.indexOf('-->');
+          var commentEnd = html.indexOf('-->');
 
-          if ( index >= 0 ) {
+          if ( commentEnd >= 0 ) {
             if ( handler.comment ) {
-              handler.comment( html.substring( 4, index ) );
+              handler.comment( html.substring( 4, commentEnd ) );
             }
-            html = html.substring( index + 3 );
-            chars = false;
+            html = html.substring( commentEnd + 3 );
+            prevTag = '';
+            continue;
           }
         }
 
         // http://en.wikipedia.org/wiki/Conditional_comment#Downlevel-revealed_conditional_comment
         if ( /^<!\[/.test( html ) ) {
-          index = html.indexOf(']>');
+          var conditionalEnd = html.indexOf(']>');
 
-          if (index >= 0) {
+          if (conditionalEnd >= 0) {
             if ( handler.comment ) {
-              handler.comment( html.substring(2, index + 1 ), true /* non-standard */ );
-            }
-            html = html.substring( index + 2 );
-            chars = false;
-          }
-        }
-
-        // Ignored elements?
-        else if ( /^<\?/.test( html ) ) {
-          index = html.indexOf( '?>', 2 );
-          if ( index >= 0 ) {
-            if ( handler.chars ) {
-              handler.chars( html.substring( 0, index + 2 ) );
-            }
-            html = html.substring( index + 2 );
-          }
-        }
-
-        else if ( /^<%/.test( html ) ) {
-          index = html.indexOf( '%>', 2 );
-          if ( index >= 0 ) {
-            if ( handler.chars ) {
-              handler.chars(html.substring( 0, index + 2) );
+              handler.comment( html.substring(2, conditionalEnd + 1 ), true /* non-standard */ );
             }
-            html = html.substring( index + 2 );
+            html = html.substring( conditionalEnd + 2 );
+            prevTag = '';
+            continue;
           }
         }
 
         // Doctype:
-        else if ( (match = doctype.exec( html )) ) {
+        var doctypeMatch = html.match( doctype );
+        if ( doctypeMatch ) {
           if ( handler.doctype ) {
-            handler.doctype( match[0] );
+            handler.doctype( doctypeMatch[0] );
           }
-          html = html.substring( match[0].length );
-          chars = false;
+          html = html.substring( doctypeMatch[0].length );
+          prevTag = '';
+          continue;
         }
 
         // End tag:
-        else if ( /^<\//.test( html ) ) {
-          match = html.match( endTag );
-
-          if ( match ) {
-            html = html.substring( match[0].length );
-            match[0].replace( endTag, parseEndTag );
-            prevTag = '/' + match[1].toLowerCase();
-            chars = false;
-          }
-
+        var endTagMatch = html.match( endTag );
+        if ( endTagMatch ) {
+          html = html.substring( endTagMatch[0].length );
+          endTagMatch[0].replace( endTag, parseEndTag );
+          prevTag = '/' + endTagMatch[1].toLowerCase();
+          continue;
         }
+
         // Start tag:
-        else if ( /^</.test( html ) ) {
-          match = html.match( startTag );
-          if ( match ) {
-            html = html.substring( match[0].length );
-            match[0].replace( startTag, parseStartTag );
-            prevTag = match[1].toLowerCase();
-            chars = false;
-          }
+        var startTagMatch = parseStartTag(html);
+        if ( startTagMatch ) {
+          html = startTagMatch.rest;
+          handleStartTag(startTagMatch);
+          prevTag = startTagMatch.tagName.toLowerCase();
+          continue;
         }
+      }
 
-        if ( chars ) {
-          index = html.indexOf('<');
-
-          var text = index < 0 ? html : html.substring( 0, index );
-          html = index < 0 ? '' : html.substring( index );
-
-          // next tag
-          tagMatch = html.match( startTag );
-          if (tagMatch) {
-            nextTag = tagMatch[1];
-          }
-          else {
-            tagMatch = html.match( endTag );
-            if (tagMatch) {
-              nextTag = '/' + tagMatch[1];
-            }
-            else {
-              nextTag = '';
-            }
-          }
-
-          if ( handler.chars ) {
-            handler.chars(text, prevTag, nextTag);
-          }
-
-        }
+      var text;
+      if (textEnd >= 0) {
+        text = html.substring( 0, textEnd );
+        html = html.substring( textEnd );
+      }
+      else {
+        text = html;
+        html = '';
+      }
 
