autolinker - npm Package Compare versions

Comparing version 0.17.0 to 0.17.1

dist/Autolinker.min.js

 /*!
  * Autolinker.js
- * 0.17.0
+ * 0.17.1
  *
@@ -10,2 +10,2 @@ * Copyright(c) 2015 Gregory Jacobs <[e-mail]>
  */
-!function(a,b){"function"==typeof define&&define.amd?define([],function(){return a.Autolinker=b()}):"object"==typeof exports?module.exports=b():a.Autolinker=b()}(this,function(){var a=function(b){a.Util.assign(this,b);var c=this.hashtag;if(c!==!1&&"twitter"!==c&&"facebook"!==c)throw new Error("invalid `hashtag` cfg - see docs")};return a.prototype={constructor:a,urls:!0,email:!0,twitter:!0,phone:!0,hashtag:!1,newWindow:!0,stripPrefix:!0,truncate:void 0,className:"",htmlParser:void 0,matchParser:void 0,tagBuilder:void 0,link:function(a){for(var b=this.getHtmlParser(),c=b.parse(a),d=0,e=[],f=0,g=c.length;g>f;f++){var h=c[f],i=h.getType(),j=h.getText();if("element"===i)"a"===h.getTagName()&&(h.isClosing()?d=Math.max(d-1,0):d++),e.push(j);else if("entity"===i)e.push(j);else if(0===d){var k=this.linkifyStr(j);e.push(k)}else e.push(j)}return e.join("")},linkifyStr:function(a){return this.getMatchParser().replace(a,this.createMatchReturnVal,this)},createMatchReturnVal:function(b){var c;if(this.replaceFn&&(c=this.replaceFn.call(this,this,b)),"string"==typeof c)return c;if(c===!1)return b.getMatchedText();if(c instanceof a.HtmlTag)return c.toAnchorString();var d=this.getTagBuilder(),e=d.build(b);return e.toAnchorString()},getHtmlParser:function(){var b=this.htmlParser;return b||(b=this.htmlParser=new a.htmlParser.HtmlParser),b},getMatchParser:function(){var b=this.matchParser;return b||(b=this.matchParser=new a.matchParser.MatchParser({urls:this.urls,email:this.email,twitter:this.twitter,phone:this.phone,hashtag:this.hashtag,stripPrefix:this.stripPrefix})),b},getTagBuilder:function(){var b=this.tagBuilder;return b||(b=this.tagBuilder=new a.AnchorTagBuilder({newWindow:this.newWindow,truncate:this.truncate,className:this.className})),b}},a.link=function(b,c){var d=new a(c);return d.link(b)},a.match={},a.htmlParser={},a.matchParser={},a.Util={abstractMethod:function(){throw"abstract"},assign:function(a,b){for(var c in b)b.hasOwnProperty(c)&&(a[c]=b[c]);return a},extend:function(b,c){var d=b.prototype,e=function(){};e.prototype=d;var f;f=c.hasOwnProperty("constructor")?c.constructor:function(){d.constructor.apply(this,arguments)};var g=f.prototype=new e;return g.constructor=f,g.superclass=d,delete c.constructor,a.Util.assign(g,c),f},ellipsis:function(a,b,c){return a.length>b&&(c=null==c?"..":c,a=a.substring(0,b-c.length)+c),a},indexOf:function(a,b){if(Array.prototype.indexOf)return a.indexOf(b);for(var c=0,d=a.length;d>c;c++)if(a[c]===b)return c;return-1},splitAndCapture:function(a,b){if(!b.global)throw new Error("`splitRegex` must have the 'g' flag set");for(var c,d=[],e=0;c=b.exec(a);)d.push(a.substring(e,c.index)),d.push(c[0]),e=c.index+c[0].length;return d.push(a.substring(e)),d}},a.HtmlTag=a.Util.extend(Object,{whitespaceRegex:/\s+/,constructor:function(b){a.Util.assign(this,b),this.innerHtml=this.innerHtml||this.innerHTML},setTagName:function(a){return this.tagName=a,this},getTagName:function(){return this.tagName||""},setAttr:function(a,b){var c=this.getAttrs();return c[a]=b,this},getAttr:function(a){return this.getAttrs()[a]},setAttrs:function(b){var c=this.getAttrs();return a.Util.assign(c,b),this},getAttrs:function(){return this.attrs||(this.attrs={})},setClass:function(a){return this.setAttr("class",a)},addClass:function(b){for(var c,d=this.getClass(),e=this.whitespaceRegex,f=a.Util.indexOf,g=d?d.split(e):[],h=b.split(e);c=h.shift();)-1===f(g,c)&&g.push(c);return this.getAttrs()["class"]=g.join(" "),this},removeClass:function(b){for(var c,d=this.getClass(),e=this.whitespaceRegex,f=a.Util.indexOf,g=d?d.split(e):[],h=b.split(e);g.length&&(c=h.shift());){var i=f(g,c);-1!==i&&g.splice(i,1)}return this.getAttrs()["class"]=g.join(" "),this},getClass:function(){return this.getAttrs()["class"]||""},hasClass:function(a){return-1!==(" "+this.getClass()+" ").indexOf(" "+a+" ")},setInnerHtml:function(a){return this.innerHtml=a,this},getInnerHtml:function(){return this.innerHtml||""},toAnchorString:function(){var a=this.getTagName(),b=this.buildAttrsStr();return b=b?" "+b:"",["<",a,b,">",this.getInnerHtml(),"</",a,">"].join("")},buildAttrsStr:function(){if(!this.attrs)return"";var a=this.getAttrs(),b=[];for(var c in a)a.hasOwnProperty(c)&&b.push(c+'="'+a[c]+'"');return b.join(" ")}}),a.AnchorTagBuilder=a.Util.extend(Object,{constructor:function(b){a.Util.assign(this,b)},build:function(b){var c=new a.HtmlTag({tagName:"a",attrs:this.createAttrs(b.getType(),b.getAnchorHref()),innerHtml:this.processAnchorText(b.getAnchorText())});return c},createAttrs:function(a,b){var c={href:b},d=this.createCssClass(a);return d&&(c["class"]=d),this.newWindow&&(c.target="_blank"),c},createCssClass:function(a){var b=this.className;return b?b+" "+b+"-"+a:""},processAnchorText:function(a){return a=this.doTruncate(a)},doTruncate:function(b){return a.Util.ellipsis(b,this.truncate||Number.POSITIVE_INFINITY)}}),a.htmlParser.HtmlParser=a.Util.extend(Object,{htmlRegex:function(){var a=/[0-9a-zA-Z][0-9a-zA-Z:]*/,b=/[^\s\0"'>\/=\x01-\x1F\x7F]+/,c=/(?:"[^"]*?"|'[^']*?'|[^'"=<>`\s]+)/,d=b.source+"(?:\\s*=\\s*"+c.source+")?";return new RegExp(["(?:","<(!DOCTYPE)","(?:","\\s+","(?:",d,"|",c.source+")",")*",">",")","|","(?:","<(/)?","("+a.source+")","(?:","\\s+",d,")*","\\s*/?",">",")"].join(""),"gi")}(),htmlCharacterEntitiesRegex:/(&nbsp;|&#160;|&lt;|&#60;|&gt;|&#62;|&quot;|&#34;|&#39;)/gi,parse:function(a){for(var b,c,d=this.htmlRegex,e=0,f=[];null!==(b=d.exec(a));){var g=b[0],h=b[1]||b[3],i=!!b[2],j=a.substring(e,b.index);j&&(c=this.parseTextAndEntityNodes(j),f.push.apply(f,c)),f.push(this.createElementNode(g,h,i)),e=b.index+g.length}if(e<a.length){var k=a.substring(e);k&&(c=this.parseTextAndEntityNodes(k),f.push.apply(f,c))}return f},parseTextAndEntityNodes:function(b){for(var c=[],d=a.Util.splitAndCapture(b,this.htmlCharacterEntitiesRegex),e=0,f=d.length;f>e;e+=2){var g=d[e],h=d[e+1];g&&c.push(this.createTextNode(g)),h&&c.push(this.createEntityNode(h))}return c},createElementNode:function(b,c,d){return new a.htmlParser.ElementNode({text:b,tagName:c.toLowerCase(),closing:d})},createEntityNode:function(b){return new a.htmlParser.EntityNode({text:b})},createTextNode:function(b){return new a.htmlParser.TextNode({text:b})}}),a.htmlParser.HtmlNode=a.Util.extend(Object,{text:"",constructor:function(b){a.Util.assign(this,b)},getType:a.Util.abstractMethod,getText:function(){return this.text}}),a.htmlParser.ElementNode=a.Util.extend(a.htmlParser.HtmlNode,{tagName:"",closing:!1,getType:function(){return"element"},getTagName:function(){return this.tagName},isClosing:function(){return this.closing}}),a.htmlParser.EntityNode=a.Util.extend(a.htmlParser.HtmlNode,{getType:function(){return"entity"}}),a.htmlParser.TextNode=a.Util.extend(a.htmlParser.HtmlNode,{getType:function(){return"text"}}),a.matchParser.MatchParser=a.Util.extend(Object,{urls:!0,email:!0,twitter:!0,phone:!0,hashtag:!1,stripPrefix:!0,matcherRegex:function(){var a=/(^|[^\w])@(\w{1,15})/,b=/(^|[^\w])#(\w{1,15})/,c=/(?:[\-;:&=\+\$,\w\.]+@)/,d=/(?:\+?\d{1,3}[-\s.])?\(?\d{3}\)?[-\s.]?\d{3}[-\s.]\d{4}/,e=/(?:[A-Za-z][-.+A-Za-z0-9]+:(?![A-Za-z][-.+A-Za-z0-9]+:\/\/)(?!\d+\/?)(?:\/\/)?)/,f=/(?:www\.)/,g=/[A-Za-z0-9\.\-]*[A-Za-z0-9\-]/,h=/\.(?:international|construction|contractors|enterprises|photography|productions|foundation|immobilien|industries|management|properties|technology|christmas|community|directory|education|equipment|institute|marketing|solutions|vacations|bargains|boutique|builders|catering|cleaning|clothing|computer|democrat|diamonds|graphics|holdings|lighting|partners|plumbing|supplies|training|ventures|academy|careers|company|cruises|domains|exposed|flights|florist|gallery|guitars|holiday|kitchen|neustar|okinawa|recipes|rentals|reviews|shiksha|singles|support|systems|agency|berlin|camera|center|coffee|condos|dating|estate|events|expert|futbol|kaufen|luxury|maison|monash|museum|nagoya|photos|repair|report|social|supply|tattoo|tienda|travel|viajes|villas|vision|voting|voyage|actor|build|cards|cheap|codes|dance|email|glass|house|mango|ninja|parts|photo|shoes|solar|today|tokyo|tools|watch|works|aero|arpa|asia|best|bike|blue|buzz|camp|club|cool|coop|farm|fish|gift|guru|info|jobs|kiwi|kred|land|limo|link|menu|mobi|moda|name|pics|pink|post|qpon|rich|ruhr|sexy|tips|vote|voto|wang|wien|wiki|zone|bar|bid|biz|cab|cat|ceo|com|edu|gov|int|kim|mil|net|onl|org|pro|pub|red|tel|uno|wed|xxx|xyz|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)\b/,i=/[\-A-Za-z0-9+&@#\/%=~_()|'$*\[\]?!:,.;]*[\-A-Za-z0-9+&@#\/%=~_()|'$*\[\]]/;return new RegExp(["(",a.source,")","|","(",c.source,g.source,h.source,")","|","(","(?:","(",e.source,g.source,")","|","(?:","(.?//)?",f.source,g.source,")","|","(?:","(.?//)?",g.source,h.source,")",")","(?:"+i.source+")?",")","|","(",d.source,")","|","(",b.source,")"].join(""),"gi")}(),charBeforeProtocolRelMatchRegex:/^(.)?