Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SOLR-13690: Migrate field type configurations in default/example schema files to look up factories by 'name'

This commit is contained in:
Tomoko Uchida 2019-08-31 23:06:32 +09:00
parent ea67d9c8c6
commit 77c1ed7d16
9 changed files with 1487 additions and 1487 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
solr/CHANGES.txt
View File

@ -64,7 +64,7 @@ Upgrade Notes
* SOLR-11266: default Content-Type override for JSONResponseWriter from _default configSet is removed. Example has been
provided in sample_techproducts_configs to override content-type. (Ishan Chattopadhyaya, Munendra S N, Gus Heck)
* SOLR-13593: Allow to look up analyzer components by their SPI names in field type configuration. (Tomoko Uchida)
* SOLR-13593 SOLR-13690: Allow to look up analyzer components by their SPI names in field type configuration. (Tomoko Uchida)
Other Changes
----------------------

36
solr/example/example-DIH/solr/atom/conf/managed-schema
View File

@ -61,31 +61,31 @@
<fieldType name="text_en_splitting" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal. -->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1"
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" 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"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" generateWordParts="1" generateNumberParts="1"
<filter name="wordDelimiterGraph" 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"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -95,11 +95,11 @@
-->
<fieldType name="url_only" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.UAX29URLEmailTokenizerFactory" maxTokenLength="255"/>
<filter class="solr.TypeTokenFilterFactory" types="url_types.txt" useWhitelist="true"/>
<tokenizer name="UAX29URLEmail" maxTokenLength="255"/>
<filter name="type" types="url_types.txt" useWhitelist="true"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
</analyzer>
</fieldType>

488
solr/example/example-DIH/solr/db/conf/managed-schema
View File

@ -389,7 +389,7 @@
<!-- 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"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
@ -400,19 +400,19 @@
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -423,39 +423,39 @@
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -470,33 +470,33 @@
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -504,29 +504,29 @@
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 type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="removeDuplicates"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter name="removeDuplicates"/>
</analyzer>
</fieldType>
@ -534,17 +534,17 @@
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
<filter name="reversedWildcard" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -552,8 +552,8 @@
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<charFilter name="mapping" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
-->
@ -567,13 +567,13 @@
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<filter name="lowercase" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<filter name="trim" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
@ -585,7 +585,7 @@
http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
<filter name="patternReplace"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
@ -593,14 +593,14 @@
<fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
<tokenizer name="standard"/>
<filter name="doubleMetaphone" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
@ -612,15 +612,15 @@
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
<filter name="delimitedPayload" encoder="float"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<tokenizer name="keyword"/>
<filter name="lowercase" />
</analyzer>
</fieldType>
@ -630,10 +630,10 @@
-->
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
</fieldType>
<!--
@ -642,10 +642,10 @@
-->
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
</fieldType>
@ -701,124 +701,124 @@
<!-- Arabic -->
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ar.txt" />
<!-- normalizes ﻯ to ﻱ, etc -->
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
<filter name="arabicNormalization"/>
<filter name="arabicStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_bg.txt" />
<filter name="bulgarianStem"/>
</analyzer>
</fieldType>
<!-- Catalan -->
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/>
<filter name="elision" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ca.txt" />
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
<filter class="solr.CJKWidthFilterFactory"/>
<filter name="cjkWidth"/>
<!-- for any non-CJK -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
<filter name="lowercase"/>
<filter name="cjkBigram"/>
</analyzer>
</fieldType>
<!-- Kurdish -->
<fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SoraniNormalizationFilterFactory"/>
<tokenizer name="standard"/>
<filter name="soraniNormalization"/>
<!-- for any latin text -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter class="solr.SoraniStemFilterFactory"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter name="soraniStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_cz.txt" />
<filter name="czechStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter name="germanNormalization"/>
<filter name="germanLightStem"/>
<!-- less aggressive: <filter name="germanMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="German2"/> -->
</analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
<filter name="greekLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter name="greekStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter name="spanishLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_eu.txt" />
<filter name="snowballPorter" language="Basque"/>
</analyzer>
</fieldType>
@ -826,121 +826,121 @@
<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" />
<charFilter name="persian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="arabicNormalization"/>
<filter name="persianNormalization"/>
<filter name="stop" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter name="snowballPorter" language="Finnish"/>
<!-- less aggressive: <filter name="finnishLightStem"/> -->
</analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter name="frenchLightStem"/>
<!-- less aggressive: <filter name="frenchMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="French"/> -->
</analyzer>
</fieldType>
<!-- Irish -->
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
<filter name="elision" 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"/>
<filter name="stop" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
<filter name="irishLowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ga.txt"/>
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_gl.txt" />
<filter name="galicianStem"/>
<!-- less aggressive: <filter name="galicianMinimalStem"/> -->
</analyzer>
</fieldType>
<!-- Hindi -->
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<!-- normalizes unicode representation -->
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter name="indicNormalization"/>
<!-- normalizes variation in spelling -->
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter class="solr.HindiStemFilterFactory"/>
<filter name="hindiNormalization"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter name="hindiStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter name="snowballPorter" language="Hungarian"/>
<!-- less aggressive: <filter name="hungarianLightStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hy.txt" />
<filter name="snowballPorter" 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" />
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" 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"/>
<filter name="indonesianStem" stemDerivational="true"/>
</analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter name="italianLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Italian"/> -->
</analyzer>
</fieldType>
@ -979,20 +979,20 @@
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<tokenizer name="japanese" mode="search"/>
<!--<tokenizer name="japanese" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter name="japaneseBaseForm"/>
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<filter name="japanesePartOfSpeechStop" 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"/>
<filter name="cjkWidth"/>
<!-- 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" />
<filter name="stop" 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"/>
<filter name="japaneseKatakanaStem" minimumLength="4"/>
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -1017,49 +1017,49 @@
* decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
* outputUnknownUnigrams: If true outputs unigrams for unknown words.
-->
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
<tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
<!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
listing the tags to remove. By default it removes:
E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
This is basically an equivalent to stemming.
-->
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
<filter name="koreanPartOfSpeechStop" />
<!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
<filter class="solr.KoreanReadingFormFilterFactory" />
<filter class="solr.LowerCaseFilterFactory" />
<filter name="koreanReadingForm" />
<filter name="lowercase" />
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_lv.txt" />
<filter name="latvianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
<filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter name="snowballPorter" 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" variant="nb"/> -->
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
<filter name="snowballPorter" language="Norwegian"/>
<!-- less aggressive: <filter name="norwegianLightStem" variant="nb"/> -->
<!-- singular/plural: <filter name="norwegianMinimalStem" variant="nb"/> -->
<!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</analyzer>
</fieldType>
@ -1067,65 +1067,65 @@
<!-- 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
<filter name="portugueseLightStem"/>
<!-- less aggressive: <filter name="prtugueseMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="Portuguese"/> -->
<!-- most aggressive: <filter name="prtugueseStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ro.txt" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
<filter name="snowballPorter" language="Russian"/>
<!-- less aggressive: <filter name="russianLightStem"/> -->
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
<filter name="snowballPorter" language="Swedish"/>
<!-- less aggressive: <filter name="swedishLightStem"/> -->
</analyzer>
</fieldType>
<!-- Thai -->
<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" />
<tokenizer name="thai"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_th.txt" />
</analyzer>
</fieldType>
<!-- Turkish -->
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ApostropheFilterFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
<tokenizer name="standard"/>
<filter name="apostrophe"/>
<filter name="turkishLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter name="snowballPorter" language="Turkish"/>
</analyzer>
</fieldType>

