psu-libraries/psulib_blacklight

View on GitHub
solr/conf/schema.xml

Summary

Maintainability
Test Coverage
<?xml version="1.0" encoding="UTF-8"?>
<schema name="PsulCat Index" version="1.6">
  <!-- NOTE: various comments and unused configuration possibilities have been purged
     from this file.  Please refer to http://wiki.apache.org/solr/SchemaXml,
     as well as the default schema file included with Solr -->

  <uniqueKey>id</uniqueKey>

  <fields>
    <field name="id" type="string" stored="true" indexed="true" multiValued="false" required="true"/>
    <field name="_version_" type="long" indexed="true" stored="true"/>
    <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
    <field name="subject_facet" type="descendent_path" indexed="true" stored="true" multiValued="true"/>

    <field name="lat" type="tdouble" stored="true" indexed="true" multiValued="false"/>
    <field name="lng" type="tdouble" stored="true" indexed="true" multiValued="false"/>

    <!-- you must define copyField source and dest fields explicity or schemaBrowser doesn't work -->
    <field name="all_text_timv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true"
           termPositions="true" termOffsets="true"/>


    <!-- NOTE:  not all possible Solr field types are represented in the dynamic fields -->

    <!-- text (_t...) -->

    <dynamicField name="*_ti" type="text" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_tim" type="text" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_ts" type="text" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_tsm" type="text" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_tsi" type="text" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_tsim" type="text" stored="true" indexed="true" multiValued="true"/>

    <dynamicField name="*_tiv" type="text" stored="false" indexed="true" multiValued="false" termVectors="true"
                  termPositions="true" termOffsets="true"/>
    <dynamicField name="*_timv" type="text" stored="false" indexed="true" multiValued="true" termVectors="true"
                  termPositions="true" termOffsets="true"/>

    <dynamicField name="*_tsiv" type="text" stored="true" indexed="true" multiValued="false" termVectors="true"
                  termPositions="true" termOffsets="true"/>
    <dynamicField name="*_tsimv" type="text" stored="true" indexed="true" multiValued="true" termVectors="true"
                  termPositions="true" termOffsets="true"/>

    <!-- unstemmed text-->
    <dynamicField name="*_unstem_search" type="text_not_stemmed" indexed="true" stored="false" multiValued="true"/>

    <!-- English text (_te...) -->

    <dynamicField name="*_tei" type="text_en" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_teim" type="text_en" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_tes" type="text_en" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_tesm" type="text_en" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_tesi" type="text_en" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_tesim" type="text_en" stored="true" indexed="true" multiValued="true"/>

    <dynamicField name="*_teiv" type="text_en" stored="false" indexed="true" multiValued="false" termVectors="true"
                  termPositions="true" termOffsets="true"/>
    <dynamicField name="*_teimv" type="text_en" stored="false" indexed="true" multiValued="true" termVectors="true"
                  termPositions="true" termOffsets="true"/>

    <dynamicField name="*_tesiv" type="text_en" stored="true" indexed="true" multiValued="false" termVectors="true"
                  termPositions="true" termOffsets="true"/>
    <dynamicField name="*_tesimv" type="text_en" stored="true" indexed="true" multiValued="true" termVectors="true"
                  termPositions="true" termOffsets="true"/>

    <!-- Chinese, Japanese, Korean text (cjk_...) -->

    <dynamicField name="cjk_*" type="text_cjk" stored="true" indexed="true" multiValued="true" />

    <!-- string (_s...) -->

    <dynamicField name="*_si" type="string" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_sim" type="string" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_ss" type="string" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_ssm" type="string" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_ssi" type="string" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_ssim" type="string" stored="true" indexed="true" multiValued="true"/>

    <dynamicField name="*_ssort" type="alphaSort" stored="false" indexed="true" multiValued="false"/>


    <!-- integer (_i...) -->

    <dynamicField name="*_ii" type="int" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_iim" type="int" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_is" type="int" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_ism" type="int" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_isi" type="int" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_isim" type="int" stored="true" indexed="true" multiValued="true"/>