\/\//,constructor:function(b){a.Util.assign(this,b),this.matchValidator=new a.MatchValidator},replace:function(a,b,c){var d=this;return a.replace(this.matcherRegex,function(a,e,f,g,h,i,j,k,l,m,n,o,p){var q=d.processCandidateMatch(a,e,f,g,h,i,j,k,l,m,n,o,p);if(q){var r=b.call(c,q.match);return q.prefixStr+r+q.suffixStr}return a})},processCandidateMatch:function(b,c,d,e,f,g,h,i,j,k,l,m,n){var o,p=i||j,q="",r="";if(g&&!this.urls||f&&!this.email||k&&!this.phone||c&&!this.twitter||l&&!this.hashtag||!this.matchValidator.isValidMatch(g,h,p))return null;if(this.matchHasUnbalancedClosingParen(b)&&(b=b.substr(0,b.length-1),r=")"),f)o=new a.match.Email({matchedText:b,email:f});else if(c)d&&(q=d,b=b.slice(1)),o=new a.match.Twitter({matchedText:b,twitterHandle:e});else if(k){var s=b.replace(/\D/g,"");o=new a.match.Phone({matchedText:b,number:s})}else if(l)m&&(q=m,b=b.slice(1)),o=new a.match.Hashtag({matchedText:b,serviceName:this.hashtag,hashtag:n});else{if(p){var t=p.match(this.charBeforeProtocolRelMatchRegex)[1]||"";t&&(q=t,b=b.slice(1))}o=new a.match.Url({matchedText:b,url:b,protocolUrlMatch:!!h,protocolRelativeMatch:!!p,stripPrefix:this.stripPrefix})}return{prefixStr:q,suffixStr:r,match:o}},matchHasUnbalancedClosingParen:function(a){var b=a.charAt(a.length-1);if(")"===b){var c=a.match(/\(/g),d=a.match(/\)/g),e=c&&c.length||0,f=d&&d.length||0;if(f>e)return!0}return!1}}),a.MatchValidator=a.Util.extend(Object,{invalidProtocolRelMatchRegex:/^[\w]\/\//,hasFullProtocolRegex:/^[A-Za-z][-.+A-Za-z0-9]+:\/\//,uriSchemeRegex:/^[A-Za-z][-.+A-Za-z0-9]+:/,hasWordCharAfterProtocolRegex:/:[^\s]*?[A-Za-z]/,isValidMatch:function(a,b,c){return b&&!this.isValidUriScheme(b)||this.urlMatchDoesNotHaveProtocolOrDot(a,b)||this.urlMatchDoesNotHaveAtLeastOneWordChar(a,b)||this.isInvalidProtocolRelativeMatch(c)?!1:!0},isValidUriScheme:function(a){var b=a.match(this.uriSchemeRegex)[0].toLowerCase();return"javascript:"!==b&&"vbscript:"!==b},urlMatchDoesNotHaveProtocolOrDot:function(a,b){return!(!a||b&&this.hasFullProtocolRegex.test(b)||-1!==a.indexOf("."))},urlMatchDoesNotHaveAtLeastOneWordChar:function(a,b){return a&&b?!this.hasWordCharAfterProtocolRegex.test(a):!1},isInvalidProtocolRelativeMatch:function(a){return!!a&&this.invalidProtocolRelMatchRegex.test(a)}}),a.match.Match=a.Util.extend(Object,{constructor:function(b){a.Util.assign(this,b)},getType:a.Util.abstractMethod,getMatchedText:function(){return this.matchedText},getAnchorHref:a.Util.abstractMethod,getAnchorText:a.Util.abstractMethod}),a.match.Email=a.Util.extend(a.match.Match,{getType:function(){return"email"},getEmail:function(){return this.email},getAnchorHref:function(){return"mailto:"+this.email},getAnchorText:function(){return this.email}}),a.match.Hashtag=a.Util.extend(a.match.Match,{getType:function(){return"hashtag"},getHashtag:function(){return this.hashtag},getAnchorHref:function(){var a=this.serviceName,b=this.hashtag;switch(a){case"twitter":return"https://twitter.com/hashtag/"+b;case"facebook":return"https://www.facebook.com/hashtag/"+b;default:throw new Error("Unknown service name to point hashtag to: ",a)}},getAnchorText:function(){return"#"+this.hashtag}}),a.match.Phone=a.Util.extend(a.match.Match,{getType:function(){return"phone"},getNumber:function(){return this.number},getAnchorHref:function(){return"tel:"+this.number},getAnchorText:function(){return this.matchedText}}),a.match.Twitter=a.Util.extend(a.match.Match,{getType:function(){return"twitter"},getTwitterHandle:function(){return this.twitterHandle},getAnchorHref:function(){return"https://twitter.com/"+this.twitterHandle},getAnchorText:function(){return"@"+this.twitterHandle}}),a.match.Url=a.Util.extend(a.match.Match,{urlPrefixRegex:/^(https?:\/\/)?(www\.)?/i,protocolRelativeRegex:/^\/\//,protocolPrepended:!1,getType:function(){return"url"},getUrl:function(){var a=this.url;return this.protocolRelativeMatch||this.protocolUrlMatch||this.protocolPrepended||(a=this.url="http://"+a,this.protocolPrepended=!0),a},getAnchorHref:function(){var a=this.getUrl();return a.replace(/&amp;/g,"&")},getAnchorText:function(){var a=this.getUrl();return this.protocolRelativeMatch&&(a=this.stripProtocolRelativePrefix(a)),this.stripPrefix&&(a=this.stripUrlPrefix(a)),a=this.removeTrailingSlash(a)},stripUrlPrefix:function(a){return a.replace(this.urlPrefixRegex,"")},stripProtocolRelativePrefix:function(a){return a.replace(this.protocolRelativeRegex,"")},removeTrailingSlash:function(a){return"/"===a.charAt(a.length-1)&&(a=a.slice(0,-1)),a}}),a});
+!function(a,b){"function"==typeof define&&define.amd?define([],function(){return a.Autolinker=b()}):"object"==typeof exports?module.exports=b():a.Autolinker=b()}(this,function(){var a=function(b){a.Util.assign(this,b);var c=this.hashtag;if(c!==!1&&"twitter"!==c&&"facebook"!==c)throw new Error("invalid `hashtag` cfg - see docs")};return a.prototype={constructor:a,urls:!0,email:!0,twitter:!0,phone:!0,hashtag:!1,newWindow:!0,stripPrefix:!0,truncate:void 0,className:"",htmlParser:void 0,matchParser:void 0,tagBuilder:void 0,link:function(a){for(var b=this.getHtmlParser(),c=b.parse(a),d=0,e=[],f=0,g=c.length;g>f;f++){var h=c[f],i=h.getType(),j=h.getText();if("element"===i)"a"===h.getTagName()&&(h.isClosing()?d=Math.max(d-1,0):d++),e.push(j);else if("entity"===i||"comment"===i)e.push(j);else if(0===d){var k=this.linkifyStr(j);e.push(k)}else e.push(j)}return e.join("")},linkifyStr:function(a){return this.getMatchParser().replace(a,this.createMatchReturnVal,this)},createMatchReturnVal:function(b){var c;if(this.replaceFn&&(c=this.replaceFn.call(this,this,b)),"string"==typeof c)return c;if(c===!1)return b.getMatchedText();if(c instanceof a.HtmlTag)return c.toAnchorString();var d=this.getTagBuilder(),e=d.build(b);return e.toAnchorString()},getHtmlParser:function(){var b=this.htmlParser;return b||(b=this.htmlParser=new a.htmlParser.HtmlParser),b},getMatchParser:function(){var b=this.matchParser;return b||(b=this.matchParser=new a.matchParser.MatchParser({urls:this.urls,email:this.email,twitter:this.twitter,phone:this.phone,hashtag:this.hashtag,stripPrefix:this.stripPrefix})),b},getTagBuilder:function(){var b=this.tagBuilder;return b||(b=this.tagBuilder=new a.AnchorTagBuilder({newWindow:this.newWindow,truncate:this.truncate,className:this.className})),b}},a.link=function(b,c){var d=new a(c);return d.link(b)},a.match={},a.htmlParser={},a.matchParser={},a.Util={abstractMethod:function(){throw"abstract"},trimRegex:/^[\s\uFEFF\xA0]+|[\s\uFEFF\xA0]+$/g,assign:function(a,b){for(var c in b)b.hasOwnProperty(c)&&(a[c]=b[c]);return a},extend:function(b,c){var d=b.prototype,e=function(){};e.prototype=d;var f;f=c.hasOwnProperty("constructor")?c.constructor:function(){d.constructor.apply(this,arguments)};var g=f.prototype=new e;return g.constructor=f,g.superclass=d,delete c.constructor,a.Util.assign(g,c),f},ellipsis:function(a,b,c){return a.length>b&&(c=null==c?"..":c,a=a.substring(0,b-c.length)+c),a},indexOf:function(a,b){if(Array.prototype.indexOf)return a.indexOf(b);for(var c=0,d=a.length;d>c;c++)if(a[c]===b)return c;return-1},splitAndCapture:function(a,b){if(!b.global)throw new Error("`splitRegex` must have the 'g' flag set");for(var c,d=[],e=0;c=b.exec(a);)d.push(a.substring(e,c.index)),d.push(c[0]),e=c.index+c[0].length;return d.push(a.substring(e)),d},trim:function(a){return a.replace(this.trimRegex,"")}},a.HtmlTag=a.Util.extend(Object,{whitespaceRegex:/\s+/,constructor:function(b){a.Util.assign(this,b),this.innerHtml=this.innerHtml||this.innerHTML},setTagName:function(a){return this.tagName=a,this},getTagName:function(){return this.tagName||""},setAttr:function(a,b){var c=this.getAttrs();return c[a]=b,this},getAttr:function(a){return this.getAttrs()[a]},setAttrs:function(b){var c=this.getAttrs();return a.Util.assign(c,b),this},getAttrs:function(){return this.attrs||(this.attrs={})},setClass:function(a){return this.setAttr("class",a)},addClass:function(b){for(var c,d=this.getClass(),e=this.whitespaceRegex,f=a.Util.indexOf,g=d?d.split(e):[],h=b.split(e);c=h.shift();)-1===f(g,c)&&g.push(c);return this.getAttrs()["class"]=g.join(" "),this},removeClass:function(b){for(var c,d=this.getClass(),e=this.whitespaceRegex,f=a.Util.indexOf,g=d?d.split(e):[],h=b.split(e);g.length&&(c=h.shift());){var i=f(g,c);-1!==i&&g.splice(i,1)}return this.getAttrs()["class"]=g.join(" "),this},getClass:function(){return this.getAttrs()["class"]||""},hasClass:function(a){return-1!==(" "+this.getClass()+" ").indexOf(" "+a+" ")},setInnerHtml:function(a){return this.innerHtml=a,this},getInnerHtml:function(){return this.innerHtml||""},toAnchorString:function(){var a=this.getTagName(),b=this.buildAttrsStr();return b=b?" "+b:"",["<",a,b,">",this.getInnerHtml(),"</",a,">"].join("")},buildAttrsStr:function(){if(!this.attrs)return"";var a=this.getAttrs(),b=[];for(var c in a)a.hasOwnProperty(c)&&b.push(c+'="'+a[c]+'"');return b.join(" ")}}),a.AnchorTagBuilder=a.Util.extend(Object,{constructor:function(b){a.Util.assign(this,b)},build:function(b){var c=new a.HtmlTag({tagName:"a",attrs:this.createAttrs(b.getType(),b.getAnchorHref()),innerHtml:this.processAnchorText(b.getAnchorText())});return c},createAttrs:function(a,b){var c={href:b},d=this.createCssClass(a);return d&&(c["class"]=d),this.newWindow&&(c.target="_blank"),c},createCssClass:function(a){var b=this.className;return b?b+" "+b+"-"+a:""},processAnchorText:function(a){return a=this.doTruncate(a)},doTruncate:function(b){return a.Util.ellipsis(b,this.truncate||Number.POSITIVE_INFINITY)}}),a.htmlParser.HtmlParser=a.Util.extend(Object,{htmlRegex:function(){var a=/!