490
solr/example/example-DIH/solr/mail/conf/managed-schema
View File

@ -308,7 +308,7 @@
<!-- 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"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
@ -319,19 +319,19 @@
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -342,39 +342,39 @@
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -389,33 +389,33 @@
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -423,29 +423,29 @@
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 type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="removeDuplicates"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter name="removeDuplicates"/>
</analyzer>
</fieldType>
@ -453,17 +453,17 @@
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
<filter name="reversedWildcard" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -471,8 +471,8 @@
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<charFilter name="mapping" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
-->
@ -486,13 +486,13 @@
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<filter name="lowercase" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<filter name="trim" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
@ -504,7 +504,7 @@
http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
<filter name="patternReplace"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
@ -512,14 +512,14 @@
<fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
<tokenizer name="standard"/>
<filter name="doubleMetaphone" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
@ -531,15 +531,15 @@
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
<filter name="delimitedPayload" encoder="float"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<tokenizer name="keyword"/>
<filter name="lowercase" />
</analyzer>
</fieldType>
@ -549,10 +549,10 @@
-->
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
</fieldType>
<!--
@ -561,10 +561,10 @@
-->
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
</fieldType>
@ -620,124 +620,124 @@
<!-- Arabic -->
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ar.txt" />
<!-- normalizes ﻯ to ﻱ, etc -->
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
<filter name="arabicNormalization"/>
<filter name="arabicStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_bg.txt" />
<filter name="bulgarianStem"/>
</analyzer>
</fieldType>
<!-- Catalan -->
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/>
<filter name="elision" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ca.txt" />
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
<filter class="solr.CJKWidthFilterFactory"/>
<filter name="cjkWidth"/>
<!-- for any non-CJK -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
<filter name="lowercase"/>
<filter name="cjkBigram"/>
</analyzer>
</fieldType>
<!-- Kurdish -->
<fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SoraniNormalizationFilterFactory"/>
<tokenizer name="standard"/>
<filter name="soraniNormalization"/>
<!-- for any latin text -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter class="solr.SoraniStemFilterFactory"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter name="soraniStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_cz.txt" />
<filter name="czechStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter name="germanNormalization"/>
<filter name="germanLightStem"/>
<!-- less aggressive: <filter name="germanMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="German2"/> -->
</analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
<filter name="greekLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter name="greekStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter name="spanishLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_eu.txt" />
<filter name="snowballPorter" language="Basque"/>
</analyzer>
</fieldType>
@ -745,121 +745,121 @@
<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" />
<charFilter name="persian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="arabicNormalization"/>
<filter name="persianNormalization"/>
<filter name="stop" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter name="snowballPorter" language="Finnish"/>
<!-- less aggressive: <filter name="finnishLightStem"/> -->
</analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter name="frenchLightStem"/>
<!-- less aggressive: <filter name="frenchMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="French"/> -->
</analyzer>
</fieldType>
<!-- Irish -->
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
<filter name="elision" 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"/>
<filter name="stop" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
<filter name="irishLowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ga.txt"/>
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_gl.txt" />
<filter name="galicianStem"/>
<!-- less aggressive: <filter name="galicianMinimalStem"/> -->
</analyzer>
</fieldType>
<!-- Hindi -->
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<!-- normalizes unicode representation -->
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter name="indicNormalization"/>
<!-- normalizes variation in spelling -->
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter class="solr.HindiStemFilterFactory"/>
<filter name="hindiNormalization"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter name="hindiStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter name="snowballPorter" language="Hungarian"/>
<!-- less aggressive: <filter name="hungarianLightStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hy.txt" />
<filter name="snowballPorter" 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" />
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" 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"/>
<filter name="indonesianStem" stemDerivational="true"/>
</analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter name="italianLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Italian"/> -->
</analyzer>
</fieldType>
@ -898,20 +898,20 @@
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<tokenizer name="japanese" mode="search"/>
<!--<tokenizer name="japanese" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter name="japaneseBaseForm"/>
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<filter name="japanesePartOfSpeechStop" 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"/>
<filter name="cjkWidth"/>
<!-- 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" />
<filter name="stop" 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"/>
<filter name="japaneseKatakanaStem" minimumLength="4"/>
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -936,115 +936,115 @@
* decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
* outputUnknownUnigrams: If true outputs unigrams for unknown words.
-->
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
<tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
<!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
listing the tags to remove. By default it removes:
E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
This is basically an equivalent to stemming.
-->
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
<filter name="koreanPartOfSpeechStop" />
<!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
<filter class="solr.KoreanReadingFormFilterFactory" />
<filter class="solr.LowerCaseFilterFactory" />
<filter name="koreanReadingForm" />
<filter name="lowercase" />
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_lv.txt" />
<filter name="latvianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
<filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter name="snowballPorter" 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" variant="nb"/> -->
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
<!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
<filter name="snowballPorter" language="Norwegian"/>
<!-- less aggressive: <filter name="norwegianLightStem" variant="nb"/> -->
<!-- singular/plural: <filter name="norwegianMinimalStem" variant="nb"/> -->
<!-- Tfhe "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
<filter name="portugueseLightStem"/>
<!-- less aggressive: <filter name="portugueseMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="Portuguese"/> -->
<!-- most aggressive: <filter name="portugueseStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ro.txt" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
<filter name="snowballPorter" language="Russian"/>
<!-- less aggressive: <filter name="russianLightStem"/> -->
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
<filter name="snowballPorter" language="Swedish"/>
<!-- less aggressive: <filter name="swedishLightStem"/> -->
</analyzer>
</fieldType>
<!-- Thai -->
<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" />
<tokenizer name="thai"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_th.txt" />
</analyzer>
</fieldType>
<!-- Turkish -->
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ApostropheFilterFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
<tokenizer name="standard"/>
<filter name="apostrophe"/>
<filter name="turkishLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter name="snowballPorter" language="Turkish"/>
</analyzer>
</fieldType>

