1. 程式人生 > >Lucene高亮顯示及中文分詞

Lucene高亮顯示及中文分詞

直接demo,不廢話

建立一個Maven

在pom.xml貼上依賴

<dependencies>
  	<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>
	
	
	
	<dependency>
		<groupId>junit</groupId>
		<artifactId>junit</artifactId>
		<version>4.12</version>
	</dependency>
生成索引:
package com.java1234.lucene;


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[]={"青島","南京","上海"};
	private String descs[]={
			"青島是一個美麗的城市。",
			"南京是一個有文化的城市。南京是一個文化的城市南京,簡稱寧,是江蘇省會,地處中國東部地區,長江下游,瀕江近海。全市下轄11個區,總面積6597平方公里,2013年建成區面積752.83平方公里,常住人口818.78萬,其中城鎮人口659.1萬人。[1-4] “江南佳麗地,金陵帝王州”,南京擁有著6000多年文明史、近2600年建城史和近500年的建都史,是中國四大古都之一,有“六朝古都”、“十朝都會”之稱,是中華文明的重要發祥地,歷史上曾數次庇佑華夏之正朔,長期是中國南方的政治、經濟、文化中心,擁有厚重的文化底蘊和豐富的歷史遺存。[5-7] 南京是國家重要的科教中心,自古以來就是一座崇文重教的城市,有“天下文樞”、“東南第一學”的美譽。截至2013年,南京有高等院校75所,其中211高校8所,僅次於北京上海;國家重點實驗室25所、國家重點學科169個、兩院院士83人,均居中國第三。[8-10] 。",
			"上海是一個繁華的城市。"
	};
	
	private Directory dir;
	
	/**
	 * 獲取IndexWriter例項
	 * @return
	 * @throws Exception
	 */
	private IndexWriter getWriter()throws Exception{
		//Analyzer analyzer=new StandardAnalyzer(); // 標準分詞器
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
		IndexWriter writer=new IndexWriter(dir, iwc);
		return writer;
	}
	
	/**
	 * 生成索引
	 * @param indexDir
	 * @throws Exception
	 */
	private 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); // 新增文件
		}
		writer.close();
	}
	
	
	public static void main(String[] args) throws Exception {
		new Indexer().index("D:\\lucene6");
	}
	
}

開始查詢
package com.java1234.lucene;

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

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
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.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;

public class Searcher {

	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);
		// Analyzer analyzer=new StandardAnalyzer(); // 標準分詞器
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		QueryParser parser=new QueryParser("desc", analyzer);
		Query query=parser.parse(q);
		long start=System.currentTimeMillis();
		TopDocs hits=is.search(query, 10);
		long end=System.currentTimeMillis();
		System.out.println("匹配 "+q+" ,總共花費"+(end-start)+"毫秒"+"查詢到"+hits.totalHits+"個記錄");
		
		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"));
			String desc=doc.get("desc");
			if(desc!=null){
				TokenStream tokenStream=analyzer.tokenStream("desc", new StringReader(desc));
				System.out.println(highlighter.getBestFragment(tokenStream, desc));
			}
		}
		reader.close();
	}
	
	public static void main(String[] args) {
		String indexDir="D:\\lucene6";
		String q="南京文明";
		try {
			search(indexDir,q);
		} catch (Exception e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
}


結果顯示:


放在網頁上效果展示更佳,ok基本完事