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

<?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.itcast</groupId>
    <artifactId>UDFtest</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>1.2.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.4</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.2</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </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)