488
solr/example/example-DIH/solr/solr/conf/managed-schema
View File

@ -389,7 +389,7 @@
<!-- 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"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
@ -400,19 +400,19 @@
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -423,39 +423,39 @@
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -470,33 +470,33 @@
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -504,29 +504,29 @@
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 type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="removeDuplicates"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter name="removeDuplicates"/>
</analyzer>
</fieldType>
@ -534,17 +534,17 @@
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
<filter name="reversedWildcard" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -552,8 +552,8 @@
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<charFilter name="mapping" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
-->
@ -567,13 +567,13 @@
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<filter name="lowercase" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<filter name="trim" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
@ -585,7 +585,7 @@
http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
<filter name="patternReplace"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
@ -593,14 +593,14 @@
<fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
<tokenizer name="standard"/>
<filter name="doubleMetaphone" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
@ -612,15 +612,15 @@
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
<filter name="delimitedPayload" encoder="float"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<tokenizer name="keyword"/>
<filter name="lowercase" />
</analyzer>
</fieldType>
@ -630,10 +630,10 @@
-->
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
</fieldType>
<!--
@ -642,10 +642,10 @@
-->
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
</fieldType>
@ -701,124 +701,124 @@
<!-- Arabic -->
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ar.txt" />
<!-- normalizes ﻯ to ﻱ, etc -->
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
<filter name="arabicNormalization"/>
<filter name="arabicStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_bg.txt" />
<filter name="bulgarianStem"/>
</analyzer>
</fieldType>
<!-- Catalan -->
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/>
<filter name="elision" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ca.txt" />
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
<filter class="solr.CJKWidthFilterFactory"/>
<filter name="cjkWidth"/>
<!-- for any non-CJK -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
<filter name="lowercase"/>
<filter name="cjkBigram"/>
</analyzer>
</fieldType>
<!-- Kurdish -->
<fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SoraniNormalizationFilterFactory"/>
<tokenizer name="standard"/>
<filter name="soraniNormalization"/>
<!-- for any latin text -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter class="solr.SoraniStemFilterFactory"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter name="soraniStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_cz.txt" />
<filter name="czechStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter name="germanNormalization"/>
<filter name="germanLightStem"/>
<!-- less aggressive: <filter name="germanMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="German2"/> -->
</analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
<filter name="greekLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter name="greekStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter name="spanishLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_eu.txt" />
<filter name="snowballPorter" language="Basque"/>
</analyzer>
</fieldType>
@ -826,121 +826,121 @@
<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" />
<charFilter name="persian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="arabicNormalization"/>
<filter name="persianNormalization"/>
<filter name="stop" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter name="snowballPorter" language="Finnish"/>
<!-- less aggressive: <filter name="finnishLightStem"/> -->
</analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter name="frenchLightStem"/>
<!-- less aggressive: <filter name="frenchMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="French"/> -->
</analyzer>
</fieldType>
<!-- Irish -->
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
<filter name="elision" 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"/>
<filter name="stop" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
<filter name="irishLowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ga.txt"/>
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_gl.txt" />
<filter name="galicianStem"/>
<!-- less aggressive: <filter name="galicianMinimalStem"/> -->
</analyzer>
</fieldType>
<!-- Hindi -->
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<!-- normalizes unicode representation -->
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter name="indicNormalization"/>
<!-- normalizes variation in spelling -->
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter class="solr.HindiStemFilterFactory"/>
<filter name="hindiNormalization"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter name="hindiStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter name="snowballPorter" language="Hungarian"/>
<!-- less aggressive: <filter name="hungarianLightStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hy.txt" />
<filter name="snowballPorter" 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" />
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" 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"/>
<filter name="indonesianStem" stemDerivational="true"/>
</analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter name="italianLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Italian"/> -->
</analyzer>
</fieldType>
@ -979,20 +979,20 @@
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<tokenizer name="japanese" mode="search"/>
<!--<tokenizer name="japanese" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter name="japaneseBaseForm"/>
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<filter name="japanesePartOfSpeechStop" 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"/>
<filter name="cjkWidth"/>
<!-- 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" />
<filter name="stop" 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"/>
<filter name="japaneseKatakanaStem" minimumLength="4"/>
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -1017,49 +1017,49 @@
* decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
* outputUnknownUnigrams: If true outputs unigrams for unknown words.
-->
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
<tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
<!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
listing the tags to remove. By default it removes:
E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
This is basically an equivalent to stemming.
-->
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
<filter name="koreanPartOfSpeechStop" />
<!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
<filter class="solr.KoreanReadingFormFilterFactory" />
<filter class="solr.LowerCaseFilterFactory" />
<filter name="koreanReadingForm" />
<filter name="lowercase" />
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_lv.txt" />
<filter name="latvianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
<filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter name="snowballPorter" 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" variant="nb"/> -->
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
<filter name="snowballPorter" language="Norwegian"/>
<!-- less aggressive: <filter name="norwegianLightStem" variant="nb"/> -->
<!-- singular/plural: <filter name="norwegianMinimalStem" variant="nb"/> -->
<!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</analyzer>
</fieldType>
@ -1067,65 +1067,65 @@
<!-- 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
<filter name="portugueseLightStem"/>
<!-- less aggressive: <filter name="portugueseMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="Portuguese"/> -->
<!-- most aggressive: <filter name="portugueseStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ro.txt" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
<filter name="snowballPorter" language="Russian"/>
<!-- less aggressive: <filter name="russianLightStem"/> -->
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
<filter name="snowballPorter" language="Swedish"/>
<!-- less aggressive: <filter name="swedishLightStem"/> -->
</analyzer>
</fieldType>
<!-- Thai -->
<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" />
<tokenizer name="thai"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_th.txt" />
</analyzer>
</fieldType>
<!-- Turkish -->
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ApostropheFilterFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
<tokenizer name="standard"/>
<filter name="apostrophe"/>
<filter name="turkishLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter name="snowballPorter" language="Turkish"/>
</analyzer>
</fieldType>

