mirror of https://github.com/apache/lucene.git
550 lines
32 KiB
XML
550 lines
32 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!-- Solr managed schema - automatically generated - DO NOT EDIT -->
|
|
<schema name="example-data-driven-schema" version="1.6">
|
|
<uniqueKey>id</uniqueKey>
|
|
<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>
|
|
<fieldType name="binary" class="solr.BinaryField"/>
|
|
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
|
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
|
|
<fieldType name="currency" class="solr.CurrencyField" currencyConfig="currency.xml" defaultCurrency="USD" precisionStep="8"/>
|
|
<fieldType name="date" class="solr.TrieDateField" positionIncrementGap="0" precisionStep="0"/>
|
|
<fieldType name="dates" class="solr.TrieDateField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
|
|
<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>
|
|
<fieldType name="double" class="solr.TrieDoubleField" positionIncrementGap="0" precisionStep="0"/>
|
|
<fieldType name="doubles" class="solr.TrieDoubleField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
|
|
<fieldType name="float" class="solr.TrieFloatField" positionIncrementGap="0" precisionStep="0"/>
|
|
<fieldType name="floats" class="solr.TrieFloatField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
|
|
<fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" multiValued="true"/>
|
|
<fieldType name="int" class="solr.TrieIntField" positionIncrementGap="0" precisionStep="0"/>
|
|
<fieldType name="ints" class="solr.TrieIntField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
|
|
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
|
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/>
|
|
<fieldType name="long" class="solr.TrieLongField" positionIncrementGap="0" precisionStep="0"/>
|
|
<fieldType name="longs" class="solr.TrieLongField" positionIncrementGap="0" multiValued="true" precisionStep="0"/>
|
|
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
|
|
<fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
|
|
<fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
|
|
<fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
|
|
<fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="plong" class="solr.LongPointField" docValues="true"/>
|
|
<fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="point" class="solr.PointType" subFieldSuffix="_d" dimension="2"/>
|
|
<fieldType name="random" class="solr.RandomSortField" indexed="true"/>
|
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true"/>
|
|
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true"/>
|
|
<fieldType name="tdate" class="solr.TrieDateField" positionIncrementGap="0" precisionStep="6"/>
|
|
<fieldType name="tdates" class="solr.TrieDateField" positionIncrementGap="0" multiValued="true" precisionStep="6"/>
|
|
<fieldType name="tdouble" class="solr.TrieDoubleField" positionIncrementGap="0" precisionStep="8"/>
|
|
<fieldType name="tdoubles" class="solr.TrieDoubleField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
|
|
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_ar.txt" ignoreCase="true"/>
|
|
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
<filter class="solr.ArabicStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_bg.txt" ignoreCase="true"/>
|
|
<filter class="solr.BulgarianStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_ca.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_ca.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.CJKWidthFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.CJKBigramFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_cz.txt" ignoreCase="true"/>
|
|
<filter class="solr.CzechStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/>
|
|
<filter class="solr.GermanNormalizationFilterFactory"/>
|
|
<filter class="solr.GermanLightStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_el.txt" ignoreCase="false"/>
|
|
<filter class="solr.GreekStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
|
|
<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.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.EnglishPossessiveFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.PorterStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="true"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.EnglishMinimalStemFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/>
|
|
<filter class="solr.SpanishLightStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_eu.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<charFilter class="solr.PersianCharFilterFactory"/>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
<filter class="solr.PersianNormalizationFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_fa.txt" ignoreCase="true"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_fr.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/>
|
|
<filter class="solr.FrenchLightStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_ga.txt" ignoreCase="true"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/hyphenations_ga.txt" ignoreCase="true"/>
|
|
<filter class="solr.IrishLowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_ga.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
|
|
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_gl.txt" ignoreCase="true"/>
|
|
<filter class="solr.GalicianStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.IndicNormalizationFilterFactory"/>
|
|
<filter class="solr.HindiNormalizationFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_hi.txt" ignoreCase="true"/>
|
|
<filter class="solr.HindiStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_hy.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_id.txt" ignoreCase="true"/>
|
|
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt" ignoreCase="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/>
|
|
<filter class="solr.ItalianLightStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_ja" class="solr.TextField" autoGeneratePhraseQueries="false" positionIncrementGap="100">
