incorporating Markdown decoding, fixes #150

Author: Zirak

master.js

@@ -102,7 +102,49 @@ var IO = window.IO = {
 	}
 };
 
-IO.decodehtmlEntities = (function (){
+//turns some html tags into markdown. a major assumption is that the input is
+// properly sanitised - that is, all <, &, etc entered by the user got turned
+// into html entities.
+IO.htmlToMarkdown = (function () {
+
+// A string value is the delimiter (what replaces the tag)
+var markdown = {
+	i : '*',
+	b : '**',
+	strike : '---',
+	code : '`',
+
+	a : function ( $0, $1, text ) {
+		var href = /href="([^"]+?)"/.exec( $0 );
+
+		if ( !href ) {
+			return $0;
+		}
+		return '[' + text + '](' + href[1] + ')';
+	},
+};
+var htmlRe = /<(\S+)[^\>]*>([^<]+)<\/\1>/g;
+
+return function ( html ) {
+	var delim;
+
+	return html.replace( htmlRe, decodeHtml );
+
+	function decodeHtml ( $0, tag, text ) {
+		if ( !markdown.hasOwnProperty(tag) ) {
+			return $0;
+		}
+
+		delim = markdown[ tag ];
+
+		return delim.apply ?
+			markdown[ tag ].apply( markdown, arguments ) :
+			delim + text + delim;
+	}
+};
+}());
+
+IO.decodehtmlEntities = (function () {
 var entities; //will be filled in the following line
 entities = {"quot":"\"","amp":"&","apos":"'","lt":"<","gt":">","nbsp":" ","iexcl":"¡","cent":"¢","pound":"£","curren":"¤","yen":"¥","brvbar":"¦","sect":"§","uml":"¨","copy":"©","ordf":"ª","laquo":"«","not":"¬","reg":"®","macr":"¯","deg":"°","plusmn":"±","sup2":"²","sup3":"³","acute":"´","micro":"µ","para":"¶","middot":"·","cedil":"¸","sup1":"¹","ordm":"º","raquo":"»","frac14":"¼","frac12":"½","frac34":"¾","iquest":"¿","Agrave":"À","Aacute":"Á","Acirc":"Â","Atilde":"Ã","Auml":"Ä","Aring":"Å","AElig":"Æ","Ccedil":"Ç","Egrave":"È","Eacute":"É","Ecirc":"Ê","Euml":"Ë","Igrave":"Ì","Iacute":"Í","Icirc":"Î","Iuml":"Ï","ETH":"Ð","Ntilde":"Ñ","Ograve":"Ò","Oacute":"Ó","Ocirc":"Ô","Otilde":"Õ","Ouml":"Ö","times":"×","Oslash":"Ø","Ugrave":"Ù","Uacute":"Ú","Ucirc":"Û","Uuml":"Ü","Yacute":"Ý","THORN":"Þ","szlig":"ß","agrave":"à","aacute":"á","acirc":"â","atilde":"ã","auml":"ä","aring":"å","aelig":"æ","ccedil":"ç","egrave":"è","eacute":"é","ecirc":"ê","euml":"ë","igrave":"ì","iacute":"í","icirc":"î","iuml":"ï","eth":"ð","ntilde":"ñ","ograve":"ò","oacute":"ó","ocirc":"ô","otilde":"õ","ouml":"ö","divide":"÷","oslash":"ø","ugrave":"ù","uacute":"ú","ucirc":"û","uuml":"ü","yacute":"ý","thorn":"þ","yuml":"ÿ","OElig":"Œ","oelig":"œ","Scaron":"Š","scaron":"š","Yuml":"Ÿ","fnof":"ƒ","circ":"ˆ","tilde":"˜","Alpha":"Α","Beta":"Β","Gamma":"Γ","Delta":"Δ","Epsilon":"Ε","Zeta":"Ζ","Eta":"Η","Theta":"Θ","Iota":"Ι","Kappa":"Κ","Lambda":"Λ","Mu":"Μ","Nu":"Ν","Xi":"Ξ","Omicron":"Ο","Pi":"Π","Rho":"Ρ","Sigma":"Σ","Tau":"Τ","Upsilon":"Υ","Phi":"Φ","Chi":"Χ","Psi":"Ψ","Omega":"Ω","alpha":"α","beta":"β","gamma":"γ","delta":"δ","epsilon":"ε","zeta":"ζ","eta":"η","theta":"θ","iota":"ι","kappa":"κ","lambda":"λ","mu":"μ","nu":"ν","xi":"ξ","omicron":"ο","pi":"π","rho":"ρ","sigmaf":"ς","sigma":"σ","tau":"τ","upsilon":"υ","phi":"φ","chi":"χ","psi":"ψ","omega":"ω","thetasym":"ϑ","upsih":"ϒ","piv":"ϖ","ensp":" ","emsp":" ","thinsp":" ","ndash":"–","mdash":"—","lsquo":"‘","rsquo":"’","sbquo":"‚","ldquo":"“","rdquo":"”","bdquo":"„","dagger":"†","Dagger":"‡","bull":"•","hellip":"…","permil":"‰","prime":"′","Prime":"″","lsaquo":"‹","rsaquo":"›","oline":"‾","frasl":"⁄","euro":"€","image":"ℑ","weierp":"℘","real":"ℜ","trade":"™","alefsym":"ℵ","larr":"←","uarr":"↑","rarr":"→","darr":"↓","harr":"↔","crarr":"↵","lArr":"⇐","uArr":"⇑","rArr":"⇒","dArr":"⇓","hArr":"⇔","forall":"∀","part":"∂","exist":"∃","empty":"∅","nabla":"∇","isin":"∈","notin":"∉","ni":"∋","prod":"∏","sum":"∑","minus":"−","lowast":"∗","radic":"√","prop":"∝","infin":"∞","ang":"∠","and":"∧","or":"∨","cap":"∩","cup":"∪","int":"∫","there4":"∴","sim":"∼","cong":"≅","asymp":"≈","ne":"≠","equiv":"≡","le":"≤","ge":"≥","sub":"⊂","sup":"⊃","nsub":"⊄","sube":"⊆","supe":"⊇","oplus":"⊕","otimes":"⊗","perp":"⊥","sdot":"⋅","lceil":"⌈","rceil":"⌉","lfloor":"⌊","rfloor":"⌋","lang":"〈","rang":"〉","loz":"◊","spades":"♠","clubs":"♣","hearts":"♥","diams":"♦", "zwnj":"", "zwsp":""};
 