4
solr/example/example-DIH/solr/tika/conf/managed-schema
View File

@ -46,8 +46,8 @@
-->
<fieldType name="text_simple" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>

438
solr/example/files/conf/managed-schema
View File

@ -4,10 +4,10 @@
<uniqueKey>id</uniqueKey>
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
<tokenizer name="pathHierarchy" delimiter="/"/>
</analyzer>
</fieldType>
<fieldType name="binary" class="solr.BinaryField"/>
@ -16,10 +16,10 @@
<fieldType name="currency" class="solr.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns" defaultCurrency="USD" currencyConfig="currency.xml" />
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/"/>
<tokenizer name="pathHierarchy" delimiter="/"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
</analyzer>
</fieldType>
<fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" multiValued="true"/>
@ -27,14 +27,14 @@
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType" geo="true" maxDistErr="0.001" distErrPct="0.025" distanceUnits="kilometers"/>
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="keyword"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
<fieldType name="phonetic_en" class="solr.TextField" indexed="true" stored="false">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
<tokenizer name="standard"/>
<filter name="doubleMetaphone" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
@ -53,386 +53,386 @@
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true"/>
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_ar.txt" ignoreCase="true"/>
<filter name="arabicNormalization"/>
<filter name="arabicStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_bg.txt" ignoreCase="true"/>
<filter name="bulgarianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="elision" articles="lang/contractions_ca.txt" ignoreCase="true"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_ca.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="cjkWidth"/>
<filter name="lowercase"/>
<filter name="cjkBigram"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_cz.txt" ignoreCase="true"/>
<filter name="czechStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_da.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_de.txt" ignoreCase="true"/>
<filter name="germanNormalization"/>
<filter name="germanLightStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="greekLowercase"/>
<filter name="stop" words="lang/stopwords_el.txt" ignoreCase="false"/>
<filter name="greekStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</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" />
<tokenizer name="whitespace"/>
<filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter name="wordDelimiterGraph" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter name="wordDelimiterGraph" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</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" />
<tokenizer name="whitespace"/>
<filter name="synonymGraph" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
<filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter name="wordDelimiterGraph" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<filter name="removeDuplicates"/>
<filter name="flattenGraph" />
</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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
<filter name="stop" words="lang/stopwords_en.txt" ignoreCase="true"/>
<filter name="wordDelimiterGraph" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<filter name="removeDuplicates"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_es.txt" ignoreCase="true"/>
<filter name="spanishLightStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_eu.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<charFilter name="persian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="arabicNormalization"/>
<filter name="persianNormalization"/>
<filter name="stop" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_fi.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="elision" articles="lang/contractions_fr.txt" ignoreCase="true"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_fr.txt" ignoreCase="true"/>
<filter name="frenchLightStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="elision" articles="lang/contractions_ga.txt" ignoreCase="true"/>
<filter name="stop" words="lang/hyphenations_ga.txt" ignoreCase="true"/>
<filter name="irishLowercase"/>
<filter name="stop" words="lang/stopwords_ga.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="stop" words="stopwords.txt" ignoreCase="true"/>
<filter name="lowercase"/>
</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"/>
<tokenizer name="standard"/>
<filter name="stop" words="stopwords.txt" ignoreCase="true"/>
<filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter name="lowercase"/>
</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"/>
<tokenizer name="standard"/>
<filter name="stop" words="stopwords.txt" ignoreCase="true"/>
<filter name="lowercase"/>
<filter name="reversedWildcard" 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"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
<filter name="stop" words="stopwords.txt" ignoreCase="true"/>
<filter name="lowercase"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_gl.txt" ignoreCase="true"/>
<filter name="galicianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="indicNormalization"/>
<filter name="hindiNormalization"/>
<filter name="stop" words="lang/stopwords_hi.txt" ignoreCase="true"/>
<filter name="hindiStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_hu.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_hy.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_id.txt" ignoreCase="true"/>
<filter name="indonesianStem" 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"/>
<tokenizer name="standard"/>
<filter name="elision" articles="lang/contractions_it.txt" ignoreCase="true"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_it.txt" ignoreCase="true"/>
<filter name="italianLightStem"/>
</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"/>
<tokenizer name="japanese" mode="search"/>
<filter name="japaneseBaseForm"/>
<filter name="japanesePartOfSpeechStop" tags="lang/stoptags_ja.txt"/>
<filter name="cjkWidth"/>
<filter name="stop" words="lang/stopwords_ja.txt" ignoreCase="true"/>
<filter name="japaneseKatakanaStem" minimumLength="4"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
<fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
<filter class="solr.KoreanReadingFormFilterFactory" />
<filter class="solr.LowerCaseFilterFactory" />
<tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
<filter name="koreanPartOfSpeechStop" />
<filter name="koreanReadingForm" />
<filter name="lowercase" />
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_lv.txt" ignoreCase="true"/>
<filter name="latvianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_nl.txt" ignoreCase="true"/>
<filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_no.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_pt.txt" ignoreCase="true"/>
<filter name="portugueseLightStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" words="lang/stopwords_ro.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_ru.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" format="snowball" words="lang/stopwords_sv.txt" ignoreCase="true"/>
<filter name="snowballPorter" 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"/>
<tokenizer name="thai"/>
<filter name="lowercase"/>
<filter name="stop" 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"/>
<tokenizer name="standard"/>
<filter name="turkishLowercase"/>
<filter name="stop" words="lang/stopwords_tr.txt" ignoreCase="false"/>
<filter name="snowballPorter" language="Turkish"/>
</analyzer>
</fieldType>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
<fieldType name="text_email_url" class="solr.TextField">
<analyzer>
<tokenizer class="solr.UAX29URLEmailTokenizerFactory"/>
<filter class="solr.TypeTokenFilterFactory" types="email_url_types.txt" useWhitelist="true"/>
<tokenizer name="UAX29URLEmail"/>
<filter name="type" 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]+$)" replacement="" replace="all"/>
<filter class="solr.ShingleFilterFactory" minShingleSize="3" maxShingleSize="3"
<tokenizer name="standard"/>
<!-- <filter name="stop" words="lang/stopwords_en.txt" ignoreCase="false" /> -->
<filter name="length" min="2" max="18"/>
<filter name="lowercase"/>
<filter name="patternReplace" pattern="(^[^a-z]+$)" replacement="" replace="all"/>
<filter name="shingle" minShingleSize="3" maxShingleSize="3"
outputUnigrams="false" outputUnigramsIfNoShingles="false" tokenSeparator=" " fillerToken="*"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="(.*[\*].*)" replacement=""/>
<filter class="solr.TrimFilterFactory"/>
<filter name="patternReplace" pattern="(.*[\*].*)" replacement=""/>
<filter name="trim"/>
<!-- PRFF could have removed everything down to an empty string, remove if so -->
<filter class="solr.LengthFilterFactory" min="1" max="100"/>
<filter name="length" min="1" max="100"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="keyword"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>

