= Search-Service =

Versuch mit Solr4

Config File (data-config.xml):

{{{
<dataConfig>
        <dataSource type="FileDataSource" encoding="UTF-8" />
        <document>
        <entity name="f" processor="FileListEntityProcessor" excludes="^\..*" baseDir="/Volumes/online_permanent/einstein/annalen" fileName=".*\.meta"  recursive="true" rootEntity="false" dataSource="null">
        <entity name="page"
                processor="de.mpiwg.itgroup.solr.transformer.ExtendedXPathEntityProcessor"
                stream="true"
               
                url="${f.fileAbsolutePath}"
                transformer="RegexTransformer,DateFormatTransformer"
                xsl="/Users/dwinter/Documents/Projekte/MetaDataManagement/testData/indexMeta_to_field.xsl"
                useSolrAddSchema="true"
                                >

       </entity>
       </entity>
        </document>
</dataConfig>

}}}

indexMeta_to_field.xsl konvertiert index.meta files in das doc-format zum Indizieren. Alle Einträge in bib werden dazu in Felder umgewandelt mit dem Prefix 
"IM_". Ausserdem werden alle Felder noch in ein Feld "all-bib-data" gemappt.

{{{
<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    version="1.0">   
    <xsl:template match="/">
        <add>
            <doc>
                <field name="archive-path"><xsl:value-of select="/resource/archive-path"/>
                    </field>
                <xsl:for-each select="/resource/meta/bib//*">
                    <field><xsl:attribute name="name">IM_<xsl:value-of select="name()"/>
                    </xsl:attribute><xsl:value-of select="."/></field>
                     <field name="all-bib-data"><xsl:value-of select="."/></field>
                    
                </xsl:for-each>
            </doc>
        </add>    
    </xsl:template>    
</xsl:stylesheet>

}}}


In schema.xml:
{{{

<field name="all-bib-data" type="text_general" indexed="true" stored="true" multiValued="true"/>
<field name="archive-path" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
<dynamicField name="IM_*"  type="text_general"    indexed="true"  stored="true"/>

<uniqueKey>archive-path</uniqueKey>
}}}

ExtendedXPathEntityProcessor ist eine fehlertolerantere Erweiterung von XPathEntityProcessor.

{{{
package de.mpiwg.itgroup.solr.transformer;

import java.util.Map;

import org.apache.solr.handler.dataimport.XPathEntityProcessor;

public class ExtendedXPathEntityProcessor extends XPathEntityProcessor {
  
	public Map<String,Object> nextRow(){
	
	
		
	
	Map<String, Object> r;
	try {
		r = super.nextRow();
	} catch (Exception e) {
		// TODO Auto-generated catch block
		e.printStackTrace();
		r = null;
	}
	
	return r;
	}
}
}}}