clean-html - npm Package Compare versions

Comparing version 1.1.3 to 1.2.0

demo.js

@@ -6,3 +6,3 @@ var cleaner = require('./index.js'),
 if (!file) {
-    return process.stderr.write('no file specified\n');
+    throw 'no file specified\n';
 }
@@ -12,6 +12,8 @@
     if (err) {
-        return process.stderr.write(err);
+        throw err;
     }
 
-    process.stdout.write(cleaner.clean(data) + '\n');
+    cleaner.clean(data, function (html) {
+        console.log(html);
+    });
 });

index.js

@@ -1,2 +0,3 @@
-var options = {};
+var htmlparser = require('htmlparser2'),
+    options = {};
 
@@ -7,12 +8,16 @@ function setup(opt) {
             'align',
-            'valign',
             'bgcolor',
+            'border',
+            'cellpadding',
+            'cellspacing',
             'color',
-            'width',
+            'disabled',
             'height',
-            'border',
-            'cellpadding',
-            'cellspacing'
+            'target',
+            'valign',
+            'width'
         ],
         'block-tags': [
+            'blockquote',
+            'div',
             'h1',
@@ -24,12 +29,10 @@ 'h2',
             'h6',
-            'div',
+            'hr',
             'p',
             'table',
-            'tr',
             'td',
-            'blockquote',
-            'hr'
+            'tr'
         ],
+        'break-around-comments': true,
         'break-after-br': true,
-        'close-empty-tags': false,
         'empty-tags': [
@@ -40,8 +43,7 @@ 'br',
         ],
-        'fix-end-tags': true,
         'indent': '  ',
-        'pretty': true,
         'remove-comments': false,
         'remove-empty-paras': false,
         'tags-to-remove': [
+            'center',
             'font'
@@ -57,8 +59,6 @@ ]
     options['block-tags'] = opt['block-tags'] || options['block-tags'];
+    options['break-around-comments'] = opt['break-around-comments'] === false ? false : true;
     options['break-after-br'] = opt['break-after-br'] === false ? false : true;
-    options['close-empty-tags'] = opt['close-empty-tags'] === true ? true : false;
     options['empty-tags'] = opt['empty-tags'] || options['empty-tags'];
-    options['fix-end-tags'] = opt['fix-end-tags'] === false ? false : true;
     options['indent'] = opt['indent'] || options['indent'];
-    options['pretty'] = opt['pretty'] === false ? false : true;
     options['remove-comments'] = opt['remove-comments'] === true ? true : false;
@@ -85,105 +85,94 @@ options['remove-empty-paras'] = opt['remove-empty-paras'] === true ? true : false;
 
-function replaceWhiteSpace(html) {
-    return html.replace(/\s/g, ' ');
-}
+function isEmpty(node) {
+    if (node.type == 'text' || node.type == 'comment') {
+        return !node.data.trim();
+    }
 
-function removeExtraSpaces(html) {
-    return html.replace(/ {2,}/g, ' ');
+    return !node.children.length || node.children.every(isEmpty);
 }
 
-function closeEmptyTag(tag) {
-    return tag.replace(/ ?\/?>/, '/>');
+function renderText(node) {
+    return node.data.replace(/\s+/g, ' ');
 }
 
-function removeTrailingSlash(tag) {
-    return tag.replace(/ ?\/>/, '>');
-}
+function renderComment(node) {
+    if (options['remove-comments']) {
+        return '';
+    }
 
-function cleanAttributes(tag) {
-    return tag.replace(/ (\w+)=['"].+?['"]/g, function (attribute, attributeName) {
-        if (options['attr-to-remove'].indexOf(attributeName) > -1) {
-            return '';
-        }
+    if (options['break-around-comments']) {
+        return '\n' + '<!--' + node.data + '-->' + '\n';
+    }
 
-        return attribute;
-    });
+    return '<!--' + node.data + '-->';
 }
 
-function cleanTags(html) {
-    var openTags = [];
+function renderTag(node) {
+    if (options['remove-empty-paras'] && node.name == 'p' && isEmpty(node)) {
+        return '';
+    }
 
