最近公司做一个文档管理系统，需要用到Lucene搜索引擎，一接触这个东东也开始在网上搜索一翻，但是搜索了很久都没能找到一个完全能整合我们现有的SSH的框架中。
先大体说一下，我遇到的问题：
1.包冲突的问题
2.分词类的选择
对问题解决方法：
1.关键包使用以下包： Hibernate core 3.3.1.GA，Hibernate Search 3.1.0.GA,Hibernate Annotations 3.2.0.GA,slf4j-api- 1.5.6.jar，slf4j-log4j12-1.5.6.jar，log4j-1.2.15.jar，solr-core-1.3.0.jar，Lucene2.9.1,Spring2.5,struts2.1
2.使用中文分词类得特别注意，一些中文分词类只能识别中文，对英文支持不好，建议使用：je-analysis-1.5.1.jar
现在把一些关键的部分的代码复制如下：
持久对象：
[java]
view plaincopypackage com.yhwj.docsh.domain;
import java.util.Date;
import java.util.Set;
import javax.persistence.Entity;
import javax.persistence.Id;
import jeasy.analysis.MMAnalyzer;
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;
@Entity
@Analyzer(impl = MMAnalyzer.class)
@Indexed(index="Doc")
public class Doc implements Cloneable{
private Long id;
private String docName;
/**
* 文件大小：byte
*/
private Long docSize;
/**
* 文件类型：doc xls txt
*/
private String docType;
/**
* 文件种类：综合类、资源类、维护优化类、资本工程类、人力资源类、网管支撑类、监控应急类、企业发展类、安全类
*/
private String docVariety;
/**
* 上传者id
*/
private User docUpLoader;
/**
* 收藏夹
*/
private Set<Collector> collectors;
/**
* 上传时间
*/
private Date docUpTime;
/**
* 可否下载
*/
private boolean download;
/**
* 可否删除 1为删除 0为未删除
*/
private boolean deleted;
/**
* 关键字
*/
private String keywords;
/**
* 权限 1：向所有用户开放 2：仅向上级领导开放 3：只针对部分选择的用户开放
*/
private int limited;
/**
* 当权限为3时，此处用户列表就是该文件的开放访问列表
*/
private String limitedUser;
/**
* 描述
*/
private String detail;
/**
* 用户名
*/
private String userName;
@Id
@DocumentId
public Long getId() {
return id;
}
public void setId(Long id) {
this.id = id;
}
@Field(name="docName",index=Index.TOKENIZED,store=Store.YES)
public String getDocName() {
return docName;
}
public void setDocName(String docName) {
this.docName = docName;
}
public Long getDocSize() {
return docSize;
}
public void setDocSize(Long docSize) {
this.docSize = docSize;
}
@Field(name="docType",index=Index.TOKENIZED,store=Store.YES)
public String getDocType() {
return docType;
}
public void setDocType(String docType) {
this.docType = docType;
}
@Field(name="docVariety",index=Index.TOKENIZED,store=Store.YES)
public String getDocVariety() {
return docVariety;
}
public void setDocVariety(String docVariety) {
this.docVariety = docVariety;
}
public User getDocUpLoader() {
return docUpLoader;
}
public void setDocUpLoader(User docUpLoader) {
this.docUpLoader = docUpLoader;
}
@Field(name="docUpTime",index=Index.TOKENIZED,store=Store.YES)
public Date getDocUpTime() {
return docUpTime;
}
public void setDocUpTime(Date docUpTime) {
this.docUpTime = docUpTime;
}
public boolean isDownload() {
return download;
}
public void setDownload(boolean download) {
this.download = download;
}
public boolean isDeleted() {
return deleted;
}
public void setDeleted(boolean deleted) {
this.deleted = deleted;
}
@Field(name="keyWords",index=Index.TOKENIZED,store=Store.YES)
public String getKeywords() {
return keywords;
}
public void setKeywords(String keywords) {
this.keywords = keywords;
}
public int getLimited() {
return limited;
}
public void setLimited(int limited) {
this.limited = limited;
}
public String getLimitedUser() {
return limitedUser;
}
public void setLimitedUser(String limitedUser) {
this.limitedUser = limitedUser;
}
public String getDetail() {
return detail;
}
public void setDetail(String detail) {
this.detail = detail;
}
/**
* 注意Lucene中文分词不支持类关联
**/
@Field(name="userName",index=Index.TOKENIZED,store=Store.YES)
