Lucene——索引的创建、删除、修改

package cn.tz.lucene;

import java.io.File;
import java.util.ArrayList;
import java.util.List;

import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.junit.Test;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class IndexManagerTest {

	@Test
	public void testIndexCreate() throws Exception{
		 //采集文件系统中的文档数据到Lucene中
		 //创建文档列表
		 List<Document> docList=new ArrayList<Document>();
		 //指定文件目录
		File dir=new File("C:\Users\admin\searchsource");
		 //循环文件夹
		for(File file:dir.listFiles()){
			String fileName = file.getName();
			String fileContent=FileUtils.readFileToString(file);
			Long fileSize=FileUtils.sizeOf(file);
			//创建文档对象
			Document document=new Document();
			TextField namefield=new TextField("fileName",fileName,Store.YES);
			TextField contentField=new TextField("fileContent",fileContent,Store.YES);
			LongField sizeField=new LongField("fileSize",fileSize,Store.YES);
			//LongField 
			document.add(namefield);
			document.add(contentField);
			document.add(sizeField);
			docList.add(document);
		}
		
		//创建分词器Analyzer
		// Analyzer analyzer=new StandardAnalyzer();
		
		//采用第三方的中文分词器 IKAnalyzer
		Analyzer analyzer=new IKAnalyzer();
		 //指定索引和文档的存储目录
		 FSDirectory desFile=FSDirectory.open(new File("d:\lucene"));
		 //创建写对象的初始化对象
		 IndexWriterConfig config=new IndexWriterConfig(Version.LUCENE_4_10_3,analyzer);
		 //创建索引和文档的写对象
		 IndexWriter writer=new IndexWriter(desFile,config);
		 //将文档 加到索引和文档的写对象中
		for(Document doc:docList){
			writer.addDocument(doc);
		}
		//提交
		writer.commit();
		//关闭流
		writer.close();
	}
	
	@Test
	public void testIndexDel() throws Exception{
		Analyzer analyzer=new IKAnalyzer();
		FSDirectory dir=FSDirectory.open(new File("d:\lucene"));
		IndexWriterConfig config=new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
		IndexWriter writer=new IndexWriter(dir, config);
		
		//删除所有索引
		//writer.deleteAll();
		
		//删除指定索引(根据域删除)
		//Term("域名","搜索的关键字")
		writer.deleteDocuments(new Term("fileName","apache"));
		//提交
		writer.commit();
		//关闭
		writer.close();
		
	}
	
	/**
	 * 更新操作<br>:
	 *  <li>按照Term进行指定域搜索关键字,如果查到记录就删除,然后将更新后的内容重新生成Document对象</li>
	 *  <li>如果没有查到记录,则直接将更新后的内容添加一个Document对象</li>
	 */
	@Test
	public void testIndexUpdate() throws Exception{
		Analyzer analyzer=new IKAnalyzer();
		//存储目录
		FSDirectory dir=FSDirectory.open(new File("d:\lucene"));
		IndexWriterConfig config=new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
		IndexWriter writer=new IndexWriter(dir,config);
		
		//按照fileName域进行搜索关键字"web"
		Term term=new Term("fileName","哦哦");
		
		Document doc=new Document();
		doc.add(new TextField("fileName","not exit",Store.YES));
		doc.add(new LongField("fileSize",100L,Store.YES));
		doc.add(new StringField("fileContent", "egfao容", Store.YES));
		//更新
		writer.updateDocument(term, doc);	
		//提交
		writer.commit();
		//关闭
		writer.close();
	}
}

  

原文地址:https://www.cnblogs.com/yuefeng123/p/8311115.html