-    html = html.replace(/<\/?(\w+).*?>/g, function (tag, tagName) {
-        tag = tag.toLowerCase();
-        tagName = tagName.toLowerCase();
-
-        if (options['tags-to-remove'].indexOf(tagName) > -1) {
+    if (options['tags-to-remove'].indexOf(node.name) > -1) {
+        if (!node.children.length) {
             return '';
         }
 
-        if (options['empty-tags'].indexOf(tagName) > -1) {
-            if (options['close-empty-tags']) {
-                tag = closeEmptyTag(tag);
-            } else {
-                tag = removeTrailingSlash(tag);
-            }
+        return render(node.children);
+    }
 
-            return cleanAttributes(tag);
-        }
+    var openTag = '<' + node.name,
+        closeTag;
 
-        if (tag.indexOf('</') == -1) {
-            // open tag
-            openTags.unshift(tagName);
-
-            return cleanAttributes(tag);
+    for (var attrib in node.attribs) {
+        if (options['attr-to-remove'].indexOf(attrib) == -1) {
+            openTag += ' ' + attrib + '="' + node.attribs[attrib] + '"';
         }
+    }
 
-        if (openTags[0] == tagName) {
-            // close tag
-            openTags.shift();
+    openTag += '>';
 
-            return tag;
+    if (options['empty-tags'].indexOf(node.name) > -1) {
+        if (options['break-after-br'] && node.name == 'br') {
+            return openTag + '\n';
         }
 
-        var openTagIndex = openTags.indexOf(tagName);
+        return openTag;
+    }
 
-        if (openTagIndex > -1) {
-            // tags are out of order - close previous tags, then close this tag
-            return '</' + openTags.splice(0, openTagIndex + 1).join('></') + '>';
-        }
+    closeTag = '</' + node.name + '>';
 
-        // tag was never opened or was already closed - discard
-        return '';
-    });
+    if (options['block-tags'].indexOf(node.name) > -1) {
+        openTag = '\n' + openTag + '\n';
+        closeTag = '\n' + closeTag + '\n';
+    }
 
-    if (openTags.length) {
-        // append remaining tags
-        html += '</' + openTags.join('></') + '>';
+    if (!node.children.length) {
+        return openTag + closeTag;
     }
 
-    return html;
+    return openTag + render(node.children) + closeTag;
 }
 
-function removeComments(html) {
-    return html.replace(/<!--.*?-->/g, '');
-}
+function render(nodes) {
+    var html = '';
 
-function removeEmptyParagraphs(html) {
-    return html.replace(/<p( \w+=['"].+?['"])?>\s*<\/p>/g, '');
-}
+    nodes.forEach(function (node) {
+        if (node.type == 'root') {
+            html += render(node.children);
+            return;
+        }
 
-function addLineBreaks(html) {
-    return html.replace(/<\/?(\w+).*?>/g, function (tag, tagName) {
-        if (options['block-tags'].indexOf(tagName) > -1) {
-            return '\n' + tag + '\n';
+        if (node.type == 'text') {
+            html += renderText(node);
+            return;
         }
 
-        if (tagName == 'br' && options['break-after-br']) {
-            return tag + '\n';
+        if (node.type == 'comment') {
+            html += renderComment(node);
+            return;
         }
 
-        return tag;
+        html += renderTag(node);
     });
-}
 
-function removeBlankLines(html) {
     return html.replace(/\s{2,}/g, '\n');
@@ -231,24 +220,24 @@ }
 
-function clean(html, opt) {
+function clean(html, opt, callback) {
+    if (typeof opt == 'function') {
+        callback = opt;
+        opt = null;
+    }
+
     setup(opt);
 
-    html = replaceWhiteSpace(html);
-    html = removeExtraSpaces(html);
-    html = cleanTags(html);
+    var handler = new htmlparser.DomHandler(function (err, dom) {
+        if (err) {
+            throw err;
+        }
 
