|
@@ -1,378 +1,22 @@
|
|
<!--
|
|
<!--
|
|
- Arabic Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ar.txt"/>
|
|
|
|
- <filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.ArabicStemFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ar.txt"/>
|
|
|
|
- <filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ar.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.ArabicStemFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Arabic Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_ar" class="solr.ICUCollationField" locale="ar" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Arabic Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_ar" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ar.txt"/>
|
|
|
|
- <filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ar.txt"/>
|
|
|
|
- <filter class="solr.ArabicNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ar.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Bulgarian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_bg.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_bg.txt"/>
|
|
|
|
- <filter class="solr.BulgarianStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_bg.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_bg.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_bg.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.BulgarianStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Bulgarian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_bg" class="solr.ICUCollationField" locale="bg" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Bulgarian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_bg" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_bg.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_bg.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_bg.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_bg.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_bg.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Catalan Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ca.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ElisionFilterFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ca.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ca.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan" protected="protwords_ca.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ca.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ca.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ca.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ca.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Catalan" protected="protwords_ca.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Catalan Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_ca" class="solr.ICUCollationField" locale="ca" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Catalan Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_ca" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ca.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ElisionFilterFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ca.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ca.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ca.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ca.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ca.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ca.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Croatian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_hr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hr.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hr.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hr.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_hr.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Croatian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_hr" class="solr.ICUCollationField" locale="hr" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Croatian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_hr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hr.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hr.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hr.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_hr.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Czech Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_cs" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_cs.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_cs.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cs.txt"/>
|
|
|
|
- <filter class="solr.CzechStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_cs.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_cs.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_cs.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cs.txt"/>
|
|
|
|
- <filter class="solr.CzechStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Czech Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_cs" class="solr.ICUCollationField" locale="cs" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Czech Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_cs" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_cs.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_cs.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cs.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_cs.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_cs.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_cs.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_cs.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Danish Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_da.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_da.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_da.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_da.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Danish" protected="protwords_da.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_da.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_da.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_da.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_da.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Danish" protected="protwords_da.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Danish Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_da" class="solr.ICUCollationField" locale="da" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Danish Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_da" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_da.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_da.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_da.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_da.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_da.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_da.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_da.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_da.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Dutch Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_nl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_nl.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nl.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Kp" protected="protwords_nl.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_nl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nl.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nl.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Kp" protected="protwords_nl.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Dutch Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_nl" class="solr.ICUCollationField" locale="nl" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Dutch Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
|
|
+ Edge NGram ASCII String Field
|
|
|
|
+ 6.0.0
|
|
-->
|
|
-->
|
|
-<fieldType name="text_unstemmed_nl" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
|
|
+<fieldType name="text_edgenasciistring" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<analyzer type="index">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_nl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
|
|
+ <tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_nl.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nl.txt"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
+ <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
|
|
|
|
+ <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
|
|
|
|
+ <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<analyzer type="query">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_nl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
|
|
+ <tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nl.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nl.txt"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
+ <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
|
|
|
|
+ <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|
|
<!--
|
|
<!--
|
|
@@ -472,67 +116,6 @@
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|
|
-<!--
|
|
|
|
- Finnish Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fi.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fi.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fi.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish" protected="protwords_fi.txt"/>
|
|
|
|
- <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="50"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_fi.txt" minWordSize="5" minSubwordSize="2" maxSubwordSize="20" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fi.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_fi.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fi.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fi.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Finnish" protected="protwords_fi.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Finnish Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_fi" class="solr.ICUCollationField" locale="fi" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Finnish Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_fi" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fi.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fi.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fi.txt"/>
|
|
|
|
- <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="50"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_fi.txt" minWordSize="5" minSubwordSize="2" maxSubwordSize="20" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fi.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_fi.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fi.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fi.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
