1.配置环境
1.引入jar包:hive-exec-0.8.0.jar 和 hadoop-core-0.20.2.jar
2.编写udf函数
1.extends UDF
2.重新定义UDF的evaluate函数。
- package com.qunar.hiveudf;
- import java.text.SimpleDateFormat;
- import java.util.Calendar;
- import java.util.Date;
- import org.apache.hadoop.hive.ql.exec.UDF;
- public class IsSundayOrSaturday extends UDF
- {
- public Boolean evaluate(String dateString)
- {
- try
- {
- //将string转化为date
- String str = dateString.split(" ")[0];
- SimpleDateFormat sdf= new SimpleDateFormat("yyyy-MM-dd");
- Date date =sdf.parse(str);
- //将date转换为calendar
- Calendar calendar = Calendar.getInstance();
- calendar.setTime(date);
- //获取date的星期
- int week = calendar.get(Calendar.DAY_OF_WEEK)-1;
- if(week == 0 || week == 6)
- {
- return true;
- }
- else
- {
- return false;
- }
- }
- catch (Exception e)
- {
- // TODO: handle exception
- return false;
- }
- }
- }
package com.qunar.hiveudf;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Date;
import org.apache.hadoop.hive.ql.exec.UDF;
public class IsSundayOrSaturday extends UDF
{
public Boolean evaluate(String dateString)
{
try
{
//将string转化为date
String str = dateString.split(" ")[0];
SimpleDateFormat sdf= new SimpleDateFormat("yyyy-MM-dd");
Date date =sdf.parse(str);
//将date转换为calendar
Calendar calendar = Calendar.getInstance();
calendar.setTime(date);
//获取date的星期
int week = calendar.get(Calendar.DAY_OF_WEEK)-1;
if(week == 0 || week == 6)
{
return true;
}
else
{
return false;
}
}
catch (Exception e)
{
// TODO: handle exception
return false;
}
}
}
3.将jar包引入hadoop环境
1.将jar放入hive的lib的物理目录下;
2.打开hive客户端,加入jar包
add jar /home/hive/lib/HiveUDF.jar
3.创建一个临时文件
create temporary function IsSundayOrSaturday AS 'com.qunar.hiveudf.IsSundayOrSaturday'
4.调用函数
select IsSundayOrSaturday(intime) from user_tag
注意:
1.如果函数的参数中含有文件,则先要将文件放入hive的运行环境中
add file /home/filename