gh-53203: Fix strptime(..,'%c') on locales with short month names

In some locales (for example French and Hebrew), the default month
used in __calc_date_time has the same name in full and abbreviated
form. So the code failed to correctly distinguish formats %b and %B.

Co-authored-by: Eli Bendersky <[email protected]>

Author: serhiy-storchaka

Lib/_strptime.py

@@ -119,13 +119,19 @@ def __calc_date_time(self):
         date_time[1] = time.strftime("%x", time_tuple).lower()
         date_time[2] = time.strftime("%X", time_tuple).lower()
         replacement_pairs = [('%', '%%'), (self.f_weekday[2], '%A'),
-                    (self.f_month[3], '%B'), (self.a_weekday[2], '%a'),
-                    (self.a_month[3], '%b'), (self.am_pm[1], '%p'),
+                    (self.a_weekday[2], '%a'),
+                    (self.am_pm[1], '%p'),
                     ('1999', '%Y'), ('99', '%y'), ('22', '%H'),
                     ('44', '%M'), ('55', '%S'), ('76', '%j'),
                     ('17', '%d'), ('03', '%m'), ('3', '%m'),
                     # '3' needed for when no leading zero.
                     ('2', '%w'), ('10', '%I')]
+        # The month format is treated specially because of a possible
+        # ambiguity in some locales where the full and abbreviated
+        # month names are equal. See doc of __find_month_format for more
+        # details.
+        #
+        month_format = self.__find_month_format()
         replacement_pairs.extend([(tz, "%Z") for tz_values in self.timezone
                                                 for tz in tz_values])
         for offset,directive in ((0,'%c'), (1,'%x'), (2,'%X')):
@@ -137,6 +143,8 @@ def __calc_date_time(self):
                 # strings (e.g., MacOS 9 having timezone as ('','')).
                 if old:
                     current_format = current_format.replace(old, new)
+            for month_str in (self.f_month[3], self.a_month[3]):
+                current_format = current_format.replace(month_str, month_format)
             # If %W is used, then Sunday, 2005-01-03 will fall on week 0 since
             # 2005-01-03 occurs before the first Monday of the year.  Otherwise
             # %U is used.
@@ -150,6 +158,26 @@ def __calc_date_time(self):
         self.LC_date = date_time[1]
         self.LC_time = date_time[2]
 
+    def __find_month_format(self):
+        """Find the month format appropriate for the current locale.
+
+        In some locales (for example French and Hebrew), the default month
+        used in __calc_date_time has the same name in full and abbreviated
+        form. Thus, cycle months of the year until a month is found where
+        these representations differ, and check the datetime string created
+        by strftime against this month, to make sure we select the correct
+        format specifier.
+        """
+        for m in range(1, 13):
+            if self.f_month[m] != self.a_month[m]:
+                time_tuple = time.struct_time((1999, m, 17, 22, 44, 55, 2, 76, 0))
+                datetime = time.strftime('%c', time_tuple).lower()
+                if datetime.find(self.f_month[m]) >= 0:
+                    return '%B'
+                elif datetime.find(self.a_month[m]) >= 0:
+                    return '%b'
+        return '%B'
+
     def __calc_timezone(self):
         # Set self.timezone by using time.tzname.
         # Do not worry about possibility of time.tzname[0] == time.tzname[1]

Lib/test/support/__init__.py

@@ -930,8 +930,8 @@ def check_sizeof(test, o, size):
     test.assertEqual(result, size, msg)
 
 #=======================================================================
-# Decorator for running a function in a different locale, correctly resetting
-# it afterwards.
+# Decorator/context manager for running a code in a different locale,
+# correctly resetting it afterwards.
 
