smallearth
- 浏览: 34558 次
- 性别:
-
最新评论
Lucene小练四——为数字和日期添加索引
//主程序
package org.se.lucene;
import java.io.File;
import java.io.IOException;
//import java.sql.Date;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
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.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 lucene_index {
private String[] ids={"1","2","3","4","5","6"};
private String[] emails={"welcometotyu","hellowboy",
"higirl","howareyou","googluck","badgosh"};
private String[] contents={"I like 1","I like 2","I like 3","I like 4" +
"I like 5"};
private int[] attachs={1,2,3,4,5,6};
private String[] names={"liwu","zhangsan","xiaoqinag","laona",
"dabao","lisi"};
private Date[] dates=null;
private Directory directory=null;
private Map<String,Float> scores=new HashMap<String, Float>();
public void index()
{
IndexWriter writer=null;
Document doc=null;
try {
writer =new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_36,
new StandardAnalyzer(Version.LUCENE_36)));
//writer.deleteAll();
for(int i=0;i<ids.length;i++)
{
doc=new Document();
doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
doc.add(new Field("email",emails[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("contents",contents[i],Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("name",names[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
//存储数字
doc.add(new NumericField("attachs",Field.Store.YES,true).setIntValue(attachs[i]));
//存储日期
doc.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);
if(scores.containsKey(et))
{
doc.setBoost(scores.get(et));
}
else {
doc.setBoost(0.5f);
}
writer.addDocument(doc);
}
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (LockObtainFailedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
finally{
if(writer!=null)
{
try {
writer.close();
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
public void setDate()
{
SimpleDateFormat sdf=new SimpleDateFormat("yyyy-mm-kk");
try {
dates=new Date[ids.length];
dates[0]=sdf.parse("2010-08-17");
dates[1]=sdf.parse("2011-02-17");
dates[2]=sdf.parse("2012-03-17");
dates[3]=sdf.parse("2011-04-17");
dates[4]=sdf.parse("2012-05-17");
dates[5]=sdf.parse("2011-07-17");
} catch (Exception e) {
e.printStackTrace();
// TODO: handle exception
}
}
public lucene_index()
{
setDate();
try {
directory=FSDirectory.open(new File("f:/lucene/index02"));
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void quary()
{
try {
IndexReader reader=IndexReader.open(directory);
System.out.println("numdocs"+reader.numDocs());
System.out.println("maxDocs"+reader.maxDoc());
System.out.println("detelemaxDocs"+reader.numDeletedDocs());
reader.close();
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
@SuppressWarnings("deprecation")
public void undelete()
{
try {
//回复时必须把reader的只读设为false
IndexReader reader=IndexReader.open(directory,false);
reader.undeleteAll();
reader.close();
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
//清空回收站，强制优化
public void forceDelete()
{
IndexWriter writer=null;
try {
writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36,
new StandardAnalyzer(Version.LUCENE_36)));
//参数十一个选项，可以是一个query，也可以是一个term term就是一个精确查找的值
//此时删除的文档并未完全删除，而是存储在回收站中，可以恢复的
writer.forceMergeDeletes();
} 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) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
public void merge()
{
IndexWriter writer=null;
try {
writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36,
new StandardAnalyzer(Version.LUCENE_36)));
writer.forceMerge(2);
} 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) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
public void delete()
{
IndexWriter writer=null;
try {
