From 5bcd7198664dca2bf85ddf8b3a89f417cd4e4796 Mon Sep 17 00:00:00 2001 From: Vojta Jina Date: Tue, 10 Apr 2012 16:50:31 -0700 Subject: chore(ngSanitize): extract $sanitize, ngBindHtml, linkyFilter into a module Create build for other modules as well (ngResource, ngCookies): - wrap into a function - add license - add version Breaks `$sanitize` service, `ngBindHtml` directive and `linky` filter were moved to the `ngSanitize` module. Apps that depend on any of these will need to load `angular-sanitize.js` and include `ngSanitize` in their dependency list: `var myApp = angular.module('myApp', ['ngSanitize']);` --- src/AngularPublic.js | 2 - src/module.prefix | 6 + src/module.suffix | 2 + src/ng/directive/ngBind.js | 73 +++--- src/ng/filter.js | 1 - src/ng/filter/filters.js | 107 --------- src/ng/sanitize.js | 381 ------------------------------- src/ngSanitize/directive/ngBindHtml.js | 26 +++ src/ngSanitize/filter/linky.js | 106 +++++++++ src/ngSanitize/sanitize.js | 395 +++++++++++++++++++++++++++++++++ 10 files changed, 560 insertions(+), 539 deletions(-) create mode 100644 src/module.prefix create mode 100644 src/module.suffix delete mode 100644 src/ng/sanitize.js create mode 100644 src/ngSanitize/directive/ngBindHtml.js create mode 100644 src/ngSanitize/filter/linky.js create mode 100644 src/ngSanitize/sanitize.js (limited to 'src') diff --git a/src/AngularPublic.js b/src/AngularPublic.js index 352e14a8..834fd04a 100644 --- a/src/AngularPublic.js +++ b/src/AngularPublic.js @@ -71,7 +71,6 @@ function publishExternalAPI(angular){ style: styleDirective, option: optionDirective, ngBind: ngBindDirective, - ngBindHtml: ngBindHtmlDirective, ngBindHtmlUnsafe: ngBindHtmlUnsafeDirective, ngBindTemplate: ngBindTemplateDirective, ngClass: ngClassDirective, @@ -123,7 +122,6 @@ function publishExternalAPI(angular){ $routeParams: $RouteParamsProvider, $rootScope: $RootScopeProvider, $q: $QProvider, - $sanitize: $SanitizeProvider, $sniffer: $SnifferProvider, $templateCache: $TemplateCacheProvider, $window: $WindowProvider diff --git a/src/module.prefix b/src/module.prefix new file mode 100644 index 00000000..92367961 --- /dev/null +++ b/src/module.prefix @@ -0,0 +1,6 @@ +/** + * @license AngularJS v"NG_VERSION_FULL" + * (c) 2010-2012 AngularJS http://angularjs.org + * License: MIT + */ +(function(angular) { diff --git a/src/module.suffix b/src/module.suffix new file mode 100644 index 00000000..4c04d073 --- /dev/null +++ b/src/module.suffix @@ -0,0 +1,2 @@ + +})(window.angular); diff --git a/src/ng/directive/ngBind.js b/src/ng/directive/ngBind.js index 4f6d49aa..82402ae8 100644 --- a/src/ng/directive/ngBind.js +++ b/src/ng/directive/ngBind.js @@ -55,54 +55,6 @@ var ngBindDirective = ngDirective(function(scope, element, attr) { }); -/** - * @ngdoc directive - * @name angular.module.ng.$compileProvider.directive.ngBindHtmlUnsafe - * - * @description - * Creates a binding that will innerHTML the result of evaluating the `expression` into the current - * element. *The innerHTML-ed content will not be sanitized!* You should use this directive only if - * {@link angular.module.ng.$compileProvider.directive.ngBindHtml ngBindHtml} directive is too - * restrictive and when you absolutely trust the source of the content you are binding to. - * - * See {@link angular.module.ng.$sanitize $sanitize} docs for examples. - * - * @element ANY - * @param {expression} ngBindHtmlUnsafe {@link guide/dev_guide.expressions Expression} to evaluate. - */ -var ngBindHtmlUnsafeDirective = ngDirective(function(scope, element, attr) { - element.addClass('ng-binding').data('$binding', attr.ngBindHtmlUnsafe); - scope.$watch(attr.ngBindHtmlUnsafe, function(value) { - element.html(value || ''); - }); -}); - - -/** - * @ngdoc directive - * @name angular.module.ng.$compileProvider.directive.ngBindHtml - * - * @description - * Creates a binding that will sanitize the result of evaluating the `expression` with the - * {@link angular.module.ng.