yacy_search_server/examples/surrogate_dublin_core.xml

<?xml version="1.0" encoding="utf-8"?>
<!-- YaCy surrogate file using dublin core notion -->
<!-- 
  This is a surrogate file which is an intermediate document description
  file for index generation. Once you have YaCy started, you can copy a file
  like this (or actual this file) into DATA/SURROGATE/in and then the indexing
  process will read the file, store the content into the search index and moves
  the file into DATA/SURROGATE/out
  Using surrogate files and the surrogate file format you can easily create your
  own data harvesting sources for the YaCy indexer. Just write a file generator
  that generates files like this. The xml schema is very similar to that
  described in
    http://dublincore.org/documents/dc-xml-guidelines/
  using the Dublin Core metadata element set.
-->

<surrogates
  xmlns:dc="http://purl.org/dc/elements/1.1/"
  xmlns:md="http://localhost:8090/api/schema.xml?core=collection1"
>

  <record>
    <dc:Title><![CDATA[Alan Smithee]]></dc:Title>
    <dc:Identifier>http://de.wikipedia.org/wiki/Alan_Smithee</dc:Identifier>
    <dc:Description><![CDATA[Der als Filmregisseur oft genannte '''Alan Smithee''' ist ein Anagramm von „The Alias Men“.]]></dc:Description>
    <dc:Language>de</dc:Language>
    <dc:Date>2009-03-02T11:12:36Z</dc:Date> <!-- date is in ISO 8601 -->
    <md:h1_txt>Alan Smithee</md:h1_txt>
    <md:h2_txt>Geschichte</md:h2_txt>
    <md:h3_txt>Entstehung</md:h3_txt>
    <md:h3_txt>Aufdeckung und Abkehr</md:h3_txt>
    <md:h2_txt>Verwendung</md:h2_txt>
    <md:h2_txt>Literatur</md:h2_txt>
    <md:h2_txt>Weblinks</md:h2_txt>
    <md:h2_txt>Referenzen</md:h2_txt>
    <md:collection_sxt>surrogate</md:collection_sxt>
  </record>

</surrogates>