 @contextlib.contextmanager
 def run_with_locale(catstr, *locales):
@@ -959,6 +959,46 @@ def run_with_locale(catstr, *locales):
         if locale and orig_locale:
             locale.setlocale(category, orig_locale)
 
+#=======================================================================
+# Decorator for running a function in multiple locales (if they are
+# availasble) and resetting the original locale afterwards.
+
+def run_with_locales(catstr, *locales):
+    def deco(func):
+        @functools.wraps(func)
+        def wrapper(self, /, *args, **kwargs):
+            dry_run = True
+            try:
+                import locale
+                category = getattr(locale, catstr)
+                orig_locale = locale.setlocale(category)
+            except AttributeError:
+                # if the test author gives us an invalid category string
+                raise
+            except:
+                # cannot retrieve original locale, so do nothing
+                pass
+            else:
+                try:
+                    for loc in locales:
+                        with self.subTest(locale=loc):
+                            try:
+                                locale.setlocale(category, loc)
+                            except:
+                                self.skipTest(f'no locale {loc!r}')
+                            else:
+                                dry_run = False
+                                func(self, *args, **kwargs)
+                finally:
+                    locale.setlocale(category, orig_locale)
+            if dry_run:
+                # no locales available, so just run the test
+                # with the current locale
+                with self.subTest(locale=None):
+                    func(self, *args, **kwargs)
+        return wrapper
+    return deco
+
 #=======================================================================
 # Decorator for running a function in a specific timezone, correctly
 # resetting it afterwards.

Lib/test/test_strptime.py

@@ -7,7 +7,8 @@
 import os
 import sys
 from test import support
-from test.support import skip_if_buggy_ucrt_strfptime, warnings_helper
+from test.support import warnings_helper
+from test.support import skip_if_buggy_ucrt_strfptime, run_with_locales
 from datetime import date as datetime_date
 
 import _strptime
@@ -289,54 +290,64 @@ def test_unconverteddata(self):
         # Check ValueError is raised when there is unconverted data
         self.assertRaises(ValueError, _strptime._strptime_time, "10 12", "%m")
 
-    def helper(self, directive, position):
+    def roundtrip(self, fmt, position, time_tuple=None):
         """Helper fxn in testing."""
-        fmt = "%d %Y" if directive == 'd' else "%" + directive
-        strf_output = time.strftime(fmt, self.time_tuple)
+        if time_tuple is None:
+            time_tuple = self.time_tuple
+        strf_output = time.strftime(fmt, time_tuple)
         strp_output = _strptime._strptime_time(strf_output, fmt)
-        self.assertTrue(strp_output[position] == self.time_tuple[position],
-                        "testing of '%s' directive failed; '%s' -> %s != %s" %
-                         (directive, strf_output, strp_output[position],
-                          self.time_tuple[position]))
+        self.assertEqual(strp_output[position], time_tuple[position],
+                        "testing of %r format failed; %r -> %r != %r" %
+                         (fmt, strf_output, strp_output[position],
+                          time_tuple[position]))
+        if support.verbose >= 3:
+            print("testing of %r format: %r -> %r" %
+                  (fmt, strf_output, strp_output[position]))
 
     def test_year(self):
         # Test that the year is handled properly
-        for directive in ('y', 'Y'):
-            self.helper(directive, 0)
+        self.roundtrip('%Y', 0)
+        self.roundtrip('%y', 0)
+        self.roundtrip('%Y', 0, (1900, 1, 1, 0, 0, 0, 0, 1, 0))
+
         # Must also make sure %y values are correct for bounds set by Open Group
-        for century, bounds in ((1900, ('69', '99')), (2000, ('00', '68'))):
-            for bound in bounds:
-                strp_output = _strptime._strptime_time(bound, '%y')
-                expected_result = century + int(bound)
-                self.assertTrue(strp_output[0] == expected_result,
-                                "'y' test failed; passed in '%s' "
-                                "and returned '%s'" % (bound, strp_output[0]))
+        strptime = _strptime._strptime_time
+        self.assertEqual(strptime('00', '%y')[0], 2000)
+        self.assertEqual(strptime('68', '%y')[0], 2068)
+        self.assertEqual(strptime('69', '%y')[0], 1969)
+        self.assertEqual(strptime('99', '%y')[0], 1999)
 
