solr.Items.conf.schema.xml Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of mklab-framework-client Show documentation
Show all versions of mklab-framework-client Show documentation
The project contains a set of convenience methods on top of common data repositories.
The newest version!
<?xml version="1.0" encoding="utf-8"?>
<schema name="items" version="1.5">
<fields>
<!-- Item fields -->
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<field name="source" type="string" indexed="true" stored="false" multiValued="false" />
<field name="original" type="boolean" indexed="true" stored="false" multiValued="false" />
<field name="title" type="text_en" indexed="true" stored="true" multiValued="false" />
<field name="description" type="text_en" indexed="true" stored="false" multiValued="false" />
<field name="tags" type="tags" indexed="true" stored="true" multiValued="true" />
<field name="uid" type="string" indexed="true" stored="false" multiValued="false" />
<field name="username" type="tags" indexed="true" stored="false" multiValued="false" />
<field name="reference" type="string" indexed="true" stored="false" multiValued="false" />
<field name="publicationTime" type="long" indexed="true" stored="false" multiValued="false" />
<field name="language" type="string" indexed="true" stored="false" multiValued="false" />
<field name="latitude" type="double" indexed="true" stored="false" multiValued="false" />
<field name="longitude" type="double" indexed="true" stored="false" multiValued="false" />
<field name="location" type="string" indexed="true" stored="false" multiValued="false" />
<field name="city" type="string" indexed="true" stored="false" multiValued="false" />
<field name="country" type="string" indexed="true" stored="false" multiValued="false" />
<field name="latlon" type="location_latlon" indexed="true" stored="true" multiValued="false" />
<field name="latlonRPT" type="location_rpt" indexed="true" stored="true" multiValued="false" />
<field name="labels" type="string" indexed="true" stored="false" multiValued="true" />
<field name="mediaIds" type="string" indexed="true" stored="false" multiValued="true" />
<field name="persons" type="tags" indexed="true" stored="false" multiValued="true" />
<field name="locations" type="tags" indexed="true" stored="false" multiValued="true" />
<field name="organizations" type="tags" indexed="true" stored="false" multiValued="true" />
<field name="mentions" type="string" indexed="true" stored="false" multiValued="true" />
<field name="text" type="text_ws" indexed="true" stored="false" multiValued="false" />
<field name="allText" type="text_general" indexed="true" stored="false" multiValued="true" />
<field name="text1" type="text_general" indexed="true" stored="false" multiValued="false" />
<field name="text2" type="text_en_splitting" indexed="true" stored="false" multiValued="false" />
<field name="text3" type="text_en_splitting_tight" indexed="true" stored="false" multiValued="false" />
<field name="referenceUserId" type="string" indexed="true" stored="false" multiValued="true" />
<field name="likes" type="long" indexed="true" stored="false" multiValued="false" />
<field name="comments" type="long" indexed="true" stored="false" multiValued="false" />
<field name="shares" type="long" indexed="true" stored="false" multiValued="false" />
<field name="followers" type="long" indexed="true" stored="false" multiValued="false" />
<field name="friends" type="long" indexed="true" stored="false" multiValued="false" />
<!-- Type used to index the lat and lon components for the "location" FieldType -->
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" />
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
<field name="_version_" type="long" indexed="true" stored="true" />
</fields>
<uniqueKey>id</uniqueKey>
<copyField source="title" dest="text1" />
<copyField source="title" dest="text2" />
<copyField source="title" dest="text3" />
<copyField source="title" dest="allText" />
<copyField source="description" dest="allText" />
<copyField source="tags" dest="allText" />
<copyField source="persons" dest="allText" />
<copyField source="organizations" dest="allText" />
<types>
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" />
<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="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0" />
<fieldtype name="binary" class="solr.BinaryField" />
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<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"/>
<!-- A specialized field for geo-spatial search. If indexed, this fieldType must not be multi-valued. -->
<fieldType name="location_latlon" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
<!-- A specialized field for geo-spatial search. -->
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory" />
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="tags" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory" />
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!-- A general text field that has reasonable, generic cross-language defaults: it tokenizes with StandardTokenizer,
removes stop words from case-insensitive "lang/stopwords_en.txt" (empty by default), and down cases. -->
<fieldType name="text_general" 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" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" />
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English: it tokenizes with StandardTokenizer, removes English stop words
(lang/stopwords_en.txt), down cases and finally applies Porter's stemming. -->
<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.EnglishMinimalStemFilterFactory"/> -->
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
<analyzer type="query">
<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.EnglishMinimalStemFilterFactory"/> -->
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English, plus aggressive word-splitting and autophrase features enabled.
This field is just like text_en, except it adds WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars. This means certain compound word
cases will work, for example query "wi fi" will match document "WiFi" or "wi-fi".
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory" />
<!-- Case insensitive stop word removal. add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries. -->
<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.PorterStemFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory" />
<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.PorterStemFilterFactory" />
</analyzer>
</fieldType>
<!-- Less flexible matching, but less false matches. Probably not ideal for product names, but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory" />
<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.EnglishMinimalStemFilterFactory" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory" />
</analyzer>
</fieldType>
<!-- Different languages (generally ordered by ISO code) -->
<!-- Arabic -->
<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 -->
<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 -->
<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) -->
<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 -->
<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 -->
<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 -->
<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" />
<!-- 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 -->
<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 -->
<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 -->
<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 -->
<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>
<!-- Irish -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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" />
<!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
<filter class="solr.IndonesianStemFilterFactory" stemDerivational="true" />
</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>
<!-- Japanese using morphological analysis -->
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
<analyzer>
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" />
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter class="solr.JapaneseBaseFormFilterFactory" />
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
<filter class="solr.CJKWidthFilterFactory" />
<!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
<!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4" />
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!-- Latvian -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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>
<!-- Turkish -->
<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>
</types>
</schema>
© 2015 - 2025 Weber Informatics LLC | Privacy Policy