[dateparser] Update to 1.5.*

stubs/dateparser/@tests/stubtest_allowlist.txt

@@ -1,3 +1,4 @@
+dateparser.calendars.french_republican
 dateparser.calendars.hijri
 dateparser.calendars.hijri_parser
 dateparser.calendars.jalali
@@ -6,3 +7,6 @@ dateparser.search.detection.BaseLanguageDetector.iterate_applicable_languages
 
 # Timezone and other internal data:
 dateparser.data.date_translation_data.*
+
+# A (str, Enum) mixin: stubtest compares str.__new__ in the stub with Enum.__new__ at runtime.
+dateparser._parts_of_day.PartOfDay.__new__

stubs/dateparser/METADATA.toml

@@ -1,4 +1,4 @@
-version = "1.4.3"
+version = "1.5.0"
 upstream-repository = "https://github.com/scrapinghub/dateparser"
 
 [tool.stubtest]

stubs/dateparser/dateparser/__init__.pyi

@@ -1,9 +1,11 @@
 import datetime
+from collections.abc import Mapping
 from typing import Any, Final, Literal, TypedDict, type_check_only
 
 from dateparser.conf import Settings
 
-from .date import DateDataParser, _DetectLanguagesFunction
+from ._parts_of_day import PartOfDay as PartOfDay, PartsOfDay as PartsOfDay
+from .date import DateDataParser as DateDataParser, _DetectLanguagesFunction
 
 __version__: Final[str]
 
@@ -13,9 +15,11 @@ _default_parser: DateDataParser
 class _Settings(TypedDict, total=False):  # noqa: Y049
     DATE_ORDER: Literal["DMY", "DYM", "MDY", "MYD", "YDM", "YMD"]
     PREFER_LOCALE_DATE_ORDER: bool
+    STRICT_DATE_ORDER: Literal["none", "year", "all"]
     TIMEZONE: str
     TO_TIMEZONE: str
     RETURN_AS_TIMEZONE_AWARE: bool
+    TIMEZONE_ABBREVIATIONS: Mapping[str, datetime.timedelta]
     PREFER_MONTH_OF_YEAR: Literal["current", "first", "last"]
     PREFER_DAY_OF_MONTH: Literal["current", "first", "last"]
     PREFER_DATES_FROM: Literal["current_period", "future", "past"]
@@ -29,8 +33,10 @@ class _Settings(TypedDict, total=False):  # noqa: Y049
     RETURN_TIME_SPAN: bool
     DEFAULT_START_OF_WEEK: Literal["monday", "sunday"]
     DEFAULT_DAYS_IN_MONTH: int
+    PARTS_OF_DAY: PartsOfDay
     PARSERS: list[Literal["timestamp", "relative-time", "custom-formats", "absolute-time", "no-spaces-time"]]
     DEFAULT_LANGUAGES: list[str]
+    USE_GIVEN_LANGUAGE_ORDER: bool
     LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD: float
     CACHE_SIZE_LIMIT: int
 

stubs/dateparser/dateparser/_parts_of_day.pyi

@@ -0,0 +1,19 @@
+from dataclasses import dataclass
+from datetime import time
+from enum import Enum
+
+class PartOfDay(str, Enum):
+    EARLY_MORNING = "early_morning"
+    MORNING = "morning"
+    AFTERNOON = "afternoon"
+    EVENING = "evening"
+    NIGHT = "night"
+
+@dataclass(frozen=True)
+class PartsOfDay:
+    early_morning: time = ...
+    morning: time = ...
+    afternoon: time = ...
+    evening: time = ...
+    night: time = ...
+    def __post_init__(self) -> None: ...

stubs/dateparser/dateparser/calendars/__init__.pyi

@@ -1,6 +1,6 @@
 from abc import abstractmethod
-from datetime import datetime
-from typing import ClassVar, Protocol, type_check_only
+from datetime import datetime, tzinfo
+from typing import ClassVar, Literal, Protocol, type_check_only
 
 from dateparser.conf import Settings
 from dateparser.date import DateData
@@ -12,20 +12,20 @@ class _CalendarConverter(Protocol):
     @classmethod
     def to_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: ...
     @classmethod
-    def from_gregorian(
-        cls, year: int | None = None, month: int | None = None, day: int | None = None
-    ) -> tuple[int, int, int]: ...
+    def from_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: ...
     @classmethod
     def month_length(cls, year: int, month: int) -> int: ...
 
