html-janitor - npm Package Compare versions

Comparing version 0.2.0 to 0.3.1

bower.json

 {
   "name": "html-janitor",
-  "version": "0.2.0",
-  "homepage": "https://github.com/guardian/html-janitor",
-  "main": "src/html-janitor.js",
-  "authors": [
-    "Oliver Joseph Ash <[e-mail]>"
-  ],
-  "license": "MIT",
-  "ignore": [
-    "**/.*",
-    "node_modules",
-    "bower_components",
-    "test",
-    "tests"
-  ],
   "devDependencies": {
-    "requirejs": "~2.1.9"
+    "requirejs": "2.1.9"
   }
 }

package.json

 {
   "name": "html-janitor",
-  "version": "0.2.0",
-  "description": "",
+  "version": "0.3.1",
   "main": "src/html-janitor.js",
@@ -9,22 +8,15 @@ "scripts": {
   },
-  "repository": {
-    "type": "git",
-    "url": "git://github.com/guardian/html-janitor.git"
-  },
-  "author": "Oliver Joseph Ash <[e-mail]>",
-  "license": "MIT",
-  "bugs": {
-    "url": "https://github.com/guardian/html-janitor/issues"
-  },
   "devDependencies": {
-    "karma-script-launcher": "~0.1.0",
-    "karma-firefox-launcher": "~0.1.0",
+    "karma": "~0.10.2",
     "karma-chrome-launcher": "~0.1.0",
-    "karma-html2js-preprocessor": "~0.1.0",
     "karma-jasmine": "~0.1.3",
-    "karma-requirejs": "~0.1.0",
-    "karma-coffee-preprocessor": "~0.1.0",
     "karma-phantomjs-launcher": "~0.1.0",
-    "karma": "~0.10.2"
+    "karma-requirejs": "~0.2.0",
+    "plumber": "~0.4.0",
+    "plumber-all": "~0.4.0",
+    "plumber-glob": "~0.4.0",
+    "plumber-requirejs": "~0.4.0",
+    "plumber-uglifyjs": "~0.4.0",
+    "plumber-write": "~0.4.0"
   }
 }

src/html-janitor.js

@@ -1,7 +0,8 @@
-// UMD
 (function (root, factory) {
   if (typeof define === 'function' && define.amd) {
-    define(factory);
+    define('html-janitor', factory);
+  } else if (typeof exports === 'object') {
+    module.exports = factory();
   } else {
-    root.amdWeb = factory();
+    root.HTMLJanitor = factory();
   }
@@ -14,2 +15,8 @@ }(this, function () {
 
+  // TODO: not exhaustive?
+  var blockElementNames = ['P', 'LI', 'DIV'];
+  function isBlockElement(node) {
+    return blockElementNames.indexOf(node.nodeName) !== -1;
+  }
+
   HTMLJanitor.prototype.clean = function (html) {
@@ -33,14 +40,35 @@ var sandbox = document.createElement('div');
 
-      // Ignore text nodes and nodes that have already been sanitized
-      if (node.nodeType === 3 || node._sanitized) {
+      // Ignore nodes that have already been sanitized
+      if (node._sanitized) {
         continue;
       }
 
+      if (node.nodeType === Node.TEXT_NODE) {
+        // If this text node is just whitespace and the previous or next element
+        // sibling is a block element, remove it
+        // N.B.: This heuristic could change. Very specific to a bug with
+        // `contenteditable` in Firefox: http://jsbin.com/EyuKase/1/edit?js,output
+        // FIXME: make this an option?
+        if (node.data.trim() === ''
+            && ((node.previousElementSibling && isBlockElement(node.previousElementSibling))
+                 || (node.nextElementSibling && isBlockElement(node.nextElementSibling)))) {
+          parentNode.removeChild(node);
+          this._sanitize(parentNode);
+          break;
+        } else {
+          continue;
+        }
+      }
+
+      // Remove all comments
+      if (node.nodeType === Node.COMMENT_NODE) {
+        parentNode.removeChild(node);
+        this._sanitize(parentNode);
+        break;
+      }
+
       var isInlineElement = nodeName === 'b';
       var containsBlockElement;
       if (isInlineElement) {
-        containsBlockElement = Array.prototype.some.call(node.childNodes, function (childNode) {
-          // TODO: test other block elements
-          return childNode.nodeName === 'P';
-        });
+        containsBlockElement = Array.prototype.some.call(node.childNodes, isBlockElement);
       }
@@ -50,5 +78,15 @@
 
