diff options
| author | Davies Liu <davies@databricks.com> | 2015-02-24 14:50:00 -0800 |
|---|---|---|
| committer | Joseph K. Bradley <joseph@databricks.com> | 2015-02-24 14:50:00 -0800 |
| commit | da505e59274d1c838653c1109db65ad374e65304 (patch) | |
| tree | 4217693d3d266655bd800f8ca678aa5e39e68a93 /python/pyspark/tests.py | |
| parent | a2b9137923e0ba328da8fff2fbbfcf2abf50b033 (diff) | |
| download | spark-da505e59274d1c838653c1109db65ad374e65304.tar.gz spark-da505e59274d1c838653c1109db65ad374e65304.tar.bz2 spark-da505e59274d1c838653c1109db65ad374e65304.zip | |
[SPARK-5973] [PySpark] fix zip with two RDDs with AutoBatchedSerializer
Author: Davies Liu <davies@databricks.com>
Closes #4745 from davies/fix_zip and squashes the following commits:
2124b2c [Davies Liu] Update tests.py
b5c828f [Davies Liu] increase the number of records
c1e40fd [Davies Liu] fix zip with two RDDs with AutoBatchedSerializer
Diffstat (limited to 'python/pyspark/tests.py')
| -rw-r--r-- | python/pyspark/tests.py | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/python/pyspark/tests.py b/python/pyspark/tests.py index 52e82091c9..06ba2b461d 100644 --- a/python/pyspark/tests.py +++ b/python/pyspark/tests.py @@ -543,6 +543,12 @@ class RDDTests(ReusedPySparkTestCase): # regression test for bug in _reserializer() self.assertEqual(cnt, t.zip(rdd).count()) + def test_zip_with_different_object_sizes(self): + # regress test for SPARK-5973 + a = self.sc.parallelize(range(10000)).map(lambda i: '*' * i) + b = self.sc.parallelize(range(10000, 20000)).map(lambda i: '*' * i) + self.assertEqual(10000, a.zip(b).count()) + def test_zip_with_different_number_of_items(self): a = self.sc.parallelize(range(5), 2) # different number of partitions |