schema.xml

<?xml version="1.0" encoding="UTF-8" ?>
<!--
 Licensed to the Apache Software Foundation (ASF) under one or more
 contributor license agreements.  See the NOTICE file distributed with
 this work for additional information regarding copyright ownership.
 The ASF licenses this file to You under the Apache License, Version 2.0
 (the "License"); you may not use this file except in compliance with
 the License.  You may obtain a copy of the License at

     http://www.apache.org/licenses/LICENSE-2.0

 Unless required by applicable law or agreed to in writing, software
 distributed under the License is distributed on an "AS IS" BASIS,
 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License.
-->

<!--
 This is the Solr schema file. This file should be named "schema.xml" and
 should be in the conf directory under the solr home
 (i.e. ./solr/conf/schema.xml by default)
 or located where the classloader for the Solr webapp can find it.

 This example schema is the recommended starting point for users.
 It should be kept correct and concise, usable out-of-the-box.

 For more information, on how to customize this file, please see
 http://wiki.apache.org/solr/SchemaXml

 PERFORMANCE NOTE: this schema includes many optional features and should not
 be used for benchmarking.  To improve performance one could
  - set stored="false" for all fields possible (esp large fields) when you
    only need to search on the field but don't need to return the original
    value.
  - set indexed="false" if you don't need to search on the field, but only
    return the field as a result of searching on other indexed fields.
  - remove all unneeded copyField statements
  - for best index size and searching performance, set "index" to false
    for all general text fields, use copyField to copy them to the
    catchall "text" field, and use that for searching.
  - For maximum indexing performance, use the StreamingUpdateSolrServer
    java client.
  - Remember to run the JVM in server mode, and use a higher logging level
    that avoids logging every request
-->

<schema name="Temple Library Search" version="1.5">
  <!-- attribute "name" is the name of this schema and is only used for display purposes.
       Applications should change this to reflect the nature of the search collection.
       version="1.4" is Solr's version number for the schema syntax and semantics.  It should
       not normally be changed by applications.
       1.0: multiValued attribute did not exist, all fields are multiValued by nature
       1.1: multiValued attribute introduced, false by default
       1.2: omitTermFreqAndPositions attribute introduced, true by default except for text fields.
       1.3: removed optional field compress feature
       1.4: default auto-phrase (QueryParser feature) to off
     -->

  <types>
    <!-- field type definitions. The "name" attribute is
       just a label to be used by field definitions.  The "class"
       attribute and any other attributes determine the real
       behavior of the fieldType.
         Class names starting with "solr" refer to java classes in the
       org.apache.solr.analysis package.
    -->

    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
    <!-- boolean type: "true" or "false" -->
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
    <fieldtype name="binary" class="solr.BinaryField"/>

    <!-- The optional sortMissingLast and sortMissingFirst attributes are
         currently supported on types that are sorted internally as strings
         and on numeric types.
	       This includes "string","boolean", and, as of 3.5 (and 4.x),
	       int, float, long, date, double, including the "Trie" variants.
       - If sortMissingLast="true", then a sort on this field will cause documents
         without the field to come after documents with the field,
         regardless of the requested sort order (asc or desc).
       - If sortMissingFirst="true", then a sort on this field will cause documents
         without the field to come before documents with the field,
         regardless of the requested sort order.
       - If sortMissingLast="false" and sortMissingFirst="false" (the default),
         then default lucene sorting will be used which places docs without the
         field first in an ascending sort and last in a descending sort.
    -->

    <fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
    <fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
    <!--
      Numeric field types that index values using KD-trees.
      Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
    -->
    <fieldType name="pint" class="solr.IntPointField" docValues="true"/>
    <fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
    <fieldType name="plong" class="solr.LongPointField" docValues="true"/>
    <fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>

    <fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
    <fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
    <fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
    <fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>

    <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"/>
    <fieldType name="date" class="solr.DatePointField" docValues="true"/>

