Fix last_modified_date_to_timestamp on non-UTC systems

Before, we were calling datetime.datetime.strftime('%s.%f') to convert
a datetime to epoch seconds + microseconds. However, the '%s' format
isn't actually part of Python's library. Rather, Python passes that on
to the system C library, which is typically glibc. Now, glibc takes
the '%s' format and helpfully* applies the current timezone as an
offset. This gives bogus results on machines where UTC is not the
system timezone. (Yes, some people really do that.)

For example:

    >>> import os
    >>> from swift.common import utils
    >>> os.environ['TZ'] = 'PST8PDT,M3.2.0,M11.1.0'
    >>> float(utils.last_modified_date_to_timestamp('1970-01-01T00:00:00.000000'))
    28800.0
    >>>

That timestamp should obviously be 0.

This patch replaces the strftime() call with datetime arithmetic,
which is entirely in Python so the system timezone doesn't mess it up.

* unhelpfully

Change-Id: I56855acd79a5d8f2c98a771fa9fd2729e4f490b1
This commit is contained in:
Samuel Merritt 2014-08-29 15:48:38 -07:00
parent 8d02147d04
commit 33980c792d
2 changed files with 32 additions and 5 deletions

View File

@ -696,16 +696,25 @@ def normalize_timestamp(timestamp):
return Timestamp(timestamp).normal
EPOCH = datetime.datetime(1970, 1, 1)
def last_modified_date_to_timestamp(last_modified_date_str):
"""
Convert a last modified date (like you'd get from a container listing,
e.g. 2014-02-28T23:22:36.698390) to a float.
"""
return Timestamp(
datetime.datetime.strptime(
last_modified_date_str, '%Y-%m-%dT%H:%M:%S.%f'
).strftime('%s.%f')
)
start = datetime.datetime.strptime(last_modified_date_str,
'%Y-%m-%dT%H:%M:%S.%f')
delta = start - EPOCH
# TODO(sam): after we no longer support py2.6, this expression can
# simplify to Timestamp(delta.total_seconds()).
#
# This calculation is based on Python 2.7's Modules/datetimemodule.c,
# function delta_to_microseconds(), but written in Python.
return Timestamp(delta.days * 86400 +
delta.seconds +
delta.microseconds / 1000000.0)
def normalize_delete_at_timestamp(timestamp):

View File

@ -859,6 +859,24 @@ class TestUtils(unittest.TestCase):
real = utils.last_modified_date_to_timestamp(last_modified)
self.assertEqual(real, ts, "failed for %s" % last_modified)
def test_last_modified_date_to_timestamp_when_system_not_UTC(self):
try:
old_tz = os.environ.get('TZ')
# Western Argentina Summer Time. Found in glibc manual; this
# timezone always has a non-zero offset from UTC, so this test is
# always meaningful.
os.environ['TZ'] = 'WART4WARST,J1/0,J365/25'
self.assertEqual(utils.last_modified_date_to_timestamp(
'1970-01-01T00:00:00.000000'),
0.0)
finally:
if old_tz is not None:
os.environ['TZ'] = old_tz
else:
os.environ.pop('TZ')
def test_backwards(self):
# Test swift.common.utils.backward