Solr将数据库中table中的数据导入到索引

Solr将数据库中table中的数据导入到索引

版权信息: 可以任意转载, 转载时请务必以超链接形式标明文章原文出处, 即下面的声明.
原文出处：http://tbwuming.iteye.com/blog/1152333

1、首先在MySQL中创建表，并写入数据

-- ----------------------------
-- Table structure for course
-- ----------------------------
CREATE TABLE `course` (
  `id` int(11) NOT NULL,
  `user` varchar(20) NOT NULL,
  `title` varchar(50) NOT NULL,
  `content` varchar(200) NOT NULL,
  `time` datetime NOT NULL DEFAULT '0000-00-00 00:00:00',
  PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

-- ----------------------------
-- Records
-- ----------------------------
INSERT INTO `course` VALUES ('1', 'tiehong', '搜索', '这一小节讲搜索引擎，可以通过搜索引擎查找一些数据', '2011-08-18 10:41:35');
INSERT INTO `course` VALUES ('2', 'chenyun', '存储', '这一小节讲分布式存储，可以存储很多数据', '2011-08-18 10:42:19');
INSERT INTO `course` VALUES ('3', 'lengda', '数据导入', '这一小节讲数据导入，可以从mysql数据库中导入数据', '2011-08-18 10:42:59');

2、修改apache-solr-3.3.0\example\solr\conf\schema.xml文件

<?xml version="1.0" encoding="UTF-8" ?>
<schema name="example" version="1.4">
  <types>    
     <fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>

     <fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>

     <fieldType name="text" 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="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>  
</types>

<fields>
   <field name="id" type="tint" indexed="true" stored="true" required="true" />
   <field name="user" type="string" indexed="true" stored="true"/>
   <field name="title" type="text" indexed="true" stored="true"/> 
   <field name="content" type="text" indexed="true" stored="true" /> 
   <field name="time" type="date" indexed="true" stored="true" default="NOW"/>  
</fields>

<uniqueKey>id</uniqueKey>
<defaultSearchField>title</defaultSearchField> 
<solrQueryParser defaultOperator="AND"/>  

</schema>

3、编辑apache-solr-3.3.0\example\solr\conf\solrconfig.xml文件，添加内容如下：

<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler"> 
          <lst name="defaults"> 
               <str name="config">data-config.xml</str> 
          </lst> 
</requestHandler>

4、创建data-config.xml文件，放在apache-solr-3.3.0\example\solr\conf\目录下，文件内容如下：

<dataConfig> 
  <dataSource type="JdbcDataSource" 
              driver="com.mysql.jdbc.Driver" 
              url="jdbc:mysql://localhost/dbname" 
              user="user-name" 
              password="password"/> 
  <document> 
    <entity name="id" 
            query="select * from course"> 
    </entity> 
  </document> 
</dataConfig>  

5、将MySQL的JDBC驱动放在apache-solr-3.3.0\example\lib目录下

6、启动Solr服务，命令行进入apache-solr-3.3.0\example\目录，运行 java -jar start.jar
出现问题：

严重: org.apache.solr.common.SolrException: QueryElevationComponent requires the
schema to have a uniqueKeyField implemented using StrField at org.apache.solr.handler.component.QueryElevationComponent.inform(QueryElevationComponent.java:158)
        at org.apache.solr.core.SolrResourceLoader.inform(SolrResourceLoader.java:522)
        at org.apache.solr.core.SolrCore.<init>(SolrCore.java:594)
        at org.apache.solr.core.CoreContainer.create(CoreContainer.java:463)
        at org.apache.solr.core.CoreContainer.load(CoreContainer.java:316)
        at org.apache.solr.core.CoreContainer.load(CoreContainer.java:207)
        at org.apache.solr.core.CoreContainer$Initializer.initialize(CoreContainer.java:130)
        at org.apache.solr.servlet.SolrDispatchFilter.init(SolrDispatchFilter.java:94)
        at org.mortbay.jetty.servlet.FilterHolder.doStart(FilterHolder.java:97)
        at org.mortbay.component.AbstractLifeCycle.start(AbstractLifeCycle.java:50)
        at org.mortbay.jetty.servlet.ServletHandler.initialize(ServletHandler.java:713)
        at org.mortbay.jetty.servlet.Context.startContext(Context.java:140)
        at org.mortbay.jetty.webapp.WebAppContext.startContext(WebAppContext.java:1282)
        at org.mortbay.jetty.handler.ContextHandler.doStart(ContextHandler.java:518)
        at org.mortbay.jetty.webapp.WebAppContext.doStart(WebAppContext.java:499)
        at org.mortbay.component.AbstractLifeCycle.start(AbstractLifeCycle.java:50)
        at org.mortbay.jetty.handler.HandlerCollection.doStart(HandlerCollection.java:152)
        at org.mortbay.jetty.handler.ContextHandlerCollection.doStart(ContextHandlerCollection.java:156)
        at org.mortbay.component.AbstractLifeCycle.start(AbstractLifeCycle.java:50)
        at org.mortbay.jetty.handler.HandlerCollection.doStart(HandlerCollection.java:152)
        at org.mortbay.component.AbstractLifeCycle.start(AbstractLifeCycle.java:50)
        at org.mortbay.jetty.handler.HandlerWrapper.doStart(HandlerWrapper.java:130)
        at org.mortbay.jetty.Server.doStart(Server.java:224)
        at org.mortbay.component.AbstractLifeCycle.start(AbstractLifeCycle.java:50)
        at org.mortbay.xml.XmlConfiguration.main(XmlConfiguration.java:985)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
        at java.lang.reflect.Method.invoke(Method.java:597)
        at org.mortbay.start.Main.invokeMain(Main.java:194)
        at org.mortbay.start.Main.start(Main.java:534)
        at org.mortbay.start.Main.start(Main.java:441)
        at org.mortbay.start.Main.main(Main.java:119)

