Lucene 的一个程序

package com.cngine.Index;import java.io.File;import java.io.IOException;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.index.CorruptIndexException;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriter.MaxFieldLength;import org.apache.lucene.queryParser.MultiFieldQueryParser;import org.apache.lucene.queryParser.ParseException;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.search.Filter;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;import org.junit.Test;import com.cngine.utils.File2Docuement;public class IndexDemo {private String sourceDir = "D://sourceDir//Baidu studies i'm.txt";private String indexDir = "D://indexDir";Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);/*** * 创建索引 */@Testpublic void CreateIndex() throws Exception {// 操作索引库 (增删改)// MaxFieldLength.LIMITED = new MaxFieldLength(10000);// 索引前一万个10000IndexWriter index = new IndexWriter(FSDirectory.open(new File(indexDir)), analyzer, true, MaxFieldLength.LIMITED);//把文件转换成一个Document文档Document doc = File2Docuement.ToDocument(sourceDir);//在索引文件中添加Document文档index.addDocument(doc);//刷新缓存里面的数据到索引库//index.commit();//优化index.optimize();// 释放资源index.close();}/** * 搜索索引 */@Testpublic void SearchIndex() {String searchString = "baidu";Date BeginDate = new Date();try {// 1.根据索引的目录获取 搜索 索引器IndexSearcher indexSearcher = new IndexSearcher(FSDirectory.open(new File(indexDir)));// 2.把要搜索的文本 解析成Query对象//要搜索的字段String[] fields = { "name", "content" };//Query对象转换器QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_CURRENT, fields, analyzer);//根据Query转换器把要搜索的 字符串转换成 Query对象Query query = parser.parse(searchString);// 3.过滤器，过滤掉不想要的词语Filter filter = null;// 4.搜索TopDocs topDocs = indexSearcher.search(query, filter, 10000);// 5.打印结果System.out.println("---------------------------------------------");System.out.println("总共有条"+topDocs.totalHits+"记录");ScoreDoc[] scoreDoc = topDocs.scoreDocs;for(ScoreDoc score :scoreDoc){int i = score.doc;Document doc = indexSearcher.doc(i);//获取值//1.// Field field = doc.getField("name");// field.stringValue();//2.//doc.get("name");System.out.println("name:"+doc.get("name"));System.out.println("content:"+doc.get("content"));System.out.println("size:"+doc.get("size"));System.out.println("path:"+doc.get("path"));}Date endDate = new Date();System.out.println(String.valueOf(endDate.getTime()-BeginDate.getTime())+"ms");} catch (CorruptIndexException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();} catch (ParseException e) {e.printStackTrace();}}}

 

工具类

 

package com.cngine.utils;import java.io.BufferedReader;import java.io.File;import java.io.FileInputStream;import java.io.InputStreamReader;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;public class File2Docuement {public static Document ToDocument(String path){File file = new File(path);Document doc = new Document();doc.add(new Field("name",file.getName(),Store.YES,Index.ANALYZED));doc.add(new Field("content",ReadFile(file),Store.YES,Index.ANALYZED));doc.add(new Field("size",String.valueOf(file.length()),Store.YES,Index.NOT_ANALYZED));doc.add(new Field("path",file.getAbsolutePath(),Store.YES,Index.NO));return doc;}/** * * @param file * @return */public static String ReadFile(File file){try {BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(file)));StringBuffer sb = new StringBuffer();for(String line=null;(line = reader.readLine()) != null;){sb.append(line).append("/n");}return sb.toString();} catch (Exception e) {throw new RuntimeException(e);}}}