writer=new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36,
new StandardAnalyzer(Version.LUCENE_36)));
//参数十一个选项，可以是一个query，也可以是一个term term就是一个精确查找的值
//此时删除的文档并未完全删除，而是存储在回收站中，可以恢复的
writer.deleteDocuments(new Term("id","1"));
} 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) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
//更新索引
public void update()
{
/*lucene本身不支持更新
*
* 通过删除索引然后再建立索引来更新
*
*/
IndexWriter writer=null;
Document doc=null;
try {
writer =new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_36,
new StandardAnalyzer(Version.LUCENE_36)));
writer.deleteAll();
for(int i=0;i<ids.length;i++)
{
doc=new Document();
doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
doc.add(new Field("emails",emails[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("contents",contents[i],Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("name",names[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
writer.updateDocument(new Term("id","1"), doc);
}
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (LockObtainFailedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
finally{
if(writer!=null)
{
try {
writer.close();
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
public void serch()
{
try {
IndexReader reader=IndexReader.open(directory);
IndexSearcher searcher=new IndexSearcher(reader);
TermQuery query=new TermQuery(new Term("contents","like"));
TopDocs tds=searcher.search(query, 10);
for(ScoreDoc sd:tds.scoreDocs)
{
Document doc=searcher.doc(sd.doc);
System.out.println("("+sd.doc+"-"+doc.getBoost()+"-"+sd.score+")"+doc.get("name")+"["+doc.get("email")+"]-->"
+doc.get("id")+","+doc.get("attachs")+","+doc.get("date"));
}
} catch (CorruptIndexException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch blocket
e.printStackTrace();
}
}
}
//测试类
package org.se.lucene;
import org.junit.Test;
public class test {
@Test
public void testIndex()
{
lucene_index l_index=new lucene_index();
l_index.index();
}
@Test
public void testquary()
{
lucene_index l_index=new lucene_index();
l_index.quary();
}
@Test
public void testDelete()
{
lucene_index l_index=new lucene_index();
l_index.delete();
}
@Test
public void testunDelete()
{
lucene_index l_index=new lucene_index();
l_index.undelete();
}
@Test
public void testForceDelete()
{
lucene_index l_index=new lucene_index();
l_index.forceDelete();
}
@Test
public void testmerge()
{
lucene_index l_index=new lucene_index();
l_index.merge();
}
@Test
public void upDate()
{
lucene_index l_index=new lucene_index();
l_index.update();
}
@Test
public void testSercher()
{
lucene_index l_index=new lucene_index();
l_index.serch();
}
}
分享到：
发表评论
相关推荐
lucene 对 xml建立索引 建立索引就是怎么简单 呵呵
Lucene索引器实例Lucene索引器实例Lucene索引器实例Lucene索引器实例
基于lucene技术的增量索引，实现索引的首次创建，动态增删改
Lucene创建索引，查询索引的简单使用。
Lucene之删除索引 Lucene之删除索引 Lucene之删除索引 http://blog.csdn.net/nupt123456789/article/details/10666105
基于lucene 2.4简单的一个索引和搜索实例
Lucene.Net 2.3.1开发介绍 —— 二、分词（四），这是一个系列的文档，太多了，只好分开
基于Java的全文索引检索引擎——Lucene，关于这个分词的自己还是很不懂，希望大家有好地资源一起分享一下
Lucene创建索引步骤： 1、创建Directory（索引位置） 2、创建IndexWrite（写入索引） 3、创建Document对象 4、为Document添加Field（相当于添加属性：类似于表与字段的关系） 5、通过IndexWriter添加文档到索引中
这款已经老了，2.4以后的lucene索引用不了。我上传了最新版本的，有需要的话!请到http://download.csdn.net/source/1423241 下。一款可以查看Lucene分词后在索引的排名以及是否有无该词，很多时候用于查看有无需要...
Lucene索引的基本操作,包括添加和更新操作及测试代码；
Lucene3.0创建索引 读取目录下的所有txt文档格式的文件，然后生成一个索引文件到某目录下！
lucene 索引 查看 工具
该程序代码属于本人2015所写，虽然尚有不足，却实现了对多个文件夹下的数据进行Lucene建立索引和查询功能，并包含了所需的所有jar包，工程直接导入即可运行。
lucene索引查看工具及源码lucene索引查看工具及源码lucene索引查看工具及源码
Lucene实现索引和查询的实例讲解Lucene实现索引和查询的实例讲解
lucene索引结构原理
lukeall-0.9.jar为Lucene索引查看工具，方便大家查看索引
深入 Lucene 索引机制深入 Lucene 索引机制深入 Lucene 索引机制深入 Lucene 索引机制深入 Lucene 索引机制深入 Lucene 索引机制
Lucene 删除 合并索引，可以指定几个索引文件合并成一个索引文件。自己写的，有很多不足之处请多指教