From 94207f8fb6ee8fe26fe18657f6b5aca6def99605 Mon Sep 17 00:00:00 2001
From: Igor Minar <igor@angularjs.org>
Date: Fri, 7 Aug 2015 09:30:26 -0700
Subject: [PATCH] fix($sanitize): support void elements, fixups, remove dead
 code, typos

Closes #12524
---
 .../$sanitize/{ddns.ngdoc => noinert.ngdoc}   |  6 +--
 src/ngSanitize/sanitize.js                    | 49 ++++++-------------
 test/ngSanitize/sanitizeSpec.js               | 28 +++--------
 3 files changed, 25 insertions(+), 58 deletions(-)
 rename docs/content/error/$sanitize/{ddns.ngdoc => noinert.ngdoc} (60%)

diff --git a/docs/content/error/$sanitize/ddns.ngdoc b/docs/content/error/$sanitize/noinert.ngdoc
similarity index 60%
rename from docs/content/error/$sanitize/ddns.ngdoc
rename to docs/content/error/$sanitize/noinert.ngdoc
index a1f6f77390c8..0562016bede1 100644
--- a/docs/content/error/$sanitize/ddns.ngdoc
+++ b/docs/content/error/$sanitize/noinert.ngdoc
@@ -1,9 +1,9 @@
 @ngdoc error
-@name $sanitize:ddns
-@fullName DOMDocument not supported
+@name $sanitize:noinert
+@fullName Can't create an inert html document
 @description
 
-This error occurs when `$sanitize` sanitizer determines that `DOMDocument` api is not supported by the current browser.
+This error occurs when `$sanitize` sanitizer determines that `document.implementation.createHTMLDocument ` api is not supported by the current browser.
 
 This api is necessary for safe parsing of HTML strings into DOM trees and without it the sanitizer can't sanitize the input.
 
diff --git a/src/ngSanitize/sanitize.js b/src/ngSanitize/sanitize.js
index d423fef72180..70797a1c9267 100644
--- a/src/ngSanitize/sanitize.js
+++ b/src/ngSanitize/sanitize.js
@@ -149,7 +149,7 @@ function sanitizeText(chars) {
 // Regular Expressions for parsing tags and attributes
 var SURROGATE_PAIR_REGEXP = /[\uD800-\uDBFF][\uDC00-\uDFFF]/g,
   // Match everything outside of normal chars and " (quote character)
-  NON_ALPHANUMERIC_REGEXP = /([^\#-~| |!])/g;
+  NON_ALPHANUMERIC_REGEXP = /([^\#-~ |!])/g;
 
 
 // Good source of info about elements and attributes
@@ -236,28 +236,24 @@ function toMap(str, lowercaseKeys) {
   return obj;
 }
 
-var baseNode;
+var inertBodyElement;
 (function(window) {
   var doc;
-  if (window.DOMDocument) {
-    doc = new window.DOMDocument();
-  } else if (window.document && window.document.implementation) {
+  if (window.document && window.document.implementation) {
     doc = window.document.implementation.createHTMLDocument("inert");
-  } else if (window.ActiveXObject) {
-    doc = new window.ActiveXObject("Msxml.DOMDocument");
   } else {
-    throw $sanitizeMinErr('ddns', "DOMDocument not supported");
+    throw $sanitizeMinErr('noinert', "Can't create an inert html document");
   }
   var docElement = doc.documentElement || doc.getDocumentElement();
   var bodyElements = docElement.getElementsByTagName('body');
 
   // usually there should be only one body element in the document, but IE doesn't have any, so we need to create one
   if (bodyElements.length === 1) {
-    baseNode = bodyElements[0];
+    inertBodyElement = bodyElements[0];
   } else {
     var html = doc.createElement('html');
-    baseNode = doc.createElement('body');
-    html.appendChild(baseNode);
+    inertBodyElement = doc.createElement('body');
+    html.appendChild(inertBodyElement);
     doc.appendChild(html);
   }
 })(window);
@@ -280,8 +276,8 @@ function htmlParser(html, handler) {
   } else if (typeof html !== 'string') {
     html = '' + html;
   }
-  baseNode.innerHTML = html;
-  var node = baseNode.firstChild;
+  inertBodyElement.innerHTML = html;
+  var node = inertBodyElement.firstChild;
   while (node) {
     switch (node.nodeType) {
       case 1: // ELEMENT_NODE
@@ -290,9 +286,6 @@ function htmlParser(html, handler) {
       case 3: // TEXT NODE
         handler.chars(node.textContent);
         break;
-      case 8: // COMMENT NODE
-        handler.comment(node.textContent);
-        break;
     }
 
     var nextNode;
@@ -304,7 +297,7 @@ function htmlParser(html, handler) {
       if (!nextNode) {
         while (nextNode == null) {
           node = node.parentNode;
-          if (node === baseNode) break;
+          if (node === inertBodyElement) break;
           nextNode = node.nextSibling;
           if (node.nodeType == 1) {
             handler.end(node.nodeName.toLowerCase());
@@ -315,8 +308,8 @@ function htmlParser(html, handler) {
     node = nextNode;
   }
 
