solr1.3 multicore + tomcat5.5 + paoding分词安装

一.安装jdk6,tomcat5.5。
二.解压solr1.3,创建以下目录:
  /usr/local/solr/solrApps: 保存的是solr.war
  /usr/local/solr/multicore  : 保存的是多核 solr的配制文件
拷贝solr1.3解压目录里的dist/apache-solr-1.3.0.war到solrApps里,example/multicore里的文件到multicore里。
三.配制如下:
   1.在tomcat/conf/Catalina/localhost目录里增加solr.xml内容如下:
<?xml version="1.0" encoding="UTF-8" ?>

<Context docBase="/usr/local/solr/solrApps/solr.war" debug="0" crossContext="true" >
   <Environment name="solr/home" type="java.lang.String" value="/usr/local/solr/multicore" override="true" />
</Context>

  2.修改solr/multicore/solr.xml配制solr的多核参数为:
<solr persistent="false" sharedLib="paodingLib"> //增加一个共享lib配制,存放中文分词paoding的文件。

  <!--
  adminPath: RequestHandler path to manage cores.  
    If 'null' (or absent), cores will not be manageable via REST
  -->
  <cores adminPath="/admin/cores">
    <core name="core0" instanceDir="core0" />
    <core name="core1" instanceDir="core1" />
  </cores>
</solr>

  3.配制multicore/core0/conf/solrconfig.xml,内容如下:
<config>
  <updateHandler class="solr.DirectUpdateHandler2" />
  
  <dataDir>/usr/local/solr/multicore/sodao</dataDir>  //此处配制每个core创建个自索引文件的目录,在配制目录下自动创建一个index目录,保存索引文件

  <requestDispatcher handleSelect="true" >
    <requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
  </requestDispatcher>
  
  <requestHandler name="standard" class="solr.StandardRequestHandler" default="true" />
  <requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
  <requestHandler name="/admin/" 
class="org.apache.solr.handler.admin.AdminHandlers" />

     
  <!-- config for the admin interface -->
  <admin>
    <defaultQuery>solr</defaultQuery>
  </admin>

</config>

这个目录里的schema.xml为创建索引文件的配制。

四、起动tomcat,输入http://localhost:8080/solr,测试

五、配制中文paoding分词
  1.在网上下载paoding分词,将分词的lib包放到/usr/local/solr/multicore放到这个目录下面,并编写如下类:
package net.qhsoft.analyzer;

import java.io.Reader;
import java.util.Map;

import net.paoding.analysis.analyzer.PaodingTokenizer;
import net.paoding.analysis.analyzer.TokenCollector;
import net.paoding.analysis.knife.PaodingMaker;
import net.paoding.analysis.analyzer.impl.MostWordsTokenCollector;
import net.paoding.analysis.analyzer.impl.MaxWordLengthTokenCollector;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.analysis.BaseTokenizerFactory;

public class ChineseTokenizerFactory extends BaseTokenizerFactory {

    /**

     * 最多切分   默认模式

     */

    public static final String MOST_WORDS_MODE = "most-words";

    /**

     * 按最大切分

     */

    public static final String MAX_WORD_LENGTH_MODE = "max-word-length";

    private String mode = null;

    public void setMode(String mode) {

             if (mode==null||MOST_WORDS_MODE.equalsIgnoreCase(mode)

                      || "default".equalsIgnoreCase(mode)) {

                  this.mode=MOST_WORDS_MODE;

             } else if (MAX_WORD_LENGTH_MODE.equalsIgnoreCase(mode)) {

                  this.mode=MAX_WORD_LENGTH_MODE;

             }

             else {

                  throw new IllegalArgumentException("不合法的分析器Mode参数设置:" + mode);

             }

        }

    @Override

    public void init(Map<String, String> args) {

        super.init(args);

        setMode(args.get("mode"));

    }

    public TokenStream create(Reader input) {

        return new PaodingTokenizer(input, PaodingMaker.make(),

                  createTokenCollector());

    }

    private TokenCollector createTokenCollector() {

        if( MOST_WORDS_MODE.equals(mode))

             return new MostWordsTokenCollector();

        if( MAX_WORD_LENGTH_MODE.equals(mode))

             return new MaxWordLengthTokenCollector();

        throw new Error("never happened");

    }

}



打成一个net.jar包,也放到lib包里面

  2. 把paoding的字典放到/usr/local/solr/multicore下面的dic目录里,并编辑/etc/profile文件,增加:
export PAODING_DIC_HOME=/usr/local/solr/multicore/dic
  3.将lib目录下的paoding-analysis.properties,paoding-dic-home.properties两个文件考到/usr/local/solr目录下面。

你可能感兴趣的:(tomcat,.net,xml,Lucene,Solr)