hive之UDF函数编程详解

<?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.wsk.bigdata</groupId>
<artifactId>g6-hadoop</artifactId>
<version>1.0</version>
<name>g6-hadoop</name>
<properties>
<maven.compiler.source>1.7</maven.compiler.source>
<maven.compiler.target>1.7</maven.compiler.target>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
<hive.version>1.1.0-cdh5.7.0</hive.version>
</properties>
<!--添加CDH的仓库-->
<repositories>
<repository>
<id>nexus-aliyun</id>
<url>http://maven.aliyun.com/nexus/content/groups/public</url>
</repository>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos</url>
</repository>
</repositories>
<dependencies>
<!--添加Hadoop的依赖-->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<!--添加hive依赖-->
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>${hive.version}</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>2.4</version>
<configuration>
<source>1.7</source>
<target>1.7</target>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
</plugins>
</build>
</project>

 [hadoop@hadoop001 lib]$ rz

[hadoop@hadoop001 lib]$ ll  g6-hadoop-1.0.jar

-rw-r--r--. 1 hadoop hadoop 11447 Apr 19 2019 g6-hadoop-1.0.jar

hive> add jar /home/hadoop/data/hive/g6-hadoop-1.0.jar;

CREATE TEMPORARY FUNCTION function_name AS class_name;   

function_name函数名                        

*******class_name 类路径，包名+类名*********   这里就是你写的UDF函数的第一行的package后边的东西然后在加个点加个类的名字

hive>CREATE TEMPORARY FUNCTION HelloUDF AS ‘org.apache.hadoop.hive.ql.udf.HelloUDF‘;

 OK Time taken: 0.485 seconds

hive>

hive> show functions; 【查看可以看到HelloUDF】

hive>select HelloUDF(‘17‘);

OK

Hello：17

#检查mysql中的元数据，因为是临时函数，故元数据中并没有相关的信息

mysql> select * from funcs;

Empty set (0.11 sec)

hive> DROP TEMPORARY FUNCTION IF EXISTS HelloUDF;

OK

Time taken: 0.003 seconds

hive> select HelloUDF(‘17‘);

FAILED: SemanticException [Error 10011]: Line 1:7 Invalid function ‘HelloUDF‘

##其实不删除也无所谓，重新开一个窗口即可

CREATE TEMPORARY FUNCTION function_name AS class_name USING JAR path;

function_name函数名                        

class_name 类路径，

包名+类名 

path jar包hdfs路径

[hadoop@hadoop hive-1.1.0-cdh5.7.0]$ hadoop fs -mkdir /lib

[hadoop@hadoop hive-1.1.0-cdh5.7.0]$ hadoop fs -put /home/hadoop/data/hive/hive_UDF.jar /lib/

[hadoop@hadoop001 ~]$ hadoop fs -mkdir /lib
[hadoop@hadoop001 ~]$ hadoop fs -ls /lib
[hadoop@hadoop001 ~]$ hadoop fs -put ~/lib/g6-hadoop-1.0.jar  /lib/   把本地的jar上传到HDFS的/lib/目录下
[hadoop@hadoop001 ~]$ hadoop fs -ls /lib

CREATE FUNCTION HelloUDF AS ‘org.apache.hadoop.hive.ql.udf.HelloUDF‘

USING JAR ‘hdfs://hadoop001:9000/lib/g6-hadoop-1.0.jar‘;

#测试 hive> select HelloUDF("17") ;

OK hello:17

mysql> select * from funcs;
+---------+------------------------------+-------------+-------+------------+-----------+------------+------------+
| FUNC_ID | CLASS_NAME | CREATE_TIME | DB_ID | FUNC_NAME | FUNC_TYPE | OWNER_NAME | OWNER_TYPE |
+---------+------------------------------+-------------+-------+------------+-----------+------------+------------+
| 1 |org.apache.hadoop.hive.ql.udf.HelloUDF | 1555263915 | 6 | HelloUDF | 1 | NULL | USER |
+---------+------------------------------+-------------+-------+------------+-----------+------------+------------+