Skip to content

[SPARK-31788][CORE][PYTHON] Fix UnionRDD of PairRDDs #28603

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 5 commits into from
Closed

[SPARK-31788][CORE][PYTHON] Fix UnionRDD of PairRDDs #28603

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
28dce3a
Fix UnionRDD of PairRDDs
May 21, 2020
1d8d308
Address review comments
May 22, 2020
5da0ad6
Fix nit
May 22, 2020
66fb353
Fix indentation
May 22, 2020
c65be0d
Condense test
May 22, 2020
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
12 changes: 10 additions & 2 deletions python/pyspark/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
from tempfile import NamedTemporaryFile

from py4j.protocol import Py4JError
from py4j.java_gateway import is_instance_of

from pyspark import accumulators
from pyspark.accumulators import Accumulator
Expand Down Expand Up @@ -864,10 +865,17 @@ def union(self, rdds):
first_jrdd_deserializer = rdds[0]._jrdd_deserializer
if any(x._jrdd_deserializer != first_jrdd_deserializer for x in rdds):
rdds = [x._reserialize() for x in rdds]
gw = SparkContext._gateway
cls = SparkContext._jvm.org.apache.spark.api.java.JavaRDD
jrdds = SparkContext._gateway.new_array(cls, len(rdds))
is_jrdd = is_instance_of(gw, rdds[0]._jrdd, cls)
jrdds = gw.new_array(cls, len(rdds))
for i in range(0, len(rdds)):
jrdds[i] = rdds[i]._jrdd
if is_jrdd:
jrdds[i] = rdds[i]._jrdd
else:
# zip could return JavaPairRDD hence we ensure `_jrdd`
# to be `JavaRDD` by wrapping it in a `map`
jrdds[i] = rdds[i].map(lambda x: x)._jrdd
return RDD(self._jsc.union(jrdds), self, rdds[0]._jrdd_deserializer)

def broadcast(self, value):
Expand Down
9 changes: 9 additions & 0 deletions python/pyspark/tests/test_rdd.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -168,6 +168,15 @@ def test_zip_chaining(self):
set([(x, (x, x)) for x in 'abc'])
)

def test_union_pair_rdd(self):
# Regression test for SPARK-31788
rdd = self.sc.parallelize([1, 2])
pair_rdd = rdd.zip(rdd)
self.assertEqual(
self.sc.union([pair_rdd, pair_rdd]).collect(),
[((1, 1), (2, 2)), ((1, 1), (2, 2))]
)

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