2016-11-25 142 views
0

Solr的更好的搜索結果,我已經配置Solr的爲我的電子商務應用軟件(主要包含圖書資料)。搜索結果似乎沒有回報我所期望的。與相鄰的查詢關鍵詞

以下是配置。

schema.xml中 '

<field name="namespace" type="string" indexed="true" stored="false" /> 
    <field name="id" type="string" indexed="true" stored="true" /> 
    <field name="productId" type="long" indexed="true" stored="true" /> 
    <field name="skuId" type="long" indexed="true" stored="true" /> 
    <field name="category" type="long" indexed="true" stored="false" multiValued="true" /> 
    <field name="explicitCategory" type="long" indexed="true" stored="false" multiValued="true" /> 
    <field name="searchable" type="text_general" indexed="true" stored="false" /> 

    <dynamicField name="*_searchable" type="text_general" indexed="true" stored="false" /> 
    <dynamicField name="*_i" type="int" indexed="true" stored="false" /> 
    <dynamicField name="*_is" type="int" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_s" type="string" indexed="true" stored="false" /> 
    <dynamicField name="*_ss" type="string" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_l" type="long" indexed="true" stored="false" /> 
    <dynamicField name="*_ls" type="long" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_t" type="text_general" indexed="true" stored="false" /> 
    <dynamicField name="*_txt" type="text_general" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_b" type="boolean" indexed="true" stored="false" /> 
    <dynamicField name="*_bs" type="boolean" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_d" type="double" indexed="true" stored="false" /> 
    <dynamicField name="*_ds" type="double" indexed="true" stored="false" multiValued="true" /> 
    <dynamicField name="*_p" type="double" indexed="true" stored="false" /> 

    <dynamicField name="*_dt" type="date" indexed="true" stored="false" /> 
    <dynamicField name="*_dts" type="date" indexed="true" stored="false" multiValued="true" /> 

    <!-- some trie-coded dynamic fields for faster range queries --> 
    <dynamicField name="*_ti" type="tint" indexed="true" stored="false" /> 
    <dynamicField name="*_tl" type="tlong" indexed="true" stored="false" /> 
    <dynamicField name="*_td" type="tdouble" indexed="true" stored="false" /> 
    <dynamicField name="*_tdt" type="tdate" indexed="true" stored="false" /> 

    <!-- Both field types required for geolocation searches. First stores the 
     lat and lon components for the "coordinate" FieldType. Second stores 
     the coordinate. --> 
    <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/> 
    <dynamicField name="*_c" type="coordinate" indexed="true" stored="false"/> 
</fields> 

<uniqueKey>id</uniqueKey> 

<types> 
    <!-- The StrField type is not analyzed, but indexed/stored verbatim. --> 
    <fieldType name="string" class="solr.StrField" sortMissingLast="true" /> 

    <!-- boolean type: "true" or "false" --> 
    <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" /> 

    <!-- Default numeric field types. For faster range queries, consider the 
     tint/tlong/tdouble types. --> 
    <fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0" /> 
    <fieldType name="long" class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0" /> 
    <fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0" /> 

    <!-- Numeric field types that index each value at various levels of precision 
     to accelerate range queries when the number of values between the range endpoints 
     is large. See the javadoc for NumericRangeQuery for internal implementation 
     details. Smaller precisionStep values (specified in bits) will lead to more 
     tokens indexed per value, slightly larger index size, and faster range queries. 
     A precisionStep of 0 disables indexing at different precision levels. --> 
    <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" positionIncrementGap="0" /> 
    <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" positionIncrementGap="0" /> 
    <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" positionIncrementGap="0" /> 

    <!-- The format for this date field is of the form 1995-12-31T23:59:59Z, 
     and is a more restricted form of the canonical representation of dateTime 
     http://www.w3.org/TR/xmlschema-2/#dateTime The trailing "Z" designates UTC 
     time and is mandatory. Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z 
     All other components are mandatory. Expressions can also be used to denote 
     calculations that should be performed relative to "NOW" to determine the 
     value, ie... NOW/HOUR ... Round to the start of the current hour NOW-1DAY 
     ... Exactly 1 day prior to now NOW/DAY+6MONTHS+3DAYS ... 6 months and 3 days 
     in the future from the start of the current day Consult the DateField javadocs 
     for more information. Note: For faster range queries, consider the tdate 
     type --> 
    <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0" /> 

