全文检索Lucene（三）--中文分词与高亮显示

<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-highlighter</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>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
</dependency>
</dependencies>

package com.feiyang.lucene3;

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
* @return
* @throws Exception
*/
private IndexWriter getWriter()throws Exception{
//Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
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); // 添加文档
}
writer.close();
}

public static void main(String[] args) throws Exception {
new Indexer().index("D:\\lucene6");
}

}

package com.feiyang.lucene3;

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);
//中文分词器
SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
QueryParser parser=new QueryParser("desc", analyzer);
//创建查询规则
Query query=parser.parse(q);
long start=System.currentTimeMillis();
//获取命中文档
TopDocs hits=is.search(query, 10);
long end=System.currentTimeMillis();
System.out.println("匹配 "+q+" ，总共花费"+(end-start)+"毫秒"+"查询到"+hits.totalHits+"个记录");

//创建QueryScoer
QueryScorer scorer=new QueryScorer(query);//获得
Fragmenter fragmenter=new SimpleSpanFragmenter(scorer);
//自定义高亮显示格式
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));
//获取最高分的文本片段，即摘要
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();
}
}
}