Skip to content

[SPARK-20685] Fix BatchPythonEvaluation bug in case of single UDF w/ repeated arg. #17927

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 2 commits into from
Closed

[SPARK-20685] Fix BatchPythonEvaluation bug in case of single UDF w/ repeated arg. #17927

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6912cb2
Add (failing) regression test.
JoshRosen May 9, 2017
17e69b5
Fix SPARK-20685
JoshRosen May 9, 2017
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
6 changes: 6 additions & 0 deletions python/pyspark/sql/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -324,6 +324,12 @@ def test_chained_udf(self):
[row] = self.spark.sql("SELECT double(double(1) + 1)").collect()
self.assertEqual(row[0], 6)

def test_single_udf_with_repeated_argument(self):
# regression test for SPARK-20685
self.spark.catalog.registerFunction("add", lambda x, y: x + y, IntegerType())
row = self.spark.sql("SELECT add(1, 1)").first()
self.assertEqual(tuple(row), (2, ))

def test_multiple_udfs(self):
self.spark.catalog.registerFunction("double", lambda x: x * 2, IntegerType())
[row] = self.spark.sql("SELECT double(1), double(2)").collect()
Expand Down
29 changes: 13 additions & 16 deletions python/pyspark/worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,22 +87,19 @@ def read_single_udf(pickleSer, infile):

def read_udfs(pickleSer, infile):
num_udfs = read_int(infile)
if num_udfs == 1:
# fast path for single UDF
_, udf = read_single_udf(pickleSer, infile)
mapper = lambda a: udf(*a)
else:
udfs = {}
call_udf = []
for i in range(num_udfs):
arg_offsets, udf = read_single_udf(pickleSer, infile)
udfs['f%d' % i] = udf
args = ["a[%d]" % o for o in arg_offsets]
call_udf.append("f%d(%s)" % (i, ", ".join(args)))
# Create function like this:
# lambda a: (f0(a0), f1(a1, a2), f2(a3))
mapper_str = "lambda a: (%s)" % (", ".join(call_udf))
mapper = eval(mapper_str, udfs)
udfs = {}
call_udf = []
for i in range(num_udfs):
arg_offsets, udf = read_single_udf(pickleSer, infile)
udfs['f%d' % i] = udf
args = ["a[%d]" % o for o in arg_offsets]
call_udf.append("f%d(%s)" % (i, ", ".join(args)))
# Create function like this:
# lambda a: (f0(a0), f1(a1, a2), f2(a3))
# In the special case of a single UDF this will return a single result rather
# than a tuple of results; this is the format that the JVM side expects.
mapper_str = "lambda a: (%s)" % (", ".join(call_udf))
mapper = eval(mapper_str, udfs)

func = lambda _, it: map(mapper, it)
ser = BatchedSerializer(PickleSerializer(), 100)
Expand Down