|
File: Data.xml
<poem>
<author>author 1</author>
<date>1912</date>
<title>Song</title>
<stanza>
<line>line 1</line>
<line>line 2</line>
<line>line 3</line>
<line>line 4</line>
</stanza>
<stanza>
<line>line 5</line>
<line>line 6</line>
<line>line 7</line>
<line>line 8</line>
</stanza>
<stanza>
<line>line 9</line>
<line>line 10</line>
<line>line 11</line>
<line>line 12</line>
</stanza>
</poem>
File: Transform.xslt
<?xml version="1.0" encoding="iso-8859-1"?>
<xsl:stylesheet version="2.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
<xsl:output method="xml" indent="yes" />
<xsl:template match="/">
<wordcount>
<xsl:for-each-group group-by="."
select="
for $w in tokenize(string(.), '\W+') return lower-case($w)">
<xsl:sort select="count(current-group())"
order="descending" />
<word word="{current-grouping-key()}"
frequency="{count(current-group())}" />
</xsl:for-each-group>
</wordcount>
</xsl:template>
</xsl:stylesheet>
Output:
<?xml version="1.0" encoding="UTF-8"?>
<wordcount>
<word word="line" frequency="12"/>
<word word="" frequency="2"/>
<word word="1" frequency="2"/>
<word word="author" frequency="1"/>
<word word="1912" frequency="1"/>
<word word="song" frequency="1"/>
<word word="2" frequency="1"/>
<word word="3" frequency="1"/>
<word word="4" frequency="1"/>
<word word="5" frequency="1"/>
<word word="6" frequency="1"/>
<word word="7" frequency="1"/>
<word word="8" frequency="1"/>
<word word="9" frequency="1"/>
<word word="10" frequency="1"/>
<word word="11" frequency="1"/>
<word word="12" frequency="1"/>
</wordcount>
|