今天看了看Lucene,其实好早以前就通过买的参考书学习过了。现在又重温一下。
关于Lucene2014年底最新的版本是4.10的。但是4.8+的版本都只支持JDK1.7,4.0的版本是支持JDK1.6的。只是4.0版本所用的中文分词都不太好,所以这里还是介绍一下常用的3.5版本吧。
3.5版本采用的分词器是IKAnalyzer。这个在4.0已经不支持了。
还是先说JAR文件吧,工程中使用的JAR文件:lucene-core-3.5.0.jar、lucene-analyzers-3.5.0.jar、lucene-highlighter-3.5.0.jar、IKAnalyzer3.2.5Stable.jar其中有核心包、分词包和高亮包。
工程中写了两个类,一个是创建索引的类,一个是搜索的类:
创建索引:
package com.zyujie.lucene;
import java.io.File;
import java.util.ArrayList;
import java.util.List;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;
public class CreateIndexFile {
/*
* 创建索引
*/
public void createIndex() throws Exception {
String filePath = "D:\\lucene\\cityDemo\\cityIndex"; //索引文件夹目录
//创建索引之前,先将旧的索引文件清空
this.deleteIndexFile(filePath);
File indexFile = new File(filePath); //索引文件存放的目录
Analyzer analyzer = new IKAnalyzer(); //IKAnalyzer支持中文分词器
IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35, analyzer); //配置项
iwc.setOpenMode(OpenMode.CREATE_OR_APPEND); //模式
IndexWriter indexWriter = null;
try {
indexWriter = new IndexWriter(FSDirectory.open(indexFile), iwc); //打开索引文件夹
List cityList = this.getCityDatas();
for (int i = 0; i < cityList.size(); i++) {
Document doc = (Document) cityList.get(i);
indexWriter.addDocument(doc); //将doc生成的数据添加到indexWriter,写入索引文件
}
System.out.println("索引已经创建!");
} catch (Exception e) {
e.printStackTrace();
}
finally {
indexWriter.close(); // 需关闭
}
}
/*
* 删除索引文件
*/
public void deleteIndexFile(String indexFilePath){
File file = new File(indexFilePath);
String[] filelist = file.list(); //获取下面的所有索引文件
for (int i = 0; i < filelist.length; i++) {
File delfile = new File(indexFilePath + "\\" + filelist[i]);
delfile.delete(); //删除所有索引文件
}
System.out.println("已清空索引文件");
}
/*
* 造数据
*/
public List getCityDatas(){
List cityList = new ArrayList();
//创建Document对象
Document bjdoc = new Document();
bjdoc.add(new Field("id", "010", Store.YES, Index.NOT_ANALYZED)); //Store.YES存入索引文件,Index.NOT_ANALYZED不进行分词
bjdoc.add(new Field("name", "北京", Store.YES, Index.ANALYZED));
bjdoc.add(new Field("area", "华北地区", Store.YES, Index.ANALYZED));
bjdoc.add(new Field("population", "2114.8万", Store.YES, Index.NOT_ANALYZED));
bjdoc.add(new Field("description", "中华人民共和国的首都、直辖市和国家中心城市,也是中国的政治、文化、科教和国际交往中心", Store.YES, Index.ANALYZED));
Document shdoc = new Document();
shdoc.add(new Field("id", "021", Store.YES, Index.NOT_ANALYZED));
shdoc.add(new Field("name", "上海", Store.YES, Index.ANALYZED));
shdoc.add(new Field("area", "华东地区", Store.YES, Index.ANALYZED));
shdoc.add(new Field("population", "2500万", Store.YES, Index.NOT_ANALYZED));
shdoc.add(new Field("description", "上海(Shanghai),简称“沪”,有“东方巴黎”的美称,中华人民共和国直辖市之一", Store.YES, Index.ANALYZED));
Document gzdoc = new Document();
gzdoc.add(new Field("id", "020", Store.YES, Index.NOT_ANALYZED));
gzdoc.add(new Field("name", "广州", Store.YES, Index.ANALYZED));
gzdoc.add(new Field("area", "华南地区", Store.YES, Index.ANALYZED));
gzdoc.add(new Field("population", "1292.68万", Store.YES, Index.NOT_ANALYZED));
gzdoc.add(new Field("description", "广州,简称穗,别称羊城、花城,广东省省会,位于广东省中南部", Store.YES, Index.ANALYZED));
Document tjdoc = new Document();
tjdoc.add(new Field("id", "022", Store.YES, Index.NOT_ANALYZED));
tjdoc.add(new Field("name", "天津", Store.YES, Index.ANALYZED));
tjdoc.add(new Field("area", "华北地区", Store.YES, Index.ANALYZED));
tjdoc.add(new Field("population", "11946.88万", Store.YES, Index.NOT_ANALYZED));
tjdoc.add(new Field("description", "天津,简称津,中华人民共和国直辖市、中国国家中心城市、中国北方经济中心", Store.YES, Index.ANALYZED));
Document cddoc = new Document();
cddoc.add(new Field("id", "028", Store.YES, Index.NOT_ANALYZED));
cddoc.add(new Field("name", "成都", Store.YES, Index.ANALYZED));
cddoc.add(new Field("area", "西南地区", Store.YES, Index.ANALYZED));
cddoc.add(new Field("population", "1417万", Store.YES, Index.NOT_ANALYZED));
cddoc.add(new Field("description", "成都,四川省省会[1] ,成都位于中国华西地区东部,成都平原腹地,古为蜀国地", Store.YES, Index.ANALYZED));