<!--
|
|
<!--
|
|
French Text Field
|
|
French Text Field
|
|
7.0.0
|
|
7.0.0
|
|
@@ -661,1647 +244,85 @@
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|
|
<!--
|
|
<!--
|
|
- Fulltext Phonetic German
|
|
|
|
|
|
+ Language Undefined Text Field
|
|
7.0.0
|
|
7.0.0
|
|
-->
|
|
-->
|
|
-<fieldType name="text_phonetic_de" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_de.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_de.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_de.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="german" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_de.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_de.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="german" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Fulltext Phonetic Greek
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_phonetic_el" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_el.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_el.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="greek" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_el.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_el.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="greek" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Fulltext Phonetic Italian
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_phonetic_it" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_it.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_it.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="italian" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_it.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_it.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="italian" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Fulltext Phonetic Polish
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_phonetic_pl" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_pl.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pl.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="polish" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_pl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pl.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="polish" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Fulltext Phonetic Russian
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_phonetic_ru" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ru.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ru.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="cyrillic" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ru.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ru.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="cyrillic" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Fulltext Phonetic Spanish
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_phonetic_es" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_es.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_es.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="spanish" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_es.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_es.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="spanish" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Fulltext Phonetic Ukrainian
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_phonetic_uk" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_uk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_uk.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="cyrillic" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_uk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_uk.txt"/>
|
|
|
|
- <filter class="solr.BeiderMorseFilterFactory" languageSet="cyrillic" nameType="GENERIC" ruleType="APPROX" concat="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- German Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_de.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_de.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_de.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_de.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="German2" protected="protwords_de.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_de.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_de.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_de.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_de.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="German2" protected="protwords_de.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- German Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_de" class="solr.ICUCollationField" locale="de" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- German Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_de" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_de.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_de.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.DictionaryCompoundWordTokenFilterFactory" dictionary="nouns_de.txt" minWordSize="5" minSubwordSize="4" maxSubwordSize="15" onlyLongestMatch="false"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_de.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_de.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_de.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_de.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_de.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Greek Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_el.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_el.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_el.txt"/>
|
|
|
|
- <filter class="solr.GreekStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_el.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_el.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_el.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_el.txt"/>
|
|
|
|
- <filter class="solr.GreekStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Greek Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_el" class="solr.ICUCollationField" locale="el" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Greek Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_el" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_el.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_el.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_el.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_el.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_el.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.GreekLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_el.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_el.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Hindi Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hi.txt"/>
|
|
|
|
- <filter class="solr.HindiNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.HindiStemFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hi.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_hi.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.HindiNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.HindiStemFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Hindi Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_hi" class="solr.ICUCollationField" locale="hi" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Hindi Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_hi" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hi.txt"/>
|
|
|
|
- <filter class="solr.HindiNormalizationFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hi.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_hi.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.HindiNormalizationFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Hungarian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hu.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hu.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hu.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hu.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hu.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_hu.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hu.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Hungarian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_hu" class="solr.ICUCollationField" locale="hu" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Hungarian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_hu" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hu.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hu.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hu.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_hu.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_hu.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_hu.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_hu.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Indonesian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_id.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_id.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_id.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.IndonesianStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_id.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_id.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_id.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_id.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.IndonesianStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Indonesian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_id" class="solr.ICUCollationField" locale="id" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Indonesian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_id" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_id.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_id.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_id.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_id.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_id.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_id.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_id.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Irish/Gaelic Text Field
|
|
|
|
