用Lucene 2.0建立索引及查询示例

建立索引程序:

/*
 * Created on 2004-4-26
 */

import org.apache.lucene.index.*;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.document.*;
import java.io.*;

public class IndexFiles {

	public static void main(String[] args) {
		try {
			IndexWriter writer = new IndexWriter("/myindex",
					new StandardAnalyzer(), true);

			File files = new File("mydoc");
			String[] Fnamelist = files.list();
			for (int i = 0; i < Fnamelist.length; i++) {
				File file = new File(files, Fnamelist[i]);

				Document doc = new Document();
				Field fld = new Field("path",file.getPath(),Field.Store.YES,Field.Index.NO);
//				Field fld = Field.Text("path", file.getPath());
				doc.add(fld);
				fld = new Field("modified",DateField.timeToString(file.lastModified()),Field.Store.YES,Field.Index.NO);
//				fld = Field.Keyword("modified", DateField.timeToString(file
//						.lastModified()));
				doc.add(fld);

				FileInputStream in = new FileInputStream(file);
				Reader reader = new BufferedReader(new InputStreamReader(in));
				fld = new Field("contents",reader);
//				fld = Field.Text("contents", reader);
				doc.add(fld);

				writer.addDocument(doc);
				System.out.println("Added : " + doc.get("path"));

			}
			writer.optimize();
			writer.close();
			System.out.println("Has Added Total: " + Fnamelist.length);
		} catch (Exception e) {
			System.out.println(e);
		}
	}
}

程序对当前路径下mydoc目录下所有文件建立索引，其中索引有三个字段: 文件路径，
最后修改时间，文件内容.  建立的索引文件在当前路径下的myindex目录

检索程序:

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TermQuery;

/**
 * @author Sivyer
 * 
 */
public class SearchFile {

	public static void main(String[] args) {

		// XMap a = new XMap("");
		Analyzer anlzr = new StandardAnalyzer();
		try {
			
			
//			Query q = QueryParser.parse("数据库", "contents", anlzr);
			Query q = makeQuery("readme.txt");
			System.out.println("Searching for : " + q.toString("contents"));

			Searcher serch = new IndexSearcher("/myindex");
			Hits hts = serch.search(q);
			for (int i = 0; i < hts.length(); i++) {
				Document doc = hts.doc(i);
				String path = doc.get("path");
				System.out.println("Find: " + i + ": " + path);
				System.out.println("Find: " + doc.get("modified"));
				System.out.println("Find: " + doc.get("path"));
			}
			System.out.println("Find Total: " + hts.length());
		} catch (Exception e) {
			System.out.println(e);
		}
	}
	public static Query makeQuery(String query) {
		TermQuery qu = new TermQuery(new Term("all", query.toLowerCase()));
		return qu;
	}
}

程序对索引的contents字段用“数据库“关键字进行查询，返回
的是所有包含有关键字的文档集合，分别打印出各个字段.

上面的程序我用纯文本文件测试通过，.txt,.jsp,.html 都可以，
word,pdf 等文件需要经过转化才能对其进行索引。

-------------------------------
说明: 来源网络