Repository: spark Updated Branches: refs/heads/branch-1.4 5118abb4e -> 94789f374
[SPARK-11870][STREAMING][PYSPARK] Rethrow the exceptions in TransformFunction and TransformFunctionSerializer TransformFunction and TransformFunctionSerializer don't rethrow the exception, so when any exception happens, it just return None. This will cause some weird NPE and confuse people. Author: Shixiong Zhu <shixi...@databricks.com> Closes #9847 from zsxwing/pyspark-streaming-exception. (cherry picked from commit be7a2cfd978143f6f265eca63e9e24f755bc9f22) Signed-off-by: Tathagata Das <tathagata.das1...@gmail.com> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/94789f37 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/94789f37 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/94789f37 Branch: refs/heads/branch-1.4 Commit: 94789f37400ea534e051d1df19f3a567646979fd Parents: 5118abb Author: Shixiong Zhu <shixi...@databricks.com> Authored: Fri Nov 20 14:23:01 2015 -0800 Committer: Tathagata Das <tathagata.das1...@gmail.com> Committed: Fri Nov 20 14:23:57 2015 -0800 ---------------------------------------------------------------------- python/pyspark/streaming/tests.py | 16 ++++++++++++++++ python/pyspark/streaming/util.py | 3 +++ 2 files changed, 19 insertions(+) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/94789f37/python/pyspark/streaming/tests.py ---------------------------------------------------------------------- diff --git a/python/pyspark/streaming/tests.py b/python/pyspark/streaming/tests.py index ab1cc3f..830fd9e 100644 --- a/python/pyspark/streaming/tests.py +++ b/python/pyspark/streaming/tests.py @@ -376,6 +376,22 @@ class BasicOperationTests(PySparkStreamingTestCase): expected = [[('k', v)] for v in expected] self._test_func(input, func, expected) + def test_failed_func(self): + input = [self.sc.parallelize([d], 1) for d in range(4)] + input_stream = self.ssc.queueStream(input) + + def failed_func(i): + raise ValueError("failed") + + input_stream.map(failed_func).pprint() + self.ssc.start() + try: + self.ssc.awaitTerminationOrTimeout(10) + except: + return + + self.fail("a failed func should throw an error") + class WindowFunctionTests(PySparkStreamingTestCase): http://git-wip-us.apache.org/repos/asf/spark/blob/94789f37/python/pyspark/streaming/util.py ---------------------------------------------------------------------- diff --git a/python/pyspark/streaming/util.py b/python/pyspark/streaming/util.py index 34291f3..0a2773b 100644 --- a/python/pyspark/streaming/util.py +++ b/python/pyspark/streaming/util.py @@ -59,6 +59,7 @@ class TransformFunction(object): return r._jrdd except Exception: traceback.print_exc() + raise def __repr__(self): return "TransformFunction(%s)" % self.func @@ -90,6 +91,7 @@ class TransformFunctionSerializer(object): return bytearray(self.serializer.dumps((func.func, func.deserializers))) except Exception: traceback.print_exc() + raise def loads(self, data): try: @@ -97,6 +99,7 @@ class TransformFunctionSerializer(object): return TransformFunction(self.ctx, f, *deserializers) except Exception: traceback.print_exc() + raise def __repr__(self): return "TransformFunctionSerializer(%s)" % self.serializer --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org