1、检索实体类
2、索引的建立
3、搜索
说明:
1、使用的luncene的版本为lucene-2.9.2
2、需注意的是搜索英文时,单词是以空格分开的。如youger dream,若搜索"ea"是搜索不到的,只有搜索"youger"或"dream"才能搜索得到。
package com.dxcollector.entity;
public class DxNovel implements java.io.Serializable {
private Long id;
private String pid;
private String NTitle;
private String NAuthor;
private String NDesc;
private String NType;
private String NTotalWords;
private String NImgUrl;
private String NSourceUrl;
//省略getter and setter
}
2、索引的建立
package com.dxcollector.search;
import java.io.File;
import java.io.IOException;
import java.util.List;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;
import com.dxcollector.entity.DxNovel;
import com.dxcollector.novels.readnovel.NovelMgr;
/**
* 索引管理
*
* @author 忧里修斯
*/
public class IndexMgr {
NovelMgr novelMgr = new NovelMgr();
/**
* 创建新的索引
*
* @param index_store_path 索引存放路径
*/
public void createIndex(String index_store_path){
IndexWriter indexWriter = null;
try {
Directory directory = FSDirectory.open(new File(index_store_path));
indexWriter = new IndexWriter(directory,new StandardAnalyzer(Version.LUCENE_29),IndexWriter.MaxFieldLength.UNLIMITED);
List<DxNovel> novelList = novelMgr.getAllNovel();
System.out.println("大小:"+novelList.size());
Document doc = null;
for (DxNovel dxNovel : novelList) {
doc = new Document();
Field titleField = new Field("NTitle",dxNovel.getNTitle(),Field.Store.YES,Field.Index.ANALYZED);
Field authorField = new Field("NAuthor",dxNovel.getNAuthor(),Field.Store.YES,Field.Index.NOT_ANALYZED);
Field descField = new Field("NDesc",dxNovel.getNDesc(),Field.Store.YES,Field.Index.ANALYZED);
Field typeField = new Field("NType",dxNovel.getNType(),Field.Store.YES,Field.Index.ANALYZED);
doc.add(titleField);
doc.add(authorField);
doc.add(descField);
doc.add(typeField);
indexWriter.addDocument(doc);
}
indexWriter.optimize();
indexWriter.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("索引建立完成");
}
public static void main(String[] args) {
IndexMgr im = new IndexMgr();
im.createIndex("C:/index/");
}
}
3、搜索
package com.dxcollector.search;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import com.dxcollector.entity.DxNovel;
/**
* 搜索管理器
*
* @author 忧里修斯
*
*/
public class SearchMgr {
//索引文件存放的位置
private String index_store_path = "C:/index/";
public SearchMgr(String index_store_path){
this.index_store_path = index_store_path;
}
/**
* 搜索小说
*
* @param searchType 搜索类型,对应小说标题NTitle等
* @param keyword 关键字
* @return List<DxNovel>
*/
public List<DxNovel> search(String searchType,String keyword){
List<DxNovel> novelList = null;
try {
novelList = new ArrayList<DxNovel>();
Directory directory = FSDirectory.open(new File(index_store_path));
IndexSearcher indexSearcher = new IndexSearcher(directory,true);
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_29);
//建立搜索单元
Query query = null;
QueryParser queryParser = new QueryParser(Version.LUCENE_29,searchType,analyzer);
query = queryParser.parse(keyword);
//多域搜索
if(searchType.equals("")){
queryParser.setDefaultOperator(QueryParser.OR_OPERATOR);
String[] fields = {"NTitle", "NAuthor", "NDesc","NType"};
BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
BooleanClause.Occur.SHOULD,
BooleanClause.Occur.SHOULD,
BooleanClause.Occur.SHOULD};
try {
query = MultiFieldQueryParser.parse(Version.LUCENE_29,keyword, fields, flags, analyzer);
} catch (ParseException e) {
e.printStackTrace();
}
}
//检索
TopDocs topDocs = indexSearcher.search(query,100);
ScoreDoc[] hits = topDocs.scoreDocs;
System.out.println("结果集大小:"+hits.length);
for (int i = 0; i < hits.length; i++) {
int docId = hits[i].doc;
Document doc = indexSearcher.doc(docId);
DxNovel novel = new DxNovel();
novel.setNTitle(doc.get("NTitle"));
novel.setNAuthor(doc.get("NAuthor"));
novel.setNDesc(doc.get("NDesc"));
novel.setNType(doc.get("NType"));
novelList.add(novel);
}
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (ParseException e) {
e.printStackTrace();
}
return novelList;
}
public static void main(String[] args) {
SearchMgr searcher = new SearchMgr("C:/index/");
List<DxNovel> novelList = new ArrayList<DxNovel>();
novelList = searcher.search("NTitle", "my");
for (DxNovel dxNovel : novelList) {
System.out.println("标题:"+dxNovel.getNTitle());
System.out.println("作者:"+dxNovel.getNAuthor());
System.out.println("类型:"+dxNovel.getNType());
System.out.println("简介:"+dxNovel.getNDesc());
}
}
}
说明:
1、使用的luncene的版本为lucene-2.9.2
2、需注意的是搜索英文时,单词是以空格分开的。如youger dream,若搜索"ea"是搜索不到的,只有搜索"youger"或"dream"才能搜索得到。