04e44b37cc
This PR update PySpark to support Python 3 (tested with 3.4). Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped. TODO: ec2/spark-ec2.py is not fully tested with python3. Author: Davies Liu <davies@databricks.com> Author: twneale <twneale@gmail.com> Author: Josh Rosen <joshrosen@databricks.com> Closes #5173 from davies/python3 and squashes the following commits: d7d6323 [Davies Liu] fix tests 6c52a98 [Davies Liu] fix mllib test 99e334f [Davies Liu] update timeout b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 cafd5ec [Davies Liu] adddress comments from @mengxr bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 179fc8d [Davies Liu] tuning flaky tests 8c8b957 [Davies Liu] fix ResourceWarning in Python 3 5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 4006829 [Davies Liu] fix test 2fc0066 [Davies Liu] add python3 path 71535e9 [Davies Liu] fix xrange and divide 5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ed498c8 [Davies Liu] fix compatibility with python 3 820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ad7c374 [Davies Liu] fix mllib test and warning ef1fc2f [Davies Liu] fix tests 4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 59bb492 [Davies Liu] fix tests 1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ca0fdd3 [Davies Liu] fix code style 9563a15 [Davies Liu] add imap back for python 2 0b1ec04 [Davies Liu] make python examples work with Python 3 d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 a716d34 [Davies Liu] test with python 3.4 f1700e8 [Davies Liu] fix test in python3 671b1db [Davies Liu] fix test in python3 692ff47 [Davies Liu] fix flaky test 7b9699f [Davies Liu] invalidate import cache for Python 3.3+ 9c58497 [Davies Liu] fix kill worker 309bfbf [Davies Liu] keep compatibility 5707476 [Davies Liu] cleanup, fix hash of string in 3.3+ 8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 f53e1f0 [Davies Liu] fix tests 70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3 a39167e [Davies Liu] support customize class in __main__ 814c77b [Davies Liu] run unittests with python 3 7f4476e [Davies Liu] mllib tests passed d737924 [Davies Liu] pass ml tests 375ea17 [Davies Liu] SQL tests pass 6cc42a9 [Davies Liu] rename 431a8de [Davies Liu] streaming tests pass 78901a7 [Davies Liu] fix hash of serializer in Python 3 24b2f2e [Davies Liu] pass all RDD tests 35f48fe [Davies Liu] run future again 1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py 6e3c21d [Davies Liu] make cloudpickle work with Python3 2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run 1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out 7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work. b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?). f40d925 [twneale] xrange --> range e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206 79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper 2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3 854be27 [Josh Rosen] Run `futurize` on Python code: 7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.
256 lines
8.6 KiB
Bash
Executable file
256 lines
8.6 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.
|
|
#
|
|
|
|
# Go to the Spark project root directory
|
|
FWDIR="$(cd "`dirname $0`"/..; pwd)"
|
|
cd "$FWDIR"
|
|
|
|
# Clean up work directory and caches
|
|
rm -rf ./work
|
|
rm -rf ~/.ivy2/local/org.apache.spark
|
|
rm -rf ~/.ivy2/cache/org.apache.spark
|
|
|
|
source "$FWDIR/dev/run-tests-codes.sh"
|
|
|
|
CURRENT_BLOCK=$BLOCK_GENERAL
|
|
|
|
function handle_error () {
|
|
echo "[error] Got a return code of $? on line $1 of the run-tests script."
|
|
exit $CURRENT_BLOCK
|
|
}
|
|
|
|
|
|
# Build against the right version of Hadoop.
|
|
{
|
|
if [ -n "$AMPLAB_JENKINS_BUILD_PROFILE" ]; then
|
|
if [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop1.0" ]; then
|
|
export SBT_MAVEN_PROFILES_ARGS="-Dhadoop.version=1.0.4"
|
|
elif [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop2.0" ]; then
|
|
export SBT_MAVEN_PROFILES_ARGS="-Dhadoop.version=2.0.0-mr1-cdh4.1.1"
|
|
elif [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop2.2" ]; then
|
|
export SBT_MAVEN_PROFILES_ARGS="-Pyarn -Phadoop-2.2 -Dhadoop.version=2.2.0"
|
|
elif [ "$AMPLAB_JENKINS_BUILD_PROFILE" = "hadoop2.3" ]; then
|
|
export SBT_MAVEN_PROFILES_ARGS="-Pyarn -Phadoop-2.3 -Dhadoop.version=2.3.0"
|
|
fi
|
|
fi
|
|
|
|
if [ -z "$SBT_MAVEN_PROFILES_ARGS" ]; then
|
|
export SBT_MAVEN_PROFILES_ARGS="-Pyarn -Phadoop-2.3 -Dhadoop.version=2.3.0"
|
|
fi
|
|
}
|
|
|
|
export SBT_MAVEN_PROFILES_ARGS="$SBT_MAVEN_PROFILES_ARGS -Pkinesis-asl"
