1: hive用户自定义函数udf,实现对字符串的格式化操作
引入maven依赖:
<dependency>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
<version>2.6</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>3.1.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.hive/hive-exec -->
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>3.0.0</version>
</dependency>
package com.hadoop.hive;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.Text;
public class MyUdf extends UDF {
private Text resoult=new Text();
//去除字符串text前后空字符
public Text evaluate(Text text){
if (text==null){
return null;
}
resoult.set(StringUtils.strip(text.toString()));
return resoult;
}
//去除字符串text尾在st中出现的字符
public Text evaluate(Text text,String st){
if (text==null){
return null;
}
resoult.set(StringUtils.strip(text.toString(),st));
return resoult;
}
}
HiveQL操作:https://blog.csdn.net/qq_34696236/article/details/81385770