From f2132fcd2a6da7b2b86e80189fa009ce1d2c753b Mon Sep 17 00:00:00 2001 From: Jelle Zijlstra Date: Tue, 9 Apr 2024 06:50:37 -0400 Subject: gh-117516: Implement typing.TypeIs (#117517) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit See PEP 742. Co-authored-by: Carl Meyer Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com> --- Doc/library/typing.rst | 118 ++++++++++++++++----- Doc/whatsnew/3.13.rst | 4 + Lib/test/test_typing.py | 56 +++++++++- Lib/typing.py | 96 +++++++++++++++-- .../2024-04-03-16-01-31.gh-issue-117516.7DlHje.rst | 1 + 5 files changed, 236 insertions(+), 39 deletions(-) create mode 100644 Misc/NEWS.d/next/Library/2024-04-03-16-01-31.gh-issue-117516.7DlHje.rst diff --git a/Doc/library/typing.rst b/Doc/library/typing.rst index 73214e1..19dbd37 100644 --- a/Doc/library/typing.rst +++ b/Doc/library/typing.rst @@ -1385,22 +1385,23 @@ These can be used as types in annotations. They all support subscription using .. versionadded:: 3.9 -.. data:: TypeGuard +.. data:: TypeIs - Special typing construct for marking user-defined type guard functions. + Special typing construct for marking user-defined type predicate functions. - ``TypeGuard`` can be used to annotate the return type of a user-defined - type guard function. ``TypeGuard`` only accepts a single type argument. - At runtime, functions marked this way should return a boolean. + ``TypeIs`` can be used to annotate the return type of a user-defined + type predicate function. ``TypeIs`` only accepts a single type argument. + At runtime, functions marked this way should return a boolean and take at + least one positional argument. - ``TypeGuard`` aims to benefit *type narrowing* -- a technique used by static + ``TypeIs`` aims to benefit *type narrowing* -- a technique used by static type checkers to determine a more precise type of an expression within a program's code flow. Usually type narrowing is done by analyzing conditional code flow and applying the narrowing to a block of code. The - conditional expression here is sometimes referred to as a "type guard":: + conditional expression here is sometimes referred to as a "type predicate":: def is_str(val: str | float): - # "isinstance" type guard + # "isinstance" type predicate if isinstance(val, str): # Type of ``val`` is narrowed to ``str`` ... @@ -1409,8 +1410,73 @@ These can be used as types in annotations. They all support subscription using ... Sometimes it would be convenient to use a user-defined boolean function - as a type guard. Such a function should use ``TypeGuard[...]`` as its - return type to alert static type checkers to this intention. + as a type predicate. Such a function should use ``TypeIs[...]`` or + :data:`TypeGuard` as its return type to alert static type checkers to + this intention. ``TypeIs`` usually has more intuitive behavior than + ``TypeGuard``, but it cannot be used when the input and output types + are incompatible (e.g., ``list[object]`` to ``list[int]``) or when the + function does not return ``True`` for all instances of the narrowed type. + + Using ``-> TypeIs[NarrowedType]`` tells the static type checker that for a given + function: + + 1. The return value is a boolean. + 2. If the return value is ``True``, the type of its argument + is the intersection of the argument's original type and ``NarrowedType``. + 3. If the return value is ``False``, the type of its argument + is narrowed to exclude ``NarrowedType``. + + For example:: + + from typing import assert_type, final, TypeIs + + class Parent: pass + class Child(Parent): pass + @final + class Unrelated: pass + + def is_parent(val: object) -> TypeIs[Parent]: + return isinstance(val, Parent) + + def run(arg: Child | Unrelated): + if is_parent(arg): + # Type of ``arg`` is narrowed to the intersection + # of ``Parent`` and ``Child``, which is equivalent to + # ``Child``. + assert_type(arg, Child) + else: + # Type of ``arg`` is narrowed to exclude ``Parent``, + # so only ``Unrelated`` is left. + assert_type(arg, Unrelated) + + The type inside ``TypeIs`` must be consistent with the type of the + function's argument; if it is not, static type checkers will raise + an error. An incorrectly written ``TypeIs`` function can lead to + unsound behavior in the type system; it is the user's responsibility + to write such functions in a type-safe manner. + + If a ``TypeIs`` function is a class or instance method, then the type in + ``TypeIs`` maps to the type of the second parameter after ``cls`` or + ``self``. + + In short, the form ``def foo(arg: TypeA) -> TypeIs[TypeB]: ...``, + means that if ``foo(arg)`` returns ``True``, then ``arg`` is an instance + of ``TypeB``, and if it returns ``False``, it is not an instance of ``TypeB``. + + ``TypeIs`` also works with type variables. For more information, see + :pep:`742` (Narrowing types with ``TypeIs``). + + .. versionadded:: 3.13 + + +.. data:: TypeGuard + + Special typing construct for marking user-defined type predicate functions. + + Type predicate functions are user-defined functions that return whether their + argument is an instance of a particular type. + ``TypeGuard`` works similarly to :data:`TypeIs`, but has subtly different + effects on type checking behavior (see below). Using ``-> TypeGuard`` tells the static type checker that for a given function: @@ -1419,6 +1485,8 @@ These can be used as types in annotations. They all support subscription using 2. If the return value is ``True``, the type of its argument is the type inside ``TypeGuard``. + ``TypeGuard`` also works with type variables. See :pep:`647` for more details. + For example:: def is_str_list(val: list[object]) -> TypeGuard[list[str]]: @@ -1433,23 +1501,19 @@ These can be used as types in annotations. They all support subscription using # Type of ``val`` remains as ``list[object]``. print("Not a list of strings!") - If ``is_str_list`` is a class or instance method, then the type in - ``TypeGuard`` maps to the type of the second parameter after ``cls`` or - ``self``. - - In short, the form ``def foo(arg: TypeA) -> TypeGuard[TypeB]: ...``, - means that if ``foo(arg)`` returns ``True``, then ``arg`` narrows from - ``TypeA`` to ``TypeB``. - - .. note:: - - ``TypeB`` need not be a narrower form of ``TypeA`` -- it can even be a - wider form. The main reason is to allow for things like - narrowing ``list[object]`` to ``list[str]`` even though the latter - is not a subtype of the former, since ``list`` is invariant. - The responsibility of writing type-safe type guards is left to the user. - - ``TypeGuard`` also works with type variables. See :pep:`647` for more details. + ``TypeIs`` and ``TypeGuard`` differ in the following ways: + + * ``TypeIs`` requires the narrowed type to be a subtype of the input type, while + ``TypeGuard`` does not. The main reason is to allow for things like + narrowing ``list[object]`` to ``list[str]`` even though the latter + is not a subtype of the former, since ``list`` is invariant. + * When a ``TypeGuard`` function returns ``True``, type checkers narrow the type of the + variable to exactly the ``TypeGuard`` type. When a ``TypeIs`` function returns ``True``, + type checkers can infer a more precise type combining the previously known type of the + variable with the ``TypeIs`` type. (Technically, this is known as an intersection type.) + * When a ``TypeGuard`` function returns ``False``, type checkers cannot narrow the type of + the variable at all. When a ``TypeIs`` function returns ``False``, type checkers can narrow + the type of the variable to exclude the ``TypeIs`` type. .. versionadded:: 3.10 diff --git a/Doc/whatsnew/3.13.rst b/Doc/whatsnew/3.13.rst index 72b3a4c..707dcaa 100644 --- a/Doc/whatsnew/3.13.rst +++ b/Doc/whatsnew/3.13.rst @@ -87,6 +87,10 @@ Interpreter improvements: Performance improvements are modest -- we expect to be improving this over the next few releases. +New typing features: + +* :pep:`742`: :data:`typing.TypeIs` was added, providing more intuitive + type narrowing behavior. New Features ============ diff --git a/Lib/test/test_typing.py b/Lib/test/test_typing.py index 927f74e..bae0a84 100644 --- a/Lib/test/test_typing.py +++ b/Lib/test/test_typing.py @@ -38,7 +38,7 @@ from typing import Annotated, ForwardRef from typing import Self, LiteralString from typing import TypeAlias from typing import ParamSpec, Concatenate, ParamSpecArgs, ParamSpecKwargs -from typing import TypeGuard +from typing import TypeGuard, TypeIs import abc import textwrap import typing @@ -5207,6 +5207,7 @@ class GenericTests(BaseTestCase): Literal[1, 2], Concatenate[int, ParamSpec("P")], TypeGuard[int], + TypeIs[range], ): with self.subTest(msg=obj): with self.assertRaisesRegex( @@ -6748,6 +6749,7 @@ class GetUtilitiesTestCase(TestCase): self.assertEqual(get_args(NotRequired[int]), (int,)) self.assertEqual(get_args(TypeAlias), ()) self.assertEqual(get_args(TypeGuard[int]), (int,)) + self.assertEqual(get_args(TypeIs[range]), (range,)) Ts = TypeVarTuple('Ts') self.assertEqual(get_args(Ts), ()) self.assertEqual(get_args((*Ts,)[0]), (Ts,)) @@ -9592,6 +9594,56 @@ class TypeGuardTests(BaseTestCase): issubclass(int, TypeGuard) +class TypeIsTests(BaseTestCase): + def test_basics(self): + TypeIs[int] # OK + + def foo(arg) -> TypeIs[int]: ... + self.assertEqual(gth(foo), {'return': TypeIs[int]}) + + with self.assertRaises(TypeError): + TypeIs[int, str] + + def test_repr(self): + self.assertEqual(repr(TypeIs), 'typing.TypeIs') + cv = TypeIs[int] + self.assertEqual(repr(cv), 'typing.TypeIs[int]') + cv = TypeIs[Employee] + self.assertEqual(repr(cv), 'typing.TypeIs[%s.Employee]' % __name__) + cv = TypeIs[tuple[int]] + self.assertEqual(repr(cv), 'typing.TypeIs[tuple[int]]') + + def test_cannot_subclass(self): + with self.assertRaisesRegex(TypeError, CANNOT_SUBCLASS_TYPE): + class C(type(TypeIs)): + pass + with self.assertRaisesRegex(TypeError, CANNOT_SUBCLASS_TYPE): + class D(type(TypeIs[int])): + pass + with self.assertRaisesRegex(TypeError, + r'Cannot subclass typing\.TypeIs'): + class E(TypeIs): + pass + with self.assertRaisesRegex(TypeError, + r'Cannot subclass typing\.TypeIs\[int\]'): + class F(TypeIs[int]): + pass + + def test_cannot_init(self): + with self.assertRaises(TypeError): + TypeIs() + with self.assertRaises(TypeError): + type(TypeIs)() + with self.assertRaises(TypeError): + type(TypeIs[Optional[int]])() + + def test_no_isinstance(self): + with self.assertRaises(TypeError): + isinstance(1, TypeIs[int]) + with self.assertRaises(TypeError): + issubclass(int, TypeIs) + + SpecialAttrsP = typing.ParamSpec('SpecialAttrsP') SpecialAttrsT = typing.TypeVar('SpecialAttrsT', int, float, complex) @@ -9691,6 +9743,7 @@ class SpecialAttrsTests(BaseTestCase): typing.Optional: 'Optional', typing.TypeAlias: 'TypeAlias', typing.TypeGuard: 'TypeGuard', + typing.TypeIs: 'TypeIs', typing.TypeVar: 'TypeVar', typing.Union: 'Union', typing.Self: 'Self', @@ -9705,6 +9758,7 @@ class SpecialAttrsTests(BaseTestCase): typing.Literal[True, 2]: 'Literal', typing.Optional[Any]: 'Optional', typing.TypeGuard[Any]: 'TypeGuard', + typing.TypeIs[Any]: 'TypeIs', typing.Union[Any]: 'Any', typing.Union[int, float]: 'Union', # Incompatible special forms (tested in test_special_attrs2) diff --git a/Lib/typing.py b/Lib/typing.py index d8e4ee3..231492c 100644 --- a/Lib/typing.py +++ b/Lib/typing.py @@ -153,6 +153,7 @@ __all__ = [ 'TYPE_CHECKING', 'TypeAlias', 'TypeGuard', + 'TypeIs', 'TypeAliasType', 'Unpack', ] @@ -818,28 +819,31 @@ def Concatenate(self, parameters): @_SpecialForm def TypeGuard(self, parameters): - """Special typing construct for marking user-defined type guard functions. + """Special typing construct for marking user-defined type predicate functions. ``TypeGuard`` can be used to annotate the return type of a user-defined - type guard function. ``TypeGuard`` only accepts a single type argument. + type predicate function. ``TypeGuard`` only accepts a single type argument. At runtime, functions marked this way should return a boolean. ``TypeGuard`` aims to benefit *type narrowing* -- a technique used by static type checkers to determine a more precise type of an expression within a program's code flow. Usually type narrowing is done by analyzing conditional code flow and applying the narrowing to a block of code. The - conditional expression here is sometimes referred to as a "type guard". + conditional expression here is sometimes referred to as a "type predicate". Sometimes it would be convenient to use a user-defined boolean function - as a type guard. Such a function should use ``TypeGuard[...]`` as its - return type to alert static type checkers to this intention. + as a type predicate. Such a function should use ``TypeGuard[...]`` or + ``TypeIs[...]`` as its return type to alert static type checkers to + this intention. ``TypeGuard`` should be used over ``TypeIs`` when narrowing + from an incompatible type (e.g., ``list[object]`` to ``list[int]``) or when + the function does not return ``True`` for all instances of the narrowed type. - Using ``-> TypeGuard`` tells the static type checker that for a given - function: + Using ``-> TypeGuard[NarrowedType]`` tells the static type checker that + for a given function: 1. The return value is a boolean. 