-# Examples: `hijri_parser.HijriDate` or `jalali_parser.PersianDate`
+# Examples: `hijri_parser.HijriDate`, `jalali_parser.PersianDate` or `datetime.date`
 @type_check_only
 class _NonGregorianDate(Protocol):
-    year: int
-    month: int
-    day: int
+    @property
+    def year(self) -> int: ...
+    @property
+    def month(self) -> int: ...
+    @property
+    def day(self) -> int: ...
     def __init__(self, year: int, month: int, day: int) -> None: ...
-    def weekday(self) -> int | None: ...
 
 class CalendarBase:
     parser: type[_parser]
@@ -44,4 +44,10 @@ class non_gregorian_parser(_parser):
     @abstractmethod
     def handle_two_digit_year(self, year: int) -> int: ...
     @classmethod
-    def parse(cls, datestring: str, settings: Settings) -> tuple[datetime, str | None]: ...  # type: ignore[override]
+    def parse(
+        cls,
+        datestring: str,
+        settings: Settings,
+        tz: tzinfo | None = None,
+        date_order: Literal["DMY", "DYM", "MDY", "MYD", "YDM", "YMD"] | None = None,
+    ) -> tuple[datetime, str | None]: ...

stubs/dateparser/dateparser/calendars/french_republican.pyi

@@ -0,0 +1,12 @@
+from datetime import datetime
+
+from dateparser.conf import Settings
+
+from . import CalendarBase
+
+class _french_republican_parser:
+    @classmethod
+    def _parse_with_parts(cls, datestring: str, settings: Settings) -> tuple[datetime, str | None, tuple[str, ...]]: ...
+
+class FrenchRepublicanCalendar(CalendarBase):
+    parser: type[_french_republican_parser]  # type: ignore[assignment]

stubs/dateparser/dateparser/calendars/hijri_parser.pyi

@@ -17,7 +17,6 @@ class HijriDate:
     month: int
     day: int
     def __init__(self, year: int, month: int, day: int) -> None: ...
-    def weekday(self) -> int | None: ...
 
 class hijri_parser(non_gregorian_parser):
     calendar_converter: ClassVar[type[hijri]]

stubs/dateparser/dateparser/calendars/minguo.pyi

@@ -0,0 +1,20 @@
+from datetime import date
+from typing import ClassVar
+
+from . import CalendarBase, non_gregorian_parser
+
+class _minguo:
+    @classmethod
+    def to_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: ...
+    @classmethod
+    def from_gregorian(cls, year: int, month: int, day: int) -> tuple[int, int, int]: ...
+    @classmethod
+    def month_length(cls, year: int, month: int) -> int: ...
+
+class _minguo_parser(non_gregorian_parser):
+    calendar_converter: ClassVar[type[_minguo]]
+    non_gregorian_date_cls: ClassVar[type[date]]
+    def handle_two_digit_year(self, year: int) -> int: ...
+
+class MinguoCalendar(CalendarBase):
+    parser: type[_minguo_parser]

stubs/dateparser/dateparser/conf.pyi

@@ -1,7 +1,9 @@
 import datetime
-from collections.abc import Callable
+from collections.abc import Callable, Mapping
 from typing import Any, Literal, ParamSpec, TypeVar
-from typing_extensions import Self
+from typing_extensions import Self, deprecated
+
+from ._parts_of_day import PartsOfDay
 
 _P = ParamSpec("_P")
 _R = TypeVar("_R")
@@ -11,9 +13,11 @@ class Settings:
     # Please keep in sync with _Settings TypedDict
     DATE_ORDER: Literal["DMY", "DYM", "MDY", "MYD", "YDM", "YMD"]
     PREFER_LOCALE_DATE_ORDER: bool
+    STRICT_DATE_ORDER: Literal["none", "year", "all"]
     TIMEZONE: str
     TO_TIMEZONE: str
     RETURN_AS_TIMEZONE_AWARE: bool
+    TIMEZONE_ABBREVIATIONS: Mapping[str, datetime.timedelta]
     PREFER_MONTH_OF_YEAR: Literal["current", "first", "last"]
     PREFER_DAY_OF_MONTH: Literal["current", "first", "last"]
     PREFER_DATES_FROM: Literal["current_period", "future", "past"]
@@ -27,16 +31,18 @@ class Settings:
     RETURN_TIME_SPAN: bool
     DEFAULT_START_OF_WEEK: Literal["monday", "sunday"]
     DEFAULT_DAYS_IN_MONTH: int
+    PARTS_OF_DAY: PartsOfDay
     PARSERS: list[Literal["timestamp", "relative-time", "custom-formats", "absolute-time", "no-spaces-time"]]
     DEFAULT_LANGUAGES: list[str]
+    USE_GIVEN_LANGUAGE_ORDER: bool
     LANGUAGE_DETECTION_CONFIDENCE_THRESHOLD: float
     CACHE_SIZE_LIMIT: int
 
