`

hibernate Search 学习研究 附件是maven工程

 
阅读更多

 

Jboss 的 hibernate search 支持 hibernate 应该比较好。

 

所以想在项目 里面使用 hibernate search 进行 搜索。

 

分词使用的是 IKAnalyzer 

 

网站是 :

 

http://code.google.com/p/ik-analyzer/

 

使用的 是 hibernate 3.6.8 + spring 3.0.6 + hibernate search 3.4.1 +IKAnalyzer 3.2.8 

 

数据库是mysql  链接池是 c3p0 

 

 

在 hibernate search 3.4 版本的时候 就不需要配置 hibernate 的监听了。(Jboss 自家的东西支持就是好点)

 

下面是配置文件:

 

 

<bean id="sessionFactory"
		class="org.springframework.orm.hibernate3.annotation.AnnotationSessionFactoryBean">
		<property name="dataSource">
			<ref bean="dataSource" />
		</property>
		<property name="packagesToScan">
			<list>
				<value>com.freewebsys</value>
			</list>
		</property>
		<!-- <property name="mappingDirectoryLocations"> <list> <value>classpath:com/**/pojo</value> 
			</list> </property> -->
		<property name="hibernateProperties">
			<props>
				<prop key="hibernate.dialect">${hibernate.dialect}</prop>
				<!-- <prop key="hibernate.dialect"> org.hibernate.dialect.Oracle9Dialect 
					</prop> <prop key="hibernate.dialect"> org.hibernate.dialect.MySQLDialect 
					</prop> -->
				<prop key="hibernate.hbm2ddl.auto">${hibernate.hbm2ddl.auto}</prop>
				<prop key="cglib.use_reflection_optimizer">true</prop>
				<prop key="hibernate.show_sql">${hibernate.show_sql}</prop>
				<prop key="hibernate.jdbc.fetch_size">${hibernate.jdbc.fetch_size}</prop>
				<prop key="hibernate.jdbc.batch_size">${hibernate.jdbc.batch_size}</prop>
				<prop key="hibernate.cache.use_query_cache">${hibernate.cache.use_query_cache}</prop>
				<!-- <prop key="hibernate.cache.provider_class">${hibernate.cache.provider_class} 
					</prop> -->
				<prop key="hibernate.query.substitutions">true 1, false 0, yes 'Y', no 'N'</prop>

				<!-- add hibernate search. -->
				<prop key="hibernate.search.default.directory_provider">${hibernate.search.default.directory_provider}</prop>
				<prop key="hibernate.search.default.indexBase">${hibernate.search.default.indexBase}</prop>
				<prop key="hibernate.search.analyzer">${hibernate.search.analyzer}</prop>

			</props>
		</property>
	</bean>

 

 

 

 

 

<property name="packagesToScan">这个属性直接可以把配置下面的java bena 读取出来。不用一条一条添加了。

 

 

然后就是配置 hiberante 事物。

 

 

<!-- ####下面是用spring对事务进行配置的代码.#####开始 -->
	<bean id="transactionManager"
		class="org.springframework.orm.hibernate3.HibernateTransactionManager">
		<property name="sessionFactory">
			<ref bean="sessionFactory" />
		</property>
	</bean>

	<bean id="hibernateTemplate" class="org.springframework.orm.hibernate3.HibernateTemplate">
		<property name="sessionFactory">
			<ref bean="sessionFactory" />
		</property>
		<property name="cacheQueries">
			<value>true</value>
		</property>
	</bean>