$sanitize $sanitize} service and innerHTML the result into the current - * element. - * - * See {@link angular.module.ng.$sanitize $sanitize} docs for examples. - * - * @element ANY - * @param {expression} ngBindHtml {@link guide/dev_guide.expressions Expression} to evaluate. - */ -var ngBindHtmlDirective = ['$sanitize', function($sanitize) { - return function(scope, element, attr) { - element.addClass('ng-binding').data('$binding', attr.ngBindHtml); - scope.$watch(attr.ngBindHtml, function(value) { - value = $sanitize(value); - element.html(value || ''); - }); - } -}]; - - /** * @ngdoc directive * @name angular.module.ng.$compileProvider.directive.ngBindTemplate @@ -160,3 +112,28 @@ var ngBindTemplateDirective = ['$interpolate', function($interpolate) { }); } }]; + + +/** + * @ngdoc directive + * @name angular.module.ng.$compileProvider.directive.ngBindHtmlUnsafe + * + * @description + * Creates a binding that will innerHTML the result of evaluating the `expression` into the current + * element. *The innerHTML-ed content will not be sanitized!* You should use this directive only if + * {@link angular.module.ng.$compileProvider.directive.ngBindHtml ngBindHtml} directive is too + * restrictive and when you absolutely trust the source of the content you are binding to. + * + * See {@link angular.module.ng.$sanitize $sanitize} docs for examples. + * + * @element ANY + * @param {expression} ngBindHtmlUnsafe {@link guide/dev_guide.expressions Expression} to evaluate. + */ +var ngBindHtmlUnsafeDirective = [function() { + return function(scope, element, attr) { + element.addClass('ng-binding').data('$binding', attr.ngBindHtmlUnsafe); + scope.$watch(attr.ngBindHtmlUnsafe, function(value) { + element.html(value || ''); + }); + }; +}]; diff --git a/src/ng/filter.js b/src/ng/filter.js index 4ed3f620..24ba248c 100644 --- a/src/ng/filter.js +++ b/src/ng/filter.js @@ -96,7 +96,6 @@ function $FilterProvider($provide) { register('filter', filterFilter); register('json', jsonFilter); register('limitTo', limitToFilter); - register('linky', linkyFilter); register('lowercase', lowercaseFilter); register('number', numberFilter); register('orderBy', orderByFilter); diff --git a/src/ng/filter/filters.js b/src/ng/filter/filters.js index faea82d4..841a0eaa 100644 --- a/src/ng/filter/filters.js +++ b/src/ng/filter/filters.js @@ -439,110 +439,3 @@ var lowercaseFilter = valueFn(lowercase); * @see angular.uppercase */ var uppercaseFilter = valueFn(uppercase); - - -/** - * @ngdoc filter - * @name angular.module.ng.$filter.linky - * @function - * - * @description - * Finds links in text input and turns them into html links. Supports http/https/ftp/mailto and - * plain email address links. - * - * @param {string} text Input text. - * @returns {string} Html-linkified text. - * - * @example - - - -
- Snippet: - - - - - - - - - - - - - - - - -
FilterSourceRendered
linky filter - 
<div ng-bind-html="snippet | linky">
</div>
- 		-
-
no filter
<div ng-bind="snippet">
</div>
- - - it('should linkify the snippet with urls', function() { - expect(using('#linky-filter').binding('snippet | linky')). - toBe('Pretty text with some links: ' + - 'http://angularjs.org/, ' + - 'us@somewhere.org, ' + - 'another@somewhere.org, ' + - 'and one more: ftp://127.0.0.1/.'); - }); - - it ('should not linkify snippet without the linky filter', function() { - expect(using('#escaped-html').binding('snippet')). - toBe("Pretty text with some links:\n" + - "http://angularjs.org/,\n" + - "mailto:us@somewhere.org,\n" + - "another@somewhere.org,\n" + - "and one more: ftp://127.0.0.1/."); - }); - - it('should update', function() { - input('snippet').enter('new http://link.'); - expect(using('#linky-filter').binding('snippet | linky')). - toBe('new http://link.'); - expect(using('#escaped-html').binding('snippet')).toBe('new http://link.'); - }); - - - */ -function linkyFilter() { - var LINKY_URL_REGEXP = /((ftp|https?):\/\/|(mailto:)?[A-Za-z0-9._%+-]+@)\S*[^\s\.