Another crack at bug #1460340: make random.sample(dict)
work, this time by ugly brute force.
diff --git a/Lib/random.py b/Lib/random.py
index 943fa51..465f477 100644
--- a/Lib/random.py
+++ b/Lib/random.py
@@ -285,6 +285,15 @@
large population: sample(xrange(10000000), 60)
"""
+ # XXX Although the documentation says `population` is "a sequence",
+ # XXX attempts are made to cater to any iterable with a __len__
+ # XXX method. This has had mixed success. Examples from both
+ # XXX sides: sets work fine, and should become officially supported;
+ # XXX dicts are much harder, and have failed in various subtle
+ # XXX ways across attempts. Support for mapping types should probably
+ # XXX be dropped (and users should pass mapping.keys() or .values()
+ # XXX explicitly).
+
# Sampling without replacement entails tracking either potential
# selections (the pool) in a list or previous selections in a set.
@@ -304,7 +313,9 @@
setsize = 21 # size of a small set minus size of an empty list
if k > 5:
setsize += 4 ** _ceil(_log(k * 3, 4)) # table size for big sets
- if n <= setsize: # is an n-length list smaller than a k-length set
+ if n <= setsize or hasattr(population, "keys"):
+ # An n-length list is smaller than a k-length set, or this is a
+ # mapping type so the other algorithm wouldn't work.
pool = list(population)
for i in xrange(k): # invariant: non-selected at [0,n-i)
j = _int(random() * (n-i))
@@ -320,10 +331,10 @@
j = _int(random() * n)
selected_add(j)
result[i] = population[j]
- except (TypeError, KeyError): # handle sets and dictionaries
+ except (TypeError, KeyError): # handle (at least) sets
if isinstance(population, list):
raise
- return self.sample(list(population), k)
+ return self.sample(tuple(population), k)
return result
## -------------------- real-valued distributions -------------------
diff --git a/Lib/test/test_random.py b/Lib/test/test_random.py
index c9431b3..bba4c7c 100644
--- a/Lib/test/test_random.py
+++ b/Lib/test/test_random.py
@@ -93,12 +93,28 @@
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_sample_on_dicts(self):
+ self.gen.sample(dict.fromkeys('abcdefghijklmnopqrst'), 2)
+
# SF bug #1460340 -- random.sample can raise KeyError
a = dict.fromkeys(range(10)+range(10,100,2)+range(100,110))
- self.gen.sample(a,3)
+ self.gen.sample(a, 3)
+
+ # A followup to bug #1460340: sampling from a dict could return
+ # a subset of its keys or of its values, depending on the size of
+ # the subset requested.
+ N = 30
+ d = dict((i, complex(i, i)) for i in xrange(N))
+ for k in xrange(N+1):
+ samp = self.gen.sample(d, k)
+ # Verify that we got ints back (keys); the values are complex.
+ for x in samp:
+ self.assert_(type(x) is int)
+ samp.sort()
+ self.assertEqual(samp, range(N))
def test_gauss(self):
# Ensure that the seed() method initializes all the hidden state. In
diff --git a/Misc/NEWS b/Misc/NEWS
index ea5095f..974712a 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -489,6 +489,11 @@
Library
-------
+- Bug #1460340: ``random.sample(dict)`` failed in various ways. Dicts
+ aren't officially supported here, and trying to use them will probably
+ raise an exception some day. But dicts have been allowed, and "mostly
+ worked", so support for them won't go away without warning.
+
- Bug #1445068: getpass.getpass() can now be given an explicit stream
argument to specify where to write the prompt.