    <!-- The "RandomSortField" is not used to store or search any
         data.  You can declare fields of this type it in your schema
         to generate pseudo-random orderings of your docs for sorting
         purposes.  The ordering is generated based on the field name
         and the version of the index, As long as the index version
         remains unchanged, and the same field name is reused,
         the ordering of the docs will be consistent.
         If you want different psuedo-random orderings of documents,
         for the same version of the index, use a dynamicField and
         change the name
     -->
    <fieldType name="random" class="solr.RandomSortField" indexed="true" />

    <!-- solr.TextField allows the specification of custom text analyzers
         specified as a tokenizer and a list of token filters. Different
         analyzers may be specified for indexing and querying.

         The optional positionIncrementGap puts space between multiple fields of
         this type on the same document, with the purpose of preventing false phrase
         matching across fields.

         For more info on customizing your analyzer chain, please see
         http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
     -->
     <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
       <analyzer>
        <charFilter class="solr.MappingCharFilterFactory" mapping="char-filter-mapping.txt"/>
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="\s+(\p{Punct}+)\s+" replacement=" " />
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="\s+(&quot;)" replacement=" " />
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="([;:.,&quot;]+)\s*$" replacement=" " />
         <tokenizer class="solr.WhitespaceTokenizerFactory"/>
         <filter class="solr.ICUFoldingFilterFactory" /> <!-- NFKC, case folding, diacritics removed -->
         <filter class="solr.WordDelimiterGraphFilterFactory" catenateAll="1" preserveOriginal="1"/>
         <filter class="solr.FlattenGraphFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
         <filter class="solr.PorterStemFilterFactory" />
       </analyzer>
     </fieldType>

    <!-- A general text field that has reasonable, generic
        cross-language defaults: it tokenizes with StandardTokenizer,
        , and down cases.  At query time only, it
        also applies synonyms. -->
    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <charFilter class="solr.MappingCharFilterFactory" mapping="char-filter-mapping.txt"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.FlattenGraphFilterFactory"/>
        <!-- The LowerCaseFilterFactory gives us better results by normalizing case. -->
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <charFilter class="solr.MappingCharFilterFactory" mapping="char-filter-mapping.txt"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- A general text field that has unstemmed, generic
        cross-language defaults: it tokenizes with StandardTokenizer,
        and down cases. -->
    <fieldType name="text_exact" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <charFilter class="solr.MappingCharFilterFactory" mapping="char-filter-mapping.txt"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <!-- The LowerCaseFilterFactory gives us better results by normalizing case. -->        
        <filter class="solr.FlattenGraphFilterFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

    <!-- A text field with defaults appropriate for English: it
        tokenizes with StandardTokenizer, down cases, protects words from protwords.txt, and
        finally applies Porter's stemming.  The query time analyzer
        also applies synonyms from synonyms.txt. -->
    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <charFilter class="solr.MappingCharFilterFactory" mapping="char-filter-mapping.txt"/>
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="\s+(\p{Punct}+)\s+" replacement=" " />
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="\s+(&quot;)" replacement=" " />
        <charFilter class="solr.PatternReplaceCharFilterFactory" pattern="([;:.,&quot;]+)\s*$" replacement=" " />
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.ICUFoldingFilterFactory" /> <!-- NFKC, case folding, diacritics removed -->
        <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.WordDelimiterGraphFilterFactory" catenateAll="1" preserveOriginal="1"/>
        <filter class="solr.FlattenGraphFilterFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
    </fieldType>

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

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

    <!-- This is an example of using the KeywordTokenizer along
         With various TokenFilterFactories to produce a sortable field
         that does not include some properties of the source text
      -->
    <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
      <analyzer>
        <!-- KeywordTokenizer does no actual tokenizing, so the entire
             input string is preserved as a single token
          -->
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <!-- The LowerCase TokenFilter does what you expect, which can be
             when you want your sorting to be case insensitive
          -->
        <filter class="solr.LowerCaseFilterFactory" />
        <!-- The TrimFilter removes any leading or trailing whitespace -->
        <filter class="solr.TrimFilterFactory" />
        <!-- The PatternReplaceFilter gives you the flexibility to use
             Java Regular expression to replace any sequence of characters
             matching a pattern with an arbitrary replacement string,
             which may include back references to portions of the original
             string matched by the pattern.

