Using NLP Models

Documentation > Wiki > Using NLP Models

Using the NLP Models in your schema_extra_types.xml:

<fieldType name="text_edge_nouns_nl" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="nl-sent.bin" tokenizerModel="nl-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="nl-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_edge_nouns_nl.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
    <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="nl-sent.bin" tokenizerModel="nl-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="nl-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_edge_nouns_nl.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_edge_nouns_nl.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>

To reference the NLP models correctly, you need to enter the full path.

For example, instead of

sentenceModel="nl-sent.bin"

You would enter:

sentenceModel="/opt/nlp/nl-sent.bin"

Since that's where the nlp models reside, in Opensolr.

So here is the correct schema_extra_types.xml file:

<!--
  Dutch Edge NGram Nouns Field
  7.0.0
-->
<fieldType name="text_edge_nouns_nl" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/nl-sent.bin" tokenizerModel="nl-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/nl-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_edge_nouns_nl.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
    <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/nl-sent.bin" tokenizerModel="/opt/nlp/nl-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/nl-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_edge_nouns_nl.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_edge_nouns_nl.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Dutch Nouns Field
  7.0.0
-->
<fieldType name="text_nouns_nl" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/nl-sent.bin" tokenizerModel="/opt/nlp/nl-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/nl-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_nouns_nl.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/nl-sent.bin" tokenizerModel="/opt/nlp/nl-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/nl-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_nouns_nl.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nouns_nl.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" protected="protwords_nl.txt" language="Kp"/>
    <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" ignoreCase="true" synonyms="synonyms_nl.txt" expand="true"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nl.txt"/>
    <filter class="solr.SnowballPorterFilterFactory" protected="protwords_nl.txt" language="Kp"/>
    <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
-->
<fieldType name="text_unstemmed_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.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" ignoreCase="true" synonyms="synonyms_nl.txt" expand="true"/>
    <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords_nl.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Edge NGram String Field
  6.0.0
-->
<fieldType name="text_edgenstring" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
  <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" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <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.StandardTokenizerFactory"/>
    <filter class="solr.LengthFilterFactory" min="2" max="100"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  English Nouns Field
  7.0.0
-->
<fieldType name="text_nouns_en" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/en-sent.bin" tokenizerModel="/opt/nlp/en-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/en-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_nouns_en.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/en-sent.bin" tokenizerModel="/opt/nlp/en-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/en-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_nouns_en.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nouns_en.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  English Text Field
  7.0.0
-->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <filter class="solr.LengthFilterFactory" min="2" max="100"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SnowballPorterFilterFactory" protected="protwords_en.txt" language="English"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_en.txt" expand="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" protected="protwords_en.txt" language="English"/>
    <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" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_en.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <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.StandardTokenizerFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_en.txt" expand="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>
<!--
  Fulltext Phonetic
  7.0.0
-->
<fieldType name="text_phonetic_und" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <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.StandardTokenizerFactory"/>
    <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" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <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.StandardTokenizerFactory"/>
    <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 String Field
  6.0.0
-->
<fieldType name="text_string" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <tokenizer class="solr.PatternTokenizerFactory" pattern="[\t\r\n]"/>
    <filters/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.PatternTokenizerFactory" pattern="[\t\r\n]"/>
    <filters/>
  </analyzer>
</fieldType>
<!--
  Language Undefined Edge NGram Nouns Field
  7.0.0
-->
<fieldType name="text_edge_nouns_und" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/en-sent.bin" tokenizerModel="/opt/nlp/en-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/en-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_edge_nouns_und.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
    <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/en-sent.bin" tokenizerModel="/opt/nlp/en-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/en-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_edge_nouns_und.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_edge_nouns_und.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Language Undefined Nouns Field
  7.0.0
-->
<fieldType name="text_nouns_und" class="solr.TextField" positionIncrementGap="100">
  <analyzer type="index">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/en-sent.bin" tokenizerModel="/opt/nlp/en-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/en-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_nouns_und.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
  <analyzer type="query">
    <tokenizer class="solr.OpenNLPTokenizerFactory" sentenceModel="/opt/nlp/en-sent.bin" tokenizerModel="/opt/nlp/en-token.bin"/>
    <filter class="solr.OpenNLPPOSFilterFactory" posTaggerModel="/opt/nlp/en-pos-maxent.bin"/>
    <filter class="solr.TypeTokenFilterFactory" types="pos_nouns_und.txt" useWhitelist="true"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms_nouns_und.txt"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>
<!--
  Language Undefined Text Field
  7.0.0
-->
<fieldType name="text_und" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <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.StandardTokenizerFactory"/>
    <filter class="solr.SynonymGraphFilterFactory" ignoreCase="true" synonyms="synonyms_und.txt" expand="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" storeOffsetsWithPositions="true">
  <analyzer>
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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="" strength="primary" caseLevel="false"/>
<!--
  NGram String Field
  6.0.0
-->
<fieldType name="text_ngramstring" class="solr.TextField" positionIncrementGap="100" storeOffsetsWithPositions="true">
  <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" storeOffsetsWithPositions="true">
  <analyzer type="index">
    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
    <tokenizer class="solr.StandardTokenizerFactory"/>
    <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.FlattenGraphFilterFactory"/>
    <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.StandardTokenizerFactory"/>
    <filter class="solr.LengthFilterFactory" min="2" max="100"/>
    <filter class="solr.LowerCaseFilterFactory"/>
    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
  </analyzer>
</fieldType>