SF bug #801342: Bug (documentation or real, your choice) in random.sample.

random.sample() uses one of two algorithms depending on the ratio of the
sample size to the population size.  One of the algorithms accepted any
iterable population argument so long as it defined __len__().  The other
had a stronger requirement that the population argument be indexable.

While it met the documentation specifications which insisted that the
population argument be a sequence, it made random.sample() less usable
with sets.  So, the second algorithm was modified to coerce non-indexable
iterables and dictionaries into a tuple before proceeding.
This commit is contained in:
Raymond Hettinger 2003-09-06 04:25:54 +00:00
parent c8b08b446a
commit 66d09f1b30
2 changed files with 14 additions and 0 deletions

View File

@ -258,6 +258,10 @@ class Random(_random.Random):
result[i] = pool[j]
pool[j] = pool[n-i-1] # move non-selected item into vacancy
else:
try:
n > 0 and (population[0], population[n//2], population[n-1])
except (TypeError, KeyError): # handle sets and dictionaries
population = tuple(population)
selected = {}
for i in xrange(k):
j = _int(random() * n)

View File

@ -86,6 +86,16 @@ class TestBasicOps(unittest.TestCase):
else:
self.fail()
def test_sample_inputs(self):
# SF bug #801342 -- population can be any iterable defining __len__()
from sets import Set
self.gen.sample(Set(range(20)), 2)
self.gen.sample(range(20), 2)
self.gen.sample(xrange(20), 2)
self.gen.sample(dict.fromkeys('abcdefghijklmnopqrst'), 2)
self.gen.sample(str('abcdefghijklmnopqrst'), 2)
self.gen.sample(tuple('abcdefghijklmnopqrst'), 2)
def test_gauss(self):
# Ensure that the seed() method initializes all the hidden state. In
# particular, through 2.2.1 it failed to reset a piece of state used