Lucene查找txt文件中包含指定内容的文件

[luozhangwen]

package com.lzw.lucene;


import java.io.*;
import java.util.*;

import org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.*;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.*;

/**
 * 2010-5-12lucene学习第一天
 * 搜索指定字符所在的文件
 * lucene-core-2.4.1.jar
 */
public class LuceneTest {
	public static void main(String[] args) {
		LuceneUtil test = new LuceneUtil();
//		test.createIndex("D:\\lzwLucene\\src", "D:\\lzwLucene\\index");
		test.search("添加路由的命令  PMSV300R002C05B055",  "D:\\lzwLucene\\index");
		//加上AND是两空格之间都必须有. 不加就是OR
	}
	
	public static void getFileList(File srcFile, List<File> list) {
		if (srcFile.isDirectory()) {
			File[] files = srcFile.listFiles();
			for (int i = 0; i < files.length; i++) {
				getFileList(files[i], list);
			}
		} else {
			if (srcFile.getName().toLowerCase().endsWith(".txt")) {
				list.add(srcFile);
			}
		}
	}

	public static String fileReaderAll(File file, String charset) throws IOException {
		BufferedReader reader = new BufferedReader(new InputStreamReader(
				new FileInputStream(file), charset));
		String temp = null;
		StringBuffer sb = new StringBuffer();

		while ((temp = reader.readLine()) != null) {
			sb.append(temp + "\n");
		}
		reader.close();
		return sb.toString();
	}

}

[luozhangwen]

class LuceneUtil{
	public Map<String, String> search(String key,String indexFilePath){
		try {
			IndexSearcher searcher = new IndexSearcher(indexFilePath);
			QueryParser queryParser = new QueryParser("content",new StandardAnalyzer());
			Query query = queryParser.parse(key);
			if(searcher != null){
				long startTime = new Date().getTime();
				Hits hits = searcher.search(query);
				
				if (hits == null || hits.length() == 0) {
					System.out.println("对不起。没你想要的结果!");
				}else {
					for (int i = 0; i < hits.length(); i++) {
						long endTime = new Date().getTime();
						System.out.println("路径:" + hits.doc(i).get("path"));
						System.out.println("内容:" + hits.doc(i).get("content"));
						
						System.out.println("检索完成，用时" + (endTime - startTime) + "毫秒");
					}
				} 
			}
		} catch (Exception e) {
			e.printStackTrace();
		} 
		return null;
	}
    /**
     * @param indexFilePath  创建索引的文件路径
     * @param srcFilePath    被索引的文件路径
     */
	public void createIndex(String indexFilePath, String srcFilePath) {
		File indexFileDir = new File(indexFilePath);
		File srcFileDir = new File(srcFilePath);
		IndexWriter indexWriter = null;
		List<File> files = new ArrayList<File>();
		Analyzer luceneAnalyzer = new StandardAnalyzer();
		try {
			indexWriter = new IndexWriter(indexFileDir, luceneAnalyzer, true);
			LuceneTest.getFileList(srcFileDir, files);
			System.out.println("一共被索引的文件有:" + files.size());
			long startTime = new Date().getTime();

			for (File file : files) {
				System.out.println("文件:" + file.getAbsolutePath() + "开始被索引...");
				String tempStr = LuceneTest.fileReaderAll(file, "GBK");
				System.out.println("文件内容Lenth:" + tempStr.length());
				Document doc = new Document();
				Field fieldPath = new Field("filePath", file.getPath(),
					    Field.Store.YES, Field.Index.NO);  
				Field fieldContent = new Field("content", tempStr,
						Field.Store.YES, Field.Index.TOKENIZED,
						Field.TermVector.WITH_POSITIONS_OFFSETS);
				doc.add(fieldPath);
				doc.add(fieldContent);
				indexWriter.addDocument(doc);
			}

			indexWriter.optimize();// optimize()方法是对索引进行优化

			// 测试一下索引的时间
			long endTime = new Date().getTime();
			System.out.println("花费了" + (endTime - startTime) + " 毫秒来把文档增加到索引里面去!" + indexFileDir.getPath());
		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			try {
				indexWriter.close();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}

}