Schema.xml

gistfile1.txt

<?xml version="1.0" encoding="UTF-8" ?>
<schema name="default" version="1.0">
<fields>
    <field name="uid" type="string" indexed="true" stored="true" required="true" multiValued="false"/>
    <field name="publisher" type="text_pl" indexed="true" stored="true" multiValued="true"/>
    <field name="publisher_hl" type="text_pl_hl" indexed="true" stored="true" multiValued="true" termVectors="true"
           termPositions="true" termOffsets="true"/>
    <field name="publisherFacet" type="string" indexed="true" stored="true" multiValued="true"/>
    <field name="_version_" type="string" indexed="true" stored="true" multiValued="false"/>

</fields>


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

<copyField source="publisher" dest="publisherFacet"/>
<copyField source="publisher" dest="publisher_hl"/>

<types>
    <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
    <fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100">
        <analyzer type="index">
            <charFilter class="solr.HTMLStripCharFilterFactory"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.CommonGramsFilterFactory" words="stopwords.txt" ignoreCase="true"/>
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
            <filter class="solr.LowerCaseTokenizerFactory"/>
            <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
        </analyzer>
        <analyzer type="query">
            <charFilter class="solr.HTMLStripCharFilterFactory"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
            <filter class="solr.CommonGramsFilterFactory" words="stopwords.txt" ignoreCase="true"/>
            <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.LowerCaseTokenizerFactory"/>
            <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
        </analyzer>
    </fieldType>

    <fieldType name="text_pl_hl" class="solr.TextField" positionIncrementGap="100">
        <analyzer type="index">
            <charFilter class="solr.HTMLStripCharFilterFactory"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.LowerCaseTokenizerFactory"/>
            <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
            <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="20" side="front"/>
        </analyzer>
        <analyzer type="query">
            <charFilter class="solr.HTMLStripCharFilterFactory"/>
            <tokenizer class="solr.StandardTokenizerFactory"/>
            <filter class="solr.LowerCaseTokenizerFactory"/>
            <filter class="solr.MorfologikFilterFactory" dictionary="MORFOLOGIK" />
        </analyzer>
    </fieldType>
</types>

</schema>