data.WEB-INF.solr.configsets.default.conf.schema.xml Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of opencms-test Show documentation
Show all versions of opencms-test Show documentation
OpenCms is an enterprise-ready, easy to use website content management system based on Java and XML technology. Offering a complete set of features, OpenCms helps content managers worldwide to create and maintain beautiful websites fast and efficiently.
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="example" version="1.5">
<types>
<fieldType name="uuid" class="solr.UUIDField" indexed="true" />
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldtype name="binary" class="solr.BinaryField"/>
<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"/>
<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"/>
<fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="2">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.HyphenatedWordsFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- This is an example of using the KeywordTokenizer along with various TokenFilterFactories to produce a sortable field -->
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.TrimFilterFactory" />
<filter class="solr.PatternReplaceFilterFactory" pattern="([^a-z])" replacement="" replace="all" />
</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>
<!-- A field type that stored the Hierarchy of an path. -->
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
</analyzer>
</fieldType>
<!-- A field type that splits at commas -->
<fieldType name="text_cs" class="solr.TextField" positionIncrementGap="2">
<analyzer>
<tokenizer class="solr.PatternTokenizerFactory" pattern=",\s*" />
</analyzer>
</fieldType>
<!-- A general text field -->
<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" />
<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>
<!-- Just like text_general except it reverses the characters of each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true" maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</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="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English -->
<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"/>
<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"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English, plus aggressive word-splitting and autophrase features enabled. -->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<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.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- German -->
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter class="solr.GermanNormalizationFilterFactory"/>
<filter class="solr.GermanLightStemFilterFactory"/>
<!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
</analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
</analyzer>
</fieldType>
<!-- Spanish -->
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter class="solr.SpanishLightStemFilterFactory"/>
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
</analyzer>
</fieldType>
<!-- Finnish -->
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
<!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter class="solr.FrenchLightStemFilterFactory"/>
<!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
</analyzer>
</fieldType>
<!-- Hungarian -->
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
<!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
</analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- removes l', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter class="solr.ItalianLightStemFilterFactory"/>
<!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
</analyzer>
</fieldType>
</types>
<fields>
<field name="id" type="uuid" indexed="true" stored="true" /><!-- Unique identifier. -->
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW"/>
<field name="path" type="string" indexed="true" stored="true" required="true" />
<field name="filename" type="string" indexed="true" stored="true" required="true" />
<field name="path_hierarchy" type="text_path" indexed="true" stored="true" required="true" /><!-- is copied -->
<field name="parent-folders" type="string" indexed="true" stored="true" required="true" multiValued="true" />
<field name="type" type="string" indexed="true" stored="true" required="true" />
<field name="state" type="string" indexed="true" stored="true" />
<field name="userLastModified" type="string" indexed="true" stored="true" />
<field name="userCreated" type="string" indexed="true" stored="true" />
<field name="version" type="int" indexed="true" stored="true" />
<field name="search_exclude" type="boolean" indexed="true" stored="true" />
<field name="search_channel" type="string" indexed="true" stored="true" multiValued="true" />
<field name="mimetype" type="string" indexed="true" stored="true" />
<field name="container_types" type="string" indexed="true" stored="true" />
<field name="suffix" type="string" indexed="true" stored="true" />
<field name="size" type="int" indexed="true" stored="true" required="true" />
<field name="res_locales" type="string" indexed="true" stored="true" required="true" multiValued="true" />
<field name="con_locales" type="string" indexed="true" stored="true" required="true" multiValued="true" />
<field name="contentdate" type="date" indexed="true" stored="true" required="true" />
<field name="created" type="date" indexed="true" stored="true" required="true" />
<field name="lastmodified" type="date" indexed="true" stored="true" required="true" />
<field name="expired" type="date" indexed="true" stored="true" />
<field name="released" type="date" indexed="true" stored="true" />
<field name="meta" type="text_general" indexed="true" stored="true" multiValued="true" />
<field name="content" type="text_general" indexed="true" stored="true" multiValued="true" />
<field name="contentblob" type="binary" indexed="false" stored="true" />
<field name="category" type="text_general" indexed="true" stored="true" multiValued="true" />
<field name="category_exact" type="string" indexed="true" stored="true" multiValued="true" termVectors="true" /><!-- is copied -->
<field name="additional_info" type="string" indexed="false" stored="true" />
<field name="dependencyType" type="string" indexed="true" stored="true" />
<field name="place" type="location" indexed="true" stored="true" />
<field name="text" type="text_general" indexed="true" stored="true" multiValued="true"/><!-- Catchall for general text fields -->
<field name="text_en" type="text_en" indexed="true" stored="true" multiValued="true"/><!-- Catchall for English text fields -->
<field name="text_de" type="text_de" indexed="true" stored="true" multiValued="true"/><!-- Catchall for German text fields -->
<field name="text_el" type="text_el" indexed="true" stored="true" multiValued="true"/><!-- Catchall for Greek text fields -->
<field name="text_es" type="text_es" indexed="true" stored="true" multiValued="true"/><!-- Catchall for Spanish text fields -->
<field name="text_fr" type="text_fr" indexed="true" stored="true" multiValued="true"/><!-- Catchall for French text fields -->
<field name="text_hu" type="text_hu" indexed="true" stored="true" multiValued="true"/><!-- Catchall for Hungarian text fields -->
<field name="text_it" type="text_it" indexed="true" stored="true" multiValued="true"/><!-- Catchall for Italian text fields -->
<!-- For test cases only -->
<field name="test_text_en" type="text_en" indexed="true" stored="true" />
<field name="test_text_de" type="text_de" indexed="true" stored="true" />
<field name="explicit_title" type="string" indexed="true" stored="true" />
<field name="mteaser" type="string" indexed="true" stored="true" multiValued="true" />
<dynamicField name="*_excerpt" type="text_general" indexed="true" stored="true" termVectors="on" termPositions="on" termOffsets="on" />
<dynamicField name="*_exact" type="string" indexed="true" stored="false"/>
<dynamicField name="*_prop" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_dprop" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_de" type="text_de" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_el" type="text_el" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_es" type="text_es" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_fi" type="text_fi" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_fr" type="text_fr" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_hu" type="text_hu" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_it" type="text_it" 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"/>
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<dynamicField name="*_loc" type="location" indexed="true" stored="true"/>
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="random_*" type="random" />
<dynamicField name="text_*" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true"/>
<dynamicField name="dep_*" type="string" indexed="false" stored="true" multiValued="true"/>
<dynamicField name="*_cs" type="text_cs" indexed="true" stored="false" multiValued="true"/>
<dynamicField name="*_sort" type="alphaOnlySort" indexed="true" stored="false" required="false" multiValued="false"/>
</fields>
<copyField source="*_en" dest="text_en"/>
<copyField source="*_de" dest="text_de"/>
<copyField source="*_el" dest="text_el"/>
<copyField source="*_es" dest="text_es"/>
<copyField source="*_fi" dest="text_fi"/>
<copyField source="*_fr" dest="text_fr"/>
<copyField source="*_hu" dest="text_hu"/>
<copyField source="*_it" dest="text_it"/>
<copyField source="text_*" dest="text"/>
<copyField source="*_prop" dest="text" />
<copyField source="content" dest="text" />
<copyField source="category" dest="text" />
<copyField source="*_prop" dest="*_exact" />
<copyField source="path" dest="path_hierarchy" />
<copyField source="category" dest="category_exact" />
<uniqueKey>id</uniqueKey>
</schema> © 2015 - 2024 Weber Informatics LLC | Privacy Policy