             See the Java Regular Expression documentation for more
             information on pattern and replacement string syntax.

             http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
          -->
        <filter class="solr.PatternReplaceFilterFactory"
                pattern="([^a-z])" replacement="" replace="all"
        />
      </analyzer>
    </fieldType>

    <!-- since fields of this type are by default not stored or indexed,
         any data added to them will be ignored outright.  -->
    <fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />

    <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
    <fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true" />

    <!-- For fields you do not want split into tokens -->
    <fieldType name="simple_string" class="solr.TextField" omitNorms="true">
      <analyzer>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory" />
      </analyzer>
    </fieldType>
  </types>


  <fields>
    <!-- Valid attributes for fields:
      name: mandatory - the name for the field
      type: mandatory - the name of a previously defined type from the
        <types> section
      indexed: true if this field should be indexed (searchable or sortable)
      stored: true if this field should be retrievable
      multiValued: true if this field may contain multiple values per document
      omitNorms: (expert) set to true to omit the norms associated with
        this field (this disables length normalization and index-time
        boosting for the field, and saves some memory).  Only full-text
        fields or fields that need an index-time boost need norms.
      termVectors: [false] set to true to store the term vector for a
        given field.
        When using MoreLikeThis, fields used for similarity should be
        stored for best performance.
      termPositions: Store position information with the term vector.
        This will increase storage costs.
      termOffsets: Store offset information with the term vector. This
        will increase storage costs.
      default: a value that should be used if no value is specified
        when adding a document.
    -->

    <!-- NOTE: this is not a full list of fields in the index; dynamic fields are also used -->
    <field name="id" type="string" indexed="true" stored="true" required="true" />
    <field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
    <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
    <!-- default, catch all search field -->
    <field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
    <!-- these display fields are NOT multi-valued -->
    <field name="marc_display_raw" type="string" indexed="false" stored="true" multiValued="false"/>
    <field name="library_facet" type="string" indexed="true" stored="true" multiValued="true" />
    <field name="availability_facet" type="string" indexed="true" stored="true" multiValued="true" />
    <field name="language_facet" type="string" indexed="true" stored="true" multiValued="true" />
    <field name="subject_topic_facet" type="string" indexed="true" stored="true" multiValued="true" />
    <field name="subject_era_facet" type="string" indexed="true" stored="true" multiValued="true" />
    <field name="subject_geo_facet" type="string" indexed="true" stored="true" multiValued="true" />
    <!-- pub_date is used for facet and display so it must be indexed and stored -->
    <field name="pub_date" type="string" indexed="true" stored="true" multiValued="true"/>
    <!-- pub_date sort uses new trie-based int fields, which are recommended for any int and are displayable, sortable, and range-quer
    we use 'pint' for faster range-queries. -->
    <field name="pub_date_sort" type="pint" indexed="true" stored="true" multiValued="false"/>
    <field name="date_added_facet" type="pints" indexed="true" stored="true" multiValued="true"/>
    <field name="lc_outer_facet" type="string" indexed="true" stored="true" multiValued="false" />
    <field name="lc_inner_facet" type="string" indexed="true" stored="true" multiValued="false" />
    <!-- format is used for facet, display, and choosing which partial to use for the show view, so it must be stored and indexed -->
    <field name="format" type="string" indexed="true" stored="true" multiValued="true"/>
    <!--field name="library_facet" type="string" indexed="true" stored="true" multiValued="true"/>
    <field name="subject" type="string" indexed="true" stored="true" multiValued="true"/ -->
    <field name="record_creation_date" type="string" indexed="true" stored="true" multiValued="false"/>
    <field name="record_update_date" type="string" indexed="true" stored="true" multiValued="false"/>
    <field name="bound_with_ids" type="string" indexed="true" stored="true" multiValued="true"/>
    <field name="work_access_point" type="string" indexed="true" stored="true" multiValued="true"/>
    <field name="purchase_order" type="boolean" indexed="false" stored="true" multiValued="false" default="false" />
    <field name="call_number_t" type="simple_string" indexed="true" stored="true" multiValued="true"/>

