JamoCA · September 21, 2023 13:34 · briannaess · Sep 21, 2023
diff --git a/JUnidecode-ColdFusion-Demo.cfm b/JUnidecode-ColdFusion-Demo.cfm
 <cfprocessingdirective pageEncoding="utf-8">
 <cfsetting enablecfoutputonly="Yes">
 <!---
 BLOG: https://dev.to/gamesover/convert-unicode-strings-to-ascii-with-coldfusion-junidecode-lhf
 --->

 <cfscript>
 function JUnidecode(inputString){
 	var JUnidecodeLib = "";
 	var response = "";
 	var temp = {};
 	temp.encoder = createObject("java", "java.nio.charset.Charset").forName("utf-8").newEncoder();
 	temp.isUTF = temp.encoder.canEncode(arguments.inputString);
 	if (temp.isUTF){
 		/* NFKC: UTF Compatibility Decomposition, followed by Canonical Composition */
 		temp.normalizer = createObject( "java", "java.text.Normalizer" );
 		temp.normalizerForm = createObject( "java", "java.text.Normalizer$Form" );
 		arguments.inputString = temp.normalizer.normalize( javaCast( "string", arguments.inputString ), temp.normalizerForm.NFKC );
 	}
 	try {
 		JUnidecodeLib = createObject("java", "net.gcardone.junidecode.Junidecode");
 		response = JUnidecodeLib.unidecode( javacast("string", arguments.inputString) );
 	} catch (any e) {
 		response = "ERROR: JUnidecode is not installed";
 	}
 	return trim(Response.replaceAll("\[\?\]", ""));
 }
 function isDiff(compareArr, val, pos){
 	return (pos GT arrayLen(comparearr) OR comparearr[pos] neq val);
 }
 </cfscript>

 <cfset TestStrings = [
 	"ℰ𝒳𝒜ℳ𝓟ℒℰ",
 	"ABC #chr(160)# Café “test”",
 	"北亰",
 	"Mr. まさゆき たけだ",
 	"Łukasiński",
 	"⠏⠗⠑⠍⠊⠑⠗",
 	"What about Ø, Ł or æøåá",
 	"ราชอาณาจักรไทย",
 	"Ελληνικά",
 	"Москвa",
 	"Հայաստան",
 	"čeština",
 	"®™™™©©©Ⓒ½⅓⅔¼¾⅕⅖⅗⅘⅙⅚⅐⅛⅜⅝⅞⅑⅒●⚫⬤",
 	"ÀÁÂÃÄÅÆÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝàáâãäåæèéêëìíîïñòóôõöøùúûüý’“”–…",
 	"Häuser Bäume Höfe Gärten daß Ü ü ö ä Ä Ö ß "
 ]>

 <cfset CFString = "cfscript">
 <cfparam name="URL.testString" default="">
 <cfif len(trim(URL.testString))>
 	<cfset TestStrings = listToArray(trim(URL.testString))>
 </cfif>

 <cfsetting enablecfoutputonly="no">

 <!doctype html>
 <html lang="en">
 	<head>
 		<title>JUnidecode ColdFusion Demo</title>
 	</head>
 	<style>
 	.diff {background-color:#ff0;}
 	fieldset:nth-child(even) {background-color:#ededed;}
 	</style>
 	<body>
 	<h1>JUnidecode ColdFusion Demo</h1>
 	<p>by <a href="https://about.me/jamesmoberg">James Moberg</a> / <a href="https://www.sunstarmedia.com/">SunStar Media</a> (February 6, 2019)</p>
 	<p>This is a demo on how to use <a href="https://github.com/gcardone/junidecode">JUnidecode</a> with <a href="https://www.adobe.com/products/coldfusion-family.html">ColdFusion</a> to convert Unicode strings to somewhat reasonable ASCII7-only strings then strip diacritics and convert strings.</p>
 	<p>I've compared this Java library against <a href="https://www.bennadel.com/blog/1155-cleaning-high-ascii-values-for-web-safeness-in-coldfusion.htm">regex</a>, <a href="https://cflib.org/udf/deAccent">java.text.Normalizer</a>, <a href="https://gist.github.com/JamoCA/ec4617b066fc4bb601f620bc93bacb57">ICU4J Transliterate</a> (390k vs 12mb+) and <a href="https://www.codota.com/code/java/methods/org.apache.commons.lang3.StringUtils/stripAccents">Apache.Lang3.StringUtils.StripAccents()</a> (500k) and found it to generate more consistent results while safely converting more characters than other solutions.  I've also updated our <a href="https://gist.github.com/JamoCA/fee34a03bbe61a2f8e40">SanitizeFilename UDF</a> to use it.</p>
 	<p><b>Installation:</b> Download the latest <a href="https://github.com/gcardone/junidecode/releases">JUnidecode JAR</a>, place it in your java path &amp; restart your ColdFusion server (or use Javaloader).<P>
 	<p><b>Sample User-Defined Function (UDF):</b></p>
 	<cfoutput>
 		<textarea rows="7" cols="100" style="margin-left:25px;"><#CFString#>
 function JUnidecode(inputString){
    var JUnidecodeLib = createObject("java", "net.gcardone.junidecode.Junidecode");
    var response = JUnidecodeLib.unidecode( javacast("string", arguments.inputString) );
    return trim(replacenocase(Response, "[?]", "", "all"));
 }
 </#CFString#></textarea>
 	<p><b>Usage:</b></p>
 	<p style="margin-left:25px;">JUnidecode(<i>string</i>)</p>
 	<hr>
 	