-    def __new__(cls, *args, **kwargs) -> Self: ...
-    def __init__(self, settings: dict[str, Any] | None = None) -> None: ...
+    def __init__(self, settings: Mapping[str, Any] | None = None) -> None: ...
     @classmethod
-    def get_key(cls, settings: dict[str, Any] | None = None) -> str: ...
-    def replace(self, mod_settings: dict[str, Any] | None = None, **kwds) -> Self: ...
+    @deprecated("Deprecated since dateparser 1.5.0; it will be removed in a future version.")
+    def get_key(cls, settings: Mapping[str, Any] | None = None) -> str: ...
+    def replace(self, mod_settings: Mapping[str, Any] | None = None, **kwds: Any) -> Self: ...
 
 settings: Settings
 

stubs/dateparser/dateparser/date.pyi

@@ -5,14 +5,15 @@ from collections.abc import Callable, Iterable, Iterator, Set as AbstractSet
 from datetime import date, datetime, tzinfo
 from typing import Any, ClassVar, Final, Literal, NamedTuple, TypeAlias, TypeVar, overload, type_check_only
 
+from dateparser._parts_of_day import PartOfDay
 from dateparser.conf import Settings
 from dateparser.languages.loader import LocaleDataLoader
 from dateparser.languages.locale import Locale
 
 _DateT = TypeVar("_DateT", bound=date)
 
 _DetectLanguagesFunction: TypeAlias = Callable[[str, float], list[str]]
-_Period: TypeAlias = Literal["time", "day", "week", "month", "year"]
+_Period: TypeAlias = Literal["time", "part_of_day", "day", "week", "month", "quarter", "year"]
 # Work around attribute and type having the same name.
 _Weekday: TypeAlias = Incomplete  # Actually it's dateutil._common.weekday class
 
@@ -23,15 +24,18 @@ class _DateData(NamedTuple):
     period: _Period | None
 
 APOSTROPHE_LOOK_ALIKE_CHARS: Final[list[str]]
+DASH_LOOK_ALIKE_CHARS: Final[list[str]]
 RE_NBSP: Final[re.Pattern[str]]
 RE_SPACES: Final[re.Pattern[str]]
 RE_TRIM_SPACES: Final[re.Pattern[str]]
-RE_TRIM_COLONS: Final[re.Pattern[str]]
+RE_TRIM_COLONS: Final[re.Pattern[str]]  # deprecated since 1.5.0, emits FutureWarning
 RE_SANITIZE_SKIP: Final[re.Pattern[str]]
 RE_SANITIZE_RUSSIAN: Final[re.Pattern[str]]
 RE_SANITIZE_PERIOD: Final[re.Pattern[str]]
+RE_SANITIZE_DECIMAL_COMMA: Final[re.Pattern[str]]
 RE_SANITIZE_ON: Final[re.Pattern[str]]
 RE_SANITIZE_APOSTROPHE: Final[re.Pattern[str]]
+RE_SANITIZE_DASH: Final[re.Pattern[str]]
 RE_SEARCH_TIMESTAMP: Final[re.Pattern[str]]
 RE_SANITIZE_CROATIAN: Final[re.Pattern[str]]
 RE_SEARCH_NEGATIVE_TIMESTAMP: Final[re.Pattern[str]]
@@ -75,16 +79,9 @@ class _DateLocaleParser:
         date_formats: list[str] | tuple[str, ...] | AbstractSet[str] | None,
         settings: Settings | None = None,
         ignore_surrounding_text: bool = False,
+        alternatives: bool = False,
+        failed: set[tuple[str, str | None, str]] | None = None,
     ) -> None: ...
-    @classmethod
-    def parse(
-        cls,
-        locale: Locale,
-        date_string: str,
-        date_formats: list[str] | tuple[str, ...] | AbstractSet[str] | None = None,
-        settings: Settings | None = None,
-        ignore_surrounding_text: bool = False,
-    ) -> DateData: ...
     def _parse(self) -> DateData | None: ...
     def _try_timestamp(self) -> DateData: ...
     def _try_freshness_parser(self) -> DateData | None: ...
@@ -97,24 +94,41 @@ class _DateLocaleParser:
     def _is_valid_date_data(self, date_data: DateData) -> bool: ...
 
