Solr：在高級solr模式下使用拼寫檢查程序

Question

我正在嘗試改進我的項目上的拼寫檢查行爲。

我只在一個字段（「標題」）上拼寫檢查。底部的相關配置。

原因如果配置 - 支持特殊字符的對象。

例如：
- 憤怒的戰爭：T70，世界上最好的坦克！
- 現代芯片組M74K34＃11 $$ 1 - A：B：C - 100500bestprices！非常爽的對象|標題

覆蓋大多數情況下，我將配置 「solr.WordDelimiterFilterFactory」 過濾器。

問題：在拼​​寫檢查結果：當我嘗試搜索「安格鳥」時，我收到「憤怒的小鳥」，而不是預期的「憤怒的小鳥」。可能的話，僅僅通過spec chars（我的意思是拆分「憤怒的戰爭：T70，」=>「生氣」，「戰爭」，「T70」，「T」，「70」）修飾關鍵字就足夠了。但是，我如何通過spec chars修飾關鍵字？或者任何人有更好的想法？

<field name="title" type="text_en" indexed="true" stored="true" required="true" multiValued="false"/> 

其中 「text_en」 是：

<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100"> 
    <analyzer type="index"> 
    <tokenizer class="solr.WhitespaceTokenizerFactory"/> 
    <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/> 
    <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="1" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" splitOnNumerics="0" preserveOriginal="1"/> 
    <filter class="solr.LowerCaseFilterFactory"/> 
    <filter class="solr.EnglishPossessiveFilterFactory"/> 
    <filter class="solr.KStemFilterFactory"/> 
    </analyzer> 
    <analyzer type="query"> 
    <tokenizer class="solr.WhitespaceTokenizerFactory"/> 
    <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" splitOnNumerics="0" preserveOriginal="1"/> 
    <filter class="solr.LowerCaseFilterFactory"/> 
    <filter class="solr.EnglishPossessiveFilterFactory"/> 
    <filter class="solr.KStemFilterFactory"/> 
    </analyzer> 
</fieldType> 

在SolrConfig我用

<requestHandler name="/select" class="solr.SearchHandler"> 
<lst name="defaults"> 
    <str name="echoParams">explicit</str> 
    <int name="rows">10</int> 
    <str name="spellcheck.count">3</str> 
    <str name="spellcheck.dictionary">default</str> 
    <str name="spellcheck.dictionary">wordbreak</str> <!-- index --> 

    <str name="spellcheck.maxCollationTries">10</str> 
    <str name="spellcheck.maxCollations">5</str> 
</lst> 
<arr name="last-components"> 
    <str>spellcheck</str> 
</arr> 
</requestHandler> 


<searchComponent name="spellcheck" class="solr.SpellCheckComponent"> 

<str name="queryAnalyzerFieldType">textSpell</str> 
    <lst name="spellchecker"> 
    <str name="name">default</str> 
    <str name="field">title</str> 
    <!-- <str name="field">default_search_field</str> --> 
    <str name="classname">solr.DirectSolrSpellChecker</str> 
    <!-- the spellcheck distance measure used, the default is the internal levenshtein --> 
    <!-- <str name="distanceMeasure">internal</str> --> 
    <str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str> 

    <!-- minimum accuracy needed to be considered a valid spellcheck suggestion --> 
    <float name="accuracy">0.7</float> 
    <!-- the maximum #edits we consider when enumerating terms: can be 1 or 2 --> 
    <int name="maxEdits">2</int> 
    <!-- the minimum shared prefix when enumerating terms --> 
    <int name="minPrefix">1</int> 
    <!-- maximum number of inspections per result. --> 
    <int name="maxInspections">5</int> 
    <!-- minimum length of a query term to be considered for correction --> 
    <int name="minQueryLength">4</int> 
    <!-- maximum threshold of documents a query term can appear to be considered for correction --> 
    <float name="maxQueryFrequency">0.01</float> 
    <!-- uncomment this to require suggestions to occur in 1% of the documents 
    <float name="thresholdTokenFrequency">.01</float> 
    -->  
    <str name="buildOnCommit">false</str> 
    <str name="buildOnOptimize">true</str> 
    <str name="combineWords">true</str> 
    <str name="breakWords">true</str> 
    <str name="comparatorClass">freq</str> 
    <str name="collate">true</str> 
    <str name="count">5</str> 
</lst> 

<lst name="spellchecker"> 
    <str name="name">wordbreak</str> 
    <!-- <str name="classname">solr.DirectSolrSpellChecker</str> --> 
    <str name="classname">solr.WordBreakSolrSpellChecker</str> 
    <str name="field">title</str> 
    <str name="combineWords">true</str> 
    <str name="breakWords">true</str> 
    <int name="maxChanges">5</int> 
</lst> 

</searchComponent> 

Answer 1

你可以控制你想刪除

<filter class="solr.PatternReplaceFilterFactory" pattern="(:)" replacement=" " replace="all"/>