XSLT to copy over all nodes, and split on delimite

Question

I'm looking for an xslt that does the following:

With the input xml of, for example:

<?xml version="1.0" encoding="UTF-8"?>
<root>
    <foo1>bar1</foo1>
    <foo2>bar2^bar3^bar4</foo2>
    <foo3>bar3^bar3</foo3>
    <unknown>more data</unknown>
</root>

I want to copy all of the existing nodes to the resultant xml. I won't know what all the nodes are, i.e. I won't know that I'm receiving a foo1 node, I just want to copy them over directly. For certain nodes though, I do know what they are and I want to split them by a delimiter and number them accordingly, as below.

<?xml version="1.0" encoding="UTF-8"?>
<root>
    <foo1>bar1</foo1>
    <foo2>
        <foo2-1>bar2</foo2-1>
        <foo2-2>bar3</food2-2>
        <foo2-3>bar4</foo2-3>
    </foo2>
    <foo3>
        <foo3-1>bar3</foo3-1>
        <foo3-2>bar3</food2-2>
    </foo3>
    <unknown>more data</unknown>
</root>

Any help would be greatly appreciated.

Thanks.

Answer 1

This is fairly easy to do in XSLT 2.0:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="2.0">
    <xsl:output indent="yes"/>

 <xsl:template match="@*|node()">
     <xsl:copy>
         <xsl:apply-templates select="@*|node()"/>
     </xsl:copy>
 </xsl:template>

<xsl:template match="text()[contains(.,'^')]">  
    <xsl:variable name="elementName" select="name(..)"/>
    <xsl:for-each select="tokenize(.,'\^')">
         <xsl:element name="{$elementName}-{position()}">
            <xsl:value-of select="."/>
        </xsl:element>
    </xsl:for-each>  
</xsl:template>

</xsl:stylesheet>

---

In XSLT 1.0 you would need to use a recursive template call. For example:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
    <xsl:output indent="yes"/>

 <xsl:template match="@*|node()">
     <xsl:copy>
         <xsl:apply-templates select="@*|node()"/>
     </xsl:copy>
 </xsl:template>

<xsl:template match="text()[contains(.,'^')]">  
    <xsl:variable name="elementName" select="name(..)"/>

    <xsl:call-template name="splitIntoElements">
        <xsl:with-param name="baseName" select="name(..)" />
        <xsl:with-param name="txt" select="." />    
    </xsl:call-template>

</xsl:template>

<xsl:template name="splitIntoElements">
    <xsl:param name="baseName" />
    <xsl:param name="txt" />
    <xsl:param name="delimiter" select="'^'" />
    <xsl:param name="index" select="1" />

    <xsl:variable name="first" select="substring-before($txt, $delimiter)" />
    <xsl:variable name="remaining" select="substring-after($txt, $delimiter)" />

    <xsl:element name="{$baseName}-{$index}">
        <xsl:choose>
            <xsl:when test="$first">
                <xsl:value-of select="$first" />
            </xsl:when>
            <xsl:otherwise>
                <xsl:value-of select="$txt" />
            </xsl:otherwise>
        </xsl:choose>
    </xsl:element>

    <xsl:if test="$remaining">
        <xsl:call-template name="splitIntoElements">
            <xsl:with-param name="baseName" select="$baseName" />
            <xsl:with-param name="txt" select="$remaining" />
            <xsl:with-param name="index" select="$index+1" />
            <xsl:with-param name="delimiter" select="$delimiter" />
        </xsl:call-template>
    </xsl:if>
</xsl:template>

</xsl:stylesheet>