    <!-- IntegerPointField (_it...) (for faster range queries) -->

    <dynamicField name="*_iti" type="tint" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_itim" type="tint" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_its" type="tint" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_itsm" type="tint" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_itsi" type="tint" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_itsim" type="tint" stored="true" indexed="true" multiValued="true"/>

    <!-- date (_dt...) -->
    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z -->

    <dynamicField name="*_dti" type="date" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_dtim" type="date" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_dts" type="date" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_dtsm" type="date" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_dtsi" type="date" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_dtsim" type="date" stored="true" indexed="true" multiValued="true"/>

    <!-- DatePointField (_dtt...) (for faster range queries) -->

    <dynamicField name="*_dtti" type="tdate" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_dttim" type="tdate" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_dtts" type="tdate" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_dttsm" type="tdate" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_dttsi" type="tdate" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_dttsim" type="tdate" stored="true" indexed="true" multiValued="true"/>

    <!-- long (_l...) -->

    <dynamicField name="*_li" type="long" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_lim" type="long" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_ls" type="long" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_lsm" type="long" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_lsi" type="long" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_lsim" type="long" stored="true" indexed="true" multiValued="true"/>

    <!-- LongPointField (_lt...) (for faster range queries) -->

    <dynamicField name="*_lti" type="tlong" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_ltim" type="tlong" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_lts" type="tlong" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_ltsm" type="tlong" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_ltsi" type="tlong" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_ltsim" type="tlong" stored="true" indexed="true" multiValued="true"/>

    <!-- double (_db...) -->

    <dynamicField name="*_dbi" type="double" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_dbim" type="double" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_dbs" type="double" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_dbsm" type="double" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_dbsi" type="double" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_dbsim" type="double" stored="true" indexed="true" multiValued="true"/>

    <!-- DoublePointField (_dbt...) (for faster range queries) -->

    <dynamicField name="*_dbti" type="tdouble" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_dbtim" type="tdouble" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_dbts" type="tdouble" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_dbtsm" type="tdouble" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_dbtsi" type="tdouble" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_dbtsim" type="tdouble" stored="true" indexed="true" multiValued="true"/>

    <!-- float (_f...) -->

    <dynamicField name="*_fi" type="float" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_fim" type="float" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_fs" type="float" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_fsm" type="float" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_fsi" type="float" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_fsim" type="float" stored="true" indexed="true" multiValued="true"/>

    <!-- FloatPointField (_ft...) (for faster range queries) -->

    <dynamicField name="*_fti" type="tfloat" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_ftim" type="tfloat" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_fts" type="tfloat" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_ftsm" type="tfloat" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_ftsi" type="tfloat" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_ftsim" type="tfloat" stored="true" indexed="true" multiValued="true"/>

    <!-- boolean (_b...) -->

    <dynamicField name="*_bi" type="boolean" stored="false" indexed="true" multiValued="false"/>

    <dynamicField name="*_bs" type="boolean" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_bsi" type="boolean" stored="true" indexed="true" multiValued="false"/>

    <!-- Type used to index the lat and lon components for the "location" FieldType -->

    <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>


    <!-- location (_ll...) -->

    <dynamicField name="*_lli" type="location" stored="false" indexed="true" multiValued="false"/>
    <dynamicField name="*_llim" type="location" stored="false" indexed="true" multiValued="true"/>

    <dynamicField name="*_lls" type="location" stored="true" indexed="false" multiValued="false"/>
    <dynamicField name="*_llsm" type="location" stored="true" indexed="false" multiValued="true"/>
    <dynamicField name="*_llsi" type="location" stored="true" indexed="true" multiValued="false"/>
    <dynamicField name="*_llsim" type="location" stored="true" indexed="true" multiValued="true"/>

    <dynamicField name="*_srpt" type="location_rpt" stored="true" indexed="true" multiValued="true"/>

    <!-- suggest and spelling -->
    <dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true"/>
    <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true"/>

    <!-- JSON -->
    <dynamicField name="*_struct" type="string" stored="true" indexed="false" multiValued="true" omitNorms="true"/>