--([\s\S]+?)--/,b=/[0-9a-zA-Z][0-9a-zA-Z:]*/,c=/[^\s\0"'>\/=\x01-\x1F\x7F]+/,d=/(?:"[^"]*?"|'[^']*?'|[^'"=<>`\s]+)/,e=c.source+"(?:\\s*=\\s*"+d.source+")?";return new RegExp(["(?:","<(!DOCTYPE)","(?:","\\s+","(?:",e,"|",d.source+")",")*",">",")","|","(?:","<(/)?","(?:",a.source,"|","(?:","("+b.source+")","(?:","\\s+",e,")*","\\s*/?",")",")",">",")"].join(""),"gi")}(),htmlCharacterEntitiesRegex:/(&nbsp;|&#160;|&lt;|&#60;|&gt;|&#62;|&quot;|&#34;|&#39;)/gi,parse:function(a){for(var b,c,d=this.htmlRegex,e=0,f=[];null!==(b=d.exec(a));){var g=b[0],h=b[3],i=b[1]||b[4],j=!!b[2],k=a.substring(e,b.index);k&&(c=this.parseTextAndEntityNodes(k),f.push.apply(f,c)),f.push(h?this.createCommentNode(g,h):this.createElementNode(g,i,j)),e=b.index+g.length}if(e<a.length){var l=a.substring(e);l&&(c=this.parseTextAndEntityNodes(l),f.push.apply(f,c))}return f},parseTextAndEntityNodes:function(b){for(var c=[],d=a.Util.splitAndCapture(b,this.htmlCharacterEntitiesRegex),e=0,f=d.length;f>e;e+=2){var g=d[e],h=d[e+1];g&&c.push(this.createTextNode(g)),h&&c.push(this.createEntityNode(h))}return c},createCommentNode:function(b,c){return new a.htmlParser.CommentNode({text:b,comment:a.Util.trim(c)})},createElementNode:function(b,c,d){return new a.htmlParser.ElementNode({text:b,tagName:c.toLowerCase(),closing:d})},createEntityNode:function(b){return new a.htmlParser.EntityNode({text:b})},createTextNode:function(b){return new a.htmlParser.TextNode({text:b})}}),a.htmlParser.HtmlNode=a.Util.extend(Object,{text:"",constructor:function(b){a.Util.assign(this,b)},getType:a.Util.abstractMethod,getText:function(){return this.text}}),a.htmlParser.CommentNode=a.Util.extend(a.htmlParser.HtmlNode,{comment:"",getType:function(){return"comment"},getComment:function(){return this.comment}}),a.htmlParser.ElementNode=a.Util.extend(a.htmlParser.HtmlNode,{tagName:"",closing:!1,getType:function(){return"element"},getTagName:function(){return this.tagName},isClosing:function(){return this.closing}}),a.htmlParser.EntityNode=a.Util.extend(a.htmlParser.HtmlNode,{getType:function(){return"entity"}}),a.htmlParser.TextNode=a.Util.extend(a.htmlParser.HtmlNode,{getType:function(){return"text"}}),a.matchParser.MatchParser=a.Util.extend(Object,{urls:!0,email:!0,twitter:!0,phone:!0,hashtag:!1,stripPrefix:!0,matcherRegex:function(){var a=/(^|[^\w])@(\w{1,15})/,b=/(^|[^\w])#(\w{1,15})/,c=/(?:[\-;:&=\+\$,\w\.]+@)/,d=/(?:\+?\d{1,3}[-\s.])?\(?\d{3}\)?[-\s.]?\d{3}[-\s.]\d{4}/,e=/(?:[A-Za-z][-.+A-Za-z0-9]+:(?![A-Za-z][-.+A-Za-z0-9]+:\/\/)(?!\d+\/?)(?:\/\/)?)/,f=/(?:www\.)/,g=/[A-Za-z0-9\.\-]*[A-Za-z0-9\-]/,h=/\.(?:international|construction|contractors|enterprises|photography|productions|foundation|immobilien|industries|management|properties|technology|christmas|community|directory|education|equipment|institute|marketing|solutions|vacations|bargains|boutique|builders|catering|cleaning|clothing|computer|democrat|diamonds|graphics|holdings|lighting|partners|plumbing|supplies|training|ventures|academy|careers|company|cruises|domains|exposed|flights|florist|gallery|guitars|holiday|kitchen|neustar|okinawa|recipes|rentals|reviews|shiksha|singles|support|systems|agency|berlin|camera|center|coffee|condos|dating|estate|events|expert|futbol|kaufen|luxury|maison|monash|museum|nagoya|photos|repair|report|social|supply|tattoo|tienda|travel|viajes|villas|vision|voting|voyage|actor|build|cards|cheap|codes|dance|email|glass|house|mango|ninja|parts|photo|shoes|solar|today|tokyo|tools|watch|works|aero|arpa|asia|best|bike|blue|buzz|camp|club|cool|coop|farm|fish|gift|guru|info|jobs|kiwi|kred|land|limo|link|menu|mobi|moda|name|pics|pink|post|qpon|rich|ruhr|sexy|tips|vote|voto|wang|wien|wiki|zone|bar|bid|biz|cab|cat|ceo|com|edu|gov|int|kim|mil|net|onl|org|pro|pub|red|tel|uno|wed|xxx|xyz|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw)\b/,i=/[\-A-Za-z0-9+&@#\/%=~_()|'$*\[\]?!:,.;]*[\-A-Za-z0-9+&@#\/%=~_()|'$*\[\]]/;return new RegExp(["(",a.source,")","|","(",c.source,g.source,h.source,")","|","(","(?:","(",e.source,g.source,")","|","(?:","(.?//)?",f.source,g.source,")","|","(?:","(.?//)?",g.source,h.source,")",")","(?:"+i.source+")?",")","|","(",d.source,")","|","(",b.source,")"].join(""),"gi")}(),charBeforeProtocolRelMatchRegex:/^(.)?\/\//,constructor:function(b){a.Util.assign(this,b),this.matchValidator=new a.MatchValidator},replace:function(a,b,c){var d=this;return a.replace(this.matcherRegex,function(a,e,f,g,h,i,j,k,l,m,n,o,p){var q=d.processCandidateMatch(a,e,f,g,h,i,j,k,l,m,n,o,p);if(q){var r=b.call(c,q.match);return q.prefixStr+r+q.suffixStr}return a})},processCandidateMatch:function(b,c,d,e,f,g,h,i,j,k,l,m,n){var o,p=i||j,q="",r="";if(g&&!this.urls||f&&!this.email||k&&!this.phone||c&&!this.twitter||l&&!this.hashtag||!this.matchValidator.isValidMatch(g,h,p))return null;if(this.matchHasUnbalancedClosingParen(b)&&(b=b.substr(0,b.length-1),r=")"),f)o=new a.match.Email({matchedText:b,email:f});else if(c)d&&(q=d,b=b.slice(1)),o=new a.match.Twitter({matchedText:b,twitterHandle:e});else if(k){var s=b.replace(/\D/g,"");o=new a.match.Phone({matchedText:b,number:s})}else if(l)m&&(q=m,b=b.slice(1)),o=new a.match.Hashtag({matchedText:b,serviceName:this.hashtag,hashtag:n});else{if(p){var t=p.match(this.charBeforeProtocolRelMatchRegex)[1]||"";t&&(q=t,b=b.slice(1))}o=new a.match.Url({matchedText:b,url:b,protocolUrlMatch:!!h,protocolRelativeMatch:!!p,stripPrefix:this.stripPrefix})}return{prefixStr:q,suffixStr:r,match:o}},matchHasUnbalancedClosingParen:function(a){var b=a.charAt(a.length-1);if(")"===b){var c=a.match(/\(/g),d=a.match(/\)/g),e=c&&c.length||0,f=d&&d.length||0;if(f>e)return!0}return!1}}),a.MatchValidator=a.Util.extend(Object,{invalidProtocolRelMatchRegex:/^[\w]\/\//,hasFullProtocolRegex:/^[A-Za-z][-.+A-Za-z0-9]+:\/\//,uriSchemeRegex:/^[A-Za-z][-.+A-Za-z0-9]+:/,hasWordCharAfterProtocolRegex:/:[^\s]*?[A-Za-z]/,isValidMatch:function(a,b,c){return b&&!this.isValidUriScheme(b)||this.urlMatchDoesNotHaveProtocolOrDot(a,b)||this.urlMatchDoesNotHaveAtLeastOneWordChar(a,b)||this.isInvalidProtocolRelativeMatch(c)?!1:!0},isValidUriScheme:function(a){var b=a.match(this.uriSchemeRegex)[0].toLowerCase();return"javascript:"!==b&&"vbscript:"!==b},urlMatchDoesNotHaveProtocolOrDot:function(a,b){return!(!a||b&&this.hasFullProtocolRegex.test(b)||-1!==a.indexOf("."))},urlMatchDoesNotHaveAtLeastOneWordChar:function(a,b){return a&&b?!this.hasWordCharAfterProtocolRegex.test(a):!1},isInvalidProtocolRelativeMatch:function(a){return!!a&&this.invalidProtocolRelMatchRegex.test(a)}}),a.match.Match=a.Util.extend(Object,{constructor:function(b){a.Util.assign(this,b)},getType:a.Util.abstractMethod,getMatchedText:function(){return this.matchedText},getAnchorHref:a.Util.abstractMethod,getAnchorText:a.Util.abstractMethod}),a.match.Email=a.Util.extend(a.match.Match,{getType:function(){return"email"},getEmail:function(){return this.email},getAnchorHref:function(){return"mailto:"+this.email},getAnchorText:function(){return this.email}}),a.match.Hashtag=a.Util.extend(a.match.Match,{getType:function(){return"hashtag"},getHashtag:function(){return this.hashtag},getAnchorHref:function(){var a=this.serviceName,b=this.hashtag;switch(a){case"twitter":return"https://twitter.com/hashtag/"+b;case"facebook":return"https://www.facebook.com/hashtag/"+b;default:throw new Error("Unknown service name to point hashtag to: ",a)}},getAnchorText:function(){return"#"+this.hashtag}}),a.match.Phone=a.Util.extend(a.match.Match,{getType:function(){return"phone"},getNumber:function(){return this.number},getAnchorHref:function(){return"tel:"+this.number},getAnchorText:function(){return this.matchedText}}),a.match.Twitter=a.Util.extend(a.match.Match,{getType:function(){return"twitter"},getTwitterHandle:function(){return this.twitterHandle},getAnchorHref:function(){return"https://twitter.com/"+this.twitterHandle},getAnchorText:function(){return"@"+this.twitterHandle}}),a.match.Url=a.Util.extend(a.match.Match,{urlPrefixRegex:/^(https?:\/\/)?(www\.)?/i,protocolRelativeRegex:/^\/\//,protocolPrepended:!1,getType:function(){return"url"},getUrl:function(){var a=this.url;return this.protocolRelativeMatch||this.protocolUrlMatch||this.protocolPrepended||(a=this.url="http://"+a,this.protocolPrepended=!0),a},getAnchorHref:function(){var a=this.getUrl();return a.replace(/&amp;/g,"&")},getAnchorText:function(){var a=this.getUrl();return this.protocolRelativeMatch&&(a=this.stripProtocolRelativePrefix(a)),this.stripPrefix&&(a=this.stripUrlPrefix(a)),a=this.removeTrailingSlash(a)},stripUrlPrefix:function(a){return a.replace(this.urlPrefixRegex,"")},stripProtocolRelativePrefix:function(a){return a.replace(this.protocolRelativeRegex,"")},removeTrailingSlash:function(a){return"/"===a.charAt(a.length-1)&&(a=a.slice(0,-1)),a}}),a});