 	<h2>Form Test</h2>
 	<form action="" method="get">
 		<input type="text" name="teststring" value="" required placeholder="Enter test string"> <button type="submit">Test</button><cfif len(trim(URL.TestString))> <a href="?">Reset</a></CFIF>
 	</form>
 	
 	<h2>Test Results</h2>
 	<cfloop from="1" to="#ArrayLen(TestStrings)#" index="r">
 		<cfset TestString = TestStrings[r]>
 		<cfset TestResult = JUnidecode(TestString)>
 		<cfset letters = []>
 		<fieldset>
 			<legend>#r#. #TestString#</legend>
 			<b>Result:</b> #TestResult#
 			<table border="1" cellspacing="0" cellpadding="0">
 				<tr valign="top">
 					<th>Original</th><cfloop from="1" to="#len(TestString)#" index="i">
 					<cfset Letter = mid(TestString, i, 1)>
 					<cfset arrayAppend(letters, Letter)><td><tt>#Letter#</tt><br><tt>#asc(Letter)#</tt></td></cfloop>
 				</tr>
 				<tr valign="top">
 					<th>JUnidecode</th><cfloop from="1" to="#len(TestResult)#" index="i">
 					<cfset Letter = mid(TestResult, i, 1)>
 					<td<CFIF isDiff(Letters, Letter, i)> class="diff"</cfif>><tt>#Letter#</tt><br><tt>#asc(Letter)#</tt></td></cfloop>
 				</tr>
 			</table>
 		</fieldset>
 	</cfloop>
 	</cfoutput>
 	</body>
 </html>
	<cfprocessingdirective pageEncoding="utf-8">
	<cfsetting enablecfoutputonly="Yes">
	<!---
	BLOG: https://dev.to/gamesover/convert-unicode-strings-to-ascii-with-coldfusion-junidecode-lhf
	--->

	<cfscript>
	function JUnidecode(inputString){
	var JUnidecodeLib = "";
	var response = "";
	var temp = {};
	temp.encoder = createObject("java", "java.nio.charset.Charset").forName("utf-8").newEncoder();
	temp.isUTF = temp.encoder.canEncode(arguments.inputString);
	if (temp.isUTF){
	/* NFKC: UTF Compatibility Decomposition, followed by Canonical Composition */
	temp.normalizer = createObject( "java", "java.text.Normalizer" );
	temp.normalizerForm = createObject( "java", "java.text.Normalizer$Form" );
	arguments.inputString = temp.normalizer.normalize( javaCast( "string", arguments.inputString ), temp.normalizerForm.NFKC );
	}
	try {
	JUnidecodeLib = createObject("java", "net.gcardone.junidecode.Junidecode");
	response = JUnidecodeLib.unidecode( javacast("string", arguments.inputString) );
	} catch (any e) {
	response = "ERROR: JUnidecode is not installed";
	}
	return trim(Response.replaceAll("\[\?\]", ""));
	}
	function isDiff(compareArr, val, pos){
	return (pos GT arrayLen(comparearr) OR comparearr[pos] neq val);
	}
	</cfscript>

	<cfset TestStrings = [
	"ℰ𝒳𝒜ℳ𝓟ℒℰ",
	"ABC #chr(160)# Café “test”",
	"北亰",
	"Mr. まさゆきたけだ",
	"Łukasiński",
	"⠏⠗⠑⠍⠊⠑⠗",
	"What about Ø, Ł or æøåá",
	"ราชอาณาจักรไทย",
	"Ελληνικά",
	"Москвa",
	"Հայաստան",
	"čeština",
	"®™™™©©©Ⓒ½⅓⅔¼¾⅕⅖⅗⅘⅙⅚⅐⅛⅜⅝⅞⅑⅒●⚫⬤",
	"ÀÁÂÃÄÅÆÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝàáâãäåæèéêëìíîïñòóôõöøùúûüý’“”–…",
	"Häuser Bäume Höfe Gärten daß Ü ü ö ä Ä Ö ß "
	]>

