Solr 5.3.0集成mmseg4j、tomcat部署、Solrj 5.3.0使用

環境:Jdk 1.7    Solr 5.3.0    Tomcat 7    mmseg4j-solr-2.3.0 java

一、Solr環境搭建 web

1.解壓solr 5.3.0 apache

2.新建solr_home,將解壓文件中的 server/solr 文件夾的複製到solr_home 瀏覽器

3.配置solr_home。在solr_home/solr中新建應用 mysolr tomcat

4.將solr_home/solr/configsets/sample_techproducts_configs中的conf文件夾複製到mysolr中 服務器

5.在mysolr目錄中新建core.properties內容爲name=mysolr   (solr中的mysolr應用) app



6.以tomcat 7爲solr容器,解壓tomcat webapp

7.將solr-5.3.0\server中的solr-webapp複製到tomcat的webapps目錄,重命名爲solr maven


8.複製文件 測試

(1)將如下內容複製到tomcat/webapps/solr/WEB-INF/lib文件夾中

(2)將log4j.properties複製到tomcat/webapps/solr/WEB-INF/classes文件夾中(新建classes)

9.配置solr項目中的web.xml,打開 env-entry節點,配置solr_home



10.啓動tomcat瀏覽器輸入http://localhost:8080/solr


11.選擇剛在solr_home中建的mysolr的應用、測試分詞、默認分詞器對中文支持很差




2、配置中文分詞器(mmseg4j)

mmseg4j-solr-2.3.0支持solr5.3

1.將兩個jar包考入tomcat中solr項目裏的lib文件內


2.配置solr_home中mysolr域的schema.xml

新增:

<fieldtype name="textComplex" class="solr.TextField" positionIncrementGap="100">

<analyzer>

<tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="complex" dicPath="dic"/>

</analyzer>

</fieldtype>

<fieldtype name="textMaxWord" class="solr.TextField" positionIncrementGap="100">

<analyzer>

<tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="max-word" />

</analyzer>

</fieldtype>

<fieldtype name="textSimple" class="solr.TextField" positionIncrementGap="100">

<analyzer>

<tokenizer class="com.chenlb.mmseg4j.solr.MMSegTokenizerFactory" mode="simple" dicPath="n:/custom/path/to/my_dic" />

</analyzer>

</fieldtype>



3.重啓tomcat測試分詞:(選擇剛剛定義的textMaxWord


修改solr_home中mysolr域的schema.xml,新增要用到mmseg4j分詞索引的字段 content_test  分詞器選擇定義好的textMaxWord


<field name="content_test" type="textMaxWord" indexed="true" stored="true" multiValued="true"/>



3、Java調用Solr 5.3


package myjava.cn.dx.solr;

import org.apache.solr.client.solrj.*;
import org.apache.solr.client.solrj.impl.HttpSolrClient;
import org.apache.solr.client.solrj.response.QueryResponse;
import org.apache.solr.common.SolrDocument;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

/**
 * solr 5.3.0
 * Created by daxiong on 2015/10/23.
 */
public class MySolr {

    //solr url
    public static final String URL = "http://localhost:8080/solr";
    //solr應用
    public static final String SERVER = "mysolr";
    //待索引、查詢字段
    public static String[] docs = {"Solr是一個獨立的企業級搜索應用服務器",
                                    "它對外提供相似於Web-service的API接口",
                                    "用戶能夠經過http請求",
                                     "向搜索引擎服務器提交必定格式的XML文件生成索引",
                                    "也能夠經過Http Get操做提出查找請求",
                                    "並獲得XML格式的返回結果"};

    public static SolrClient getSolrClient(){
        return new HttpSolrClient(URL+"/"+SERVER);
    }

    /**
     * 新建索引
     */
    public static void createIndex(){
        SolrClient client = getSolrClient();
        int i = 0;
        List<SolrInputDocument> docList = new ArrayList<SolrInputDocument>();
        for(String str : docs){
            SolrInputDocument doc = new SolrInputDocument();
            doc.addField("id",i++);
            doc.addField("content_test", str);
            docList.add(doc);
        }
        try {
            client.add(docList);
            client.commit();
        } catch (SolrServerException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    };

    /**
     * 搜索
     */
    public static void search(){
        SolrClient client = getSolrClient();
        SolrQuery query = new SolrQuery();
        query.setQuery("content_test:搜索");
        QueryResponse response = null;
        try {
            response = client.query(query);
            System.out.println(response.toString());
            System.out.println();
            SolrDocumentList docs = response.getResults();
            System.out.println("文檔個數:" + docs.getNumFound());
            System.out.println("查詢時間:" + response.getQTime());
            for (SolrDocument doc : docs) {
                System.out.println("id: " + doc.getFieldValue("id") + "      content: " + doc.getFieldValue("content_test"));
            }
        } catch (SolrServerException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        //createIndex();
        search();
    }
}



maven配置 pom.xml

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>

  <groupId>myjava</groupId>
  <artifactId>cn.dx</artifactId>
  <version>1.0-SNAPSHOT</version>
  <packaging>jar</packaging>

  <name>cn.dx</name>
  <url>http://maven.apache.org</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
  </properties>

  <dependencies>
    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.12</version>
      <scope>test</scope>
    </dependency>
    <dependency>
      <groupId>org.apache.solr</groupId>
      <artifactId>solr-solrj</artifactId>
      <version>5.3.0</version>
    </dependency>
    <dependency>
      <groupId>log4j</groupId>
      <artifactId>log4j</artifactId>
      <version>1.2.17</version>
    </dependency>
    <dependency>
      <groupId>commons-logging</groupId>
      <artifactId>commons-logging</artifactId>
      <version>1.1.1</version>
    </dependency>
    
    <dependency>
      <groupId>org.slf4j</groupId>
      <artifactId>slf4j-nop</artifactId>
      <version>1.7.7</version>
    </dependency>
  </dependencies>
</project>

 

相關文章
相關標籤/搜索