002.hive-UDF自定义函数

IDEA

配置文件 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>com.star</groupId>
    <artifactId>scala_demo</artifactId>
    <version>1.0-SNAPSHOT</version>


    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-jdbc</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-simple</artifactId>
            <version>1.7.25</version>
            <scope>compile</scope>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>
    </dependencies>
</project>

java  注意方法名一定要用这个 evaluate

import   org.apache.hadoop.hive.ql.exec.UDF;
import   org.apache.hadoop.hive.ql.exec.Description;
@Description(
    name = "myudf",
    value = "this is a function",
    extended = "eg:select myudf(1,2) = > 1+2,select myudf("hello","world")=>helloworld"
)

public class MyUDF extends UDF{
    public int evaluate(int i,int j){
       return i+j;
    }
    public String evaluate(String a ,String b){
        return a+b;
    }
}

打jar包

 jar 上传到 /soft/apache-hive-2.1.1-bin/lib

重启hive服务

[centos@s101 /home/centos]$hiveserver2

连接hive

[centos@s101 /home/centos]$beeline -u jdbc:hive2://localhost:10000

注册函数

0: jdbc:hive2://localhost:10000> show databases;
+----------------+--+
| database_name |
+----------------+--+
| default |
| mydb |
+----------------+--+
2 rows selected (4.71 seconds)

0: jdbc:hive2://localhost:10000> use mydb;

0: jdbc:hive2://localhost:10000> create function myudf as 'MyUDF';
No rows affected (0.839 seconds)

0: jdbc:hive2://localhost:10000> show functions;

0: jdbc:hive2://localhost:10000> use mydb
. . . . . . . . . . . . . . . .> ;
No rows affected (14.597 seconds)
0: jdbc:hive2://localhost:10000> create function myudf as 'MyUDF';
No rows affected (0.464 seconds)
0: jdbc:hive2://localhost:10000> desc function extended myudf;
+-------------------------------------------------------------------------+--+
| tab_name |
+-------------------------------------------------------------------------+--+
| this is a function |
| Synonyms: mydb.myudf |
| eg:select myudf(1,2) = > 1+2,select myudf("hello","world")=>helloworld |
+-------------------------------------------------------------------------+--+
3 rows selected (4.17 seconds)
0: jdbc:hive2://localhost:10000> select mydb.myudf("df","df");
+-------+--+
| _c0 |
+-------+--+
| dfdf |
+-------+--+
1 row selected (4.564 seconds)