123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579 |
- """Strptime-related classes and functions.
- CLASSES:
- LocaleTime -- Discovers and stores locale-specific time information
- TimeRE -- Creates regexes for pattern matching a string of text containing
- time information
- FUNCTIONS:
- _getlang -- Figure out what language is being used for the locale
- strptime -- Calculates the time struct represented by the passed-in string
- """
- import time
- import locale
- import calendar
- from re import compile as re_compile
- from re import IGNORECASE
- from re import escape as re_escape
- from datetime import (date as datetime_date,
- timedelta as datetime_timedelta,
- timezone as datetime_timezone)
- from _thread import allocate_lock as _thread_allocate_lock
- __all__ = []
- def _getlang():
- # Figure out what the current language is set to.
- return locale.getlocale(locale.LC_TIME)
- class LocaleTime(object):
- """Stores and handles locale-specific information related to time.
- ATTRIBUTES:
- f_weekday -- full weekday names (7-item list)
- a_weekday -- abbreviated weekday names (7-item list)
- f_month -- full month names (13-item list; dummy value in [0], which
- is added by code)
- a_month -- abbreviated month names (13-item list, dummy value in
- [0], which is added by code)
- am_pm -- AM/PM representation (2-item list)
- LC_date_time -- format string for date/time representation (string)
- LC_date -- format string for date representation (string)
- LC_time -- format string for time representation (string)
- timezone -- daylight- and non-daylight-savings timezone representation
- (2-item list of sets)
- lang -- Language used by instance (2-item tuple)
- """
- def __init__(self):
- """Set all attributes.
- Order of methods called matters for dependency reasons.
- The locale language is set at the offset and then checked again before
- exiting. This is to make sure that the attributes were not set with a
- mix of information from more than one locale. This would most likely
- happen when using threads where one thread calls a locale-dependent
- function while another thread changes the locale while the function in
- the other thread is still running. Proper coding would call for
- locks to prevent changing the locale while locale-dependent code is
- running. The check here is done in case someone does not think about
- doing this.
- Only other possible issue is if someone changed the timezone and did
- not call tz.tzset . That is an issue for the programmer, though,
- since changing the timezone is worthless without that call.
- """
- self.lang = _getlang()
- self.__calc_weekday()
- self.__calc_month()
- self.__calc_am_pm()
- self.__calc_timezone()
- 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 __calc_weekday(self):
- # Set self.a_weekday and self.f_weekday using the calendar
- # module.
- a_weekday = [calendar.day_abbr[i].lower() for i in range(7)]
- f_weekday = [calendar.day_name[i].lower() for i in range(7)]
- self.a_weekday = a_weekday
- self.f_weekday = f_weekday
- def __calc_month(self):
- # Set self.f_month and self.a_month using the calendar module.
- a_month = [calendar.month_abbr[i].lower() for i in range(13)]
- f_month = [calendar.month_name[i].lower() for i in range(13)]
- self.a_month = a_month
- self.f_month = f_month
- def __calc_am_pm(self):
- # Set self.am_pm by using time.strftime().
- # The magic date (1999,3,17,hour,44,55,2,76,0) is not really that
- # magical; just happened to have used it everywhere else where a
- # static date was needed.
- 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())
- self.am_pm = am_pm
- def __calc_date_time(self):
- # Set self.date_time, self.date, & self.time by using
- # time.strftime().
- # Use (1999,3,17,22,44,55,2,76,0) for magic date because the amount of
- # overloaded numbers is minimized. The order in which searches for
- # 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'),
- ('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:
- # 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)
- # 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):
- U_W = '%W'
- else:
- U_W = '%U'
- date_time[offset] = current_format.replace('11', U_W)
- self.LC_date_time = date_time[0]
- self.LC_date = date_time[1]
- self.LC_time = date_time[2]
- def __calc_timezone(self):
- # Set self.timezone by using time.tzname.
- # 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
- 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)
- class TimeRE(dict):
- """Handle conversion from format directives to regexes."""
- def __init__(self, locale_time=None):
- """Create keys/values.
- Order of execution is important for dependency reasons.
