lucene

最新推荐文章于 2025-08-14 18:19:24 发布

原创最新推荐文章于 2025-08-14 18:19:24 发布 · 102 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#lucene

lucene 专栏收录该内容

7 篇文章

订阅专栏

本文介绍了一个基于Lucene的全文检索系统的实现过程，包括如何建立索引、优化索引及搜索文档等内容。通过示例代码展示了如何使用StandardAnalyzer分析器、IndexWriter建立索引、IndexSearcher进行搜索等关键步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

/**
 * 
 */
package two;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.Date;

import org.apache.lucene.analysis.Analyzer;
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.queryParser.ParseException;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * author lighter date 2006-8-7
 */
public class TextFileIndexer {
	public static void main(String[] args) throws Exception {
		File fileDir = new File("D:/MyEclipse/ws/test/src");
//		Directory directory = new RAMDirectory();
		Directory directory = FSDirectory.open(new File("D:/MyEclipse/ws/test/dir"));
		Analyzer luceneAnalyzer = new StandardAnalyzer(Version.LUCENE_31);
		@SuppressWarnings("deprecation")
		IndexWriter indexWriter = new IndexWriter(directory, luceneAnalyzer,
				true, new IndexWriter.MaxFieldLength(25000));
		File[] textFiles = fileDir.listFiles();

		long startTime = new Date().getTime();

		// 增加document到索引去
		for (int i = 0; i < textFiles.length; i++) {
			if (textFiles[i].isFile()
					&& textFiles[i].getName().endsWith(".txt")) {
				System.out.println("File" + textFiles[i].getCanonicalPath()
						+ " 正在被索引 . ");
				String temp = FileReaderAll(textFiles[i].getCanonicalPath(),
						"utf-8");
				System.out.println(temp);
				Document document = new Document();
				Field FieldPath = new Field("path", textFiles[i].getPath(),
						Field.Store.YES, Field.Index.NO);
				Field FieldBody = new Field("body", temp, Field.Store.YES,
						Field.Index.ANALYZED,
						Field.TermVector.WITH_POSITIONS_OFFSETS);
				document.add(FieldPath);
				document.add(FieldBody);
				indexWriter.addDocument(document);
			}
		}
		// optimize()方法是对索引进行优化
		indexWriter.optimize();
		indexWriter.close();

		// 测试一下索引的时间
		long endTime = new Date().getTime();
		System.out.println(" 这花费了 " + (endTime - startTime)
				+ "  毫秒来把文档增加到索引里面去! " + fileDir.getPath());
		String queryString = " 随便 ";
		Query query = null;
		IndexSearcher searcher = new IndexSearcher(directory, true);

		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);
		try {
			QueryParser qp = new QueryParser(Version.LUCENE_31, "body",
					analyzer);
			query = qp.parse(queryString);
		} catch (ParseException e) {
		}
		if (searcher != null) {
			ScoreDoc[] hits = searcher.search(query, 3).scoreDocs;
			if (hits.length > 0) {
				System.out.println(" 找到: " + hits.length + "  个结果! ");
				for (ScoreDoc doc : hits) {
					System.out.println(searcher.doc(doc.doc).get("body"));
				}
			}
		}
	}

	public static String FileReaderAll(String FileName, String charset)
			throws IOException {
		BufferedReader reader = new BufferedReader(new InputStreamReader(
				new FileInputStream(FileName), charset));
		String line = new String();
		String temp = new String();

		while ((line = reader.readLine()) != null) {
			temp += line;
		}
		reader.close();
		return temp;
	}
}

可以参考：http://blog.youkuaiyun.com/neusoftware_20063500/article/details/3969365

但是参考中的lucene的版本与本例的版本不同