\;\,\(\)\{\}\<\>]/, - MAILTO_REGEXP = /^mailto:/; - - return function(text) { - if (!text) return text; - var match; - var raw = text; - var html = []; - var writer = htmlSanitizeWriter(html); - var url; - var i; - while ((match = raw.match(LINKY_URL_REGEXP))) { - // We can not end in these as they are sometimes found at the end of the sentence - url = match[0]; - // if we did not match ftp/http/mailto then assume mailto - if (match[2] == match[3]) url = 'mailto:' + url; - i = match.index; - writer.chars(raw.substr(0, i)); - writer.start('a', {href:url}); - writer.chars(match[0].replace(MAILTO_REGEXP, '')); - writer.end('a'); - raw = raw.substring(i + match[0].length); - } - writer.chars(raw); - return html.join(''); - }; -} diff --git a/src/ng/sanitize.js b/src/ng/sanitize.js deleted file mode 100644 index 6a7a2be4..00000000 --- a/src/ng/sanitize.js +++ /dev/null @@ -1,381 +0,0 @@ -'use strict'; - -/* - * HTML Parser By Misko Hevery (misko@hevery.com) - * based on: HTML Parser By John Resig (ejohn.org) - * Original code by Erik Arvidsson, Mozilla Public License - * http://erik.eae.net/simplehtmlparser/simplehtmlparser.js - * - * // Use like so: - * htmlParser(htmlString, { - * start: function(tag, attrs, unary) {}, - * end: function(tag) {}, - * chars: function(text) {}, - * comment: function(text) {} - * }); - * - */ - - - -/** - * @ngdoc service - * @name angular.module.ng.$sanitize - * @function - * - * @description - * The input is sanitized by parsing the html into tokens. All safe tokens (from a whitelist) are - * then serialized back to properly escaped html string. This means that no unsafe input can make - * it into the returned string, however, since our parser is more strict than a typical browser - * parser, it's possible that some obscure input, which would be recognized as valid HTML by a - * browser, won't make it through the sanitizer. - * - * @param {string} html Html input. - * @returns {string} Sanitized html. - * - * @example - - - -
- Snippet: - - - - - - - - - - - - - - - - - - - - - -
FilterSourceRendered
html filter - 
<div ng-bind-html="snippet">
</div>
- 		-
-
no filter
<div ng-bind="snippet">
</div>
unsafe html filter
<div ng-bind-html-unsafe="snippet">
</div>
-
- - - it('should sanitize the html snippet ', function() { - expect(using('#html-filter').element('div').html()). - toBe('

an html\nclick here\nsnippet

'); - }); - - it('should escape snippet without any filter', function() { - expect(using('#escaped-html').element('div').html()). - toBe("<p style=\"color:blue\">an html\n" + - "<em onmouseover=\"this.textContent='PWN3D!'\">click here</em>\n" + - "snippet</p>"); - }); - - it('should inline raw snippet if filtered as unsafe', function() { - expect(using('#html-unsafe-filter').element("div").html()). - toBe("

an html\n" + - "click here\n" + - "snippet

"); - }); - - it('should update', function() { - input('snippet').enter('new text'); - expect(using('#html-filter').binding('snippet')).toBe('new text'); - expect(using('#escaped-html').element('div').html()).toBe("new <b>text</b>"); - expect(using('#html-unsafe-filter').binding("snippet")).toBe('new text'); - }); - - - */ - -function $SanitizeProvider() { - this.$get = valueFn(function(html) { - var buf = []; - htmlParser(html, htmlSanitizeWriter(buf)); - return buf.join(''); - }); -} - -// Regular Expressions for parsing tags and attributes -var START_TAG_REGEXP = /^<\s*([\w:-]+)((?:\s+[\w:-]+(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)\s*>/, - END_TAG_REGEXP = /^<\s*\/\s*([\w:-]+)[^>]*>/, - ATTR_REGEXP = /([\w:-]+)(?:\s*=\s*(?:(?:"((?:[^"])*)")|(?:'((?:[^'])*)')|([^>\s]+)))?/g, - BEGIN_TAG_REGEXP = /^/g, - CDATA_REGEXP = //g, - URI_REGEXP = /^((ftp|https?):\/\/|mailto:|#)/, - NON_ALPHANUMERIC_REGEXP = /([^\#-~| |!])