mirror of https://github.com/apache/lucene.git
SOLR-13690: Fix test resource.
This commit is contained in:
Tomoko Uchida
parent
31c661f2db
commit
1862ffd6a4
|
|
@ -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>
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue