Saya ingin menghapus stopwords dari indeks saya selama pengindeksan dan kueri, tetapi entah bagaimana kata-kata di dalam stopwords.txt sepertinya tidak dihapus dari indeks saya (saya masih dapat menggunakannya dalam kueri dan mendapatkan hasil yang tepat dengannya).
Ini skema.xml saya:
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.KStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.KStemFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
<field name="post_content" type="text" indexed="true" stored="true"/>
<field name="post_title" type="text" indexed="true" stored="true"/>
<field name="post_date" type="date" indexed="true" stored="true"/>
<field name="_text_" type="text" indexed="true" stored="false" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
Saya menggunakan Solr 6.0.
Terima kasih atas sarannya,
Sabine