Search code examples
xmlxsltxslt-2.0

XSLT Delete and Append Tags


In my XML below, <Subject> is a sub-tag of <Subjects>. Additionally, <Subject> has a few sub-tags. What I need to do is A) remove all the sub-tags of <Subject> (they're duplicates of other fields we're merging this doc with later) and B) make the xref number the value of <Subject> so that it becomes <Subject_xref></Subject_xref>.

I attempted this using

<xsl:template match="Subject">
   <xsl:apply-templates select="*" mode="extra" />
</xsl:template>

but it did not change <Subject> and instead changed <SubjectPhone> to <SubjectPhone_Mobile>. What am I doing wrong, and how can I fix it?

XML

<?xml version="1.0" encoding="UTF-8"?>
<NORMDOC>
   <DOC>
      <DOCID>123456789</DOCID>
      <Subjects>
         <Subject stype="PER" xref="54815594140">
            <SubjectPhone type="Mobile">JANE</SubjectPhone>
         </Subject>
      </Subjects>
      <TXT>
         <S sid="123456789-SENT-075">For assistance contact <ENAMEX type="BANK" id="BAN-123456789-323">BANK OF FURY</ENAMEX> Law Enforcement Liaison at <IDEX type="PHONE" id="PHO-123456789-324">000-000-0000</IDEX> or <CYBEX type="EMAIL" id="EMA-123456789-325">[email protected]</CYBEX>.</S>
      </TXT>
   </DOC>
   <ENTINFO ID="ACC-123456789-013"
            TYPE="ACCOUNT"
            MENTION="MI checking account # 333222111000"/>
</NORMDOC>

XSLT

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

<xsl:template match="/NORMDOC">
    <xsl:apply-templates select="DOC"/>
    <ENTINFOS>
        <xsl:apply-templates select="ENTINFO"/>
    </ENTINFOS>
</xsl:template>

<xsl:template match="TXT">
    <RAW_TXT>
        <xsl:value-of select="."/>
    </RAW_TXT>
    <xsl:copy>
        <xsl:apply-templates/>
    </xsl:copy>
</xsl:template>

<xsl:template match="S">
    <xsl:copy>
        <xsl:apply-templates select="*" mode="extra"/>
    </xsl:copy>
</xsl:template>

<xsl:template match="*" mode="extra">
    <xsl:element name="{name()}_{@type}">
        <xsl:apply-templates/>
    </xsl:element>
</xsl:template>

<xsl:template match="ENTINFO">
    <xsl:copy>
        <xsl:for-each select="@*">
            <xsl:element name="ENTINFO_{translate(name(), '-', '_')}">
                <xsl:value-of select="." />
             </xsl:element>
        </xsl:for-each>
    </xsl:copy>
</xsl:template>

<xsl:template match="/">
  <NORMDOC>
    <xsl:apply-templates/>
  </NORMDOC>
</xsl:template>

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

</xsl:stylesheet>

Actual Output

<NORMDOC>
   <DOC>
      <DOCID>123456789</DOCID>
      <Subjects>
         <Subject>
            <SubjectPhone>JANE</SubjectPhone>
         </Subject>
      </Subjects>
      <RAW_TXT>For assistance contact BANK OF FURY Law Enforcement Liaison at 000-000-0000 or [email protected].</RAW_TXT>
      <TXT>
         <S>
            <ENAMEX_BANK>BANK OF FURY</ENAMEX_BANK>
            <IDEX_PHONE>000-000-0000</IDEX_PHONE>
            <CYBEX_EMAIL>[email protected]</CYBEX_EMAIL>
         </S>
      </TXT>
   </DOC>
   <ENTINFOS>
      <ENTINFO>
         <ENTINFO_ID>ACC-123456789-013</ENTINFO_ID>
         <ENTINFO_TYPE>ACCOUNT</ENTINFO_TYPE>
         <ENTINFO_MENTION>MI checking account # 333222111000</ENTINFO_MENTION>
      </ENTINFO>
   </ENTINFOS>
</NORMDOC>

Goal

<NORMDOC>
   <DOC>
      <DOCID>123456789</DOCID>
      <Subjects>
         <Subject_xref>54815594140</Subject_xref>
      </Subjects>
      <RAW_TXT>For assistance contact BANK OF FURY Law Enforcement Liaison at 000-000-0000 or [email protected].</RAW_TXT>
      <TXT>
         <S>
            ...
         </S>
      </TXT>
   </DOC>
   <ENTINFOS>
      <ENTINFO>
         ...
      </ENTINFO>
   </ENTINFOS>
</NORMDOC>

Solution

  • Just add the following template to the set:

    <xsl:template match="Subject">
      <Subject_xref><xsl:value-of select="@xref"/></Subject_xref>
    </xsl:template>
    

    This does also remove all children of <Subject> elements.