-    if (options['remove-comments']) {
-        html = removeComments(html);
-    }
+        var html = render(dom);
+        html = indent(html).trim();
 
-    if (options['remove-empty-paras']) {
-        html = removeEmptyParagraphs(html);
-    }
+        callback(html);
+    });
 
-    if (options['pretty']) {
-        html = addLineBreaks(html);
-        html = removeBlankLines(html);
-        html = indent(html);
-    }
-
-    return html.trim();
+    var parser = new htmlparser.Parser(handler);
+    parser.write(html);
+    parser.done();
 }
@@ -255,0 +244,0 @@

package.json

 {
   "name": "clean-html",
-  "version": "1.1.3",
+  "version": "1.2.0",
   "description": "HTML cleaner and beautifier",
   "main": "index.js",
-  "dependencies": {},
+  "dependencies": {
+    "htmlparser2": "3.8.2"
+  },
   "devDependencies": {},
@@ -8,0 +10,0 @@ "scripts": {

readme.md

@@ -38,3 +38,5 @@ ## HTML cleaner and beautifier
 fs.readFile(file, 'utf-8', function (err, data) {
-    process.stdout.write(cleaner.clean(data) + '\n');
+    cleaner.clean(data, function (html) {
+        console.log(html);
+    });
 });
@@ -66,28 +68,2 @@ ```
 
-If you like, you can even close the empty tags, lose the comments and get rid of that nasty presentational markup:
-
-```javascript
-var options = {
-    'close-empty-tags': true,
-    'remove-comments': true,
-    'add-tags-to-remove': ['table', 'tr', 'td', 'blockquote']
-};
-
-process.stdout.write(cleaner.clean(data, options) + '\n');
-```
-
-Voila!
-
-```html
-<b>Currently we have these articles available:</b>
-<p>
-  <a href="foo.html">The History of Foo</a><br/>
-  An <span>informative</span> piece of information.
-</p>
-<p>
-  <a href="bar.html">A Horse Walked Into a Bar</a><br/>
-  The bartender said "Why the long face?"
-</p>
-```
-
 ## Options
@@ -100,14 +76,14 @@
 Type: Array  
-Default: `['align', 'valign', 'bgcolor', 'color', 'width', 'height', 'border', 'cellpadding', 'cellspacing']`
+Default: `['align', 'bgcolor', 'border', 'cellpadding', 'cellspacing', 'color', 'disabled', 'height', 'target', 'valign', 'width']`
 
 ### block-tags
 
-Block level element tags. Line breaks are added before and after, and nested content is indented. Note: this option has no effect unless pretty is set to true.
+Block level element tags. Line breaks are added before and after, and nested content is indented.
 
 Type: Array  
-Default: `['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'div', 'p', 'table', 'tr', 'td', 'blockquote', 'hr']`
+Default: `['blockquote', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'p', 'table', 'td', 'tr']`
 
-### break-after-br
+### break-around-comments
 
-Adds line breaks after br tags. Note: this option has no effect unless pretty is set to true.
+Adds line breaks before and after comments.
 
@@ -117,8 +93,8 @@ Type: Boolean
 
-### close-empty-tags
+### break-after-br
 
-If set to true, adds trailing slashes to empty tags. Otherwise removes trailing slashes.
+Adds line breaks after br tags.
 
 Type: Boolean  
-Default: `false`
+Default: `true`
 
@@ -132,31 +108,5 @@ ### empty-tags
 
-### fix-end-tags
-
-Adds end tags where they are missing. For example, this:
-
-```html
-<blockquote>Now Scotch is a real drink for a man.
-```
-
-becomes this:
-
-```html
-<blockquote>Now Scotch is a real drink for a man.</blockquote>
-```
-
-Also fixes end tags that are closed in the wrong order.
-
-```html
-You <b>belong in the <i>circus</b></i>, Spock, not a starship.
-```
-
-becomes this:
-
-```html
-You <b>belong in the <i>circus</i></b>, Spock, not a starship.
-```
-
 ### indent
 
-The string to use for indentation. e.g., a tab character or one or more spaces. Note: this option has no effect unless pretty is set to true.
+The string to use for indentation. e.g., a tab character or one or more spaces.
 
