这里我们拷贝之前的工程（lucene_index01）为工程lucene_index02。然后在创建索引和搜索方法上进行改进测试。
相关代码：
IndexUtil.java
package cn.lucene.index;
import java.io.File;
import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Fieldable;
import org.apache.lucene.document.NumericField;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.FieldInfo.IndexOptions;
import org.apache.lucene.index.StaleReaderException;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;
public class IndexUtil {
private String[] ids = {"1", "2", "3", "4", "5", "6"};
//下面是邮件
private String[] emails = {"aa@qq.com", "bb@sina.edu", "cc@yahu.org", "ss@sina.com", "dd@gmail.com", "ee@163.com"};
//下面是邮件内容
private String[] content = {
"welcom to visited the space,I like football",
"hello boy, i like someone",
"come on baby",
"first blood",
"I like football,I like football",
"my girlfriend is so beatiful, every body like game"
};
private int[] attaches = {2,5,6,5,8,4};//附件数量
//发件人名字
private String[] names = {"Tom", "Jack", "goudan", "alibaba", "jerry", "kitty"};
//邮件的日期
private Date[] dates = null;
private Directory directory = null;
private Map<String, Float> scores = new HashMap<String, Float>();//新建一个Map，用来存储权值
public IndexUtil() {
try {
setDates();//设置日期
scores.put("qq.com", 2.0f);//如果是"qq.com"结尾的索引则让其权值为2.0，注意：默认是1.0
scores.put("sina.edu", 1.5f);
directory = FSDirectory.open(new File("E:/myeclipse/Lucene/index"));
} catch (IOException e) {
e.printStackTrace();
}
}
//创建索引
public void index(){
IndexWriter writer = null;
try {
writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
//此方法可将索引全部清空
writer.deleteAll();
Document document = null;
for(int i = 0; i < ids.length; i++){
document = new Document();
//id需要存储，不需要加权、分词，email也需要存储，但不需要分词，有时候也需要加权
//对于内容，我们不需要存储和加权，但需要分词。而名字需要存储，不需要分词和加权
//这里我们先不对整型数据进行索引，后面再说
document.add(new Field("id", ids[i], Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
document.add(new Field("email", emails[i], Field.Store.YES, Field.Index.NOT_ANALYZED));
document.add(new Field("content", content[i], Field.Store.NO, Field.Index.ANALYZED));
document.add(new Field("name", names[i], Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));
//为数字添加索引，第三个参数设置为true表示默认索引
document.add(new NumericField("attach", Field.Store.YES, true).setIntValue(attaches[i]));
//为日期添加索引
document.add(new NumericField("date", Field.Store.YES, true).setLongValue(dates[i].getTime()));
String et = emails[i].substring(emails[i].lastIndexOf("@") + 1);
System.out.println(et);
//加入权值
if(scores.containsKey(et)){
document.setBoost(scores.get(et));
}else{
document.setBoost(0.5f);
}
writer.addDocument(document);
}
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}finally{
if(writer != null){
try {
writer.close();
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
//设置日期
private void setDates(){
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd");
try {
dates = new Date[ids.length];
dates[0] = sdf.parse("2015-02-15");
dates[1] = sdf.parse("2015-03-01");
dates[2] = sdf.parse("2015-05-18");
dates[3] = sdf.parse("2015-09-05");
dates[4] = sdf.parse("2015-12-15");
dates[5] = sdf.parse("2015-08-29");
} catch (ParseException e) {
e.printStackTrace();
}
}
public void search(){
IndexReader reader;
try {
reader = IndexReader.open(directory);
IndexSearcher searcher = new IndexSearcher(reader);
TermQuery query = new TermQuery(new Term("content", "like"));//搜索内容中含有like的
TopDocs tds = searcher.search(query, 10);
for(ScoreDoc sd : tds.scoreDocs){
Document doc = searcher.doc(sd.doc);
//这里我们获取权值getBoost()的时候发现都是1.0，这是因为这里是获取的一个document，和原来的没有关系。
//要想看其权值信息，可以使用luke工具
//而这里的日期需要我们转换成日期格式
System.out.println("(" + sd.doc + "权值："+ doc.getBoost() + ")" + doc.get("name") + "[" + doc.get("email") + "]-->"
+ doc.get("id") + "-->" + doc.get("attach") + "-->" + doc.get("date"));
reader.close();
}
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
说明：
- 这里我们首先加入日期，同时使用
//为数字添加索引，第三个参数设置为true表示默认索引
document.add(new NumericField("attach", Field.Store.YES, true).setIntValue(attaches[i]));
//为日期添加索引
document.add(new NumericField("date", Field.Store.YES, true).setLongValue(dates[i].getTime()));
为数字和日期加入索引。
- 这里要注意的是我们要想查看索引的权值不能使用
getBoost方法，不然查出来的权值都是1.0，可以使用luke工具查看。