+      // next tag
+      var nextTagMatch = parseStartTag(html);
+      if (nextTagMatch) {
+        nextTag = nextTagMatch.tagName;
       }
       else {
+        nextTagMatch = html.match( endTag );
+        if (nextTagMatch) {
+          nextTag = '/' + nextTagMatch[1];
+        }
+        else {
+          nextTag = '';
+        }
+      }
 
-        stackedTag = stack.last().toLowerCase();
-        reStackedTag = reCache[stackedTag] || (reCache[stackedTag] = new RegExp('([\\s\\S]*?)<\/' + stackedTag + '[^>]*>', 'i'));
+      if ( handler.chars ) {
+        handler.chars(text, prevTag, nextTag);
+      }
+      prevTag = '';
 
-        html = html.replace(reStackedTag, function(all, text) {
-          if (stackedTag !== 'script' && stackedTag !== 'style' && stackedTag !== 'noscript') {
-            text = text
-              .replace(/<!--([\s\S]*?)-->/g, '$1')
-              .replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, '$1');
-          }
+    }
+    else {
+      var stackedTag = lastTag.toLowerCase();
+      var reStackedTag = reCache[stackedTag] || (reCache[stackedTag] = new RegExp('([\\s\\S]*?)<\/' + stackedTag + '[^>]*>', 'i'));
+
+      html = html.replace(reStackedTag, function(all, text) {
+        if (stackedTag !== 'script' && stackedTag !== 'style' && stackedTag !== 'noscript') {
+          text = text
+            .replace(/<!--([\s\S]*?)-->/g, '$1')
+            .replace(/<!\[CDATA\[([\s\S]*?)\]\]>/g, '$1');
+        }
 
-          if ( handler.chars ) {
-            handler.chars( text );
-          }
+        if ( handler.chars ) {
+          handler.chars( text );
+        }
 
-          return '';
-        });
+        return '';
+      });
 
-        parseEndTag( '', stackedTag );
-      }
+      parseEndTag( '</' + stackedTag + '>', stackedTag );
+    }
 
-      if ( html === last ) {
-        throw 'Parse Error: ' + html;
-      }
-      last = html;
+    if ( html === last ) {
+      throw new Error('Parse Error: ' + html);
     }
+  }
 
+  if (!handler.partialMarkup) {
     // Clean up any remaining tags
     parseEndTag();
+  }
 
-    function parseStartTag( tag, tagName, rest, unary ) {
-      var unarySlash = false;
-
-      while ( !handler.html5 && stack.last() && inline[ stack.last() ]) {
-        parseEndTag( '', stack.last() );
+  function parseStartTag(input) {
+    var start = input.match(startTagOpen);
+    if (start) {
+      var match = {
+        tagName: start[1],
+        attrs: []
+      };
+      input = input.slice(start[0].length);
+      var end, attr;
+      while (!(end = input.match(startTagClose)) && (attr = input.match(attribute))) {
+        input = input.slice(attr[0].length);
+        match.attrs.push(attr);
       }
-
-      if ( closeSelf[ tagName ] && stack.last() === tagName ) {
-        parseEndTag( '', tagName );
+      if (end) {
+        match.unarySlash = end[1];
+        match.rest = input.slice(end[0].length);
+        return match;
       }
+    }
+  }
 
-      unary = empty[ tagName ] || !!unary;
+  function handleStartTag(match) {
+    var tagName = match.tagName;
+    var unarySlash = match.unarySlash;
 
-      var attrs = [];
+    if (handler.html5 && lastTag === 'p' && nonPhrasing(tagName)) {
+      parseEndTag( '', lastTag );
+    }
 
-      rest.replace(attr, function () {
-        var name, value, fallbackValue, customOpen, customClose, customAssign, quote;
-        var ncp = 7; // number of captured parts, scalar
+    if (!handler.html5) {
+      while (lastTag && inline(lastTag)) {
+        parseEndTag( '', lastTag );
+      }
+    }
 
-        // hackish work around FF bug https://bugzilla.mozilla.org/show_bug.cgi?id=369778
-        if (IS_REGEX_CAPTURING_BROKEN && arguments[0].indexOf('""') === -1) {
-          if (arguments[3] === '') { arguments[3] = undefined; }
-          if (arguments[4] === '') { arguments[4] = undefined; }
-          if (arguments[5] === '') { arguments[5] = undefined; }
-        }
+    if ( closeSelf(tagName) && lastTag === tagName ) {
+      parseEndTag( '', tagName );
+    }
 
-        name = arguments[1];
-        if ( name ) {
-          customAssign = arguments[2];
-          fallbackValue = arguments[3];
-          value = fallbackValue || arguments[4] || arguments[5];
+    var unary = empty(tagName) || tagName === 'html' && lastTag === 'head' || !!unarySlash;
 
