java

关注公众号 jb51net

关闭
首页 > 软件编程 > java > Java的Hibernate框架的search工具

详解Java的Hibernate框架中的搜索工具的运用

作者:开心的D哥

这篇文章主要介绍了详解Java的Hibernate框架中的搜索工具的运用,Hibernate是Java的SSH三大web开发框架之一,需要的朋友可以参考下

hibernate提供了全文索引功能,非常棒,这里简要介绍下它的用法,
1. 在pom.xml引入包依赖

<dependency>
      <groupId>org.hibernate</groupId>
      <artifactId>hibernate-search-orm</artifactId>
      <version>${hibernate-search.version}</version>
    </dependency>

    <dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-analyzers-smartcn</artifactId>
      <version>${lucene.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-queryparser</artifactId>
      <version>${lucene.version}</version>
    </dependency>
    <dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-analyzers-phonetic</artifactId>
      <version>${lucene.version}</version>
    </dependency>

hibernate配置 search index保存路径

 <bean id="sessionFactory"
    class="org.springframework.orm.hibernate4.LocalSessionFactoryBean"
    destroy-method="destroy">
    <property name="dataSource" ref="poolingDataSource" />
    <property name="configLocation">
      <value> classpath:hibernate.cfg.xml </value>
    </property>
    <property name="hibernateProperties">
      <props>
        <prop key="hibernate.dialect">${hibernate.dialect}</prop>
        <!-- Booleans can be easily used in expressions by 
           declaring HQL query substitutions in Hibernate configuration -->
        <prop key="hibernate.query.substitutions">true 'Y', false 'N'</prop>
        <!-- http://ehcache.org/documentation/integrations/hibernate -->
        <!-- http://www.tutorialspoint.com/hibernate/hibernate_caching.htm -->
        <prop key="hibernate.cache.use_second_level_cache">true</prop>
        <!-- org.hibernate.cache.ehcache.EhCacheRegionFactory -->
        <prop key="hibernate.cache.region.factory_class">org.hibernate.cache.ehcache.EhCacheRegionFactory</prop>
        <!-- hibernate只会缓存使用load()方法获得的单个持久化对象,如果想缓存使用findall()、 list()、Iterator()、createCriteria()、createQuery()
                等方法获得的数据结果集的话,就需要设置hibernate.cache.use_query_cache true -->
        <prop key="hibernate.cache.use_query_cache">true</prop>
        <prop key="net.sf.ehcache.configurationResourceName">ehcache-hibernate.xml</prop>
        <!-- Hibernate Search index directory -->
        ***<prop key="hibernate.search.default.indexBase">indexes/</prop>*** 
      </props>
    </property>
  </bean> 

对需要搜索的类加上Indexed Annotation,然后对类中可以被搜索的字段加上@Field Annotation,通常Enum字段不需要Analyzer进行词法分析,其他字段则需要,对于不需要Projection(返回部分字段)的情况下,不需要在index中存储实际数据。可以通过AnalyzerDef来定义不同的词法分析器以及对于的特殊词过滤器

@Indexed
@AnalyzerDef(
    name="enTopicAnalyzer",
    charFilters={
      @CharFilterDef(factory=HTMLStripCharFilterFactory.class)
    },
    tokenizer=@TokenizerDef(factory=StandardTokenizerFactory.class),
    filters={
      @TokenFilterDef(factory=StandardFilterFactory.class),
      @TokenFilterDef(factory=StopFilterFactory.class),
      @TokenFilterDef(factory=PhoneticFilterFactory.class,
        params = {
          @Parameter(name="encoder", value="DoubleMetaphone")
        }),
      @TokenFilterDef(factory=SnowballPorterFilterFactory.class,
        params = {
          @Parameter(name="language", value="English")
        })
      }
  )
public class Topic {

  ......
  @Field(index=Index.YES, analyze=Analyze.YES, store=Store.NO)
  @Analyzer(definition = "enTopicAnalyzer")
  private String title;
  ......
  @Field(index=Index.YES, analyze=Analyze.YES, store=Store.NO)
  @Analyzer(definition = "enTopicAnalyzer")
  private String content;
  ......  
  @Enumerated(EnumType.STRING)
  @Field(index=Index.YES, analyze=Analyze.NO, store=Store.NO, bridge=@FieldBridge(impl=EnumBridge.class))
  private TopicStatus status;
  ...
  }

通过代码对已有数据创建index

ApplicationContext context = new ClassPathXmlApplicationContext("spring-resources.xml");

    SessionFactory sessionFactory = (SessionFactory) context.getBean("sessionFactory");

    Session sess = sessionFactory.openSession();
    FullTextSession fullTextSession = Search.getFullTextSession(sess);
    try {
      fullTextSession.createIndexer().startAndWait();
    } catch (InterruptedException e) {
       LOG.error(e.getMessage(), e);
    } finally {
      fullTextSession.close();
    }
    ((AbstractApplicationContext)context).close();

