lucene 5.3.1

最新推荐文章于 2022-11-11 11:39:55 发布

爱笑的T_T

最新推荐文章于 2022-11-11 11:39:55 发布

阅读量656

点赞数

文章标签： lucene

依赖包

<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-core</artifactId>
		<version>5.3.1</version>
	</dependency>
	
	<dependency>
	<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-queryparser</artifactId>
		<version>5.3.1</version>
	</dependency>
	
	<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-analyzers-common</artifactId>
		<version>5.3.1</version>
	</dependency>
	
	<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-analyzers-smartcn</artifactId>
		<version>5.3.1</version>
	</dependency>
	
	<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-highlighter</artifactId>
		<version>5.3.1</version>
	</dependency>

索引类

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class Indexer {
	private Integer ids[] = { 1, 2, 3 };
	private String citys[] = { "青岛", "南京", "上海" };
	private String descs[] = { "青岛是一个美丽的城市。",
			"南京是一个有文化的城市。南京是一个文化的城市南京，简称宁，是江苏省会，地处中国东部地区，长江下游，濒江近海。全市下辖11个区，总面积6597平方公里，2013年建成区面积752.83平方公里，常住人口818.78万，其中城镇人口659.1万人。[1-4] “江南佳丽地，金陵帝王州”，南京拥有着6000多年文明史、近2600年建城史和近500年的建都史，是中国四大古都之一，有“六朝古都”、“十朝都会”之称，是中华文明的重要发祥地，历史上曾数次庇佑华夏之正朔，长期是中国南方的政治、经济、文化中心，拥有厚重的文化底蕴和丰富的历史遗存。[5-7] 南京是国家重要的科教中心，自古以来就是一座崇文重教的城市，有“天下文枢”、“东南第一学”的美誉。截至2013年，南京有高等院校75所，其中211高校8所，仅次于北京上海；国家重点实验室25所、国家重点学科169个、两院院士83人，均居中国第三。[8-10] 。",
			"上海是一个繁华的城市。" };

	private Directory dir;

	/**
	 * 获取IndexWriter实例
	 */
	private IndexWriter getWriter() throws Exception {
		//Analyzer analyzer = new StandardAnalyzer();
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
		IndexWriter writer = new IndexWriter(dir, iwc);
		return writer;
	}

	/**
	 * 生成索引
	 */
	public void index(String indexDir) throws Exception {
		dir = FSDirectory.open(Paths.get(indexDir));
		IndexWriter writer = getWriter();
		for (int i = 0; i < ids.length; i++) {
			Document doc = new Document();
			doc.add(new IntField("id", ids[i], Field.Store.YES));
			doc.add(new StringField("city", citys[i], Field.Store.YES));
			doc.add(new TextField("desc", descs[i], Field.Store.YES));
			writer.addDocument(doc);
		}
		writer.close();
	}

	public static void main(String[] args) {
		try {
			new Indexer().index("D:\\Lucene");
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}

高亮查询

import java.io.StringReader;
import java.nio.file.Paths;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.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.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.After;
import org.junit.Before;

public class SearchTest {
	
	public static void search(String indexDir,String q) throws Exception{
	 	Directory dir = FSDirectory.open(Paths.get(indexDir));
	    IndexReader reader = DirectoryReader.open(dir);
	    IndexSearcher is = new IndexSearcher(reader);
	    
	    SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
	    QueryParser parser = new QueryParser("desc",analyzer);
	    Query query =parser.parse(q);
	    TopDocs hits = is.search(query, 10);
	    
		System.out.println("匹配 "+q+"查询到"+hits.totalHits+"个记录");
		
		QueryScorer scorer = new QueryScorer(query);
		Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
		SimpleHTMLFormatter simpleHTMLFormatter = new 
				SimpleHTMLFormatter("<b><font color='red'>","</font></b>");
		Highlighter highlighter = new Highlighter(simpleHTMLFormatter,scorer);
		
		highlighter.setTextFragmenter(fragmenter);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc = is.doc(scoreDoc.doc);
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
			System.out.println(doc.get("city"));
			String desc = doc.get("desc");
			if(desc!=null){
				TokenStream tokenStream =analyzer.tokenStream("desc", new StringReader(desc));
				System.out.println(highlighter.getBestFragment(tokenStream,desc));
				
