solr-materio-d8/materio_autocomplete/conf/schema_extra_types.xml

<!--
  ASCII String Field
  6.0.0
-->
<fieldType name="text_asciistring" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Edge NGram ASCII String Field
  6.0.0
-->
<fieldType name="text_edgenasciistring" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <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 type="query">
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
    <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="true"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" preserveOriginal="1"/>
  </analyzer>
</fieldType>
<!--
  Edge NGram String Field
  6.0.0
-->
<fieldType name="text_edgenstring" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.KeywordTokenizerFactory"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
    <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.KeywordTokenizerFactory"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Edge NGram Text Field
  7.0.0
-->
<fieldType name="text_edge" 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.EdgeNGramFilterFactory" 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>
<!--
  English Text Field
  7.0.0
-->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.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.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.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.SnowballPorterFilterFactory" language="English" protected="protwords_en.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  English Text Field collated
  7.0.0
-->
<fieldType name="collated_en" class="solr.ICUCollationField" locale="en" strength="primary" caseLevel="false"/>
<!--
  English Text Field unstemmed
  7.0.0
-->
<fieldType name="text_unstemmed_en" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.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_en.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_en.txt" expand="true" ignoreCase="true"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.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>
<!--
  French Text Field
  7.0.0
-->
<fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.ElisionFilterFactory"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
    <filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.ElisionFilterFactory"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fr.txt" expand="true" ignoreCase="true"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
    <filter class="solr.SnowballPorterFilterFactory" language="French" protected="protwords_fr.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  French Text Field collated
  7.0.0
-->
<fieldType name="collated_fr" class="solr.ICUCollationField" locale="fr" strength="primary" caseLevel="false"/>
<!--
  French Text Field unstemmed
  7.0.0
-->
<fieldType name="text_unstemmed_fr" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.ElisionFilterFactory"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_fr.txt"/>
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="0" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_fr.txt" expand="true" ignoreCase="true"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Fulltext Phonetic
  7.0.0
-->
<fieldType name="text_phonetic_und" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <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.BeiderMorseFilterFactory" languageSet="auto" nameType="GENERIC" ruleType="APPROX" concat="true"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <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.BeiderMorseFilterFactory" languageSet="auto" nameType="GENERIC" ruleType="APPROX" concat="true"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Fulltext Phonetic English
  7.0.0
-->
<fieldType name="text_phonetic_en" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_en.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.BeiderMorseFilterFactory" languageSet="english" nameType="GENERIC" ruleType="APPROX" concat="true"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_en.txt"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="0" generateNumberParts="1" protected="protwords_en.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.BeiderMorseFilterFactory" languageSet="english" nameType="GENERIC" ruleType="APPROX" concat="true"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Fulltext Phonetic French
  7.0.0
-->
<fieldType name="text_phonetic_fr" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.WhitespaceTokenizerFactory"/>
    <filter class="solr.ElisionFilterFactory"/>
    <filter class="solr.WordDelimiterGraphFilterFactory" catenateNumbers="1" generateNumberParts="1" protected="protwords_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="1"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
    <filter class="solr.BeiderMorseFilterFactory" languageSet="french" 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_fr.txt" splitOnCaseChange="1" generateWordParts="1" preserveOriginal="1" catenateAll="0" catenateWords="0"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_fr.txt"/>
    <filter class="solr.BeiderMorseFilterFactory" languageSet="french" nameType="GENERIC" ruleType="APPROX" concat="true"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </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"/>
<!--
  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>