/g; // Match everything outside of normal chars and " (quote character) - - -// Good source of info about elements and attributes -// http://dev.w3.org/html5/spec/Overview.html#semantics -// http://simon.html5.org/html-elements - -// Safe Void Elements - HTML5 -// http://dev.w3.org/html5/spec/Overview.html#void-elements -var voidElements = makeMap("area,br,col,hr,img,wbr"); - -// Elements that you can, intentionally, leave open (and which close themselves) -// http://dev.w3.org/html5/spec/Overview.html#optional-tags -var optionalEndTagBlockElements = makeMap("colgroup,dd,dt,li,p,tbody,td,tfoot,th,thead,tr"), - optionalEndTagInlineElements = makeMap("rp,rt"), - optionalEndTagElements = extend({}, optionalEndTagInlineElements, optionalEndTagBlockElements); - -// Safe Block Elements - HTML5 -var blockElements = extend({}, optionalEndTagBlockElements, makeMap("address,article,aside," + - "blockquote,caption,center,del,dir,div,dl,figure,figcaption,footer,h1,h2,h3,h4,h5,h6," + - "header,hgroup,hr,ins,map,menu,nav,ol,pre,script,section,table,ul")); - -// Inline Elements - HTML5 -var inlineElements = extend({}, optionalEndTagInlineElements, makeMap("a,abbr,acronym,b,bdi,bdo," + - "big,br,cite,code,del,dfn,em,font,i,img,ins,kbd,label,map,mark,q,ruby,rp,rt,s,samp,small," + - "span,strike,strong,sub,sup,time,tt,u,var")); - - -// Special Elements (can contain anything) -var specialElements = makeMap("script,style"); - -var validElements = extend({}, voidElements, blockElements, inlineElements, optionalEndTagElements); - -//Attributes that have href and hence need to be sanitized -var uriAttrs = makeMap("background,cite,href,longdesc,src,usemap"); -var validAttrs = extend({}, uriAttrs, makeMap( - 'abbr,align,alt,axis,bgcolor,border,cellpadding,cellspacing,class,clear,'+ - 'color,cols,colspan,compact,coords,dir,face,headers,height,hreflang,hspace,'+ - 'ismap,lang,language,nohref,nowrap,rel,rev,rows,rowspan,rules,'+ - 'scope,scrolling,shape,span,start,summary,target,title,type,'+ - 'valign,value,vspace,width')); - -/** - * @example - * htmlParser(htmlString, { - * start: function(tag, attrs, unary) {}, - * end: function(tag) {}, - * chars: function(text) {}, - * comment: function(text) {} - * }); - * - * @param {string} html string - * @param {object} handler - */ -function htmlParser( html, handler ) { - var index, chars, match, stack = [], last = html; - stack.last = function() { return stack[ stack.length - 1 ]; }; - - while ( html ) { - chars = true; - - // Make sure we're not in a script or style element - if ( !stack.last() || !specialElements[ stack.last() ] ) { - - // Comment - if ( html.indexOf(""); - - if ( index >= 0 ) { - if (handler.comment) handler.comment( html.substring( 4, index ) ); - html = html.substring( index + 3 ); - chars = false; - } - - // end tag - } else if ( BEGING_END_TAGE_REGEXP.test(html) ) { - match = html.match( END_TAG_REGEXP ); - - if ( match ) { - html = html.substring( match[0].length ); - match[0].replace( END_TAG_REGEXP, parseEndTag ); - chars = false; - } - - // start tag - } else if ( BEGIN_TAG_REGEXP.test(html) ) { - match = html.match( START_TAG_REGEXP ); - - if ( match ) { - html = html.substring( match[0].length ); - match[0].replace( START_TAG_REGEXP, parseStartTag ); - chars = false; - } - } - - if ( chars ) { - index = html.indexOf("<"); - - var text = index < 0 ? html : html.substring( 0, index ); - html = index < 0 ? "" : html.substring( index ); - - if (handler.chars) handler.chars( decodeEntities(text) ); - } - - } else { - html = html.replace(new RegExp("(.*)<\\s*\\/\\s*" + stack.last() + "[^>]*>", 'i'), function(all, text){ - text = text. - replace(COMMENT_REGEXP, "$1"). - replace(CDATA_REGEXP, "$1"); - - if (handler.chars) handler.chars( decodeEntities(text) ); - - return ""; - }); - - parseEndTag( "", stack.last() ); - } - - if ( html == last ) { - throw "Parse Error: " + html; - } - last = html; - } - - // Clean up any remaining tags - parseEndTag(); - - function parseStartTag( tag, tagName, rest, unary ) { - tagName = lowercase(tagName); - if ( blockElements[ tagName ] ) { - while ( stack.last() && inlineElements[ stack.last() ] ) { - parseEndTag( "", stack.last() ); - } - } - - if ( optionalEndTagElements[ tagName ] && stack.last() == tagName ) { - parseEndTag( "", tagName ); - } - - unary = voidElements[ tagName ] || !!unary; - - if ( !unary ) - stack.push( tagName ); - - var attrs = {}; - - rest.replace(ATTR_REGEXP, function(match, name, doubleQuotedValue, singleQoutedValue, unqoutedValue) { - var value = doubleQuotedValue - || singleQoutedValue - || unqoutedValue - || ''; - - attrs[name] = decodeEntities(value); - }); - if (handler.start) handler.start( tagName, attrs, unary ); - } - - function parseEndTag( tag, tagName ) { - var pos = 0, i; - tagName = lowercase(tagName); - if ( tagName ) - // Find the closest opened tag of the same type - for ( pos = stack.length - 1; pos >= 0; pos-- ) - if ( stack[ pos ] == tagName ) - break; - - if ( pos >= 0 ) { - // Close all the open elements, up the stack - for ( i = stack.length - 1; i >= pos; i-- ) - if (handler.end) handler.end( stack[ i ] ); - - // Remove the open elements from the stack - stack.length = pos; - } - } -} - -/** - * decodes all entities into regular string - * @param value - * @returns {string} A string with decoded entities. - */ -var hiddenPre=document.createElement("pre"); -function decodeEntities(value) { - hiddenPre.innerHTML=value.replace(//g, '>'); -} - -/** - * create an HTML/XML writer which writes to buffer - * @param {Array} buf use buf.jain('') to get out sanitized html string - * @returns {object} in the form of { - * start: function(tag, attrs, unary) {}, - * end: function(tag) {}, - * chars: function(text) {}, - * comment: function(text) {} - * } - */ -function htmlSanitizeWriter(buf){ - var ignore = false; - var out = bind(buf, buf.push); - return { - start: function(tag, attrs, unary){ - tag = lowercase(tag); - if (!ignore && specialElements[tag]) { - ignore = tag; - } - if (!ignore && validElements[tag] == true) { - out('<'); - out(tag); - forEach(attrs, function(value, key){ - var lkey=lowercase(key); - if (validAttrs[lkey]==true && (uriAttrs[lkey]!==true || value.match(URI_REGEXP))) { - out(' '); - out(key); - out('="'); - out(encodeEntities(value)); - out('"'); - } - }); - out(unary ? '/>' : '>'); - } - }, - end: function(tag){ - tag = lowercase(tag); - if (!ignore && validElements[tag] == true) { - out(''); - } - if (tag == ignore) { - ignore = false; - } - }, - chars: function(chars){ - if (!ignore) { - out(encodeEntities(chars)); - } - } - }; -} diff --git a/src/ngSanitize/directive/ngBindHtml.js b/src/ngSanitize/directive/ngBindHtml.js new file mode 100644 index 00000000..f8ccef18 --- /dev/null +++ b/src/ngSanitize/directive/ngBindHtml.js @@ -0,0 +1,26 @@ + + + +/** + * @ngdoc directive + * @name angular.module.ngSanitize.directive.ngBindHtml + * + * @description + * Creates a binding that will sanitize the result of evaluating the `expression` with the + * {@link angular.module.ng.$sanitize $sanitize} service and innerHTML the result into the current + * element. + * + * See {@link angular.module.ng.$sanitize $sanitize} docs for examples. + * + * @element ANY + * @param {expression} ngBindHtml {@link guide/dev_guide.expressions Expression} to evaluate. + */ +angular.module('ngSanitize').directive('ngBindHtml', ['$sanitize', function($sanitize) { + return function(scope, element, attr) { + element.addClass('ng-binding').data('$binding', attr.ngBindHtml); + scope.$watch(attr.ngBindHtml, function(value) { + value = $sanitize(value); + element.html(value || ''); + }); + }; +}]); diff --git a/src/ngSanitize/filter/linky.js b/src/ngSanitize/filter/linky.js new file mode 100644 index 00000000..c30665a2 --- /dev/null +++ b/src/ngSanitize/filter/linky.js @@ -0,0 +1,106 @@ +/** + * @ngdoc filter + * @name angular.module.ngSanitize.filter.linky + * @function + * + * @description + * Finds links in text input and turns them into html links. Supports http/https/ftp/mailto and + * plain email address links. + * + * @param {string} text Input text. + * @returns {string} Html-linkified text. + * + * @example + + + +
+ Snippet: + + + + + + + + + + + + + + + + +
FilterSourceRendered
linky filter + 