@@ -166,9 +116,2 @@ Type: String
 
-### pretty
-
-Pretty prints the output by adding line breaks and indentation.
-
-Type: Boolean  
-Default: `true`
-
 ### remove-comments
@@ -193,3 +136,3 @@
 Type: Array  
-Default: `['font']`
+Default: `['center', 'font']`
 
@@ -196,0 +139,0 @@ ## Adding values to option lists

test.js

@@ -5,58 +5,77 @@ var assert = require('assert'),
 // test that text is unchanged
-assert.equal(cleaner.clean('Foo Bar'), 'Foo Bar');
+cleaner.clean('Foo Bar', function (html) {
+    assert.equal(html, 'Foo Bar');
+});
 
 // test that extra whitespace is removed
-assert.equal(cleaner.clean('Foo  Bar'), 'Foo Bar');
-assert.equal(cleaner.clean('Foo\nBar'), 'Foo Bar');
+cleaner.clean('Foo  Bar', function (html) {
+    assert.equal(html, 'Foo Bar');
+});
+cleaner.clean('Foo\nBar', function (html) {
+    assert.equal(html, 'Foo Bar');
+});
 
-// test that uppercase tags and attributes are lowercased
-assert.equal(cleaner.clean('<FOO BAR="QUX">Bam</FOO>'), '<foo bar="qux">Bam</foo>');
+// test that comments are removed
+cleaner.clean('<!-- foo -->', function (html) {
+    assert.equal(html, '<!-- foo -->');
+});
+cleaner.clean('<!-- foo -->', {'remove-comments': true}, function (html) {
+    assert.equal(html, '');
+});
 
+// test that lines breaks are added before and after comments
+cleaner.clean('foo<!-- bar -->qux', function (html) {
+    assert.equal(html, 'foo\n<!-- bar -->\nqux');
+});
+cleaner.clean('foo<!-- bar -->qux', {'break-around-comments': false}, function (html) {
+    assert.equal(html, 'foo<!-- bar -->qux');
+});
+
+// test that empty paragraph tags are removed
+cleaner.clean('<p>\n</p>', function (html) {
+    assert.equal(html, '<p>\n</p>');
+});
+cleaner.clean('<p>\n</p>', {'remove-empty-paras': true}, function (html) {
+    assert.equal(html, '');
+});
+
 // test that deprecated tags are removed
-assert.equal(cleaner.clean('foo <font="arial">bar</font>'), 'foo bar');
+cleaner.clean('<font face="arial">foo</font>', function (html) {
+    assert.equal(html, 'foo');
+});
 
-// test that trailing slash is removed from empty element tag
-assert.equal(cleaner.clean('<br />'), '<br>');
-assert.equal(cleaner.clean('<br/>'), '<br>');
-assert.equal(cleaner.clean('<br>'), '<br>');
-assert.equal(cleaner.clean('<br />', {'close-empty-tags': true}), '<br/>');
-assert.equal(cleaner.clean('<br/>', {'close-empty-tags': true}), '<br/>');
-assert.equal(cleaner.clean('<br>', {'close-empty-tags': true}), '<br/>');
-
 // test that legacy attributes are removed
-assert.equal(cleaner.clean('<foo color="red">bar</foo>'), '<foo>bar</foo>');
+cleaner.clean('<span color="red">foo</span>', function (html) {
+    assert.equal(html, '<span>foo</span>');
+});
 
-// test that missing end tags are added
-assert.equal(cleaner.clean('<quote>Now Scotch is a real drink for a man.'), '<quote>Now Scotch is a real drink for a man.</quote>');
+// test that line break is added after br tag
+cleaner.clean('foo<br>bar', function (html) {
+    assert.equal(html, 'foo<br>\nbar');
+});
+cleaner.clean('foo<br>bar', {'break-after-br': false}, function (html) {
+    assert.equal(html, 'foo<br>bar');
+});
 
