lunece入门之HelloWorld

 屌丝又发少年狂

左键盘，右鼠标

闲来无事学搜索。

 

好久没有学习新的技术了，一直在项目中晃悠。

Lucene，上学那会儿就想学习学习了，遥记得当年毕业答辩的时候我用的搜索功能是直接查询数据库，被答辩的老师狠狠的鄙视了。

下面是一个入门级别的demo，写到这里或许可以帮助都别人，主要的是为了自己以后备忘。

step1：下载lucene

step2：新建项目helloworld，并引进必要的包，[You need four JARs: the Lucene JAR, the queryparser JAR, the common analysis JAR, and the Lucene demo JAR. You should see the Lucene JAR file in the core/ directory you created when you extracted the archive -- it should be named something like lucene-core-{version}.jar. You should also see files called lucene-queryparser-{version}.jar, lucene-analyzers-common-{version}.jar and lucene-demo-{version}.jar under queryparser, analysis/common/ and demo/, respectively.] 我们这个demo中用到的是以下几个包：

lucene-analyzers-common-4.4.0.jar ,

lucene-core-4.4.0.jar ,

lucene-queryparser-4.4.0.jar.

step3：准备测试用的文档，我的是

public static final String PATH_INDEX = "E:\\temp\\index";
public static final String PATH_FILE = "E:\\temp\\document";

 PATH_INDEX存放的是索引文件，PATH_FILE存放的是测试文档。

step4：前3步是准备工作，现在开始写代码。代码就不一一描述了，在关键地方我都添加了注释

code1：新建/更新索引

package org.i94livng.lucene;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;

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.Store;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * 建索引
 * @author HuHongyu
 *
 */
public class LuceneIndex {
	
	public static final String PATH_INDEX = "E:\\temp\\index";
	
	public static final String PATH_FILE = "E:\\temp\\document";
	
	/**
	 * 创建索引
	 * @throws IOException
	 */
	public void createIndex()throws IOException{
		
		File fileSource = new File(PATH_FILE);
		File[] files = fileSource.listFiles();
		IndexWriter indexWriter =  getIndexWriter();
		for (File file : files) {
			Document document = new Document();
			document.add(new StringField("path", file.getPath(), Store.YES));
			document.add(new TextField("content", getDocumentContent(file), Store.YES));
			document.add(new StringField("fileName",file.getName(),Store.YES));
			//System.out.println(document.get("path"));
			//indexWriter.addDocument(document);
			//避免重复建索引，暂时用文件名进行区分
			indexWriter.updateDocument(new Term("fileName", file.getName()), document);
		}
		indexWriter.close();
		
	}
	
	/**
	 * 获取文件中的数据
	 * @param file
	 * @return
	 * @throws Exception
	 */
	public static String getDocumentContent(File file){
		
		String content = new String();
		StringBuffer sb = new StringBuffer();;
		try {
			FileInputStream fis =  new FileInputStream(file);
			BufferedReader bfr = new BufferedReader(new InputStreamReader(fis));
			String s;
			while((s=bfr.readLine())!=null){
				sb.append(s+"\n");
			}
			fis.close();
			bfr.close();
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		content = sb.toString();
		return content;
	}
	
	/**
	 * 获取IndexWriter
	 * @return
	 * @throws Exception
	 */
	public static IndexWriter getIndexWriter() {
		
		IndexWriter indexWriter = null;
		try {
			Directory directory = FSDirectory.open(new File(PATH_INDEX));
			Analyzer luceneAnalyzer = new StandardAnalyzer(Version.LUCENE_44);
			IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_44, luceneAnalyzer);
			indexWriter = new IndexWriter(directory, indexWriterConfig);
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		return indexWriter;
	}
}

 PS：由于我想读取到文件中的内容，目前我是文件流吧文档中的内容取出来，再放到document中。

code2：搜索文档

 

package org.i94livng.lucene;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
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;

public class LuceneSearch {
	
	public static List<ResultModel> search(Map<String,String> searchMap)throws IOException,ParseException{
		Directory directory = FSDirectory.open(new File(LuceneIndex.PATH_INDEX));
		String serachContent = searchMap.get("content");
		
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);
		
		//组装查询条件
		QueryParser parser = new QueryParser(Version.LUCENE_44, "content",analyzer);
		// 将关键字包装成Query对象
		Query query = parser.parse(serachContent);
		//获取准确度就高的5条记录
		TopDocs topDocs =  searcher.search(query, 5);
		
		//获取纪律列表
		ScoreDoc[]scoreDocs = topDocs.scoreDocs;
		//把查询出来的结果转成document 并组装到 ResultModel中
		List<ResultModel> resultList = new ArrayList<ResultModel>();
		
		for (ScoreDoc scoreDoc : scoreDocs) {
			ResultModel resultModel = new ResultModel();
			int docId = scoreDoc.doc;
			Document document = searcher.doc(docId);
			resultModel.setFilePath(document.get("path"));
			resultModel.setFileContent(document.get("content"));
			resultModel.setFileName(document.get("fileName"));
			resultList.add(resultModel);
		}
		
		return resultList;
	}
	
	public static void main(String[] args)throws IOException , ParseException{
		LuceneIndex index = new LuceneIndex();
		index.createIndex();
		Map<String,String> searchMap = new HashMap<String,String>();
		//搜索文档中出现“中”的文档
		searchMap.put("content", "中");
		List<ResultModel> result = search(searchMap);
		for (ResultModel resultModel : result) {
			System.out.println(resultModel.toString());
		}
	}
}
  

  

 code3：搜索出来的结果实体。

package org.i94livng.lucene;

public class ResultModel {
	
	private String fileName;
	private String fileContent;
	private String filePath;

	public String getFileName() {
		return fileName;
	}

	public void setFileName(String fileName) {
		this.fileName = fileName;
	}

	public String getFileContent() {
		return fileContent;
	}

	public void setFileContent(String fileContent) {
		this.fileContent = fileContent;
	}

	public String getFilePath() {
		return filePath;
	}

	public void setFilePath(String filePath) {
		this.filePath = filePath;
	}
	
	@Override
	public String toString() {
		return "ResultModel [fileName=" + fileName + ", fileContent="
				+ fileContent + ", filePath=" + filePath + "]";
	}
}

 

 OK，代码就这样了，我执行main方法得到的结果如下

ResultModel [fileName=test3.txt, fileContent=中华人民共和国, filePath=E:\temp\document\test3.txt]
ResultModel [fileName=test5.txt, fileContent=中华人民共和国, filePath=E:\temp\document\test5.txt]

 

 PS：项目代码见附件。