Merge rev 43511 from the trunk.

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 7ebcb8bd0980a36eb080a0e7cbf7bac201a3da7c..dcceea92055e5bd396e54da3c41b7275ca55db87 100644 (file)
--- a/Lib/random.py
+++ b/Lib/random.py
@@ -285,6 +285,15 @@ class Random(_random.Random):
         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
         # dictionary.
@@ -302,7 +311,9 @@ class Random(_random.Random):
         random = self.random
         _int = int
         result = [None] * k
-        if n < 6 * k:     # if n len list takes less space than a k len dict
+        if n < 6 * k 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))
@@ -316,10 +327,10 @@ class Random(_random.Random):
                     while j in selected:
                         j = _int(random() * n)
                     result[i] = selected[j] = 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 c9431b372647dcf16474119e01705d1549192e3c..bba4c7cf8ba5cda267a2f8c336127d13f1827e6f 100644 (file)
--- a/Lib/test/test_random.py
+++ b/Lib/test/test_random.py
@@ -93,12 +93,28 @@ class TestBasicOps(unittest.TestCase):
         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 1d2f1e8babced12a4d489a439db40845486cdcd9..9de19d983409f037736df35e47dbca296168bdfe 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -4,6 +4,20 @@ Python News
 
 (editors: check NEWS.help for information about editing NEWS using ReST.)
 
+What's New in Python 2.4.4c1?
+=============================
+
+*Release date: DD-MMM-2006*
+
+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.
+
+
 What's New in Python 2.4.3?
 ===========================
 
@@ -14,10 +28,10 @@ Core and builtins
 
 - A few reference leaks were squished.
 
-- A threading issue that caused random segfaults on some platforms from 
+- A threading issue that caused random segfaults on some platforms from
   the testsuite was fixed in test_capi.
 
-- Reverted fix for Bug #1379994: Builtin unicode_escape and 
+- Reverted fix for Bug #1379994: Builtin unicode_escape and
   raw_unicode_escape codec now encodes backslash correctly.
   This caused another issue for unicode repr strings being double-escaped
   (SF Bug #1459029). Correct fix will be in 2.5, but is too risky for 2.4.3.