public String getUserName() {
return docUpLoader.getUsername();
}
public void setUserName(String userName) {
this.userName = userName;
}
public Set<Collector> getCollectors() {
return collectors;
}
public void setCollectors(Set<Collector> collectors) {
this.collectors = collectors;
}
}
Hibernate的配置文件，这个我个人认为是必须的，在网上看到很多直接在spring配置文件里，直接进行配置，但是我尝试了很多次最终没有成功，故最后还是不得不使用Hibernate配置文件
[xhtml]
view plaincopy<?xml version='1.0' encoding='UTF-8'?>
<!DOCTYPE hibernate-configuration PUBLIC
"-//Hibernate/Hibernate Configuration DTD 3.0//EN"
"http://hibernate.sourceforge.net/hibernate-configuration-3.0.dtd">
<!-- Generated by MyEclipse Hibernate Tools. -->
<hibernate-configuration>
<session-factory name="sessionFactory">
<property name="hibernate.search.default.indexBase">D://indexDir//file</property>
<property name="hibernate.lucene.analyzer">jeasy.analysis.MMAnalyzer</property>
<event type="post-update">
<listener class="org.hibernate.search.event.FullTextIndexEventListener" />
</event>
<event type="post-insert">
<listener class="org.hibernate.search.event.FullTextIndexEventListener" />
</event>
<event type="post-delete">
<listener class="org.hibernate.search.event.FullTextIndexEventListener" />
</event>
</session-factory>
</hibernate-configuration>
配置spring加载Hibernate文件的代码，注意业务逻辑层需要申明事物，Hibernate只有在事物提交的时候采取更新索引
[xhtml]
view plaincopy<bean id="sessionFactory" class="org.springframework.orm.hibernate3.LocalSessionFactoryBean">
<property name="dataSource" ref="dataSource" />
<property name="mappingResources">
<list>
</list>
</property>
<property name="hibernateProperties">
<props>
<prop key="hibernate.dialect">${hibernate.dialect}</prop>
<prop key="hibernate.show_sql">${hibernate.show_sql}</prop>
<prop
key="hibernate.format_sql">${hibernate.format_sql}</prop>
<prop key="hibernate.use_sql_comments">${hibernate.use_sql_comments}</prop>
<prop key="hibernate.hbm2ddl.auto">${hibernate.hbm2ddl.auto}</prop>
</props>
</property>
<property name="configurationClass" value="org.hibernate.cfg.AnnotationConfiguration"/>
<property name="configLocation">
<value type="org.springframework.core.io.Resource">classpath:hibernate.cfg.xml</value>
</property>
</bean>
采用Lucene搜索进行更新操作，Hibernate会自动帮我们去维护索引，下面是使用Lucene去搜索文件的代码
[c-sharp]
view plaincopypackage com.yhwj.docsh.util;
import java.io.File;
import java.util.ArrayList;
import java.util.List;
import jeasy.analysis.MMAnalyzer;
import org.apache.commons.lang.StringUtils;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.highlight.Formatter;
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.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.oro.text.regex.MalformedPatternException;
import org.apache.oro.text.regex.MatchResult;
import org.apache.oro.text.regex.Pattern;
import org.apache.oro.text.regex.PatternMatcherInput;
import org.apache.oro.text.regex.Perl5Compiler;
import org.apache.oro.text.regex.Perl5Matcher;
import com.yhwj.docsh.data.VFile;
/**
* Lucene解析类
*
* @author sunguoqiang sunguoqiang@yhwj.com 2010-12-13下午04:05:55
*
*/
public class LuceneUtil {
private static final String FIELD_DOCNAME = "docName";
private static final String FIELD_USERNAME = "userName";
private static final String FIELD_KEYWORDS = "keyWords";
private static final String FIELD_DOCVARIETY = "docVariety";
private static final String FIELD_DOCTYPE = "docType";
private static final String PATH = "D://indexDir//file//Doc";