Document cqdoc = new Document();
cqdoc.add(new Field("id", "023", Store.YES, Index.NOT_ANALYZED));
cqdoc.add(new Field("name", "重庆", Store.YES, Index.ANALYZED));
cqdoc.add(new Field("area", "西南地区", Store.YES, Index.ANALYZED));
cqdoc.add(new Field("population", "2970万", Store.YES, Index.NOT_ANALYZED));
cqdoc.add(new Field("description", "重庆,简称巴和渝,别称山城、渝都、桥都,中华人民共和国直辖市", Store.YES, Index.ANALYZED));
cityList.add(bjdoc);
cityList.add(shdoc);
cityList.add(gzdoc);
cityList.add(tjdoc);
cityList.add(cddoc);
cityList.add(cqdoc);
return cityList;
}
}
搜索类:
package com.zyujie.lucene;
import java.io.File;
import java.io.IOException;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.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.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.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;
import org.wltea.analyzer.lucene.IKSimilarity;
public class SearchCity {
public void searchCityInfo(String queryStr){
String filePath = "D:\\lucene\\cityDemo\\cityIndex"; //索引文件夹目录
String[] fields = { "id", "name", "area", "description" }; //允许搜索的字段
File indexFile = new File(filePath); //索引文件存放的目录
Analyzer analyzer = new IKAnalyzer(); //IKAnalyzer支持中文分词器
IndexReader indexReader = null;
IndexSearcher indexSearcher = null;
try {
QueryParser queryParser = new MultiFieldQueryParser(Version.LUCENE_35, fields, analyzer); //构造查询器用来搜索多个字段
//PrefixQuery prefixQuery = new PrefixQuery(new Term("name","成")); //与查询前缀匹配的查询,suggest功能
Query query = queryParser.parse(queryStr);
indexReader = IndexReader.open(FSDirectory.open(indexFile)); //indexReader读取索引目录
indexSearcher = new IndexSearcher(indexReader); //实例化搜索对象
indexSearcher.setSimilarity(new IKSimilarity()); //设置匹配实现
TopDocs docs = indexSearcher.search(query, 10); //搜索返回的条目数,关键词包括最多的前10条
int totalHits = docs.totalHits; //匹配的结果总数
System.out.println("total : " + totalHits);
//为允许搜索的字段,设置高亮,html标签
Formatter formatter = new SimpleHTMLFormatter("<font color='red'>","</font>");
Scorer scorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(formatter, scorer);
//复杂的很长的文本字段,需要截取部分来显示,设置片断边界大小,可以保证分词的完整性
Fragmenter fragmenter = new SimpleFragmenter(50);
highlighter.setTextFragmenter(fragmenter);
for (ScoreDoc doc : docs.scoreDocs) {
Document document = indexSearcher.doc(doc.doc); //从符合结果的集合中取出每个文档对象
System.out.println("城市区号:-->" + document.get("id")); //通过key得到值
//返回高亮后的结果,如果当前属性值没有出现关键字则出现null
String hc_name = highlighter.getBestFragment(analyzer, "name", document.get("name")); //需要高亮显示的字段
if (hc_name == null) {
String description = document.get("name");
int endIndex = Math.min(50, description.length()); //返回较小的值
hc_name = description.substring(0, endIndex);// 最多前50个字符
}
System.out.println("城市名称:-->" + hc_name);
System.out.println("所在区域:-->" + document.get("area"));
System.out.println("人口:-->" + document.get("population"));
// System.out.println("简介:-->" + document.get("description"));
//返回高亮后的结果,如果当前属性值没有出现关键字则出现null
String hc_description = highlighter.getBestFragment(analyzer, "description", document.get("description"));
if (hc_description == null) {
String description = document.get("description");
int endIndex = Math.min(50, description.length());
hc_description = description.substring(0, endIndex);
}
System.out.println("简介:-->" + hc_description);
}
} catch (Exception e) {
e.printStackTrace();
} finally {
// 使用完毕需要关闭!
try {
indexReader.close();
indexSearcher.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
写了一个main方法去调用:
public static void main(String[] args) throws Exception {
// CreateIndexFile cif = new CreateIndexFile();
// cif.createIndex();
SearchCity sc = new SearchCity();
sc.searchCityInfo("上海");
}
运行结果:
total : 1
城市区号:-->021
城市名称:--><font color='red'>上海</font>
所在区域:-->华东地区
人口:-->2500万
简介:--><font color='red'>上海</font>(Shanghai),简称“沪”,有“东方巴黎”的美称,中华人民共和国直辖市之一
以上只是Lucene3.5简单的应用,还有一些更多功能,可参见demo和api。