interfaces: introduce and use a protocol class for the `charencoding` module
See
f2832de2a46c for details when this was done for the `bdiff` module.
This lets us dump the hack where the `pure` implementation was imported during
the type checking phase to provide signatures for the module methods it
provides. Now the protocol classes are starting to shine, because these methods
are provided by `pure.charencoding` and `cext.parsers`, and references to
`cffi.charencoding` and `cext.charencoding` are forwarded to them as appropriate
by the `policy` module. But none of that matters, as long as the module
returned provides the listed methods.
The interface was copy/pasted from the `pure` module, but `jsonescapeu8fallback`
is omitted because it is accessed from the `pure` module directly when the
escaping fails in the primary module's `jsonescapeu8()`.
from datetime import date, datetime, time, timedelta, timezone, tzinfo
from functools import lru_cache
import re
from typing import Any, Optional, Union
from ._types import ParseFloat
# E.g.
# - 00:32:00.999999
# - 00:32:00
_TIME_RE_STR = r"([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(?:\.([0-9]{1,6})[0-9]*)?"
RE_NUMBER = re.compile(
r"""
0
(?:
x[0-9A-Fa-f](?:_?[0-9A-Fa-f])* # hex
|
b[01](?:_?[01])* # bin
|
o[0-7](?:_?[0-7])* # oct
)
|
[+-]?(?:0|[1-9](?:_?[0-9])*) # dec, integer part
(?P<floatpart>
(?:\.[0-9](?:_?[0-9])*)? # optional fractional part
(?:[eE][+-]?[0-9](?:_?[0-9])*)? # optional exponent part
)
""",
flags=re.VERBOSE,
)
RE_LOCALTIME = re.compile(_TIME_RE_STR)
RE_DATETIME = re.compile(
fr"""
([0-9]{{4}})-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01]) # date, e.g. 1988-10-27
(?:
[Tt ]
{_TIME_RE_STR}
(?:([Zz])|([+-])([01][0-9]|2[0-3]):([0-5][0-9]))? # optional time offset
)?
""",
flags=re.VERBOSE,
)
def match_to_datetime(match: "re.Match") -> Union[datetime, date]:
"""Convert a `RE_DATETIME` match to `datetime.datetime` or `datetime.date`.
Raises ValueError if the match does not correspond to a valid date
or datetime.
"""
(
year_str,
month_str,
day_str,
hour_str,
minute_str,
sec_str,
micros_str,
zulu_time,
offset_sign_str,
offset_hour_str,
offset_minute_str,
) = match.groups()
year, month, day = int(year_str), int(month_str), int(day_str)
if hour_str is None:
return date(year, month, day)
hour, minute, sec = int(hour_str), int(minute_str), int(sec_str)
micros = int(micros_str.ljust(6, "0")) if micros_str else 0
if offset_sign_str:
tz: Optional[tzinfo] = cached_tz(
offset_hour_str, offset_minute_str, offset_sign_str
)
elif zulu_time:
tz = timezone.utc
else: # local date-time
tz = None
return datetime(year, month, day, hour, minute, sec, micros, tzinfo=tz)
@lru_cache(maxsize=None)
def cached_tz(hour_str: str, minute_str: str, sign_str: str) -> timezone:
sign = 1 if sign_str == "+" else -1
return timezone(
timedelta(
hours=sign * int(hour_str),
minutes=sign * int(minute_str),
)
)
def match_to_localtime(match: "re.Match") -> time:
hour_str, minute_str, sec_str, micros_str = match.groups()
micros = int(micros_str.ljust(6, "0")) if micros_str else 0
return time(int(hour_str), int(minute_str), int(sec_str), micros)
def match_to_number(match: "re.Match", parse_float: "ParseFloat") -> Any:
if match.group("floatpart"):
return parse_float(match.group())
return int(match.group(), 0)