Gruntfile.js

@@ -61,2 +61,3 @@ /*global require, module */
 					'src/htmlParser/HtmlNode.js',
+					'src/htmlParser/CommentNode.js',
 					'src/htmlParser/ElementNode.js',
@@ -63,0 +64,0 @@ 'src/htmlParser/EntityNode.js',

package.json

 {
   "name": "autolinker",
-  "version": "0.17.0",
+  "version": "0.17.1",
   "description": "Utility to automatically link the URLs, email addresses, and Twitter handles in a given block of text/HTML",
@@ -5,0 +5,0 @@ "main": "dist/Autolinker.js",

src/Autolinker.js

@@ -263,3 +263,3 @@ /**
 	 *   (depending on if the {@link #urls}, {@link #email}, {@link #phone},
-	 *   {@link #twitter}, and {@link #hashtags} options are enabled).
+	 *   {@link #twitter}, and {@link #hashtag} options are enabled).
 	 * @return {String} The HTML, with matches automatically linked.
@@ -289,4 +289,4 @@ */
 
-			} else if( nodeType === 'entity' ) {
-				resultHtml.push( nodeText );  // append HTML entity nodes (such as ' ') verbatim
+			} else if( nodeType === 'entity' || nodeType === 'comment' ) {
+				resultHtml.push( nodeText );  // append HTML entity nodes (such as '&nbsp;') or HTML comments (such as '<!-- Comment -->') verbatim
 
@@ -312,4 +312,5 @@ } else {
 	/**
-	 * Process the text that lies in between HTML tags, performing the anchor tag replacements for
-	 * the matches, and returns the string with the replacements made.
+	 * Process the text that lies in between HTML tags, performing the anchor
+	 * tag replacements for the matches, and returns the string with the
+	 * replacements made.
 	 *
@@ -328,3 +329,4 @@ * This method does the actual wrapping of matches with anchor tags.
 	/**
-	 * Creates the return string value for a given match in the input string, for the {@link #processTextNode} method.
+	 * Creates the return string value for a given match in the input string,
+	 * for the {@link #linkifyStr} method.
 	 *
@@ -448,4 +450,4 @@ * This method handles the {@link #replaceFn}, if one was provided.
  *
- * For instance, if given the text: `You should go to http://www.yahoo.com`, then the result
- * will be `You should go to &lt;a href="http://www.yahoo.com"&gt;http://www.yahoo.com&lt;/a&gt;`
+ * For instance, if given the text: `You should go to http://www.yahoo.com`,
+ * then the result will be `You should go to &lt;a href="http://www.yahoo.com"&gt;http://www.yahoo.com&lt;/a&gt;`
  *
@@ -458,6 +460,8 @@ * Example:
  * @static
- * @param {String} textOrHtml The HTML or text to find matches within (depending on if
- *   the {@link #urls}, {@link #email}, {@link #phone}, {@link #twitter}, and {@link #hashtags} options are enabled).
- * @param {Object} [options] Any of the configuration options for the Autolinker class, specified in an Object (map).
- *   See the class description for an example call.
+ * @param {String} textOrHtml The HTML or text to find matches within (depending
+ *   on if the {@link #urls}, {@link #email}, {@link #phone}, {@link #twitter},
+ *   and {@link #hashtag} options are enabled).
+ * @param {Object} [options] Any of the configuration options for the Autolinker
+ *   class, specified in an Object (map). See the class description for an
+ *   example call.
  * @return {String} The HTML text, with matches automatically linked.
@@ -464,0 +468,0 @@ */

src/htmlParser/HtmlParser.js

@@ -6,6 +6,6 @@ /*global Autolinker */
  * @extends Object
- * 
- * An HTML parser implementation which simply walks an HTML string and returns an array of 
+ *
+ * An HTML parser implementation which simply walks an HTML string and returns an array of
  * {@link Autolinker.htmlParser.HtmlNode HtmlNodes} that represent the basic HTML structure of the input string.
- * 
+ *
  * Autolinker uses this to only link URLs/emails/Twitter handles within text nodes, effectively ignoring / "walking
@@ -15,34 +15,37 @@ * around" HTML tags.
 Autolinker.htmlParser.HtmlParser = Autolinker.Util.extend( Object, {
-	
+
 	/**
 	 * @private
 	 * @property {RegExp} htmlRegex
-	 * 
+	 *
 	 * The regular expression used to pull out HTML tags from a string. Handles namespaced HTML tags and
 	 * attribute names, as specified by http://www.w3.org/TR/html-markup/syntax.html.
-	 * 
+	 *
 	 * Capturing groups:
-	 * 
+	 *
 	 * 1. The "!DOCTYPE" tag name, if a tag is a <!DOCTYPE> tag.
 	 * 2. If it is an end tag, this group will have the '/'.
-	 * 3. The tag name for all tags (other than the <!DOCTYPE> tag)
+	 * 3. If it is a comment tag, this group will hold the comment text (i.e.
+	 *    the text inside the `<!--` and `-->`.
+	 * 4. The tag name for all tags (other than the <!DOCTYPE> tag)
 	 */
 	htmlRegex : (function() {
-		var tagNameRegex = /[0-9a-zA-Z][0-9a-zA-Z:]*/,
+		var commentTagRegex = /!--([\s\S]+?)--/,
+		    tagNameRegex = /[0-9a-zA-Z][0-9a-zA-Z:]*/,
 		    attrNameRegex = /[^\s\0"'>\/=\x01-\x1F\x7F]+/,   // the unicode range accounts for excluding control chars, and the delete char
 		    attrValueRegex = /(?:"[^"]*?"|'[^']*?'|[^'"=<>`\s]+)/, // double quoted, single quoted, or unquoted attribute values
 		    nameEqualsValueRegex = attrNameRegex.source + '(?:\\s*=\\s*' + attrValueRegex.source + ')?';  // optional '=[value]'
-		
+
 		return new RegExp( [
-			// for <!DOCTYPE> tag. Ex: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">) 
+			// for <!DOCTYPE> tag. Ex: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">)
 			'(?:',
 				'<(!DOCTYPE)',  // *** Capturing Group 1 - If it's a doctype tag
-					
+
 					// Zero or more attributes following the tag name
 					'(?:',
 						'\\s+',  // one or more whitespace chars before an attribute
-						
+
 						// Either:
-						// A. attr="value", or 
-						// B. "value" alone (To cover example doctype tag: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">) 
+						// A. attr="value", or
+						// B. "value" alone (To cover example doctype tag: <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">)
 						'(?:', nameEqualsValueRegex, '|', attrValueRegex.source + ')',
@@ -52,20 +55,30 @@ ')*',
 			')',
-			
+
 			'|',
-			
+
 			// All other HTML tags (i.e. tags that are not <!DOCTYPE>)
 			'(?:',
-				'<(/)?',  // Beginning of a tag. Either '<' for a start tag, or '</' for an end tag. 
+				'<(/)?',  // Beginning of a tag or comment. Either '<' for a start tag, or '</' for an end tag.
 				          // *** Capturing Group 2: The slash or an empty string. Slash ('/') for end tag, empty string for start or self-closing tag.
-			
-					// *** Capturing Group 3 - The tag name
-					'(' + tagNameRegex.source + ')',
-					
-					// Zero or more attributes following the tag name
+
 					'(?:',
-						'\\s+',                // one or more whitespace chars before an attribute
-						nameEqualsValueRegex,  // attr="value" (with optional ="value" part)
-					')*',
-					
-					'\\s*/?',  // any trailing spaces and optional '/' before the closing '>'
+						commentTagRegex.source,  // *** Capturing Group 3 - A Comment Tag's Text
+
+						'|',
+
+						'(?:',
+
+							// *** Capturing Group 4 - The tag name
+							'(' + tagNameRegex.source + ')',
+
+							// Zero or more attributes following the tag name
+							'(?:',
+								'\\s+',                // one or more whitespace chars before an attribute
+								nameEqualsValueRegex,  // attr="value" (with optional ="value" part)
+							')*',
+
+							'\\s*/?',  // any trailing spaces and optional '/' before the closing '>'
+
+						')',
+					')',
 				'>',
@@ -75,3 +88,3 @@ ')'
 	} )(),
-	
+
 	/**
@@ -82,12 +95,12 @@ * @private
 	 * The regular expression that matches common HTML character entities.
-	 * 
+	 *
 	 * Ignoring &amp; as it could be part of a query string -- handling it separately.
 	 */
 	htmlCharacterEntitiesRegex: /(&nbsp;|&#160;|&lt;|&#60;|&gt;|&#62;|&quot;|&#34;|&#39;)/gi,
-	
-	
+
+
 	/**
-	 * Parses an HTML string and returns a simple array of {@link Autolinker.htmlParser.HtmlNode HtmlNodes} to represent
-	 * the HTML structure of the input string. 
-	 * 
+	 * Parses an HTML string and returns a simple array of {@link Autolinker.htmlParser.HtmlNode HtmlNodes}
+	 * to represent the HTML structure of the input string.
+	 *
 	 * @param {String} html The HTML to parse.
@@ -102,9 +115,10 @@ * @return {Autolinker.htmlParser.HtmlNode[]}
 		    nodes = [];  // will be the result of the method
-		
+
 		while( ( currentResult = htmlRegex.exec( html ) ) !== null ) {
 			var tagText = currentResult[ 0 ],
-			    tagName = currentResult[ 1 ] || currentResult[ 3 ],  // The <!DOCTYPE> tag (ex: "!DOCTYPE"), or another tag (ex: "a" or "img") 
+			    commentText = currentResult[ 3 ], // if we've matched a comment
+			    tagName = currentResult[ 1 ] || currentResult[ 4 ],  // The <!DOCTYPE> tag (ex: "!DOCTYPE"), or another tag (ex: "a" or "img")
 			    isClosingTag = !!currentResult[ 2 ],
 			    inBetweenTagsText = html.substring( lastIndex, currentResult.index );
-			
+
 			// Push TextNodes and EntityNodes for any text found between tags
@@ -115,13 +129,17 @@ if( inBetweenTagsText ) {
 			}
-			
-			// Push the ElementNode
-			nodes.push( this.createElementNode( tagText, tagName, isClosingTag ) );
-			
+
+			// Push the CommentNode or ElementNode
+			if( commentText ) {
+				nodes.push( this.createCommentNode( tagText, commentText ) );
+			} else {
+				nodes.push( this.createElementNode( tagText, tagName, isClosingTag ) );
+			}
+
 			lastIndex = currentResult.index + tagText.length;
 		}
-		
+
 		// Process any remaining text after the last HTML element. Will process all of the text if there were no HTML elements.
 		if( lastIndex < html.length ) {
 			var text = html.substring( lastIndex );
-			
+
 			// Push TextNodes and EntityNodes for any text found between tags
@@ -133,15 +151,16 @@ if( text ) {
 		}
-		
+
 		return nodes;
 	},
-	
-	
+
+
 	/**
-	 * Parses text and HTML entity nodes from a given string. The input string should not have any HTML tags (elements)
-	 * within it.
-	 * 
+	 * Parses text and HTML entity nodes from a given string. The input string
+	 * should not have any HTML tags (elements) within it.
+	 *
 	 * @private
 	 * @param {String} text The text to parse.
-	 * @return {Autolinker.htmlParser.HtmlNode[]} An array of HtmlNodes to represent the 
-	 *   {@link Autolinker.htmlParser.TextNode TextNodes} and {@link Autolinker.htmlParser.EntityNode EntityNodes} found.
+	 * @return {Autolinker.htmlParser.HtmlNode[]} An array of HtmlNodes to
+	 *   represent the {@link Autolinker.htmlParser.TextNode TextNodes} and
+	 *   {@link Autolinker.htmlParser.EntityNode EntityNodes} found.
 	 */
@@ -151,5 +170,5 @@ parseTextAndEntityNodes : function( text ) {
 		    textAndEntityTokens = Autolinker.Util.splitAndCapture( text, this.htmlCharacterEntitiesRegex );  // split at HTML entities, but include the HTML entities in the results array
-		
+
 		// Every even numbered token is a TextNode, and every odd numbered token is an EntityNode
-		// For example: an input `text` of "Test &quot;this&quot; today" would turn into the 
+		// For example: an input `text` of "Test &quot;this&quot; today" would turn into the
 		//   `textAndEntityTokens`: [ 'Test ', '&quot;', 'this', '&quot;', ' today' ]
@@ -159,3 +178,3 @@ for( var i = 0, len = textAndEntityTokens.length; i < len; i += 2 ) {
 			    entityToken = textAndEntityTokens[ i + 1 ];
-			
+
 			if( textToken ) nodes.push( this.createTextNode( textToken ) );
@@ -166,11 +185,30 @@ if( entityToken ) nodes.push( this.createEntityNode( entityToken ) );
 	},
-	
-	
+
+
 	/**
+	 * Factory method to create an {@link Autolinker.htmlParser.CommentNode CommentNode}.
+	 *
+	 * @private
+	 * @param {String} tagText The full text of the tag (comment) that was
+	 *   matched, including its &lt;!-- and --&gt;.
+	 * @param {String} comment The full text of the comment that was matched.
+	 */
+	createCommentNode : function( tagText, commentText ) {
+		return new Autolinker.htmlParser.CommentNode( {
+			text: tagText,
+			comment: Autolinker.Util.trim( commentText )
+		} );
+	},
+
+
+	/**
 	 * Factory method to create an {@link Autolinker.htmlParser.ElementNode ElementNode}.
-	 * 
+	 *
 	 * @private
-	 * @param {String} tagText The full text of the tag (element) that was matched, including its attributes.
-	 * @param {String} tagName The name of the tag. Ex: An &lt;img&gt; tag would be passed to this method as "img".
-	 * @param {Boolean} isClosingTag `true` if it's a closing tag, false otherwise.
+	 * @param {String} tagText The full text of the tag (element) that was
+	 *   matched, including its attributes.
+	 * @param {String} tagName The name of the tag. Ex: An &lt;img&gt; tag would
+	 *   be passed to this method as "img".
+	 * @param {Boolean} isClosingTag `true` if it's a closing tag, false
+	 *   otherwise.
 	 * @return {Autolinker.htmlParser.ElementNode}
@@ -185,9 +223,10 @@ */
 	},
-	
-	
+
+
 	/**
 	 * Factory method to create a {@link Autolinker.htmlParser.EntityNode EntityNode}.
-	 * 
+	 *
 	 * @private
-	 * @param {String} text The text that was matched for the HTML entity (such as '&amp;nbsp;').
+	 * @param {String} text The text that was matched for the HTML entity (such
+	 *   as '&amp;nbsp;').
 	 * @return {Autolinker.htmlParser.EntityNode}
@@ -198,7 +237,7 @@ */
 	},
-	
-	
+
+
 	/**
 	 * Factory method to create a {@link Autolinker.htmlParser.TextNode TextNode}.
-	 * 
+	 *
 	 * @private
@@ -211,3 +250,3 @@ * @param {String} text The text that was matched.
 	}
-	
+
 } );

