lucene(二) 索引的建立、增刪改查

fan_rockrock發表於2016-05-16
索引

一、索引的整個知識架構


二、例子一：建立對多個檔案的索引並查詢

import java.io.File;
import java.io.FileReader;
import java.io.IOException;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
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.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;


public class HelloLucene {
	public static void main(String[]args){
		HelloLucene helloLucene=new HelloLucene();
		helloLucene.index();
		helloLucene.search();
	}
	/** 建立檔案索引
	 * @author
	 * @param
	 * @return
	 */
	public void index(){
		IndexWriter writer=null;
		//1、建立Directory
		//Directory directory=new RAMDirectory();//建立在記憶體中的
		try {
			Directory directory=FSDirectory.open(new File("d:/index"));//建在硬碟上的
			//2、建立IndexWriter
			writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
			//3、建立Document物件
			Document doc=null;
			//4、為Document新增Field
			File f=new File("d:/TestLucene");
			for(File file:f.listFiles()){
				doc=new Document();
				doc.add(new Field("content", new FileReader(file)));
				doc.add(new Field("filename",file.getName(),Field.Store.YES,Field.Index.NOT_ANALYZED));
				doc.add(new Field("path",file.getAbsolutePath(),Field.Store.YES,Field.Index.NOT_ANALYZED));
				writer.addDocument(doc);
			}
			
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}finally{
			if(writer!=null)
				try {
					writer.close();
				} catch (CorruptIndexException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				} catch (IOException e) {
					// TODO Auto-generated catch block
					e.printStackTrace();
				}
		}	
	}
	/** 查詢
	 * @author
	 * @param
	 * @return
	 */
	public void search(){
		
		try{
			//1、建立Directory
			Directory directory=FSDirectory.open(new File("d:/index"));
	        //2、建立IndexReader
		    IndexReader reader=IndexReader.open(directory);
		    //3、根據IndexReader建立IndexSearcher
		    IndexSearcher searcher=new IndexSearcher(reader);
		    //4、建立搜尋的Query
		    QueryParser parser=new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
			Query query=parser.parse("奧運");//查詢content欄位內容為"奧運"的檔案
			//5、根據seacher搜尋並且返回TopDocs
			TopDocs tds=searcher.search(query, 10);
			//6、根據TopDocs獲取ScoreDoc物件
			ScoreDoc[]sds=tds.scoreDocs;
			for(ScoreDoc sd:sds){
				//7、根據sercher和ScoreDoc物件獲取具體的Document物件
				Document d=searcher.doc(sd.doc);
				//8、根據Document物件獲取需要的值
				System.out.println(d.get("filename")+"["+d.get("path")+"]");
			}
			//9、關閉reader
			reader.close();
			
		}catch(CorruptIndexException e){
			e.printStackTrace();
		}
		catch (IOException e) {
			e.printStackTrace();
		}
		catch (ParseException e) {
			e.printStackTrace();
		}
	}
}

三、域的說明、使用luke開啟建立的索引二進位制檔案

1、域Field的說明


2、使用luke分析索引檔案

建立好索引之後在硬碟中找到如下所示：


使用luke簡單看一下各個檔案是幹什麼的：


luke還有其他的功能，這裡就不一一介紹了~

四、例子二：索引的增刪改查

import java.io.File;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.StaleReaderException;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;


public class IndexUtil {
	private String[] ids = {"1","2","3","4","5","6"};
	private String[] emails = {"aa@itat.org","bb@itat.org","cc@cc.org","dd@sina.org","ee@zttc.edu","ff@itat.org"};
	private String[] contents = {
			"welcome to visited the space,I like book",
			"hello boy, I like pingpeng ball",
			"my name is cc I like game",
			"I like football", 
			"I like football and I like basketball too",
			"I like movie and swim"
	};
	private int[] attachs = {2,3,1,4,5,5};//附件
	private String[] names = {"zhangsan","lisi","john","jetty","mike","jake"};
	private Map<String,Float> scores = new HashMap<String,Float>();//儲存權值
	
	private Directory directory=null;
	
