Lucene 小试牛刀 代码实现

一, 建立索引,根据索引进行搜索

package com.xbkj.business.demo.lucene;

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.BitSet;
import java.util.Date;
import java.util.HashMap;
import java.util.List;

import net.paoding.analysis.analyzer.PaodingAnalyzer;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.FSDirectory;

public class SearchIndex {
	protected static Log log = LogFactory.getLog(SearchIndex.class);

	public SearchIndex(){}

	public void indexwrite(File indexFile, File dataFile) throws Exception{
//		Analyzer luceneAnalyzer = new StandardAnalyzer();
		Analyzer luceneAnalyzer = new PaodingAnalyzer();
		IndexWriter writer = new IndexWriter(indexFile, luceneAnalyzer, true);
		long startTime = System.currentTimeMillis();
		indexDocs(writer, dataFile);
		writer.optimize();
		writer.close();	//必须,只有这样数据才会被写入索引的目录里
		long endTime = System.currentTimeMillis();
		log.info("共花费:"+(endTime-startTime)+"毫秒,索引文件存放在:"+indexFile.getCanonicalPath());
	}

	public void indexDocs(IndexWriter writer, File dataFile){
		if(dataFile.isDirectory()){
			File[] dataFiles = dataFile.listFiles();
			if(null != dataFiles){
				Arrays.sort(dataFiles);
				for(int i=0; i<dataFiles.length; i++){
					indexDocs(writer, dataFiles[i]);
				}
			}
		}else{
			//检索所有以.jsp结尾的文件     }else if(dataFile.getName().endsWith(".jsp")){
			indexFile(writer, dataFile);
		}
	}

	public void indexFile(IndexWriter writer, File dataFile){
		try{
			log.info("正索引文件:" + dataFile.getCanonicalPath()+"\t:"+dataFile.getAbsolutePath());
			//建立一个新的文档,它可以看作是数据库的一行记录 
			Document doc = new Document();
			Reader txtReader = new FileReader(dataFile);
			doc.add(new Field("name", dataFile.getName(), Field.Store.YES, Field.Index.TOKENIZED));
			doc.add(new Field("path", dataFile.getCanonicalPath(), Field.Store.YES, Field.Index.TOKENIZED));
			doc.add(new Field("lastmodify", ""+dataFile.lastModified(), Field.Store.YES, Field.Index.TOKENIZED));
			doc.add(new Field("contents", txtReader));
			writer.addDocument(doc);
		}catch(IOException ioex){
			log.error("", ioex);
		}
	}

	public List<HashMap> search(String keywords, File indexDir){
		if(!indexDir.exists()){
			log.error("索引目录不存在!");
			return null;
		}
		List<HashMap> list = new ArrayList<HashMap>();
		try{
			FSDirectory indexDirectory = FSDirectory.getDirectory(indexDir);
			IndexSearcher searcher = new IndexSearcher(indexDirectory);
			Term term = new Term("contents", keywords.toLowerCase());
			TermQuery termQuery = new TermQuery(term);
			Hits hits = searcher.search(termQuery, new Filter(){
				@Override
				public BitSet bits(IndexReader reader) throws IOException {
					BitSet bit = new BitSet(reader.maxDoc());
					for(int i=0; i<reader.maxDoc(); i++){
						if(reader.document(i).get("name").endsWith(".jar"))	//将以".tld"后缀的过滤
							continue;
						bit.set(i);
					}
					return bit;
				}
			});
			log.info("共有:"+searcher.maxDoc()+"条索引,命中:"+hits.length()+"条!");
			Document doc = null;
			for(int i=0; i<hits.length(); i++){
				int docId = hits.id(i);
				doc = hits.doc(i);
				log.info(docId+"\tlastmodify:"+new Date(new Long(doc.get("lastmodify"))).toLocaleString()+"\tcontents:"+doc.get("path"));
				HashMap<String, Object> map = new HashMap<String, Object>();
				map.put("id", docId);
				map.put("name", doc.get("name"));
				map.put("lastmodify", new Date(new Long(doc.get("lastmodify"))).toLocaleString());
				map.put("path", doc.get("path"));
				list.add(map);
			}
		}catch(Exception ex){
			log.error("", ex);
			return null;
		}
		return list;
	}

	public List<HashMap> searchFilter(String keywords, File indexDir){
		if(!indexDir.exists()){
			log.error("索引目录不存在!");
			return null;
		}
		List<HashMap> list = new ArrayList<HashMap>();
		try{
			FSDirectory indexDirectory = FSDirectory.getDirectory(indexDir);
			IndexSearcher searcher = new IndexSearcher(indexDirectory);
//			QueryParser queryParser = new QueryParser("contents", new StandardAnalyzer());
			QueryParser queryParser = new QueryParser("contents", new PaodingAnalyzer());
			queryParser.setDefaultOperator(QueryParser.AND_OPERATOR);
			Query query = queryParser.parse(keywords.toLowerCase());
			Hits hits = searcher.search(query, new Filter(){
				@Override
				public BitSet bits(IndexReader reader) throws IOException {
					BitSet bit = new BitSet(reader.maxDoc());
					for(int i=0; i<reader.maxDoc(); i++){
						if(reader.document(i).get("name").endsWith(".jar"))	//将以".tld"后缀的过滤
							continue;
						bit.set(i);
					}
					return bit;
				}
			});
			log.info("共有:"+searcher.maxDoc()+"条索引,命中:"+hits.length()+"条!");
			Document doc = null;
			for(int i=0; i<hits.length(); i++){
				int docId = hits.id(i);
				doc = hits.doc(i);
				log.info(docId+"\tlastmodify:"+new Date(new Long(doc.get("lastmodify"))).toLocaleString()+"\tcontents:"+doc.get("path"));
				HashMap<String, Object> map = new HashMap<String, Object>();
				map.put("id", docId);
				map.put("name", doc.get("name"));
				map.put("lastmodify", new Date(new Long(doc.get("lastmodify"))).toLocaleString());
				map.put("path", doc.get("path"));
				list.add(map);
			}
		}catch(Exception ex){
			log.error("", ex);
			return null;
		}
		return list;
	}
}

二, 调用

SearchIndex si = new SearchIndex();
si.indexwrite(new File("F:\\index"), new File(datadir));
//datadir 数据目录 eg. C:\\data


List list = si.searchFilter(keywords, new File("F:\\index"));
//keywords 搜索关键词 eg.lucene