	<cfset CFString = "cfscript">
	<cfparam name="URL.testString" default="">
	<cfif len(trim(URL.testString))>
	<cfset TestStrings = listToArray(trim(URL.testString))>
	</cfif>

	<cfsetting enablecfoutputonly="no">

	<!doctype html>
	<html lang="en">
	<head>
	<title>JUnidecode ColdFusion Demo</title>
	</head>
	<style>
	.diff {background-color:#ff0;}
	fieldset:nth-child(even) {background-color:#ededed;}
	</style>
	<body>
	<h1>JUnidecode ColdFusion Demo</h1>
	<p>by <a href="https://about.me/jamesmoberg">James Moberg</a> / <a href="https://www.sunstarmedia.com/">SunStar Media</a> (February 6, 2019)</p>
	<p>This is a demo on how to use <a href="https://github.com/gcardone/junidecode">JUnidecode</a> with <a href="https://www.adobe.com/products/coldfusion-family.html">ColdFusion</a> to convert Unicode strings to somewhat reasonable ASCII7-only strings then strip diacritics and convert strings.</p>
	<p>I've compared this Java library against <a href="https://www.bennadel.com/blog/1155-cleaning-high-ascii-values-for-web-safeness-in-coldfusion.htm">regex</a>, <a href="https://cflib.org/udf/deAccent">java.text.Normalizer</a>, <a href="https://gist.github.com/JamoCA/ec4617b066fc4bb601f620bc93bacb57">ICU4J Transliterate</a> (390k vs 12mb+) and <a href="https://www.codota.com/code/java/methods/org.apache.commons.lang3.StringUtils/stripAccents">Apache.Lang3.StringUtils.StripAccents()</a> (500k) and found it to generate more consistent results while safely converting more characters than other solutions. I've also updated our <a href="https://gist.github.com/JamoCA/fee34a03bbe61a2f8e40">SanitizeFilename UDF</a> to use it.</p>
	<p><b>Installation:</b> Download the latest <a href="https://github.com/gcardone/junidecode/releases">JUnidecode JAR</a>, place it in your java path & restart your ColdFusion server (or use Javaloader).<P>
	<p><b>Sample User-Defined Function (UDF):</b></p>
	<cfoutput>
	<textarea rows="7" cols="100" style="margin-left:25px;"><#CFString#>
	function JUnidecode(inputString){
	var JUnidecodeLib = createObject("java", "net.gcardone.junidecode.Junidecode");
	var response = JUnidecodeLib.unidecode( javacast("string", arguments.inputString) );
	return trim(replacenocase(Response, "[?]", "", "all"));
	}
	</#CFString#></textarea>
	<p><b>Usage:</b></p>
	<p style="margin-left:25px;">JUnidecode(<i>string</i>)</p>
	<hr>

	<h2>Form Test</h2>
	<form action="" method="get">
	<input type="text" name="teststring" value="" required placeholder="Enter test string"> <button type="submit">Test</button><cfif len(trim(URL.TestString))> <a href="?">Reset</a></CFIF>
	</form>

	<h2>Test Results</h2>
	<cfloop from="1" to="#ArrayLen(TestStrings)#" index="r">
	<cfset TestString = TestStrings[r]>
	<cfset TestResult = JUnidecode(TestString)>
	<cfset letters = []>
	<fieldset>
	<legend>#r#. #TestString#</legend>
	<b>Result:</b> #TestResult#
	<table border="1" cellspacing="0" cellpadding="0">
	<tr valign="top">
	<th>Original</th><cfloop from="1" to="#len(TestString)#" index="i">
	<cfset Letter = mid(TestString, i, 1)>
	<cfset arrayAppend(letters, Letter)><td><tt>#Letter#</tt><br><tt>#asc(Letter)#</tt></td></cfloop>
	</tr>
	<tr valign="top">
	<th>JUnidecode</th><cfloop from="1" to="#len(TestResult)#" index="i">
	<cfset Letter = mid(TestResult, i, 1)>
	<td<CFIF isDiff(Letters, Letter, i)> class="diff"</cfif>><tt>#Letter#</tt><br><tt>#asc(Letter)#</tt></td></cfloop>
	</tr>
	</table>
	</fieldset>
	</cfloop>
	</cfoutput>
	</body>
	</html>