lucene(三) lucene搜索

一、搜索知识架构

                                                    

二、例子

import java.io.File;
import java.io.IOException;
import java.text.ParseException;
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.queryParser.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.NumericRangeQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
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.search.WildcardQuery;
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 SearcherUtil {
	private Directory directory;
	private IndexReader reader;
	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 Date[] dates = null;
	private int[] attachs = {2,3,1,4,5,5};
	private String[] names = {"zhangsan","lisi","john","jetty","mike","jake"};
	private Map<String,Float> scores = new HashMap<String,Float>();
	
	public SearcherUtil() {
//		directory = new RAMDirectory();//内存索引
		try {
			directory = FSDirectory.open(new File("d:/lucenc/index03"));//硬盘索引
			setDates();
			scores.put("itat.org",2.0f);
			scores.put("zttc.edu", 1.5f);
			index();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	private void setDates() {
		SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd");
		try {
			dates = new Date[ids.length];
			dates[0] = sdf.parse("2010-02-19");
			dates[1] = sdf.parse("2012-01-11");
			dates[2] = sdf.parse("2011-09-19");
			dates[3] = sdf.parse("2010-12-22");
			dates[4] = sdf.parse("2012-01-01");
			dates[5] = sdf.parse("2011-05-19");
		} catch (ParseException e) {
			e.printStackTrace();
		}
	}

	/** 建立索引
	 * @author
	 * @param
	 * @return
	 */
	public void index() {
		IndexWriter writer = null;
		try {
			writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
			writer.deleteAll();
			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));
				//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(0.5f);
				}
				writer.addDocument(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();
			}
		}
	}
	/** 得到IndexSearcher
	 * @author
	 * @param
	 * @return
	 */
	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) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return null;
	}
	
	public IndexSearcher getSearcher(Directory directory) {
		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) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
		return null;
	}
	/** 精确查询
	 * @author
	 * @param
	 * @return
	 */
	public void searchByTerm(String field,String name,int num) {
		try {
			IndexSearcher searcher = getSearcher();
			Query query = new TermQuery(new Term(field,name));
			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();
		}
	}
	/** 范围查询
	 * @author
	 * @param
	 * @return
	 */
	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();
		}
	}
	/** 数字范围查询
	 * @author
	 * @param
	 * @return
	 */
	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();
		}
	}
	/** 前缀查询
	 * @author
	 * @param
	 * @return
	 */
	public void searchByPrefix(String field,String value,int num) {
		try {
			IndexSearcher searcher = getSearcher();
			Query query = new PrefixQuery(new Term(field,value));
			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();
		}
	}
	/** 通配符查询
	 * @author
	 * @param
	 * @return
	 */
	public void searchByWildcard(String field,String value,int num) {
		try {
			IndexSearcher searcher = getSearcher();
			//在传入的value中可以使用通配符:?和*,?表示匹配一个字符，*表示匹配任意多个字符
			Query query = new WildcardQuery(new Term(field,value));
			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();
		}
	}
	/** 连接子查询
	 * @author
	 * @param
	 * @return
	 */
	public void searchByBoolean(int num) {
		try {
			IndexSearcher searcher = getSearcher();
			BooleanQuery query = new BooleanQuery();
			/*
			 * BooleanQuery可以连接多个子查询
			 * Occur.MUST表示必须出现
			 * Occur.SHOULD表示可以出现
			 * Occur.MUSE_NOT表示不能出现
			 */
			query.add(new TermQuery(new Term("name","zhangsan")), Occur.MUST_NOT);
			query.add(new TermQuery(new Term("content","game")),Occur.SHOULD);
			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();
		}
	}
	
	/** 根据短语和距离查询
	 * @author
	 * @param
	 * @return
	 */
	public void searchByPhrase(int num) {
		try {
			IndexSearcher searcher = getSearcher();
			PhraseQuery query = new PhraseQuery();
			query.setSlop(3);
			query.add(new Term("content","pingpeng"));
			//第一个Term
			query.add(new Term("content","i"));
			//产生距离之后的第二个Term
//			query.add(new Term("content","football"));
			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();
		}
	}
	
	/** 通过短语查询，用得最多，以上都可以实现，具体的query实现不同的功能
	 * @author
	 * @param
	 * @return
	 */
	public void searchByQueryParse(Query query,int num) {
		try {
			IndexSearcher searcher = getSearcher();
			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")+"=="+sd.score);
			}
			searcher.close();
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
}

测试类：

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

import org.apache.commons.io.FileUtils;
import org.apache.commons.io.FilenameUtils;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Query;
import org.apache.lucene.util.Version;
import org.itat.index.FileIndexUtils;
import org.itat.index.SearcherUtil;
import org.junit.Before;
import org.junit.Test;

public class TestSearch {
	private SearcherUtil su;
	@Before
	public void init() {
		su = new SearcherUtil();
	}
	
	@Test
	public void testCopyFiles() {
		try {
			File file = new File("d:/lucene/example/");
			for(File f:file.listFiles()) {
				String destFileName = FilenameUtils.getFullPath(f.getAbsolutePath())+
						FilenameUtils.getBaseName(f.getName())+".she";
				FileUtils.copyFile(f, new File(destFileName));
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	@Test
	public void searchByTerm() {
		su.searchByTerm("content","i",3);
	}
	
	@Test
	public void searchByTermRange() {
		//查询name以a开头和s结尾的
//		su.searchByTermRange("name","a","s",10);
		//由于attachs是数字类型，使用TermRange无法查询
		su.searchByTermRange("attach","2","10", 5);
	}
	
	@Test
	public void searchByNumRange() {
		su.searchByNumricRange("attach",2,10, 5);
	}
	
	@Test
	public void searchByPrefix() {
		su.searchByPrefix("content", "s", 10);
	}
	
	@Test
	public void searchByWildcard() {
		//匹配@itat.org结尾的所有字符
		su.searchByWildcard("email", "*@itat.org", 10);
		//匹配j开头的有三个字符的name
		su.searchByWildcard("name", "j???", 10);
	}
	
	@Test
	public void searchByBoolean() {
		su.searchByBoolean(10);
	}
	
	@Test
	public void searchByPhrase() {
		su.searchByPhrase(10);
	}
	
	@Test
	public void searchByQueryParse() throws ParseException {
		//1、创建QueryParser对象,默认搜索域为content
		QueryParser parser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
		//改变空格的默认操作符，以下可以改成AND
		//parser.setDefaultOperator(Operator.AND);
		//开启第一个字符的通配符匹配，默认关闭因为效率不高
		parser.setAllowLeadingWildcard(true);
		//搜索content中包含有like的
		Query query = parser.parse("like");
		
		//有basketball或者football的，空格默认就是OR
		query = parser.parse("basketball football");
		
		//改变搜索域为name为mike
		//query = parser.parse("content:like");
		
		//同样可以使用*和?来进行通配符匹配
//		query = parser.parse("name:j*");
		
		//通配符默认不能放在首位
//		query = parser.parse("email:*@itat.org");
		
		//匹配name中没有mike但是content中必须有football的，+和-要放置到域说明前面
		query = parser.parse("- name:mike + like");
		
		//匹配一个区间，注意:TO必须是大写
		//query = parser.parse("id:[1 TO 6]");
		
		//闭区间匹配只会匹配到2
		//query = parser.parse("id:{1 TO 3}");
		
		//完全匹配I Like Football的
		//query = parser.parse("\"I like football\"");
		
		//匹配I 和football之间有一个单词距离的
		//query = parser.parse("\"I football\"~1");
		
		//模糊查询
		//query = parser.parse("name:make~");
		
		//没有办法匹配数字范围（自己扩展Parser）
		//query = parser.parse("attach:[2 TO 10]");
		su.searchByQueryParse(query, 10);
	}
	
	@Test
	public void indexFile() {
		FileIndexUtils.index(true);
	}
	
	@Test
	public void testSearchPage01() {
		su.searchPage("java", 2,20);
		System.out.println("-------------------------------");
//		su.searchNoPage("java");
		su.searchPageByAfter("java", 2,20);
	}
	
	@Test
	public void testSearchPage02() {
		su.searchPageByAfter("java", 3,20);
	}
	
}