Solr 6.1学习笔记 -- spellcheck 组件

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

    <str name="queryAnalyzerFieldType">text_general</str>

    <!-- 下面的spellchecker使用了DirectSolrSpellChecker, 此类会使用主索引中的term进行拼写检查 -->
    <lst name="spellchecker">
      <str name="name">default</str>
      <str name="field">text</str>
      <str name="classname">solr.DirectSolrSpellChecker</str>
      <!-- spellcheck 使用的编辑距离（由一个词转化成另一个词所做的变动）, 默认值是 internal，用的是levenshtein metric-->
      <str name="distanceMeasure">internal</str>
      <!-- 被认为是有效的 spellcheck suggestion的最小精度值，介于0和1之间的值。值越大，匹配的结果数越少。个人理解：假设对 cit进行拼写检查，
         如果此值设置够小的话，"fat"，"sit"都会被认为是"cit"的正确的拼写。如果此值设置够大，则"sit"会被认为是正确的拼写 -->
      <float name="accuracy">0.5</float>
      <!-- 值为 1 或者 2。指示最多有几个字母变动。比如：对"manag"进行拼写检查，则会找到"manager"做为正确的拼写；如果对"mana"进行
           拼写检查，因为"mana"到"manager"，需有3个字母的变动，所以"manager"会被遗弃  -->
      <int name="maxEdits">2</int>
      <!-- 最小的前辍数。如设置为1，意思是指第一个字母不能错。比如：输入"cinner",虽然和"dinner"只有一个字母的编辑距离，
           但是变动的是第一个字母，所以"dinner"不是"cinner"的正确拼写 -->
      <int name="minPrefix">1</int>
      <!-- maximum number of inspections per result. -->
      <int name="maxInspections">5</int>
      <!-- 进行拼写检查所需要的最小的字母数。此处设置为4，表示如果只输入了3个字母，则不会进行拼写检查(3个字母的单词都会写错的话，我也无语了) -->
      <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>
      <!-- 被推荐的词在文档中出现的最小频率。整数表示在文档中出现的次数，百分比数表示有百分之多少的文档出现了该推荐词
        <float name="thresholdTokenFrequency">.01</float>
      -->
    </lst>

    <!-- a spellchecker that can break or combine words.  See "/spell" handler below for usage -->
    <lst name="spellchecker">
      <str name="name">wordbreak</str>
      <str name="classname">solr.WordBreakSolrSpellChecker</str>
      <str name="field">text</str>
      <str name="combineWords">true</str>
      <str name="breakWords">true</str>
      <int name="maxChanges">10</int>
    </lst>

    <!-- a spellchecker that use an alternate comparator 

         comparatorClass be one of:
          1. score (default)
          2. freq (Frequency first, then score)
          3. A fully qualified class name
      -->
    <!--
       <lst name="spellchecker">
         <str name="name">freq</str>
         <str name="field">lowerfilt</str>
         <str name="classname">solr.DirectSolrSpellChecker</str>
         <str name="comparatorClass">freq</str>
      -->
  </searchComponent>

  <!-- A request handler for demonstrating the spellcheck component.  

       NOTE: This is purely as an example.  The whole purpose of the
       SpellCheckComponent is to hook it into the request handler that
       handles your normal user queries so that a separate request is
       not needed to get suggestions.

       IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
       NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!

       See http://wiki.apache.org/solr/SpellCheckComponent for details
       on the request parameters.
    -->
  <requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
    <lst name="defaults">
      <!-- Solr will use suggestions from both the 'default' spellchecker
           and from the 'wordbreak' spellchecker and combine them.
           collations (re-written queries) can include a combination of
           corrections from both spellcheckers -->
      <str name="spellcheck.dictionary">default</str>
      <str name="spellcheck.dictionary">wordbreak</str>
      <str name="spellcheck">on</str>

      <!-- 不仅返回建议词在索引中的频率，而且还返回原始的term在索引中的频率 -->
      <str name="spellcheck.extendedResults">true</str>
      <str name="spellcheck.count">10</str>

      <!-- 同时对多个单词进行拼写检查时，每个单词返回的建议词的数量 -->
      <str name="spellcheck.alternativeTermCount">5</str>

　　  <!-- 当查询的匹配结果超过maxResultsForSuggest设置的值时，则不再进行拼写检查。此处设置成5，是指
          如果输入"solr"，假设能找到6条匹配的记录，则不再对"solr"进行拼写检查 -->
      <str name="spellcheck.maxResultsForSuggest">5</str>
      
      <!-- Solr会基于建议词生成新的查询以替换不正确的拼写的查询 -->
      <str name="spellcheck.collate">true</str>

      <!-- 意思与spellcheck.extendedResults相同，如果spellcheck.extendedResults设置为false,则此值将会被忽略 -->
      <str name="spellcheck.collateExtendedResults">true</str> 
      <!-- 最多试几次 -->
      <str name="spellcheck.maxCollationTries">10</str>

      <!-- 最多返回多少个校验结果 -->
      <str name="spellcheck.maxCollations">5</str>
    </lst>
    <arr name="last-components">
      <str>spellcheck</str>
    </arr>
  </requestHandler>