ARROW-7717: [CI] Have nightly integration test for Spark's latest rel…

…ease Closes apache#6316 from kszucs/spark-2 Authored-by: Krisztián Szűcs <[email protected]> Signed-off-by: Krisztián Szűcs <[email protected]>
pgwhalen · Jul 2, 2020 · 0d789ac · 0d789ac
1 parent bcbb3e2
commit 0d789ac
Show file tree

Hide file tree

Showing 4 changed files with 24 additions and 8 deletions.
diff --git a/ci/docker/conda-python-spark.dockerfile b/ci/docker/conda-python-spark.dockerfile
@@ -34,11 +34,12 @@ RUN conda install -q \
 # installing specific version of spark
 ARG spark=master
 COPY ci/scripts/install_spark.sh /arrow/ci/scripts/
-RUN /arrow/ci/scripts/install_spark.sh ${spark} /spark /arrow/ci/etc
+RUN /arrow/ci/scripts/install_spark.sh ${spark} /spark
 
 # build cpp with tests
 ENV CC=gcc \
     CXX=g++ \
     ARROW_PYTHON=ON \
     ARROW_HDFS=ON \
-    ARROW_BUILD_TESTS=OFF
+    ARROW_BUILD_TESTS=OFF \
+    SPARK_VERSION=${spark}
diff --git a/ci/scripts/install_spark.sh b/ci/scripts/install_spark.sh
@@ -19,14 +19,13 @@
 
 set -e
 
-if [ "$#" -ne 3 ]; then
-  echo "Usage: $0 <spark version> <target directory> <patches directory>"
+if [ "$#" -ne 2 ]; then
+  echo "Usage: $0 <spark version> <target directory>"
   exit 1
 fi
 
 spark=$1
 target=$2
-patches=${3}
 
-mkdir "${target}"
-wget -q -O - https://github.com/apache/spark/archive/${spark}.tar.gz | tar -xzf - --strip-components=1 -C "${target}"
+git clone https://github.com/apache/spark "${target}"
+git -C "${target}" checkout "${spark}"
diff --git a/ci/scripts/integration_spark.sh b/ci/scripts/integration_spark.sh
@@ -20,6 +20,12 @@ set -eu
 
 source_dir=${1}
 spark_dir=${2}
+spark_version=${SPARK_VERSION:-master}
+
+if [ "${SPARK_VERSION:0:2}" == "2." ]; then
+  # https://github.com/apache/spark/blob/master/docs/sql-pyspark-pandas-with-arrow.md#compatibility-setting-for-pyarrow--0150-and-spark-23x-24x
+  export ARROW_PRE_0_15_IPC_FORMAT=1
+fi
 
 pushd ${source_dir}/java
   arrow_version=`mvn org.apache.maven.plugins:maven-help-plugin:2.1.1:evaluate -Dexpression=project.version | sed -n -e '/^\[.*\]/ !{ /^[0-9]/ { p; q } }'`

diff --git a/dev/tasks/tasks.yml b/dev/tasks/tasks.yml
@@ -1917,12 +1917,22 @@ tasks:
         HDFS: 2.9.2
       run: conda-python-hdfs
 
-  test-conda-python-3.7-spark-master:
+  test-conda-python-3.7-spark-branch-3.0:
     ci: github
     template: docker-tests/github.linux.yml
     params:
       env:
         PYTHON: 3.7
+        SPARK: "branch-3.0"
+      # use the master branch of spark, so prevent reusing any layers
+      run: --no-leaf-cache conda-python-spark
+
+  test-conda-python-3.8-spark-master:
+    ci: github
+    template: docker-tests/github.linux.yml
+    params:
+      env:
+        PYTHON: 3.8
         SPARK: master
       # use the master branch of spark, so prevent reusing any layers
       run: --no-leaf-cache conda-python-spark