Lucene——搜索部分

构造方法：索引建在内存里，掉用初始化方法index（）

IndexReader是单例的

搜索：调用getSearcher（）

searchByTerm(String field,String name,int num)词语查找

searchByTermRange(String field,String start,String end,int num) 范围查找

searchByNumricRange(String field,int start,int end,int num)数字的范围查找

 

su.searchByTerm("content","i",10);//I like soccer 精确查找，查找的好像是第一个字母

 

 

package org.itat.index;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
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.document.NumericField;
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.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TermRangeQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

public class SearcherUtil {

	private Directory directory=null;
	private IndexReader reader=null;
	
	private String[] ids = { "1", "2", "3", "4", "5", "6" };
	private String[] emails = { "dd@@dd.org", "aa@jingtian.org",
			"bb@jingtian.org", "cc@ytu.edu", "ee@ee.org", "ff@ff.org" };
	private String[] contents = { "I like soccer", "I like football",
			"I like soccer and I like game", "I like book", "I like soccer",
			"I like soccer" };
	private int[] attachs = { 1, 6, 8, 9, 5, 4, 5 };
	private String[] names = { "zhangsan", "lisi", "wangwu", "haoliu", "wuba",
			"chenjiu" };
	private Map<String, Float> scores = new HashMap<String, Float>();
	private Date[] dates = null;

	public SearcherUtil() {
		directory = new RAMDirectory();
		setDate();
		index();
	}
	
	public void setDate() {
		SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-DD"); // 时间转换，这个不会有点丢人
		try {
			dates = new Date[ids.length];
			dates[0] = sdf.parse("2010-08-17");
			dates[1] = sdf.parse("2011-02-17");
			dates[2] = sdf.parse("2012-03-17");
			dates[3] = sdf.parse("2011-04-17");
			dates[4] = sdf.parse("2012-05-17");
			dates[5] = sdf.parse("2011-07-17");
		} catch (Exception e) {
			e.printStackTrace();
			// TODO: handle exception
		}
	}
	
	public void index() {

		IndexWriter writer = null;
		Document doc = null;
		try {
			writer = new IndexWriter(directory, new IndexWriterConfig(
					Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
			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.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));

				// 存储数字
				doc.add(new NumericField("attach", Field.Store.YES, true)
						.setIntValue(attachs[i]));
				// 存储日期
				doc.add(new NumericField("date", Field.Store.YES, true)
						.setLongValue(dates[i].getTime()));

				String et = emails[i].substring(emails[i].lastIndexOf("@") + 1);
				if (scores.containsKey(et)) {
					doc.setBoost(scores.get(et));
				} else {
					doc.setBoost(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();
				}
			}
		}
	}


	public IndexSearcher getSearcher() {
		try {
			if (reader == null) {
				reader = IndexReader.open(directory);
			} else {
				IndexReader tr = IndexReader.openIfChanged(reader);
				if (tr != null) {
					reader.close();
					reader = tr;
				}
			}
			return new IndexSearcher(reader);
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}

		System.out.println("到这里了");
		return null;
	}
	
	public void searchByTerm(String field,String name,int num)
	{

		try {
			IndexSearcher indexSearcher = getSearcher();
			Query query = new TermQuery(new Term(field, name));
			TopDocs tds = indexSearcher.search(query, num);
			System.out.println("一共查询了:" + tds.totalHits);
			for (ScoreDoc sd : tds.scoreDocs) {
				Document doc = indexSearcher.doc(sd.doc);
				System.out.println(doc.get("id") + "---->" + doc.get("name") + "["
						+ doc.get("email") + "]-->" + doc.get("id") + ","
						+ doc.get("attach") + "," + doc.get("date"));
			}
			indexSearcher.close();
		} catch (CorruptIndexException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	
	public void searchByTermRange(String field,String start,String end,int num) {
		try {
			IndexSearcher searcher = getSearcher();
			Query query = new TermRangeQuery(field,start,end,true, true);
			TopDocs tds = searcher.search(query, num);
			System.out.println("一共查询了:"+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs) {
				Document doc = searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"---->"+
						doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
						doc.get("attach")+","+doc.get("date"));
			}
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	public void searchByNumricRange(String field,int start,int end,int num) {
		try {
			IndexSearcher searcher = getSearcher();
			Query query = NumericRangeQuery.newIntRange(field,start, end,true,true);
			TopDocs tds = searcher.search(query, num);
			System.out.println("一共查询了:"+tds.totalHits);
			for(ScoreDoc sd:tds.scoreDocs) {
				Document doc = searcher.doc(sd.doc);
				System.out.println(doc.get("id")+"---->"+
						doc.get("name")+"["+doc.get("email")+"]-->"+doc.get("id")+","+
						doc.get("attach")+","+doc.get("date"));
			}
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
}

测试类

package org.itat.test;

import org.itat.index.SearcherUtil;
import org.junit.Before;
import org.junit.Test;

public class TestSearcher {

	private SearcherUtil su;
	
	@Before
	public void init()
	{
		su=new SearcherUtil();
		
	}
	
	@Test
	public void searchByTerm()
	{
//		su.searchByTerm("content","i",10);//I like soccer 精确查找//6条结果
		su.searchByTerm("name","zhangsan",10);
	}
	
	@Test
	public void searchByTermRange()
	{
//		su.searchByTermRange("id","1","6",10);
		su.searchByTermRange("name","a","z",10);

	}
	
	@Test
	public void searchByNumRange() {
		su.searchByNumricRange("attach",2,10, 5);
	}
}