This pipeline processes a large data file that is an XML document. Each 'training-scenario' element can be processed by XSLT but the whole document is too big to load into one in-memory tree. The output is a text data file that can be read by statistical software.

<p:pipe xmlns:p="urn:publicid:IDN+smallx.com:pipeline:1.0" name="scenario2text"
        xmlns:c="urn:publicid:IDN+smallx.com:component-language:1.0"
>

<!-- add the aggregation specification to the input -->
<p:template>
<result>
<c:file href="header.xml"/>
<xsl:copy-of select="."/>
<c:file href="trailer.xml"/>
</result>
</p:template>

<!-- Aggregate by running through the file component -->
<p:file/>

</p:pipe>