Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Der ZDB Index wird mit Hilfe der Newspaper Spark App aus dem ZDB Dump aufbautaufgebaut

Schema

Code Block
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="newspaper" version="1.6"> 

    <similarity class="org.apache.lucene.search.similarities.ClassicSimilarity" />

    <fieldType name="string" class="solr.TextField" sortMissingLast="true" omitNorms="true">
        <analyzer>
            <tokenizer class="solr.KeywordTokenizerFactory" />
        </analyzer>
    </fieldType>

    <fieldType name="sort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
        <analyzer type="index">
            <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt" />
            <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="([^a-zA-Z0-9])" replacement=""/>
            <tokenizer class="solr.KeywordTokenizerFactory" />
            <filter class="solr.LowerCaseFilterFactory" />
        </analyzer>
    </fieldType>

        <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
            <analyzer>
                <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt" />
                <tokenizer class="solr.WhitespaceTokenizerFactory" />
                <filter class="solr.LowerCaseFilterFactory" />
                <filter class="solr.TrimFilterFactory" />
                <filter class="de.fhg.iais.cortex.search.analyzer.LengthTrimFilterFactory" length="32766" />
            </analyzer>
        </fieldType>
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" />
    

    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
    <field name="title" type="text" indexed="true" stored="true" required="true" multiValued="true" />
    <field name="language" type="string" indexed="true" stored="true" required="false" multiValued="true" />
    <field name="frequency" type="string" indexed="true" stored="true" required="false" multiValued="true" />
    <field name="locationUri" type="text" indexed="true" stored="true" required="false" multiValued="true" />
    <field name="location" type="text" indexed="true" stored="true" required="false" multiValued="true" />
    <field name="progress" type="string" indexed="true" stored="true" required="false" multiValued="true" />
    <field name="hasFulltext" type="boolean" indexed="true" stored="true" required="false" multiValued="false" />
    <field name="referenceId" type="string" indexed="true" stored="true" required="false" multiValued="false" />

    <field name="sort.title" type="sort" indexed="true" stored="false" required="true" multiValued="false" />
    <field name="sort.location" type="sort" indexed="true" stored="false" required="false" multiValued="false" />

    <!-- Field to use to determine and enforce document uniqueness. Unless this field is marked with required="false", it 
        will be a required field -->
    <uniqueKey>id</uniqueKey>

</schema>

...