    <!-- Dynamic field definitions.  If a field name is not found, dynamicFields
        will be used if the name matches any of the patterns.
        RESTRICTION: the glob-like pattern in the name attribute must have
        a "*" only at the start or the end.
        EXAMPLE:  name="*_i" will match any field ending in _i (like myid_i, z_i)
        Longer patterns will be matched first.  if equal size patterns
        both match, the first appearing in the schema will be used.  -->

    <dynamicField name="*_display" type="string" indexed="false" stored="true" multiValued="true" />
    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true"/>
    <dynamicField name="*_ms"  type="string"  indexed="true"  stored="true" multiValued="true"/>
    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
    <dynamicField name="*_t"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
    <dynamicField name="*_txt" type="text_exact"    indexed="true"  stored="true" multiValued="true"/>
    <dynamicField name="*_b"  type="boolean" indexed="true"  stored="true"/>
    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
    <!-- Type used to index the lat and lon components for the "location" FieldType -->
    <dynamicField name="*_coordinate"  type="pdouble" indexed="true"  stored="false"/>
    <dynamicField name="*_dt" type="date"    indexed="true"  stored="true"/>
    <!-- keeping _tdt instead of _pdt for backwards compatibility. -->
    <dynamicField name="*_tdt" type="pdate"  indexed="true"  stored="true"/>
    <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
    <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
    <dynamicField name="random_*" type="random" />
    <dynamicField name="*_facet" type="string" indexed="true" stored="false" multiValued="true" />
    <dynamicField name="*_sort" type="alphaOnlySort" indexed="true" stored="false" multiValued="false" />
    <dynamicField name="*_unstem_search" type="text_exact" indexed="true" stored="false" multiValued="true" />
    <dynamicField name="*spell" type="textSpell" indexed="true" stored="false" multiValued="true" />
    <dynamicField name="*suggest" type="textSuggest" indexed="true" stored="false" multiValued="true" />

  </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>id</uniqueKey>

  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
  <df>text</df>

  <!-- copyField commands copy one field to another at the time a document
        is added to the index.  It's used either to index the same field differently,
        or to add multiple fields to the same field for easier/faster searching.  -->
  <!-- Copy Fields -->
  <copyField source="lc_call_number_display" dest="lc_call_number_t"/>
  <copyField source="creator_group_display" dest="creator_group_t"/>

  <!-- unstemmed fields -->
  <copyField source="title_txt" dest="title_unstem_search"/>
  <copyField source="title_txt" dest="title_t"/>
  <copyField source="subtitle_txt" dest="subtitle_unstem_search"/>
  <copyField source="subtitle_txt" dest="subtitle_t"/>
  <copyField source="title_statement_txt" dest="title_statement_unstem_search"/>
  <copyField source="title_statement_txt" dest="title_statement_t"/>
  <copyField source="title_uniform_txt" dest="title_uniform_unstem_search"/>
  <copyField source="title_uniform_txt" dest="title_uniform_t"/>
  <copyField source="title_addl_txt" dest="title_addl_unstem_search"/>
  <copyField source="title_addl_txt" dest="title_addl_t"/>
  <copyField source="title_added_entry_txt" dest="title_added_entry_unstem_search"/>
  <copyField source="title_added_entry_txt" dest="title_added_entry_t"/>
  <copyField source="title_series_txt" dest="title_series_unstem_search"/>
  <copyField source="title_series_txt" dest="title_series_t"/>
  <copyField source="creator_txt" dest="creator_unstem_search"/>
  <copyField source="creator_txt" dest="creator_t"/>
  <copyField source="subject_display" dest="subject_unstem_search"/>
  <!-- <copyField source="author_addl_t" dest="author_addl_unstem_search"/> -->
  <copyField source="subject_txt" dest="subject_unstem_search"/>
  <copyField source="subject_txt" dest="subject_t"/>
  <copyField source="subject_addl_txt" dest="subject_addl_unstem_search"/>
  <copyField source="subject_addl_txt" dest="subject_addl_t"/>
  <copyField source="subject_topic_facet" dest="subject_topic_unstem_search"/>
  <copyField source="note_toc_display" dest="note_toc_unstem_search"/>
  <copyField source="note_summary_display" dest="note_summary_unstem_search"/>

