Lucene创建索引（一）

这是工程目录

package index;

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.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.LongField;
import org.junit.Test;

public class testIndexOperation {
	@Test
	public void testCreateIndex() throws Exception{
		List list =  new ArrayList();
		//读取需要创建索引的文件
		File dir =  new File("C:\\Users\\sam\\Desktop\\lucene");
		//利用io包对其进行遍历
		for(File file:dir.listFiles()){
			Document doc =  new Document();
			String fileName = file.getName();
			Long fileSize = FileUtils.sizeOf(file);
			String fileContext = FileUtils.readFileToString(file);
			TextField f1 =  new TextField("fileName", fileName, Store.YES);
			TextField f2 =  new TextField("fileContext", fileContext, Store.YES);
			LongField f3 =  new LongField("fileSize", fileSize, Store.YES);
			doc.add(f1);
			doc.add(f2);
			doc.add(f3);
			list.add(doc);
		}
		//以上对文件进行分析完毕，创建分词器
		Analyzer analyzer = new StandardAnalyzer();
		//设置索引输出目录
		Directory directory =  FSDirectory.open(new File("C:\\Users\\sam\\Desktop\\dir"));
		//设置索引输出配置
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);
		//创建索引输出器
		IndexWriter indexWriter = new IndexWriter(directory, config);
		//遍历document
		for(Document doc:list){
			indexWriter.addDocument(doc);
		}
		//提交
		indexWriter.commit();
		//关闭资源
		indexWriter.close();
	}
}
 

这是等待分析的文本

这是得到的索引文件。

索引文件可以利用lukeall打开进行查阅