-          if (customAssign) {
-            quote = arguments[0].charAt(name.length + customAssign.length);
-            quote = (quote === '\'' || quote === '"') ? quote : '';
-          }
+    var attrs = match.attrs.map(function(args) {
+      var name, value, fallbackValue, customOpen, customClose, customAssign, quote;
+      var ncp = 7; // number of captured parts, scalar
 
-        }
-        else if ( handler.customAttrSurround ) {
-          for ( var i = handler.customAttrSurround.length - 1; i >= 0; i-- ) {
-            name = arguments[i * ncp + 7];
-            customAssign = arguments[i * ncp + 8];
-            if ( name ) {
-              fallbackValue = arguments[i * ncp + 9];
-              value = fallbackValue
-                || arguments[i * ncp + 10]
-                || arguments[i * ncp + 11];
-              customOpen = arguments[i * ncp + 6];
-              customClose = arguments[i * ncp + 12];
-              break;
-            }
-          }
-        }
+      // hackish work around FF bug https://bugzilla.mozilla.org/show_bug.cgi?id=369778
+      if (IS_REGEX_CAPTURING_BROKEN && args[0].indexOf('""') === -1) {
+        if (args[3] === '') { args[3] = undefined; }
+        if (args[4] === '') { args[4] = undefined; }
+        if (args[5] === '') { args[5] = undefined; }
+      }
 
-        if ( value === undefined ) {
-          value = fillAttrs[name] ? name : fallbackValue;
+      var j = 1;
+      if (handler.customAttrSurround) {
+        for (var i = 0, l = handler.customAttrSurround.length; i < l; i++, j += ncp) {
+          name = args[j + 1];
+          customAssign = args[j + 2];
+          if (name) {
+            fallbackValue = args[j + 3];
+            value = fallbackValue || args[j + 4] || args[j + 5];
+            quote = fallbackValue ? '"' : value ? '\'' : '';
+            customOpen = args[j];
+            customClose = args[j + 6];
+            break;
+          }
         }
+      }
 
-        attrs.push({
-          name: name,
-          value: value,
-          escaped: value && value.replace(/(^|.)("+)/g, function(match) {
-            return match.replace(/"/g, '&quot;');
-          }),
-          customAssign: customAssign || '=',
-          customOpen:  customOpen || '',
-          customClose: customClose || '',
-          quote: quote || ''
-        });
-      });
-
-      if ( !unary ) {
-        stack.push( { tag: tagName, attrs: attrs } );
+      if (!name && (name = args[j])) {
+        customAssign = args[j + 1];
+        fallbackValue = args[j + 2];
+        value = fallbackValue || args[j + 3] || args[j + 4];
+        quote = fallbackValue ? '"' : value ? '\'' : '';
       }
-      else {
-        unarySlash = tag.match( endingSlash );
+
+      if (value === undefined) {
+        value = fillAttrs(name) ? name : fallbackValue;
       }
 
+      return {
+        name: name,
+        value: value,
+        customAssign: customAssign || '=',
+        customOpen: customOpen || '',
+        customClose: customClose || '',
+        quote: quote || ''
+      };
+    });
 
-      if ( handler.start ) {
-        handler.start( tagName, attrs, unary, unarySlash );
-      }
+    if ( !unary ) {
+      stack.push( { tag: tagName, attrs: attrs } );
+      lastTag = tagName;
+      unarySlash = '';
     }
 
-    function parseEndTag( tag, tagName ) {
-      var pos;
+    if ( handler.start ) {
+      handler.start( tagName, attrs, unary, unarySlash );
+    }
+  }
 
-      // If no tag name is provided, clean shop
-      if ( !tagName ) {
-        pos = 0;
-      }
-      else {
-        // Find the closest opened tag of the same type
-        var needle = tagName.toLowerCase();
-        for ( pos = stack.length - 1; pos >= 0; pos-- ) {
-          if ( stack[ pos ].tag.toLowerCase() === needle ) {
-            break;
-          }
+  function parseEndTag( tag, tagName ) {
+    var pos;
+
+    // If no tag name is provided, clean shop
+    if ( !tagName ) {
+      pos = 0;
+    }
+    else {
+      // Find the closest opened tag of the same type
+      var needle = tagName.toLowerCase();
+      for ( pos = stack.length - 1; pos >= 0; pos-- ) {
+        if ( stack[ pos ].tag.toLowerCase() === needle ) {
+          break;
         }
       }
+    }
 