     def test_month(self):
         # Test for month directives
-        for directive in ('B', 'b', 'm'):
-            self.helper(directive, 1)
+        self.roundtrip('%m', 1)
+
+    @run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP', '')
+    def test_month_locale(self):
+        # Test for month directives
+        self.roundtrip('%B', 1)
+        self.roundtrip('%b', 1)
 
     def test_day(self):
         # Test for day directives
-        self.helper('d', 2)
+        self.roundtrip('%d %Y', 2)
 
     def test_hour(self):
         # Test hour directives
-        self.helper('H', 3)
-        strf_output = time.strftime("%I %p", self.time_tuple)
-        strp_output = _strptime._strptime_time(strf_output, "%I %p")
-        self.assertTrue(strp_output[3] == self.time_tuple[3],
-                        "testing of '%%I %%p' directive failed; '%s' -> %s != %s" %
-                         (strf_output, strp_output[3], self.time_tuple[3]))
+        self.roundtrip('%H', 3)
+
+    # NB: Only works on locales with AM/PM
+    @run_with_locales('LC_TIME', 'en_US', 'ja_JP')
+    def test_hour_locale(self):
+        # Test hour directives
+        self.roundtrip('%I %p', 3)
 
     def test_minute(self):
         # Test minute directives
-        self.helper('M', 4)
+        self.roundtrip('%M', 4)
 
     def test_second(self):
         # Test second directives
-        self.helper('S', 5)
+        self.roundtrip('%S', 5)
 
     def test_fraction(self):
         # Test microseconds
@@ -347,12 +358,18 @@ def test_fraction(self):
 
     def test_weekday(self):
         # Test weekday directives
-        for directive in ('A', 'a', 'w', 'u'):
-            self.helper(directive,6)
+        self.roundtrip('%w', 6)
+        self.roundtrip('%u', 6)
+
+    @run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP', '')
+    def test_weekday_locale(self):
+        # Test weekday directives
+        self.roundtrip('%A', 6)
+        self.roundtrip('%a', 6)
 
     def test_julian(self):
         # Test julian directives
-        self.helper('j', 7)
+        self.roundtrip('%j', 7)
 
     def test_offset(self):
         one_hour = 60 * 60
@@ -449,20 +466,26 @@ def test_bad_timezone(self):
                     "time.daylight set to %s and passing in %s" %
                     (time.tzname, tz_value, time.daylight, tz_name))
 
-    def test_date_time(self):
+    # NB: Does not roundtrip on some locales like hif_FJ.
+    @run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP', '')
+    def test_date_time_locale(self):
         # Test %c directive
-        for position in range(6):
-            self.helper('c', position)
+        self.roundtrip('%c', slice(0, 6))
+        self.roundtrip('%c', slice(0, 6), (1900, 1, 1, 0, 0, 0, 0, 1, 0))
 
-    def test_date(self):
+    # NB: Dates before 1969 do not work on locales: C, POSIX,
+    # az_IR, fa_IR, sd_PK, uk_UA.
+    @run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP')
+    def test_date_locale(self):
         # Test %x directive
-        for position in range(0,3):
-            self.helper('x', position)
+        self.roundtrip('%x', slice(0, 3))
+        self.roundtrip('%x', slice(0, 3), (1900, 1, 1, 0, 0, 0, 0, 1, 0))
 
-    def test_time(self):
+    # NB: Does not distinguish AM/PM time on a number of locales.
+    @run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP')
+    def test_time_locale(self):
         # Test %X directive
-        for position in range(3,6):
-            self.helper('X', position)
+        self.roundtrip('%X', slice(3, 6))
 
     def test_percent(self):
         # Make sure % signs are handled properly

Misc/NEWS.d/next/Library/2024-10-03-20-45-57.gh-issue-53203.3Sk4Ia.rst

@@ -0,0 +1,2 @@
+Fix :func:`time.strptime` for ``%c`` format in locales with a short March
+month name, such as French or Hebrew.