- """
- if locale_time:
- self.locale_time = locale_time
- else:
- self.locale_time = LocaleTime()
- base = super()
- base.__init__({
- # The " [1-9]" 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])",
- '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])",
- '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])",
- '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)",
- '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)",
- # W is set below by using 'U'
- 'y': r"(?P<y>\d\d)",
- #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})?)?|(?-i: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'),
- 'b': self.__seqToRE(self.locale_time.a_month[1:], 'b'),
- 'p': self.__seqToRE(self.locale_time.am_pm, 'p'),
- 'Z': self.__seqToRE((tz for tz_names in self.locale_time.timezone
- for tz in tz_names),
- 'Z'),
- '%': '%'})
- base.__setitem__('W', base.__getitem__('U').replace('U', 'W'))
- base.__setitem__('c', self.pattern(self.locale_time.LC_date_time))
- base.__setitem__('x', self.pattern(self.locale_time.LC_date))
- base.__setitem__('X', self.pattern(self.locale_time.LC_time))
- def __seqToRE(self, to_convert, directive):
- """Convert a list to a regex string for matching a directive.
- Want possible matching values to be from longest to shortest. This
- prevents the possibility of a match occurring for a value that also
- a substring of a larger value that should have matched (e.g., 'abc'
- matching when 'abcdef' should have been the match).
- """
- to_convert = sorted(to_convert, key=len, reverse=True)
- for value in to_convert:
- if value != '':
- break
- else:
- return ''
- regex = '|'.join(re_escape(stuff) for stuff in to_convert)
- regex = '(?P<%s>%s' % (directive, regex)
- return '%s)' % regex
- def pattern(self, format):
- """Return regex pattern for the format string.
- Need to make sure that any characters that might be interpreted as
- regex syntax are escaped.
- """
- processed_format = ''
- # The sub() call escapes all characters that might be misconstrued
- # as regex syntax. Cannot use re.escape since we have to deal with
- # format directives (%m, etc.).
- regex_chars = re_compile(r"([\\.^$*+?\(\){}\[\]|])")
- format = regex_chars.sub(r"\\\1", format)
- whitespace_replacement = re_compile(r'\s+')
- format = whitespace_replacement.sub(r'\\s+', format)
- while '%' in format:
- directive_index = format.index('%')+1
- processed_format = "%s%s%s" % (processed_format,
- format[:directive_index-1],
- self[format[directive_index]])
- format = format[directive_index+1:]
- return "%s%s" % (processed_format, format)
- def compile(self, format):
- """Return a compiled re object for the format string."""
- 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
- # first!
- _TimeRE_cache = TimeRE()
- _CACHE_MAX_SIZE = 5 # Max number of regexes stored in _regex_cache
- _regex_cache = {}
- def _calc_julian_from_U_or_W(year, week_of_year, day_of_week, week_starts_Mon):
- """Calculate the Julian day based on the year, week of the year, and day of
- the week, with week_start_day representing whether the week of the year
- assumes the week starts on Sunday or Monday (6 or 0)."""
- first_weekday = datetime_date(year, 1, 1).weekday()
- # If we are dealing with the %U directive (week starts on Sunday), it's
- # easier to just shift the view to Sunday being the first day of the
- # week.
- if not week_starts_Mon:
- first_weekday = (first_weekday + 1) % 7
- day_of_week = (day_of_week + 1) % 7
- # Need to watch out for a week 0 (when the first day of the year is not
- # the same as that specified by %U or %W).
- week_0_length = (7 - first_weekday) % 7
- if week_of_year == 0:
- return 1 + day_of_week - first_weekday
- else:
- days_to_week = week_0_length + (7 * (week_of_year - 1))
- return 1 + days_to_week + day_of_week
- def _calc_julian_from_V(iso_year, iso_week, iso_weekday):
- """Calculate the Julian day based on the ISO 8601 year, week, and weekday.
- ISO weeks start on Mondays, with week 01 being the week containing 4 Jan.
- ISO week days range from 1 (Monday) to 7 (Sunday).
