mirror of
https://github.com/python/cpython.git
synced 2025-12-31 04:23:37 +00:00
gh-53203: Fix strptime() for %c and %x formats on many locales (GH-124946)
In some locales (like French or Hebrew) the full or abbreviated names of the default month and weekday used in __calc_date_time can be part of other name or constant part of the %c format. The month name can also match %m with constant suffix (like in Japanese). So the code failed to correctly distinguish formats %a, %A, %b, %B and %m. Cycle all month and all days of the week to find the variable part and distinguish %a from %A and %b from %B or %m. Fixed locales for the following languges: Arabic, Bislama, Breton, Bodo, Kashubian, Chuvash, Estonian, French, Irish, Ge'ez, Gurajati, Manx Gaelic, Hebrew, Hindi, Chhattisgarhi, Haitian Kreyol, Japanese, Kannada, Korean, Marathi, Malay, Norwegian, Nynorsk, Punjabi, Rajasthani, Tok Pisin, Yoruba, Yue Chinese, Yau/Nungon and Chinese. Co-authored-by: Eli Bendersky <eliben@gmail.com>
This commit is contained in:
parent
dcd58c5084
commit
c05f9dde8a
3 changed files with 134 additions and 34 deletions
127
Lib/_strptime.py
127
Lib/_strptime.py
|
|
@ -28,6 +28,18 @@ def _getlang():
|
|||
# Figure out what the current language is set to.
|
||||
return locale.getlocale(locale.LC_TIME)
|
||||
|
||||
def _findall(haystack, needle):
|
||||
# Find all positions of needle in haystack.
|
||||
if not needle:
|
||||
return
|
||||
i = 0
|
||||
while True:
|
||||
i = haystack.find(needle, i)
|
||||
if i < 0:
|
||||
break
|
||||
yield i
|
||||
i += len(needle)
|
||||
|
||||
class LocaleTime(object):
|
||||
"""Stores and handles locale-specific information related to time.
|
||||
|
||||
|
|
@ -102,7 +114,8 @@ def __calc_am_pm(self):
|
|||
am_pm = []
|
||||
for hour in (1, 22):
|
||||
time_tuple = time.struct_time((1999,3,17,hour,44,55,2,76,0))
|
||||
am_pm.append(time.strftime("%p", time_tuple).lower())
|
||||
# br_FR has AM/PM info (' ',' ').
|
||||
am_pm.append(time.strftime("%p", time_tuple).lower().strip())
|
||||
self.am_pm = am_pm
|
||||
|
||||
def __calc_date_time(self):
|
||||
|
|
@ -114,42 +127,114 @@ def __calc_date_time(self):
|
|||
# values within the format string is very important; it eliminates
|
||||
# possible ambiguity for what something represents.
|
||||
time_tuple = time.struct_time((1999,3,17,22,44,55,2,76,0))
|
||||
date_time = [None, None, None]
|
||||
date_time[0] = time.strftime("%c", time_tuple).lower()
|
||||
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'),
|
||||
time_tuple2 = time.struct_time((1999,1,3,1,1,1,6,3,0))
|
||||
replacement_pairs = [
|
||||
('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')]
|
||||
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')):
|
||||
current_format = date_time[offset]
|
||||
for old, new in replacement_pairs:
|
||||
date_time = []
|
||||
for directive in ('%c', '%x', '%X'):
|
||||
current_format = time.strftime(directive, time_tuple).lower()
|
||||
current_format = current_format.replace('%', '%%')
|
||||
# The month and the day of the week formats are treated specially
|
||||
# because of a possible ambiguity in some locales where the full
|
||||
# and abbreviated names are equal or names of different types
|
||||
# are equal. See doc of __find_month_format for more details.
|
||||
lst, fmt = self.__find_weekday_format(directive)
|
||||
if lst:
|
||||
current_format = current_format.replace(lst[2], fmt, 1)
|
||||
lst, fmt = self.__find_month_format(directive)
|
||||
if lst:
|
||||
current_format = current_format.replace(lst[3], fmt, 1)
|
||||
if self.am_pm[1]:
|
||||
# Must deal with possible lack of locale info
|
||||
# manifesting itself as the empty string (e.g., Swedish's
|
||||
# lack of AM/PM info) or a platform returning a tuple of empty
|
||||
# strings (e.g., MacOS 9 having timezone as ('','')).
|
||||
if old:
|
||||
current_format = current_format.replace(old, new)
|
||||
current_format = current_format.replace(self.am_pm[1], '%p')
|
||||
for tz_values in self.timezone:
|
||||
for tz in tz_values:
|
||||
if tz:
|
||||
current_format = current_format.replace(tz, "%Z")
|
||||
for old, new in replacement_pairs:
|
||||
current_format = current_format.replace(old, new)
|
||||
# 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.
|
||||
time_tuple = time.struct_time((1999,1,3,1,1,1,6,3,0))
|
||||
if '00' in time.strftime(directive, time_tuple):
|
||||
if '00' in time.strftime(directive, time_tuple2):
|
||||
U_W = '%W'
|
||||
else:
|
||||
U_W = '%U'
|
||||
date_time[offset] = current_format.replace('11', U_W)
|
||||
current_format = current_format.replace('11', U_W)
|
||||
date_time.append(current_format)
|
||||
self.LC_date_time = date_time[0]
|
||||
self.LC_date = date_time[1]
|
||||
self.LC_time = date_time[2]
|
||||
|
||||
def __find_month_format(self, directive):
|
||||
"""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. Also, the month name can by accident match other part of the
|
||||
representation: the day of the week name (for example in Morisyen)
|
||||
or the month number (for example in Japanese). Thus, cycle months
|
||||
of the year and find all positions that match the month name for
|
||||
each month, If no common positions are found, the representation
|
||||
does not use the month name.
