mirror of https://github.com/midoks/mdserver-web
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.
635 lines
34 KiB
635 lines
34 KiB
<?xml version="1.0" encoding="UTF-8" ?>
|
|
|
|
|
|
<schema name="example-data-driven-schema" version="1.6">
|
|
|
|
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
|
|
<field name="_version_" type="long" indexed="false" stored="false"/>
|
|
<field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
|
|
<field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<copyField source="*" dest="_text_"/>
|
|
|
|
<dynamicField name="*_i" type="int" indexed="true" stored="true"/>
|
|
<dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
|
|
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
|
|
<dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
|
|
<dynamicField name="*_l" type="long" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
|
|
<dynamicField name="*_t" type="text_general" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
|
|
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
|
<dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
|
|
<dynamicField name="*_f" type="float" indexed="true" stored="true"/>
|
|
<dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
|
|
<dynamicField name="*_d" type="double" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
|
|
|
|
<!-- Type used to index the lat and lon components for the "location" FieldType -->
|
|
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" useDocValuesAsStored="false" />
|
|
|
|
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
|
<dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/>
|
|
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
|
|
<dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
|
|
|
|
<!-- some trie-coded dynamic fields for faster range queries -->
|
|
<dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
|
|
<dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
|
|
|
|
<dynamicField name="*_c" type="currency" 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" />
|
|
|
|
<uniqueKey>id</uniqueKey>
|
|
|
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
|
|
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
|
|
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
|
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
|
|
<fieldType name="int" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<fieldType name="float" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<fieldType name="long" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<fieldType name="double" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<fieldType name="ints" class="solr.TrieIntField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="floats" class="solr.TrieFloatField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="longs" class="solr.TrieLongField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="doubles" class="solr.TrieDoubleField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="tint" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
|
<fieldType name="tfloat" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
|
<fieldType name="tlong" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
|
<fieldType name="tdouble" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0"/>
|
|
<fieldType name="tints" class="solr.TrieIntField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="tfloats" class="solr.TrieFloatField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="tlongs" class="solr.TrieLongField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="tdoubles" class="solr.TrieDoubleField" docValues="true" precisionStep="8" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="date" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<fieldType name="dates" class="solr.TrieDateField" docValues="true" precisionStep="0" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="tdate" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0"/>
|
|
<fieldType name="tdates" class="solr.TrieDateField" docValues="true" precisionStep="6" positionIncrementGap="0" multiValued="true"/>
|
|
<fieldType name="binary" class="solr.BinaryField"/>
|
|
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
|
<dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
|
|
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
|
|
<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>
|
|
|
|
<dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
|
|
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<fieldtype name="textComplex" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="complex" dicPath="dic"/>
|
|
</analyzer>
|
|
</fieldtype>
|
|
<fieldtype name="textMaxWord" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="max-word" />
|
|
</analyzer>
|
|
</fieldtype>
|
|
<fieldtype name="textSimple" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="simple" dicPath="dic" />
|
|
</analyzer>
|
|
</fieldtype>
|
|
|
|
<dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
|
|
<fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
|
|
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
|
|
<fieldType name="ancestor_path" class="solr.TextField">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.KeywordTokenizerFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
|
</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" docValues="false" multiValued="true" class="solr.StrField" />
|
|
|
|
|
|
<dynamicField name="*_point" type="point" indexed="true" stored="true"/>
|
|
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
|
|
|
<!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
|
|
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
|
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
|
|
geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
|
|
<fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />
|
|
|
|
|
|
<!-- Arabic -->
|
|
<dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
|
|
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<!-- for any non-arabic -->
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
|
|
<!-- normalizes ﻯ to ﻱ, etc -->
|
|
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
<filter class="solr.ArabicStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Bulgarian -->
|
|
<dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
|
|
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt" />
|
|
<filter class="solr.BulgarianStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Catalan -->
|
|
<dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
|
|
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<!-- removes l', etc -->
|
|
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
|
|
<dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
|
|
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
|
|
<filter class="solr.CJKWidthFilterFactory"/>
|
|
<!-- for any non-CJK -->
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.CJKBigramFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Czech -->
|
|
<dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
|
|
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt" />
|
|
<filter class="solr.CzechStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Danish -->
|
|
<dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
|
|
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- German -->
|
|
<dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
|
|
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<!-- greek specific lowercase for sigma -->
|
|
<filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
|
|
<filter class="solr.GreekStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Spanish -->
|
|
<dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Basque -->
|
|
<dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
|
|
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Persian -->
|
|
<dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
|
|
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<!-- for ZWNJ -->
|
|
<charFilter class="solr.PersianCharFilterFactory"/>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
<filter class="solr.PersianNormalizationFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Finnish -->
|
|
<dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Irish -->
|
|
<dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
|
|
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<!-- removes d', etc -->
|
|
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
|
|
<!-- removes n-, etc. position increments is intentionally false! -->
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
|
|
<filter class="solr.IrishLowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Galician -->
|
|
<dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
|
|
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt" />
|
|
<filter class="solr.GalicianStemFilterFactory"/>
|
|
<!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Hindi -->
|
|
<dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
|
|
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<!-- normalizes unicode representation -->
|
|
<filter class="solr.IndicNormalizationFilterFactory"/>
|
|
<!-- normalizes variation in spelling -->
|
|
<filter class="solr.HindiNormalizationFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
|
|
<filter class="solr.HindiStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Hungarian -->
|
|
<dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Armenian -->
|
|
<dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
|
|
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Indonesian -->
|
|
<dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
|
|
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt" />
|
|
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Italian -->
|
|
<dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
|
|
<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"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
|
|
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
|
|
<analyzer>
|
|
|
|
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
<filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
|
|
<filter class="solr.CJKWidthFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
|
|
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Latvian -->
|
|
<dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
|
|
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt" />
|
|
<filter class="solr.LatvianStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Dutch -->
|
|
<dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
|
|
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
|
|
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Norwegian -->
|
|
<dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
|
|
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
|
|
<!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
|
|
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
|
|
</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>
|
|
|
|
<!-- Romanian -->
|
|
<dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
|
|
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Russian -->
|
|
<dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
|
|
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
|
|
<!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Swedish -->
|
|
<dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
|
|
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
|
|
<!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Thai -->
|
|
<dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
|
|
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.ThaiTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Turkish -->
|
|
<dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
|
|
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.TurkishLowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
</schema>
|
|
|