- 7.7.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ga.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ElisionFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ga.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ga.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.IrishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Irish" protected="protwords_ga.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ga.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ga.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ga.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_ga.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.IrishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Irish" protected="protwords_ga.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Irish/Gaelic Text Field collated
|
|
|
|
- 7.7.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_ga" class="solr.ICUCollationField" locale="ga" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Irish/Gaelic Text Field unstemmed
|
|
|
|
- 7.7.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_ga" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ga.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ElisionFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ga.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ga.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.IrishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ga.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ga.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ga.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_ga.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.IrishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Italian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_it.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_it.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_it.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Italian" protected="protwords_it.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_it.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_it.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_it.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_it.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Italian" protected="protwords_it.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Italian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_it" class="solr.ICUCollationField" locale="it" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Italian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_it" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_it.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_it.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_it.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_it.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_it.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_it.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_it.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Japanese Text Field
|
|
|
|
- 8.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
|
|
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
|
|
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="stoptags_ja.txt"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ja.txt"/>
|
|
|
|
- <filter class="solr.JapaneseKatakanaStemFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
|
|
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
|
|
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="stoptags_ja.txt"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ja.txt"/>
|
|
|
|
- <filter class="solr.JapaneseKatakanaStemFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Japanese Text Field spellcheck
|
|
|
|
- 8.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_spell_ja" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer>
|
|
|
|
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
|
|
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
|
|
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="stoptags_ja.txt"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Japanese Text Field collated
|
|
|
|
- 8.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_ja" class="solr.ICUCollationField" locale="ja" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Japanese Text Field unstemmed
|
|
|
|
- 8.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_ja" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
|
|
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
|
|
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="stoptags_ja.txt"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ja.txt"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
|
|
- <filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
|
|
- <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="stoptags_ja.txt"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ja.txt"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Language Undefined Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_und.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Language Undefined Text Field spellcheck
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_spell_und" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer>
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Language Undefined Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_und" class="solr.ICUCollationField" locale="en" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Latvian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_lv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_lv.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_lv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.LatvianStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_lv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_lv.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_lv.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_lv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.LatvianStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Latvian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_lv" class="solr.ICUCollationField" locale="lv" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Latvian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_lv" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_lv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_lv.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_lv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_lv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_lv.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_lv.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_lv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- NGram String Field
|
|
|
|
- 6.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ngramstring" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="25"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- NGram Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ngram" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="25"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Norwegian Bokmal Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_nb" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nb.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_nb.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nb.txt"/>
|
|
|
|
- <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nb.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_nb.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nb.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nb.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.NorwegianLightStemFilterFactory" variant="nb"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Norwegian Bokmal Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_nb" class="solr.ICUCollationField" locale="nb" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Norwegian Bokmal Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_nb" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nb.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_nb.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nb.txt"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nb.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_nb.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nb.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nb.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Norwegian Nynorsk Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_nn" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nn.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_nn.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nn.txt"/>
|
|
|
|
- <filter class="solr.NorwegianLightStemFilterFactory" variant="nn"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nn.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_nn.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nn.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nn.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.NorwegianLightStemFilterFactory" variant="nn"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Norwegian Nynorsk Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_nn" class="solr.ICUCollationField" locale="nn" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Norwegian Nynorsk Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_nn" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nn.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_nn.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nn.txt"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_nn.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_nn.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nn.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nn.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Persian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fa.txt"/>
|
|
|
|
- <filter class="solr.PersianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fa.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fa.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.PersianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Persian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_fa" class="solr.ICUCollationField" locale="fa" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Persian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_fa" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fa.txt"/>
|
|
|
|
- <filter class="solr.PersianNormalizationFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fa.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fa.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.PersianNormalizationFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Polish Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_pl" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_pl.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pl.txt"/>
