This is the content of my autophrases.txt file:
al qaeda in the arabian peninsula
seat belt
I've attached a screenshot showing the analysis view of the index. When I
query for al_qaeda_in_the_arabian_peninsula or
alqaedainthearabianpeninsula, nothing comes back even though at least the
latter appears to be a token that makes it all the way through the index
filter chain.
I'm just using this to find it:
search_text:alqaedainthearabianpeninsula
Any ideas about why this isn't returning anything?
This is the field type declaration:
<fieldType name="text_en_splitting" class="solr.TextField"
positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="com.lucidworks.analysis.AutoPhrasingTokenFilterFactory"
phrases="autophrases.txt" includeTokens="true" replaceWhitespaceWith="_"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="1" catenateNumbers="1"
catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1"
generateNumberParts="1" catenateWords="0" catenateNumbers="0"
catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="com.lucidworks.analysis.AutoPhrasingTokenFilterFactory"
phrases="autophrases.txt" replaceWhitespaceWith="_"/>
<filter class="solr.ManagedSynonymFilterFactory" managed="english" />
<filter class="solr.KeywordMarkerFilterFactory"
protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