	<bean id="transactionInterceptor"
		class="org.springframework.transaction.interceptor.TransactionInterceptor">
		<property name="transactionManager" ref="transactionManager" />
		<property name="transactionAttributes">
			<props>
				<prop key="*">PROPAGATION_REQUIRED,-Exception</prop>
				<prop key="find*">PROPAGATION_REQUIRED,readOnly
				</prop>
				<prop key="list*">PROPAGATION_REQUIRED,readOnly
				</prop>
				<prop key="get*">PROPAGATION_REQUIRED,readOnly
				</prop><!-- find和get方法开头的是只读的事务,其他的都进行提交回滚. -->
			</props>
		</property>
	</bean>
	<bean
		class="org.springframework.aop.framework.autoproxy.BeanNameAutoProxyCreator">
		<property name="beanNames">
			<value>*Service</value>
			<!-- <value>*Mgr, *Service , *Director , *Outputter , importTask</value> 
				这个是通过对事务进行批量配置.对bean的名字含有Service的统统进行事务配置. 这样严格控制业务逻辑在service实现.如果有在action层进行查询的无所谓.但是 
				保持更新在action是绝度不行的. -->
		</property>
		<property name="interceptorNames">
			<list>
				<value>transactionInterceptor</value>
			</list>
		</property>
	</bean>

	<bean
		class="org.springframework.transaction.interceptor.TransactionAttributeSourceAdvisor">
		<property name="transactionInterceptor" ref="transactionInterceptor" />
	</bean>

	<!-- Auto scan the components -->
	<context:component-scan base-package="com.freewebsys" />
 

 

 

创建搜索的 bean 

 

 

package com.freewebsys.demo.pojo;

import javax.persistence.Column;
import javax.persistence.Entity;
import javax.persistence.GeneratedValue;
import javax.persistence.GenerationType;

import static javax.persistence.GenerationType.IDENTITY;
import javax.persistence.Id;
import javax.persistence.Table;
import javax.persistence.UniqueConstraint;

import org.hibernate.search.annotations.Analyzer;
import org.hibernate.search.annotations.DocumentId;
import org.hibernate.search.annotations.Field;
import org.hibernate.search.annotations.Index;
import org.hibernate.search.annotations.Indexed;
import org.hibernate.search.annotations.Store;
import org.wltea.analyzer.lucene.IKAnalyzer;

@Entity
@Table(name = "user_info")
@Indexed
public class UserInfo implements java.io.Serializable {

	private Long id;
	private String userName;
	private String passwd;
	private String city;
	private String content;

	public UserInfo() {
	}

	@Id
	@GeneratedValue(strategy = GenerationType.IDENTITY)
	@Column(name = "id", unique = true, nullable = false)
	@DocumentId
	public Long getId() {
		return id;
	}

	public void setId(Long id) {
		this.id = id;
	}

	@Column(name = "user_name", unique = false, nullable = true, length = 100)
	@Field(name = "user_name", index = Index.TOKENIZED, store = Store.YES)
	public String getUserName() {
		return userName;
	}

	public void setUserName(String userName) {
		this.userName = userName;
	}

	@Column(name = "passwd", unique = false, nullable = true, length = 100)
	@Field(name = "passwd", index = Index.TOKENIZED, store = Store.YES)
	public String getPasswd() {
		return passwd;
	}

	public void setPasswd(String passwd) {
		this.passwd = passwd;
	}

	@Column(name = "city", unique = false, nullable = true, length = 100)
	@Field(name = "city", index = Index.TOKENIZED, store = Store.YES)
	public String getCity() {
		return city;
	}

	public void setCity(String city) {
		this.city = city;
	}

	@Column(name = "content", unique = false, nullable = true, length = 4000)
	@Field(name = "content", index = Index.TOKENIZED, store = Store.YES, analyzer = @Analyzer(impl = IKAnalyzer.class))
	public String getContent() {
		return content;
	}

	public void setContent(String content) {
		this.content = content;
	}

	@Override
	public String toString() {
		return "UserInfo [id=" + id + ", userName=" + userName + ", passwd="
				+ passwd + ", city=" + city + ", content=" + content + "]";
	}

}

 

 

 

@Indexed 标识这个要被索引。

 

@Field(name = "user_name", index = Index.TOKENIZED, store = Store.YES)

标识 索引字段

 

