enable search without diacritics

[wolnelektury.git] / doc / 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="example" version="1.5">
  <!-- attribute "name" is the name of this schema and is only used for display purposes.
       version="x.y" 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
       1.5: omitNorms defaults to true for primitive field types (int, float, boolean, string...)
     -->

 <fields>
   <!-- Valid attributes for fields:
     name: mandatory - the name for the field
     type: mandatory - the name of a field type from the 
       <types> fieldType 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.
       Norms are omitted for primitive (non-analyzed) types by default.
     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.
     required: The field is required.  It will throw an error if the
       value does not exist
     default: a value that should be used if no value is specified
       when adding a document.
   -->

   <!-- field names should consist of alphanumeric or underscore characters only and
      not start with a digit.  This is not currently strictly enforced,
      but other field names will not have first class support from all components
      and back compatibility is not guaranteed.  Names with both leading and
      trailing underscores (e.g. _version_) are reserved.
   -->

   <field name="book_id" type="int" indexed="true" stored="true" />
   <field name="parent_id" type="int" indexed="false" stored="true" />
   <field name="slug" type="lowercase" stored="false" indexed="true" omitNorms="true"/> <!-- no norms -->
   <field name="is_book" type="boolean" stored="false" indexed="true"/>
   <field name="authors" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true"/>
   <field name="translators" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" />
   <field name="title" type="text_pl_nonstop" stored="false" indexed="true"/>
<!--   <field name="published_date" type="tdate" stored="false" indexed="true"/>-->
   <field name="published_date" type="string" stored="true" indexed="true"/>

   <field name="epochs" type="lowercase" stored="false" indexed="false" multiValued="true" />
   <field name="kinds" type="lowercase" stored="false" indexed="false" multiValued="true" />
   <field name="genres" type="lowercase" stored="false" indexed="false" multiValued="true" />

   <field name="metadata" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true" termPositions="true" termVectors="true" />

   <field name="themes" type="lowercase" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" />
   <field name="themes_pl" type="text_pl_nonstop" stored="true" indexed="true" termVectors="true" termPositions="true" multiValued="true" />
   <field name="header_index" type="int" stored="true" indexed="true"/>
   <field name="header_span" type="int" stored="true" indexed="true"/>
   <field name="header_type" type="lowercase" stored="true" indexed="false"/>
   <field name="text" type="text_pl" stored="false" indexed="true" termVectors="true" termPositions="true" />

   <field name="snippets_position" type="int" stored="true" indexed="false"/>
   <field name="snippets_length" type="int" stored="true" indexed="false"/>
   <field name="snippets_revision" type="int" stored="true" indexed="false"/>
   <field name="fragment_anchor" type="string" stored="true" indexed="false"/>

   <field name="picture_id" type="int" indexed="true" stored="true" />
   <field name="area_id" type="int" stored="true" indexed="false"/>

   <field name="tag_id" type="int" stored="true" indexed="true"/>
   <field name="tag_name" type="lowercase" stored="true" indexed="true" />
   <field name="tag_name_pl" type="text_pl_nonstop" stored="false" indexed="true" multiValued="true"/>
   <field name="tag_category" type="string" stored="true" indexed="true" />
   <field name="is_pdcounter" type="boolean" stored="true" indexed="true" />

   <field name="_version_" type="long" indexed="true" stored="true"/>

   <!-- Uncommenting the following will create a "timestamp" field using
        a default value of "NOW" to indicate when each document was indexed.
     -->
   <!--
   <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
     -->

   <!-- uncomment the following to ignore any fields that don't already match an existing 
        field name or dynamic field, rather than reporting them as an error. 
        alternately, change the type="ignored" to some other type e.g. "text" if you want 
        unknown fields indexed and/or stored by default --> 
   <!--dynamicField name="*" type="ignored" multiValued="true" /-->
    <field name="uid" type="string" indexed="true" stored="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>uid</uniqueKey>

  <!-- 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.  -->

  <copyField source="themes" dest="themes_pl"/>
  <copyField source="tag_name" dest="tag_name_pl"/>

  <copyField source="translators" dest="metadata"/>
  <copyField source="epochs" dest="metadata"/>
  <copyField source="kinds" dest="metadata"/>
  <copyField source="genres" dest="metadata"/>

  <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 a
       standard package such as org.apache.solr.analysis
    -->

    <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />

    <!-- boolean type: "true" or "false" -->
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>

    <!-- sortMissingLast and sortMissingFirst attributes are optional 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.
    -->    

    <!--
      Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
    -->
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>

    <!--
     Numeric field types that index each value at various levels of precision
     to accelerate range queries when the number of values between the range
     endpoints is large. See the javadoc for NumericRangeQuery for internal
     implementation details.

     Smaller precisionStep values (specified in bits) will lead to more tokens
     indexed per value, slightly larger index size, and faster range queries.
     A precisionStep of 0 disables indexing at different precision levels.
    -->
    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>

    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
         is a more restricted form of the canonical representation of dateTime
         http://www.w3.org/TR/xmlschema-2/#dateTime
         The trailing "Z" designates UTC time and is mandatory.
         Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
         All other components are mandatory.

         Expressions can also be used to denote calculations that should be
         performed relative to "NOW" to determine the value, ie...

               NOW/HOUR
                  ... Round to the start of the current hour
               NOW-1DAY
                  ... Exactly 1 day prior to now
               NOW/DAY+6MONTHS+3DAYS
                  ... 6 months and 3 days in the future from the start of
                      the current day
                      
         Consult the DateField javadocs for more information.

         Note: For faster range queries, consider the tdate type
      -->
    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>

    <!-- A Trie based date field for faster date range queries and date faceting. -->
    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>


    <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
    <fieldtype name="binary" class="solr.BinaryField"/>

    <!-- 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 
         or function 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 field name in the request.
     -->
    <fieldType name="random" class="solr.RandomSortField" indexed="true" />

    <fieldType name="uuid" class="solr.UUIDField" indexed="true" />


    <!-- 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"/>
      </analyzer>
    </fieldType>

    <!-- charFilter + WhitespaceTokenizer  -->
    <!--
    <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
      <analyzer>
        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>
    -->

    <!-- lowercases the entire field value, keeping it as a single token.  -->
    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory" />
      </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" />

    <!-- Polish -->
    <fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/>
        <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" />
        <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true" />
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pl.txt" format="snowball"/>
        <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" />
      </analyzer>
    </fieldType>

    <fieldType name="text_pl_nonstop" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" />
        <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true" />
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.MorfologikFilterFactory" dictionary="morfologik/stemming/polish/polish.dict" />
      </analyzer>
    </fieldType>

 </types>
  
  <!-- Similarity is the scoring routine for each document vs. a query.
       A custom Similarity or SimilarityFactory may be specified here, but 
       the default is fine for most applications.  
       For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
    -->
  <!--
     <similarity class="com.example.solr.CustomSimilarityFactory">
       <str name="paramkey">param value</str>
     </similarity>
    -->

</schema>