|
|
<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" words="lang/stopwords_ja.txt" ignoreCase="true"/>
|
|
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_lv.txt" ignoreCase="true"/>
|
|
<filter class="solr.LatvianStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/>
|
|
<filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/>
|
|
<filter class="solr.PortugueseLightStemFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_ro.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.ThaiTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_th.txt" ignoreCase="true"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.TurkishLowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" words="lang/stopwords_tr.txt" ignoreCase="false"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="tfloat" class="solr.TrieFloatField" positionIncrementGap="0" precisionStep="8"/>
|
|
<fieldType name="tfloats" class="solr.TrieFloatField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
|
|
<fieldType name="tint" class="solr.TrieIntField" positionIncrementGap="0" precisionStep="8"/>
|
|
<fieldType name="tints" class="solr.TrieIntField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
|
|
<fieldType name="tlong" class="solr.TrieLongField" positionIncrementGap="0" precisionStep="8"/>
|
|
<fieldType name="tlongs" class="solr.TrieLongField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
|
|
|
|
<fieldType name="text_email_url" class="solr.TextField">
|
|
<analyzer>
|
|
<tokenizer class="solr.UAX29URLEmailTokenizerFactory"/>
|
|
<filter class="solr.TypeTokenFilterFactory" types="email_url_types.txt" useWhitelist="true"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<fieldType name="text_shingles" class="solr.TextField" positionIncrementGap="100" multiValued="true">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<!-- <filter class="solr.StopFilterFactory" words="lang/stopwords_en.txt" ignoreCase="false" /> -->
|
|
<filter class="solr.LengthFilterFactory" min="2" max="18"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.PatternReplaceFilterFactory" pattern="(^[^a-z]+$)" replacement="" replace="all"/>
|
|
<filter class="solr.ShingleFilterFactory" minShingleSize="3" maxShingleSize="3"
|
|
outputUnigrams="false" outputUnigramsIfNoShingles="false" tokenSeparator=" " fillerToken="*"/>
|
|
<filter class="solr.PatternReplaceFilterFactory" pattern="(.*[\*].*)" replacement=""/>
|
|
<filter class="solr.TrimFilterFactory"/>
|
|
|
|
<!-- PRFF could have removed everything down to an empty string, remove if so -->
|
|
<filter class="solr.LengthFilterFactory" min="1" max="100"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<field name="id" type="string" multiValued="false" indexed="true" required="true" stored="true"/>
|
|
<field name="_version_" type="long" indexed="true" stored="true"/>
|
|
<field name="content_type" type="string" indexed="true" stored="true"/>
|
|
<field name="doc_type" type="string" indexed="true" stored="true"/>
|
|
<field name="title" type="string" indexed="true" stored="true"/>
|
|
<field name="language" type="string" indexed="true" stored="true"/>
|
|
<field name="content" type="text_general" multiValued="false" indexed="true" stored="true"/>
|
|
<field name="text_shingles" type="text_shingles" indexed="true" stored="false"/>
|
|
<field name="_text_" type="text_general" multiValued="true" indexed="true" stored="false"/>
|
|
|
|
<dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
|
|
<dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
|
|
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
|
|
<dynamicField name="ignored_*" type="ignored" multiValued="true"/>
|
|
<dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
|
|
<dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
|
|
<dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
|
|
<dynamicField name="random_*" type="random"/>
|
|
<dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
|
|
<dynamicField name="*_point" type="point" indexed="true" stored="true"/>
|
|
<dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tdts" type="tdates" indexed="true" stored="true"/>
|
|
<dynamicField name="attr_*" type="text_general" multiValued="true" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pdts" type="pdates" indexed="true" stored="true"/>
|
|
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
|
|
<dynamicField name="*_dts" type="date" multiValued="true" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tis" type="tints" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tls" type="tlongs" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tfs" type="tfloats" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tds" type="tdoubles" indexed="true" stored="true"/>
|
|
<dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pds" type="pdoubles" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pfs" type="pfloats" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pis" type="pints" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pls" type="plongs" indexed="true" stored="true"/>
|
|
<dynamicField name="*_is" type="ints" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ls" type="longs" indexed="true" stored="true"/>
|
|
<dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
|
|
<dynamicField name="*_fs" type="floats" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ds" type="doubles" indexed="true" stored="true"/>
|
|
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
|
<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="*_ws" type="text_ws" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
|
|
<dynamicField name="*_pl" type="plong" 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="*_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="*_p" type="location" indexed="true" stored="true"/>
|
|
<dynamicField name="*_c" type="currency" indexed="true" stored="true"/>
|
|
|
|
<copyField source="content" dest="text_shingles"/>
|
|
<copyField source="*" dest="_text_"/>
|
|
|
|
|
|
</schema>
|