 

@Field(name = "content", index = Index.TOKENIZED, store = Store.YES, analyzer = @Analyzer(impl = IKAnalyzer.class))

 

具体 其他参数 参考 博客 : http://sin90lzc.iteye.com/blog/1106258

 

标识索引字段并表示分词 为 IKAnalyzer

 

然后 就是 service 写的。。这里 省略了 dao 层 service 直接 继承 HibernateDaoSupport

 

 

package com.freewebsys.demo.service.impl;

import java.util.List;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.analysis.StopAnalyzer;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.util.Version;
import org.hibernate.Query;
import org.hibernate.SessionFactory;
import org.hibernate.search.FullTextQuery;
import org.hibernate.search.FullTextSession;
import org.hibernate.search.Search;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.orm.hibernate3.support.HibernateDaoSupport;
import org.springframework.stereotype.Service;
import org.springframework.transaction.annotation.Transactional;
import org.wltea.analyzer.lucene.IKAnalyzer;

import com.freewebsys.demo.pojo.UserInfo;
import com.freewebsys.demo.service.UserInfoService;

@Service("userInfoService")
public class UserInfoServiceImpl extends HibernateDaoSupport implements
		UserInfoService {

	private static Log log = LogFactory.getLog(UserInfoServiceImpl.class);

	@Autowired
	public void setMySessionFactory(SessionFactory sessionFactory) {
		setSessionFactory(sessionFactory);
	}

	@Transactional
	public void save(UserInfo userInfo) {
		getHibernateTemplate().save(userInfo);
	}

	@Transactional
	public void delete(UserInfo userInfo) {
		getHibernateTemplate().delete(userInfo);
	}

	/**
	 * 使用hql 进行查询。
	 */
	@Transactional
	public List<UserInfo> findUserInfo(String userName) {
		String hql = " from UserInfo userInfo where userInfo.userName = ? ";
		return getHibernateTemplate().find(hql, userName);
	}

	public List<UserInfo> findUserInfoBySearchContent(String content) {
		FullTextSession fullTextSession = Search
				.getFullTextSession(getSession());

		QueryParser parser = new QueryParser(Version.LUCENE_31, "content",
				new SimpleAnalyzer(Version.LUCENE_31));
		org.apache.lucene.search.Query luceneQuery = null;
		try {
			luceneQuery = parser.parse(content);
		} catch (ParseException e) {
			e.printStackTrace();
		}
		FullTextQuery fullTextQuery = fullTextSession.createFullTextQuery(
				luceneQuery, UserInfo.class);
		List<UserInfo> useList = (List<UserInfo>) fullTextQuery.list();

		// 高亮设置
		SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(
				"<b><font color='red'>", "</font></b>");

		QueryScorer qs = new QueryScorer(luceneQuery);
		Highlighter highlighter = new Highlighter(formatter, qs);
		// 这个20是指定关键字字符串的context的长度,你可以自己设定,因为不可能返回整篇正文内容
		highlighter.setTextFragmenter(new SimpleFragmenter(20));

		for (UserInfo userInfo : useList) {
			Analyzer analyzer = new IKAnalyzer();
			try {
				String contentHighLighter = highlighter.getBestFragment(
						analyzer, content, userInfo.getContent());
				System.out.println(contentHighLighter);
				userInfo.setContent(contentHighLighter);
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
		return useList;

	}

	/**
	 * 查询全部数据
	 */
	public List<UserInfo> findAllUserInfo() {
		String hql = " from UserInfo userInfo";
		return getHibernateTemplate().find(hql);
	}

}

 最关键的就是搜索 然后 显示 高亮并 将文章内容截取 。

 

也可以使用setFirstResult setMaxResults 对搜索进行分页。

 

fullTextQuery.getResultSize() 是获得总页数。

 

 

					fullTextQuery.setFirstResult((pageNo - 1) * pageSize);
					fullTextQuery.setMaxResults(pageSize);
 

