mirror of https://github.com/interlegis/sapl.git
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
166 lines
8.2 KiB
166 lines
8.2 KiB
<?xml version="1.0" ?>
|
|
<!--
|
|
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.
|
|
-->
|
|
|
|
<schema name="default" version="1.6">
|
|
<types>
|
|
<fieldtype name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
|
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
|
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
|
|
<fieldtype name="binary" class="solr.BinaryField"/>
|
|
|
|
<!-- Numeric field types that manipulate the value into
|
|
a string value that isn't human-readable in its internal form,
|
|
but with a lexicographic ordering the same as the numeric ordering,
|
|
so that range queries work correctly. -->
|
|
<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="pdate" class="solr.DatePointField" docValues="true" />
|
|
<!-- A Trie based date field ifor faster date range queries and date faceting. -->
|
|
|
|
<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="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
|
|
|
|
|
|
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
|
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
|
<fieldtype name="geohash" class="solr.GeoHashField"/>
|
|
|
|
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<!-- in this example, we will only use synonyms at query time
|
|
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
-->
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Portuguese -->
|
|
<dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
|
|
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
|
|
<filter class="solr.PortugueseLightStemFilterFactory"/>
|
|
<!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
|
|
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
|
|
<!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory"
|
|
ignoreCase="true"
|
|
words="lang/stopwords_en.txt"
|
|
/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
-->
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.StopFilterFactory"
|
|
ignoreCase="true"
|
|
words="lang/stopwords_en.txt"
|
|
/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
-->
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="ngram" class="solr.TextField" >
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory" />
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
|
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory" />
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
</types>
|
|
|
|
<fields>
|
|
<!-- general -->
|
|
<field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
|
|
<field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/>
|
|
<field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/>
|
|
<field name="_version_" type="plong" indexed="true" stored ="true"/>
|
|
<field name="text" type="text_pt" indexed="true" stored="true" multiValued="false" />
|
|
<field name="last_update" type="pdate" indexed="true" stored="true" default="NOW" />
|
|
|
|
</fields>
|
|
|
|
<!-- field to use to determine and enforce document uniqueness. -->
|
|
<uniqueKey>id</uniqueKey>
|
|
|
|
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
|
<df>text</df>
|
|
|
|
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
|
<solrQueryParser q.op="AND"/>
|
|
</schema>
|
|
|