[SPARK-5482][PySpark] Allow individual test suites in python/run-tests #4269
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,132 @@ | ||
| # | ||
| # 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. | ||
| # | ||
|
|
||
| function run_test() { | ||
| echo -en "Running test: $1 ... " | tee -a $LOG_FILE | ||
| start=$(date +"%s") | ||
| SPARK_TESTING=1 time "$FWDIR"/bin/pyspark $1 > $LOG_FILE 2>&1 | ||
|
|
||
| FAILED=$((PIPESTATUS[0]||$FAILED)) | ||
|
|
||
| # Fail and exit on the first test failure. | ||
| if [[ $FAILED != 0 ]]; then | ||
| cat $LOG_FILE | grep -v "^[0-9][0-9]*" # filter all lines starting with a number. | ||
| echo -en "\033[31m" # Red | ||
| echo "Had test failures; see logs." | ||
| echo -en "\033[0m" # No color | ||
| exit -1 | ||
| else | ||
| now=$(date +"%s") | ||
| echo "ok ($(($now - $start))s)" | ||
| fi | ||
| } | ||
|
|
||
| function run_core_tests() { | ||
| if [ $DO_CORE_TESTS == 0 ]; then | ||
| return 0 | ||
| fi | ||
|
|
||
| echo "Run core tests ..." | ||
| run_test "pyspark.rdd" | ||
| run_test "pyspark.context" | ||
| run_test "pyspark.conf" | ||
| run_test "pyspark.broadcast" | ||
| run_test "pyspark.accumulators" | ||
| run_test "pyspark.serializers" | ||
| run_test "pyspark.profiler" | ||
| run_test "pyspark.shuffle" | ||
| run_test "pyspark.tests" | ||
| } | ||
|
|
||
| function run_sql_tests() { | ||
| if [ $DO_SQL_TESTS == 0 ]; then | ||
| return 0 | ||
| fi | ||
|
|
||
| echo "Run sql tests ..." | ||
| run_test "pyspark.sql.types" | ||
| run_test "pyspark.sql.context" | ||
| run_test "pyspark.sql.column" | ||
| run_test "pyspark.sql.dataframe" | ||
| run_test "pyspark.sql.group" | ||
| run_test "pyspark.sql.functions" | ||
| run_test "pyspark.sql.readwriter" | ||
| run_test "pyspark.sql.window" | ||
| run_test "pyspark.sql.tests" | ||
| } | ||
|
|
||
| function run_mllib_tests() { | ||
| if [ $DO_MLLIB_TESTS == 0 ]; then | ||
|
Contributor
There was a problem hiding this comment. From a design perspective, I think it makes more sense to move these conditionals out of the
Contributor
Author
There was a problem hiding this comment. I think it is not good, because if we remove these conditions from here, we must put them into the |
||
| return 0 | ||
| fi | ||
|
|
||
| echo "Run mllib tests ..." | ||
| run_test "pyspark.mllib.classification" | ||
| run_test "pyspark.mllib.clustering" | ||
| run_test "pyspark.mllib.evaluation" | ||
| run_test "pyspark.mllib.feature" | ||
| run_test "pyspark.mllib.fpm" | ||
| run_test "pyspark.mllib.linalg" | ||
| run_test "pyspark.mllib.random" | ||
| run_test "pyspark.mllib.recommendation" | ||
| run_test "pyspark.mllib.regression" | ||
| run_test "pyspark.mllib.stat._statistics" | ||
| run_test "pyspark.mllib.stat.KernelDensity" | ||
| run_test "pyspark.mllib.tree" | ||
| run_test "pyspark.mllib.util" | ||
| run_test "pyspark.mllib.tests" | ||
| } | ||
|
|
||
| function run_ml_tests() { | ||
| if [ $DO_ML_TESTS == 0 ]; then | ||
| return 0 | ||
| fi | ||
|
|
||
| echo "Run ml tests ..." | ||
| run_test "pyspark.ml.feature" | ||
| run_test "pyspark.ml.classification" | ||
| run_test "pyspark.ml.recommendation" | ||
| run_test "pyspark.ml.regression" | ||
| run_test "pyspark.ml.tuning" | ||
| run_test "pyspark.ml.tests" | ||
| run_test "pyspark.ml.evaluation" | ||
| } | ||
|
|
||
| function run_streaming_tests() { | ||
| if [ $DO_STREAMING_TESTS == 0 ]; then | ||
| return 0 | ||
| fi | ||
|
|
||
| echo "Run streaming tests ..." | ||
|
|
||
| KAFKA_ASSEMBLY_DIR="$FWDIR"/external/kafka-assembly | ||
| JAR_PATH="${KAFKA_ASSEMBLY_DIR}/target/scala-${SPARK_SCALA_VERSION}" | ||
| for f in "${JAR_PATH}"/spark-streaming-kafka-assembly-*.jar; do | ||
| if [[ ! -e "$f" ]]; then | ||
| echo "Failed to find Spark Streaming Kafka assembly jar in $KAFKA_ASSEMBLY_DIR" 1>&2 | ||
| echo "You need to build Spark with " \ | ||
| "'build/sbt assembly/assembly streaming-kafka-assembly/assembly' or" \ | ||
| "'build/mvn package' before running this program" 1>&2 | ||
| exit 1 | ||
| fi | ||
| KAFKA_ASSEMBLY_JAR="$f" | ||
| done | ||
|
|
||
| export PYSPARK_SUBMIT_ARGS="--jars ${KAFKA_ASSEMBLY_JAR} pyspark-shell" | ||
| run_test "pyspark.streaming.util" | ||
| run_test "pyspark.streaming.tests" | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is supposed to be an array I guess but this doesn't look like the typical Bash syntax for arrays?