@@ -791,7 +833,10 @@ var bot = window.bot = {
 	prepareMessage : function ( msgObj ) {
 		msgObj = this.adapter.transform( msgObj );
 
-		var msg = IO.decodehtmlEntities( msgObj.content );
+		//decode markdown and html entities.
+		var msg = IO.htmlToMarkdown( msgObj.content ); //#150
+		msg = IO.decodehtmlEntities( msg );
+
 		//fixes issues #87 and #90 globally
 		msg = msg.replace( /\u200b|\u200c/g, '' );
 

master.min.js

@@ -102,7 +102,49 @@ var IO = window.IO = {
 	}
 };
 
-IO.decodehtmlEntities = (function (){
+//turns some html tags into markdown. a major assumption is that the input is
+// properly sanitised - that is, all <, &, etc entered by the user got turned
+// into html entities.
+IO.htmlToMarkdown = (function () {
+
+// A string value is the delimiter (what replaces the tag)
+var markdown = {
+	i : '*',
+	b : '**',
+	strike : '---',
+	code : '`',
+
+	a : function ( $0, $1, text ) {
+		var href = /href="([^"]+?)"/.exec( $0 );
+
+		if ( !href ) {
+			return $0;
+		}
+		return '[' + text + '](' + href[1] + ')';
+	},
+};
+var htmlRe = /<(\S+)[^\>]*>([^<]+)<\/\1>/g;
+
+return function ( html ) {
+	var delim;
+
+	return html.replace( htmlRe, decodeHtml );
+
+	function decodeHtml ( $0, tag, text ) {
+		if ( !markdown.hasOwnProperty(tag) ) {
+			return $0;
+		}
+
+		delim = markdown[ tag ];
+
+		return delim.apply ?
+			markdown[ tag ].apply( markdown, arguments ) :
+			delim + text + delim;
+	}
+};
+}());
+
+IO.decodehtmlEntities = (function () {
 var entities; //will be filled in the following line
 //#build static/htmlEntities.js
 

source/IO.js

@@ -135,7 +135,10 @@ var bot = window.bot = {
 	prepareMessage : function ( msgObj ) {
 		msgObj = this.adapter.transform( msgObj );
 
-		var msg = IO.decodehtmlEntities( msgObj.content );
+		//decode markdown and html entities.
+		var msg = IO.htmlToMarkdown( msgObj.content ); //#150
+		msg = IO.decodehtmlEntities( msg );
+
 		//fixes issues #87 and #90 globally
 		msg = msg.replace( /\u200b|\u200c/g, '' );