我正在索引具有大型文本内容字段的文档。大多数时候,我想对这些数据以及传入的查询进行特殊处理。(我当前的 fieldType 定义在底部。)
但是,有时,例如当用户在引号中传入某些内容时,我想从本质上使用与为字段定义的查询分析器不同的查询分析器。也许使用 KeywordTokenizerFactory 而不是 WhitespaceTokenizerFactory,这样我就可以匹配“一个短语中的多个单词”而不会将它们分开。
如何在查询时选择不同的查询分析器?
我知道我可以使用 copyField 并设置一个完全不同的字段定义,但这实际上会使我的 Solr 索引使用的空间增加一倍,这是不可行的。
<fieldType name="text_en_splitting_reversed" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
<analyzer type="index">
<!-- convert things like é to e and ŕ to r -->
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-FoldToASCII.txt"/>
<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="lang/stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnNumerics="1" splitOnCaseChange="1" types="word-delim-types.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
<!-- convert things like é to e and ŕ to r -->
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-FoldToASCII.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory"
ignoreCase="true"
words="lang/stopwords_en.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1" types="word-delim-types.txt" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
</analyzer>
</fieldType>