|
||||
"""
|
||||
full_indices = abbr_indices = None
|
||||
for m in range(1, 13):
|
||||
time_tuple = time.struct_time((1999, m, 17, 22, 44, 55, 2, 76, 0))
|
||||
datetime = time.strftime(directive, time_tuple).lower()
|
||||
indices = set(_findall(datetime, self.f_month[m]))
|
||||
if full_indices is None:
|
||||
full_indices = indices
|
||||
else:
|
||||
full_indices &= indices
|
||||
indices = set(_findall(datetime, self.a_month[m]))
|
||||
if abbr_indices is None:
|
||||
abbr_indices = indices
|
||||
else:
|
||||
abbr_indices &= indices
|
||||
if not full_indices and not abbr_indices:
|
||||
return None, None
|
||||
if full_indices:
|
||||
return self.f_month, '%B'
|
||||
if abbr_indices:
|
||||
return self.a_month, '%b'
|
||||
return None, None
|
||||
|
||||
def __find_weekday_format(self, directive):
|
||||
"""Find the day of the week format appropriate for the current locale.
|
||||
|
||||
Similar to __find_month_format().
|
||||
"""
|
||||
full_indices = abbr_indices = None
|
||||
for wd in range(7):
|
||||
time_tuple = time.struct_time((1999, 3, 17, 22, 44, 55, wd, 76, 0))
|
||||
datetime = time.strftime(directive, time_tuple).lower()
|
||||
indices = set(_findall(datetime, self.f_weekday[wd]))
|
||||
if full_indices is None:
|
||||
full_indices = indices
|
||||
else:
|
||||
full_indices &= indices
|
||||
if self.f_weekday[wd] != self.a_weekday[wd]:
|
||||
indices = set(_findall(datetime, self.a_weekday[wd]))
|
||||
if abbr_indices is None:
|
||||
abbr_indices = indices
|
||||
else:
|
||||
abbr_indices &= indices
|
||||
if not full_indices and not abbr_indices:
|
||||
return None, None
|
||||
if full_indices:
|
||||
return self.f_weekday, '%A'
|
||||
if abbr_indices:
|
||||
return self.a_weekday, '%a'
|
||||
return None, None
|
||||
|
||||
def __calc_timezone(self):
|
||||
# Set self.timezone by using time.tzname.
|
||||
# Do not worry about possibility of time.tzname[0] == time.tzname[1]
|
||||
|
|
@ -187,7 +272,7 @@ def __init__(self, locale_time=None):
|
|||
'd': r"(?P<d>3[0-1]|[1-2]\d|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)",
|
||||
'I': r"(?P<I>1[0-2]|0[1-9]|[1-9])",
|
||||
'I': r"(?P<I>1[0-2]|0[1-9]|[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])",
|
||||
'm': r"(?P<m>1[0-2]|0[1-9]|[1-9])",
|
||||
|
|
@ -349,8 +434,8 @@ def _strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
|
|||
_regex_cache[format] = format_regex
|
||||
found = format_regex.match(data_string)
|
||||
if not found:
|
||||
raise ValueError("time data %r does not match format %r" %
|
||||
(data_string, format))
|
||||
raise ValueError("time data %r does not match format %r :: /%s/" %
|
||||
(data_string, format, format_regex.pattern))
|
||||
if len(data_string) != found.end():
|
||||
raise ValueError("unconverted data remains: %s" %
|
||||
data_string[found.end():])
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@
|
|||
import locale
|
||||
import re
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
from test import support
|
||||
from test.support import warnings_helper
|
||||
|
|
@ -13,6 +14,13 @@
|
|||
|
||||
import _strptime
|
||||
|
||||
libc_ver = platform.libc_ver()
|
||||
if libc_ver[0] == 'glibc':
|
||||
glibc_ver = tuple(map(int, libc_ver[1].split('.')))
