Skip to content

bpo-39280: Don't allow datetime parsing to accept non-Ascii digits #17931

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
cool-RR wants to merge 2 commits into from
Closed

bpo-39280: Don't allow datetime parsing to accept non-Ascii digits #17931

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
864c031
Fix outdated comment in _strptime.py
cool-RR Jan 9, 2020
75bc88f
bpo-39280: Don't allow datetime parsing to accept non-Ascii digits
cool-RR Jan 9, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions Lib/_strptime.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,26 +182,26 @@ def __init__(self, locale_time=None):
self.locale_time = LocaleTime()
base = super()
base.__init__({
# The " \d" part of the regex is to make %c from ANSI C work
'd': r"(?P<d>3[0-1]|[1-2]\d|0[1-9]|[1-9]| [1-9])",
# The " [1-9]" part of the regex is to make %c from ANSI C work
'd': r"(?P<d>3[0-1]|[1-2][0-9]|0[1-9]|[1-9]| [1-9])",
'f': r"(?P<f>[0-9]{1,6})",
'H': r"(?P<H>2[0-3]|[0-1]\d|\d)",
'H': r"(?P<H>2[0-3]|[0-1][0-9]|[0-9])",
'I': r"(?P<I>1[0-2]|0[1-9]|[1-9])",
'G': r"(?P<G>\d\d\d\d)",
'j': r"(?P<j>36[0-6]|3[0-5]\d|[1-2]\d\d|0[1-9]\d|00[1-9]|[1-9]\d|0[1-9]|[1-9])",
'G': r"(?P<G>[0-9][0-9][0-9][0-9])",
'j': r"(?P<j>36[0-6]|3[0-5][0-9]|[1-2][0-9][0-9]|0[1-9][0-9]|00[1-9]|[1-9][0-9]|0[1-9]|[1-9])",
'm': r"(?P<m>1[0-2]|0[1-9]|[1-9])",
'M': r"(?P<M>[0-5]\d|\d)",
'S': r"(?P<S>6[0-1]|[0-5]\d|\d)",
'U': r"(?P<U>5[0-3]|[0-4]\d|\d)",
'M': r"(?P<M>[0-5][0-9]|[0-9])",
'S': r"(?P<S>6[0-1]|[0-5][0-9]|[0-9])",
'U': r"(?P<U>5[0-3]|[0-4][0-9]|[0-9])",
'w': r"(?P<w>[0-6])",
'u': r"(?P<u>[1-7])",
'V': r"(?P<V>5[0-3]|0[1-9]|[1-4]\d|\d)",
'V': r"(?P<V>5[0-3]|0[1-9]|[1-4][0-9]|[0-9])",
# W is set below by using 'U'
'y': r"(?P<y>\d\d)",
'y': r"(?P<y>[0-9][0-9])",
#XXX: Does 'Y' need to worry about having less or more than
# 4 digits?
'Y': r"(?P<Y>\d\d\d\d)",
'z': r"(?P<z>[+-]\d\d:?[0-5]\d(:?[0-5]\d(\.\d{1,6})?)?|Z)",
'Y': r"(?P<Y>[0-9][0-9][0-9][0-9])",
'z': r"(?P<z>[+-][0-9][0-9]:?[0-5][0-9](:?[0-5][0-9](\.[0-9]{1,6})?)?|Z)",
'A': self.__seqToRE(self.locale_time.f_weekday, 'A'),
'a': self.__seqToRE(self.locale_time.a_weekday, 'a'),
'B': self.__seqToRE(self.locale_time.f_month[1:], 'B'),
Expand Down
33 changes: 33 additions & 0 deletions Lib/test/datetimetester.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2617,6 +2617,39 @@ def test_strptime_single_digit(self):
newdate = strptime(string, format)
self.assertEqual(newdate, target, msg=reason)

def test_rejecting_non_ascii_digits(self):
# bpo-39280: Don't allow datetime parsing to accept non-Ascii digits
eastern_arabic_digits = [chr(1632 + i) for i in range(10)]
full_width_digits = [chr(65296 + i) for i in range(10)]

# Making sure we're using legit Unicode digits:
for i, eastern_arabic_digit, full_width_digit in zip(
itertools.count(), eastern_arabic_digits, full_width_digits):
assert i == int(eastern_arabic_digit) == int(full_width_digit)

formats = ['%Y %m %d %H %M %S %f',
'%y %m %d %I %M %p',
'%Y %j',
'%G %V %u',
'%Y %U %w',
'%Y %W %w']

my_datetime = datetime.fromisoformat('2020-01-09T23:41:45.973450')
for format in formats:
datetime_string = my_datetime.strftime(format)
self.assertEqual(my_datetime, datetime.strptime(datetime_string, format))
digit_indices = [i for i, c in enumerate(datetime_string) if c.isdigit()]
assert len(digit_indices) >= 6
for alternate_digits in (eastern_arabic_digits, full_width_digits):
for i in digit_indices:
tainted_datetime_string = (
datetime_string[:i] +
alternate_digits[int(datetime_string[i])] +
datetime_string[i + 1]
)
with self.assertRaises(ValueError):
datetime.strptime(tainted_datetime_string, format)

def test_more_timetuple(self):
# This tests fields beyond those tested by the TestDate.test_timetuple.
t = self.theclass(2004, 12, 31, 6, 22, 33)
Expand Down
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Library/2020-01-10-00-16-46.bpo-39280.VA476D.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Don't allow datetime parsing to accept non-Ascii digits.