  <!-- sort fields  NOTE: no longer feasible with multiple dates -->
  <!--  <copyField source="pub_date" dest="pub_date_sort"/>  -->

  <copyField source="*_display" dest="text" />
  <copyField source="title_statement_display" dest="title_statement_including_author_t"/>

  <!-- search fields for advanced search form-->
  <copyField source="title_display" dest="title_t"/>
  <copyField source="title_uniform_display" dest="title_uniform_t"/>
  <copyField source="title_addl_display" dest="title_addl_t"/>
  <copyField source="isbn_display" dest="isbn_t"/>
  <copyField source="issn_display" dest="issn_t"/>
  <copyField source="call_number_display" dest="call_number_t"/>
  <copyField source="call_number_alt_display" dest="call_number_t"/>
  <copyField source="alma_mms_display" dest="alma_mms_t"/>
  <copyField source="title_series_display" dest="title_series_t"/>
  <copyField source="note_display" dest="note_t"/>
  <copyField source="note_award_display" dest="note_t"/>
  <copyField source="note_with_display" dest="note_with_t"/>
  <copyField source="note_diss_display" dest="note_diss_t"/>
  <copyField source="note_biblio_display" dest="note_biblio_t"/>
  <copyField source="note_toc_display" dest="note_toc_t"/>
  <copyField source="note_restrictions_display" dest="note_restrictions_t"/>
  <copyField source="note_references_display" dest="note_references_t"/>
  <copyField source="note_summary_display" dest="note_summary_t"/>
  <copyField source="note_cite_display" dest="note_cite_t"/>
  <copyField source="note_finding_aid_display" dest="note_finding_aid_t"/>
  <copyField source="note_custodial_display" dest="note_custodial_t"/>
  <copyField source="note_binding_display" dest="note_binding_t"/>
  <copyField source="note_related_display" dest="note_related_t"/>
  <copyField source="note_accruals_display" dest="note_accruals_t"/>
  <copyField source="note_local_display" dest="note_local_t"/>
  <copyField source="donor_info_ms" dest="donor_info_t"/>
  <copyField source="genre_ms" dest="genre_t"/>
  <copyField source="collection_ms" dest="collection_t"/>

  <!-- OpenSearch query field should match request handler search fields -->
  <copyField source="title_t" dest="opensearch_display"/>
  <copyField source="subtitle_t" dest="opensearch_display"/>
  <copyField source="addl_titles_t" dest="opensearch_display"/>
  <copyField source="title_added_entry_t" dest="opensearch_display"/>
  <copyField source="title_series_t" dest="opensearch_display"/>
  <copyField source="creator_t" dest="opensearch_display"/>
  <!-- <copyField source="author_addl_t" dest="opensearch_display"/> -->
  <copyField source="subject_topic_facet" dest="opensearch_display"/>
  <copyField source="subject_t" dest="opensearch_display"/>
  <copyField source="subject_addl_t" dest="opensearch_display"/>

</schema>