package org.apache.hadoop.hive.ql.udf.HashMd5UDF;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.io.MD5Hash;
public class HashMd5 extends UDF {
public String evaluate(String param) {
return "EVALUATE:" + MD5Hash.digest(param.getBytes()).toString();
}
}
<?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>org.example</groupId>
<artifactId>udf_md5</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<hadoop.version>0.20.2</hadoop.version>
<hive.version>0.9.0</hive.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>${hadoop.version}</version>
</dependency>
<!-- Hive -->
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-metastore</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-pdk</artifactId>
<version>${hive.version}</version>
</dependency>
<dependency>
<groupId>javax.jdo</groupId>
<artifactId>jdo2-api</artifactId>
<version>2.3-eb</version>
</dependency>
<dependency>
<groupId>commons-logging</groupId>
<artifactId>commons-logging</artifactId>
<version>1.1.1</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.7</version>
<scope>test</scope>
</dependency>
</dependencies>
</project>
mvn package
// 创建临时UDF函数:
add jar /data/platform/olap/udf_md5-1.0-SNAPSHOT.jar;
CREATE TEMPORARY FUNCTION HashMd5 AS 'org.apache.hadoop.hive.ql.udf.HashMd5UDF.HashMd5';
// 创建永久UDF函数:
CREATE FUNCTION HashMd5 AS 'org.apache.hadoop.hive.ql.udf.HashMd5UDF.HashMd5' USING JAR 'hdfs://hadoop01:9000/lib/udf_md5-1.0-SNAPSHOT.jar';
SELECT HashMd5('a');