-  while (node = baseNode.firstChild) {
-    baseNode.removeChild(node);
+  while (node = inertBodyElement.firstChild) {
+    inertBodyElement.removeChild(node);
   }
 }
 
@@ -329,20 +322,6 @@ function attrToMap(attrs) {
   return map;
 }
 
-var hiddenPre=document.createElement("pre");
-/**
- * decodes all entities into regular string
- * @param value
- * @returns {string} A string with decoded entities.
- */
-function decodeEntities(value) {
-  if (!value) { return ''; }
-
-  hiddenPre.innerHTML = value.replace(/</g,"&lt;");
-  // innerText depends on styling as it doesn't display hidden elements.
-  // Therefore, it's better to use textContent not to cause unnecessary reflows.
-  return hiddenPre.textContent;
-}
 
 /**
  * Escapes all potentially dangerous characters, so that the
@@ -368,7 +347,7 @@ function encodeEntities(value) {
 
 /**
  * create an HTML/XML writer which writes to buffer
- * @param {Array} buf use buf.jain('') to get out sanitized html string
+ * @param {Array} buf use buf.join('') to get out sanitized html string
  * @returns {object} in the form of {
  *     start: function(tag, attrs) {},
  *     end: function(tag) {},
@@ -405,7 +384,7 @@ function htmlSanitizeWriter(buf, uriValidator) {
     },
     end: function(tag) {
       tag = angular.lowercase(tag);
-      if (!ignore && validElements[tag] === true) {
+      if (!ignore && validElements[tag] === true && voidElements[tag] !== true) {
         out('</');
         out(tag);
         out('>');
diff --git a/test/ngSanitize/sanitizeSpec.js b/test/ngSanitize/sanitizeSpec.js
index 068991e72282..0f25caa53229 100644
--- a/test/ngSanitize/sanitizeSpec.js
+++ b/test/ngSanitize/sanitizeSpec.js
@@ -50,9 +50,9 @@ describe('HTML', function() {
       };
     });
 
-    it('should parse comments', function() {
+    it('should not parse comments', function() {
       htmlParser('<!--FOOBAR-->', handler);
-      expect(comment).toEqual('FOOBAR');
+      expect(comment).not.toBeDefined();
     });
 
     it('should parse basic format', function() {
@@ -66,18 +66,6 @@ describe('HTML', function() {
         toBe('&lt;- text1 text2 &lt;1 text1 text2 &lt;{');
     });
 
-    it('should throw badparse if text content contains "<" followed by "/" without matching ">"', function() {
-      htmlParser('foo </ bar', handler);
-      expect(start).toEqual(undefined);
-      expect(text).toEqual('foo ');
-    });
-
-    it('should throw badparse if text content contains "<" followed by an ASCII letter without matching ">"', function() {
-      htmlParser('foo <a bar', handler);
-      expect(start).toEqual(undefined);
-      expect(text).toEqual('foo ');
-    });
-
     it('should accept tag delimiters such as "<" inside real tags', function() {
       // Assert that the < is part of the text node content, and not part of a tag name.
       htmlParser('<p> 10 < 100 </p>', handler);
@@ -103,8 +91,8 @@ describe('HTML', function() {
     });
 
     it('should parse empty value attribute of node', function() {
-      htmlParser('<OPTION selected value="">abc</OPTION>', handler);
-      expect(start).toEqual({tag:'option', attrs:{selected:'', value:''}});
+      htmlParser('<test-foo selected value="">abc</test-foo>', handler);
+      expect(start).toEqual({tag:'test-foo', attrs:{selected:'', value:''}});
       expect(text).toEqual('abc');
     });
   });
@@ -165,7 +153,7 @@ describe('HTML', function() {
   });
 
   it('should handle self closed elements', function() {
-    expectHTML('a<hr/>c').toEqual('a<hr></hr>c');
+    expectHTML('a<hr/>c').toEqual('a<hr>c');
   });
 
   it('should handle namespace', function() {
@@ -192,7 +180,7 @@ describe('HTML', function() {
 
   it('should ignore back slash as escape', function() {
     expectHTML('<img alt="xxx\\" title="><script>....">').
-      toEqual('<img alt="xxx\\" title="&gt;&lt;script&gt;...."></img>');
+      toEqual('<img alt="xxx\\" title="&gt;&lt;script&gt;....">');
   });
 
   it('should ignore object attributes', function() {
@@ -415,11 +403,11 @@ describe('HTML', function() {
       inject(function() {
         $$sanitizeUri.andReturn('someUri');
 
-        expectHTML('<img src="someUri"/>').toEqual('<img src="someUri"></img>');
+        expectHTML('<img src="someUri"/>').toEqual('<img src="someUri">');
         expect($$sanitizeUri).toHaveBeenCalledWith('someUri', true);
 
         $$sanitizeUri.andReturn('unsafe:someUri');
-        expectHTML('<img src="someUri"/>').toEqual('<img></img>');
+        expectHTML('<img src="someUri"/>').toEqual('<img>');
       });
     });