494
solr/server/solr/configsets/_default/conf/managed-schema
View File

@ -275,7 +275,7 @@
<dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
@ -287,19 +287,19 @@
-->
<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" />
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -316,15 +316,15 @@
<dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
<fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -334,39 +334,39 @@
<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"/>
<tokenizer name="standard"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
<filter name="englishMinimalStem"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -382,33 +382,33 @@
<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"/>
<tokenizer name="whitespace"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -417,29 +417,29 @@
<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 type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="removeDuplicates"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter name="removeDuplicates"/>
</analyzer>
</fieldType>
@ -449,25 +449,25 @@
<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"
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
<filter name="reversedWildcard" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</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"/>
<tokenizer name="standard"/>
<filter name="doubleMetaphone" inject="false"/>
</analyzer>
</fieldType>
@ -475,8 +475,8 @@
<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" />
<tokenizer name="keyword"/>
<filter name="lowercase" />
</analyzer>
</fieldType>
@ -487,10 +487,10 @@
<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="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
</fieldType>
@ -501,10 +501,10 @@
<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" />
<tokenizer name="keyword" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
</fieldType>
@ -535,20 +535,20 @@
<!-- Payloaded field types -->
<fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
<tokenizer name="whitespace"/>
<filter name="delimitedPayload" encoder="float"/>
</analyzer>
</fieldType>
<fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
<tokenizer name="whitespace"/>
<filter name="delimitedPayload" encoder="integer"/>
</analyzer>
</fieldType>
<fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
<tokenizer name="whitespace"/>
<filter name="delimitedPayload" encoder="identity"/>
</analyzer>
</fieldType>
@ -558,13 +558,13 @@
<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"/>
<tokenizer name="standard"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ar.txt" />
<!-- normalizes ﻯ to ﻱ, etc -->
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
<filter name="arabicNormalization"/>
<filter name="arabicStem"/>
</analyzer>
</fieldType>
@ -572,10 +572,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_bg.txt" />
<filter name="bulgarianStem"/>
</analyzer>
</fieldType>
@ -583,12 +583,12 @@
<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"/>
<tokenizer name="standard"/>
<!-- 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"/>
<filter name="elision" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ca.txt" />
<filter name="snowballPorter" language="Catalan"/>
</analyzer>
</fieldType>
@ -596,12 +596,12 @@
<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"/>
<tokenizer name="standard"/>
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
<filter class="solr.CJKWidthFilterFactory"/>
<filter name="CJKWidth"/>
<!-- for any non-CJK -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
<filter name="lowercase"/>
<filter name="CJKBigram"/>
</analyzer>
</fieldType>
@ -609,10 +609,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_cz.txt" />
<filter name="czechStem"/>
</analyzer>
</fieldType>
@ -620,10 +620,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
<filter name="snowballPorter" language="Danish"/>
</analyzer>
</fieldType>
@ -631,13 +631,13 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter name="germanNormalization"/>
<filter name="germanLightStem"/>
<!-- less aggressive: <filter name="germanMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="German2"/> -->
</analyzer>
</fieldType>
@ -645,11 +645,11 @@
<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"/>
<tokenizer name="standard"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
<filter name="greekLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter name="greekStem"/>
</analyzer>
</fieldType>
@ -657,11 +657,11 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter name="spanishLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Spanish"/> -->
</analyzer>
</fieldType>
@ -669,10 +669,10 @@
<dynamicField name="*_txt_et" type="text_et" indexed="true" stored="true"/>
<fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_et.txt" />
<filter name="snowballPorter" language="Estonian"/>
</analyzer>
</fieldType>
@ -680,10 +680,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_eu.txt" />
<filter name="snowballPorter" language="Basque"/>
</analyzer>
</fieldType>
@ -692,12 +692,12 @@
<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" />
<charFilter name="persian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="arabicNormalization"/>
<filter name="persianNormalization"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fa.txt" />
</analyzer>
</fieldType>
@ -705,11 +705,11 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter name="snowballPorter" language="Finnish"/>
<!-- less aggressive: <filter name="finnishLightStem"/> -->
</analyzer>
</fieldType>
@ -717,14 +717,14 @@
<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"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter name="frenchLightStem"/>
