Skip to content

[SPARK-21985][PYTHON] Fix zip-chained RDD to work #19228

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[SPARK-21985][PYTHON] Fix zip-chained RDD to work #19228

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions python/pyspark/serializers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -316,8 +316,9 @@ def _load_stream_without_unbatching(self, stream):
key_batch_stream = self.key_ser._load_stream_without_unbatching(stream)
val_batch_stream = self.val_ser._load_stream_without_unbatching(stream)
for (key_batch, val_batch) in zip(key_batch_stream, val_batch_stream):
# for correctness with repeated cartesian/zip this must be returned as one batch
yield product(key_batch, val_batch)
# for correctness with repeated cartesian/zip this must be returned as
# one batch (a list)
yield list(product(key_batch, val_batch))

def load_stream(self, stream):
return chain.from_iterable(self._load_stream_without_unbatching(stream))
Expand Down Expand Up @@ -346,8 +347,9 @@ def _load_stream_without_unbatching(self, stream):
if len(key_batch) != len(val_batch):
raise ValueError("Can not deserialize PairRDD with different number of items"
" in batches: (%d, %d)" % (len(key_batch), len(val_batch)))
# for correctness with repeated cartesian/zip this must be returned as one batch
yield zip(key_batch, val_batch)
# for correctness with repeated cartesian/zip this must be returned as
# one batch (a list)
yield list(zip(key_batch, val_batch))

def load_stream(self, stream):
return chain.from_iterable(self._load_stream_without_unbatching(stream))
Expand Down
13 changes: 13 additions & 0 deletions python/pyspark/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -644,6 +644,19 @@ def test_cartesian_chaining(self):
set([(x, (y, y)) for x in range(10) for y in range(10)])
)

def test_zip_chaining(self):
# Tests for SPARK-21985
rdd = self.sc.parallelize(range(3), 2)
self.assertSetEqual(
set(rdd.zip(rdd).zip(rdd).collect()),
set(zip(zip(range(3), range(3)), range(3)))
)

self.assertSetEqual(
set(rdd.zip(rdd.zip(rdd)).collect()),
set(zip(range(3), zip(range(3), range(3))))
)

def test_deleting_input_files(self):
# Regression test for SPARK-1025
tempFile = tempfile.NamedTemporaryFile(delete=False)
Expand Down