2. If the return value is ``True``, the type of its argument - is the type inside ``TypeGuard``. + is ``NarrowedType``. For example:: @@ -860,7 +864,7 @@ def TypeGuard(self, parameters): type-unsafe results. The main reason is to allow for things like narrowing ``list[object]`` to ``list[str]`` even though the latter is not a subtype of the former, since ``list`` is invariant. The responsibility of - writing type-safe type guards is left to the user. + writing type-safe type predicates is left to the user. ``TypeGuard`` also works with type variables. For more information, see PEP 647 (User-Defined Type Guards). @@ -869,6 +873,75 @@ def TypeGuard(self, parameters): return _GenericAlias(self, (item,)) +@_SpecialForm +def TypeIs(self, parameters): + """Special typing construct for marking user-defined type predicate functions. + + ``TypeIs`` can be used to annotate the return type of a user-defined + type predicate function. ``TypeIs`` only accepts a single type argument. + At runtime, functions marked this way should return a boolean and accept + at least one argument. + + ``TypeIs`` aims to benefit *type narrowing* -- a technique used by static + type checkers to determine a more precise type of an expression within a + program's code flow. Usually type narrowing is done by analyzing + conditional code flow and applying the narrowing to a block of code. The + conditional expression here is sometimes referred to as a "type predicate". + + Sometimes it would be convenient to use a user-defined boolean function + as a type predicate. Such a function should use ``TypeIs[...]`` or + ``TypeGuard[...]`` as its return type to alert static type checkers to + this intention. ``TypeIs`` usually has more intuitive behavior than + ``TypeGuard``, but it cannot be used when the input and output types + are incompatible (e.g., ``list[object]`` to ``list[int]``) or when the + function does not return ``True`` for all instances of the narrowed type. + + Using ``-> TypeIs[NarrowedType]`` tells the static type checker that for + a given function: + + 1. The return value is a boolean. + 2. If the return value is ``True``, the type of its argument + is the intersection of the argument's original type and + ``NarrowedType``. + 3. If the return value is ``False``, the type of its argument + is narrowed to exclude ``NarrowedType``. + + For example:: + + from typing import assert_type, final, TypeIs + + class Parent: pass + class Child(Parent): pass + @final + class Unrelated: pass + + def is_parent(val: object) -> TypeIs[Parent]: + return isinstance(val, Parent) + + def run(arg: Child | Unrelated): + if is_parent(arg): + # Type of ``arg`` is narrowed to the intersection + # of ``Parent`` and ``Child``, which is equivalent to + # ``Child``. + assert_type(arg, Child) + else: + # Type of ``arg`` is narrowed to exclude ``Parent``, + # so only ``Unrelated`` is left. + assert_type(arg, Unrelated) + + The type inside ``TypeIs`` must be consistent with the type of the + function's argument; if it is not, static type checkers will raise + an error. An incorrectly written ``TypeIs`` function can lead to + unsound behavior in the type system; it is the user's responsibility + to write such functions in a type-safe manner. + + ``TypeIs`` also works with type variables. For more information, see + PEP 742 (Narrowing types with ``TypeIs``). + """ + item = _type_check(parameters, f'{self} accepts only single type.') + return _GenericAlias(self, (item,)) + + class ForwardRef(_Final, _root=True): """Internal wrapper to hold a forward reference.""" @@ -1241,11 +1314,12 @@ class _GenericAlias(_BaseGenericAlias, _root=True): # A = Callable[[], None] # _CallableGenericAlias # B = Callable[[T], None] # _CallableGenericAlias # C = B[int] # _CallableGenericAlias - # * Parameterized `Final`, `ClassVar` and `TypeGuard`: + # * Parameterized `Final`, `ClassVar`, `TypeGuard`, and `TypeIs`: # # All _GenericAlias # Final[int] # ClassVar[float] - # TypeVar[bool] + # TypeGuard[bool] + # TypeIs[range] def __init__(self, origin, args, *, inst=True, name=None): super().__init__(origin, inst=inst, name=name) diff --git a/Misc/NEWS.d/next/Library/2024-04-03-16-01-31.gh-issue-117516.7DlHje.rst b/Misc/NEWS.d/next/Library/2024-04-03-16-01-31.gh-issue-117516.7DlHje.rst new file mode 100644 index 0000000..bbf6912 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2024-04-03-16-01-31.gh-issue-117516.7DlHje.rst @@ -0,0 +1 @@ +Add :data:`typing.TypeIs`, implementing :pep:`742`. Patch by Jelle Zijlstra. -- cgit v0.12