- """
- correction = datetime_date(iso_year, 1, 4).isoweekday() + 3
- ordinal = (iso_week * 7) + iso_weekday - correction
- # ordinal may be negative or 0 now, which means the date is in the previous
- # calendar year
- if ordinal < 1:
- ordinal += datetime_date(iso_year, 1, 1).toordinal()
- iso_year -= 1
- ordinal -= datetime_date(iso_year, 1, 1).toordinal()
- return iso_year, ordinal
- def _strptime(data_string, format="%a %b %d %H:%M:%S %Y"):
- """Return a 2-tuple consisting of a time struct and an int containing
- the number of microseconds 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(index, type(arg)))
- global _TimeRE_cache, _regex_cache
- with _cache_lock:
- 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()
- format_regex = _regex_cache.get(format)
- if not format_regex:
- try:
- format_regex = _TimeRE_cache.compile(format)
- # KeyError raised when a bad format is found; can be specified as
- # \\, in which case it was a stray % but with a space after it
- except KeyError as err:
- bad_directive = err.args[0]
- if bad_directive == "\\":
- bad_directive = "%"
- del err
- raise ValueError("'%s' is a bad directive in format '%s'" %
- (bad_directive, format)) from None
- # IndexError only occurs when the format string is "%"
- except IndexError:
- raise ValueError("stray %% in format '%s'" % format) from None
- _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))
- if len(data_string) != found.end():
- raise ValueError("unconverted data remains: %s" %
- data_string[found.end():])
- iso_year = year = None
- month = day = 1
- hour = minute = second = fraction = 0
- tz = -1
- gmtoff = None
- gmtoff_fraction = 0
- # Default to -1 to signify that values not known; not critical to have,
- # though
- iso_week = week_of_year = None
- week_of_year_start = None
- # weekday and julian defaulted to None so as to signal need to calculate
- # values
- weekday = julian = None
- found_dict = found.groupdict()
- for group_key in found_dict.keys():
- # Directives not explicitly handled below:
- # c, x, X
- # handled by making out of other directives
- # U, W
- # worthless without day of the week
- if group_key == 'y':
- year = int(found_dict['y'])
- # Open Group specification for strptime() states that a %y
- #value in the range of [00, 68] is in the century 2000, while
- #[69,99] is in the century 1900
- if year <= 68:
- year += 2000
- else:
- year += 1900
- elif group_key == 'Y':
- year = int(found_dict['Y'])
- elif group_key == 'G':
- iso_year = int(found_dict['G'])
- elif group_key == 'm':
- month = int(found_dict['m'])
- elif group_key == 'B':
- month = locale_time.f_month.index(found_dict['B'].lower())
- elif group_key == 'b':
- month = locale_time.a_month.index(found_dict['b'].lower())
- elif group_key == 'd':
- day = int(found_dict['d'])
- elif group_key == 'H':
- hour = int(found_dict['H'])
- elif group_key == 'I':
- hour = int(found_dict['I'])
- ampm = found_dict.get('p', '').lower()
- # If there was no AM/PM indicator, we'll treat this like AM
- if ampm in ('', locale_time.am_pm[0]):
- # We're in AM so the hour is correct unless we're
- # looking at 12 midnight.
- # 12 midnight == 12 AM == hour 0
- if hour == 12:
- hour = 0
- elif ampm == locale_time.am_pm[1]:
- # We're in PM so we need to add 12 to the hour unless
- # we're looking at 12 noon.
- # 12 noon == 12 PM == hour 12
- if hour != 12:
- hour += 12
- elif group_key == 'M':
- minute = int(found_dict['M'])
- elif group_key == 'S':
- second = int(found_dict['S'])
- elif group_key == 'f':
- s = found_dict['f']
- # Pad to always return microseconds.
- s += "0" * (6 - len(s))
- fraction = int(s)
- elif group_key == 'A':
- weekday = locale_time.f_weekday.index(found_dict['A'].lower())
- elif group_key == 'a':
- weekday = locale_time.a_weekday.index(found_dict['a'].lower())
- elif group_key == 'w':
- weekday = int(found_dict['w'])
- if weekday == 0:
- weekday = 6
- else:
- weekday -= 1
- elif group_key == 'u':
- weekday = int(found_dict['u'])
- weekday -= 1
- elif group_key == 'j':
- julian = int(found_dict['j'])
- elif group_key in ('U', 'W'):
- week_of_year = int(found_dict[group_key])
- if group_key == 'U':
- # U starts week on Sunday.
- week_of_year_start = 6
- else:
- # W starts week on Monday.
- week_of_year_start = 0
- elif group_key == 'V':
- iso_week = int(found_dict['V'])
- elif group_key == 'z':
- z = found_dict['z']
- if z == 'Z':
- gmtoff = 0
- else:
- if z[3] == ':':
- z = z[:3] + z[4:]
- if len(z) > 5:
- if z[5] != ':':
- msg = f"Inconsistent use of : in {found_dict['z']}"
- raise ValueError(msg)
- z = z[:5] + z[6:]
- hours = int(z[1:3])
- minutes = int(z[3:5])
- seconds = int(z[5:7] or 0)
- gmtoff = (hours * 60 * 60) + (minutes * 60) + seconds
- gmtoff_remainder = z[8:]
- # Pad to always return microseconds.
