path: root/dev/run-tests

#!/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

# Remove work directory
rm -rf ./work

if test -x "$JAVA_HOME/bin/java"; then
    declare java_cmd="$JAVA_HOME/bin/java"
else 
    declare java_cmd=java
fi
JAVA_VERSION=$($java_cmd -version 2>&1 | sed 's/java version "\(.*\)\.\(.*\)\..*"/\1\2/; 1q')
[ "$JAVA_VERSION" -ge 18 ] && echo "" || echo "[Warn] Java 8 tests will not run because JDK version is < 1.8."

# Partial solution for SPARK-1455. Only run Hive tests if there are sql changes.
if [ -n "$AMPLAB_JENKINS" ]; then
  git fetch origin master:master
  diffs=`git diff --dirstat master | awk '{ print $2; }' | grep "^sql/"`
  if [ -n "$diffs" ]; then
    echo "Detected changes in SQL. Will run Hive test suite."
    export _RUN_SQL_TESTS=true # exported for PySpark tests
  fi
fi

# Fail fast
set -e
set -o pipefail

echo "========================================================================="
echo "Running Apache RAT checks"
echo "========================================================================="
dev/check-license

echo "========================================================================="
echo "Running Scala style checks"
echo "========================================================================="
dev/scalastyle

echo "========================================================================="
echo "Running Spark unit tests"
echo "========================================================================="
# 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.
if [ -n "$_RUN_SQL_TESTS" ]; then
  echo -e "q\n" | SPARK_HIVE=true sbt/sbt clean assembly test | \
    grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
else
  echo -e "q\n" | sbt/sbt clean assembly test | \
    grep -v -e "info.*Resolving" -e "warn.*Merging" -e "info.*Including"
fi

echo "========================================================================="
echo "Running PySpark tests"
echo "========================================================================="
if [ -z "$PYSPARK_PYTHON" ]; then
  export PYSPARK_PYTHON=/usr/local/bin/python2.7
fi
./python/run-tests

echo "========================================================================="
echo "Detecting binary incompatibilites with MiMa"
echo "========================================================================="
./bin/spark-class org.apache.spark.tools.GenerateMIMAIgnore
echo -e "q\n" | sbt/sbt mima-report-binary-issues | grep -v -e "info.*Resolving"