Solr使用Django只找到完全匹配

时间:2013-02-22 23:59:19

标签: django solr django-haystack

我在索引页面上有一个django应用程序和一个搜索栏。我安装了haystack和solr。 我键入了python manage.py build_solr_schema并将以下xml粘贴到example / solr / conf / schema.xml

    <?xml version="1.0" ?>
<schema name="default" version="1.4">
  <types>
    <fieldtype name="string"  class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
    <fieldtype name="binary" class="solr.BinaryField"/>
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" sortMissingLast="true" positionIncrementGap="0"/>
    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
    <fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
    <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
    <fieldtype name="geohash" class="solr.GeoHashField"/>
    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="stopwords_en.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.EnglishPossessiveFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <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="stopwords_en.txt"
                enablePositionIncrements="true"
                />
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.EnglishPossessiveFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="ngram" class="solr.TextField" >
      <analyzer type="index">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="15" />
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="edge_ngram" class="solr.TextField" positionIncrementGap="1">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15" side="front" />
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
      </analyzer>
    </fieldType>
  </types>

  <fields>
    <!-- general -->
    <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
    <field name="django_ct" type="string" indexed="true" stored="true" multiValued="false"/>
    <field name="django_id" type="string" indexed="true" stored="true" multiValued="false"/>

    <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
    <dynamicField name="*_s"  type="string"  indexed="true"  stored="true"/>
    <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
    <dynamicField name="*_t"  type="text_en"    indexed="true"  stored="true"/>
    <dynamicField name="*_b"  type="boolean" indexed="true"  stored="true"/>
    <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
    <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
    <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
    <dynamicField name="*_p" type="location" indexed="true" stored="true"/>
    <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false"/>


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

  </fields>

  <!-- field to use to determine and enforce document uniqueness. -->
  <uniqueKey>id</uniqueKey>

  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
  <defaultSearchField>text</defaultSearchField>

  <!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
  <solrQueryParser defaultOperator="AND"/>
</schema>

我有一个名为“foorightfoo”的对象。当我搜索“foo”时,没有出现,但是 当我搜索“foorightfoo”的答案来了。当我从太阳能管理面板检查时,同样的情况继续... 我的搜索仅适用于完全匹配。任何想法?

2 个答案:

答案 0 :(得分:2)

实际上我通过操作schema.xml的最后一部分来修复了这个问题,比如

- <field name="text" type="text_en" indexed="true" stored="true" multiValued="false" />

+ <field name="text" type="ngram" indexed="true" stored="true" multiValued="false" />

使用ngram更改搜索的字段类型可以实现技巧

答案 1 :(得分:0)

您需要在最后附加一张外卡*,因此请查询

q=title:foo*