|
|
|
|
# Determine Java path and version.
|
|
{
|
|
if test -x "$JAVA_HOME/bin/java"; then
|
|
declare java_cmd="$JAVA_HOME/bin/java"
|
|
else
|
|
declare java_cmd=java
|
|
fi
|
|
|
|
# We can't use sed -r -e due to OS X / BSD compatibility; hence, all the parentheses.
|
|
JAVA_VERSION=$(
|
|
$java_cmd -version 2>&1 \
|
|
| grep -e "^java version" --max-count=1 \
|
|
| sed "s/java version \"\(.*\)\.\(.*\)\.\(.*\)\"/\1\2/"
|
|
)
|
|
|
|
if [ "$JAVA_VERSION" -lt 18 ]; then
|
|
echo "[warn] Java 8 tests will not run because JDK version is < 1.8."
|
|
fi
|
|
}
|
|
|
|
# Only run Hive tests if there are SQL changes.
|
|
# Partial solution for SPARK-1455.
|
|
if [ -n "$AMPLAB_JENKINS" ]; then
|
|
git fetch origin master:master
|
|
|
|
sql_diffs=$(
|
|
git diff --name-only master \
|
|
| grep -e "^sql/" -e "^bin/spark-sql" -e "^sbin/start-thriftserver.sh"
|
|
)
|
|
|
|
non_sql_diffs=$(
|
|
git diff --name-only master \
|
|
| grep -v -e "^sql/" -e "^bin/spark-sql" -e "^sbin/start-thriftserver.sh"
|
|
)
|
|
|
|
if [ -n "$sql_diffs" ]; then
|
|
echo "[info] Detected changes in SQL. Will run Hive test suite."
|
|
_RUN_SQL_TESTS=true
|
|
|
|
if [ -z "$non_sql_diffs" ]; then
|
|
echo "[info] Detected no changes except in SQL. Will only run SQL tests."
|
|
_SQL_TESTS_ONLY=true
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
set -o pipefail
|
|
trap 'handle_error $LINENO' ERR
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Running Apache RAT checks"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_RAT
|
|
|
|
./dev/check-license
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Running Scala style checks"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_SCALA_STYLE
|
|
|
|
./dev/lint-scala
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Running Python style checks"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_PYTHON_STYLE
|
|
|
|
./dev/lint-python
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Building Spark"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_BUILD
|
|
|
|
{
|
|
HIVE_BUILD_ARGS="$SBT_MAVEN_PROFILES_ARGS -Phive -Phive-thriftserver"
|
|
HIVE_12_BUILD_ARGS="$HIVE_BUILD_ARGS -Phive-0.12.0"
|
|
|
|
# First build with Hive 0.12.0 to ensure patches do not break the Hive 0.12.0 build
|
|
echo "[info] Compile with Hive 0.12.0"
|
|
[ -d "lib_managed" ] && rm -rf lib_managed
|
|
echo "[info] Building Spark with these arguments: $HIVE_12_BUILD_ARGS"
