[3.12] gh-130285: Fix handling of zero or empty counts in random.sample() (gh-130291) (gh-130417)

This commit is contained in:
Miss Islington (bot) 2025-02-21 18:48:46 +01:00 committed by GitHub
parent 91e5e246b3
commit 8db2fa2575
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 21 additions and 5 deletions

View file

@ -417,11 +417,11 @@ class Random(_random.Random):
cum_counts = list(_accumulate(counts)) cum_counts = list(_accumulate(counts))
if len(cum_counts) != n: if len(cum_counts) != n:
raise ValueError('The number of counts does not match the population') raise ValueError('The number of counts does not match the population')
total = cum_counts.pop() total = cum_counts.pop() if cum_counts else 0
if not isinstance(total, int): if not isinstance(total, int):
raise TypeError('Counts must be integers') raise TypeError('Counts must be integers')
if total <= 0: if total < 0:
raise ValueError('Total of counts must be greater than zero') raise ValueError('Counts must be non-negative')
selections = self.sample(range(total), k=k) selections = self.sample(range(total), k=k)
bisect = _bisect bisect = _bisect
return [population[bisect(cum_counts, s)] for s in selections] return [population[bisect(cum_counts, s)] for s in selections]

View file

@ -224,8 +224,6 @@ class TestBasicOps:
sample(['red', 'green', 'blue'], counts=10, k=10) # counts not iterable sample(['red', 'green', 'blue'], counts=10, k=10) # counts not iterable
with self.assertRaises(ValueError): with self.assertRaises(ValueError):
sample(['red', 'green', 'blue'], counts=[-3, -7, -8], k=2) # counts are negative sample(['red', 'green', 'blue'], counts=[-3, -7, -8], k=2) # counts are negative
with self.assertRaises(ValueError):
sample(['red', 'green', 'blue'], counts=[0, 0, 0], k=2) # counts are zero
with self.assertRaises(ValueError): with self.assertRaises(ValueError):
sample(['red', 'green'], counts=[10, 10], k=21) # population too small sample(['red', 'green'], counts=[10, 10], k=21) # population too small
with self.assertRaises(ValueError): with self.assertRaises(ValueError):
@ -233,6 +231,20 @@ class TestBasicOps:
with self.assertRaises(ValueError): with self.assertRaises(ValueError):
sample(['red', 'green', 'blue'], counts=[1, 2, 3, 4], k=2) # too many counts sample(['red', 'green', 'blue'], counts=[1, 2, 3, 4], k=2) # too many counts
# Cases with zero counts match equivalents without counts (see gh-130285)
self.assertEqual(
sample('abc', k=0, counts=[0, 0, 0]),
sample([], k=0),
)
self.assertEqual(
sample([], 0, counts=[]),
sample([], 0),
)
with self.assertRaises(ValueError):
sample([], 1, counts=[])
with self.assertRaises(ValueError):
sample('x', 1, counts=[0])
def test_choices(self): def test_choices(self):
choices = self.gen.choices choices = self.gen.choices
data = ['red', 'green', 'blue', 'yellow'] data = ['red', 'green', 'blue', 'yellow']

View file

@ -0,0 +1,4 @@
Fix corner case for :func:`random.sample` allowing the *counts* parameter to
specify an empty population. So now, ``sample([], 0, counts=[])`` and
``sample('abc', k=0, counts=[0, 0, 0])`` both give the same result as
``sample([], 0)``.