|
||||
else:
|
||||
glibc_ver = None
|
||||
|
||||
|
||||
class getlang_Tests(unittest.TestCase):
|
||||
"""Test _getlang"""
|
||||
def test_basic(self):
|
||||
|
|
@ -478,16 +486,16 @@ def test_bad_timezone(self):
|
|||
# * Year is not included: ha_NG.
|
||||
# * Use non-Gregorian calendar: lo_LA, thai, th_TH.
|
||||
#
|
||||
# BUG: Generates invalid regexp for br_FR, csb_PL, Arabic.
|
||||
# BUG: Generates regexp that does not match the current date and time
|
||||
# for fa_IR, gez_ER, gez_ET, lzh_TW, my_MM, or_IN, shn_MM, yo_NG.
|
||||
# BUG: Generates regexp that does not match the current date and time
|
||||
# for fa_IR, gez_ER, gez_ET, lzh_TW, my_MM, or_IN, shn_MM, yo_NG,
|
||||
# fr_FR, ja_JP, he_IL, ko_KR, zh_CN, etc.
|
||||
@run_with_locales('LC_TIME', 'C', 'en_US', 'de_DE',
|
||||
'eu_ES', 'mfe_MU')
|
||||
# for az_IR, fa_IR, lzh_TW, my_MM, or_IN, shn_MM.
|
||||
@run_with_locales('LC_TIME', 'C', 'en_US', 'fr_FR', 'de_DE', 'ja_JP',
|
||||
'he_IL', 'eu_ES', 'ar_AE', 'mfe_MU', 'yo_NG',
|
||||
'csb_PL', 'br_FR', 'gez_ET', 'brx_IN')
|
||||
def test_date_time_locale(self):
|
||||
# Test %c directive
|
||||
loc = locale.getlocale(locale.LC_TIME)[0]
|
||||
if glibc_ver and glibc_ver < (2, 31) and loc == 'br_FR':
|
||||
self.skipTest('%c in locale br_FR does not include time')
|
||||
now = time.time()
|
||||
self.roundtrip('%c', slice(0, 6), time.localtime(now))
|
||||
# 1 hour 20 minutes 30 seconds ago
|
||||
|
|
@ -505,7 +513,9 @@ def test_date_time_locale(self):
|
|||
|
||||
# NB: Dates before 1969 do not roundtrip on some locales:
|
||||
# bo_CN, bo_IN, dz_BT, eu_ES, eu_FR.
|
||||
@run_with_locales('LC_TIME', 'C', 'en_US', 'de_DE', 'ja_JP')
|
||||
@run_with_locales('LC_TIME', 'C', 'en_US', 'fr_FR', 'de_DE', 'ja_JP',
|
||||
'he_IL', 'ar_AE', 'mfe_MU', 'yo_NG',
|
||||
'csb_PL', 'br_FR', 'gez_ET', 'brx_IN')
|
||||
def test_date_time_locale2(self):
|
||||
# Test %c directive
|
||||
self.roundtrip('%c', slice(0, 6), (1900, 1, 1, 0, 0, 0, 0, 1, 0))
|
||||
|
|
@ -513,10 +523,9 @@ def test_date_time_locale2(self):
|
|||
# NB: Does not roundtrip because use non-Gregorian calendar:
|
||||
# lo_LA, thai, th_TH.
|
||||
# BUG: Generates regexp that does not match the current date
|
||||
# for az_IR, fa_IR, lzh_TW, my_MM, or_IN, shn_MM,
|
||||
# Arabic, ja_JP, ko_KR, zh_CN, etc.
|
||||
@run_with_locales('LC_TIME', 'C', 'en_US', 'fr_FR', 'de_DE',
|
||||
'he_IL', 'eu_ES')
|
||||
# for az_IR, fa_IR, lzh_TW, my_MM, or_IN, shn_MM.
|
||||
@run_with_locales('LC_TIME', 'C', 'en_US', 'fr_FR', 'de_DE', 'ja_JP',
|
||||
'he_IL', 'eu_ES', 'ar_AE')
|
||||
def test_date_locale(self):
|
||||
# Test %x directive
|
||||
now = time.time()
|
||||
|
|
@ -535,7 +544,8 @@ def test_date_locale(self):
|
|||
support.is_emscripten or support.is_wasi,
|
||||
"musl libc issue on Emscripten, bpo-46390"
|
||||
)
|
||||
@run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP')
|
||||
@run_with_locales('LC_TIME', 'en_US', 'fr_FR', 'de_DE', 'ja_JP',
|
||||
'eu_ES', 'ar_AE')
|
||||
def test_date_locale2(self):
|
||||
# Test %x directive
|
||||
self.roundtrip('%x', slice(0, 3), (1900, 1, 1, 0, 0, 0, 0, 1, 0))
|
||||
|
|
|
|||
|
|
@ -0,0 +1,5 @@
|
|||
Fix :func:`time.strptime` for ``%c`` and ``%x`` formats in many locales:
|
||||
Arabic, Bislama, Breton, Bodo, Kashubian, Chuvash, Estonian, French, Irish,
|
||||
Ge'ez, Gurajati, Manx Gaelic, Hebrew, Hindi, Chhattisgarhi, Haitian Kreyol,
|
||||
Japanese, Kannada, Korean, Marathi, Malay, Norwegian, Nynorsk, Punjabi,
|
||||
Rajasthani, Tok Pisin, Yoruba, Yue Chinese, Yau/Nungon and Chinese.
|
||||
Loading…
Add table
Add a link
Reference in a new issue