diff options
author | Marcelo Vanzin <vanzin@cloudera.com> | 2016-04-25 10:20:51 -0700 |
---|---|---|
committer | Marcelo Vanzin <vanzin@cloudera.com> | 2016-04-25 10:20:51 -0700 |
commit | a680562a6f87a03a00f71bad1c424267ae75c641 (patch) | |
tree | fe08025da6437124c283e9450dd3bbc0e99c411d /examples/pom.xml | |
parent | bfda09991398ce44be91997252cf8e5ddd361737 (diff) | |
download | spark-a680562a6f87a03a00f71bad1c424267ae75c641.tar.gz spark-a680562a6f87a03a00f71bad1c424267ae75c641.tar.bz2 spark-a680562a6f87a03a00f71bad1c424267ae75c641.zip |
[SPARK-14744][EXAMPLES] Clean up examples packaging, remove outdated examples.
First, make all dependencies in the examples module provided, and explicitly
list a couple of ones that somehow are promoted to compile by maven. This
means that to run streaming examples, the streaming connector package needs
to be provided to run-examples using --packages or --jars, just like regular
apps.
Also, remove a couple of outdated examples. HBase has had Spark bindings for
a while and is even including them in the HBase distribution in the next
version, making the examples obsolete. The same applies to Cassandra, which
seems to have a proper Spark binding library already.
I just tested the build, which passes, and ran SparkPi. The examples jars
directory now has only two jars:
```
$ ls -1 examples/target/scala-2.11/jars/
scopt_2.11-3.3.0.jar
spark-examples_2.11-2.0.0-SNAPSHOT.jar
```
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes #12544 from vanzin/SPARK-14744.
Diffstat (limited to 'examples/pom.xml')
-rw-r--r-- | examples/pom.xml | 229 |
1 files changed, 15 insertions, 214 deletions
diff --git a/examples/pom.xml b/examples/pom.xml index fcd60e3b77..43f3d2e4de 100644 --- a/examples/pom.xml +++ b/examples/pom.xml @@ -35,6 +35,10 @@ <sbt.project.name>examples</sbt.project.name> <build.testJarPhase>none</build.testJarPhase> <build.copyDependenciesPhase>package</build.copyDependenciesPhase> + <flume.deps.scope>provided</flume.deps.scope> + <hadoop.deps.scope>provided</hadoop.deps.scope> + <hive.deps.scope>provided</hive.deps.scope> + <parquet.deps.scope>provided</parquet.deps.scope> </properties> <dependencies> @@ -72,131 +76,13 @@ <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-flume_${scala.binary.version}</artifactId> <version>${project.version}</version> + <scope>provided</scope> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-kafka_${scala.binary.version}</artifactId> <version>${project.version}</version> - </dependency> - <dependency> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-protocol</artifactId> - <version>${hbase.version}</version> - <scope>${hbase.deps.scope}</scope> - </dependency> - <dependency> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-common</artifactId> - <version>${hbase.version}</version> - <scope>${hbase.deps.scope}</scope> - <exclusions> - <exclusion> - <!-- SPARK-4455 --> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-annotations</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-client</artifactId> - <version>${hbase.version}</version> - <scope>${hbase.deps.scope}</scope> - <exclusions> - <exclusion> - <!-- SPARK-4455 --> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-annotations</artifactId> - </exclusion> - <exclusion> - <groupId>io.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-server</artifactId> - <version>${hbase.version}</version> - <scope>${hbase.deps.scope}</scope> - <exclusions> - <exclusion> - <!-- SPARK-4455 --> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-annotations</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-common</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-core</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-client</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-mapreduce-client-jobclient</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-mapreduce-client-core</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-auth</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-annotations</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hadoop</groupId> - <artifactId>hadoop-hdfs</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-hadoop1-compat</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.commons</groupId> - <artifactId>commons-math</artifactId> - </exclusion> - <exclusion> - <groupId>com.sun.jersey</groupId> - <artifactId>jersey-core</artifactId> - </exclusion> - <exclusion> - <groupId>org.slf4j</groupId> - <artifactId>slf4j-api</artifactId> - </exclusion> - <exclusion> - <groupId>com.sun.jersey</groupId> - <artifactId>jersey-server</artifactId> - </exclusion> - <exclusion> - <groupId>com.sun.jersey</groupId> - <artifactId>jersey-core</artifactId> - </exclusion> - <exclusion> - <groupId>com.sun.jersey</groupId> - <artifactId>jersey-json</artifactId> - </exclusion> - <exclusion> - <!-- hbase uses v2.4, which is better, but ...--> - <groupId>commons-io</groupId> - <artifactId>commons-io</artifactId> - </exclusion> - </exclusions> - </dependency> - <dependency> - <groupId>org.apache.hbase</groupId> - <artifactId>hbase-hadoop-compat</artifactId> - <version>${hbase.version}</version> - <scope>${hbase.deps.scope}</scope> + <scope>provided</scope> </dependency> <dependency> <groupId>org.apache.commons</groupId> @@ -204,79 +90,25 @@ <scope>provided</scope> </dependency> <dependency> - <groupId>com.twitter</groupId> - <artifactId>algebird-core_${scala.binary.version}</artifactId> - <version>0.11.0</version> - </dependency> - <dependency> <groupId>org.scalacheck</groupId> <artifactId>scalacheck_${scala.binary.version}</artifactId> <scope>test</scope> </dependency> <dependency> - <groupId>org.apache.cassandra</groupId> - <artifactId>cassandra-all</artifactId> - <version>1.2.19</version> - <exclusions> - <exclusion> - <groupId>com.google.guava</groupId> - <artifactId>guava</artifactId> - </exclusion> - <exclusion> - <groupId>com.googlecode.concurrentlinkedhashmap</groupId> - <artifactId>concurrentlinkedhashmap-lru</artifactId> - </exclusion> - <exclusion> - <groupId>com.ning</groupId> - <artifactId>compress-lzf</artifactId> - </exclusion> - <exclusion> - <groupId>commons-cli</groupId> - <artifactId>commons-cli</artifactId> - </exclusion> - <exclusion> - <groupId>commons-codec</groupId> - <artifactId>commons-codec</artifactId> - </exclusion> - <exclusion> - <groupId>commons-lang</groupId> - <artifactId>commons-lang</artifactId> - </exclusion> - <exclusion> - <groupId>commons-logging</groupId> - <artifactId>commons-logging</artifactId> - </exclusion> - <exclusion> - <groupId>io.netty</groupId> - <artifactId>netty</artifactId> - </exclusion> - <exclusion> - <groupId>jline</groupId> - <artifactId>jline</artifactId> - </exclusion> - <exclusion> - <groupId>net.jpountz.lz4</groupId> - <artifactId>lz4</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.cassandra.deps</groupId> - <artifactId>avro</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.commons</groupId> - <artifactId>commons-math3</artifactId> - </exclusion> - <exclusion> - <groupId>org.apache.thrift</groupId> - <artifactId>libthrift</artifactId> - </exclusion> - </exclusions> + <groupId>org.scala-lang</groupId> + <artifactId>scala-library</artifactId> + <scope>provided</scope> </dependency> <dependency> <groupId>com.github.scopt</groupId> <artifactId>scopt_${scala.binary.version}</artifactId> <version>3.3.0</version> </dependency> + <dependency> + <groupId>com.twitter</groupId> + <artifactId>parquet-hadoop-bundle</artifactId> + <scope>provided</scope> + </dependency> </dependencies> <build> @@ -314,40 +146,9 @@ <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-kinesis-asl_${scala.binary.version}</artifactId> <version>${project.version}</version> + <scope>provided</scope> </dependency> </dependencies> </profile> - - <!-- Profiles that disable inclusion of certain dependencies. --> - <profile> - <id>flume-provided</id> - <properties> - <flume.deps.scope>provided</flume.deps.scope> - </properties> - </profile> - <profile> - <id>hadoop-provided</id> - <properties> - <hadoop.deps.scope>provided</hadoop.deps.scope> - </properties> - </profile> - <profile> - <id>hbase-provided</id> - <properties> - <hbase.deps.scope>provided</hbase.deps.scope> - </properties> - </profile> - <profile> - <id>hive-provided</id> - <properties> - <hive.deps.scope>provided</hive.deps.scope> - </properties> - </profile> - <profile> - <id>parquet-provided</id> - <properties> - <parquet.deps.scope>provided</parquet.deps.scope> - </properties> - </profile> </profiles> </project> |