 

 

在使用 高亮显示的时候 二次进行了 分词。找到 查询内容:

 

 

// 高亮设置
		SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(
				"<b><font color='red'>", "</font></b>");

		QueryScorer qs = new QueryScorer(luceneQuery);
		Highlighter highlighter = new Highlighter(formatter, qs);
		// 这个20是指定关键字字符串的context的长度,你可以自己设定,因为不可能返回整篇正文内容
		highlighter.setTextFragmenter(new SimpleFragmenter(20));

		for (UserInfo userInfo : useList) {
			Analyzer analyzer = new IKAnalyzer();
			try {
				String contentHighLighter = highlighter.getBestFragment(
						analyzer, content, userInfo.getContent());
				System.out.println(contentHighLighter);
				userInfo.setContent(contentHighLighter);
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
		return useList;
 

在test 里面是测试 先初始化 数据库。

 

还可以对 数据里面的html 代码去掉。然后再展示:

 

QueryScorer qs = new QueryScorer(luceneQuery);
		Highlighter highlighter = new Highlighter(formatter, qs);
		// 这个20是指定关键字字符串的context的长度,你可以自己设定,因为不可能返回整篇正文内容
		highlighter.setTextFragmenter(new SimpleFragmenter(20));
		String contentStr = null;

		for (UserInfo userInfo : useList) {
			Analyzer analyzer = new IKAnalyzer();
			try {
				contentStr = userInfo.getContent();
				// 去掉所有html元素,
				contentStr = contentStr.replaceAll("<[a-zA-Z]+[1-9]?[^><]*>",
						"").replaceAll("</[a-zA-Z]+[1-9]?>", "");

				String contentHighLighter = highlighter.getBestFragment(
						analyzer, content, contentStr);
				System.out.println(contentHighLighter);
				userInfo.setContent(contentHighLighter);
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
 

 

 

运行junit 测试:

 

 

List<UserInfo> list = userInfoService
				.findUserInfoBySearchContent("三个月");

		System.out.println(list.size());
		System.out.println("Finish ########");

		for (UserInfo userInfo : list) {
			System.out.println(userInfo);
		}

 

 

查询结果如下:

 

 

<b><font color='red'>三个月</font></b>必须到杭州进行全身心开发,<b><font color='red'>三个月</font></b>之后
<b><font color='red'>三个月</font></b>可以全身心在杭州专注于项目开发。<b><font color='red'>三个月</font></b>
开发的<b><font color='red'>三个月</font></b>内,天使湾将在杭州每周举办分享
<b><font color='red'>三个月</font></b>内,不同创业团队在确保独立自主的
地。在杭州<b><font color='red'>三个月</font></b>期间创业团队的住宿餐饮
<b><font color='red'>三个月</font></b>绝对以一当十! 9.天使湾聚变

 到页面就可以显示 高亮并 截取字符串了。

 

目前有一个问题就是 查询的时候 同时也执行 sql 查询。

 

如执行:

 

Hibernate: select this_.id as id0_0_, this_.city as city0_0_, this_.passwd as passwd0_0_, this_.user_name as user4_0_0_ from user_info this_ where (this_.id in (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?))

 

将 搜索查询 到的数据 从数据库中提取出来。

 

总的来说 hibernate search 将 搜索简化了很多。

 

附件是 工程代码:

 

 

2
4
分享到:
评论
3 楼 zhengliming123 2014-12-29  
  • [img][img][*]
    [*][*]
    [/flash]
    |
  • [/img][/img]
2 楼 toeo 2011-11-29  
KimHo 写道
这个应用场景是啥?
全文检索还是什么?



是lucence 的全文检索。
只不过是用了下 hibernate search 进行了封装下。简单快速实现功能。
1 楼 KimHo 2011-11-29  
这个应用场景是啥?
全文检索还是什么?

相关推荐

Global site tag (gtag.js) - Google Analytics