hive自定义UDF实现md5加密函数

hive自定义UDF实现md5加密函数

1 pom.xm配置

<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>4.0.0modelVersion>

    <groupId>com.itcastgroupId>
    <artifactId>UDFtestartifactId>
    <version>1.0-SNAPSHOTversion>

    <dependencies>
        <dependency>
            <groupId>org.apache.hivegroupId>
            <artifactId>hive-execartifactId>
            <version>1.2.1version>
        dependency>
        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-commonartifactId>
            <version>2.7.4version>
        dependency>
    dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-shade-pluginartifactId>
                <version>2.2version>
                <executions>
                    <execution>
                        <phase>packagephase>
                        <goals>
                            <goal>shadegoal>
                        goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SFexclude>
                                        <exclude>META-INF/*.DSAexclude>
                                        <exclude>META-INF/*.RSAexclude>
                                    excludes>
                                filter>
                            filters>
                        configuration>
                    execution>
                executions>
            plugin>
        plugins>
    build>
project>

2 写一个 java 类，继承 UDF，并重载 evaluate 方法

import com.google.common.base.Strings;
import com.google.common.hash.Hashing;
import org.apache.commons.compress.utils.Charsets;
import org.apache.hadoop.hive.ql.exec.UDF;

public class TestMD5 extends UDF {

    public static String evaluate(String in){
        if(Strings.isNullOrEmpty(in.trim())){
            return null;
        }
        return Hashing.md5().newHasher().putString(in, Charsets.UTF_8).hash().toString();
    }

/*    public static void main(String[] args) {
        System.out.println(evaluate("wangjie"));
    }*/
}

3 打成 jar 包上传到服务器

4 将 jar 包添加到 hive 的 classpath

add jar /root/UDFtest-1.0-SNAPSHOT.jar;

5 注册临时函数（用户自定义函数重启之后 就失效）

create temporary function itcastfunc as 'TestMD5';
create temporary function 函数名 as '类全路径';

6 测试

 select itcastfunc("wangjie");

+-----------------------------------+--+
|                _c0                |
+-----------------------------------+--+
| 209eae20cef54355b3fc1086cb9ceae2  |
+-----------------------------------+--+
1 row selected (0.149 seconds)