基於edismax類型錯誤的Solr自動完成

Question

嘗試基於edismax類型實現自動完成時，收到以下錯誤。

SEVERE: java.lang.IllegalStateException: field "locality_ng" was indexed without position data; cannot run PhraseQuery (term=львів) 
at org.apache.lucene.search.PhraseQuery$PhraseWeight.scorer(PhraseQuery.java:241) 
at org.apache.lucene.search.DisjunctionMaxQuery$DisjunctionMaxWeight.scorer(DisjunctionMaxQuery.java:145) 
at org.apache.lucene.search.BooleanQuery$BooleanWeight.scorer(BooleanQuery.java:317) 
at org.apache.lucene.search.IndexSearcher.search(IndexSearcher.java:551) 
at org.apache.lucene.search.IndexSearcher.search(IndexSearcher.java:324) 
at org.apache.solr.search.SolrIndexSearcher.getDocListNC(SolrIndexSearcher.java:1275) 

模式類型：

 <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100"> 
     <analyzer type="index"> 
      <!--charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/--> 
      <tokenizer class="solr.StandardTokenizerFactory"/> 
      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1" splitOnNumerics="1" preserveOriginal="1" /> 
      <filter class="solr.LowerCaseFilterFactory"/> 
     </analyzer> 
     <analyzer type="query"> 
      <!--charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/--> 
      <tokenizer class="solr.StandardTokenizerFactory"/> 
      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" splitOnNumerics="0"/> 
      <filter class="solr.LowerCaseFilterFactory"/> 
     </analyzer> 
    </fieldType> 

    <!-- autocomplete_edge : Will match from the left of the field, e.g. if the document field 
     is "A brown fox" and the query is "A bro", it will match, but not "brown" 
    --> 
    <fieldType name="autocomplete_edge" class="solr.TextField"> 
     <analyzer type="index"> 
      <!--charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/--> 
      <tokenizer class="solr.KeywordTokenizerFactory"/> 
      <filter class="solr.LowerCaseFilterFactory"/> 
      <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:_])" replacement=" " replace="all"/> 
      <filter class="solr.EdgeNGramFilterFactory" maxGramSize="50" minGramSize="2"/> 
     </analyzer> 
     <analyzer type="query"> 
      <!--charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/--> 
      <tokenizer class="solr.KeywordTokenizerFactory"/> 
      <filter class="solr.LowerCaseFilterFactory"/> 
      <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:_])" replacement=" " replace="all"/> 
      <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{50})(.*)?" replacement="$1" replace="all"/> 
     </analyzer> 
    </fieldType> 

    <!-- autocomplete_ngram : Matches any word in the input field, with implicit right truncation. 
     This means that the field "A brown fox" will be matched by query "bro". 
     We use this to get partial matches, but these whould be boosted lower than exact and left-anchored 
    --> 
    <fieldType name="autocomplete_ngram" class="solr.TextField"> 
     <analyzer type="index"> 
      <!--charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/--> 
      <tokenizer class="solr.StandardTokenizerFactory"/> 
      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> 
      <filter class="solr.LowerCaseFilterFactory"/> 
      <filter class="solr.EdgeNGramFilterFactory" maxGramSize="20" minGramSize="2"/> 
     </analyzer> 
     <analyzer type="query"> 
      <!--charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/--> 
      <tokenizer class="solr.StandardTokenizerFactory"/> 
      <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/> 
      <filter class="solr.LowerCaseFilterFactory"/> 
      <filter class="solr.PatternReplaceFilterFactory" pattern="^(.{20})(.*)?" replacement="$1" replace="all"/> 
     </analyzer> 
    </fieldType> 

架構字段

 <!-- AutoComplete fields 
     Construct documents containing these fields for all suggestions you like to provide 
     Then use a dismax query to search on some fields, display some fields and boost others 
    --> 
    <field name="locality_id" type="int" indexed="true" stored="true" required="true"/> 
    <!-- The main text to return as the suggestion. This is not searched --> 
    <field name="locality_suggest" type="text_suggest" indexed="true" stored="true" omitNorms="true" multiValued="true" /> 

    <!-- A variant of textsuggest which only matches from the very left edge --> 
    <copyField source="locality_suggest" dest="locality_nge"/> 
    <field name="locality_nge" type="autocomplete_edge" indexed="true" stored="false" multiValued="true" /> 

    <!-- A variant of textsuggest which matches from the left edge of all terms (implicit truncation) --> 
    <copyField source="locality_suggest" dest="locality_ng"/> 
    <field name="locality_ng" type="autocomplete_ngram" indexed="true" stored="false" omitNorms="true" omitTermFreqAndPositions="true" multiValued="true" /> 

solr的配置，使用下面的請求處理機與edismax類型：

<requestHandler class="solr.SearchHandler" name="autocomplete" > 
<lst name="defaults"> 
    <str name="defType">edismax</str> 
    <str name="rows">10</str> 
    <str name="fl">*,score</str> 
    <str name="qf">locality_suggest locality_ng^5.0 locality_nge^10.0</str> 
    <str name="debugQuery">false</str> 
</lst> 

發生這種錯誤只有在查詢中包含像+特殊符號 - 單詞後$ @

львів+в київ+а

任何建議將是巨大

Answer 1

變化

<field name="locality_ng" type="autocomplete_ngram" indexed="true" stored="false" omitNorms="true" omitTermFreqAndPositions="true" multiValued="true" /> 

納入

<field name="locality_ng" type="autocomplete_ngram" indexed="true" stored="false" omitNorms="true" multiValued="true" />