WARC mail extract loop

This commit is contained in:
Eric van der Vlist 2012-04-27 17:34:18 +02:00
parent 466d4473ce
commit 5b162a64df
2 changed files with 49 additions and 8 deletions

View File

@ -80,14 +80,55 @@
<!-- Loop over the WARC file to store and transform documents -->
<p:for-each href="#warc-xml" select="/warc/record[headers/header[@name='Content-Type'] = 'application/http; msgtype=response' and content/status/status = 200]" root="root" id="loop">
<p:processor name="oxf:xslt">
<p:input name="data" href="aggregate('root', current(), #index)" debug="aggregate"/>
<p:input name="config">
<resource xsl:version="2.0">
<xsl:copy-of select="/root/index/resource[uri = /root/record/headers/header[@name = 'WARC-Target-URI']]/*"/>
</resource>
</p:input>
<p:output name="data" id="index-entry" debug="index-entry"/>
</p:processor>
<p:choose href="#index-entry">
<p:when test="/entry/embeds">
<!-- The resource has embedded content and must be rewritten -->
<p:processor name="oxf:identity">
<p:input name="data" href="current()#xpointer(/record/content/document)"/>
<p:output name="data" id="document"/>
</p:processor>
</p:when>
<p:otherwise>
<!-- The resource can be stored -->
<p:processor name="oxf:identity">
<p:input name="data" href="current()#xpointer(/record/content/document)"/>
<p:output name="data" id="document"/>
</p:processor>
</p:otherwise>
</p:choose>
<p:processor name="oxf:file-serializer">
<p:input name="config">
<config>
<scope>request</scope>
</config>
</p:input>
<p:input name="data" href="#document"/>
<p:output name="data" id="doc-location" debug="doc-location"/>
</p:processor>
<p:processor name="oxf:identity">
<p:input name="data" href="aggregate('doc', #index-entry, #doc-location)"/>
<p:output name="data" ref="loop"/>
</p:processor>
</p:for-each>
<p:processor name="oxf:null-serializer"> <p:processor name="oxf:null-serializer">
<p:input name="data" href="#index"/> <p:input name="data" href="#loop" debug="loop"/>
</p:processor> </p:processor>
<!-- Loop over the WARC file to store and transform documents -->
<!-- <p:for-each href="#warc-xml" select="/warc/record[header[name='Content-Type'] = 'application/http; msgtype=response' and content/status/status = 200]"> </p:for-each>
-->
<!-- Store the WARC in a temp file --> <!-- Store the WARC in a temp file -->
<p:processor name="oxf:file-serializer"> <p:processor name="oxf:file-serializer">
<p:input name="config"> <p:input name="config">

View File

@ -1,6 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?> <?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:owk="http://owark.org/xslt/" xmlns:xd="http://www.oxygenxml.com/ns/doc/xsl" <xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:owk="http://owark.org/xslt/" xmlns:xd="http://www.oxygenxml.com/ns/doc/xsl"
exclude-result-prefixes="xs xd" version="2.0"> exclude-result-prefixes="xs xd owk" version="2.0">
<xd:doc scope="stylesheet"> <xd:doc scope="stylesheet">
<xd:desc> <xd:desc>
<xd:p><xd:b>Created on:</xd:b> Apr 26, 2012</xd:p> <xd:p><xd:b>Created on:</xd:b> Apr 26, 2012</xd:p>