初始lucene

刚开始接触Lucene，看到好多推荐Lucene in action
虽然代码用的是lucene 1，但原理讲的很清楚，稍作修改即可。

下面给出lucene最简单的一个应用实例，从书上修改而来
Lucene in action 中用的为Lucene 1，我用lucene 2来实现了Lucene in action 第一章 初始Lucene

 

索引过程:

核心类：
IndexWriter, Directory, Analyzer, Document, Field

Indexer如下

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;

/**
 * @author xusulong
 *
 */
public class Indexer {
	public static void main(String[] args) throws Exception {
		File indexDir = new File("D:\\index");
		File dataDir = new File("D:\\lucene-2.4.1");
		
		long start = new Date().getTime();
		int numIndexed = index(indexDir, dataDir);
		long end = new Date().getTime();
		
		System.out.println("Indexing " + numIndexed + " files took "
				+ (end - start) + " milliseconds");
	}
	
	public static int index(File indexDir, File dataDir) throws IOException{
		if(!dataDir.exists() || !dataDir.isDirectory()) {
			throw new IOException(dataDir + " does not exixt or is not a diretory");
		}
		//创建lucene索引
		IndexWriter writer = new IndexWriter(indexDir, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
		writer.setUseCompoundFile(false);
		
		indexDirectory(writer, dataDir);
		
		int numIndexed = writer.maxDoc();
		writer.optimize();
		writer.close();		//关闭索引
		return numIndexed;
	}
	
	private static void indexDirectory(IndexWriter writer, File dir) throws IOException{
		File[] files = dir.listFiles();
		
		for( int i = 0; i < files.length; i ++) {
			File f = files[i];
			if(f.isDirectory()) {
				indexDirectory(writer, f);//遍历
			} else if(f.getName().toLowerCase().endsWith(".txt")) {
				indexFile(writer, f);
			}
		}
	}
	
	private static void indexFile(IndexWriter writer, File f) throws IOException{
		if(f.isHidden() || !f.exists() || !f.canRead()) {
			return;
		}
		
		System.out.println("Indexing " + f.getCanonicalPath());
		Document doc = new Document();
		//索引文件中的内容
		doc.add(new Field("contents", new FileReader(f)));
		//索引文件名
		doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
		//将Document对象添加到lucene的索引中去
		writer.addDocument(doc);
	}
}

 

搜索过程：

核心类：
IndexSearcher, Term, Query, QueryParser, TopDocs, ScoreDoc

Searcher如下

import java.io.File;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.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;

/**
 * @author xusulong
 * 
 */
public class Searcher {
	public static void main(String[] args) throws Exception {
		File indexDir = new File("D:\\index");
		String q = "lucene";

		if (!indexDir.exists() || !indexDir.isDirectory()) {
			throw new Exception(indexDir
					+ " does not exixt or is not a diretory");
		}

		search(indexDir, q);
	}

	public static void search(File indexDir, String q) throws Exception {
		// 打开索引
		Directory fsDir = FSDirectory.getDirectory(indexDir);
		// 对查询的字符串进行解析
		IndexSearcher is = new IndexSearcher(fsDir);
		QueryParser parser = new QueryParser("contents", new StandardAnalyzer());
		Query query = parser.parse(q);
		long start = new Date().getTime();
		// 搜索索引
		TopDocs topDocs = is.search(query, 100);
		ScoreDoc[] hits = topDocs.scoreDocs;

		long end = new Date().getTime();
		System.out.println("Found " + hits.length + " document(s) (in "
				+ (end - start) + " milliseconds) that mactched query '" + q
				+ "':");
		for (int i = 0; i < hits.length; i++) {
			int docId = hits[i].doc;
			// 检索匹配到的文件，显示文件名
			Document doc = is.doc(docId);
			System.out.println(docId + ": " + doc.get("filename"));
		}
	}
}

 

结果

两个程序都在我的机器上运行成功(windows xp)，结果如下：

Indexer:
Indexing D:\lucene-2.4.1\BUILD.txt
Indexing D:\lucene-2.4.1\CHANGES.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\java\org\apache\lucene\analysis\nl\stems.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\java\org\apache\lucene\analysis\nl\words.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\test\org\apache\lucene\analysis\de\data.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\test\org\apache\lucene\analysis\ru\stemsUnicode.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\test\org\apache\lucene\analysis\ru\test1251.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\test\org\apache\lucene\analysis\ru\testKOI8.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\test\org\apache\lucene\analysis\ru\testUnicode.txt
Indexing D:\lucene-2.4.1\contrib\analyzers\src\test\org\apache\lucene\analysis\ru\wordsUnicode.txt
Indexing D:\lucene-2.4.1\contrib\ant\src\test\org\apache\lucene\ant\test.txt
Indexing D:\lucene-2.4.1\contrib\benchmark\CHANGES.txt
Indexing D:\lucene-2.4.1\contrib\benchmark\src\test\org\apache\lucene\benchmark\quality\trecQRels.txt
Indexing D:\lucene-2.4.1\contrib\benchmark\src\test\org\apache\lucene\benchmark\quality\trecTopics.txt
Indexing D:\lucene-2.4.1\contrib\CHANGES.txt
Indexing D:\lucene-2.4.1\contrib\memory\src\test\org\apache\lucene\index\memory\testqueries.txt
Indexing D:\lucene-2.4.1\contrib\memory\src\test\org\apache\lucene\index\memory\testqueries2.txt
Indexing D:\lucene-2.4.1\contrib\miscellaneous\README.txt
Indexing D:\lucene-2.4.1\contrib\queries\README.txt
Indexing D:\lucene-2.4.1\contrib\similarity\README.txt
Indexing D:\lucene-2.4.1\contrib\snowball\LICENSE.txt
Indexing D:\lucene-2.4.1\contrib\snowball\README.txt
Indexing D:\lucene-2.4.1\contrib\snowball\SNOWBALL-LICENSE.txt
Indexing D:\lucene-2.4.1\contrib\surround\README.txt
Indexing D:\lucene-2.4.1\contrib\wordnet\README.txt
Indexing D:\lucene-2.4.1\contrib\xml-query-parser\src\test\org\apache\lucene\xmlparser\reuters21578.txt
Indexing D:\lucene-2.4.1\docs\skin\images\README.txt
Indexing D:\lucene-2.4.1\docs\skin\note.txt
Indexing D:\lucene-2.4.1\LICENSE.txt
Indexing D:\lucene-2.4.1\NOTICE.txt
Indexing D:\lucene-2.4.1\README.txt
Indexing D:\lucene-2.4.1\src\jsp\README.txt
Indexing 32 files took 657 milliseconds

Searcher:

Found 14 document(s) (in 15 milliseconds) that mactched query 'lucene':
30: D:\lucene-2.4.1\README.txt
24: D:\lucene-2.4.1\contrib\wordnet\README.txt
17: D:\lucene-2.4.1\contrib\miscellaneous\README.txt
19: D:\lucene-2.4.1\contrib\similarity\README.txt
21: D:\lucene-2.4.1\contrib\snowball\README.txt
31: D:\lucene-2.4.1\src\jsp\README.txt
0: D:\lucene-2.4.1\BUILD.txt
29: D:\lucene-2.4.1\NOTICE.txt
23: D:\lucene-2.4.1\contrib\surround\README.txt
11: D:\lucene-2.4.1\contrib\benchmark\CHANGES.txt
14: D:\lucene-2.4.1\contrib\CHANGES.txt
18: D:\lucene-2.4.1\contrib\queries\README.txt
1: D:\lucene-2.4.1\CHANGES.txt
28: D:\lucene-2.4.1\LICENSE.txt