Question

我目前正在使用SolrJ API进行Web应用。我们需要在应用程序中进行多个单词搜索。但我不知道该怎么做。

以下是我们迄今为止通过网络搜索开发的代码。

HttpSolrClient solr = new HttpSolrClient("http://localhost:8983/solr/Test");
SolrQuery query = new SolrQuery();          
query.setQuery("product_name:Dell laptop*");
query.setFields("product_name");
query.setStart(0);
query.setRows(1000);

QueryResponse response = solr.query(query);
SolrDocumentList results = response.getResults();
for (int i = 0; i < results.size(); ++i) {
    System.out.println(results.get(i));
}

但我没有得到任何结果输出。我们的Solr在一个运行在8983端口的apache Solr的管理控制台的帮助下合并了一个mongo数据库。

请帮忙。我是apache SOLR的新手。

更新：这是我们创建的 schema.xml

<?xml version="1.0" encoding="UTF-8" ?>

<schema name="example" version="1.5">

   <field name="_version_" type="long" indexed="true" stored="true"/>
    <field name="_root_" type="string" indexed="true" stored="false"/>
    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> 
    <field name="product_name" type="string" indexed="true" stored="true" required="true" multiValued="true"/>
    <field name="product_url" type="string" indexed="true" stored="true" required="true" multiValued="true"/>
    <field name="product_img" type="string" indexed="true" stored="true" required="true" multiValued="true"/>
    <field name="product_price" type="double" indexed="true" stored="true" required="true" multiValued="true"/>

   <dynamicField name="*_i"  type="int"    indexed="true"  stored="true"/>
   <dynamicField name="*_is" type="int"    indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true" />
   <dynamicField name="*_ss" type="string"  indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_l"  type="long"   indexed="true"  stored="true"/>
   <dynamicField name="*_ls" type="long"   indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_t"  type="text_general"    indexed="true"  stored="true"/>
   <dynamicField name="*_txt" type="text_general"   indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_en"  type="text_en"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true" stored="true"/>
   <dynamicField name="*_bs" type="boolean" indexed="true" stored="true"  multiValued="true"/>
   <dynamicField name="*_f"  type="float"  indexed="true"  stored="true"/>
   <dynamicField name="*_fs" type="float"  indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_d"  type="double" indexed="true"  stored="true"/>
   <dynamicField name="*_ds" type="double" indexed="true"  stored="true"  multiValued="true"/>
   <dynamicField name="*_coordinate"  type="tdouble" indexed="true"  stored="false" />
   <dynamicField name="*_dt"  type="date"    indexed="true"  stored="true"/>
   <dynamicField name="*_dts" type="date"    indexed="true"  stored="true" multiValued="true"/>
   <dynamicField name="*_p"  type="location" indexed="true" stored="true"/>
  <dynamicField name="*_ti" type="tint"    indexed="true"  stored="true"/>
   <dynamicField name="*_tl" type="tlong"   indexed="true"  stored="true"/>
   <dynamicField name="*_tf" type="tfloat"  indexed="true"  stored="true"/>
   <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
   <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
   <dynamicField name="*_c"   type="currency" indexed="true"  stored="true"/>
   <dynamicField name="ignored_*" type="ignored" multiValued="true"/>
   <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/>
   <dynamicField name="random_*" type="random" />
  <uniqueKey>id</uniqueKey>
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="float" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
    <fieldType name="binary" class="solr.BinaryField"/>
     <fieldType name="random" class="solr.RandomSortField" indexed="true" />

    <fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
      </analyzer>
    </fieldType>
    <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" />
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <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="lang/stopwords_en.txt"
                />
        <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="lang/stopwords_en.txt"
                />
        <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_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
        <filter class="solr.StopFilterFactory"
                ignoreCase="true"
                words="lang/stopwords_en.txt"
                />
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.PorterStemFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
        <filter class="solr.EnglishMinimalStemFilterFactory"/>
         <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
           maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
      </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.txt" />
        <filter class="solr.LowerCaseFilterFactory"/>
      </analyzer>
    </fieldType>

    <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
      <analyzer>
         <tokenizer class="solr.KeywordTokenizerFactory"/>
       <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.TrimFilterFactory" />
         <filter class="solr.PatternReplaceFilterFactory"
                pattern="([^a-z])" replacement="" replace="all"
        />
      </analyzer>
    </fieldType>

    <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
      <analyzer>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory" />
      </analyzer>
    </fieldType>

    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />

    <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>

    <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>

    <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
        geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />

    <fieldType name="bbox" class="solr.BBoxField"
               geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
    <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/>

    <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" />

</schema>

这是 data-config.xml

<?xml version="1.0" encoding="UTF-8" ?>
<dataConfig>
     <dataSource name="client_XXXX" type="MongoDataSource" database="client_XXXX" host="192.168.11.XXX" port="27017"/>
     <document name="Titles">
         <entity name="TitleEntity"
        processor="MongoEntityProcessor"
                 query=""
                 collection="XXXX_data"
                 datasource="client_XXXX"
                 transformer="MongoMapperTransformer" >
                 <field column="product_name" name="product_name"/>
                 <field column="product_url" name="product_url"/>        
                 <field column="product_img" name="product_img"/>

                 <field column="product_price" name="product_price"/>

        <field column="_id" name="id"/>
         </entity>
     </document>
 </dataConfig>

Answer 1

Lucene的JavaDoc中提到了您遇到的问题。为何选择Lucene？ Solr的查询语法是Lucene的超集。 As mentioned there

注意：该字段仅对其直接前面的术语有效，因此查询

标题：做得对

只会在标题字段中找到“Do”。它将在默认字段中找到“it”和“right”（在本例中为文本字段）。

在您的情况下， Dell 仅定向到 product_name 字段，其余部分将定向到您配置中定义的默认搜索字段。

您想要使用它来解决这个问题称为 Field Grouping 。因此，您需要将带有圆括号的单词包围在一个字段中，如此

SolrQuery query = new SolrQuery();          
query.setQuery("product_name:(Dell laptop*)"); // surround the words with ( ... )
query.setFields("product_name");
query.setStart(0);
query.setRows(1000);

Answer 2

我们通过删除不需要的引用创建了一个新的schema.xml，这里是我们使用的模式。

<schema name="example" version="1.5">

<field name="_version_" type="long" indexed="true" stored="true"/>
<field name="_root_" type="string" indexed="true" stored="false"/>

        <fields>    
        <field name="id" type="long" indexed="true" stored="true" required="true" multiValued="false" /> 
        <field name="product_name" type="string" indexed="true" stored="true" required="true" />
        <field name="product_price" type="" indexed="true" stored="true" required="true" />

    </fields>  
    <uniqueKey>id</uniqueKey>
     <types>
                <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
                <fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0" />
                <fieldType name="text_wslc" class="solr.TextField" positionIncrementGap="100">
                        <analyzer type="index">
                                <tokenizer class="solr.WhitespaceTokenizerFactory"/>
                                <filter class="solr.LowerCaseFilterFactory"/>
                        </analyzer>
                        <analyzer type="query">
                                <tokenizer class="solr.WhitespaceTokenizerFactory"/>
                                <filter class="solr.LowerCaseFilterFactory"/>
                        </analyzer>
                </fieldType>
                <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0"/>
                <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
                <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
        <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0"/>
     </types>

        <defaultSearchField>product_name</defaultSearchField>

        <!-- we don't want too many results in this usecase -->
        <solrQueryParser defaultOperator="AND"/>

           </schema>

如何在SOLRJQuery中进行多字搜索

2 个答案: