spark-instrumented-optimizer/external/kafka-0-10-assembly/pom.xml
Chao Sun cb3fa6c936 [SPARK-33212][BUILD] Move to shaded clients for Hadoop 3.x profile
### What changes were proposed in this pull request?

This switches Spark to use shaded Hadoop clients, namely hadoop-client-api and hadoop-client-runtime, for Hadoop 3.x. For Hadoop 2.7, we'll still use the same modules such as hadoop-client.

In order to still keep default Hadoop profile to be hadoop-3.2, this defines the following Maven properties:

```
hadoop-client-api.artifact
hadoop-client-runtime.artifact
hadoop-client-minicluster.artifact
```

which default to:
```
hadoop-client-api
hadoop-client-runtime
hadoop-client-minicluster
```
but all switch to `hadoop-client` when the Hadoop profile is hadoop-2.7. A side affect from this is we'll import the same dependency multiple times. For this I have to disable Maven enforcer `banDuplicatePomDependencyVersions`.

Besides above, there are the following changes:
- explicitly add a few dependencies which are imported via transitive dependencies from Hadoop jars, but are removed from the shaded client jars.
- removed the use of `ProxyUriUtils.getPath` from `ApplicationMaster` which is a server-side/private API.
- modified `IsolatedClientLoader` to exclude `hadoop-auth` jars when Hadoop version is 3.x. This change should only matter when we're not sharing Hadoop classes with Spark (which is _mostly_ used in tests).

### Why are the changes needed?

This serves two purposes:
- to unblock Spark from upgrading to Hadoop 3.2.2/3.3.0+. Latest Hadoop versions have upgraded to use Guava 27+ and in order to adopt the latest Hadoop versions in Spark, we'll need to resolve the Guava conflicts. This takes the approach by switching to shaded client jars provided by Hadoop.
- avoid pulling 3rd party dependencies from Hadoop and avoid potential future conflicts.

### Does this PR introduce _any_ user-facing change?

When people use Spark with `hadoop-provided` option, they should make sure class path contains `hadoop-client-api` and `hadoop-client-runtime` jars. In addition, they may need to make sure these jars appear before other Hadoop jars in the order. Otherwise, classes may be loaded from the other non-shaded Hadoop jars and cause potential conflicts.

### How was this patch tested?

Relying on existing tests.

Closes #29843 from sunchao/SPARK-29250.

Authored-by: Chao Sun <sunchao@apple.com>
Signed-off-by: DB Tsai <d_tsai@apple.com>
2020-10-22 03:21:34 +00:00

177 lines
6.1 KiB
XML

<?xml version="1.0" encoding="UTF-8"?>
<!--
~ Licensed to the Apache Software Foundation (ASF) under one or more
~ contributor license agreements. See the NOTICE file distributed with
~ this work for additional information regarding copyright ownership.
~ The ASF licenses this file to You under the Apache License, Version 2.0
~ (the "License"); you may not use this file except in compliance with
~ the License. You may obtain a copy of the License at
~
~ http://www.apache.org/licenses/LICENSE-2.0
~
~ Unless required by applicable law or agreed to in writing, software
~ distributed under the License is distributed on an "AS IS" BASIS,
~ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
~ See the License for the specific language governing permissions and
~ limitations under the License.
-->
<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>
<parent>
<groupId>org.apache.spark</groupId>
<artifactId>spark-parent_2.12</artifactId>
<version>3.1.0-SNAPSHOT</version>
<relativePath>../../pom.xml</relativePath>
</parent>
<artifactId>spark-streaming-kafka-0-10-assembly_2.12</artifactId>
<packaging>jar</packaging>
<name>Spark Integration for Kafka 0.10 Assembly</name>
<url>http://spark.apache.org/</url>
<properties>
<sbt.project.name>streaming-kafka-0-10-assembly</sbt.project.name>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_${scala.binary.version}</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_${scala.binary.version}</artifactId>
<version>${project.version}</version>
<scope>provided</scope>
</dependency>
<!--
Demote already included in the Spark assembly.
-->
<dependency>
<groupId>commons-codec</groupId>
<artifactId>commons-codec</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>commons-lang</groupId>
<artifactId>commons-lang</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.google.protobuf</groupId>
<artifactId>protobuf-java</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.lz4</groupId>
<artifactId>lz4-java</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>${hadoop-client-api.artifact}</artifactId>
<version>${hadoop.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>${hadoop-client-runtime.artifact}</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.avro</groupId>
<artifactId>avro-mapred</artifactId>
<classifier>${avro.mapred.classifier}</classifier>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.curator</groupId>
<artifactId>curator-recipes</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.zookeeper</groupId>
<artifactId>zookeeper</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.xerial.snappy</groupId>
<artifactId>snappy-java</artifactId>
<scope>provided</scope>
</dependency>
</dependencies>
<build>
<outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory>
<testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<configuration>
<shadedArtifactAttached>false</shadedArtifactAttached>
<artifactSet>
<includes>
<include>*:*</include>
</includes>
</artifactSet>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
</configuration>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<transformers>
<transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
<transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
<resource>reference.conf</resource>
</transformer>
<transformer implementation="org.apache.maven.plugins.shade.resource.DontIncludeResourceTransformer">
<resource>log4j.properties</resource>
</transformer>
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheLicenseResourceTransformer"/>
<transformer implementation="org.apache.maven.plugins.shade.resource.ApacheNoticeResourceTransformer"/>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>