-      if ( pos >= 0 ) {
-        // Close all the open elements, up the stack
-        for ( var i = stack.length - 1; i >= pos; i-- ) {
-          if ( handler.end ) {
-            handler.end( stack[ i ].tag, stack[ i ].attrs );
-          }
+    if ( pos >= 0 ) {
+      // Close all the open elements, up the stack
+      for ( var i = stack.length - 1; i >= pos; i-- ) {
+        if ( handler.end ) {
+          handler.end( stack[ i ].tag, stack[ i ].attrs, i > pos || !tag );
         }
+      }
 
-        // Remove the open elements from the stack
-        stack.length = pos;
+      // Remove the open elements from the stack
+      stack.length = pos;
+      lastTag = pos && stack[ pos - 1 ].tag;
+    }
+    else if (tagName.toLowerCase() === 'br') {
+      if (handler.start) {
+        handler.start(tagName, [], true, '');
       }
     }
-  };
-
-  global.HTMLtoXML = function( html ) {
-    var results = '';
+    else if (tagName.toLowerCase() === 'p') {
+      if (handler.start) {
+        handler.start(tagName, [], false, '', true);
+      }
+      if (handler.end) {
+        handler.end(tagName, []);
+      }
+    }
+  }
+}
 
-    new HTMLParser(html, {
-      start: function( tag, attrs, unary ) {
-        results += '<' + tag;
+exports.HTMLParser = HTMLParser;
+exports.HTMLtoXML = function( html ) {
+  var results = '';
 
-        for ( var i = 0; i < attrs.length; i++ ) {
-          results += ' ' + attrs[i].name + '="' + attrs[i].escaped + '"';
-        }
+  new HTMLParser(html, {
+    start: function( tag, attrs, unary ) {
+      results += '<' + tag;
 
-        results += (unary ? '/' : '') + '>';
-      },
-      end: function( tag ) {
-        results += '</' + tag + '>';
-      },
-      chars: function( text ) {
-        results += text;
-      },
-      comment: function( text ) {
-        results += '<!--' + text + '-->';
-      },
-      ignore: function(text) {
-        results += text;
+      for ( var i = 0; i < attrs.length; i++ ) {
+        results += ' ' + attrs[i].name + '="' + (attrs[i].value || '').replace(/"/g, '&#34;') + '"';
       }
-    });
 
-    return results;
-  };
+      results += (unary ? '/' : '') + '>';
+    },
+    end: function( tag ) {
+      results += '</' + tag + '>';
+    },
+    chars: function( text ) {
+      results += text;
+    },
+    comment: function( text ) {
+      results += '<!--' + text + '-->';
+    },
+    ignore: function(text) {
+      results += text;
+    }
+  });
 
-  global.HTMLtoDOM = function( html, doc ) {
-    // There can be only one of these elements
-    var one = makeMap('html,head,body,title');
+  return results;
+};
 
-    // Enforce a structure for the document
-    var structure = {
-      link: 'head',
-      base: 'head'
-    };
+exports.HTMLtoDOM = function( html, doc ) {
+  // There can be only one of these elements
+  var one = {
+    html: true,
+    head: true,
+    body: true,
+    title: true
+  };
 
-    if ( !doc ) {
-      if ( typeof DOMDocument !== 'undefined' ) {
-        doc = new DOMDocument();
-      }
-      else if ( typeof document !== 'undefined' && document.implementation && document.implementation.createDocument ) {
-        doc = document.implementation.createDocument('', '', null);
-      }
-      else if ( typeof ActiveX !== 'undefined' ) {
-        doc = new ActiveXObject('Msxml.DOMDocument');
-      }
+  // Enforce a structure for the document
+  var structure = {
+    link: 'head',
+    base: 'head'
+  };
 
+  if ( !doc ) {
+    if ( typeof DOMDocument !== 'undefined' ) {
+      doc = new DOMDocument();
     }
-    else {
-      doc = doc.ownerDocument ||
-        doc.getOwnerDocument && doc.getOwnerDocument() ||
-        doc;
+    else if ( typeof document !== 'undefined' && document.implementation && document.implementation.createDocument ) {
+      doc = document.implementation.createDocument('', '', null);
+    }
+    else if ( typeof ActiveX !== 'undefined' ) {
+      doc = new ActiveXObject('Msxml.DOMDocument');
     }
 
-    var elems = [],
+  }
+  else {
+    doc = doc.ownerDocument ||
+      doc.getOwnerDocument && doc.getOwnerDocument() ||
+      doc;
+  }
+
+  var elems = [],
       documentElement = doc.documentElement ||
         doc.getDocumentElement && doc.getDocumentElement();
 