public synchronized Analyzer getAnalyzer() {
return new MMAnalyzer();
}
/**
* 搜索
* @param keywords 关键字
* @param docType 文件类型
* @param begin 开始
* @param number 结束 用于分页
* @return
* @throws MalformedPatternException
*/
@SuppressWarnings("deprecation")
public List<VFile> searchFile(String keywords,String docType,int begin,int number) throws MalformedPatternException {
List<VFile> vFiles = new ArrayList<VFile>();
File fsDir = new File(PATH);
try {
// 索引查询
IndexReader reader = IndexReader.open(FSDirectory.open(fsDir), true); // only searching, so // read-only=true
IndexSearcher isearcher = new IndexSearcher(reader);
TopScoreDocCollector collector = TopScoreDocCollector.create(100,true);
BooleanQuery booleanQuery = new BooleanQuery();
if(StringUtils.isNotBlank(keywords))
{
/* 下面这个表示要同时搜索这三个域，而且只要一个域里面有满足我们搜索的内容就行 */
BooleanClause.Occur[] clauses = { BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD,BooleanClause.Occur.SHOULD,BooleanClause.Occur.SHOULD};
Query query = MultiFieldQueryParser.parse(keywords, new String[] {FIELD_DOCNAME, FIELD_KEYWORDS,FIELD_USERNAME,FIELD_DOCVARIETY},clauses, getAnalyzer());
booleanQuery.add(query, Occur.SHOULD);
}
QueryParser parser_docType = new QueryParser(Version.LUCENE_29,FIELD_DOCTYPE, getAnalyzer());
if(StringUtils.isEmpty(docType))
{
docType = "all";
}
// query.setBoost(1.0f);
if(docType.equals("all"))
{
Query query_docType = parser_docType.parse("doc xls ppt");// 检索词
booleanQuery.add(query_docType, Occur.SHOULD);
}
else {
Query query_docType = parser_docType.parse(docType);// 检索词
booleanQuery.add(query_docType, Occur.MUST);
}
System.out.println(booleanQuery.toString());
isearcher.search(booleanQuery, collector);
ScoreDoc[] hits = collector.topDocs().scoreDocs;
// 用这个进行高亮显示，默认是<b>..</b>
Formatter formatter = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
QueryScorer qs = new QueryScorer(booleanQuery);
// 构造高亮
// 指定高亮的格式
// 指定查询评分
Highlighter highlighter = new Highlighter(formatter,qs);
// 这个一般等于你要返回的，高亮的数据长度
// 如果太小，则只有数据的开始部分被解析并高亮，且返回的数据也少
// 太大，有时太浪费了。
highlighter.setTextFragmenter(new SimpleFragmenter(1000));
for (int i = begin; i < hits.length && i < begin + number; i++) {
VFile vFile = new VFile();
Document d = isearcher.doc(hits[i].doc);
vFile.setId(Long.valueOf(d.get("id")));
vFile.setFileName(d.get("docName"));
vFile.setFileVariety(d.get("docVariety"));
vFile.setKeywords(d.get("keyWords"));
vFile.setUpLoader(d.get("userName"));
vFile.setUpTime(d.get("docUpTime"));
vFiles.add(vFile);
String str = highlighter.getBestFragment(getAnalyzer(), FIELD_DOCNAME, d.get(FIELD_DOCNAME));
System.out.println(str);
vFile.setFileName(str);
}
isearcher.close();
} catch (Exception e) {
e.printStackTrace();
}
return vFiles;
}
public static void main(String[] args) throws MalformedPatternException {
String keywords = "你好 你好 test 您";
String[] keys = new LuceneUtil().getKeys(keywords);
System.out.println(keys.toString());
}
public String[] getKeys(String keywords) throws MalformedPatternException
{
List<String> list = new ArrayList<String>();
Pattern pattern = new Perl5Compiler().compile("//S+");
Perl5Matcher matcher = new Perl5Matcher();
PatternMatcherInput matcherInput = new PatternMatcherInput(keywords);
while (matcher.contains(matcherInput, pattern)) {
MatchResult result = matcher.getMatch();
list.add(result.group(0));
}
return (String[]) list.toArray(new String[list.size()]);
}
}