|
|
|
|
if [ "${AMPLAB_JENKINS_BUILD_TOOL}" == "maven" ]; then
|
|
build/mvn $HIVE_12_BUILD_ARGS clean package -DskipTests
|
|
else
|
|
# NOTE: echo "q" is needed because sbt on encountering a build file with failure
|
|
# (either resolution or compilation) prompts the user for input either q, r, etc
|
|
# to quit or retry. This echo is there to make it not block.
|
|
# NOTE: Do not quote $BUILD_MVN_PROFILE_ARGS or else it will be interpreted as a
|
|
# single argument!
|
|
# QUESTION: Why doesn't 'yes "q"' work?
|
|
# QUESTION: Why doesn't 'grep -v -e "^\[info\] Resolving"' work?
|
|
echo -e "q\n" \
|
|
| build/sbt $HIVE_12_BUILD_ARGS clean hive/compile hive-thriftserver/compile \
|
|
| grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
|
|
fi
|
|
|
|
# Then build with default Hive version (0.13.1) because tests are based on this version
|
|
echo "[info] Compile with Hive 0.13.1"
|
|
[ -d "lib_managed" ] && rm -rf lib_managed
|
|
echo "[info] Building Spark with these arguments: $HIVE_BUILD_ARGS"
|
|
|
|
if [ "${AMPLAB_JENKINS_BUILD_TOOL}" == "maven" ]; then
|
|
build/mvn $HIVE_BUILD_ARGS clean package -DskipTests
|
|
else
|
|
echo -e "q\n" \
|
|
| build/sbt $HIVE_BUILD_ARGS package assembly/assembly streaming-kafka-assembly/assembly \
|
|
| grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
|
|
fi
|
|
}
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Detecting binary incompatibilities with MiMa"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_MIMA
|
|
|
|
./dev/mima
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Running Spark unit tests"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_SPARK_UNIT_TESTS
|
|
|
|
{
|
|
# If the Spark SQL tests are enabled, run the tests with the Hive profiles enabled.
|
|
# This must be a single argument, as it is.
|
|
if [ -n "$_RUN_SQL_TESTS" ]; then
|
|
SBT_MAVEN_PROFILES_ARGS="$SBT_MAVEN_PROFILES_ARGS -Phive -Phive-thriftserver"
|
|
fi
|
|
|
|
if [ -n "$_SQL_TESTS_ONLY" ]; then
|
|
# This must be an array of individual arguments. Otherwise, having one long string
|
|
# will be interpreted as a single test, which doesn't work.
|
|
SBT_MAVEN_TEST_ARGS=("catalyst/test" "sql/test" "hive/test" "hive-thriftserver/test" "mllib/test")
|
|
else
|
|
SBT_MAVEN_TEST_ARGS=("test")
|
|
fi
|
|
|
|
echo "[info] Running Spark tests with these arguments: $SBT_MAVEN_PROFILES_ARGS ${SBT_MAVEN_TEST_ARGS[@]}"
|
|
|
|
if [ "${AMPLAB_JENKINS_BUILD_TOOL}" == "maven" ]; then
|
|
build/mvn test $SBT_MAVEN_PROFILES_ARGS --fail-at-end
|
|
else
|
|
# NOTE: echo "q" is needed because sbt on encountering a build file with failure
|
|
# (either resolution or compilation) prompts the user for input either q, r, etc
|
|
# to quit or retry. This echo is there to make it not block.
|
|
# NOTE: Do not quote $SBT_MAVEN_PROFILES_ARGS or else it will be interpreted as a
|
|
# single argument!
|
|
# "${SBT_MAVEN_TEST_ARGS[@]}" is cool because it's an array.
|
|
# QUESTION: Why doesn't 'yes "q"' work?
|
|
# QUESTION: Why doesn't 'grep -v -e "^\[info\] Resolving"' work?
|
|
echo -e "q\n" \
|
|
| build/sbt $SBT_MAVEN_PROFILES_ARGS "${SBT_MAVEN_TEST_ARGS[@]}" \
|
|
| grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
|
|
fi
|
|
}
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Running PySpark tests"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_PYSPARK_UNIT_TESTS
|
|
|
|
# add path for python 3 in jenkins
|
|
export PATH="${PATH}:/home/anaonda/envs/py3k/bin"
|
|
./python/run-tests
|
|
|
|
echo ""
|
|
echo "========================================================================="
|
|
echo "Running SparkR tests"
|
|
echo "========================================================================="
|
|
|
|
CURRENT_BLOCK=$BLOCK_SPARKR_UNIT_TESTS
|
|
|
|
if [ $(command -v R) ]; then
|
|
./R/install-dev.sh
|
|
./R/run-tests.sh
|
|
else
|
|
echo "Ignoring SparkR tests as R was not found in PATH"
|
|
fi
|
|
|