<div ng-bind-html="snippet | linky">
</div>
+ 		+
+
no filter
<div ng-bind="snippet">
</div>
+ + + it('should linkify the snippet with urls', function() { + expect(using('#linky-filter').binding('snippet | linky')). + toBe('Pretty text with some links: ' + + 'http://angularjs.org/, ' + + 'us@somewhere.org, ' + + 'another@somewhere.org, ' + + 'and one more: ftp://127.0.0.1/.'); + }); + + it ('should not linkify snippet without the linky filter', function() { + expect(using('#escaped-html').binding('snippet')). + toBe("Pretty text with some links:\n" + + "http://angularjs.org/,\n" + + "mailto:us@somewhere.org,\n" + + "another@somewhere.org,\n" + + "and one more: ftp://127.0.0.1/."); + }); + + it('should update', function() { + input('snippet').enter('new http://link.'); + expect(using('#linky-filter').binding('snippet | linky')). + toBe('new http://link.'); + expect(using('#escaped-html').binding('snippet')).toBe('new http://link.'); + }); + + + */ +angular.module('ngSanitize').filter('linky', function() { + var LINKY_URL_REGEXP = /((ftp|https?):\/\/|(mailto:)?[A-Za-z0-9._%+-]+@)\S*[^\s\.\;\,\(\)\{\}\<\>]/, + MAILTO_REGEXP = /^mailto:/; + + return function(text) { + if (!text) return text; + var match; + var raw = text; + var html = []; + // TODO(vojta): use $sanitize instead + var writer = htmlSanitizeWriter(html); + var url; + var i; + while ((match = raw.match(LINKY_URL_REGEXP))) { + // We can not end in these as they are sometimes found at the end of the sentence + url = match[0]; + // if we did not match ftp/http/mailto then assume mailto + if (match[2] == match[3]) url = 'mailto:' + url; + i = match.index; + writer.chars(raw.substr(0, i)); + writer.start('a', {href:url}); + writer.chars(match[0].replace(MAILTO_REGEXP, '')); + writer.end('a'); + raw = raw.substring(i + match[0].length); + } + writer.chars(raw); + return html.join(''); + }; +}); diff --git a/src/ngSanitize/sanitize.js b/src/ngSanitize/sanitize.js new file mode 100644 index 00000000..c8d28315 --- /dev/null +++ b/src/ngSanitize/sanitize.js @@ -0,0 +1,395 @@ +'use strict'; + +/** + * @ngdoc overview + * @name angular.module.ngSanitize + * @description + */ + +/* + * HTML Parser By Misko Hevery (misko@hevery.com) + * based on: HTML Parser By John Resig (ejohn.org) + * Original code by Erik Arvidsson, Mozilla Public License + * http://erik.eae.net/simplehtmlparser/simplehtmlparser.js + * + * // Use like so: + * htmlParser(htmlString, { + * start: function(tag, attrs, unary) {}, + * end: function(tag) {}, + * chars: function(text) {}, + * comment: function(text) {} + * }); + * + */ + + +/** + * @ngdoc service + * @name angular.module.ngSanitize.$sanitize + * @function + * + * @description + * The input is sanitized by parsing the html into tokens. All safe tokens (from a whitelist) are + * then serialized back to properly escaped html string. This means that no unsafe input can make + * it into the returned string, however, since our parser is more strict than a typical browser + * parser, it's possible that some obscure input, which would be recognized as valid HTML by a + * browser, won't make it through the sanitizer. + * + * @param {string} html Html input. + * @returns {string} Sanitized html. + * + * @example + + + +
+ Snippet: + + + + + + + + + + + + + + + + + + + + + +
FilterSourceRendered
html filter + 
<div ng-bind-html="snippet">
</div>
+ 		+
+
no filter
<div ng-bind="snippet">
</div>
unsafe html filter
<div ng-bind-html-unsafe="snippet">
</div>
+
+ + + it('should sanitize the html snippet ', function() { + expect(using('#html-filter').element('div').html()). + toBe('

an html\nclick here\nsnippet

'); + }); + + it('should escape snippet without any filter', function() { + expect(using('#escaped-html').element('div').html()). + toBe("<p style=\"color:blue\">an html\n" + + "<em onmouseover=\"this.textContent='PWN3D!'\">click here</em>\n" + + "snippet</p>"); + }); + + it('should inline raw snippet if filtered as unsafe', function() { + expect(using('#html-unsafe-filter').element("div").html()). + toBe("