    <!-- Shelf keys: Multi-valued fields that need to be sorted alphanumerically -->
    <dynamicField name="*_shelfkey" type="string" stored="true" indexed="true" multiValued="true" docValues="true"/>

    <!-- docValues -->
    <!-- Facets -->
    <field name="access_facet"         type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="all_authors_facet"    type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="campus_facet"         type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="collection_facet"     type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="format"               type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="genre_facet"          type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="genre_full_facet"     type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="language_facet"       type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="lc_1letter_facet"     type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="lc_rest_facet"        type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="library_facet"        type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="location_facet"       type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="media_type_facet"     type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="subject_browse_facet" type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="subject_topic_facet"  type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="thesis_dept_facet"    type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="up_library_facet"     type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="author_demo_facet"    type="string" docValues="true" indexed="true" stored="false" multiValued="true" />

    <!-- Sorts -->
    <field name="title_sort"          type="string" docValues="true" indexed="true" stored="false" multiValued="true" />
    <field name="id_sort"             type="int" docValues="true" indexed="true" stored="false" multiValued="true" />
  </fields>


  <!-- Above, multiple source fields are copied to the [text] field.
      Another way to map multiple source fields to the same
      destination field is to use the dynamic field syntax.
      copyField also supports a maxChars to copy setting.  -->

  <copyField source="*_tsim" dest="all_text_timv" maxChars="3000"/>
  <copyField source="*_tesim" dest="all_text_timv" maxChars="3000"/>
  <copyField source="*_ssim" dest="all_text_timv" maxChars="3000"/>
  <copyField source="*_si" dest="all_text_timv" maxChars="3000"/>

  <copyField source="*_tsim" dest="suggest"/>
  <copyField source="*_tesim" dest="suggest"/>
  <copyField source="*_ssim" dest="suggest"/>
  <copyField source="*_si" dest="suggest"/>
  <copyField source="id" dest="id_sort" />

  <!-- unstemmed fields -->
  <copyField source="title_tsim" dest="title_unstem_search"/>
  <copyField source="title_245ab_tsim" dest="title_245ab_unstem_search"/>
  <copyField source="title_addl_tsim" dest="title_addl_unstem_search"/>
  <copyField source="title_added_entry_tsim" dest="title_added_entry_unstem_search"/>
  <copyField source="title_related_tsim" dest="title_related_unstem_search"/>
  <copyField source="series_title_tsim" dest="series_title_unstem_search"/>
  <copyField source="author_tsim" dest="author_unstem_search"/>
  <copyField source="author_addl_tsim" dest="author_addl_unstem_search"/>
  <copyField source="subject_tsim" dest="subject_unstem_search"/>
  <copyField source="subject_addl_tsim" dest="subject_addl_unstem_search"/>
  <copyField source="subject_topic_facet" dest="subject_topic_unstem_search"/>
  <copyField source="genre_tsim" dest="genre_unstem_search"/>
  <copyField source="language_facet" dest="language_ssim"/>
  <copyField source="subject_topic_facet" dest="subject_topic_facet_sim"/>

  <!-- Chinese, Japanese, Korean fields -->
  <copyField source="title_tsim" dest="cjk_title_search"/>
  <copyField source="title_245ab_tsim" dest="cjk_title_245ab_search"/>
  <copyField source="title_addl_tsim" dest="cjk_title_addl_search"/>
  <copyField source="author_tsim" dest="cjk_author_search"/>
  <copyField source="author_addl_tsim" dest="cjk_author_addl_search"/>

  <types>
    <fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
    <fieldType name="rand" class="solr.RandomSortField" omitNorms="true"/>

    <!-- Default numeric field types.  -->
    <fieldType name="int" class="solr.IntPointField" docValues="true"/>
    <fieldType name="float" class="solr.FloatPointField" docValues="true"/>
    <fieldType name="long" class="solr.LongPointField" docValues="true"/>
    <fieldType name="double" class="solr.DoublePointField" docValues="true"/>