src/matchParser/MatchParser.js

@@ -10,5 +10,5 @@ /*global Autolinker */
  * The MatchParser is fed a non-HTML string in order to search for matches.
- * Autolinker first uses the {@link HtmlParser} to "walk around" HTML tags,
- * and then the text around the HTML tags is passed into the MatchParser in
- * order to find the actual matches.
+ * Autolinker first uses the {@link Autolinker.htmlParser.HtmlParser} to "walk
+ * around" HTML tags, and then the text around the HTML tags is passed into the
+ * MatchParser in order to find the actual matches.
  */
@@ -185,7 +185,9 @@ Autolinker.matchParser.MatchParser = Autolinker.Util.extend( Object, {
 	 *
-	 * The regular expression used to retrieve the character before a protocol-relative URL match.
+	 * The regular expression used to retrieve the character before a
+	 * protocol-relative URL match.
 	 *
-	 * This is used in conjunction with the {@link #matcherRegex}, which needs to grab the character before a protocol-relative
-	 * '//' due to the lack of a negative look-behind in JavaScript regular expressions. The character before the match is stripped
-	 * from the URL.
+	 * This is used in conjunction with the {@link #matcherRegex}, which needs
+	 * to grab the character before a protocol-relative '//' due to the lack of
+	 * a negative look-behind in JavaScript regular expressions. The character
+	 * before the match is stripped from the URL.
 	 */
@@ -198,4 +200,4 @@ charBeforeProtocolRelMatchRegex : /^(.)?\/\//,
 	 *
-	 * The MatchValidator object, used to filter out any false positives from the {@link #matcherRegex}. See
-	 * {@link Autolinker.MatchValidator} for details.
+	 * The MatchValidator object, used to filter out any false positives from
+	 * the {@link #matcherRegex}. See {@link Autolinker.MatchValidator} for details.
 	 */
@@ -206,3 +208,4 @@
 	 * @constructor
-	 * @param {Object} [cfg] The configuration options for the AnchorTagBuilder instance, specified in an Object (map).
+	 * @param {Object} [cfg] The configuration options for the AnchorTagBuilder
+	 * instance, specified in an Object (map).
 	 */
@@ -218,3 +221,4 @@ constructor : function( cfg ) {
 	 * Parses the input `text` to search for matches, and calls the `replaceFn`
-	 * to allow replacements of the matches. Returns the `text` with matches replaced.
+	 * to allow replacements of the matches. Returns the `text` with matches
+	 * replaced.
 	 *
@@ -321,4 +325,6 @@ * @param {String} text The text to search and repace matches in.
 
-		// Return out with `null` for match types that are disabled (url, email, twitter, hashtag), or for matches that are
-		// invalid (false positives from the matcherRegex, which can't use look-behinds since they are unavailable in JS).
+		// Return out with `null` for match types that are disabled (url, email,
+		// twitter, hashtag), or for matches that are invalid (false positives
+		// from the matcherRegex, which can't use look-behinds since they are
+		// unavailable in JS).
 		if(
@@ -335,3 +341,4 @@ ( urlMatch && !this.urls ) ||
 
-		// Handle a closing parenthesis at the end of the match, and exclude it if there is not a matching open parenthesis
+		// Handle a closing parenthesis at the end of the match, and exclude it
+		// if there is not a matching open parenthesis
 		// in the match itself.
@@ -347,4 +354,5 @@ if( this.matchHasUnbalancedClosingParen( matchStr ) ) {
 		} else if( twitterMatch ) {
-			// fix up the `matchStr` if there was a preceding whitespace char, which was needed to determine the match
-			// itself (since there are no look-behinds in JS regexes)
+			// fix up the `matchStr` if there was a preceding whitespace char,
+			// which was needed to determine the match itself (since there are
+			// no look-behinds in JS regexes)
 			if( twitterHandlePrefixWhitespaceChar ) {
@@ -362,4 +370,5 @@ prefixStr = twitterHandlePrefixWhitespaceChar;
 		} else if( hashtagMatch ) {
-			// fix up the `matchStr` if there was a preceding whitespace char, which was needed to determine the match
-			// itself (since there are no look-behinds in JS regexes)
+			// fix up the `matchStr` if there was a preceding whitespace char,
+			// which was needed to determine the match itself (since there are
+			// no look-behinds in JS regexes)
 			if( hashtagPrefixWhitespaceChar ) {
@@ -372,4 +381,6 @@ prefixStr = hashtagPrefixWhitespaceChar;
 		} else {  // url match
-			// If it's a protocol-relative '//' match, remove the character before the '//' (which the matcherRegex needed
-			// to match due to the lack of a negative look-behind in JavaScript regular expressions)
+			// If it's a protocol-relative '//' match, remove the character
+			// before the '//' (which the matcherRegex needed to match due to
+			// the lack of a negative look-behind in JavaScript regular
+			// expressions)
 			if( protocolRelativeMatch ) {
@@ -402,15 +413,19 @@ var charBeforeMatch = protocolRelativeMatch.match( this.charBeforeProtocolRelMatchRegex )[ 1 ] || "";
 	/**
-	 * Determines if a match found has an unmatched closing parenthesis. If so, this parenthesis will be removed
-	 * from the match itself, and appended after the generated anchor tag in {@link #processTextNode}.
+	 * Determines if a match found has an unmatched closing parenthesis. If so,
+	 * this parenthesis will be removed from the match itself, and appended
+	 * after the generated anchor tag in {@link #processCandidateMatch}.
 	 *
-	 * A match may have an extra closing parenthesis at the end of the match because the regular expression must include parenthesis
-	 * for URLs such as "wikipedia.com/something_(disambiguation)", which should be auto-linked.
+	 * A match may have an extra closing parenthesis at the end of the match
+	 * because the regular expression must include parenthesis for URLs such as
+	 * "wikipedia.com/something_(disambiguation)", which should be auto-linked.
 	 *
-	 * However, an extra parenthesis *will* be included when the URL itself is wrapped in parenthesis, such as in the case of
-	 * "(wikipedia.com/something_(disambiguation))". In this case, the last closing parenthesis should *not* be part of the URL
-	 * itself, and this method will return `true`.
+	 * However, an extra parenthesis *will* be included when the URL itself is
+	 * wrapped in parenthesis, such as in the case of "(wikipedia.com/something_(disambiguation))".
+	 * In this case, the last closing parenthesis should *not* be part of the
+	 * URL itself, and this method will return `true`.
 	 *
 	 * @private
 	 * @param {String} matchStr The full match string from the {@link #matcherRegex}.
-	 * @return {Boolean} `true` if there is an unbalanced closing parenthesis at the end of the `matchStr`, `false` otherwise.
+	 * @return {Boolean} `true` if there is an unbalanced closing parenthesis at
+	 *   the end of the `matchStr`, `false` otherwise.
 	 */
@@ -417,0 +432,0 @@ matchHasUnbalancedClosingParen : function( matchStr ) {

