A new, and much hairier, implementation of astimezone(), building on

an idea from Guido.  This restores that the datetime implementation
never passes a datetime d to a tzinfo method unless d.tzinfo is the
tzinfo instance whose method is being called.  That in turn allows
enormous simplifications in user-written tzinfo classes (see the Python
sandbox US.py and EU.py for fully fleshed-out examples).

d.astimezone(tz) also raises ValueError now if d lands in the one hour
of the year that can't be expressed in tz (this can happen iff tz models
both standard and daylight time).  That it used to return a nonsense
result always ate at me, and it turned out that it seemed impossible to
force a consistent nonsense result under the new implementation (which
doesn't know anything about how tzinfo classes implement their methods --
it can only infer properties indirectly).  Guido doesn't like this --
expect it to change.

New tests of conversion between adjacent DST-aware timezones don't pass
yet, and are commented out.

Running the datetime tests in a loop under a debug build leaks 9
references per test run, but I don't believe the datetime code is the
cause (it didn't leak the last time I changed the C code, and the leak
is the same if I disable all the tests that invoke the only function
that changed here).  I'll pursue that next.

Lib/test/test_datetime.py

@@ -2560,16 +2560,7 @@ def dst(self, dt):
             # An exception instead may be sensible here, in one or more of
             # the cases.
             return ZERO
-
+        assert dt.tzinfo is self
-        convert_endpoints_to_utc = False
-        if dt.tzinfo is not self:
-            # Convert dt to UTC.
-            offset = dt.utcoffset()
-            if offset is None:
-                # Again, an exception instead may be sensible.
-                return ZERO
-            convert_endpoints_to_utc = True
-            dt -= offset
 
         # Find first Sunday in April.
         start = first_sunday_on_or_after(DSTSTART.replace(year=dt.year))
@@ -2579,10 +2570,6 @@ def dst(self, dt):
         end = first_sunday_on_or_after(DSTEND.replace(year=dt.year))
         assert end.weekday() == 6 and end.month == 10 and end.day >= 25
 
-        if convert_endpoints_to_utc:
-            start -= self.stdoffset    # start is in std time
-            end -= self.stdoffset + HOUR # end is in DST time
-
         # Can't compare naive to aware objects, so strip the timezone from
         # dt first.
         if start <= dt.astimezone(None) < end:
@@ -2591,6 +2578,8 @@ def dst(self, dt):
             return ZERO
 
 Eastern  = USTimeZone(-5, "Eastern",  "EST", "EDT")
+Central  = USTimeZone(-6, "Central",  "CST", "CDT")
+Mountain = USTimeZone(-7, "Mountain", "MST", "MDT")
 Pacific  = USTimeZone(-8, "Pacific",  "PST", "PDT")
 utc_real = FixedOffset(0, "UTC", 0)
 # For better test coverage, we want another flavor of UTC that's west of
@@ -2602,25 +2591,17 @@ class TestTimezoneConversions(unittest.TestCase):
     dston = datetimetz(2002, 4, 7, 2)
     dstoff = datetimetz(2002, 10, 27, 2)
 
-    def convert_between_tz_and_utc(self, tz, utc):
-        dston = self.dston.replace(tzinfo=tz)
-        dstoff = self.dstoff.replace(tzinfo=tz)
-        for delta in (timedelta(weeks=13),
-                      DAY,
-                      HOUR,
-                      timedelta(minutes=1),
-                      timedelta(microseconds=1)):
 
-            for during in dston, dston + delta, dstoff - delta:
+    # Check a time that's inside DST.
-                self.assertEqual(during.dst(), HOUR)
+    def checkinside(self, dt, tz, utc, dston, dstoff):
+        self.assertEqual(dt.dst(), HOUR)
 
         # Conversion to our own timezone is always an identity.
-                self.assertEqual(during.astimezone(tz), during)
+        self.assertEqual(dt.astimezone(tz), dt)
         # Conversion to None is always the same as stripping tzinfo.
-                self.assertEqual(during.astimezone(None),
+        self.assertEqual(dt.astimezone(None), dt.replace(tzinfo=None))
-                                 during.replace(tzinfo=None))
 
-                asutc = during.astimezone(utc)
+        asutc = dt.astimezone(utc)
         there_and_back = asutc.astimezone(tz)
 
         # Conversion to UTC and back isn't always an identity here,
@@ -2631,19 +2612,19 @@ def convert_between_tz_and_utc(self, tz, utc):
         # daylight time then (it's "after 2am"), really an alias
         # for 1:MM:SS standard time.  The latter form is what
         # conversion back from UTC produces.
-                if during.date() == dston.date() and during.hour == 2:
+        if dt.date() == dston.date() and dt.hour == 2:
             # We're in the redundant hour, and coming back from
             # UTC gives the 1:MM:SS standard-time spelling.
-                    self.assertEqual(there_and_back + HOUR, during)
+            self.assertEqual(there_and_back + HOUR, dt)
             # Although during was considered to be in daylight
             # time, there_and_back is not.
             self.assertEqual(there_and_back.dst(), ZERO)
             # They're the same times in UTC.
             self.assertEqual(there_and_back.astimezone(utc),
-                                     during.astimezone(utc))
+                             dt.astimezone(utc))
         else:
             # We're not in the redundant hour.
-                    self.assertEqual(during, there_and_back)
+            self.assertEqual(dt, there_and_back)
 
