集成Hibernate Search做全文检索

集成Hibernate Search做全文检索 原文来自 http://blog.csdn.net/zhengwei223/article/details/11952763

 

版本及依赖：

 

<dependency>
            <groupId>org.hibernate</groupId>
            <artifactId>hibernate-search-orm</artifactId>
            <version>4.2.0.Final</version>
        </dependency>

<dependency>
<span style="white-space:pre">          </span><groupId>org.apache.lucene</groupId>
<span style="white-space:pre">          </span><artifactId>lucene-smartcn</artifactId>
<span style="white-space:pre">          </span><version>3.6.2</version>
<span style="white-space:pre">      </span></dependency>

 

1、修改hibernate主配置文件，增加：

 

<property name="hibernate.search.default.directory_provider">
            org.hibernate.search.store.impl.FSDirectoryProvider
        </property>
        <property name="hibernate.search.default.indexBase">
            e:\luceneLinde
        </property>

一个是存储的实现，一个是存储的路径

 

 

2、给实体类上注解

 

import javax.persistence.*;

import org.hibernate.annotations.GenericGenerator;

import org.hibernate.search.annotations.DocumentId;
import org.hibernate.search.annotations.Field;
import org.hibernate.search.annotations.Indexed;
import org.hibernate.search.annotations.IndexedEmbedded;
import org.hibernate.search.annotations.Store;


@Entity
@Table(name = "PAGEINFO")
@Indexed(index="PageInfo")/*标记该表可索引，参数index指定存放索引信息的文件名，路径在主配置文件中指定*/

@Analyzer(impl=SmartChineseAnalyzer.class)//分词器
public class Pageinfo implements java.io.Serializable {
    private static final long serialVersionUID = 5454155825314635342L;



    // columns START
//省略1000字
    // columns END

    @Id
    @GeneratedValue(generator = "custom-id")
    @GenericGenerator(name = "custom-id", strategy = "uuid")
    @Column(name = "ID", unique = true, nullable = false, insertable = true, updatable = true, length = 32)
    @DocumentId  /*以字段id作为文档id*/
    public java.lang.String getId() {
        return this.id;
    }

    @Column(name = "TITLE", unique = false, nullable = true, insertable = true, updatable = true, length = 255)
    @Field(store=Store.NO)  /*可索引，但不存储*/
    public java.lang.String getTitle() {
        return this.title;
    }

    @Column(name = "CONTENT", unique = false, nullable = true, insertable = true, updatable = true)
    @Field(store=Store.NO)
    public java.lang.String getContent() {
        return this.content;
    }

    @Column(name = "SOURCE", unique = false, nullable = true, insertable = true, updatable = true)
    @Field(store=Store.NO)
    public java.lang.String getSource() {
        return this.source;
    }


    @Column(name = "SUMMARY", unique = false, nullable = true, insertable = true, updatable = true)
    @Field(store=Store.NO)
    public java.lang.String getSummary() {
        return this.summary;
    }


    @ManyToOne(cascade = {}, fetch = FetchType.LAZY)
    @JoinColumns({ @JoinColumn(name = "SITE_ID", nullable = false, insertable = false, updatable = false) })
    @IndexedEmbedded(prefix="site_",depth=1)  /*关联检索，如field为site_name实则是按关联表的那么属性检索*/
    public GrabageSiteconfig getGrabageSiteconfig() {
        return grabageSiteconfig;
    }

}

省略了大量东西，如域成员，set方法等，一般以id作为doc的id，其他的你想对哪些字段做全文检索，就使用@Field标记，至于其store属性和lucene中的含义一致，不赘述。

 

 

3、使用API

 

package othertest;

import java.util.Iterator;
import java.util.List;

import javacommon.gather.bean.Pageinfo;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.Version;
import org.hibernate.Session;
import org.hibernate.SessionFactory;
import org.hibernate.Transaction;
import org.hibernate.search.FullTextQuery;
import org.hibernate.search.FullTextSession;
import org.hibernate.search.Search;
import org.junit.Before;
import org.junit.BeforeClass;
import org.junit.Test;

public class SearchTest {
    private static SessionFactory sf;

    @BeforeClass
    public static void init() {
        sf = HibernateConfigTest.sf;//弄一个SessionFactory，不多说

    }
    @Before
    //执行索引
    public void index(){
        Session session = sf.openSession();
        FullTextSession fullTextSession = Search.getFullTextSession(session);
        //查出结果
        List<Pageinfo> pageinfos = session.createCriteria(Pageinfo.class).list();
        session.beginTransaction();
        //依次建立索引
        for (Iterator iterator = pageinfos.iterator(); iterator.hasNext();) {
            Pageinfo pageinfo = (Pageinfo) iterator.next();
            fullTextSession.index(pageinfo);
        }
        session.getTransaction().commit();
        session.close();
        System.out.println("index over......");
    }

    @Test
    public void searchTest() {
        Session session = sf.openSession();
        FullTextSession fullTextSession = Search.getFullTextSession(session);
        //在字段content中检索
        QueryParser queryParser = new QueryParser(Version.LUCENE_36, "content", new SmartChineseAnalyzer(Version.LUCENE_36));
        Query luceneqQuery=null;
        try {
            //检索含有“大风”的信息
            luceneqQuery = queryParser.parse("大风");
        } catch (ParseException e) {
            e.printStackTrace();
        }
        //执行检索，得到结果集
        FullTextQuery fullTextQuery = fullTextSession.createFullTextQuery(luceneqQuery, Pageinfo.class);
        List<Pageinfo> pageinfos = fullTextQuery.list();
        //查看结果做验证
        for (Iterator iterator = pageinfos.iterator(); iterator.hasNext();) {
            Pageinfo pageinfo = (Pageinfo) iterator.next();
            System.out.println(pageinfo.getContent());
        }
    }
}