THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
...
"Literal" searches are performed by appending appending _lit to the field for the literal search. This is treated as a fielded phrase search on an alternate field (i.e. _text__lit or title_lit) so the following two searches are equivalent:
| Code Block |
|---|
title:'foo and bar' title |
...
_lit:"foo and bar" |
This does impose requirements on the indexing strategy, but this is an "Advanced" feature (hence then name!) so that's ok. The result is that "literal" search can be as literal or analyzed as desired depending on the configuration of the corresponding _lit field.
...
| Code Block | ||
|---|---|---|
| ||
<fieldType name="text_aqp" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.PatternTypingFilterFactory" patternFile="patterns.txt"/>
<filter class="solr.TokenAnalyzerFilterFactory" asType="text_general" preserveType="true"/>
<filter class="solr.TypeAsSynonymFilterFactory" prefix="__TAS__" synFlagsMask="0" ignore="word"/>
<filter class="solr.DropIfFlaggedFilterFactory" dropFlags="2"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/> <!-- query parser already handles splitting -->
<filter class="solr.PatternTypingFilterFactory" patternFile="patterns.txt"/>
<filter class="solr.TokenAnalyzerFilterFactory" asType="text_en_aqp" preserveType="true" />
<filter class="solr.TypeAsSynonymFilterFactory" prefix="__TAS__" synFlagsMask="0"ignore="word"/>
<filter class="solr.DropIfFlaggedFilterFactory" dropFlags="2"/>
</analyzer>
</fieldType>
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_general_lit" class="solr.TextField" positionIncrementGap="100" multiValued="true">
<analyzer type="index"> <tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
---- patterns.txt ----
2 (\d+)\(?([a-z])\)? ::: legal2_$1_$2
2 (\d+)\(?([a-z])\)?\(?(\d+)\)? ::: legal3_$1_$2_$3
2 C\+\+ ::: c_plus_plus |
...