lucene3.2 简单的建立索引和查询

由于lucene3.2发布不久找个用法都比较困难啊，看了其他人以前写的早期版本的用法以及看api来学习
由于新版本，以前版本很多方法都不能用了

学习之后终于写出了个能用的代码
首先是建索引：

import java.io.BufferedReader;
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;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class Main {
	static File filedir = new File("e:\\work\\java\\crawl\\test");
	static File indexdir = new File("e:\\work\\java\\crawl\\index");
	static IndexWriter writer;

	public static void main(String[] args) {
		try {
			Date start = new Date();
			writeToIndex();
			Date end = new Date();
			System.out.println("建索引时间" + (end.getTime() - start.getTime())
					+ "毫秒");
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	public static int writeToIndex() throws Exception {
		StandardAnalyzer aa = new StandardAnalyzer(Version.LUCENE_32);
		writer = new IndexWriter(FSDirectory.open(indexdir),
				new IndexWriterConfig(Version.LUCENE_32, aa));
		indexDirectory(filedir);
		int numIndexed = writer.numDocs();
		System.out.println(numIndexed);
		writer.optimize();
		writer.close();
		return numIndexed;
	}

	private static void indexDirectory(File dir) throws IOException {
		File[] files = dir.listFiles();
		for (int i = 0; i < files.length; i++) {
			File f = files[i];
			if (f.isDirectory()) {
				indexDirectory(f);
			} else if (f.getName().endsWith(".txt")) {
				indexFile(f);
			}
		}
	}

	private static void indexFile(File f) throws IOException {
		if (f.isHidden() || !f.exists() || !f.canRead())
			return;
		Document doc = new Document();
		BufferedReader in=new BufferedReader(new FileReader(f));
		String temp;
		StringBuffer sb=new StringBuffer();
		while((temp=in.readLine())!=null)
			sb.append(temp);
		doc.add(new Field("content", sb.toString(), Field.Store.YES,
				Field.Index.ANALYZED));
		doc.add(new Field("name", f.getCanonicalPath(), Field.Store.YES,
				Field.Index.ANALYZED));
		writer.addDocument(doc);
	}
}

然后说明下
Field.Store.YES:存储字段值（未分词前的字段值）
Field.Store.NO:不存储,存储与索引没有关系
Field.Store.COMPRESS:压缩存储,用于长文本或二进制，但性能受损
Field.Index.ANALYZED:分词建索引
Field.Index.ANALYZED_NO_NORMS:分词建索引，但是Field的值不像通常那样被保存，而是只取一个byte，这样节约存储空间
Field.Index.NOT_ANALYZED:不分词且索引
Field.Index.NOT_ANALYZED_NO_NORMS:不分词建索引，Field的值去一个byte保存TermVector表示文档的条目（由一个Document和Field定位）和它们在当前文档中所出现的次数
Field.TermVector.YES:为每个文档（Document）存储该字段的TermVector
Field.TermVector.NO:不存储TermVector
Field.TermVector.WITH_POSITIONS:存储位置
Field.TermVector.WITH_OFFSETS:存储偏移量
Field.TermVector.WITH_POSITIONS_OFFSETS:存储位置和偏移量

然后就是查询代码了

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.TopScoreDocCollector;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class Main {
	static File indexdir = new File("e:\\work\\java\\crawl\\index");
	static String KEYWORD = "高新区";
	static int TOP_NUM = 5;

	public static void main(String[] args) throws Exception {
		search(KEYWORD);
	}

	public static void search(String q) throws Exception {
		IndexSearcher is = new IndexSearcher(FSDirectory.open(indexdir), true);
		String field = "content";
		QueryParser parser = new QueryParser(Version.LUCENE_32, field,
				new StandardAnalyzer(Version.LUCENE_32));
		Query query = parser.parse(q);
		TopScoreDocCollector collector = TopScoreDocCollector.create(TOP_NUM,
				true);
		long start = new Date().getTime();
		is.search(query, collector);
		ScoreDoc[] hits = collector.topDocs().scoreDocs;
		System.out.println(hits.length);
		for (int i = 0; i < hits.length; i++) {
			Document doc = is.doc(hits[i].doc);
			System.out.println(doc.get("content"));
		}
		long end = new Date().getTime();
		System.out.println("Found " + collector.getTotalHits()
				+ " document(s) (in " + (end - start)
				+ " milliseconds) that matched query '" + q + "':");
	}
}

如果是多个关键字查询就这样

String[] queries = { "高新区", "1000" };
String[] fields = { "content", "money" };
BooleanClause.Occur[] clauses = { BooleanClause.Occur.MUST,
				BooleanClause.Occur.MUST};
Query query = MultiFieldQueryParser.parse(Version.LUCENE_32, queries,
fields, clauses, new StandardAnalyzer(Version.LUCENE_32));

代码还是比较好懂的就不解释了。。。