- gmtoff_remainder_padding = "0" * (6 - len(gmtoff_remainder))
- gmtoff_fraction = int(gmtoff_remainder + gmtoff_remainder_padding)
- if z.startswith("-"):
- gmtoff = -gmtoff
- gmtoff_fraction = -gmtoff_fraction
- elif group_key == 'Z':
- # Since -1 is default value only need to worry about setting tz if
- # it can be something other than -1.
- found_zone = found_dict['Z'].lower()
- for value, tz_values in enumerate(locale_time.timezone):
- if found_zone in tz_values:
- # Deal with bad locale setup where timezone names are the
- # same and yet time.daylight is true; too ambiguous to
- # be able to tell what timezone has daylight savings
- if (time.tzname[0] == time.tzname[1] and
- time.daylight and found_zone not in ("utc", "gmt")):
- break
- else:
- tz = value
- break
- # Deal with the cases where ambiguities arize
- # don't assume default values for ISO week/year
- if year is None and iso_year is not None:
- if iso_week is None or weekday is None:
- raise ValueError("ISO year directive '%G' must be used with "
- "the ISO week directive '%V' and a weekday "
- "directive ('%A', '%a', '%w', or '%u').")
- if julian is not None:
- raise ValueError("Day of the year directive '%j' is not "
- "compatible with ISO year directive '%G'. "
- "Use '%Y' instead.")
- elif week_of_year is None and iso_week is not None:
- if weekday is None:
- raise ValueError("ISO week directive '%V' must be used with "
- "the ISO year directive '%G' and a weekday "
- "directive ('%A', '%a', '%w', or '%u').")
- else:
- raise ValueError("ISO week directive '%V' is incompatible with "
- "the year directive '%Y'. Use the ISO year '%G' "
- "instead.")
- leap_year_fix = False
- if year is None and month == 2 and day == 29:
- year = 1904 # 1904 is first leap year of 20th century
- leap_year_fix = True
- elif year is None:
- year = 1900
- # If we know the week of the year and what day of that week, we can figure
- # out the Julian day of the year.
- if julian is None and weekday is not None:
- if week_of_year is not None:
- week_starts_Mon = True if week_of_year_start == 0 else False
- julian = _calc_julian_from_U_or_W(year, week_of_year, weekday,
- week_starts_Mon)
- elif iso_year is not None and iso_week is not None:
- year, julian = _calc_julian_from_V(iso_year, iso_week, weekday + 1)
- if julian is not None and julian <= 0:
- year -= 1
- yday = 366 if calendar.isleap(year) else 365
- julian += yday
- if julian is None:
- # Cannot pre-calculate datetime_date() since can change in Julian
- # calculation and thus could have different value for the day of
- # the week calculation.
- # Need to add 1 to result since first day of the year is 1, not 0.
- julian = datetime_date(year, month, day).toordinal() - \
- datetime_date(year, 1, 1).toordinal() + 1
- else: # Assume that if they bothered to include Julian day (or if it was
- # calculated above with year/week/weekday) it will be accurate.
- datetime_result = datetime_date.fromordinal(
- (julian - 1) +
- datetime_date(year, 1, 1).toordinal())
- year = datetime_result.year
- month = datetime_result.month
- day = datetime_result.day
- if weekday is None:
- weekday = datetime_date(year, month, day).weekday()
- # Add timezone info
- tzname = found_dict.get("Z")
- if leap_year_fix:
- # the caller didn't supply a year but asked for Feb 29th. We couldn't
- # use the default of 1900 for computations. We set it back to ensure
- # that February 29th is smaller than March 1st.
- year = 1900
- return (year, month, day,
- hour, minute, second,
- weekday, julian, tz, tzname, gmtoff), fraction, gmtoff_fraction
- def _strptime_time(data_string, format="%a %b %d %H:%M:%S %Y"):
- """Return a time struct based on the input string and the
- format string."""
- tt = _strptime(data_string, format)[0]
- return time.struct_time(tt[:time._STRUCT_TM_ITEMS])
- def _strptime_datetime(cls, data_string, format="%a %b %d %H:%M:%S %Y"):
- """Return a class cls instance based on the input string and the
- format string."""
- tt, fraction, gmtoff_fraction = _strptime(data_string, format)
- tzname, gmtoff = tt[-2:]
- args = tt[:6] + (fraction,)
- if gmtoff is not None:
- tzdelta = datetime_timedelta(seconds=gmtoff, microseconds=gmtoff_fraction)
- if tzname:
- tz = datetime_timezone(tzdelta, tzname)
- else:
- tz = datetime_timezone(tzdelta)
- args += (tz,)
- return cls(*args)
|