我配置了solr 4.10(也5.3)和highlighting functionality。它可以很好地處理大多數單詞,但是我找到了一些「不會」字樣的字樣,即solr會返回所需的文檔,但不會突出顯示其中的一些。Solr不突出顯示某些詞
什麼會導致這種影響?
solrconfig.xml中
<requestHandler name="/select" class="solr.SearchHandler">
<lst name="defaults">
<str name="wt">json</str>
<str name="indent">true</str>
<str name="defType">edismax</str>
<str name="bf">product(concount)</str>
<str name="df">text bio text_syn text_syn_other</str>
<str name="qf">
text^25 bio^16 text_syn^8 text_syn_other^3
</str>
<str name="hl">on</str>
<str name="hl.fl">text bio text_syn text_syn_other</str>
<str name="hl.preserveMulti">true</str>
<str name="hl.encoder">html</str>
<str name="f.text.hl.fragsize">100</str>
<str name="hl.snippets">20</str>
<arr name="components">
<str>highlight</str>
</arr>
</lst>
schema.xml中
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\s\n,/\\]" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms_abbr.txt" ignoreCase="true" expand="false"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\s\n,/\\]" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en_syn" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\s\n,/\\]" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\s\n,/\\]" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="text_en_syn_other" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\s\n,/\\]" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms_other.txt" ignoreCase="true" expand="false"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\s\n,/\\]" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPossessiveFilterFactory"/>
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldType>
<field name="text" type="text_en" indexed="true" stored="true" multiValued="false" />
<field name="text_syn" type="text_en_syn" indexed="true" stored="false" multiValued="true" />
<field name="text_syn_other" type="text_en_syn_other" indexed="true" stored="false" multiValued="true" />
<field name="text_exact" type="string" indexed="true" stored="false" multiValued="false" />
<field name="bio" type="text_en" indexed="true" stored="true" multiValued="false" />
<field name="bio_exact" type="string" indexed="true" stored="false" multiValued="false" />
<field name="concount" type="long" indexed="true" stored="true" multiValued="false" />
<field name="concount_exact" type="long" indexed="true" stored="false" multiValued="false" />
<copyField source="text" dest="text_syn"/>
<copyField source="bio" dest="text_syn"/>
<copyField source="text" dest="text_syn_other"/>
<copyField source="bio" dest="text_syn_other"/>
對於查詢http://localhost:8983/solr/select?q=senior
我得到了包含單詞senior
文檔,但在強調Solr的響應一節詞不突出顯示。
更新1: 我發現,我有話senior
在我synonyms_abbr.txt
文件,該行senior,lead
。當我評論那條線或者替換單詞的地方時,令人驚訝的是senior
這個單詞開始突出顯示。有任何想法嗎 ?
更新2:從synonyms.txt
和synonyms_other.txt
詞越來越突出正常,但從synonyms_abbr.txt
詞語運行異常如下。舉例來說,我也行lead,head,senior
在synonyms_abbr.txt
然後
- 查詢
http://localhost:8983/solr/select?q=senior
和http://localhost:8983/solr/select?q=head
不突出任何文字, - 查詢
http://localhost:8983/solr/select?q=lead
亮點不僅字lead
,也head
和senior
。
請使用Solr後端功能來分析單詞的轉換。我不確定這個詞的轉換方式。這可能是一個棘手的問題。否則,使用不同的字段,關閉轉換隻留下標記器,然後嘗試從該字段突出顯示。 – 0xCAFEBABE
@Mher是否突出顯示停用詞?或者只是隨機? –
我沒有任何停用詞配置。整個'stopwords.txt'文件被評論。 – Mher