dc126f2121
This adds some changes on top of the initial work by @scrapcodes in #20: The goal here is to do automated checking of Spark commits to determine whether they break binary compatibility. 1. Special case for inner classes of package-private objects. 2. Made tools classes accessible when running `spark-class`. 3. Made some declared types in MLLib more general. 4. Various other improvements to exclude-generation script. 5. In-code documentation. Author: Patrick Wendell <pwendell@gmail.com> Author: Prashant Sharma <prashant.s@imaginea.com> Author: Prashant Sharma <scrapcodes@gmail.com> Closes #207 from pwendell/mima and squashes the following commits: 22ae267 [Patrick Wendell] New binary changes after upmerge 6c2030d [Patrick Wendell] Merge remote-tracking branch 'apache/master' into mima 3666cf1 [Patrick Wendell] Minor style change 0e0f570 [Patrick Wendell] Small fix and removing directory listings 647c547 [Patrick Wendell] Reveiw feedback. c39f3b5 [Patrick Wendell] Some enhancements to binary checking. 4c771e0 [Prashant Sharma] Added a tool to generate mima excludes and also adapted build to pick automatically. b551519 [Prashant Sharma] adding a new exclude after rebasing with master 651844c [Prashant Sharma] Support MiMa for reporting binary compatibility accross versions.
102 lines
4.7 KiB
Bash
Executable file
102 lines
4.7 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
#
|
|
# 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.
|
|
#
|
|
|
|
# This script computes Spark's classpath and prints it to stdout; it's used by both the "run"
|
|
# script and the ExecutorRunner in standalone cluster mode.
|
|
|
|
SCALA_VERSION=2.10
|
|
|
|
# Figure out where Spark is installed
|
|
FWDIR="$(cd `dirname $0`/..; pwd)"
|
|
|
|
# Load environment variables from conf/spark-env.sh, if it exists
|
|
if [ -e "$FWDIR/conf/spark-env.sh" ] ; then
|
|
. $FWDIR/conf/spark-env.sh
|
|
fi
|
|
|
|
# Build up classpath
|
|
CLASSPATH="$SPARK_CLASSPATH:$FWDIR/conf"
|
|
|
|
# Support for interacting with Hive. Since hive pulls in a lot of dependencies that might break
|
|
# existing Spark applications, it is not included in the standard spark assembly. Instead, we only
|
|
# include it in the classpath if the user has explicitly requested it by running "sbt hive/assembly"
|
|
# Hopefully we will find a way to avoid uber-jars entirely and deploy only the needed packages in
|
|
# the future.
|
|
if [ -f "$FWDIR"/sql/hive/target/scala-$SCALA_VERSION/spark-hive-assembly-*.jar ]; then
|
|
echo "Hive assembly found, including hive support. If this isn't desired run sbt hive/clean."
|
|
|
|
# Datanucleus jars do not work if only included in the uberjar as plugin.xml metadata is lost.
|
|
DATANUCLEUSJARS=$(JARS=("$FWDIR/lib_managed/jars"/datanucleus-*.jar); IFS=:; echo "${JARS[*]}")
|
|
CLASSPATH=$CLASSPATH:$DATANUCLEUSJARS
|
|
|
|
ASSEMBLY_DIR="$FWDIR/sql/hive/target/scala-$SCALA_VERSION/"
|
|
else
|
|
ASSEMBLY_DIR="$FWDIR/assembly/target/scala-$SCALA_VERSION/"
|
|
fi
|
|
|
|
# First check if we have a dependencies jar. If so, include binary classes with the deps jar
|
|
if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
|
|
CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/tools/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
|
|
|
|
DEPS_ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark*-assembly*hadoop*-deps.jar`
|
|
CLASSPATH="$CLASSPATH:$DEPS_ASSEMBLY_JAR"
|
|
else
|
|
# Else use spark-assembly jar from either RELEASE or assembly directory
|
|
if [ -f "$FWDIR/RELEASE" ]; then
|
|
ASSEMBLY_JAR=`ls "$FWDIR"/jars/spark*-assembly*.jar`
|
|
else
|
|
ASSEMBLY_JAR=`ls "$ASSEMBLY_DIR"/spark*-assembly*hadoop*.jar`
|
|
fi
|
|
CLASSPATH="$CLASSPATH:$ASSEMBLY_JAR"
|
|
fi
|
|
|
|
# Add test classes if we're running from SBT or Maven with SPARK_TESTING set to 1
|
|
if [[ $SPARK_TESTING == 1 ]]; then
|
|
CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/graphx/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/streaming/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/sql/catalyst/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/test-classes"
|
|
CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/test-classes"
|
|
fi
|
|
|
|
# Add hadoop conf dir if given -- otherwise FileSystem.*, etc fail !
|
|
# Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
|
|
# the configurtion files.
|
|
if [ "x" != "x$HADOOP_CONF_DIR" ]; then
|
|
CLASSPATH="$CLASSPATH:$HADOOP_CONF_DIR"
|
|
fi
|
|
if [ "x" != "x$YARN_CONF_DIR" ]; then
|
|
CLASSPATH="$CLASSPATH:$YARN_CONF_DIR"
|
|
fi
|
|
|
|
echo "$CLASSPATH"
|