 class DateData:
+    part_of_day: PartOfDay | None
     date_obj: datetime | None
     locale: str | None
     period: _Period | None
-    def __init__(self, *, date_obj: datetime | None = None, period: _Period | None = None, locale: str | None = None) -> None: ...
+    parts: tuple[Literal["year", "month", "day", "time"], ...]
+    def __init__(
+        self,
+        *,
+        date_obj: datetime | None = None,
+        period: _Period | None = None,
+        locale: str | None = None,
+        parts: tuple[Literal["year", "month", "day", "time"], ...] = (),
+    ) -> None: ...
 
     @overload
     def __getitem__(self, k: Literal["date_obj"]) -> datetime | None: ...
     @overload
     def __getitem__(self, k: Literal["locale"]) -> str | None: ...
     @overload
     def __getitem__(self, k: Literal["period"]) -> _Period | None: ...
+    @overload
+    def __getitem__(self, k: Literal["parts"]) -> tuple[Literal["year", "month", "day", "time"], ...]: ...
+    @overload
+    def __getitem__(self, k: Literal["part_of_day"]) -> PartOfDay | None: ...
 
     @overload
     def __setitem__(self, k: Literal["date_obj"], v: datetime) -> None: ...
     @overload
     def __setitem__(self, k: Literal["locale"], v: str) -> None: ...
     @overload
     def __setitem__(self, k: Literal["period"], v: _Period) -> None: ...
+    @overload
+    def __setitem__(self, k: Literal["parts"], v: tuple[Literal["year", "month", "day", "time"], ...]) -> None: ...
+    @overload
+    def __setitem__(self, k: Literal["part_of_day"], v: PartOfDay | None) -> None: ...
 
 class DateDataParser:
     _settings: Settings

stubs/dateparser/dateparser/freshness_date_parser.pyi

@@ -15,6 +15,6 @@ class FreshnessDateDataParser:
     def get_kwargs(
         self, date_string: str
     ) -> tuple[dict[str, float], dict[str, Incomplete]] | dict[None, None]: ...  # return empty dict if pattern not found
-    def get_date_data(self, date_string: str, settings: Settings | None = None) -> DateData: ...
+    def get_date_data(self, date_string: str, settings: Settings) -> DateData: ...
 
 freshness_date_parser: FreshnessDateDataParser

stubs/dateparser/dateparser/languages/locale.pyi

@@ -10,6 +10,7 @@ _K = TypeVar("_K", bound=Sized)
 _V = TypeVar("_V")
 
 NUMERAL_PATTERN: Final[Pattern[str]]
+PUNCTUATION: Final[str]
 
 class Locale:
     shortname: str
@@ -34,4 +35,3 @@ class Locale:
     ) -> str: ...
     def translate_search(self, search_string: str, settings: Settings | None = None) -> tuple[list[str], list[str]]: ...
     def get_wordchars_for_detection(self, settings: Settings) -> set[str]: ...
-    def to_parserinfo(self, base_cls: type = ...): ...

stubs/dateparser/dateparser/parser.pyi

@@ -61,15 +61,8 @@ class _parser:
         tokens: Iterable[tuple[str, _TokenType]],
         settings: Settings,
         date_order: Literal["DMY", "DYM", "MDY", "MYD", "YDM", "YMD"] | None = None,
-    ) -> None: ...
-    @classmethod
-    def parse(
-        cls,
-        datestring: str,
-        settings: Settings,
         tz: datetime.tzinfo | None = None,
-        date_order: Literal["DMY", "DYM", "MDY", "MYD", "YDM", "YMD"] | None = None,
-    ) -> tuple[datetime.datetime, str | None]: ...
+    ) -> None: ...
 
 class tokenizer:
     digits: Literal["0123456789:"]