			}
		}
	}

	@Before
	public void setUp() throws Exception {
	}

	@After
	public void tearDown() throws Exception {
	}

	
	public static void main(String[] args) {
		String indexDir="D:\\Lucene";
		String q="南京文明";
		try {
			search(indexDir,q);
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}

package com.java00.lucene;

import java.io.StringReader;
import java.nio.file.Paths;
import java.util.LinkedList;
import java.util.List;

import org.apache.lucene.analysis.TokenStream;
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.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.BooleanClause.Occur;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.BooleanQuery.Builder;
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.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import com.java00.entity.Blog;
import com.java00.util.DateUtil;
import com.java00.util.StringUtil;

/**
 * 博客索引类
 * 
 *
 */
public class BlogIndex {
	private Directory dir;
	
	/**
	 * 获取IndexWriter实例
	 */
	public IndexWriter getWriter() throws Exception {
		dir = FSDirectory.open(Paths.get("D://Lucene"));
		SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
		IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
		IndexWriter indexWriter = new IndexWriter(dir, iwc);

		return indexWriter;
	}

	/**
	 * 添加博客索引
	 */
	public void addIndex(Blog blog) throws Exception {
		IndexWriter indexWriter = getWriter();
		Document doc = new Document();
		doc.add(new StringField("id", String.valueOf(blog.getId()), Field.Store.YES));
		doc.add(new TextField("title", blog.getTitle(), Field.Store.YES));
		doc.add(new StringField("releaseDate", DateUtil.formatDate(blog.getReleaseDate(), "yyyy-MM-dd"),
				Field.Store.YES));
		doc.add(new TextField("content", blog.getContent(), Field.Store.YES));
		
		indexWriter.addDocument(doc);
		indexWriter.close();
	}

	/**
	 * 查询博客信息
	 */
	public List<Blog> searchBlog(String q) throws Exception{
		dir =FSDirectory.open(Paths.get("D://Lucene"));
		DirectoryReader reader = DirectoryReader.open(dir);
		IndexSearcher is = new IndexSearcher(reader);
		Builder booleanQuery = new BooleanQuery.Builder();
		SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
		QueryParser parser = new QueryParser("title",analyzer);
		Query query = parser.parse(q);
		
		QueryParser parser2 = new QueryParser("content",analyzer);
		Query query2 = parser.parse(q);
		
		booleanQuery.add(query, Occur.SHOULD);
		booleanQuery.add(query, Occur.SHOULD);
		
		TopDocs hits = is.search(booleanQuery.build(), 100);
		QueryScorer scorer = new QueryScorer(query);
		Fragmenter fragmenter =new SimpleSpanFragmenter(scorer);
		SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
		Highlighter highlighter = new Highlighter(simpleHTMLFormatter, scorer);
		highlighter.setTextFragmenter(fragmenter);
		
		List<Blog> blogList = new LinkedList<Blog>();
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc = is.doc(scoreDoc.doc);
			Blog blog = new Blog();
			blog.setId(Integer.parseInt(doc.get("id")));
			blog.setReleaseDateStr(doc.get("releaseDate"));
			String title = doc.get("title");
			String content = doc.get("content");
			if(title!=null){
				TokenStream tokenStream = analyzer.tokenStream("title", new StringReader(title));
				String hTitle = highlighter.getBestFragment(tokenStream, title);
				if(StringUtil.isEmpty(hTitle)){
					blog.setTitle(title);
				}else{
					blog.setTitle(hTitle);
				}
				
			}
			if(content!=null){
				TokenStream tokenStream = analyzer.tokenStream("content", new StringReader(title));
				String hContent = highlighter.getBestFragment(tokenStream, title);
				if(StringUtil.isEmpty(hContent)){
					if(hContent.length()<200){
						blog.setContent(hContent);
					}else{
						blog.setContent(hContent.substring(0, 200));
					}
			
				}else{
					blog.setTitle(hContent);
				}
				
			}
			blogList.add(blog);
		}
		return blogList;
	}

}