Hive自定义函数支持国密SM4解密

当前项目背景需要使用到国密SM4对加密后的数据进行解密，Hive是不支持的，尝试了华为DWS数仓，华为只支持在DWS中的SM4加密解密，不支持外部加密数据DWS解密

新建Maven工程

只需要将引用的第三方依赖打到jar包中，hadoop和hive的依赖不需要打，不需要打的依赖scope选择provided即可。
使用idea新建maven工程，pom.xml配置如下:

<?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.szc.bigdata.hive</groupId>
    <artifactId>sm4_decode</artifactId>
    <version>0.1</version>
    <properties>
        <hadoop.version>3.1.1-hw-ei-311006</hadoop.version>
        <hive.version>3.1.0-hw-ei-311006</hive.version>
    </properties>

    <dependencies>
      <!-- 国密解密依赖以下3个包，commons-codec用来将字节数组转string用的 -->
        <dependency>
            <groupId>commons-codec</groupId>
            <artifactId>commons-codec</artifactId>
            <version>1.15</version>
        </dependency>
        <dependency>
            <groupId>org.bouncycastle</groupId>
            <artifactId>bcprov-jdk15to18</artifactId>
            <version>1.69</version>
        </dependency>
        <dependency>
            <groupId>cn.hutool</groupId>
            <artifactId>hutool-crypto</artifactId>
            <version>5.8.16</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>${hadoop.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-jdbc</artifactId>
            <version>${hive.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-common</artifactId>
            <version>${hive.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-shims</artifactId>
            <version>${hive.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>${hive.version}</version>
            <scope>provided</scope>
        </dependency>

    </dependencies>
    <repositories>
      <!-- 这里根据实际情况选择，我这边使用的是华为平台 -->
        <repository>
            <id>huaweicloudsdk</id>
            <url>https://mirrors.huaweicloud.com/repository/maven/huaweicloudsdk/</url>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
            </snapshots>
        </repository>
    </repositories>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.1.0</version>
                <configuration>
                  <!-- 此配置会打两个包，一个是不带依赖的，一个是将依赖打到jar包的 -->
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                            <addClasspath>true</addClasspath>
                            <mainClass>com.szc.bigdata.hive.udf.SM4Decode</mainClass>
                        </manifest>
                    </archive>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <!-- bind to the packaging phase -->
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

编写自定义函数类

SmUtil引用的是hutools里的工具类

public class SM4Decode extends UDF {
    public String evaluate(String data, String key) {
        if (data == null || "".equals(data)) {
            return null;
        }
        SymmetricCrypto sm4 = SmUtil.sm4(key.getBytes());
        return  StringUtils.newStringUtf8(sm4.decrypt(data));
    }
}

上传jar包到hdfs上

上传jar包到hdfs上

如果集群开启了权限控制，kerberos需要先试用kinit登录才可以

# 刷新环境变量
source bigdate_env

# kinit 登录
kinit <用户名>
# 回车后输入密码

# 上传到指定目录
hdfs dfs -put ~/sm4_decode-3.1.0-hw-ei-311006-jar-with-dependencies.jar /tmp

# 授权
hdfs dfs -chmod 777 /tmp/sm4_decode-3.1.0-hw-ei-311006-jar-with-dependencies.jar

创建函数

# 进入到hive目录下执行beeline
beeline

# 授权admin权限
set role admin;

# 创建函数
CREATE   FUNCTION sm4decode AS 'com.szc.bigdata.hive.udf.SM4Decode' 
	using jar 'hdfs:///tmp/sm4_decode-3.1.0-hw-ei-311006-jar-with-dependencies.jar';
 
# 创建临时函数
CREATE TEMPORARY  FUNCTION sm4decode AS 'com.szc.bigdata.hive.udf.SM4Decode' 
	using jar 'hdfs:///tmp/sm4_decode-3.1.0-hw-ei-311006-jar-with-dependencies.jar';

# 使用函数
select sm4decode('decodestr','key');