cdh6.3.2的hive配udf

背景

大数据平台的租户要使用udf，他们用beeline连接，
意味着要通过hs2，但如果有多个hs2，各个hs2之间不能共享，需要先把文件传到hdfs，然后手动在各hs2上create function。之后就可以永久使用了，重启hs2也可以

调研

先查的hive官网

https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF#LanguageManualUDF-CreatingCustomUDFs
在这里插入图片描述
用beeline执行add jar 和create function，但发现只在当前的hs2生效

然后查cdh官网

cdh的官网上说配UDF，需要考虑是否重启hs2，是否启用sentry，列出了3种方案。
https://docs.cloudera.com/documentation/enterprise/latest/topics/cm_mc_hive_udf.html
在这里插入图片描述
Direct JAR reference configuration
Straight-forward, but recommended for development only. Does not support Sentry.
试了下，是永久的，重启仍然生效，但只对当前的hs2有效，如果有多个hs2，需要在每个hs2上都执行create function命令
虽然我们开了sentry，但没影响，sentry仍然有效

pom

<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>sm3UDF</artifactId><version>1.0</version><packaging>jar</packaging><name>sm3UDF</name><url>http://maven.apache.org</url><properties><project.build.sourceEncoding>UTF-8</project.build.sourceEncoding></properties><dependencies><dependency><groupId>org.bouncycastle</groupId><artifactId>bcprov-jdk15on</artifactId><version>1.68</version></dependency><dependency><groupId>org.apache.hadoop</groupId><artifactId>hadoop-common</artifactId><version>3.1.1</version></dependency>
<!--        <dependency>-->
<!--            <groupId>junit</groupId>-->
<!--            <artifactId>junit</artifactId>-->
<!--            <version>4.13.2</version>-->
<!--            <scope>test</scope>-->
<!--        </dependency>--><dependency><groupId>org.apache.hive</groupId><artifactId>hive-exec</artifactId><version>2.1.1-cdh6.3.2</version></dependency></dependencies><build><plugins><plugin><groupId>org.apache.maven.plugins</groupId><artifactId>maven-compiler-plugin</artifactId><version>3.1</version><configuration><source>1.8</source><target>1.8</target></configuration></plugin></plugins></build>
</project>

java

package org.picc.encrypt;import org.apache.commons.codec.binary.Hex;
import org.apache.hadoop.io.Text;
import org.bouncycastle.crypto.digests.SM3Digest;
import org.apache.hadoop.hive.ql.exec.UDF;public class Sm3Fun extends UDF{public static String sm3(String saltBefore, String text, String saltAfter) {if (text == null) {return null;}Text result = new Text();SM3Digest digest = new SM3Digest();Text sb = new Text(saltBefore);Text value = new Text(text);Text sa = new Text(saltAfter);byte[] hashData = new byte[32];digest.reset();digest.update(sb.getBytes(), 0, sb.getLength());digest.update(value.getBytes(), 0, value.getLength());digest.update(sa.getBytes(), 0, sa.getLength());digest.doFinal(hashData, 0);String sm3Hex = Hex.encodeHexString(hashData);result.set(sm3Hex);return result.toString();}public String evaluate(String text) {if (text == null) {return null;}Text result = new Text();SM3Digest digest = new SM3Digest();Text value = new Text(text);byte[] hashData = new byte[32];digest.reset();digest.update(value.getBytes(), 0, value.getLength());digest.doFinal(hashData, 0);String sm3Hex = Hex.encodeHexString(hashData);result.set(sm3Hex);return result.toString();}
}