15-使用NRTManager和TimeManager实现近实时搜索

TestIndex.java

package org.itat.lucene.test;

import org.itat.lucene.util.IndexUtil;
import org.junit.Test;

/**
 * @ProjectName:lucene_index
 * @ClassName:TestIndex
 * @Description:索引
 * @date: 2015-4-20下午06:07:37
 * @author: 半仙儿
 * @version: V1.0
 * @date:2015-4-20下午06:07:37
 */
public class TestIndex {

	/**
	 *@MethodName:testIndex
	 *@Description:创建索引
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-27下午01:56:51
	 */
	@Test
	public void testIndex() {
		IndexUtil iu = new IndexUtil();
		iu.index();
	}

	/**
	 *@MethodName:testQuery
	 *@Description:查询索引有多少条 numDocs\maxDocs\deleteDocs
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-27下午01:56:44
	 */
	@Test
	public void testQuery() {
		IndexUtil iu = new IndexUtil();
		iu.query();
	}



	/**
	 *@MethodName:testSearch02
	 *@Description:NRT搜索
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-27下午02:13:11
	 */
	@Test
	public void testSearch02() {
		IndexUtil iu = new IndexUtil();
		for (int i = 0; i < 5; i++) {
			// 进行查询
			iu.searcher02();
			System.out.println("------------------------------------");
			// 删除id为11的
			iu.delete();
			if (i == 2) {
				// 更新
				iu.update();
			}
			try {
				Thread.sleep(2000);
			} catch (Exception e) {
				e.printStackTrace();
			}
		}
		// 提交
		iu.commit();
	}

}

IndexUtil.java

package org.itat.lucene.util;

import java.io.File;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.GregorianCalendar;
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.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.NRTManager;
import org.apache.lucene.search.NRTManagerReopenThread;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.SearcherManager;
import org.apache.lucene.search.SearcherWarmer;
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.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" };
	// 邮件日期
	private Date[] dates = null;
	private int[] attachs = { 2, 3, 1, 4, 5, 5 };
	private String[] names = { "zhangsan", "lisi", "john", "jetty", "mike",
			"jake" };
	private Directory directory = null;

	// NRT搜索
	private SearcherManager mgr = null;
	private NRTManager nrtMgr = null;
	private IndexWriter writer = null;
	// 加权
	private Map<String, Float> scores = new HashMap<String, Float>();

	// 构造方法实例化Directory
	public IndexUtil() {
		try {
			setDates();
			scores.put("itat.org", 2.0f);
			scores.put("zttc.edu", 1.5f);
			directory = FSDirectory.open(new File("d:/lucene/index02"));
			// mgr = new SearcherManager(directory, new SearcherWarmer() {
			// @Override
			// public void warm(IndexSearcher s) throws IOException {
			// System.out.println("has changed");
			// }
			// }, Executors.newCachedThreadPool());
			writer = new IndexWriter(directory, new IndexWriterConfig(
					Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
			nrtMgr = new NRTManager(writer, new SearcherWarmer() {

				@Override
				public void warm(IndexSearcher arg0) throws IOException {
					System.out.println("reopen");
				}
			});

			// 0.0025*10000=25秒重新打开一次searcher
			NRTManagerReopenThread reopen = new NRTManagerReopenThread(nrtMgr,
					5.0, 0.025);
			// 后台进程
			reopen.setDaemon(true);
			reopen.setName("Nrt Manager Reopen Thread");
			// 启动NRTManager的reopen线程
			reopen.start();
			// true表示引起索引的更新，该提交的进行提交
			mgr = nrtMgr.getSearcherManager(true);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 *@MethodName:delete
	 *@Description:删除索引
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-14上午09:58:24
	 */
	public void delete() {
		try {
			// 删除全部索引
			// writer.deleteAll();
			nrtMgr.deleteDocuments(new Term("id", "11"));
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 *@MethodName:update
	 *@Description:更新索引
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-14上午09:58:42
	 */
	public void update() {
		try {
			// lucene的更新是先删除再添加
			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));
			nrtMgr.updateDocument(new Term("id", "1"), doc);
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 *@MethodName:query
	 *@Description:查询索引
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-14上午09:58:52
	 */
	public void query() {
		try {
			IndexReader reader = IndexReader.open(directory);
			// 通过reader可以有效的获取到文档的数量
			System.out.println("numDocs:" + reader.numDocs());
			System.out.println("maxDocs:" + reader.maxDoc());
			System.out.println("deleteDocs:" + reader.numDeletedDocs());
			reader.close();
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 *@MethodName:index
	 *@Description:创建索引
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-14上午09:59:01
	 */
	public void index() {
		IndexWriter writer = null;
		try {

			writer = new IndexWriter(directory, new IndexWriterConfig(
					Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
			Document doc = null;
			// 清空
			writer.deleteAll();
			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));
				doc.add(new NumericField("attach", Field.Store.YES, true)
						.setIntValue(attachs[i]));
				doc.add(new NumericField("date", Field.Store.YES, true)
						.setLongValue(dates[i].getTime()));
				// 获取邮箱后缀
				String et = emails[i].substring(emails[i].lastIndexOf("@") + 1);
				System.out.println(et);
				if (scores.containsKey(et)) {
					doc.setBoost(scores.get(et));
				} else {
					doc.setBoost(0.5f);
				}
				writer.addDocument(doc);
			}
		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			if (writer != null) {
				try {
					writer.close();
				} catch (Exception e) {
					e.printStackTrace();
				}
			}
		}
	}

	public void setDates() {
		SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd");
		dates = new Date[ids.length];
		try {
			dates[0] = sdf.parse("2010-02-19");
			dates[1] = sdf.parse("2012-01-11");
			dates[2] = sdf.parse("2010-09-19");
			dates[3] = sdf.parse("2010-12-22");
			dates[4] = sdf.parse("2012-01-01");
			dates[5] = sdf.parse("2011-05-19");
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 *@MethodName:formateNumToDateString
	 *@Description:将字符串的数字格式的日期转换为日期格式
	 *@param num
	 *@author:半仙儿
	 *@return String
	 *@date:2015-4-14下午04:03:18
	 */
	public String formateNumToDateString(Long num) {
		Date dat = new Date(num);
		GregorianCalendar gc = new GregorianCalendar();
		gc.setTime(dat);
		java.text.SimpleDateFormat format = new java.text.SimpleDateFormat(
				"yyyy-MM-dd");
		String sb = format.format(gc.getTime());
		return sb;
	}

	/**
	 *@MethodName:searcher02
	 *@Description:NTR实时搜索
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-27下午03:04:17
	 */
	public void searcher02() {
		// 使用searcherManager进行获取IndexSearcher------NRT
		IndexSearcher searcher = mgr.acquire();
		try {
			// 是否要重新打开一个searcher
			// mgr.maybeReopen();
			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(doc.get("id") + "---->" + doc.get("name")
						+ "[" + doc.get("email") + "]-->" + doc.get("id") + ","
						+ doc.get("attach") + "," + doc.get("date"));
			}

		} catch (Exception e) {
			e.printStackTrace();
		} finally {
			try {
				// 释放
				mgr.release(searcher);
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}

	/**
	 *@MethodName:commit
	 *@Description:提交操作
	 *@author:半仙儿
	 *@return void
	 *@date:2015-4-27下午02:55:56
	 */
	public void commit() {
		try {
			writer.commit();
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}