The current example schema has some changes to the parameters used to process text fields:

http://svn.apache.org/repos/asf/lucene/solr/trunk/example/solr/conf/sche...

possibly we should mimic those changes to get the best results.

    <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of
        words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
        so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
        Synonyms and stopwords are customized by external files, and stemming is enabled.
        Duplicate tokens at the same position (which may result from Stemmed Synonyms or
        WordDelim parts) are removed.
        -->
    <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <!-- in this example, we will only use synonyms at query time
        <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
        -->
        <!-- Case insensitive stop word removal.
          add enablePositionIncrements=true in both the index and query
          analyzers to leave a 'gap' for more accurate phrase queries.
        -->
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords.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.EnglishPorterFilterFactory" protected="protwords.txt"/>
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
        <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>
CommentFileSizeAuthor
#1 new-text-377494-1.patch2.58 KBpwolanin

Comments

pwolanin’s picture

Assigned: Unassigned » pwolanin
Status: Active » Needs review
StatusFileSize
new2.58 KB
pwolanin’s picture

Status: Needs review » Fixed

committed to 6.x

Status: Fixed » Closed (fixed)

Automatically closed -- issue fixed for 2 weeks with no activity.