    <!-- PointField numeric field types for faster range queries -->
    <fieldType name="tint" class="solr.IntPointField" docValues="true"/>
    <fieldType name="tfloat" class="solr.FloatPointField" docValues="true"/>
    <fieldType name="tlong" class="solr.LongPointField" docValues="true"/>
    <fieldType name="tdouble" class="solr.DoublePointField" docValues="true"/>

    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z
         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
      -->
    <fieldType name="date" class="solr.DatePointField" docValues="true"/>
    <!-- A PointField based date field for faster date range queries and date faceting. -->
    <fieldType name="tdate" class="solr.DatePointField" docValues="true"/>


    <!-- This point type indexes the coordinates as separate fields (subFields)
      If subFieldType is defined, it references a type, and a dynamic field
      definition is created matching *___<typename>.  Alternately, if
      subFieldSuffix is defined, that is used to create the subFields.
      Example: if subFieldType="double", then the coordinates would be
        indexed in fields myloc_0___double,myloc_1___double.
      Example: if subFieldSuffix="_d" then the coordinates would be indexed
        in fields myloc_0_d,myloc_1_d
      The subFields are an implementation detail of the fieldType, and end
      users normally should not need to know about them.
     -->
    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>

    <!-- A specialized field for geospatial search filters and distance sorting. -->
    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>

    <!-- An alternative geospatial field type new to Solr 4.  It supports multiValued and polygon shapes.
      For more information about this and other Spatial fields new to Solr 4, see:
      http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
    -->
    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
               geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers"/>

    <fieldType name="text" class="solr.TextField" omitNorms="false">
      <analyzer>
        <tokenizer class="solr.ICUTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.TrimFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- Analyze/process text, but don't stem. Useful for matching  -->
    <fieldType name="text_not_stemmed" class="solr.TextField" positionIncrementGap="1000"
               autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="\s+(\p{Punct}+)\s+" replacement=" "/>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.WordDelimiterGraphFilterFactory"
                splitOnCaseChange="1" generateWordParts="1" catenateWords="1"
                splitOnNumerics="0" generateNumberParts="1" catenateNumbers="1"
                catenateAll="0" preserveOriginal="0" stemEnglishPossessive="0"/>
        <filter class="solr.FlattenGraphFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="\s+(\p{Punct}+)\s+" replacement=" "/>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.WordDelimiterGraphFilterFactory"
                splitOnCaseChange="1" generateWordParts="1" catenateWords="1"
                splitOnNumerics="0" generateNumberParts="1" catenateNumbers="1"
                catenateAll="0" preserveOriginal="0" stemEnglishPossessive="0"/>
      </analyzer>
    </fieldType>

    <!-- A text field that only splits on whitespace for exact matching of words -->
    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.TrimFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- single token analyzed text, for sorting.  Punctuation is significant. -->
    <fieldtype name="alphaSort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
      <analyzer>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>
        <filter class="solr.TrimFilterFactory"/>
      </analyzer>
    </fieldtype>

    <!-- A text field with defaults appropriate for English -->
    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.ICUTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.EnglishPossessiveFilterFactory"/>
        <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
        <filter class="solr.EnglishMinimalStemFilterFactory"/>
        <!--
        <filter class="solr.PorterStemFilterFactory"/>
        -->
        <filter class="solr.TrimFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- A text field with defaults appropriate for English an NGrams -->
    <fieldType name="text_en_ng" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.ICUTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.EnglishPossessiveFilterFactory"/>
        <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
        <filter class="solr.EnglishMinimalStemFilterFactory"/>
        <filter class="solr.TrimFilterFactory"/>
        <filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="15"/>
      </analyzer>