<!-- less aggressive: <filter name="frenchMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="French"/> -->
</analyzer>
</fieldType>
@ -732,14 +732,14 @@
<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"/>
<tokenizer name="standard"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
<filter name="elision" 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"/>
<filter name="stop" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
<filter name="irishLowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ga.txt"/>
<filter name="snowballPorter" language="Irish"/>
</analyzer>
</fieldType>
@ -747,11 +747,11 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_gl.txt" />
<filter name="galicianStem"/>
<!-- less aggressive: <filter name="galicianMinimalStem"/> -->
</analyzer>
</fieldType>
@ -759,14 +759,14 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<!-- normalizes unicode representation -->
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter name="indicNormalization"/>
<!-- normalizes variation in spelling -->
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter class="solr.HindiStemFilterFactory"/>
<filter name="hindiNormalization"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter name="hindiStem"/>
</analyzer>
</fieldType>
@ -774,11 +774,11 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter name="snowballPorter" language="Hungarian"/>
<!-- less aggressive: <filter name="hungarianLightStem"/> -->
</analyzer>
</fieldType>
@ -786,10 +786,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hy.txt" />
<filter name="snowballPorter" language="Armenian"/>
</analyzer>
</fieldType>
@ -797,11 +797,11 @@
<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" />
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" 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"/>
<filter name="indonesianStem" stemDerivational="true"/>
</analyzer>
</fieldType>
@ -809,13 +809,13 @@
<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"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter name="italianLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Italian"/> -->
</analyzer>
</fieldType>
@ -853,20 +853,20 @@
Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
-->
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<tokenizer name="japanese" mode="search"/>
<!--<tokenizer name="japanese" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter name="japaneseBaseForm"/>
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<filter name="japanesePartOfSpeechStop" 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"/>
<filter name="cjkWidth"/>
<!-- 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" />
<filter name="stop" 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"/>
<filter name="japaneseKatakanaStem" minimumLength="4"/>
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -891,16 +891,16 @@
* decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
* outputUnknownUnigrams: If true outputs unigrams for unknown words.
-->
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
<tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
<!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
listing the tags to remove. By default it removes:
E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
This is basically an equivalent to stemming.
-->
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
<filter name="koreanPartOfSpeechStop" />
<!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
<filter class="solr.KoreanReadingFormFilterFactory" />
<filter class="solr.LowerCaseFilterFactory" />
<filter name="koreanReadingForm" />
<filter name="lowercase" />
</analyzer>
</fieldType>
@ -908,10 +908,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_lv.txt" />
<filter name="latvianStem"/>
</analyzer>
</fieldType>
@ -919,11 +919,11 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
<filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter name="snowballPorter" language="Dutch"/>
</analyzer>
</fieldType>
@ -931,12 +931,12 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
<filter name="snowballPorter" language="Norwegian"/>
<!-- less aggressive: <filter name="norwegianLightStem"/> -->
<!-- singular/plural: <filter name="norwegianMinimalStem"/> -->
</analyzer>
</fieldType>
@ -944,13 +944,13 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
<filter name="portugueseLightStem"/>
<!-- less aggressive: <filter name="portugueseMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="Portuguese"/> -->
<!-- most aggressive: <filter name="portugueseStem"/> -->
</analyzer>
</fieldType>
@ -958,10 +958,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ro.txt" />
<filter name="snowballPorter" language="Romanian"/>
</analyzer>
</fieldType>
@ -969,11 +969,11 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
<filter name="snowballPorter" language="Russian"/>
<!-- less aggressive: <filter name="russianLightStem"/> -->
</analyzer>
</fieldType>
@ -981,11 +981,11 @@
<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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
<filter name="snowballPorter" language="Swedish"/>
<!-- less aggressive: <filter name="swedishLightStem"/> -->
</analyzer>
</fieldType>
@ -993,9 +993,9 @@
<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" />
<tokenizer name="thai"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_th.txt" />
</analyzer>
</fieldType>
@ -1003,10 +1003,10 @@
<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"/>
<tokenizer name="standard"/>
<filter name="turkishLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter name="snowballPorter" language="Turkish"/>
</analyzer>
</fieldType>

