diff options
| author | Marcelo Vanzin <vanzin@cloudera.com> | 2016-04-04 16:52:21 -0700 |
|---|---|---|
| committer | Josh Rosen <joshrosen@databricks.com> | 2016-04-04 16:52:22 -0700 |
| commit | 24d7d2e453ab5eef6099a32fb9e8ed60f6ada93a (patch) | |
| tree | 2069beb0e471afa4e1b1867efe786100b7f77f79 /python/run-tests.py | |
| parent | 400b2f863ffaa01a34a8dae1541c61526fef908b (diff) | |
| download | spark-24d7d2e453ab5eef6099a32fb9e8ed60f6ada93a.tar.gz spark-24d7d2e453ab5eef6099a32fb9e8ed60f6ada93a.tar.bz2 spark-24d7d2e453ab5eef6099a32fb9e8ed60f6ada93a.zip | |
[SPARK-13579][BUILD] Stop building the main Spark assembly.
This change modifies the "assembly/" module to just copy needed
dependencies to its build directory, and modifies the packaging
script to pick those up (and remove duplicate jars packages in the
examples module).
I also made some minor adjustments to dependencies to remove some
test jars from the final packaging, and remove jars that conflict with each
other when packaged separately (e.g. servlet api).
Also note that this change restores guava in applications' classpaths, even
though it's still shaded inside Spark. This is now needed for the Hadoop
libraries that are packaged with Spark, which now are not processed by
the shade plugin.
Author: Marcelo Vanzin <vanzin@cloudera.com>
Closes #11796 from vanzin/SPARK-13579.
Diffstat (limited to 'python/run-tests.py')
| -rwxr-xr-x | python/run-tests.py | 18 |
1 files changed, 16 insertions, 2 deletions
diff --git a/python/run-tests.py b/python/run-tests.py index a9f8854e6f..38b3bb84c1 100755 --- a/python/run-tests.py +++ b/python/run-tests.py @@ -53,11 +53,25 @@ LOG_FILE = os.path.join(SPARK_HOME, "python/unit-tests.log") FAILURE_REPORTING_LOCK = Lock() LOGGER = logging.getLogger() +# Find out where the assembly jars are located. +for scala in ["2.11", "2.10"]: + build_dir = os.path.join(SPARK_HOME, "assembly", "target", "scala-" + scala) + if os.path.isdir(build_dir): + SPARK_DIST_CLASSPATH = os.path.join(build_dir, "jars", "*") + break +else: + raise Exception("Cannot find assembly build directory, please build Spark first.") + def run_individual_python_test(test_name, pyspark_python): env = dict(os.environ) - env.update({'SPARK_TESTING': '1', 'PYSPARK_PYTHON': which(pyspark_python), - 'PYSPARK_DRIVER_PYTHON': which(pyspark_python)}) + env.update({ + 'SPARK_DIST_CLASSPATH': SPARK_DIST_CLASSPATH, + 'SPARK_TESTING': '1', + 'SPARK_PREPEND_CLASSES': '1', + 'PYSPARK_PYTHON': which(pyspark_python), + 'PYSPARK_DRIVER_PYTHON': which(pyspark_python) + }) LOGGER.debug("Starting test(%s): %s", pyspark_python, test_name) start_time = time.time() try: |