         # Because we have a redundant spelling when DST begins,
         # there is (unforunately) an hour when DST ends that can't
@@ -2654,8 +2635,7 @@ def convert_between_tz_and_utc(self, tz, utc):
         # standard time.  The hour 1:MM:SS standard time ==
         # 2:MM:SS daylight time can't be expressed in local time.
         nexthour_utc = asutc + HOUR
-                nexthour_tz = nexthour_utc.astimezone(tz)
+        if dt.date() == dstoff.date() and dt.hour == 1:
-                if during.date() == dstoff.date() and during.hour == 1:
             # We're in the hour before DST ends.  The hour after
             # is ineffable.
             # For concreteness, picture Eastern.  during is of
@@ -2668,20 +2648,37 @@ def convert_between_tz_and_utc(self, tz, utc):
             # That's correct, too, *if* 1:MM:SS were taken as
             # being standard time.  But it's not -- on this day
             # it's taken as daylight time.
-                    self.assertEqual(during, nexthour_tz)
+            self.assertRaises(ValueError,
+                              nexthour_utc.astimezone, tz)
         else:
-                    self.assertEqual(nexthour_tz - during, HOUR)
+            nexthour_tz = nexthour_utc.astimezone(utc)
+            self.assertEqual(nexthour_tz - dt, HOUR)
 
-            for outside in dston - delta, dstoff, dstoff + delta:
+    # Check a time that's outside DST.
-                self.assertEqual(outside.dst(), ZERO)
+    def checkoutside(self, dt, tz, utc):
-                there_and_back = outside.astimezone(utc).astimezone(tz)
+        self.assertEqual(dt.dst(), ZERO)
-                self.assertEqual(outside, there_and_back)
 
         # Conversion to our own timezone is always an identity.
-                self.assertEqual(outside.astimezone(tz), outside)
+        self.assertEqual(dt.astimezone(tz), dt)
         # Conversion to None is always the same as stripping tzinfo.
-                self.assertEqual(outside.astimezone(None),
+        self.assertEqual(dt.astimezone(None), dt.replace(tzinfo=None))
-                                 outside.replace(tzinfo=None))
+
+    def convert_between_tz_and_utc(self, tz, utc):
+        dston = self.dston.replace(tzinfo=tz)
+        dstoff = self.dstoff.replace(tzinfo=tz)
+        for delta in (timedelta(weeks=13),
+                      DAY,
+                      HOUR,
+                      timedelta(minutes=1),
+                      timedelta(microseconds=1)):
+
+            self.checkinside(dston, tz, utc, dston, dstoff)
+            for during in dston + delta, dstoff - delta:
+                self.checkinside(during, tz, utc, dston, dstoff)
+
+            self.checkoutside(dstoff, tz, utc)
+            for outside in dston - delta, dstoff + delta:
+                self.checkoutside(outside, tz, utc)
 
     def test_easy(self):
         # Despite the name of this test, the endcases are excruciating.
@@ -2694,6 +2691,9 @@ def test_easy(self):
         # hours" don't overlap.
         self.convert_between_tz_and_utc(Eastern, Pacific)
         self.convert_between_tz_and_utc(Pacific, Eastern)
+        # XXX These fail!
+        #self.convert_between_tz_and_utc(Eastern, Central)
+        #self.convert_between_tz_and_utc(Central, Eastern)
 
 
 def test_suite():

Modules/datetimemodule.c

@@ -4751,6 +4751,11 @@ datetimetz_astimezone(PyDateTime_DateTimeTZ *self, PyObject *args,
 	int ss = DATE_GET_SECOND(self);
 	int us = DATE_GET_MICROSECOND(self);
 
+	PyObject *result;
+	PyObject *temp;
+	int myoff, otoff, newoff;
+	int none;
+
 	PyObject *tzinfo;
 	static char *keywords[] = {"tz", NULL};
 
@@ -4760,30 +4765,127 @@ datetimetz_astimezone(PyDateTime_DateTimeTZ *self, PyObject *args,
 	if (check_tzinfo_subclass(tzinfo) < 0)
 		return NULL;
 