    <!-- A Trie based date field for faster date range queries and date faceting. --> 
    <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0" /> 

    <!-- A general text field that has reasonable, generic cross-language defaults: 
     it tokenizes with StandardTokenizer and down cases. --> 
    <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100"> 
     <analyzer type="index"> 
      <tokenizer class="solr.StandardTokenizerFactory" /> 
      <filter class="solr.LowerCaseFilterFactory" /> 
     </analyzer> 
     <analyzer type="query"> 
      <tokenizer class="solr.StandardTokenizerFactory" /> 
      <filter class="solr.LowerCaseFilterFactory" /> 
     </analyzer> 
    </fieldType> 

    <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. --> 
    <fieldType name="coordinate" class="solr.LatLonType" subFieldSuffix="_coordinate"/> 

</types> 

`

solrconfig.xml中

<?xml version="1.0" encoding="UTF-8" ?> 
<config> 
<luceneMatchVersion>4.10.3</luceneMatchVersion> 
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.StandardDirectoryFactory}" /> 
<updateHandler class="solr.DirectUpdateHandler2" /> 

<query> 
    <maxBooleanClauses>1024</maxBooleanClauses> 

    <filterCache class="solr.FastLRUCache" size="512" initialSize="512" autowarmCount="0" /> 
    <queryResultCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0" /> 
    <documentCache class="solr.LRUCache" size="512" initialSize="512" autowarmCount="0" /> 
    <cache name="perSegFilter" class="solr.search.LRUCache" size="10" initialSize="0" autowarmCount="10" 
      regenerator="solr.NoOpRegenerator" /> 

    <enableLazyFieldLoading>true</enableLazyFieldLoading> 

    <queryResultWindowSize>20</queryResultWindowSize> 
    <queryResultMaxDocsCached>200</queryResultMaxDocsCached> 

    <listener event="newSearcher" class="solr.QuerySenderListener" /> 
    <listener event="firstSearcher" class="solr.QuerySenderListener"> 
     <arr name="queries"> 
      <lst> 
       <str name="q">static firstSearcher warming in solrconfig.xml</str> 
      </lst> 
     </arr> 
    </listener> 

    <useColdSearcher>false</useColdSearcher> 
    <maxWarmingSearchers>2</maxWarmingSearchers> 
</query> 

<requestDispatcher handleSelect="false"> 
    <requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048000" formdataUploadLimitInKB="2048" 
       addHttpRequestToContext="false"/> 
    <httpCaching never304="true" /> 
</requestDispatcher> 

<requestHandler name="/select" class="solr.SearchHandler"> 
    <lst name="defaults"> 
     <str name="echoParams">explicit</str> 
     <int name="rowsa">10</int> 
     <str name="df">name_t</str> 
    </lst> 
</requestHandler> 

<queryResponseWriter name="json" class="solr.JSONResponseWriter"> 
    <str name="content-type">text/plain; charset=UTF-8</str> 
</queryResponseWriter> 

對於例如,當我搜索2個狀態時,它給了我很多隨機結果,甚至在標題中甚至沒有包含2個狀態。

enter image description here

然而,當我搜索的短語「2個國」 2個狀態,我得到的相關結果」

enter image description here

我不想限制每一個搜索到的報價,因爲用戶可以搜索,如「書的作者」如果在搜索短語,因爲它不會完全相符的詞組,這當然給0結果的某種組合。

我怎樣才能imporve我的搜索,這樣我可以在最上面列出最相關的結果。

+1

能否請您分享您使用來從Solr的結果整個查詢? –

回答

3

您可以使用pf2pf3參數在edismax處理給提升到你的條件的兩(pf2)或三個(pf3)是在後場相互找到的文檔。

defType=edismax&pf2=title^4 

你也有pf參數爲經常dismax處理程序,但這是建立在假設所有的條款都是併攏。它可能會幫助,但pf2pf3聽起來更適合你的需要。