solr_conf.schema.xml Maven / Gradle / Ivy

Go to download
<?xml version="1.0" encoding="UTF-8" ?>
<!-- ================================================================================================== -->
<!--
    ***********************************************************************************************
    ********************************* Schema Version 4.8.2 ****************************************
    ***********************************************************************************************

    Solr-Schema-Datei

    Changelog
    ***********************************************************************************************

    2018-02-19 ML:
    - Upgrade to Solr 7

    2017-01-18 DP:
    - Reduziertes Schema fuer Bookshelf
    - Nicht benötigte Elemente entfernt
    2017-01-17 CL:
    - Fix Stopwords aus encoded-analyzer entfernt

    2014-05-08 SL:
    - Schema 4.8.0 auf Basis von DC
    - Reduziertes schema fuer 5.4
    _______________________________________________________________________________________________
-->
<!-- ================================================================================================== -->
<schema name="bookshelf-webapp" version="1.4">

  <types>

    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
    <fieldType name="integer" class="solr.TrieIntField" sortMissingLast="true" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" sortMissingLast="true" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
    <fieldType name="date" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>


    <!-- Text Standard -->
    <fieldType name="text" class="solr.TextField" positionIncrementGap="1000" sortMissingLast="true" autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ger_umlauts2ascii.txt"/>
        <!-- splits at Whitespace only-->
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <!-- Special filter for chinese, japanese and korean tokens-->        
        <filter class="solr.CJKBigramFilterFactory"/>
        <!-- Helps to match words with different delimiters: it deletes the non-word characters but also creates and stores substrings (e.g. when you have []- within an expression)--> 
        <filter class="solr.WordDelimiterFilterFactory" preserveOriginal="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1" splitOnNumerics="1" stemEnglishPossessive="1"/>
        <filter class="solr.LengthFilterFactory" min="1" max="2147483647"/>
        <!-- removes diacritical signs and replaces them by their non-diacritical equivalent-->
        <filter class="solr.ASCIIFoldingFilterFactory"/>
        <!-- normalizes to lower case--> 
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ger_umlauts2ascii.txt"/>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.CJKBigramFilterFactory"/>
        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity" delimiter="|"/>
        <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="0" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="0" splitOnNumerics="0" stemEnglishPossessive="1"/>
        <filter class="solr.LengthFilterFactory" min="1" max="128"/>
        <filter class="solr.ASCIIFoldingFilterFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Field facet - as the string is only used to be displayed, but not to be searched actively, it should remaine unchanged-->
    <fieldType name="facet" class="solr.TextField" positionIncrementGap="1000" sortMissingLast="true" omitNorms="true">
      <analyzer type="index">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
      </analyzer>
    </fieldType>

  </types>

  <fields>

    <!--+
        | Technische Felder
        +-->

    <!-- cloud -->
    <field name="_version_" type="long" indexed="true" stored="true"/>
    <!-- Nested document support -->
    <field name="_root_" type="string" indexed="true" stored="false"/>
    <!-- id -->
    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false"/>
    <!-- core  -->
    <field name="core" type="string" indexed="true" stored="true" required="true" multiValued="false" default="${solr.core.name}"/>
    <!-- lastMod: letzte Modifikation -->
    <field name="lastMod" type="date" indexed="true" stored="true" required="true" default="NOW" multiValued="false"/>
    <!-- DRM -->
    <field name="access" type="integer" indexed="true" stored="true" required="true" multiValued="false" default="1"/>

    <!--+
        | Dynamisch
        +-->

    <!-- dynamisches Feld fuer unbekannte Felder als Metadaten -->
    <dynamicField name="*_txt" type="text" indexed="true" stored="true" required="false" multiValued="true"/>
    <dynamicField name="*_str" type="string" indexed="true" stored="true" required="false" multiValued="true"/>
    <dynamicField name="*_fct" type="facet" indexed="true" stored="false" required="false" multiValued="true"/>
    <dynamicField name="*_keu" type="string" indexed="true" stored="true" required="false" multiValued="false"/>
    <field name="text" type="text" indexed="true" stored="false" required="false" multiValued="true"/>
    <copyField source="*_txt" dest="text"/>

  </fields>

  <uniqueKey>id</uniqueKey>

</schema>