Lucene3.6demo小试

最新推荐文章于 2025-08-06 18:22:29 发布

原创最新推荐文章于 2025-08-06 18:22:29 发布 · 401 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#lucene #file #string #javadoc #query #exception

本文通过实际代码示例，介绍了如何使用Lucene进行文本索引与查询，并重点讨论了版本管理对于代码实践的重要性。从文件读取、文档构建到索引创建，再到查询与搜索，展示了Lucene在文本检索领域的应用流程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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

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.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
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.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;


public class Test {

	/**
	 * 读取文件的内容
	 * @param file
	 * @return
	 */
	public static String getContent(File file) {
        try {
            BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
            StringBuffer content = new StringBuffer();
            for (String line = null; (line = reader.readLine()) != null;) {
                content.append(line).append("\n");
            }
            reader.close();
            return content.toString();
        } catch (Exception e) {
            throw new RuntimeException(e);
        }
    }
	
	   
	
	/**
	 * 构造Document对象
	 * @param file
	 * @return
	 */
	public static Document makeDocument(File file){
	   Document doc = new Document();
	   doc.add(new Field(
					"name",
					file.getName(),
					Store.YES,
					Index.ANALYZED));
		doc.add(new Field(
					"content",
					getContent(file),
					Store.YES,
					Index.ANALYZED));
		
	   return doc;
	   
   }
	
	/**
	 * 
	 * @param args
	 * @throws IOException 
	 * @throws ParseException 
	 */
	public static void main(String[] args) throws IOException, ParseException {
		//数据源
		File fileDir = new File("d:\\test.txt");
		File fileDir2 = new File("d:\\test_hehe.txt");
		//构造Directory对象,这里使用内存版的
		Directory indexdir = new RAMDirectory();
		
		//对两个数据分别构造Document对象
		Document doc = makeDocument(fileDir);
		Document doc2 = makeDocument(fileDir2);
		
		//实例化Analyzer和索引用到的参数
		Analyzer luceneAnalyzer = new StandardAnalyzer(Version.LUCENE_36);
		IndexWriterConfig config=new IndexWriterConfig(Version.LUCENE_36, luceneAnalyzer);
		IndexWriter indexWriter = new IndexWriter(indexdir,config);
		
		//将需要索引的Document加入indexWriter
		indexWriter.addDocument(doc);
		indexWriter.addDocument(doc2);
		
		//用完要记得关闭
		indexWriter.close();
		
		//待查询串
		String queryString = "test";
		//查询域
		String[] fields = {"name","content"};
		
		QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_36,fields,luceneAnalyzer);
		Query query = queryParser.parse(queryString);
		
		//新的IndexSearcher需要IndexReader作为参数
		IndexReader indexReader = IndexReader.open(indexdir);
		IndexSearcher indexSearcher = new IndexSearcher(indexReader);
		
		//开始查询
		TopDocs topDocs = indexSearcher.search(query, 1000);
		
		indexSearcher.close();
		
		System.out.println(topDocs.totalHits);
		
		for (ScoreDoc scoreDoc : topDocs.scoreDocs){
			int index = scoreDoc.doc;
			Document docu = indexSearcher.doc(index);
			System.out.println("name:"+docu.get("name"));
			System.out.println("content:"+docu.get("content"));
		}
	}

}

最近准备面试,突然想到要看看lucene,上课的时候讲过原理,但是代码还没写过,于是下了最新版的lucene包
按照俺的常规代码学习方法,当然是demo流了..所以去网上找代码..不过貌似都不是3.6的,一些构造函数要么是不推荐使用,要么是作废的
所以还是得求助javadoc , 对着说明发现有些改动,但是并不是特别大,比如增加了版本管理Version之类的,于是在原代码的基础上做了一些修改就成了这样的东西了