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.
diff --git a/Lib/random.py b/Lib/random.py
index 7210f62..2530c39 100644
--- a/Lib/random.py
+++ b/Lib/random.py
@@ -258,6 +258,10 @@
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)
diff --git a/Lib/test/test_random.py b/Lib/test/test_random.py
index c9103e8..fbd4184 100644
--- a/Lib/test/test_random.py
+++ b/Lib/test/test_random.py
@@ -86,6 +86,16 @@
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