src/matchParser/MatchValidator.js

@@ -7,30 +7,35 @@ /*global Autolinker */
  * @extends Object
- * 
- * Used by Autolinker to filter out false positives from the {@link Autolinker#matcherRegex}.
- * 
- * Due to the limitations of regular expressions (including the missing feature of look-behinds in JS regular expressions),
- * we cannot always determine the validity of a given match. This class applies a bit of additional logic to filter out any
- * false positives that have been matched by the {@link Autolinker#matcherRegex}.
+ *
+ * Used by Autolinker to filter out false positives from the
+ * {@link Autolinker.matchParser.MatchParser#matcherRegex}.
+ *
+ * Due to the limitations of regular expressions (including the missing feature
+ * of look-behinds in JS regular expressions), we cannot always determine the
+ * validity of a given match. This class applies a bit of additional logic to
+ * filter out any false positives that have been matched by the
+ * {@link Autolinker.matchParser.MatchParser#matcherRegex}.
  */
 Autolinker.MatchValidator = Autolinker.Util.extend( Object, {
-	
+
 	/**
 	 * @private
 	 * @property {RegExp} invalidProtocolRelMatchRegex
-	 * 
-	 * The regular expression used to check a potential protocol-relative URL match, coming from the 
-	 * {@link Autolinker#matcherRegex}. A protocol-relative URL is, for example, "//yahoo.com"
-	 * 
-	 * This regular expression checks to see if there is a word character before the '//' match in order to determine if 
-	 * we should actually autolink a protocol-relative URL. This is needed because there is no negative look-behind in 
-	 * JavaScript regular expressions. 
-	 * 
-	 * For instance, we want to autolink something like "Go to: //google.com", but we don't want to autolink something 
-	 * like "abc//google.com"
+	 *
+	 * The regular expression used to check a potential protocol-relative URL
+	 * match, coming from the {@link Autolinker.matchParser.MatchParser#matcherRegex}.
+	 * A protocol-relative URL is, for example, "//yahoo.com"
+	 *
+	 * This regular expression checks to see if there is a word character before
+	 * the '//' match in order to determine if we should actually autolink a
+	 * protocol-relative URL. This is needed because there is no negative
+	 * look-behind in JavaScript regular expressions.
+	 *
+	 * For instance, we want to autolink something like "Go to: //google.com",
+	 * but we don't want to autolink something like "abc//google.com"
 	 */
 	invalidProtocolRelMatchRegex : /^[\w]\/\//,
-	
+
 	/**
 	 * Regex to test for a full protocol, with the two trailing slashes. Ex: 'http://'
-	 * 
+	 *
 	 * @private
@@ -40,8 +45,8 @@ * @property {RegExp} hasFullProtocolRegex
 	hasFullProtocolRegex : /^[A-Za-z][-.+A-Za-z0-9]+:\/\//,
-	
+
 	/**
 	 * Regex to find the URI scheme, such as 'mailto:'.
-	 * 
+	 *
 	 * This is used to filter out 'javascript:' and 'vbscript:' schemes.
-	 * 
+	 *
 	 * @private
@@ -51,6 +56,6 @@ * @property {RegExp} uriSchemeRegex
 	uriSchemeRegex : /^[A-Za-z][-.+A-Za-z0-9]+:/,
-	
+
 	/**
 	 * Regex to determine if at least one word char exists after the protocol (i.e. after the ':')
-	 * 
+	 *
 	 * @private
@@ -60,24 +65,32 @@ * @property {RegExp} hasWordCharAfterProtocolRegex
 	hasWordCharAfterProtocolRegex : /:[^\s]*?[A-Za-z]/,
-	
-	
+
+
 	/**
-	 * Determines if a given match found by {@link Autolinker#processTextNode} is valid. Will return `false` for:
-	 * 
-	 * 1) URL matches which do not have at least have one period ('.') in the domain name (effectively skipping over 
-	 *    matches like "abc:def"). However, URL matches with a protocol will be allowed (ex: 'http://localhost')
-	 * 2) URL matches which do not have at least one word character in the domain name (effectively skipping over
-	 *    matches like "git:1.0").
-	 * 3) A protocol-relative url match (a URL beginning with '//') whose previous character is a word character 
-	 *    (effectively skipping over strings like "abc//google.com")
-	 * 
+	 * Determines if a given match found by the {@link Autolinker.matchParser.MatchParser}
+	 * is valid. Will return `false` for:
+	 *
+	 * 1) URL matches which do not have at least have one period ('.') in the
+	 *    domain name (effectively skipping over matches like "abc:def").
+	 *    However, URL matches with a protocol will be allowed (ex: 'http://localhost')
+	 * 2) URL matches which do not have at least one word character in the
+	 *    domain name (effectively skipping over matches like "git:1.0").
+	 * 3) A protocol-relative url match (a URL beginning with '//') whose
+	 *    previous character is a word character (effectively skipping over
+	 *    strings like "abc//google.com")
+	 *
 	 * Otherwise, returns `true`.
-	 * 
-	 * @param {String} urlMatch The matched URL, if there was one. Will be an empty string if the match is not a URL match.
-	 * @param {String} protocolUrlMatch The match URL string for a protocol match. Ex: 'http://yahoo.com'. This is used to match
-	 *   something like 'http://localhost', where we won't double check that the domain name has at least one '.' in it.
-	 * @param {String} protocolRelativeMatch The protocol-relative string for a URL match (i.e. '//'), possibly with a preceding
-	 *   character (ex, a space, such as: ' //', or a letter, such as: 'a//'). The match is invalid if there is a word character
-	 *   preceding the '//'.
-	 * @return {Boolean} `true` if the match given is valid and should be processed, or `false` if the match is invalid and/or 
-	 *   should just not be processed.
+	 *
+	 * @param {String} urlMatch The matched URL, if there was one. Will be an
+	 *   empty string if the match is not a URL match.
+	 * @param {String} protocolUrlMatch The match URL string for a protocol
+	 *   match. Ex: 'http://yahoo.com'. This is used to match something like
+	 *   'http://localhost', where we won't double check that the domain name
+	 *   has at least one '.' in it.
+	 * @param {String} protocolRelativeMatch The protocol-relative string for a
+	 *   URL match (i.e. '//'), possibly with a preceding character (ex, a
+	 *   space, such as: ' //', or a letter, such as: 'a//'). The match is
+	 *   invalid if there is a word character preceding the '//'.
+	 * @return {Boolean} `true` if the match given is valid and should be
+	 *   processed, or `false` if the match is invalid and/or should just not be
+	 *   processed.
 	 */
@@ -93,14 +106,14 @@ isValidMatch : function( urlMatch, protocolUrlMatch, protocolRelativeMatch ) {
 		}
-		
+
 		return true;
 	},
-	
-	
+
+
 	/**
-	 * Determines if the URI scheme is a valid scheme to be autolinked. Returns `false` if the scheme is 
-	 * 'javascript:' or 'vbscript:'
-	 * 
+	 * Determines if the URI scheme is a valid scheme to be autolinked. Returns
+	 * `false` if the scheme is 'javascript:' or 'vbscript:'
+	 *
 	 * @private
-	 * @param {String} uriSchemeMatch The match URL string for a full URI scheme match. Ex: 'http://yahoo.com' 
-	 *   or 'mailto:[e-mail]'.
+	 * @param {String} uriSchemeMatch The match URL string for a full URI scheme
+	 *   match. Ex: 'http://yahoo.com' or 'mailto:[e-mail]'.
 	 * @return {Boolean} `true` if the scheme is a valid one, `false` otherwise.
@@ -110,22 +123,27 @@ */
 		var uriScheme = uriSchemeMatch.match( this.uriSchemeRegex )[ 0 ].toLowerCase();
-		
+
 		return ( uriScheme !== 'javascript:' && uriScheme !== 'vbscript:' );
 	},
-	
-	
+
+
 	/**
 	 * Determines if a URL match does not have either:
-	 * 
+	 *
 	 * a) a full protocol (i.e. 'http://'), or
-	 * b) at least one dot ('.') in the domain name (for a non-full-protocol match).
-	 * 
-	 * Either situation is considered an invalid URL (ex: 'git:d' does not have either the '://' part, or at least one dot
-	 * in the domain name. If the match was 'git:abc.com', we would consider this valid.)
-	 * 
+	 * b) at least one dot ('.') in the domain name (for a non-full-protocol
+	 *    match).
+	 *
+	 * Either situation is considered an invalid URL (ex: 'git:d' does not have
+	 * either the '://' part, or at least one dot in the domain name. If the
+	 * match was 'git:abc.com', we would consider this valid.)
+	 *
 	 * @private
-	 * @param {String} urlMatch The matched URL, if there was one. Will be an empty string if the match is not a URL match.
-	 * @param {String} protocolUrlMatch The match URL string for a protocol match. Ex: 'http://yahoo.com'. This is used to match
-	 *   something like 'http://localhost', where we won't double check that the domain name has at least one '.' in it.
-	 * @return {Boolean} `true` if the URL match does not have a full protocol, or at least one dot ('.') in a non-full-protocol
-	 *   match.
+	 * @param {String} urlMatch The matched URL, if there was one. Will be an
+	 *   empty string if the match is not a URL match.
+	 * @param {String} protocolUrlMatch The match URL string for a protocol
+	 *   match. Ex: 'http://yahoo.com'. This is used to match something like
+	 *   'http://localhost', where we won't double check that the domain name
+	 *   has at least one '.' in it.
+	 * @return {Boolean} `true` if the URL match does not have a full protocol,
+	 *   or at least one dot ('.') in a non-full-protocol match.
 	 */
@@ -135,17 +153,20 @@ urlMatchDoesNotHaveProtocolOrDot : function( urlMatch, protocolUrlMatch ) {
 	},
-	
-	
+
+
 	/**
-	 * Determines if a URL match does not have at least one word character after the protocol (i.e. in the domain name).
-	 * 
-	 * At least one letter character must exist in the domain name after a protocol match. Ex: skip over something 
-	 * like "git:1.0"
-	 * 
+	 * Determines if a URL match does not have at least one word character after
+	 * the protocol (i.e. in the domain name).
+	 *
+	 * At least one letter character must exist in the domain name after a
+	 * protocol match. Ex: skip over something like "git:1.0"
+	 *
 	 * @private
-	 * @param {String} urlMatch The matched URL, if there was one. Will be an empty string if the match is not a URL match.
-	 * @param {String} protocolUrlMatch The match URL string for a protocol match. Ex: 'http://yahoo.com'. This is used to
-	 *   know whether or not we have a protocol in the URL string, in order to check for a word character after the protocol
-	 *   separator (':').
-	 * @return {Boolean} `true` if the URL match does not have at least one word character in it after the protocol, `false`
-	 *   otherwise.
+	 * @param {String} urlMatch The matched URL, if there was one. Will be an
+	 *   empty string if the match is not a URL match.
+	 * @param {String} protocolUrlMatch The match URL string for a protocol
+	 *   match. Ex: 'http://yahoo.com'. This is used to know whether or not we
+	 *   have a protocol in the URL string, in order to check for a word
+	 *   character after the protocol separator (':').
+	 * @return {Boolean} `true` if the URL match does not have at least one word
+	 *   character in it after the protocol, `false` otherwise.
 	 */
@@ -159,14 +180,17 @@ urlMatchDoesNotHaveAtLeastOneWordChar : function( urlMatch, protocolUrlMatch ) {
 	},
-	
-	
+
+
 	/**
-	 * Determines if a protocol-relative match is an invalid one. This method returns `true` if there is a `protocolRelativeMatch`,
-	 * and that match contains a word character before the '//' (i.e. it must contain whitespace or nothing before the '//' in
-	 * order to be considered valid).
-	 * 
+	 * Determines if a protocol-relative match is an invalid one. This method
+	 * returns `true` if there is a `protocolRelativeMatch`, and that match
+	 * contains a word character before the '//' (i.e. it must contain
+	 * whitespace or nothing before the '//' in order to be considered valid).
+	 *
 	 * @private
-	 * @param {String} protocolRelativeMatch The protocol-relative string for a URL match (i.e. '//'), possibly with a preceding
-	 *   character (ex, a space, such as: ' //', or a letter, such as: 'a//'). The match is invalid if there is a word character
-	 *   preceding the '//'.
-	 * @return {Boolean} `true` if it is an invalid protocol-relative match, `false` otherwise.
+	 * @param {String} protocolRelativeMatch The protocol-relative string for a
+	 *   URL match (i.e. '//'), possibly with a preceding character (ex, a
+	 *   space, such as: ' //', or a letter, such as: 'a//'). The match is
+	 *   invalid if there is a word character preceding the '//'.
+	 * @return {Boolean} `true` if it is an invalid protocol-relative match,
+	 *   `false` otherwise.
 	 */
@@ -173,0 +197,0 @@ isInvalidProtocolRelativeMatch : function( protocolRelativeMatch ) {

