Re: XSLT2 node comparison, wordlists

I'm sure this is easy to do in XSLT2 but I've just not got my head
wrapped around how to compare things properly in an efficient manner.

t:\ftemp>type cummings.xml
<entry xml:id="let22-w27">
  <form>
    <orth type="hw">the</orth>
    <form type="orthVar">
      <orth xml:id="w72">The</orth>
      <orth xml:id="w3955">The</orth>
      <orth xml:id="w4513">The</orth>
      <orth xml:id="w4578">The</orth>
      <orth xml:id="w4650">The</orth>
      <orth xml:id="w4672">The</orth>
      <orth xml:id="w4703">The</orth>
      <orth xml:id="w4824">The</orth>
      <orth xml:id="w4830">The</orth>
      <orth xml:id="w2045">the</orth>
      <orth xml:id="w2079">the</orth>
      <orth xml:id="w2101">the</orth>
      <orth xml:id="w2112">the</orth>
      <orth xml:id="w2333">the</orth>
      <orth xml:id="w2400">the</orth>
      <orth xml:id="w2442">the</orth>
      <orth xml:id="w1402">T<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w2422">T<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w6458">T<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w7822">T<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w2097">t<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w2155">t<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w2482">t<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w5887">t<ex>h</ex><hi rend="sup">e</hi></orth>
      <orth xml:id="w5642">T<ex>h</ex>e</orth>
      <orth xml:id="w5378">t<ex>h</ex>e</orth>
      </form>
  </form>
</entry>

t:\ftemp>type cummings.xsl
<?xml version="1.0" encoding="US-ASCII"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
                xmlns:xsd="http://www.w3.org/2001/XMLSchema"
                xmlns:c="urn:x-cummings"
                exclude-result-prefixes="xsd c"
                version="2.0">

<xsl:template match="/">
  <xsl:variable name="filename"
                select="tokenize(document-uri(.),'/')[last()]"/>
  <xsl:variable name="id-base" select="entry/@xml:id"/>
  <div>
    <xsl:apply-templates/>

    <div type="links">
      <linkGrp xml:id="{/*/@xml:id}-lg">
        <xsl:for-each-group select="entry/form/form/orth"
                            group-by="c:deep-structure-hash(.)">
          <xsl:text>
          </xsl:text>
          <link>
            <xsl:attribute name="targets">
              <xsl:text/>#<xsl:value-of select="$id-base"/>-v<xsl:text/>
              <xsl:number format="A" value="position()"/>
              <xsl:for-each select="current-group()">
                <xsl:text> </xsl:text>
                <xsl:value-of select="concat($filename,'#',@xml:id)"/>
              </xsl:for-each>
            </xsl:attribute>
          </link>
        </xsl:for-each-group>
      </linkGrp>
      <xsl:text>
      </xsl:text>
    </div>
  </div>
</xsl:template>

<xsl:template match="form[@type='orthVar']">
  <xsl:variable name="id-base" select="ancestor::entry/@xml:id"/>
  <form n="{count(distinct-values(orth))}">
    <xsl:copy-of select="@*"/>
    <xsl:for-each-group select="orth"
                            group-by="c:deep-structure-hash(.)">
      <xsl:text>
      </xsl:text>
      <orth>
        <xsl:attribute name="xml:id">
          <xsl:value-of select="$id-base"/>-v<xsl:text/>
          <xsl:number format="A" value="position()"/>
        </xsl:attribute>
        <xsl:apply-templates/>
      </orth>
    </xsl:for-each-group>
    <xsl:text>
    </xsl:text>
  </form>
</xsl:template>

<xsl:function name="c:deep-structure-hash">
  <!--create a hash based on the structure of the element's descendants-->
  <xsl:param name="node"/>
  <xsl:variable name="return">
    <xsl:apply-templates select="$node/node()" mode="c:deep-structure-hash"/>
  </xsl:variable>
  <!--return the hash as a string value-->
  <xsl:sequence select="string($return)"/>
</xsl:function>

<!--mimic markup in the creation of the deep hash-->
<xsl:template mode="c:deep-structure-hash" match="*">
  <xsl:value-of select="concat('&lt;',name(.))"/>
  <xsl:for-each select="@*">
    <xsl:sort select="name(.)"/>
    <xsl:value-of select="concat(' ',name(.),'=&quot;',.,'&quot;')"/>
    <xsl:text>></xsl:text>
  </xsl:for-each>
  <xsl:apply-templates mode="c:deep-structure-hash"/>
  <xsl:value-of select="concat('&lt;/',name(.),'>')"/>
</xsl:template>

<xsl:template match="@*|*"><!--identity for all other nodes-->
  <xsl:copy>
    <xsl:apply-templates select="@*|node()"/>
  </xsl:copy>
</xsl:template>

</xsl:stylesheet>
t:\ftemp>call xslt2 cummings.xml cummings.xsl cummings.out

--
Comprehensive in-depth XSLT2/XSL-FO1.1 classes: Austin TX,Jan-2008
World-wide corporate, govt. & user group XML, XSL and UBL training
RSS feeds:     publicly-available developer resources and training
G. Ken Holman                 mailto:gkholman@xxxxxxxxxxxxxxxxxxxx
Crane Softwrights Ltd.          http://www.CraneSoftwrights.com/s/
Box 266, Kars, Ontario CANADA K0A-2E0    +1(613)489-0999 (F:-0995)
Male Cancer Awareness Jul'07  http://www.CraneSoftwrights.com/s/bc
Legal business disclaimers:  http://www.CraneSoftwrights.com/legal