RESplit() - Splitting Strings With Regular Expressions In ColdFusion

code-1.cfm

<cffunction
	name="reSplit"
	access="public"
	returntype="array"
	output="false"
	hint="I split the given string using the given Java regular expression.">

	<!--- Define arguments. --->
	<cfargument
		name="regex"
		type="string"
		required="true"
		hint="I am the regular expression being used to split the string."
		/>

	<cfargument
		name="value"
		type="string"
		required="true"
		hint="I am the string being split."
		/>

	<!--- Define the local scope. --->
	<cfset var local = {} />

	<!---
		Get the split functionality from the core Java script. I am
		using JavaCast here as a way to alleviate the fact that I'm
		using *undocumented* functionality... sort of.

		The -1 argument tells the split() method to include trailing
		parts that are empty.
	--->
	<cfset local.parts = javaCast( "string", arguments.value ).split(
		javaCast( "string", arguments.regex ),
		javaCast( "int", -1 )
		) />

	<!---
		We now have the individual parts; however, the split()
		method does not return a ColdFusion array - it returns a
		typed String[] array. We now have to convert that to a
		standard ColdFusion array.
	--->
	<cfset local.result = [] />

	<!--- Loop over the parts and append them to the results. --->
	<cfloop
		index="local.part"
		array="#local.parts#">

		<cfset arrayAppend( local.result, local.part ) />

	</cfloop>

	<!--- Return the result. --->
	<cfreturn local.result />
</cffunction>



<!--- ----------------------------------------------------- --->
<!--- ----------------------------------------------------- --->
<!--- ----------------------------------------------------- --->
<!--- ----------------------------------------------------- --->



<!--- Create a list of values in which some are empty. --->
<cfset womenList = ",Katie,,Jill,Sarah," />

<!--- Split this list, using the comma as our pattern. --->
<cfset women = reSplit( ",", womenList ) />

<!--- Output the resultant collection. --->
<cfdump
	var="#women#"
	label="reSplit() Women"
	/>

code-2.cfm

<!--- Define the tab for our field delimiter. --->
<cfset tab = chr( 9 ) />

<!--- Define our tab-delimited data. --->
<cfsavecontent variable="csvData">
<cfoutput>
Name#tab#Age#tab#Hair
Katie#tab#29#tab#Brown
<!--- Totally empty row. --->
Jill#tab##tab#Brown
#tab##tab#
Sarah#tab#33#tab#
</cfoutput>
</cfsavecontent>


<!---
	Remove non-relevant white space - ie. remove the leading or
	trailing line breaks, but do not remove any TABS.
--->
<cfset csvData = reReplace(
	csvData,
	"^[\r\n]+|[\r\n]+$",
	"",
	"all"
	) />


<!--- Get the rows using the line breaks. --->
<cfset rows = reSplit( "\r\n?|\n", csvData ) />

<!---
	Now that we have the rows, loop over them and split each row
	value by the tab-delimiter. This will result in an array of
	arrays.
--->
<cfloop
	index="rowIndex"
	from="1"
	to="#arrayLen( rows )#"
	step="1">

	<!---
		Convert the row data to an array of field values (as
		delimited by Tabs).
	--->
	<cfset rows[ rowIndex ] = reSplit( tab, rows[ rowIndex ] ) />

</cfloop>

<!--- Output our resultant CSV data. --->
<cfdump
	var="#rows#"
	label="Parsed CSV Data"
	/>