an html\n" + + "click here\n" + + "snippet

"); + }); + + it('should update', function() { + input('snippet').enter('new text'); + expect(using('#html-filter').binding('snippet')).toBe('new text'); + expect(using('#escaped-html').element('div').html()).toBe("new <b>text</b>"); + expect(using('#html-unsafe-filter').binding("snippet")).toBe('new text'); + }); + + + */ +var $sanitize = function(html) { + var buf = []; + htmlParser(html, htmlSanitizeWriter(buf)); + return buf.join(''); +}; + + +// Regular Expressions for parsing tags and attributes +var START_TAG_REGEXP = /^<\s*([\w:-]+)((?:\s+[\w:-]+(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)\s*>/, + END_TAG_REGEXP = /^<\s*\/\s*([\w:-]+)[^>]*>/, + ATTR_REGEXP = /([\w:-]+)(?:\s*=\s*(?:(?:"((?:[^"])*)")|(?:'((?:[^'])*)')|([^>\s]+)))?/g, + BEGIN_TAG_REGEXP = /^/g, + CDATA_REGEXP = //g, + URI_REGEXP = /^((ftp|https?):\/\/|mailto:|#)/, + NON_ALPHANUMERIC_REGEXP = /([^\#-~| |!])/g; // Match everything outside of normal chars and " (quote character) + + +// Good source of info about elements and attributes +// http://dev.w3.org/html5/spec/Overview.html#semantics +// http://simon.html5.org/html-elements + +// Safe Void Elements - HTML5 +// http://dev.w3.org/html5/spec/Overview.html#void-elements +var voidElements = makeMap("area,br,col,hr,img,wbr"); + +// Elements that you can, intentionally, leave open (and which close themselves) +// http://dev.w3.org/html5/spec/Overview.html#optional-tags +var optionalEndTagBlockElements = makeMap("colgroup,dd,dt,li,p,tbody,td,tfoot,th,thead,tr"), + optionalEndTagInlineElements = makeMap("rp,rt"), + optionalEndTagElements = angular.extend({}, optionalEndTagInlineElements, optionalEndTagBlockElements); + +// Safe Block Elements - HTML5 +var blockElements = angular.extend({}, optionalEndTagBlockElements, makeMap("address,article,aside," + + "blockquote,caption,center,del,dir,div,dl,figure,figcaption,footer,h1,h2,h3,h4,h5,h6," + + "header,hgroup,hr,ins,map,menu,nav,ol,pre,script,section,table,ul")); + +// Inline Elements - HTML5 +var inlineElements = angular.extend({}, optionalEndTagInlineElements, makeMap("a,abbr,acronym,b,bdi,bdo," + + "big,br,cite,code,del,dfn,em,font,i,img,ins,kbd,label,map,mark,q,ruby,rp,rt,s,samp,small," + + "span,strike,strong,sub,sup,time,tt,u,var")); + + +// Special Elements (can contain anything) +var specialElements = makeMap("script,style"); + +var validElements = angular.extend({}, voidElements, blockElements, inlineElements, optionalEndTagElements); + +//Attributes that have href and hence need to be sanitized +var uriAttrs = makeMap("background,cite,href,longdesc,src,usemap"); +var validAttrs = angular.extend({}, uriAttrs, makeMap( + 'abbr,align,alt,axis,bgcolor,border,cellpadding,cellspacing,class,clear,'+ + 'color,cols,colspan,compact,coords,dir,face,headers,height,hreflang,hspace,'+ + 'ismap,lang,language,nohref,nowrap,rel,rev,rows,rowspan,rules,'+ + 'scope,scrolling,shape,span,start,summary,target,title,type,'+ + 'valign,value,vspace,width')); + +function makeMap(str) { + var obj = {}, items = str.split(','), i; + for (i = 0; i < items.length; i++) obj[items[i]] = true; + return obj; +} + + +/** + * @example + * htmlParser(htmlString, { + * start: function(tag, attrs, unary) {}, + * end: function(tag) {}, + * chars: function(text) {}, + * comment: function(text) {} + * }); + * + * @param {string} html string + * @param {object} handler + */ +function htmlParser( html, handler ) { + var index, chars, match, stack = [], last = html; + stack.last = function() { return stack[ stack.length - 1 ]; }; + + while ( html ) { + chars = true; + + // Make sure we're not in a script or style element + if ( !stack.last() || !specialElements[ stack.last() ] ) { + + // Comment + if ( html.indexOf(""); + + if ( index >= 0 ) { + if (handler.comment) handler.comment( html.substring( 4, index ) ); + html = html.substring( index + 3 ); + chars = false; + } + + // end