534
solr/server/solr/configsets/sample_techproducts_configs/conf/managed-schema
View File

@ -382,22 +382,22 @@
<!-- 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"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
<!-- A text type for English text where stopwords and synonyms are managed using the REST API -->
<fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ManagedStopFilterFactory" managed="english" />
<filter class="solr.ManagedSynonymGraphFilterFactory" managed="english" />
<filter class="solr.FlattenGraphFilterFactory"/>
<tokenizer name="standard"/>
<filter name="managedStop" managed="english" />
<filter name="managedSynonymGraph" managed="english" />
<filter name="flattenGraph"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ManagedStopFilterFactory" managed="english" />
<filter class="solr.ManagedSynonymGraphFilterFactory" managed="english" />
<tokenizer name="standard"/>
<filter name="managedStop" managed="english" />
<filter name="managedSynonymGraph" managed="english" />
</analyzer>
</fieldType>
@ -408,19 +408,19 @@
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -434,15 +434,15 @@
-->
<fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -453,39 +453,39 @@
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.FlattenGraphFilterFactory"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="flattenGraph"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter name="englishMinimalStem"/>
-->
<filter name="porterStem"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
<filter name="lowercase"/>
<filter name="englishPossessive"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter name="englishMinimalStem"/>
-->
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -500,33 +500,33 @@
-->
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="synonymGraph" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
-->
<filter class="solr.StopFilterFactory"
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop"
ignoreCase="true"
words="lang/stopwords_en.txt"
/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<filter name="wordDelimiterGraph" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="porterStem"/>
</analyzer>
</fieldType>
@ -534,29 +534,29 @@
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 type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.FlattenGraphFilterFactory" />
<filter name="removeDuplicates"/>
<filter name="flattenGraph" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.WordDelimiterGraphFilterFactory" 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"/>
<tokenizer name="whitespace"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter name="wordDelimiterGraph" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter name="lowercase"/>
<filter name="keywordMarker" protected="protwords.txt"/>
<filter name="englishMinimalStem"/>
<!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
possible with WordDelimiterGraphFilter in conjuncton with stemming. -->
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter name="removeDuplicates"/>
</analyzer>
</fieldType>
@ -564,17 +564,17 @@
each token, to enable more efficient leading wildcard queries. -->
<fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
<tokenizer name="standard"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
<filter name="reversedWildcard" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="synonymGraph" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter name="stop" ignoreCase="true" words="stopwords.txt" />
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -582,8 +582,8 @@
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<charFilter name="mapping" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>
-->
@ -597,13 +597,13 @@
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<tokenizer name="keyword"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<filter name="lowercase" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<filter name="trim" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
@ -615,7 +615,7 @@
http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
<filter name="patternReplace"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
@ -623,14 +623,14 @@
<fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
<tokenizer name="standard"/>
<filter name="doubleMetaphone" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
@ -642,15 +642,15 @@
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
<filter name="delimitedPayload" encoder="float"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
<tokenizer name="keyword"/>
<filter name="lowercase" />
</analyzer>
</fieldType>
@ -660,10 +660,10 @@
-->
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
</fieldType>
<!--
@ -672,10 +672,10 @@
-->
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory" />
<tokenizer name="keyword" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
<tokenizer name="pathHierarchy" delimiter="/" />
</analyzer>
</fieldType>
@ -737,134 +737,134 @@
<!-- Arabic -->
<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- for any non-arabic -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt" />
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ar.txt" />
<!-- normalizes ﻯ to ﻱ, etc -->
<filter class="solr.ArabicNormalizationFilterFactory"/>
<filter class="solr.ArabicStemFilterFactory"/>
<filter name="arabicNormalization"/>
<filter name="arabicStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_bg.txt" />
<filter name="bulgarianStem"/>
</analyzer>
</fieldType>
<!-- Catalan -->
<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/>
<filter name="elision" ignoreCase="true" articles="lang/contractions_ca.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ca.txt" />
<filter name="snowballPorter" 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"/>
<tokenizer name="standard"/>
<!-- normalize width before bigram, as e.g. half-width dakuten combine -->
<filter class="solr.CJKWidthFilterFactory"/>
<filter name="cjkWidth"/>
<!-- for any non-CJK -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.CJKBigramFilterFactory"/>
<filter name="lowercase"/>
<filter name="cjkBigram"/>
</analyzer>
</fieldType>
<!-- Kurdish -->
<fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SoraniNormalizationFilterFactory"/>
<tokenizer name="standard"/>
<filter name="soraniNormalization"/>
<!-- for any latin text -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter class="solr.SoraniStemFilterFactory"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter name="soraniStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_cz.txt" />
<filter name="czechStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball" />
<filter name="germanNormalization"/>
<filter name="germanLightStem"/>
<!-- less aggressive: <filter name="germanMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="German2"/> -->
</analyzer>
</fieldType>
<!-- Greek -->
<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- greek specific lowercase for sigma -->
<filter class="solr.GreekLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter class="solr.GreekStemFilterFactory"/>
<filter name="greekLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_el.txt" />
<filter name="greekStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball" />
<filter name="spanishLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Spanish"/> -->
</analyzer>
</fieldType>