创建查询fulltextsession,按照query条件获取结果

 FullTextSession fullTextSession = Search
        .getFullTextSession(getSession());

    QueryBuilder queryBuilder = fullTextSession.getSearchFactory()
        .buildQueryBuilder().forEntity(Show.class).get();
    org.apache.lucene.search.Query luceneQuery = null;

      luceneQuery = queryBuilder.keyword()// .wildcard()
          .onFields("title", "content").matching(query.getKeyword())
          // .matching("*" + query.getKeyword() + "*")
          .createQuery();

    FullTextQuery hibernateQuery = fullTextSession.createFullTextQuery(
        luceneQuery, Show.class);
    return hibernateQuery.list();

note:
1. 在一次测试过程中,修改了value object,添加了新的index,忘记了rebuildIndex,结果unit test没问题,生成环境就出错了。
2. 搜索还不是很强大,比如搜索测,含有测试的结果可能就搜索不出来

中文词法分析

hibernate search底层使用Lucene,所以Lucene可以使用的中文分词,hibernate search都可以用来支持中文词法分析,比较常用的词法分析器包括paoding,IKAnalyzer,mmseg4j 等等。具体可以参考分词分析 最近分析。hibernate search默认的分词器是org.apache.lucene.analysis.standard.StandardAnalyzer,中文按字分词,显然不符合我们的需求。
这里介绍一下如何在hibernate中配置中文分词,选择的是Lucene自带的中文分词–。使用可以通过3种方式,一种是在hibernate的配置文件设置词法分析方法,另外一种是在每个需要被搜索的类中定义分词方法,最后一种是对单个字段配置。这里介绍下前2种的配置方式。
hibernate配置方式:

<property name="hibernate.search.analyzer"> org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer</property>

被搜索类配置中文分词:

@Indexed
@Analyzer(impl=SmartChineseAnalyzer.class)

同时需要在maven中引入相关包依赖

<dependency>
      <groupId>org.apache.lucene</groupId>
      <artifactId>lucene-analyzers-smartcn</artifactId>
      <version>${lucene.version}</version>
    </dependency>

多条件查询
hibernate search可以通过多组合条件来实现多条件查询,这里简单介绍一下多条件查询的一个实践。
如果只是单个条件查询,那么这个查询就可以很简单

luceneQuery = queryBuilder.keyword().onFields("title", "content").matching(query.getKeyword()).createQuery()

如果是多条件并查询,那么就需要使用到Must Join,如果是多条件或查询,就需要使用should Join,这里举个Must Join的例子

//must true
MustJunction term = queryBuilder.bool().must(queryBuilder.keyword()
          .onFields("title", "content")   .matching(query.getKeyword()).createQuery());
//must false
 term.must(queryBuilder.keyword()
              .onField("status")             .matching(query.getExcludeStatus()).createQuery()).not();

完整例子:

private FullTextQuery findByKeywordQuery(TopicQuery query) {
    FullTextSession fullTextSession = Search
        .getFullTextSession(getSession());


    QueryBuilder queryBuilder = fullTextSession.getSearchFactory()
        .buildQueryBuilder().forEntity(Topic.class).get();
    org.apache.lucene.search.Query luceneQuery = null;
    if (null == query.getStatus() && null == query.getUsername() && null == query.getExcludeStatus()) {
      luceneQuery = queryBuilder.keyword()// .wildcard()
          .onFields("title", "content").matching(query.getKeyword())
          // .matching("*" + query.getKeyword() + "*")
          .createQuery();
      if(LOG.isDebugEnabled()){
        LOG.debug("create clean keyword search query: " + luceneQuery.toString());
      }
    } else {
      MustJunction term = queryBuilder.bool().must(queryBuilder.keyword()
          .onFields("title", "content")   .matching(query.getKeyword()).createQuery());
      if(null != query.getStatus()){
        term.must(queryBuilder.keyword()
              // .wildcard()
              .onField("status")
              .matching(query.getStatus()).createQuery());
      }
      if(null != query.getExcludeStatus()){
        term.must(queryBuilder.keyword()
              .onField("status")
              .matching(query.getExcludeStatus()).createQuery()).not();
      }
      if(null != query.getUsername()){
        term.must(queryBuilder.keyword()
              // .wildcard()
              .onField("owner.username")
               .ignoreFieldBridge()
              .matching(query.getUsername()).createQuery());
      }
      luceneQuery =term.createQuery();
      if(LOG.isDebugEnabled()){
        LOG.debug("create complicated keyword search query: " + luceneQuery.toString());
      }
    }
    // BooleanQuery
    FullTextQuery hibernateQuery = fullTextSession.createFullTextQuery(
        luceneQuery, Topic.class);
    return hibernateQuery;
  }

您可能感兴趣的文章:
阅读全文