lucene2.4 start

首先说明，我是这方面新的感兴趣者，现在可以称之为：菜鸟

下面是一个针对2.4版本的简单例子（官网找不到2.3版本的bin下载，郁闷中...）。代码算是看着demo一行行研读过的。

 

1.建立索引

package tutorial;

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

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;

/**
 * 索引创建者
 */
public class Indexer {
	public static void main(String[] args) throws IOException {
		//盛放索引的目录
		File indexDir = new File("I:/index");
		//盛放数据文件的目录
		File dataDir = new File("I:/data");

		int numAdded = index(indexDir, dataDir);
		System.out.println("共有：" + numAdded + " 个文件加入到索引当中");
	}

	/**
	 * 创建索引
	 * @param indexDir 盛放索引的目录
	 * @param dataDir 盛放数据文件的目录
	 * @return int 加入文件的个数
	 * @throws IOException
	 */
	public static int index(File indexDir, File dataDir) throws IOException {
		if (!indexDir.exists() || !dataDir.isDirectory()) {
			throw new IOException();
		}

		//第三个参数为true的意思是，如果没有该索引就创建，否则覆盖原有索引
		IndexWriter writer = new IndexWriter(indexDir, new StandardAnalyzer(),
				true, IndexWriter.MaxFieldLength.LIMITED);
		//该属性设为true的意思是，所以文件建立的索引都融合到统一的文件中，可以把这个设为false
		//看看结果会生成多少索引文件
		writer.setUseCompoundFile(true);

		//建立索引
		indexDirectory(writer, dataDir);

		int numAdded = writer.maxDoc();
		writer.optimize();
		writer.close();
		return numAdded;
	}

	/**
	 * 给目录建立索引
	 * @param writer
	 * @param dir
	 * @throws IOException
	 */
	private static void indexDirectory(IndexWriter writer, File dir)
			throws IOException {

		File[] files = dir.listFiles();

		//应用递归方式
		for (int i = 0; i < files.length; i++) {
			File f = files[i];
			if (f.isDirectory()) {
				indexDirectory(writer, f);
			} else if (f.getName().toLowerCase().endsWith(".txt")) {
				indexFile(writer, f);
			}
		}
	}

	/**
	 * 给文件建立索引
	 * @param writer
	 * @param f
	 * @throws IOException
	 */
	public static void indexFile(IndexWriter writer, File f) throws IOException {

		if (f.isHidden() || !f.exists() || !f.canRead()) {
			return;
		}

		System.out.println("加入： " + f.getCanonicalPath());

		//针对参数文件建立索引文档
		Document doc = new Document();
		//Field.Index.NOT_ANALYZED 文件名称 建立索引，但不分词
		doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES,
				Field.Index.NOT_ANALYZED));
		doc.add(new Field("contents", new FileReader(f)));
		//在writer中加入此文档
		writer.addDocument(doc);
	}
}

 

2.进行查询

package tutorial;

import java.io.File;
import java.io.IOException;

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;

/**
 * 查询者
 */
public class Searcher {

	public static void main(String[] args) throws Exception {
		File indexDir = new File("I:/index");
		String q = "中文";
		if (!indexDir.exists() || !indexDir.isDirectory()) {
			throw new IOException();
		}
		search(indexDir, q);
	}

	/**
	 * 查询
	 * @param indexDir 索引目录
	 * @param q 查询字符串
	 * @throws Exception
	 */
	public static void search(File indexDir, String q) throws Exception {
		Directory fsDir = FSDirectory.getDirectory(indexDir);
		IndexSearcher searcher = new IndexSearcher(fsDir);
		//建立查询分析器
		QueryParser parser = new QueryParser("contents", new StandardAnalyzer());
		Query query = parser.parse(q);

		//100是显示队列的Size
		TopDocs topDocs = searcher.search(query, 100);
		ScoreDoc[] hits = topDocs.scoreDocs;
		System.out.println("共有" + searcher.maxDoc() + "条索引，命中" + hits.length
				+ "条");
		for (int i = 0; i < hits.length; i++) {
			int docId = hits[i].doc;
			Document document = searcher.doc(docId);
			System.out.println(docId + ":" + document.get("filename"));
		}
	}
}