Make sure time.strptime only accepts strings (and document the fact like

strftime). Already didn't accept bytes but make the check earlier. This also
lifts the limitation of requiring ASCII.

Closes issue #5236. Thanks Tennessee Leeuwenburg.

diff --git a/Doc/library/time.rst b/Doc/library/time.rst
index 46d972a3f0e7cea7f4bb45440c238ce584f6a394..cdc623d60d1efdc91421d18448fe2a1353fd9bd9 100644 (file)
--- a/Doc/library/time.rst
+++ b/Doc/library/time.rst
@@ -358,15 +358,17 @@ The module defines the following functions and data items:
 
 .. function:: strptime(string[, format])
 
-   Parse a string representing a time according to a format.  The return  value is
-   a :class:`struct_time` as returned by :func:`gmtime` or :func:`localtime`.
+   Parse a string representing a time according to a format.  The return value
+   is a :class:`struct_time` as returned by :func:`gmtime` or
+   :func:`localtime`.
 
    The *format* parameter uses the same directives as those used by
    :func:`strftime`; it defaults to ``"%a %b %d %H:%M:%S %Y"`` which matches the
-   formatting returned by :func:`ctime`. If *string* cannot be parsed according to
-   *format*, or if it has excess data after parsing, :exc:`ValueError` is raised.
-   The default values used to fill in any missing data when more accurate values
-   cannot be inferred are ``(1900, 1, 1, 0, 0, 0, 0, 1, -1)``.
+   formatting returned by :func:`ctime`. If *string* cannot be parsed according
+   to *format*, or if it has excess data after parsing, :exc:`ValueError` is
+   raised. The default values used to fill in any missing data when more
+   accurate values cannot be inferred are ``(1900, 1, 1, 0, 0, 0, 0, 1, -1)``.
+   Both *string* and *format* must be strings.
 
    For example:
 

diff --git a/Lib/_strptime.py b/Lib/_strptime.py
index 896c7986c4e1911d7e4e4555b18d15d9d73cfa12..9ff29bce8f7678c7ba3ac3b5f6f03ae340cd1c99 100644 (file)
--- a/Lib/_strptime.py
+++ b/Lib/_strptime.py
@@ -262,7 +262,7 @@ class TimeRE(dict):
 
     def compile(self, format):
         """Return a compiled re object for the format string."""
-        return re_compile(self.pattern(format), IGNORECASE | ASCII)
+        return re_compile(self.pattern(format), IGNORECASE)
 
 _cache_lock = _thread_allocate_lock()
 # DO NOT modify _TimeRE_cache or _regex_cache without acquiring the cache lock
@@ -294,8 +294,15 @@ def _calc_julian_from_U_or_W(year, week_of_year, day_of_week, week_starts_Mon):
 
 def _strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
     """Return a time struct based on the input string and the format string."""
+
+    for index, arg in enumerate([data_string, format]):
+        if not isinstance(arg, str):
+            msg = "strptime() argument {} must be str, not {}"
+            raise TypeError(msg.format(arg, index))
+
     global _TimeRE_cache, _regex_cache
     with _cache_lock:
+
         if _getlang() != _TimeRE_cache.locale_time.lang:
             _TimeRE_cache = TimeRE()
             _regex_cache.clear()

diff --git a/Lib/test/test_time.py b/Lib/test/test_time.py
index 4c89f03bab31f8bf222648b90898cd415bb6d2e6..c2dfaca968ced6b1625386f207ac9cb2ecca2c32 100644 (file)
--- a/Lib/test/test_time.py
+++ b/Lib/test/test_time.py
@@ -116,6 +116,11 @@ class TimeTestCase(unittest.TestCase):
                 self.fail("conversion specifier %r failed with '%s' input." %
                           (format, strf_output))
 
+    def test_strptime_bytes(self):
+        # Make sure only strings are accepted as arguments to strptime.
+        self.assertRaises(TypeError, time.strptime, b'2009', "%Y")
+        self.assertRaises(TypeError, time.strptime, '2009', b'%Y')
+
     def test_asctime(self):
         time.asctime(time.gmtime(self.t))
         self.assertRaises(TypeError, time.asctime, 0)

diff --git a/Misc/ACKS b/Misc/ACKS
index 85bc8a1279411de8009403d4a9aa43fc1dd849ef..85a443bba7d4dead46cb755a3bfc2028d201da4f 100644 (file)
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -411,6 +411,7 @@ John J. Lee
 Inyeol Lee
 Thomas Lee
 Christopher Lee
+Tennessee Leeuwenburg
 Luc Lefebvre
 Kip Lehman
 Joerg Lehmann

diff --git a/Misc/NEWS b/Misc/NEWS
index f0dafcb8caf12f33f9b95a4f301b929a1fa18c31..f2888be1f3b1191ed7b4ca452b3da88658baacb3 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -43,6 +43,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #5236: Change time.strptime() to only take strings. Didn't work with
+  bytes already but the failure was non-obvious.
+
 - Issue #5177: Multiprocessing's SocketListener class now uses
   socket.SO_REUSEADDR on all connections so that the user no longer needs
   to wait 120 seconds for the socket to expire.