初识lucene

lucene的介绍网上有好多，再写一遍可能有点多余了。

使用lucene之前，有一系列的疑问

• 为什么lucene就比数据库快？
• 倒排索引是什么，他是怎么做到的
• lucene的数据结构是什么样的，cpu消耗，内存消耗主要因为什么
• lucene的索引流程以及查询流程是什么样的

推荐两篇文章，更进一步了解lucene

可以参考lucene与数据库对比部分

http://www.chedong.com/tech/lucene.html

可以参考第一篇和第二篇部分对lucene有一部分了解

http://blog.csdn.net/forfuture1978/article/details/5668956

《Lucene 原理与代码分析》看过一点，但是有点难度。

现在从《lucene实战》这本书来看，lucene使用的是4.7可能与3.0有所区别。

下面是第一节的例子

package com.mitchz.lucence;

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

import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * @author mitchz
 * @version 1.0
 * @since 2014年4月30日
 * @category com.mitchz.lucence
 */
public class Indexer
{

	private IndexWriter writer;

	public Indexer(String indexDir) throws IOException
	{
		Directory dir = FSDirectory.open(new File(indexDir));
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_47,
				new SimpleAnalyzer(Version.LUCENE_47));
		writer = new IndexWriter(dir, config);
	}

	public int index(String dataDir, FileFilter filter) throws Exception
	{
		File[] files = (new File(dataDir)).listFiles();
		for (File file : files)
		{
			if (!file.isDirectory() && !file.isHidden() && file.canRead()
					&& (filter == null || filter.accept(file)))
			{
				indexFile(file);
			}
		}
		return writer.numDocs();
	}

	private static class TextFilesFilter implements FileFilter
	{

		@Override
		public boolean accept(File path)
		{
			return path.getName().toLowerCase().endsWith(".txt");
		}
	}

	protected Document getDocument(File file) throws Exception
	{
		Document doc = new Document();
		doc.add(new TextField("contents", new FileReader(file)));
		doc.add(new StringField("filename", file.getName(), Field.Store.YES));
		doc.add(new StringField("fullpath", file.getCanonicalPath(), Field.Store.YES));
		return doc;
	}

	protected void indexFile(File file) throws Exception
	{
		System.out.println("Indexing " + file.getCanonicalPath());
		Document doc = getDocument(file);
		writer.addDocument(doc);
	}

	protected void close() throws IOException
	{
		writer.close();
	}

	public static void main(String[] args) throws Exception
	{
		if (args.length != 2)
		{
			throw new IllegalArgumentException("Usage java " + Indexer.class.getName()
					+ "<index dir> <data dir>");
		}
		String indexDir = args[0];
		String dataDir = args[1];
		System.out.println("indexDir:" + indexDir);
		System.out.println("dataDir:" + dataDir);
		long start = System.currentTimeMillis();
		Indexer indexer = new Indexer(indexDir);
		int numIndexed;
		try
		{
			numIndexed = indexer.index(dataDir, new TextFilesFilter());
		}
		finally
		{
			indexer.close();
		}
		long end = System.currentTimeMillis();
		System.out.println("Indexing " + numIndexed + " files took " + (end - start)
				+ " milliseconds");
	}
}

package com.mitchz.lucence;

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

import org.apache.lucene.analysis.core.SimpleAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
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;

/**
 * @author mitchz
 * @version 1.0
 * @since 2014年4月30日
 * @category com.mitchz.lucence
 */
public class Searcher
{

	public static void main(String args[]) throws IOException, ParseException
	{
		if (args.length != 2)
		{
			throw new IllegalArgumentException("Usage java " + Searcher.class.getName()
					+ "<index dir> <query>");
		}
		String indexDir = args[0];
		String q = args[1];
		search(indexDir, q);
	}

	public static void search(String indexDir, String q) throws IOException,
			ParseException
	{
		Directory dir = FSDirectory.open(new File(indexDir));
		DirectoryReader dirReader = DirectoryReader.open(dir);
		IndexSearcher is = new IndexSearcher(dirReader);
		QueryParser parser = new QueryParser(Version.LUCENE_47, "contents",
				new SimpleAnalyzer(Version.LUCENE_47));
		Query query = parser.parse(q);
		long start = System.currentTimeMillis();
		TopDocs hits = is.search(query, 10);
		long end = System.currentTimeMillis();
		System.out.println("Found " + hits.totalHits + " document(s) (in "
				+ (end - start) + " milliseconds) that matched query '" + q + "':");
		for (ScoreDoc scoreDoc : hits.scoreDocs)
		{
			Document doc = is.doc(scoreDoc.doc);
			System.out.println(doc.get("filename"));
		}
	}
}

maven的配置如下：

<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.mitchz</groupId>
	<artifactId>lucence-test</artifactId>
	<version>0.0.1-SNAPSHOT</version>
	<packaging>jar</packaging>

	<name>lucence-test</name>
	<url>http://maven.apache.org</url>

	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
	</properties>

	<dependencies>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>3.8.1</version>
			<scope>test</scope>
		</dependency>
		<dependency>
			<groupId>org.apache.lucene</groupId>
			<artifactId>lucene-core</artifactId>
			<version>4.7.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.lucene</groupId>
			<artifactId>lucene-analyzers-common</artifactId>
			<version>4.7.0</version>
		</dependency>
		<dependency>
			<groupId>org.apache.lucene</groupId>
			<artifactId>lucene-queryparser</artifactId>
			<version>4.7.0</version>
		</dependency>
	</dependencies>
</project>