JAVA UDF炸裂与脱敏编写:
pom.xml:
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>cn.kgc.demo</groupId>
<artifactId>udf-demo</artifactId>
<version>1.0-SNAPSHOT</version>
<name>udf-demo</name>
<!-- FIXME change it to the project's website -->
<url>http://www.example.com</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
</properties>
<repositories>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.6.0-cdh5.14.2</version>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>1.1.0-cdh5.14.2</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.3</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
</plugin>
</plugins>
</build>
</project>
ActionDivideDemo(UDF炸裂)
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.Text;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Date;
/***
* UDF + explode UDTF
* UDTF
* UDAF sum
*
*
*/
public class ActionDivideDemo extends UDF {
public static Text evaluate(Text strDay, Text date) {
SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd");
Date tempDate = null;
Calendar today = null; //日期的工具类
try {
tempDate = df.parse(date.toString());
today = Calendar.getInstance();
today.setTime(tempDate);
today.add(Calendar.DAY_OF_YEAR, -1);
} catch (ParseException e) {
e.printStackTrace();
}
int days = Integer.parseInt(strDay.toString());
StringBuffer result = new StringBuffer("");
for (int i = 1; i <= days; i++) {
if (i != days) {
today.add(Calendar.DAY_OF_YEAR, -1);
result.append(df.format(today.getTime()) + ",");
} else {
today.add(Calendar.DAY_OF_YEAR, -1);
result.append(df.format(today.getTime()));
}
}
return new Text(String.valueOf(result));
}
public static void main(String[] args) {
//测试
System.out.println(ActionDivideDemo.evaluate(new Text("7"), new Text("2023-03-13")));
}
}
结果:
2023-03-11,2023-03-10,2023-03-09,2023-03-08,2023-03-07,2023-03-06,2023-03-05
Desensitization 脱敏(加密)
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.Text;
public class Desensitization extends UDF {
// 1200001234 --> 120******4 加密
public Text evaluate(Text text) {
String str = text.toString();
String result = str.replace(str.substring(3, 9), "******");
return new Text(result);
}
public static void main(String[] args) {
System.out.println(new Desensitization().evaluate(new Text("1200001234")));
}
}