      <analyzer type="index">
        <tokenizer class="solr.ICUTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory"/>  <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.EnglishPossessiveFilterFactory"/>
        <!-- EnglishMinimalStemFilterFactory is less aggressive than PorterStemFilterFactory: -->
        <filter class="solr.EnglishMinimalStemFilterFactory"/>
        <filter class="solr.TrimFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="textSuggest" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="descendent_path" class="solr.TextField">
      <analyzer type="index">
        <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="—"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="10000" autoGeneratePhraseQueries="false">
      <analyzer>
        <!-- remove spaces among hangul and han chars if there is at least one hangul char -->
        <!-- a korean char guaranteed at the start of the pattern:  pattern="(\p{Hangul}\p{Han}*)\s+(?=[\p{Hangul}\p{Han}])" -->
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="([\p{InHangul_Jamo}\p{InHangul_Compatibility_Jamo}\p{InHangul_Syllables}][\p{InBopomofo}\p{InBopomofo_Extended}\p{InCJK_Compatibility}\p{InCJK_Compatibility_Forms}\p{InCJK_Compatibility_Ideographs}\p{InCJK_Compatibility_Ideographs_Supplement}\p{InCJK_Radicals_Supplement}\p{InCJK_Symbols_And_Punctuation}\p{InCJK_Unified_Ideographs}\p{InCJK_Unified_Ideographs_Extension_A}\p{InCJK_Unified_Ideographs_Extension_B}\p{InKangxi_Radicals}\p{InHalfwidth_And_Fullwidth_Forms}\p{InIdeographic_Description_Characters}]*)\s+(?=[\p{InHangul_Jamo}\p{InHangul_Compatibility_Jamo}\p{InHangul_Syllables}\p{InBopomofo}\p{InBopomofo_Extended}\p{InCJK_Compatibility}\p{InCJK_Compatibility_Forms}\p{InCJK_Compatibility_Ideographs}\p{InCJK_Compatibility_Ideographs_Supplement}\p{InCJK_Radicals_Supplement}\p{InCJK_Symbols_And_Punctuation}\p{InCJK_Unified_Ideographs}\p{InCJK_Unified_Ideographs_Extension_A}\p{InCJK_Unified_Ideographs_Extension_B}\p{InKangxi_Radicals}\p{InHalfwidth_And_Fullwidth_Forms}\p{InIdeographic_Description_Characters}])" replacement="$1"/>
        <!-- a korean char guaranteed at the end of the pattern:    pattern="([\p{Hangul}\p{Han}])\s+(?=[\p{Han}\s]*\p{Hangul})" -->
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="([\p{InHangul_Jamo}\p{InHangul_Compatibility_Jamo}\p{InHangul_Syllables}\p{InBopomofo}\p{InBopomofo_Extended}\p{InCJK_Compatibility}\p{InCJK_Compatibility_Forms}\p{InCJK_Compatibility_Ideographs}\p{InCJK_Compatibility_Ideographs_Supplement}\p{InCJK_Radicals_Supplement}\p{InCJK_Symbols_And_Punctuation}\p{InCJK_Unified_Ideographs}\p{InCJK_Unified_Ideographs_Extension_A}\p{InCJK_Unified_Ideographs_Extension_B}\p{InKangxi_Radicals}\p{InHalfwidth_And_Fullwidth_Forms}\p{InIdeographic_Description_Characters}])\s+(?=[\p{InBopomofo}\p{InBopomofo_Extended}\p{InCJK_Compatibility}\p{InCJK_Compatibility_Forms}\p{InCJK_Compatibility_Ideographs}\p{InCJK_Compatibility_Ideographs_Supplement}\p{InCJK_Radicals_Supplement}\p{InCJK_Symbols_And_Punctuation}\p{InCJK_Unified_Ideographs}\p{InCJK_Unified_Ideographs_Extension_A}\p{InCJK_Unified_Ideographs_Extension_B}\p{InKangxi_Radicals}\p{InHalfwidth_And_Fullwidth_Forms}\p{InIdeographic_Description_Characters}\s]*[\p{InHangul_Jamo}\p{InHangul_Compatibility_Jamo}\p{InHangul_Syllables}])" replacement="$1"/>
        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-cjkMarcCompatibility.txt"/>
        <tokenizer class="solr.ICUTokenizerFactory" />
        <filter class="solr.CJKWidthFilterFactory"/>
        <filter class="solr.ICUTransformFilterFactory" id="Traditional-Simplified"/>
        <filter class="solr.ICUTransformFilterFactory" id="Katakana-Hiragana" />
        <filter class="solr.ICUFoldingFilterFactory"/>
      </analyzer>
    </fieldType>

  </types>

</schema>