+      // Block elements should not be nested (e.g. <li><p>...); if
+      // they are, we want to unwrap the inner block element.
+      var isNotTopContainer = !! parentNode.parentNode;
+      // TODO: Don't hardcore this — this is not invalid markup. Should be
+      // configurable.
+      var isNestedBlockElement =
+            isBlockElement(parentNode) &&
+            isBlockElement(node) &&
+            isNotTopContainer;
+
       // Drop tag entirely according to the whitelist *and* if the markup
       // is invalid.
-      if (!this.config.tags[nodeName] || isInvalid) {
+      if (!this.config.tags[nodeName] || isInvalid || isNestedBlockElement) {
         // Do not keep the inner text of SCRIPT/STYLE elements.
@@ -87,7 +125,8 @@ if (! (node.nodeName === 'SCRIPT' || node.nodeName === 'STYLE')) {
       node._sanitized = true;
-    } while (node = treeWalker.nextSibling());
+    } while ((node = treeWalker.nextSibling()));
   };
 
   function createTreeWalker(node) {
-    return document.createTreeWalker(node, NodeFilter.SHOW_ELEMENT);
+    return document.createTreeWalker(node,
+                                     NodeFilter.SHOW_TEXT | NodeFilter.SHOW_ELEMENT | NodeFilter.SHOW_COMMENT);
   }
@@ -94,0 +133,0 @@

test/janitor.spec.js

@@ -8,3 +8,5 @@ define([ 'html-janitor' ], function (HTMLJanitor) {
         b: {},
-        p: { foo: true, bar: 'baz' }
+        p: { foo: true, bar: 'baz' },
+        ul: {},
+        li: {}
       }
@@ -58,4 +60,31 @@
     });
+
+    it('should clean paragraphs in lists', function () {
+      var ul = document.createElement('ul');
+      ul.innerHTML = '<li><p>Some text</p></li>';
+      expect(janitor.clean(ul.outerHTML)).toBe('<ul><li>Some text</li></ul>');
+    });
+
+    it('should remove comments', function () {
+      var p = document.createElement('p');
+      p.innerHTML = 'Hello <b>world</b> <!-- a salutation -->!';
+      expect(janitor.clean(p.outerHTML)).toBe('<p>Hello <b>world</b> !</p>');
+    });
+
+    it('should remove text nodes in-between block elements', function () {
+      var html = '<p></p>\n<p></p>';
+      expect(janitor.clean(html)).toBe('<p></p><p></p>');
+    });
+
+    it('should remove text nodes before block elements', function () {
+      var html = '\n<p></p>';
+      expect(janitor.clean(html)).toBe('<p></p>');
+    });
+
+    it('should remove text nodes after block elements', function () {
+      var html = '<p></p>\n';
+      expect(janitor.clean(html)).toBe('<p></p>');
+    });
   });
 
 });

New alerts

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

Found 1 instance in 1 package

No contributors or author data

Maintenance

Package does not specify a list of contributors or an author in package.json.

Found 1 instance in 1 package

No bug tracker

Maintenance

Package does not have a linked bug tracker in package.json.

Found 1 instance in 1 package

No repository

Supply chain risk

Package does not have a linked source code repository. Without this field, a package will have no reference to the location of the source code use to generate the package.

Found 1 instance in 1 package

Fixed alerts

No README

Quality

Package does not have a README. This may indicate a failed publish or a low quality package.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

22779

increased by174.15%

Number of package files

15

increased by36.36%

Lines of code

279

increased by33.49%

Number of medium quality alerts

0

decreased by-100%

Number of lines in readme file

15

increased byInfinity%

Worsened metrics

Dev dependency count

11

increased by22.22%

Number of low maintenance alerts

3

increased by200%

Number of low supply chain risk alerts

3

increased by50%

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes