Lucene5.3.1最新版Query测试

1.作者

caicongyang:http://blog.csdn.net/caicongyang

2.代码（注释清晰）

package com.ccy.lucene.app;

import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;

/**
 * 
 * <p> 
 * Title: QueryTest.java 
 * Package com.ccy.lucene.app 
 * </p>
 * <p>
 * Description: 各种Query测试
 * <p>
 * @author Tom.Cai
 * @created 2015-11-10 下午8:17:50 
 * @version V1.0 
 *
 */
public class QueryTest {
	
	//索引文件
    String indexPath = "D:\\newWork\\lucene5.3\\luceneIndex";
	//分词器
    Analyzer analyzer = new SmartChineseAnalyzer();// 词库分词

    /**
     * 关键字查询(英文经过分词器全部为小写)
     * @throws Exception
     */
    @Test
	public void testTermQuery() throws Exception{
		Term term = new Term("content", "room");
		TermQuery query = new TermQuery(term);
		search(query);
	}
    
    /**
     * 短语查询
     * @throws Exception
     */
	@Test
	public void testPhraseQuery() throws Exception {
		PhraseQuery.Builder builder = new PhraseQuery.Builder();
		builder.add(new Term("content", "房间"));
		builder.add(new Term("content", "安排"));
		builder.setSlop(5);//中级差几个字
		PhraseQuery phraseQuery = builder.build();
		search(phraseQuery);
	}
	
	/**
	 * 通配符查询
	 * '?' 代表一个字符， '*' 代表0个或多个字符
	 * @throws Exception
	 */
	@Test
	public void testWildcardQuery() throws Exception {
		Term term = new Term("content", "roo?");
		Query query = new WildcardQuery(term);
		search(query);
	}
	
	/**
	 * 布尔关联查询
	 * @throws Exception
	 */
	@Test
	public void testBooleanQuery() throws Exception {
		// 条件1
		PhraseQuery.Builder builder = new PhraseQuery.Builder();
		builder.add(new Term("content", "房间"));
		builder.add(new Term("content", "安排"));
		builder.setSlop(5);//中间差几个字
		PhraseQuery query1 = builder.build();

		// 条件2
		Term term = new Term("content", "总统");
		TermQuery query2 = new TermQuery(term);

		// 组合
		BooleanQuery.Builder bbuilder = new BooleanQuery.Builder();
		bbuilder.add(query1, Occur.MUST);
		bbuilder.add(query2, Occur.MUST);
		BooleanQuery boolQuery = bbuilder.build();
		search(boolQuery);
	}
	
	
	public void search(Query query) throws Exception{
		
		//1、打开索引库
		IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(indexPath)));
		IndexSearcher searcher = new IndexSearcher(reader);
		
		//3、根据关键词进行搜索  
        TopDocs topDocs = searcher.search(query, 100);;  
        int recordCount = topDocs.totalHits;
		System.out.println("总共有【" + recordCount + "】条匹配结果");
		List<Document> recordList = new ArrayList<Document>();
		//准备高亮器
		Formatter formatter = new SimpleHTMLFormatter("<font color='red'>", "</font>");
		Scorer scorer = new QueryScorer(query);
		Highlighter highlighter = new Highlighter(formatter, scorer);
		// 摘要
		Fragmenter fragmenter = new SimpleFragmenter(50);
		highlighter.setTextFragmenter(fragmenter);
		// 3，取出当前页的数据
		int end = Math.min(10, topDocs.totalHits);
		for (int i = 0; i < end; i++) {
			ScoreDoc scoreDoc = topDocs.scoreDocs[i];
			int docSn = scoreDoc.doc; // 文档内部编号
			Document doc = searcher.doc(docSn); // 根据编号取出相应的文档
			// 返回高亮后的结果，如果当前属性值中没有出现关键字，会返回 null
			String hc = highlighter.getBestFragment(analyzer, "content", doc.get("content"));
			if (hc == null) {
				String content = doc.get("content");
				int endIndex = Math.min(50, content.length());
				hc = content.substring(0, endIndex);// 最多前50个字符
			}
			doc.removeField("content");
			doc.add(new Field("content", hc, TextField.TYPE_STORED));
			recordList.add(doc);
		}
		for (Document document : recordList) {
			System.out.println("------------------------------");
			System.out.println("name     = " + document.get("name"));
			System.out.println("content  = " + document.get("content"));
			System.out.println("size     = " + document.get("size"));
			System.out.println("path     = " + document.get("path"));
		}
        
        reader.close();  
	}
}

3.我的博客

我的博客： http://blog.csdn.net/caicongyang