Lucene 初体验

     今天看了下Lucene的更新，已经到4.4.0的版本了，而且新的API变化也比较多，对于老版本的Lucene想要升级到最新的版本，不是简单的更新jar包就可以的。

    下面写了个简单的小例子。可以看一下

 

1.创建maven工程

    在eclipse里面创建个maven项目，一个简单的项目即可，下面是对于的pom.xml文件，需要将Lucene的jar包引入进来。

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
  <modelVersion>4.0.0</modelVersion>
  <groupId>com.jacksoft</groupId>
  <artifactId>Lucene-test</artifactId>
  <version>0.0.1-SNAPSHOT</version>
  
  <properties>
  	<lucene.version>4.4.0</lucene.version>
  </properties>
  
  <dependencies>
  	<dependency>
  		<groupId>org.apache.lucene</groupId>
  		<artifactId>lucene-core</artifactId>
  		<version>${lucene.version}</version>
  	</dependency>
	
	<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-analyzers-common</artifactId>
		<version>${lucene.version}</version>
	</dependency>
	
	<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-queryparser</artifactId>
		<version>${lucene.version}</version>
	</dependency>
            
            
            
  </dependencies>
  
</project>

   这里只是简单的添加依赖关系，下载好jar包之后，我在本地创建了3个txt文件，如下：

  

  

 准备工作就差不多了，下面就开始进行编码工作

 

2. 编码

    由于是多个文件的搜索，这里创建一个工具类来递归目录，找到这三个txt文件，我将这三个txt文件放在本地:D:\lucene\luceneData目录中

   

package com.jacksoft.lucene.util;

import java.io.File;
import java.util.List;

public class FileUtils {

	public static void listFile(File f,List<String> fileList){
		if(f.isDirectory()){
			File[] files = f.listFiles();
			for(int i=0;i<files.length ;i++)
			{
				listFile(files[i],fileList) ;
			}
		}else{
			fileList.add(f.getAbsolutePath());
		}
	}
}

    这样返回的fileList中就包含了我们需要的txt文件，当然这里还可以设置过滤器来指定后缀名。

  接下来就是创建索引和查询的过程：

package com.jacksoft.lucene;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
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.document.TextField;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
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;

import com.jacksoft.lucene.util.FileUtils;

/**
 *  多文件搜索
 * @Project Lucene-test
 *
 * @Filename MultLuceneTest2.java
 *
 * @author Jack.Zhou
 *
 * @Date 2013-8-29
 *
 */
public class LuceneTest {

	private static final String QUERY_STR = "四川";
	
	private static final String FILE_TARGET = "D:\\lucene\\luceneData";
	
	private static final String FILE_INDEX = "D:\\lucene\\luceneIndex";
	
	
	public static void main(String[] args) {
		try {
			LuceneTest t = new LuceneTest();
			t.createIndex();
			t.searchByKeyWords(QUERY_STR);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
	
	/**
	 *  创建索引
	 * @throws Exception
	 */
	private void createIndex() throws Exception{
		Long startTime = System.currentTimeMillis();
		File indexDir = new File(FILE_INDEX);
		Analyzer luceneAnalyzer = new StandardAnalyzer(Version.LUCENE_44);
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_44, luceneAnalyzer);
		config.setOpenMode(OpenMode.CREATE);
		Directory directory = FSDirectory.open(indexDir);
		IndexWriter indexWriter = new IndexWriter(directory, config);
		List<String> fileList = new ArrayList<String>();
		FileUtils.listFile(new File(FILE_TARGET), fileList);
		for(String filePath : fileList){
			System.out.println("文件:" + filePath + "正在被索引....");
			String content = readFile(filePath);
			Document doc = new Document();
			doc.add(new TextField("content", content.toString(), Store.YES));
			doc.add(new TextField("path", filePath, Store.YES));
			indexWriter.addDocument(doc);
		}
		indexWriter.close();
		Long endTime = System.currentTimeMillis();
		System.out.println("花费了" + (endTime - startTime) + "毫秒来创建索引文件");
		
	}
	/**
	 *  读取文件内容
	 * @param filePath
	 * @return
	 * @throws Exception
	 */
	private String readFile(String filePath) throws Exception{
		@SuppressWarnings("resource")
		BufferedReader bufferedReader = new BufferedReader(
				new InputStreamReader(new FileInputStream(filePath)));
		StringBuffer content = new StringBuffer();
		String str = null;
		while ((str = bufferedReader.readLine()) != null) {
			content.append(str).append("\n");
		}
		return content.toString();
	}
	
	
	private void searchByKeyWords(String keyWords) throws Exception{
		IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(FILE_INDEX)));
		IndexSearcher searcher = new IndexSearcher(reader);
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);
		QueryParser parser = new QueryParser(Version.LUCENE_44, "content",analyzer);
		Query query = parser.parse(keyWords);
		TopDocs results = searcher.search(query,1000);
		ScoreDoc[] score = results.scoreDocs;
		if (score.length == 0) {
			System.out.println("对不起，没有找到您要的结果。");
		} else {
			System.out.println("查找["+QUERY_STR+"]有" + score.length + "个结果");
			for (int i = 0; i < score.length; i++) {
				try {
					Document doc = searcher.doc(score[i].doc);
					System.out.print("这是第" + i + "个检索到的结果，文件名为：");
					System.out.println(doc.get("path"));
					System.out.println("内容:\n" + doc.get("content"));
				} catch (Exception e) {
					e.printStackTrace();
				}
			}
		}
	}
}

 

   代码中的常量可以通过文档来查看，运行后就可以看到搜索的结果了。

 

   当然这里只是对txt进行搜索，你还可以对word，excel，pdf等文档进行搜索，前提是要将其内容读取出来，创建索引即可。