-// test that end tags are closed in the right order
-assert.equal(cleaner.clean('You <b>belong in the <i>circus</b></i>, Spock, not a starship.'), 'You <b>belong in the <i>circus</i></b>, Spock, not a starship.');
-
-// test that comments are removed
-assert.equal(cleaner.clean('foo<!-- bar -->'), 'foo<!-- bar -->');
-assert.equal(cleaner.clean('foo<!-- bar -->', {'remove-comments': true}), 'foo');
-
-// test that empty paragraph tags are removed
-assert.equal(cleaner.clean('<p></p>', {'remove-empty-paras': true}), '');
-assert.equal(cleaner.clean('<p>\n</p>', {'remove-empty-paras': true}), '');
-assert.equal(cleaner.clean('<p foo="bar"></p>', {'remove-empty-paras': true}), '');
-
 // test that line breaks are added before and after block element tags
-assert.equal(cleaner.clean('foo<div></div>foo'), 'foo\n<div>\n</div>\nfoo');
-assert.equal(cleaner.clean('foo<div></div>foo', {'pretty': false}), 'foo<div></div>foo');
+cleaner.clean('foo<div></div>bar', function (html) {
+    assert.equal(html, 'foo\n<div>\n</div>\nbar');
+});
 
-// test that line break is added after br element tag
-assert.equal(cleaner.clean('foo<br>foo'), 'foo<br>\nfoo');
-assert.equal(cleaner.clean('foo<br>foo', {'break-after-br': false}), 'foo<br>foo');
-assert.equal(cleaner.clean('foo<br>foo', {'pretty': false}), 'foo<br>foo');
-
 // test that nested tags are indented after block element tags
-assert.equal(cleaner.clean('<div>bar</div>'), '<div>\n  bar\n</div>');
-assert.equal(cleaner.clean('<div><div>bar</div></div>'), '<div>\n  <div>\n    bar\n  </div>\n</div>');
-assert.equal(cleaner.clean('<div>bar</div>', {'indent': '	'}), '<div>\n	bar\n</div>');
-assert.equal(cleaner.clean('<div>bar</div>', {'pretty': false}), '<div>bar</div>');
+cleaner.clean('<div>foo</div>', function (html) {
+    assert.equal(html, '<div>\n  foo\n</div>');
+});
+cleaner.clean('<div><div>foo</div></div>', function (html) {
+    assert.equal(html, '<div>\n  <div>\n    foo\n  </div>\n</div>');
+});
+cleaner.clean('<div>foo</div>', {'indent': '	'}, function (html) {
+    assert.equal(html, '<div>\n	foo\n</div>');
+});
 
 // test that output is trimmed
-assert.equal(cleaner.clean(' Foo\n'), 'Foo');
+cleaner.clean(' foo\n', function (html) {
+    assert.equal(html, 'foo');
+});
 
-process.stdout.write('all tests passed\n');
+console.log('all tests passed');

New alerts

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Number of package files

6

increased by20%

Lines of code

275

increased by5.77%

Worsened metrics

Total package byte prevSize

12478

decreased by-16.09%

Dependency count

1

increased byInfinity%

Number of lines in readme file

163

decreased by-25.91%

Number of medium supply chain risk alerts

1

increased byInfinity%

Dependency changes

• + Addedhtmlparser2@3.8.2

• + Addedcore-util-is@1.0.3(transitive)

• + Addeddom-serializer@0.2.2(transitive)

• + Addeddomelementtype@1.3.12.3.0(transitive)

• + Addeddomhandler@2.3.0(transitive)

• + Addeddomutils@1.5.1(transitive)

• + Addedentities@1.0.02.2.0(transitive)

• + Addedhtmlparser2@3.8.2(transitive)

• + Addedinherits@2.0.4(transitive)

• + Addedisarray@0.0.1(transitive)

• + Addedreadable-stream@1.1.14(transitive)

• + Addedstring_decoder@0.10.31(transitive)