详解Java的Hibernate框架中的搜索工具的运用

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;
  }