<!-- Estonian -->
<fieldType name="text_et" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_et.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Estonian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_et.txt" />
<filter name="snowballPorter" language="Estonian"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_eu.txt" />
<filter name="snowballPorter" language="Basque"/>
</analyzer>
</fieldType>
@ -872,121 +872,121 @@
<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" />
<charFilter name="persian"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="arabicNormalization"/>
<filter name="persianNormalization"/>
<filter name="stop" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball" />
<filter name="snowballPorter" language="Finnish"/>
<!-- less aggressive: <filter name="finnishLightStem"/> -->
</analyzer>
</fieldType>
<!-- French -->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_fr.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball" />
<filter name="frenchLightStem"/>
<!-- less aggressive: <filter name="frenchMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="French"/> -->
</analyzer>
</fieldType>
<!-- Irish -->
<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- removes d', etc -->
<filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
<filter name="elision" 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"/>
<filter name="stop" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
<filter name="irishLowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ga.txt"/>
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_gl.txt" />
<filter name="galicianStem"/>
<!-- less aggressive: <filter name="galicianMinimalStem"/> -->
</analyzer>
</fieldType>
<!-- Hindi -->
<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<!-- normalizes unicode representation -->
<filter class="solr.IndicNormalizationFilterFactory"/>
<filter name="indicNormalization"/>
<!-- normalizes variation in spelling -->
<filter class="solr.HindiNormalizationFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter class="solr.HindiStemFilterFactory"/>
<filter name="hindiNormalization"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hi.txt" />
<filter name="hindiStem"/>
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball" />
<filter name="snowballPorter" language="Hungarian"/>
<!-- less aggressive: <filter name="hungarianLightStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_hy.txt" />
<filter name="snowballPorter" 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" />
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" 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"/>
<filter name="indonesianStem" stemDerivational="true"/>
</analyzer>
</fieldType>
<!-- Italian -->
<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<tokenizer name="standard"/>
<!-- 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"/> -->
<filter name="elision" ignoreCase="true" articles="lang/contractions_it.txt"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball" />
<filter name="italianLightStem"/>
<!-- more aggressive: <filter name="snowballPorter" language="Italian"/> -->
</analyzer>
</fieldType>
@ -1025,20 +1025,20 @@
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<tokenizer name="japanese" mode="search"/>
<!--<tokenizer name="japanese" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
<filter class="solr.JapaneseBaseFormFilterFactory"/>
<filter name="japaneseBaseForm"/>
<!-- Removes tokens with certain part-of-speech tags -->
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
<filter name="japanesePartOfSpeechStop" 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"/>
<filter name="cjkWidth"/>
<!-- 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" />
<filter name="stop" 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"/>
<filter name="japaneseKatakanaStem" minimumLength="4"/>
<!-- Lower-cases romaji characters -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter name="lowercase"/>
</analyzer>
</fieldType>
@ -1063,49 +1063,49 @@
* decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
* outputUnknownUnigrams: If true outputs unigrams for unknown words.
-->
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
<tokenizer name="korean" decompoundMode="discard" outputUnknownUnigrams="false"/>
<!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
listing the tags to remove. By default it removes:
E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
This is basically an equivalent to stemming.
-->
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
<filter name="koreanPartOfSpeechStop" />
<!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
<filter class="solr.KoreanReadingFormFilterFactory" />
<filter class="solr.LowerCaseFilterFactory" />
<filter name="koreanReadingForm" />
<filter name="lowercase" />
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_lv.txt" />
<filter name="latvianStem"/>
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball" />
<filter name="stemmerOverride" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
<filter name="snowballPorter" 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" variant="nb"/> -->
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball" />
<filter name="snowballPorter" language="Norwegian"/>
<!-- less aggressive: <filter name="norwegianLightStem" variant="nb"/> -->
<!-- singular/plural: <filter name="norwegianMinimalStem" variant="nb"/> -->
<!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</analyzer>
</fieldType>
@ -1113,65 +1113,65 @@
<!-- 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball" />
<filter name="portugueseLightStem"/>
<!-- less aggressive: <filter name="portugueseMinimalStem"/> -->
<!-- more aggressive: <filter name="snowballPorter" language="Portuguese"/> -->
<!-- most aggressive: <filter name="portugueseStem"/> -->
</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"/>
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ro.txt" />
<filter name="snowballPorter" 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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball" />
<filter name="snowballPorter" language="Russian"/>
<!-- less aggressive: <filter name="russianLightStem"/> -->
</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"/> -->
<tokenizer name="standard"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball" />
<filter name="snowballPorter" language="Swedish"/>
<!-- less aggressive: <filter name="swedishLightStem"/> -->
</analyzer>
</fieldType>
<!-- Thai -->
<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" />
<tokenizer name="thai"/>
<filter name="lowercase"/>
<filter name="stop" ignoreCase="true" words="lang/stopwords_th.txt" />
</analyzer>
</fieldType>
<!-- Turkish -->
<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ApostropheFilterFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
<tokenizer name="standard"/>
<filter name="apostrophe"/>
<filter name="turkishLowercase"/>
<filter name="stop" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter name="snowballPorter" language="Turkish"/>
</analyzer>
</fieldType>
@ -1179,7 +1179,7 @@
<fieldType name="preanalyzed" class="solr.PreAnalyzedField">
<!-- PreAnalyzedField's builtin index analyzer just decodes the pre-analyzed token stream. -->
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<tokenizer name="whitespace"/>
</analyzer>
</fieldType>