schema.xml配置 - 分词器配置

在FieldType中，对于TextField，可以通过<analyzer>元素配置分词器，从而影响TextField的分词行为。

<fieldType name="text_en" 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"/> -->
<!-- case insensitive stop word removal.-->
<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"/>
<!--optionally you may want to use this less aggressive stemmer instead of ProterStemFilterFactory:
<filter class="solr.EnglishMinimalStrmFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" 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"/>
<!-- optionally, you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/> -->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>