	
	public static void main(String[]args){
		IndexUtil iUtil=new IndexUtil();
		iUtil.index();
		iUtil.search();
	}
	/** 建構函式
	 * @author 
	 * @param
	 * @return
	 */
	public IndexUtil(){
		scores.put("itat.org",2.0f);
		scores.put("zttc.edu", 1.5f);
		try {
			//1、建立索引存在的地方
			directory=FSDirectory.open(new File("d:/index"));
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	
	/** 建立索引
	 * @author 
	 * @param
	 * @return
	 */
	public void index(){
		//2、建立索引
		IndexWriter writer=null;
			try {
				writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
			    //3、建立文件並建立索引(文件相當於二維表中的每一條記錄，域相當於表的欄位，所以整個索引可以理解為一個二維表)
				Document doc=null;
				for(int i=0;i<ids.length;i++){
					doc = new Document();
					doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
					doc.add(new Field("email",emails[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
					doc.add(new Field("content",contents[i],Field.Store.NO,Field.Index.ANALYZED));
					doc.add(new Field("name",names[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
					String et = emails[i].substring(emails[i].lastIndexOf("@")+1);
					System.out.println(et);
					//對文件進行加權處理
//					if(scores.containsKey(et)) {
//						doc.setBoost(scores.get(et));
//					} else {
//						doc.setBoost(0.5f);
//					}
					writer.addDocument(doc);
				}
			} catch (CorruptIndexException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			} catch (LockObtainFailedException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			} catch (IOException e) {
				// TODO Auto-generated catch block
				e.printStackTrace();
			}finally{
				if(writer!=null)
					try {
						writer.close();
					} catch (CorruptIndexException e) {
						// TODO Auto-generated catch block
						e.printStackTrace();
					} catch (IOException e) {
						// TODO Auto-generated catch block
						e.printStackTrace();
					}
			}
	}
	
	/** 查詢索引基本資訊
	 * @author 
	 * @param
	 * @return
	 */ 
	public void query() {
		try {
			IndexReader reader = IndexReader.open(directory);
			//通過reader可以有效的獲取到文件的數量
			System.out.println("numDocs:"+reader.numDocs());
			System.out.println("maxDocs:"+reader.maxDoc());
			System.out.println("deleteDocs:"+reader.numDeletedDocs());
			reader.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();		}
	}
	/** 使用TermQuery具體查詢
	 * @author 
	 * @param
	 * @return
	 */ 
	public void search() {
		try {
			IndexReader reader = IndexReader.open(directory);
			IndexSearcher searcher = new IndexSearcher(reader);
			TermQuery query = new TermQuery(new Term("content","like"));
			TopDocs tds = searcher.search(query, 10);
			for(ScoreDoc sd:tds.scoreDocs) {
				Document doc = searcher.doc(sd.doc);
				System.out.println("("+sd.doc+"-"+doc.getBoost()+"-"+sd.score+")"+
						doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id"));
			}
			reader.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	/** 刪除索引
	 * @author 
	 * @param
	 * @return
	 */ 
	public void delete() {
		IndexWriter writer = null;
		try {
			writer = new IndexWriter(directory,
					new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));
			//引數是一個選項，可以是一個Query，也可以是一個term，term是一個精確查詢的值
			//此時刪除的文件並不會被完全刪除，而是儲存在一個回收站中的，可以恢復
			writer.deleteDocuments(new Term("id","1"));
			writer.commit();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			try {
				if(writer!=null) writer.close();
			} catch (CorruptIndexException e) {
				e.printStackTrace();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}
	/** 恢復刪除的索引
	 * @author 
	 * @param
	 * @return
	 */ 
	public void undelete() {
		//使用IndexReader進行恢復
		try {
			IndexReader reader = IndexReader.open(directory,false);
			//恢復時，必須把IndexReader的只讀(readOnly)設定為false
			reader.undeleteAll();
			reader.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (StaleReaderException e) {
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	/** 強制刪除回收站中的索引
	 * @author 
	 * @param
	 * @return
	 */ 
	public void forceDelete() {
		IndexWriter writer = null;
		
		try {
			writer = new IndexWriter(directory,
					new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));
			writer.forceMergeDeletes();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			try {
				if(writer!=null) writer.close();
			} catch (CorruptIndexException e) {
				e.printStackTrace();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}
	/** 索引的更新
	 * @author 
	 * @param
	 * @return
	 */ 
	public void update() {
		IndexWriter writer = null;
		try {
			writer = new IndexWriter(directory,
					new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));
			/*
			 * Lucene並沒有提供更新，這裡的更新操作其實是如下兩個操作的合集
			 * 先刪除之後再新增
			 */
			Document doc = new Document();
			doc.add(new Field("id","11",Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
			doc.add(new Field("email",emails[0],Field.Store.YES,Field.Index.NOT_ANALYZED));
			doc.add(new Field("content",contents[0],Field.Store.NO,Field.Index.ANALYZED));
			doc.add(new Field("name",names[0],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
			writer.updateDocument(new Term("id","1"), doc);
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			try {
				if(writer!=null) writer.close();
			} catch (CorruptIndexException e) {
				e.printStackTrace();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}
}





相關文章