-	if (tzinfo != Py_None && self->tzinfo != Py_None) {
+        /* Don't call utcoffset unless necessary. */
-		int none;
+	result = new_datetimetz(y, m, d, hh, mm, ss, us, tzinfo);
-		int selfoffset;
+	if (result == NULL ||
-		selfoffset = call_utcoffset(self->tzinfo,
+	    tzinfo == Py_None ||
-					    (PyObject *)self,
+	    self->tzinfo == Py_None ||
-					    &none);
+	    self->tzinfo == tzinfo)
-	        if (selfoffset == -1 && PyErr_Occurred())
+		return result;
-	        	return NULL;
+
-	        if (! none) {
+        /* Get the offsets.  If either object turns out to be naive, again
-			int tzoffset;
+         * there's no conversion of date or time fields.
-	        	tzoffset = call_utcoffset(tzinfo,
+         */
-	        				  (PyObject *)self,
+	myoff = call_utcoffset(self->tzinfo, (PyObject *)self, &none);
-	        				  &none);
+	if (myoff == -1 && PyErr_Occurred())
-	        	if (tzoffset == -1 && PyErr_Occurred())
+		goto Fail;
-	        		return NULL;
+	if (none)
-	        	if (! none) {
+		return result;
-	        		mm -= selfoffset - tzoffset;
+
-	        		if (normalize_datetime(&y, &m, &d,
+	otoff = call_utcoffset(tzinfo, result, &none);
-	        				       &hh, &mm, &ss, &us) < 0)
+	if (otoff == -1 && PyErr_Occurred())
-	        			return NULL;
+		goto Fail;
+	if (none)
+		return result;
+
+	/* Add otoff-myoff to result. */
+	mm += otoff - myoff;
+	if (normalize_datetime(&y, &m, &d, &hh, &mm, &ss, &us) < 0)
+		goto Fail;
+	temp = new_datetimetz(y, m, d, hh, mm, ss, us, tzinfo);
+	if (temp == NULL)
+		goto Fail;
+	Py_DECREF(result);
+	result = temp;
+
+	/* If tz is a fixed-offset class, we're done, but we can't know
+	 * whether it is.  If it's a DST-aware class, and we're not near a
+	 * DST boundary, we're also done.  If we crossed a DST boundary,
+	 * the offset will be different now, and that's our only clue.
+	 * Unfortunately, we can be in trouble even if we didn't cross a
+	 * DST boundary, if we landed on one of the DST "problem hours".
+	 */
+	newoff = call_utcoffset(tzinfo, result, &none);
+	if (newoff == -1 && PyErr_Occurred())
+		goto Fail;
+	if (none)
+		goto Inconsistent;
+
+	if (newoff != otoff) {
+		/* We did cross a boundary.  Try to correct. */
+		mm += newoff - otoff;
+		if (normalize_datetime(&y, &m, &d, &hh, &mm, &ss, &us) < 0)
+			goto Fail;
+		temp = new_datetimetz(y, m, d, hh, mm, ss, us, tzinfo);
+		if (temp == NULL)
+			goto Fail;
+		Py_DECREF(result);
+		result = temp;
+
+		otoff = call_utcoffset(tzinfo, result, &none);
+		if (otoff == -1 && PyErr_Occurred())
+			goto Fail;
+		if (none)
+			goto Inconsistent;
         }
+	/* If this is the first hour of DST, it may be a local time that
+	 * doesn't make sense on the local clock, in which case the naive
+	 * hour before it (in standard time) is equivalent and does make
+	 * sense on the local clock.  So force that.
+	 */
+	hh -= 1;
+	if (normalize_datetime(&y, &m, &d, &hh, &mm, &ss, &us) < 0)
+		goto Fail;
+	temp = new_datetimetz(y, m, d, hh, mm, ss, us, tzinfo);
+	if (temp == NULL)
+		goto Fail;
+	newoff = call_utcoffset(tzinfo, temp, &none);
+	if (newoff == -1 && PyErr_Occurred()) {
+		Py_DECREF(temp);
+		goto Fail;
 	}
+	if (none) {
+		Py_DECREF(temp);
+		goto Inconsistent;
 	}
-	return new_datetimetz(y, m, d, hh, mm, ss, us, tzinfo);
+	/* Are temp and result really the same time?  temp == result iff
+	 * temp - newoff == result - otoff, iff
+	 * (result - HOUR) - newoff = result - otoff, iff
+	 * otoff - newoff == HOUR
+	 */
+	if (otoff - newoff == 60) {
+		/* use the local time that makes sense */
+		Py_DECREF(result);
+		return temp;
+	}
+	Py_DECREF(temp);
+
+	/* There's still a problem with the unspellable (in local time)
+	 * hour after DST ends.
+	 */
+	temp = datetime_richcompare((PyDateTime_DateTime *)self,
+				    result, Py_EQ);
+	if (temp == NULL)
+		goto Fail;
+	if (temp == Py_True) {
+		Py_DECREF(temp);
+		return result;
+	}
+	Py_DECREF(temp);
+        /* Else there's no way to spell self in zone other.tz. */
+        PyErr_SetString(PyExc_ValueError, "astimezone(): the source "
+        		"datetimetz can't be expressed in the target "
+        		"timezone's local time");
+        goto Fail;
+
+Inconsistent:
+	PyErr_SetString(PyExc_ValueError, "astimezone(): tz.utcoffset() "
+			"gave inconsistent results; cannot convert");
+
+	/* fall thru to failure */
+Fail:
+	Py_DECREF(result);
+	return NULL;
 }
 
 static PyObject *