src/Util.js

@@ -6,18 +6,28 @@ /*global Autolinker */
  * @singleton
- * 
+ *
  * A few utility methods for Autolinker.
  */
 Autolinker.Util = {
-	
+
 	/**
 	 * @property {Function} abstractMethod
-	 * 
+	 *
 	 * A function object which represents an abstract method.
 	 */
 	abstractMethod : function() { throw "abstract"; },
-	
-	
+
+
 	/**
+	 * @private
+	 * @property {RegExp} trimRegex
+	 *
+	 * The regular expression used to trim the leading and trailing whitespace
+	 * from a string.
+	 */
+	trimRegex : /^[\s\uFEFF\xA0]+|[\s\uFEFF\xA0]+$/g,
+
+
+	/**
 	 * Assigns (shallow copies) the properties of `src` onto `dest`.
-	 * 
+	 *
 	 * @param {Object} dest The destination object.
@@ -33,10 +43,10 @@ * @param {Object} src The source object.
 		}
-		
+
 		return dest;
 	},
-	
-	
+
+
 	/**
 	 * Extends `superclass` to create a new subclass, adding the `protoProps` to the new subclass's prototype.
-	 * 
+	 *
 	 * @param {Function} superclass The constructor function for the superclass.
@@ -49,6 +59,6 @@ * @param {Object} protoProps The methods/properties to add to the subclass's prototype. This may contain the
 		var superclassProto = superclass.prototype;
-		
+
 		var F = function() {};
 		F.prototype = superclassProto;
-		
+
 		var subclass;
@@ -60,19 +70,19 @@ if( protoProps.hasOwnProperty( 'constructor' ) ) {
 		}
-		
+
 		var subclassProto = subclass.prototype = new F();  // set up prototype chain
 		subclassProto.constructor = subclass;  // fix constructor property
 		subclassProto.superclass = superclassProto;
-		
+
 		delete protoProps.constructor;  // don't re-assign constructor property to the prototype, since a new function may have been created (`subclass`), which is now already there
 		Autolinker.Util.assign( subclassProto, protoProps );
-		
+
 		return subclass;
 	},
-	
-	
+
+
 	/**
 	 * Truncates the `str` at `len - ellipsisChars.length`, and adds the `ellipsisChars` to the
-	 * end of the string (by default, two periods: '..'). If the `str` length does not exceed 
+	 * end of the string (by default, two periods: '..'). If the `str` length does not exceed
 	 * `len`, the string will be returned unchanged.
-	 * 
+	 *
 	 * @param {String} str The string to truncate and add an ellipsis to.
@@ -90,7 +100,7 @@ * @param {Number} truncateLen The length to truncate the string at.
 	},
-	
-	
+
+
 	/**
 	 * Supports `Array.prototype.indexOf()` functionality for old IE (IE8 and below).
-	 * 
+	 *
 	 * @param {Array} arr The array to find an element of.
@@ -103,3 +113,3 @@ * @param {*} element The element to find in the array, and return the index of.
 			return arr.indexOf( element );
-			
+
 		} else {
@@ -112,25 +122,25 @@ for( var i = 0, len = arr.length; i < len; i++ ) {
 	},
-	
-	
-	
+
+
+
 	/**
 	 * Performs the functionality of what modern browsers do when `String.prototype.split()` is called
 	 * with a regular expression that contains capturing parenthesis.
-	 * 
+	 *
 	 * For example:
-	 * 
-	 *     // Modern browsers: 
+	 *
+	 *     // Modern browsers:
 	 *     "a,b,c".split( /(,)/ );  // --> [ 'a', ',', 'b', ',', 'c' ]
-	 *     
+	 *
 	 *     // Old IE (including IE8):
 	 *     "a,b,c".split( /(,)/ );  // --> [ 'a', 'b', 'c' ]
-	 *     
+	 *
 	 * This method emulates the functionality of modern browsers for the old IE case.
-	 * 
+	 *
 	 * @param {String} str The string to split.
 	 * @param {RegExp} splitRegex The regular expression to split the input `str` on. The splitting
-	 *   character(s) will be spliced into the array, as in the "modern browsers" example in the 
-	 *   description of this method. 
+	 *   character(s) will be spliced into the array, as in the "modern browsers" example in the
+	 *   description of this method.
 	 *   Note #1: the supplied regular expression **must** have the 'g' flag specified.
-	 *   Note #2: for simplicity's sake, the regular expression does not need 
+	 *   Note #2: for simplicity's sake, the regular expression does not need
 	 *   to contain capturing parenthesis - it will be assumed that any match has them.
@@ -141,18 +151,29 @@ * @return {String[]} The split array of strings, with the splitting character(s) included.
 		if( !splitRegex.global ) throw new Error( "`splitRegex` must have the 'g' flag set" );
-		
+
 		var result = [],
 		    lastIdx = 0,
 		    match;
-		
+
 		while( match = splitRegex.exec( str ) ) {
 			result.push( str.substring( lastIdx, match.index ) );
 			result.push( match[ 0 ] );  // push the splitting char(s)
-			
+
 			lastIdx = match.index + match[ 0 ].length;
 		}
 		result.push( str.substring( lastIdx ) );
-		
+
 		return result;
+	},
+
+
+	/**
+	 * Trims the leading and trailing whitespace from a string.
+	 *
+	 * @param {String} str The string to trim.
+	 * @return {String}
+	 */
+	trim : function( str ) {
+		return str.replace( this.trimRegex, '' );
 	}
-	
+
 };