tag + } else if ( BEGING_END_TAGE_REGEXP.test(html) ) { + match = html.match( END_TAG_REGEXP ); + + if ( match ) { + html = html.substring( match[0].length ); + match[0].replace( END_TAG_REGEXP, parseEndTag ); + chars = false; + } + + // start tag + } else if ( BEGIN_TAG_REGEXP.test(html) ) { + match = html.match( START_TAG_REGEXP ); + + if ( match ) { + html = html.substring( match[0].length ); + match[0].replace( START_TAG_REGEXP, parseStartTag ); + chars = false; + } + } + + if ( chars ) { + index = html.indexOf("<"); + + var text = index < 0 ? html : html.substring( 0, index ); + html = index < 0 ? "" : html.substring( index ); + + if (handler.chars) handler.chars( decodeEntities(text) ); + } + + } else { + html = html.replace(new RegExp("(.*)<\\s*\\/\\s*" + stack.last() + "[^>]*>", 'i'), function(all, text){ + text = text. + replace(COMMENT_REGEXP, "$1"). + replace(CDATA_REGEXP, "$1"); + + if (handler.chars) handler.chars( decodeEntities(text) ); + + return ""; + }); + + parseEndTag( "", stack.last() ); + } + + if ( html == last ) { + throw "Parse Error: " + html; + } + last = html; + } + + // Clean up any remaining tags + parseEndTag(); + + function parseStartTag( tag, tagName, rest, unary ) { + tagName = angular.lowercase(tagName); + if ( blockElements[ tagName ] ) { + while ( stack.last() && inlineElements[ stack.last() ] ) { + parseEndTag( "", stack.last() ); + } + } + + if ( optionalEndTagElements[ tagName ] && stack.last() == tagName ) { + parseEndTag( "", tagName ); + } + + unary = voidElements[ tagName ] || !!unary; + + if ( !unary ) + stack.push( tagName ); + + var attrs = {}; + + rest.replace(ATTR_REGEXP, function(match, name, doubleQuotedValue, singleQoutedValue, unqoutedValue) { + var value = doubleQuotedValue + || singleQoutedValue + || unqoutedValue + || ''; + + attrs[name] = decodeEntities(value); + }); + if (handler.start) handler.start( tagName, attrs, unary ); + } + + function parseEndTag( tag, tagName ) { + var pos = 0, i; + tagName = angular.lowercase(tagName); + if ( tagName ) + // Find the closest opened tag of the same type + for ( pos = stack.length - 1; pos >= 0; pos-- ) + if ( stack[ pos ] == tagName ) + break; + + if ( pos >= 0 ) { + // Close all the open elements, up the stack + for ( i = stack.length - 1; i >= pos; i-- ) + if (handler.end) handler.end( stack[ i ] ); + + // Remove the open elements from the stack + stack.length = pos; + } + } +} + +/** + * decodes all entities into regular string + * @param value + * @returns {string} A string with decoded entities. + */ +var hiddenPre=document.createElement("pre"); +function decodeEntities(value) { + hiddenPre.innerHTML=value.replace(//g, '>'); +} + +/** + * create an HTML/XML writer which writes to buffer + * @param {Array} buf use buf.jain('') to get out sanitized html string + * @returns {object} in the form of { + * start: function(tag, attrs, unary) {}, + * end: function(tag) {}, + * chars: function(text) {}, + * comment: function(text) {} + * } + */ +function htmlSanitizeWriter(buf){ + var ignore = false; + var out = angular.bind(buf, buf.push); + return { + start: function(tag, attrs, unary){ + tag = angular.lowercase(tag); + if (!ignore && specialElements[tag]) { + ignore = tag; + } + if (!ignore && validElements[tag] == true) { + out('<'); + out(tag); + angular.forEach(attrs, function(value, key){ + var lkey=angular.lowercase(key); + if (validAttrs[lkey]==true && (uriAttrs[lkey]!==true || value.match(URI_REGEXP))) { + out(' '); + out(key); + out('="'); + out(encodeEntities(value)); + out('"'); + } + }); + out(unary ? '/>' : '>'); + } + }, + end: function(tag){ + tag = angular.lowercase(tag); + if (!ignore && validElements[tag] == true) { + out(''); + } + if (tag == ignore) { + ignore = false; + } + }, + chars: function(chars){ + if (!ignore) { + out(encodeEntities(chars)); + } + } + }; +} + + +// define ngSanitize module and register $sanitize service +angular.module('ngSanitize', []).value('$sanitize', $sanitize); -- cgit v1.2.3