|
|
|
|
- <filter class="solr.MorfologikFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_pl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_pl.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pl.txt"/>
|
|
|
|
- <filter class="solr.MorfologikFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Polish Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_pl" class="solr.ICUCollationField" locale="pl" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Polish Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_pl" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" protected="protwords_pl.txt" generateWordParts="1" generateNumberParts="1" splitOnCaseChange="0" splitOnNumerics="1" catenateWords="1" catenateNumbers="1" catenateAll="0" stemEnglishPossessive="0" preserveOriginal="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pl.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pl.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_pl.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_pl.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pl.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Portuguese, Brazilian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_pt_br" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_br.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_pt_br.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_br.txt"/>
|
|
|
|
- <filter class="solr.PortugueseStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_br.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_pt_br.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_br.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_pt_br.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.PortugueseStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Portuguese, Brazilian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_pt_br" class="solr.ICUCollationField" locale="pt" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Portuguese, Brazilian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_pt_br" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_br.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_pt_br.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_br.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_br.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_pt_br.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_pt_br.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_br.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Portuguese, Portugal Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_pt_pt" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_pt.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_pt_pt.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_pt.txt"/>
|
|
|
|
- <filter class="solr.PortugueseStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_pt.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_pt_pt.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_pt.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_pt_pt.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.PortugueseStemFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Portuguese, Portugal Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_pt_pt" class="solr.ICUCollationField" locale="pt" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Portuguese, Portugal Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_pt_pt" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_pt.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_pt_pt.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_pt.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_pt_pt.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_pt_pt.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_pt_pt.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_pt_pt.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Romanian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ro.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ro.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ro.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian" protected="protwords_ro.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ro.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ro.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ro.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ro.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Romanian" protected="protwords_ro.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Romanian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_ro" class="solr.ICUCollationField" locale="ro" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Romanian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_ro" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ro.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_ro.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ro.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_ro.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ro.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ro.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ro.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Russian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ru.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ru.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Russian" protected="protwords_ru.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ru.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ru.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ru.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Russian" protected="protwords_ru.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Russian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_ru" class="solr.ICUCollationField" locale="ru" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Russian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_ru" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ru.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ru.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_ru.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_ru.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_ru.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Serbian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_sr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
|
|
+<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<analyzer type="index">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sr.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- <filter class="solr.SerbianNormalizationFilterFactory" haircut="bald"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sr.txt"/>
|
|
|
|
|
|
+ <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sr.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
|
|
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
|
|
|
+ <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sr.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_sr.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- <filter class="solr.SerbianNormalizationFilterFactory" haircut="bald"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Serbian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_sr" class="solr.ICUCollationField" locale="sr" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Serbian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_sr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sr.txt"/>
|
|
|
|
- <filter class="solr.SerbianNormalizationFilterFactory" haircut="bald"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<analyzer type="query">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sr.txt"/>
|
|
|
|
|
|
+ <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sr.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
|
|
+ <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_und.txt" expand="true" ignoreCase="true"/>
|
|
|
|
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
|
|
|
+ <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sr.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_sr.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.SerbianNormalizationFilterFactory" haircut="bald"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|
|
<!--
|
|
<!--
|
|
- Simplified Chinese Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_zh_hans" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.HMMChineseTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" words="org/apache/lucene/analysis/cn/smart/stopwords.txt"/>
|
|
|
|
- <filter class="solr.PorterStemFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.HMMChineseTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" words="org/apache/lucene/analysis/cn/smart/stopwords.txt"/>
|
|
|
|
- <filter class="solr.PorterStemFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Simplified Chinese Text Field spellcheck
|
|
|
|
|
|
+ Language Undefined Text Field spellcheck
|
|
7.0.0
|
|
7.0.0
|
|
-->
|
|
-->
|
|
-<fieldType name="text_spell_zh_hans" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
|
|
+<fieldType name="text_spell_und" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<analyzer>
|
|
- <tokenizer class="solr.HMMChineseTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Simplified Chinese Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_zh-hans" class="solr.ICUCollationField" locale="zh" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Simplified Chinese Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_zh_hans" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.HMMChineseTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" words="org/apache/lucene/analysis/cn/smart/stopwords.txt"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.HMMChineseTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" words="org/apache/lucene/analysis/cn/smart/stopwords.txt"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Slovak Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_sk" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sk.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sk.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sk.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sk.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_sk.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sk.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Slovak Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_sk" class="solr.ICUCollationField" locale="sk" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Slovak Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_sk" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sk.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sk.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sk.txt"/>
