lucene检索简单例子

最新推荐文章于 2022-08-19 20:24:31 发布

lizhenfu123

最新推荐文章于 2022-08-19 20:24:31 发布

阅读量344

点赞数

分类专栏： lucene

本文链接：https://blog.csdn.net/lizhenfu123/article/details/34865099

版权

lucene 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

1、新建资源文件

2、给资源文件建立索引

package com.sf.test;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
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.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class StandardAnalyzerTest {

	public static void main(String[] args) throws Exception {

		File fileDir = new File("D:\\source");
		File indexDir = new File("D:\\index");
		Directory dir = FSDirectory.open(indexDir);
		
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_36);
		IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_36, analyzer);
		
		iwc.setOpenMode(OpenMode.CREATE);
		IndexWriter iw = new IndexWriter(dir, iwc);
		File[] textFiles = fileDir.listFiles();
		long startTime = new Date().getTime();
		
		for (int i = 0; i < textFiles.length; i++) {
			if(textFiles[i].isFile() && textFiles[i].getName().endsWith(".txt"))
			{
				System.out.println("File"+textFiles[i].getParentFile()+"正在被搜索...");
				String temp = fileReaderAll(textFiles[i].getCanonicalPath(),"GBK");//
				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);
				iw.addDocument(document);
			}
		}
		iw.close();
		
		long endTime = new Date().getTime();
		System.out.println("这个花费了"+(endTime - startTime) +"毫秒来把文档增加到索引里面"+fileDir.getPath());
		
	}
	
	public static String fileReaderAll(String fileName,String charset) throws Exception
	{
		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;
		
	}
	
	
	
	
	
	
	
	
	
	
	
}

2、检索文件

package com.sf.test;

import java.io.File;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexReader;
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.FSDirectory;
import org.apache.lucene.util.Version;

public class SearchTest {

	public static void main(String[] args) throws Exception {
		String index = "D:\\index";         //搜索的索引路径
		
		IndexReader iReader = IndexReader.open(FSDirectory.open(new File(index)));
		IndexSearcher is = new IndexSearcher(iReader);
		
		ScoreDoc[] hits = null;
		String quertString = "绝对秋香";
		Query query = null;
		
		Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_36);
		QueryParser qp = new QueryParser(Version.LUCENE_36, "body", analyzer);
		query = qp.parse(quertString);
		
		if(is != null)
		{
			TopDocs result = is.search(query, 10);
			hits = result.scoreDocs;
			if(hits.length > 0)
			{
				System.out.println("找到"+hits.length+"个结果！");
			}
			
			is.close();
		}
		
		
	}
}