Skip to content
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

Jump to bottom

[SPARK-8573] [SPARK-8568] [SQL] [PYSPARK] raise Exception if column is used in booelan expression #6961

Closed
wants to merge 4 commits into from
Closed

[SPARK-8573] [SPARK-8568] [SQL] [PYSPARK] raise Exception if column is used in booelan expression #6961

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f70c08e
raise Exception if column is used in booelan expression
Jun 23, 2015
07dff84
address comments, fix tests
Jun 23, 2015
af74bd6
fix tests
Jun 23, 2015
9f19beb
update message
Jun 23, 2015
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
5 changes: 5 additions & 0 deletions python/pyspark/sql/column.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -396,6 +396,11 @@ def over(self, window):
jc = self._jc.over(window._jspec)
return Column(jc)

def __nonzero__(self):
raise ValueError("Cannot convert column into bool: please use '&' for 'and', '|' for 'or', "
"'~' for 'not' when building DataFrame boolean expressions.")
__bool__ = __nonzero__

def __repr__(self):
return 'Column<%s>' % self._jc.toString().encode('utf8')

Expand Down
10 changes: 9 additions & 1 deletion python/pyspark/sql/tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,14 @@ def test_explode(self):
self.assertEqual(result[0][0], "a")
self.assertEqual(result[0][1], "b")

def test_and_in_expression(self):
self.assertEqual(4, self.df.filter((self.df.key <= 10) & (self.df.value <= "2")).count())
self.assertRaises(ValueError, lambda: (self.df.key <= 10) and (self.df.value <= "2"))
self.assertEqual(14, self.df.filter((self.df.key <= 3) | (self.df.value < "2")).count())
self.assertRaises(ValueError, lambda: self.df.key <= 3 or self.df.value < "2")
self.assertEqual(99, self.df.filter(~(self.df.key == 1)).count())
self.assertRaises(ValueError, lambda: not self.df.key == 1)

def test_udf_with_callable(self):
d = [Row(number=i, squared=i**2) for i in range(10)]
rdd = self.sc.parallelize(d)
Expand Down Expand Up @@ -408,7 +416,7 @@ def test_column_operators(self):
self.assertTrue(isinstance((- ci - 1 - 2) % 3 * 2.5 / 3.5, Column))
rcc = (1 + ci), (1 - ci), (1 * ci), (1 / ci), (1 % ci)
self.assertTrue(all(isinstance(c, Column) for c in rcc))
cb = [ci == 5, ci != 0, ci > 3, ci < 4, ci >= 0, ci <= 7, ci and cs, ci or cs]
cb = [ci == 5, ci != 0, ci > 3, ci < 4, ci >= 0, ci <= 7]
self.assertTrue(all(isinstance(c, Column) for c in cb))
cbool = (ci & ci), (ci | ci), (~ci)
self.assertTrue(all(isinstance(c, Column) for c in cbool))
Expand Down