-    // If we're dealing with an empty document then we
-    // need to pre-populate it with the HTML document structure
-    if ( !documentElement && doc.createElement ) {
-      (function() {
-        var html = doc.createElement('html');
-        var head = doc.createElement('head');
-        head.appendChild( doc.createElement('title') );
-        html.appendChild( head );
-        html.appendChild( doc.createElement('body') );
-        doc.appendChild( html );
-      })();
-    }
+  // If we're dealing with an empty document then we
+  // need to pre-populate it with the HTML document structure
+  if ( !documentElement && doc.createElement ) {
+    (function() {
+      var html = doc.createElement('html');
+      var head = doc.createElement('head');
+      head.appendChild( doc.createElement('title') );
+      html.appendChild( head );
+      html.appendChild( doc.createElement('body') );
+      doc.appendChild( html );
+    })();
+  }
 
-    // Find all the unique elements
-    if ( doc.getElementsByTagName ) {
-      for ( var i in one ) {
-        one[ i ] = doc.getElementsByTagName( i )[0];
-      }
+  // Find all the unique elements
+  if ( doc.getElementsByTagName ) {
+    for ( var i in one ) {
+      one[ i ] = doc.getElementsByTagName( i )[0];
     }
+  }
 
-    // If we're working with a document, inject contents into
-    // the body element
-    var curParentNode = one.body;
-
-    new HTMLParser( html, {
-      start: function( tagName, attrs, unary ) {
-        // If it's a pre-built element, then we can ignore
-        // its construction
-        if ( one[ tagName ] ) {
-          curParentNode = one[ tagName ];
-          return;
-        }
-
-        var elem = doc.createElement( tagName );
-
-        for ( var attr in attrs ) {
-          elem.setAttribute( attrs[ attr ].name, attrs[ attr ].value );
-        }
+  // If we're working with a document, inject contents into
+  // the body element
+  var curParentNode = one.body;
+
+  new HTMLParser( html, {
+    start: function( tagName, attrs, unary ) {
+      // If it's a pre-built element, then we can ignore
+      // its construction
+      if ( one[ tagName ] ) {
+        curParentNode = one[ tagName ];
+        return;
+      }
 
-        if ( structure[ tagName ] && typeof one[ structure[ tagName ] ] !== 'boolean' ) {
-          one[ structure[ tagName ] ].appendChild( elem );
-        }
-        else if ( curParentNode && curParentNode.appendChild ) {
-          curParentNode.appendChild( elem );
-        }
+      var elem = doc.createElement( tagName );
 
-        if ( !unary ) {
-          elems.push( elem );
-          curParentNode = elem;
-        }
-      },
-      end: function( /* tag */ ) {
-        elems.length -= 1;
-
-        // Init the new parentNode
-        curParentNode = elems[ elems.length - 1 ];
-      },
-      chars: function( text ) {
-        curParentNode.appendChild( doc.createTextNode( text ) );
-      },
-      comment: function( /*text*/ ) {
-        // create comment node
-      },
-      ignore: function( /* text */ ) {
-        // What to do here?
+      for ( var attr in attrs ) {
+        elem.setAttribute( attrs[ attr ].name, attrs[ attr ].value );
       }
-    });
 
-    return doc;
-  };
+      if ( structure[ tagName ] && typeof one[ structure[ tagName ] ] !== 'boolean' ) {
+        one[ structure[ tagName ] ].appendChild( elem );
+      }
+      else if ( curParentNode && curParentNode.appendChild ) {
+        curParentNode.appendChild( elem );
+      }
 
-  function makeMap(str) {
-    var obj = {}, items = str.split(',');
-    for ( var i = 0; i < items.length; i++ ) {
-      obj[ items[i] ] = true;
-      obj[ items[i].toUpperCase() ] = true;
+      if ( !unary ) {
+        elems.push( elem );
+        curParentNode = elem;
+      }
+    },
+    end: function( /* tag */ ) {
+      elems.length -= 1;
+
+      // Init the new parentNode
+      curParentNode = elems[ elems.length - 1 ];
+    },
+    chars: function( text ) {
+      curParentNode.appendChild( doc.createTextNode( text ) );
+    },
+    comment: function( /* text */ ) {
+      // create comment node
+    },
+    ignore: function( /* text */ ) {
+      // What to do here?
     }
-    return obj;
-  }
-})(typeof exports === 'undefined' ? this : exports);
+  });
+
+  return doc;
+};