tests/htmlParser/HtmlParserSpec.js

 /*global Autolinker, _, describe, beforeEach, afterEach, it, expect, jasmine */
 describe( "Autolinker.htmlParser.HtmlParser", function() {
 	var HtmlParser = Autolinker.htmlParser.HtmlParser,
+	    CommentNode = Autolinker.htmlParser.CommentNode,
 	    ElementNode = Autolinker.htmlParser.ElementNode,
@@ -8,9 +9,15 @@ EntityNode = Autolinker.htmlParser.EntityNode,
 	    htmlParser;
-	
-	
+
+
 	beforeEach( function() {
 		htmlParser = new HtmlParser();
 	} );
-	
-	
+
+
+	function expectCommentNode( node, text, comment ) {
+		expect( node ).toEqual( jasmine.any( CommentNode ) );
+		expect( node.getText() ).toBe( text );
+		expect( node.getComment() ).toBe( comment );
+	}
+
 	function expectElementNode( node, tagText, tagName, isClosingTag ) {
@@ -22,3 +29,3 @@ expect( node ).toEqual( jasmine.any( ElementNode ) );
 	}
-	
+
 	function expectEntityNode( node, text ) {
@@ -28,3 +35,3 @@ expect( node ).toEqual( jasmine.any( EntityNode ) );
 	}
-	
+
 	function expectTextNode( node, text ) {
@@ -34,142 +41,233 @@ expect( node ).toEqual( jasmine.any( TextNode ) );
 	}
-	
-	
+
+
 	it( "should return an empty array for an empty input string", function() {
 		expect( htmlParser.parse( "" ) ).toEqual( [] );
 	} );
-	
-	
-	it( "should be able to reproduce the input string based on the text that was provided to each returned `HtmlNode`", function() {
-		var inputStr = 'Joe went to <a href="google.com">ebay.com</a> today,&nbsp;and bought <b>big</b> items',
-		    nodes = htmlParser.parse( inputStr ),
-		    result = [];
-		
-		for( var i = 0, len = nodes.length; i < len; i++ ) {
-			result.push( nodes[ i ].getText() );
-		}
-		
-		expect( result.length ).toBe( 11 );
-		expect( result.join( "" ) ).toBe( inputStr );
+
+
+	describe( 'text node handling', function() {
+
+		it( "should return a single text node if there are no HTML nodes in it", function() {
+			var nodes = htmlParser.parse( "Testing 123" );
+
+			expect( nodes.length ).toBe( 1 );
+			expectTextNode( nodes[ 0 ], 'Testing 123' );
+		} );
+
 	} );
-	
-	
-	it( "should properly create `HtmlNode` instances for each text/entity/element node encountered, with the proper data filled in on each node", function() {
-		var inputStr = '&quot;Joe went to &quot;<a href="google.com">ebay.com</a>&quot; today,&nbsp;and bought <b>big</b> items&quot;',
-		    nodes = htmlParser.parse( inputStr );
-		
-		expect( nodes.length ).toBe( 15 );
-		
-		var i = -1;
-		expectEntityNode ( nodes[ ++i ], '&quot;' );
-		expectTextNode   ( nodes[ ++i ], 'Joe went to ' );
-		expectEntityNode ( nodes[ ++i ], '&quot;' );
-		expectElementNode( nodes[ ++i ], '<a href="google.com">', 'a', false );
-		expectTextNode   ( nodes[ ++i ], 'ebay.com' );
-		expectElementNode( nodes[ ++i ], '</a>', 'a', true );
-		expectEntityNode ( nodes[ ++i ], '&quot;' );
-		expectTextNode   ( nodes[ ++i ], ' today,' );
-		expectEntityNode ( nodes[ ++i ], '&nbsp;' );
-		expectTextNode   ( nodes[ ++i ], 'and bought ' );
-		expectElementNode( nodes[ ++i ], '<b>', 'b', false );
-		expectTextNode   ( nodes[ ++i ], 'big' );
-		expectElementNode( nodes[ ++i ], '</b>', 'b', true );
-		expectTextNode   ( nodes[ ++i ], ' items' );
-		expectEntityNode ( nodes[ ++i ], '&quot;' );
+
+
+	describe( 'HTML comment node handling', function() {
+
+		it( "should return a single comment node if there is only an HTML comment node in it", function() {
+			var nodes = htmlParser.parse( "<!-- Testing 123 -->" );
+
+			expect( nodes.length ).toBe( 1 );
+			expectCommentNode( nodes[ 0 ], "<!-- Testing 123 -->", "Testing 123" );
+		} );
+
+
+		it( "should handle a multi-line comment, and trim any amount of whitespace in the comment for the comment's text", function() {
+			var nodes = htmlParser.parse( "<!-- \n  \t\n Testing 123  \n\t  \n\n -->" );
+
+			expect( nodes.length ).toBe( 1 );
+			expectCommentNode( nodes[ 0 ], "<!-- \n  \t\n Testing 123  \n\t  \n\n -->", "Testing 123" );
+		} );
+
+
+		it( "should produce 3 nodes for a text node, comment, then text node", function() {
+			var nodes = htmlParser.parse( "Test <!-- Comment --> Test" );
+
+			expect( nodes.length ).toBe( 3 );
+			expectTextNode   ( nodes[ 0 ], 'Test ' );
+			expectCommentNode( nodes[ 1 ], '<!-- Comment -->', 'Comment' );
+			expectTextNode   ( nodes[ 2 ], ' Test' );
+		} );
+
+
+		it( "should produce 4 nodes for a text node, comment, text node, comment", function() {
+			var nodes = htmlParser.parse( "Test <!-- Comment --> Test <!-- Comment 2 -->" );
+
+			expect( nodes.length ).toBe( 4 );
+			expectTextNode   ( nodes[ 0 ], 'Test ' );
+			expectCommentNode( nodes[ 1 ], '<!-- Comment -->', 'Comment' );
+			expectTextNode   ( nodes[ 2 ], ' Test ' );
+			expectCommentNode( nodes[ 3 ], '<!-- Comment 2 -->', 'Comment 2' );
+		} );
+
 	} );
-	
-	
-	it( 'should match tags of both upper and lower case', function() {
-		var inputStr = 'Joe <!DOCTYPE html> went <!doctype "blah" "blah blah"> to <a href="google.com">ebay.com</a> today,&nbsp;and <A href="purchase.com">purchased</A> <b>big</b> <B>items</B>',
-		    nodes = htmlParser.parse( inputStr );
-		
-		expect( nodes.length ).toBe( 22 );
-		
-		var i = -1;
-		expectTextNode   ( nodes[ ++i ], 'Joe ' );
-		expectElementNode( nodes[ ++i ], '<!DOCTYPE html>', '!doctype', false );
-		expectTextNode   ( nodes[ ++i ], ' went ' );
-		expectElementNode( nodes[ ++i ], '<!doctype "blah" "blah blah">', '!doctype', false );
-		expectTextNode   ( nodes[ ++i ], ' to ' );
-		expectElementNode( nodes[ ++i ], '<a href="google.com">', 'a', false );
-		expectTextNode   ( nodes[ ++i ], 'ebay.com' );
-		expectElementNode( nodes[ ++i ], '</a>', 'a', true );
-		expectTextNode   ( nodes[ ++i ], ' today,' );
-		expectEntityNode ( nodes[ ++i ], '&nbsp;' );
-		expectTextNode   ( nodes[ ++i ], 'and ' );
-		expectElementNode( nodes[ ++i ], '<A href="purchase.com">', 'a', false );
-		expectTextNode   ( nodes[ ++i ], 'purchased' );
-		expectElementNode( nodes[ ++i ], '</A>', 'a', true );
-		expectTextNode   ( nodes[ ++i ], ' ' );
-		expectElementNode( nodes[ ++i ], '<b>', 'b', false );
-		expectTextNode   ( nodes[ ++i ], 'big' );
-		expectElementNode( nodes[ ++i ], '</b>', 'b', true );
-		expectTextNode   ( nodes[ ++i ], ' ' );
-		expectElementNode( nodes[ ++i ], '<B>', 'b', false );
-		expectTextNode   ( nodes[ ++i ], 'items' );
-		expectElementNode( nodes[ ++i ], '</B>', 'b', true );
+
+
+	describe( 'HTML element node handling', function() {
+
+		it( "should return a single element node if there is only an HTML element node in it", function() {
+			var nodes = htmlParser.parse( "<div>" );
+
+			expect( nodes.length ).toBe( 1 );
+			expectElementNode( nodes[ 0 ], '<div>', 'div', false );
+		} );
+
+
+		it( "should produce 3 nodes for a text node, element, then text node", function() {
+			var nodes = htmlParser.parse( "Test <div> Test" );
+
+			expect( nodes.length ).toBe( 3 );
+			expectTextNode   ( nodes[ 0 ], 'Test ' );
+			expectElementNode( nodes[ 1 ], '<div>', 'div', false );
+			expectTextNode   ( nodes[ 2 ], ' Test' );
+		} );
+
+
+		it( "should be able to reproduce the input string based on the text that was provided to each returned `HtmlNode`", function() {
+			var inputStr = 'Joe went to <a href="google.com">ebay.com</a> today,&nbsp;and bought <b>big</b> items',
+				nodes = htmlParser.parse( inputStr ),
+				result = [];
+
+			for( var i = 0, len = nodes.length; i < len; i++ ) {
+				result.push( nodes[ i ].getText() );
+			}
+
+			expect( result.length ).toBe( 11 );
+			expect( result.join( "" ) ).toBe( inputStr );
+		} );
+
 	} );
-	
-	
-	it( "should *not* match the &amp; HTML entity, as this may be part of a query string", function() {
-		var nodes = htmlParser.parse( 'Me&amp;You' );
-		
-		expect( nodes.length ).toBe( 1 );
-		expectTextNode( nodes[ 0 ], 'Me&amp;You' );
+
+
+	describe( 'HTML entity handling', function() {
+
+		it( "should *not* match the &amp; HTML entity, as this may be part of a query string", function() {
+			var nodes = htmlParser.parse( 'Me&amp;You' );
+
+			expect( nodes.length ).toBe( 1 );
+			expectTextNode( nodes[ 0 ], 'Me&amp;You' );
+		} );
+
+
+		it( "should properly parse a string that begins with an HTML entity node", function() {
+			var nodes = htmlParser.parse( '&quot;Test' );
+
+			expect( nodes.length ).toBe( 2 );
+			expectEntityNode( nodes[ 0 ], '&quot;' );
+			expectTextNode( nodes[ 1 ], 'Test' );
+		} );
+
+
+		it( "should properly parse a string that ends with an HTML entity node", function() {
+			var nodes = htmlParser.parse( 'Test&quot;' );
+
+			expect( nodes.length ).toBe( 2 );
+			expectTextNode( nodes[ 0 ], 'Test' );
+			expectEntityNode( nodes[ 1 ], '&quot;' );
+		} );
+
+
+		it( "should properly parse a string that begins and ends with an HTML entity node", function() {
+			var nodes = htmlParser.parse( '&quot;Test&quot;' );
+
+			expect( nodes.length ).toBe( 3 );
+			expectEntityNode( nodes[ 0 ], '&quot;' );
+			expectTextNode( nodes[ 1 ], 'Test' );
+			expectEntityNode( nodes[ 2 ], '&quot;' );
+		} );
+
+
+		it( "should properly parse a string that has an HTML entity node in the middle", function() {
+			var nodes = htmlParser.parse( 'Test&quot;Test' );
+
+			expect( nodes.length ).toBe( 3 );
+			expectTextNode( nodes[ 0 ], 'Test' );
+			expectEntityNode( nodes[ 1 ], '&quot;' );
+			expectTextNode( nodes[ 2 ], 'Test' );
+		} );
+
+
+		it( "should properly parse a string that only has an HTML entity node", function() {
+			var nodes = htmlParser.parse( '&quot;' );
+
+			expect( nodes.length ).toBe( 1 );
+			expectEntityNode( nodes[ 0 ], '&quot;' );
+		} );
+
 	} );
-	
-	
-	it( "should properly parse a string that begins with an HTML entity node", function() {
-		var nodes = htmlParser.parse( '&quot;Test' );
-		
-		expect( nodes.length ).toBe( 2 );
-		expectEntityNode( nodes[ 0 ], '&quot;' );
-		expectTextNode( nodes[ 1 ], 'Test' );
+
+
+	describe( 'combination examples', function() {
+
+		it( "should properly create `HtmlNode` instances for each text/entity/comment/element node encountered, with the proper data filled in on each node", function() {
+			var inputStr = [
+				'&quot;Joe went to &quot;',
+				'<a href="google.com">ebay.com</a>&quot; ',
+				'today,&nbsp;and <!-- stuff -->bought <b>big</b> items&quot;'
+			].join( "" );
+
+			var nodes = htmlParser.parse( inputStr );
+			expect( nodes.length ).toBe( 17 );
+
+			var i = -1;
+			expectEntityNode ( nodes[ ++i ], '&quot;' );
+			expectTextNode   ( nodes[ ++i ], 'Joe went to ' );
+			expectEntityNode ( nodes[ ++i ], '&quot;' );
+			expectElementNode( nodes[ ++i ], '<a href="google.com">', 'a', false );
+			expectTextNode   ( nodes[ ++i ], 'ebay.com' );
+			expectElementNode( nodes[ ++i ], '</a>', 'a', true );
+			expectEntityNode ( nodes[ ++i ], '&quot;' );
+			expectTextNode   ( nodes[ ++i ], ' today,' );
+			expectEntityNode ( nodes[ ++i ], '&nbsp;' );
+			expectTextNode   ( nodes[ ++i ], 'and ' );
+			expectCommentNode( nodes[ ++i ], '<!-- stuff -->', 'stuff' );
+			expectTextNode   ( nodes[ ++i ], 'bought ' );
+			expectElementNode( nodes[ ++i ], '<b>', 'b', false );
+			expectTextNode   ( nodes[ ++i ], 'big' );
+			expectElementNode( nodes[ ++i ], '</b>', 'b', true );
+			expectTextNode   ( nodes[ ++i ], ' items' );
+			expectEntityNode ( nodes[ ++i ], '&quot;' );
+		} );
+
+
+		it( 'should match tags of both upper and lower case', function() {
+			var inputStr = 'Joe <!DOCTYPE html><!-- Comment -->went <!doctype "blah" "blah blah"> to <a href="google.com">ebay.com</a> today,&nbsp;and <A href="purchase.com">purchased</A> <b>big</b> <B><!-- Comment 2 -->items</B>',
+			    nodes = htmlParser.parse( inputStr );
+
+			expect( nodes.length ).toBe( 24 );
+
+			var i = -1;
+			expectTextNode   ( nodes[ ++i ], 'Joe ' );
+			expectElementNode( nodes[ ++i ], '<!DOCTYPE html>', '!doctype', false );
+			expectCommentNode( nodes[ ++i ], '<!-- Comment -->', 'Comment' );
+			expectTextNode   ( nodes[ ++i ], 'went ' );
+			expectElementNode( nodes[ ++i ], '<!doctype "blah" "blah blah">', '!doctype', false );
+			expectTextNode   ( nodes[ ++i ], ' to ' );
+			expectElementNode( nodes[ ++i ], '<a href="google.com">', 'a', false );
+			expectTextNode   ( nodes[ ++i ], 'ebay.com' );
+			expectElementNode( nodes[ ++i ], '</a>', 'a', true );
+			expectTextNode   ( nodes[ ++i ], ' today,' );
+			expectEntityNode ( nodes[ ++i ], '&nbsp;' );
+			expectTextNode   ( nodes[ ++i ], 'and ' );
+			expectElementNode( nodes[ ++i ], '<A href="purchase.com">', 'a', false );
+			expectTextNode   ( nodes[ ++i ], 'purchased' );
+			expectElementNode( nodes[ ++i ], '</A>', 'a', true );
+			expectTextNode   ( nodes[ ++i ], ' ' );
+			expectElementNode( nodes[ ++i ], '<b>', 'b', false );
+			expectTextNode   ( nodes[ ++i ], 'big' );
+			expectElementNode( nodes[ ++i ], '</b>', 'b', true );
+			expectTextNode   ( nodes[ ++i ], ' ' );
+			expectElementNode( nodes[ ++i ], '<B>', 'b', false );
+			expectCommentNode( nodes[ ++i ], '<!-- Comment 2 -->', 'Comment 2' );
+			expectTextNode   ( nodes[ ++i ], 'items' );
+			expectElementNode( nodes[ ++i ], '</B>', 'b', true );
+		} );
+
 	} );
-	
-	
-	it( "should properly parse a string that ends with an HTML entity node", function() {
-		var nodes = htmlParser.parse( 'Test&quot;' );
-		
-		expect( nodes.length ).toBe( 2 );
-		expectTextNode( nodes[ 0 ], 'Test' );
-		expectEntityNode( nodes[ 1 ], '&quot;' );
-	} );
-	
-	
-	it( "should properly parse a string that begins and ends with an HTML entity node", function() {
-		var nodes = htmlParser.parse( '&quot;Test&quot;' );
-		
-		expect( nodes.length ).toBe( 3 );
-		expectEntityNode( nodes[ 0 ], '&quot;' );
-		expectTextNode( nodes[ 1 ], 'Test' );
-		expectEntityNode( nodes[ 2 ], '&quot;' );
-	} );
-	
-	
-	it( "should properly parse a string that has an HTML entity node in the middle", function() {
-		var nodes = htmlParser.parse( 'Test&quot;Test' );
-		
-		expect( nodes.length ).toBe( 3 );
-		expectTextNode( nodes[ 0 ], 'Test' );
-		expectEntityNode( nodes[ 1 ], '&quot;' );
-		expectTextNode( nodes[ 2 ], 'Test' );
-	} );
-	
-	
-	it( "should properly parse a string that only has an HTML entity node", function() {
-		var nodes = htmlParser.parse( '&quot;' );
-		
-		expect( nodes.length ).toBe( 1 );
-		expectEntityNode( nodes[ 0 ], '&quot;' );
-	} );
-	
-	
+
+
 	it( "should not freeze up the regular expression engine when presented with the input string in issue #54", function() {
 		var inputStr = "Shai ist endlich in Deutschland! Und wir haben gute Nachrichten! <3 Alle, die den Shai-Rasierer kostenlos probieren, machen am Gewinnspiel eines Jahresvorrates Klingen mit. Den Rasierer bekommst Du kostenlos durch diesen Link: http://dorcoshai.de/pb1205ro, und dann machst Du am Gewinnspiel mit! 'Gefallt mir' klicken, wenn Du gern einen Jahresvorrat Shai haben mochtest. (Y)",
 		    nodes = htmlParser.parse( inputStr );
-		
+
 		expect( nodes.length ).toBe( 1 );
 		expectTextNode( nodes[ 0 ], inputStr );
 	} );
-	
+
 } );

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Mixed license

License

(Experimental) Package contains multiple licenses.

Found 1 instance in 1 package

Unidentified License

License

(Experimental) Something that seems like a license was found, but its contents could not be matched with a known license.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

3348054

increased by1000.1%

Number of package files

494

increased by1443.75%

Lines of code

6761

increased by10.96%

Worsened metrics

Number of low license alerts

2

increased byInfinity%

License quality

80

decreased by-20%

No dependency changes