Issue #6478: _strptime's regexp cache now is reset after changing timezone

with time.tzset().

Author: serhiy-storchaka

Lib/_strptime.py

@@ -77,6 +77,8 @@ def __init__(self):
         self.__calc_date_time()
         if _getlang() != self.lang:
             raise ValueError("locale changed during initialization")
+        if time.tzname != self.tzname or time.daylight != self.daylight:
+            raise ValueError("timezone changed during initialization")
 
     def __pad(self, seq, front):
         # Add '' to seq to either the front (is True), else the back.
@@ -161,15 +163,17 @@ def __calc_date_time(self):
 
     def __calc_timezone(self):
         # Set self.timezone by using time.tzname.
-        # Do not worry about possibility of time.tzname[0] == timetzname[1]
-        # and time.daylight; handle that in strptime .
+        # Do not worry about possibility of time.tzname[0] == time.tzname[1]
+        # and time.daylight; handle that in strptime.
         try:
             time.tzset()
         except AttributeError:
             pass
-        no_saving = frozenset({"utc", "gmt", time.tzname[0].lower()})
-        if time.daylight:
-            has_saving = frozenset({time.tzname[1].lower()})
+        self.tzname = time.tzname
+        self.daylight = time.daylight
+        no_saving = frozenset({"utc", "gmt", self.tzname[0].lower()})
+        if self.daylight:
+            has_saving = frozenset({self.tzname[1].lower()})
         else:
             has_saving = frozenset()
         self.timezone = (no_saving, has_saving)
@@ -307,13 +311,15 @@ def _strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
 
     global _TimeRE_cache, _regex_cache
     with _cache_lock:
-
-        if _getlang() != _TimeRE_cache.locale_time.lang:
+        locale_time = _TimeRE_cache.locale_time
+        if (_getlang() != locale_time.lang or
+            time.tzname != locale_time.tzname or
+            time.daylight != locale_time.daylight):
             _TimeRE_cache = TimeRE()
             _regex_cache.clear()
+            locale_time = _TimeRE_cache.locale_time
         if len(_regex_cache) > _CACHE_MAX_SIZE:
             _regex_cache.clear()
-        locale_time = _TimeRE_cache.locale_time
         format_regex = _regex_cache.get(format)
         if not format_regex:
             try:

Lib/test/test_strptime.py

@@ -4,6 +4,7 @@
 import time
 import locale
 import re
+import os
 import sys
 from test import support
 from datetime import date as datetime_date
@@ -324,19 +325,17 @@ def test_bad_timezone(self):
         tz_name = time.tzname[0]
         if tz_name.upper() in ("UTC", "GMT"):
             self.skipTest('need non-UTC/GMT timezone')
-        try:
-            original_tzname = time.tzname
-            original_daylight = time.daylight
+
+        with support.swap_attr(time, 'tzname', (tz_name, tz_name)), \
+             support.swap_attr(time, 'daylight', 1), \
+             support.swap_attr(time, 'tzset', lambda: None):
             time.tzname = (tz_name, tz_name)
             time.daylight = 1
             tz_value = _strptime._strptime_time(tz_name, "%Z")[8]
             self.assertEqual(tz_value, -1,
                     "%s lead to a timezone value of %s instead of -1 when "
                     "time.daylight set to %s and passing in %s" %
                     (time.tzname, tz_value, time.daylight, tz_name))
-        finally:
-            time.tzname = original_tzname
-            time.daylight = original_daylight
 
     def test_date_time(self):
         # Test %c directive
@@ -548,7 +547,7 @@ def test_new_localetime(self):
         _strptime._strptime_time("10", "%d")
         self.assertIsNot(locale_time_id, _strptime._TimeRE_cache.locale_time)
 
-    def test_TimeRE_recreation(self):
+    def test_TimeRE_recreation_locale(self):
         # The TimeRE instance should be recreated upon changing the locale.
         locale_info = locale.getlocale(locale.LC_TIME)
         try:
@@ -577,6 +576,33 @@ def test_TimeRE_recreation(self):
         finally:
             locale.setlocale(locale.LC_TIME, locale_info)
 
+    @support.run_with_tz('STD-1DST')
+    def test_TimeRE_recreation_timezone(self):
+        # The TimeRE instance should be recreated upon changing the timezone.
+        oldtzname = time.tzname
+        tm = _strptime._strptime_time(time.tzname[0], '%Z')
+        self.assertEqual(tm.tm_isdst, 0)
+        tm = _strptime._strptime_time(time.tzname[1], '%Z')
+        self.assertEqual(tm.tm_isdst, 1)
+        # Get id of current cache object.
+        first_time_re = _strptime._TimeRE_cache
+        # Change the timezone and force a recreation of the cache.
+        os.environ['TZ'] = 'EST+05EDT,M3.2.0,M11.1.0'
+        time.tzset()
+        tm = _strptime._strptime_time(time.tzname[0], '%Z')
+        self.assertEqual(tm.tm_isdst, 0)
+        tm = _strptime._strptime_time(time.tzname[1], '%Z')
+        self.assertEqual(tm.tm_isdst, 1)
+        # Get the new cache object's id.
+        second_time_re = _strptime._TimeRE_cache
+        # They should not be equal.
+        self.assertIsNot(first_time_re, second_time_re)
+        # Make sure old names no longer accepted.
+        with self.assertRaises(ValueError):
+            _strptime._strptime_time(oldtzname[0], '%Z')
+        with self.assertRaises(ValueError):
+            _strptime._strptime_time(oldtzname[1], '%Z')
+
 
 if __name__ == '__main__':
     unittest.main()

Misc/NEWS

@@ -22,6 +22,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #6478: _strptime's regexp cache now is reset after changing timezone
+  with time.tzset().
+
 - Issue #14285: When executing a package with the "python -m package" option,
   and package initialization fails, a proper traceback is now reported.  The
   "runpy" module now lets exceptions from package initialization pass back to