html-parser - npm Package Compare versions

Comparing version 0.1.0 to 0.2.0

package.json

 {
-    "name": "html-parser",
-    "version": "0.1.0",
-    "description": "HTML/XML parser with less explosions",
-    "author": {
-	    "name": "Tommy Montgomery",
-	    "email": "[e-mail]",
-	    "url": "http://tmont.com/"
-    },
+	"name": "html-parser",
+	"version": "0.2.0",
+	"description": "HTML/XML parser with less explosions",
+	"keywords": [ "html", "xml", "parser", "explosion" ],
+	"author": {
+		"name": "Tommy Montgomery",
+		"email": "[e-mail]",
+		"url": "http://tmont.com/"
+	},
 
@@ -16,7 +17,10 @@ "main": "./src/parser.js",
 
-    "repository": { "type": "git", "url": "git://github.com/tmont/html-parser.git" },
-    "devDependencies": {
-        "mocha": ">= 1.1.0",
-	    "should": ">= 0.6.3"
-    },
+	"repository": {
+		"type": "git",
+		"url": "git://github.com/tmont/html-parser.git"
+	},
+	"devDependencies": {
+		"moczha": ">= 1.1.0",
+		"should": ">= 0.6.3"
+	},
 
@@ -23,0 +27,0 @@ "scripts": {

src/parser.js

@@ -11,3 +11,3 @@ var parseContext = require('./context');
 		var attributeValueRegex = !quote
-			? /(.*?)[\s>]/
+			? /(.*?)(?=[\s>])/
 			: new RegExp(quote + '(.*?)' + quote);
@@ -220,2 +220,3 @@
 	var sanitized = '', tagStack = [];
+	var ignoring = false;
 	var callbacks = {
@@ -231,7 +232,10 @@ docType: function(value) {
 			name = name.toLowerCase();
+			tagStack.push({ name: name });
 			if (toRemove.elements.indexOf(name) !== -1) {
+				if (!ignoring) {
+					ignoring = tagStack[tagStack.length - 1];
+				}
 				return;
 			}
 			sanitized += '<' + name;
-			tagStack.push(name);
 		},
@@ -241,6 +245,2 @@
 			name = name.toLowerCase();
-			if (toRemove.elements.indexOf(name) !== -1) {
-				return;
-			}
-			sanitized += token;
 			if (token.length === 2) {
@@ -250,2 +250,6 @@ //self closing
 			}
+			if (ignoring || toRemove.elements.indexOf(name) !== -1) {
+				return;
+			}
+			sanitized += token;
 		},
@@ -255,12 +259,19 @@
 			name = name.toLowerCase();
-			if (toRemove.elements.indexOf(name) !== -1) {
+			if (tagStack.length && tagStack[tagStack.length - 1].name === name) {
+				var scope = tagStack.pop();
+				if (scope === ignoring) {
+					ignoring = null;
+				}
+			}
+			if (ignoring || toRemove.elements.indexOf(name) !== -1) {
 				return;
 			}
 			sanitized += '</' + name + '>';
-			if (tagStack.length && tagStack[tagStack.length - 1] === name) {
-				tagStack.pop();
-			}
 		},
 
 		attribute: function(name, value) {
+			if (ignoring) {
+				return;
+			}
+
 			name = name.toLowerCase();
@@ -275,2 +286,5 @@ if (toRemove.attributes.indexOf(name) !== -1) {
 		text: function(value) {
+			if (ignoring) {
+				return;
+			}
 			sanitized += value;
@@ -280,3 +294,3 @@ },
 		comment: function(value) {
-			if (toRemove.comments) {
+			if (ignoring || toRemove.comments) {
 				return;
@@ -288,8 +302,14 @@ }
 		cdata: function(value) {
-			if (tagStack.indexOf('script') !== -1 || tagStack.indexOf('xmp') !== -1) {
-				sanitized += value;
+			if (ignoring) {
+				return;
 			}
-			else {
-				sanitized += '<![CDATA[' + value + ']]>';
+
+			for (var i = tagStack.length - 1; i >= 0; i--) {
+				if (tagStack[i].name === 'script' || tagStack[i].name === 'xmp') {
+					sanitized += value;
+					return;
+				}
 			}
+
+			sanitized += '<![CDATA[' + value + ']]>';
 		}
@@ -296,0 +316,0 @@ };

tests/sanitization-tests.js

@@ -37,3 +37,4 @@ var should = require('should');
 	it('should remove specified elements', function() {
-		var sanitized = helpers.parser.sanitize('<foo><bar><baz><bat></bat></baz></bar><bat></bat></foo>', {
+		var html = '<foo><bar><baz><bat foo=bar>asdf</bat></baz></bar><bat><!-- comment --></bat></foo>';
+		var sanitized = helpers.parser.sanitize(html, {
 			elements: [ 'bat' ]
@@ -40,0 +41,0 @@ });

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

59791

increased by0.78%

Number of package files

32

increased by3.23%

Lines of code

1110

increased by1.65%

Number of medium quality alerts

0

decreased by-100%

Number of lines in readme file

61

increased byInfinity%

No dependency changes