From 0f6b2ef9823953533dd98849fc29c08e6a05c4a4 Mon Sep 17 00:00:00 2001 From: Misko Hevery Date: Mon, 21 Nov 2011 14:09:52 -0800 Subject: refactor(sanitizer): turn sanitizer into a service --- angularFiles.js | 2 +- src/sanitizer.js | 285 ------------------------------------ src/service/sanitize.js | 381 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 382 insertions(+), 286 deletions(-) delete mode 100644 src/sanitizer.js create mode 100644 src/service/sanitize.js diff --git a/angularFiles.js b/angularFiles.js index 05f93bf8..1070299f 100644 --- a/angularFiles.js +++ b/angularFiles.js @@ -6,7 +6,6 @@ angularFiles = { 'src/JSON.js', 'src/Injector.js', 'src/Resource.js', - 'src/sanitizer.js', 'src/jqLite.js', 'src/apis.js', 'src/service/anchorScroll.js', @@ -34,6 +33,7 @@ angularFiles = { 'src/service/route.js', 'src/service/routeParams.js', 'src/service/scope.js', + 'src/service/sanitize.js', 'src/service/sniffer.js', 'src/service/window.js', 'src/service/http.js', diff --git a/src/sanitizer.js b/src/sanitizer.js deleted file mode 100644 index 207b1039..00000000 --- a/src/sanitizer.js +++ /dev/null @@ -1,285 +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) {} - * }); - * - */ - -// 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/service/sanitize.js b/src/service/sanitize.js new file mode 100644 index 00000000..0d5c74af --- /dev/null +++ b/src/service/sanitize.js @@ -0,0 +1,381 @@ +'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)); + } + } + }; +} -- cgit v1.2.3