解决：
修改apache-solr-3.3.0\example\solr\conf\solrconfig.xml文件，删除内容如下：

<!-- Query Elevation Component
       http://wiki.apache.org/solr/QueryElevationComponent

       a search component that enables you to configure the top
       results for a given query regardless of the normal lucene
       scoring.
    -->
  <searchComponent name="elevator" class="solr.QueryElevationComponent" >
    <!-- pick a fieldType to analyze queries -->
    <str name="queryFieldType">string</str>
    <str name="config-file">elevate.xml</str>
  </searchComponent>

  <!-- A request handler for demonstrating the elevator component -->
  <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
    <lst name="defaults">
      <str name="echoParams">explicit</str>
    </lst>
    <arr name="last-components">
      <str>elevator</str>
    </arr>
  </requestHandler>

wiki上的解释：
[quote]The QueryElevationComponent enables you to configure the top results for a given query regardless of the normal lucene scoring. This is sometimes called "sponsored search", "editorial boosting" or "best bets". This component matches the user query text to a configured Map of top results. Although this component will work with any QueryParser, it makes the most sense to use with DisMax style queries.[/quote]
我的理解：相当于竞价排名，无视搜索的排序，可以额外在顶部配置自定义的结果


7、运行命令：在浏览器中输入：[url]http://localhost:8983/solr/dataimport?command=full-import[/url] 来完成全量数据导入，在每次全量数据导入执行的时候，原有索引会被删除，如果不想删除原有索引，可以运行如下命令：[url]http://localhost:8983/solr/dataimport?command=full-import&clean=false[/url] ，全量数据导入在浏览器中显示的效果如下：

This XML file does not appear to have any style information associated with it. The document tree is shown below.
<response>
    <lst name="responseHeader">
        <int name="status">0</int>
        <int name="QTime">5</int>
    </lst>
    <lst name="initArgs">
        <lst name="defaults">
             <str name="config">data-config.xml</str>
        </lst>
    </lst>
    <str name="command">full-import</str>
    <str name="status">idle</str>
    <str name="importResponse"/>
    <lst name="statusMessages"/>
    <str name="WARNING">
        This response format is experimental. It is likely to change in the future.
    </str>
</response>

8、进行搜索，在浏览器中输入[url]http://localhost:8983/solr/admin/[/url]

[img]http://dl.iteye.com/upload/attachment/538748/3a0c7fc6-96d5-3fe0-9e65-9fb5612c6ef9.png[/img]


搜索结果如下：

This XML file does not appear to have any style information associated with it. The document tree is shown below.
<response>
    <lst name="responseHeader">
        <int name="status">0</int>
        <int name="QTime">0</int>
        <lst name="params">
            <str name="indent">on</str>
            <str name="start">0</str>
            <str name="q">*:*</str>
            <str name="version">2.2</str>
            <str name="rows">10</str>
        </lst>
    </lst>
    <result name="response" numFound="3" start="0">
      <doc>
        <str name="content">这一小节讲搜索引擎，可以通过搜索引擎查找一些数据</str>
        <int name="id">1</int>
        <date name="time">2011-08-18T02:41:35Z</date>
        <str name="title">搜索</str>
        <str name="user">tiehong</str>
      </doc>
      <doc>
        <str name="content">这一小节讲分布式存储，可以存储很多数据</str>
        <int name="id">2</int>
        <date name="time">2011-08-18T02:42:19Z</date>
        <str name="title">存储</str>
        <str name="user">chenyun</str>
      </doc>
      <doc>
        <str name="content">这一小节讲数据导入，可以从mysql数据库中导入数据</str>
        <int name="id">3</int>
        <date name="time">2011-08-18T02:42:59Z</date>
        <str name="title">数据导入</str>
        <str name="user">lengda</str>
      </doc>
    </result>
</response>

9、以不同的名字索引域
上面data-config.xml配置中mysql中表的名字和schema.xml索引的名字相同，也可以配置使用不同的名字，如下：

<dataConfig>
  <dataSource type="JdbcDataSource"
              driver="com.mysql.jdbc.Driver"
              url="jdbc:mysql://localhost/dbname"
              user="user-name"
              password="password"/>
  <document>
    <entity name="id"
            query="select id,name,desc from mytable">
       <field column="id" name="solr_id"/>
       <field column="name" name="solr_name"/>
       <field column="desc" name="solr_desc"/>
    </entity>
  </document>
</dataConfig>

此时，solr_id， solr_name，solr_desc将被写到solr域中，务必注意要在schema.xml文件中配置好这些域

10、从多个表索引数据到Solr
修改data-config.xml文件

<dataConfig>
  <dataSource type="JdbcDataSource"
              driver="com.mysql.jdbc.Driver"
              url="jdbc:mysql://localhost/dbname"
              user="user-name"
              password="password"/>
  <document>
    <entity name="outer"
            query="select id,name,desc from mytable">
       <field column="id" name="solr_id"/>
       <field column="name" name="solr_name"/>
       <field column="desc" name="solr_desc"/>
       <entity name="inner"
               query="select details from another_table where id ='${outer.id}'">
              <field column="details" name="solr_details"/>
       </entity>
    </entity>
  </document>
</dataConfig>

注意：schema.xml中还应该有solr_details域

11、参考：
Solr Data Import 快速入门：[url]http://blog.chenlb.com/2010/03/solr-data-import-quick-start.html[/url]
Index a DB table directly into Solr:[url]http://wiki.apache.org/solr/DIHQuickStart[/url]