|
|
|
|
|
|
+ <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_sk.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_sk.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sk.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Spanish Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_es.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_es.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_es.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Spanish" protected="protwords_es.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_es.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_es.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_es.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_es.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Spanish" protected="protwords_es.txt"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|
|
<!--
|
|
<!--
|
|
- Spanish Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_es" class="solr.ICUCollationField" locale="es" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Spanish Text Field unstemmed
|
|
|
|
|
|
+ Language Undefined Text Field collated
|
|
7.0.0
|
|
7.0.0
|
|
-->
|
|
-->
|
|
-<fieldType name="text_unstemmed_es" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_es.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_es.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_es.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_es.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_es.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_es.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_es.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
|
|
+<fieldType name="collated_und" class="solr.ICUCollationField" locale="en" strength="primary" caseLevel="false"/>
|
|
<!--
|
|
<!--
|
|
- Swedish Text Field
|
|
|
|
- 7.0.0
|
|
|
|
|
|
+ NGram String Field
|
|
|
|
+ 6.0.0
|
|
-->
|
|
-->
|
|
-<fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
|
|
+<fieldType name="text_ngramstring" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<analyzer type="index">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_sv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
|
|
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sv.txt"/>
|
|
|
|
- <filter class="solr.SwedishLightStemFilterFactory"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
+ <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="25"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<analyzer type="query">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_sv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
|
|
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sv.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_sv.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.SwedishLightStemFilterFactory"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|
|
<!--
|
|
<!--
|
|
- Swedish Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_sv" class="solr.ICUCollationField" locale="no" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Swedish Text Field unstemmed
|
|
|
|
|
|
+ NGram Text Field
|
|
7.0.0
|
|
7.0.0
|
|
-->
|
|
-->
|
|
-<fieldType name="text_unstemmed_sv" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
|
|
+<fieldType name="text_ngram" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<analyzer type="index">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sv.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_sv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sv.txt"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_sv.txt"/>
|
|
|
|
|
|
+ <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_sv.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
|
|
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_und.txt"/>
|
|
|
|
+ <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_und.txt" splitOnCaseChange="0" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_sv.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_sv.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.ScandinavianNormalizationFilterFactory"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Thai Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.ThaiTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_th.txt"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.ThaiTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_th.txt"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Thai Text Field spellcheck
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_spell_th" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer>
|
|
|
|
- <tokenizer class="solr.StandardTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_th.txt"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Thai Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_th" class="solr.ICUCollationField" locale="th" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Traditional Chinese Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_zh_hant" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.ICUTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="false" katakana="false" hangul="false" outputUnigrams="false"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.ICUTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="false" katakana="false" hangul="false" outputUnigrams="false"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Traditional Chinese Text Field spellcheck
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_spell_zh_hant" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer>
|
|
|
|
- <tokenizer class="solr.ICUTokenizerFactory"/>
|
|
|
|
- <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="false" katakana="false" hangul="false" outputUnigrams="false"/>
|
|
|
|
- <filter class="solr.CJKWidthFilterFactory"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Traditional Chinese Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_zh-hant" class="solr.ICUCollationField" locale="zh-hant" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Turkish Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_tr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ApostropheFilterFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_tr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_tr.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
+ <filter class="solr.NGramFilterFactory" minGramSize="2" maxGramSize="25"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<analyzer type="query">
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_tr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ApostropheFilterFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_tr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_tr.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_tr.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Turkish Text Field spellcheck
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_spell_tr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer>
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_tr.txt"/>
|
|
|
|
|
|
+ <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
<filter class="solr.LengthFilterFactory" min="2" max="100"/>
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_tr.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Turkish Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_tr" class="solr.ICUCollationField" locale="tr" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Turkish Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_tr" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_tr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ApostropheFilterFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_tr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
|
|
|
|
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_tr.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <charFilter class="solr.MappingCharFilterFactory" mapping="accents_tr.txt"/>
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.ApostropheFilterFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_tr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.TurkishLowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_tr.txt"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_tr.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Ukrainian Text Field
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_uk" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_uk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_uk.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Russian" protected="protwords_uk.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_uk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_uk.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_uk.txt"/>
|
|
|
|
- <filter class="solr.SnowballPorterFilterFactory" language="Russian" protected="protwords_uk.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
-</fieldType>
|
|
|
|
-<!--
|
|
|
|
- Ukrainian Text Field collated
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="collated_uk" class="solr.ICUCollationField" locale="uk" strength="primary" caseLevel="false"/>
|
|
|
|
-<!--
|
|
|
|
- Ukrainian Text Field unstemmed
|
|
|
|
- 7.0.0
|
|
|
|
--->
|
|
|
|
-<fieldType name="text_unstemmed_uk" class="solr.TextField" positionIncrementGap="100">
|
|
|
|
- <analyzer type="index">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_uk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
- <filter class="solr.LowerCaseFilterFactory"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_uk.txt"/>
|
|
|
|
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
|
|
- </analyzer>
|
|
|
|
- <analyzer type="query">
|
|
|
|
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
|
|
- <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_uk.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
|
|
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
- <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_uk.txt" expand="true" ignoreCase="true"/>
|
|
|
|
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_uk.txt"/>
|
|
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
</analyzer>
|
|
</analyzer>
|
|
</fieldType>
|
|
</fieldType>
|