From 330981c533405681dbee0939ea31a6663b70494e Mon Sep 17 00:00:00 2001 From: CPython Developers <> Date: Mon, 15 Aug 2022 03:30:12 +0900 Subject: [PATCH] Update dataclasses from CPython 3.10.6 --- Lib/dataclasses.py | 289 ++++++++++--- Lib/test/dataclass_module_1.py | 32 ++ Lib/test/dataclass_module_1_str.py | 32 ++ Lib/test/dataclass_module_2.py | 32 ++ Lib/test/dataclass_module_2_str.py | 32 ++ Lib/test/dataclass_textanno.py | 12 + Lib/test/test_dataclasses.py | 664 ++++++++++++++++++++++++++++- 7 files changed, 1013 insertions(+), 80 deletions(-) create mode 100644 Lib/test/dataclass_module_1.py create mode 100644 Lib/test/dataclass_module_1_str.py create mode 100644 Lib/test/dataclass_module_2.py create mode 100644 Lib/test/dataclass_module_2_str.py create mode 100644 Lib/test/dataclass_textanno.py diff --git a/Lib/dataclasses.py b/Lib/dataclasses.py index ec881093a..105a95b95 100644 --- a/Lib/dataclasses.py +++ b/Lib/dataclasses.py @@ -6,8 +6,9 @@ import inspect import keyword import builtins import functools +import abc import _thread -from types import GenericAlias +from types import FunctionType, GenericAlias __all__ = ['dataclass', @@ -15,6 +16,7 @@ __all__ = ['dataclass', 'Field', 'FrozenInstanceError', 'InitVar', + 'KW_ONLY', 'MISSING', # Helper functions. @@ -151,6 +153,20 @@ __all__ = ['dataclass', # # See _hash_action (below) for a coded version of this table. +# __match_args__ +# +# +--- match_args= parameter +# | +# v | | | +# | no | yes | <--- class has __match_args__ in __dict__? +# +=======+=======+=======+ +# | False | | | +# +-------+-------+-------+ +# | True | add | | <- the default +# +=======+=======+=======+ +# __match_args__ is always added unless the class already defines it. It is a +# tuple of __init__ parameter names; non-init fields must be matched by keyword. + # Raised when an attempt is made to modify a frozen class. class FrozenInstanceError(AttributeError): pass @@ -169,6 +185,12 @@ class _MISSING_TYPE: pass MISSING = _MISSING_TYPE() +# A sentinel object to indicate that following fields are keyword-only by +# default. Use a class to give it a better repr. +class _KW_ONLY_TYPE: + pass +KW_ONLY = _KW_ONLY_TYPE() + # Since most per-field metadata will be unused, create an empty # read-only proxy that can be shared among all fields. _EMPTY_METADATA = types.MappingProxyType({}) @@ -200,18 +222,14 @@ _POST_INIT_NAME = '__post_init__' # https://bugs.python.org/issue33453 for details. _MODULE_IDENTIFIER_RE = re.compile(r'^(?:\s*(\w+)\s*\.)?\s*(\w+)') -class _InitVarMeta(type): - def __getitem__(self, params): - return InitVar(params) - -class InitVar(metaclass=_InitVarMeta): +class InitVar: __slots__ = ('type', ) def __init__(self, type): self.type = type def __repr__(self): - if isinstance(self.type, type): + if isinstance(self.type, type) and not isinstance(self.type, GenericAlias): type_name = self.type.__name__ else: # typing objects, e.g. List[int] @@ -241,11 +259,12 @@ class Field: 'init', 'compare', 'metadata', + 'kw_only', '_field_type', # Private: not to be used by user code. ) def __init__(self, default, default_factory, init, repr, hash, compare, - metadata): + metadata, kw_only): self.name = None self.type = None self.default = default @@ -257,6 +276,7 @@ class Field: self.metadata = (_EMPTY_METADATA if metadata is None else types.MappingProxyType(metadata)) + self.kw_only = kw_only self._field_type = None def __repr__(self): @@ -270,6 +290,7 @@ class Field: f'hash={self.hash!r},' f'compare={self.compare!r},' f'metadata={self.metadata!r},' + f'kw_only={self.kw_only!r},' f'_field_type={self._field_type}' ')') @@ -323,17 +344,19 @@ class _DataclassParams: # so that a type checker can be told (via overloads) that this is a # function whose type depends on its parameters. def field(*, default=MISSING, default_factory=MISSING, init=True, repr=True, - hash=None, compare=True, metadata=None): + hash=None, compare=True, metadata=None, kw_only=MISSING): """Return an object to identify dataclass fields. default is the default value of the field. default_factory is a 0-argument function called to initialize a field's value. If init - is True, the field will be a parameter to the class's __init__() - function. If repr is True, the field will be included in the - object's repr(). If hash is True, the field will be included in - the object's hash(). If compare is True, the field will be used - in comparison functions. metadata, if specified, must be a - mapping which is stored but not otherwise examined by dataclass. + is true, the field will be a parameter to the class's __init__() + function. If repr is true, the field will be included in the + object's repr(). If hash is true, the field will be included in the + object's hash(). If compare is true, the field will be used in + comparison functions. metadata, if specified, must be a mapping + which is stored but not otherwise examined by dataclass. If kw_only + is true, the field will become a keyword-only parameter to + __init__(). It is an error to specify both default and default_factory. """ @@ -341,7 +364,16 @@ def field(*, default=MISSING, default_factory=MISSING, init=True, repr=True, if default is not MISSING and default_factory is not MISSING: raise ValueError('cannot specify both default and default_factory') return Field(default, default_factory, init, repr, hash, compare, - metadata) + metadata, kw_only) + + +def _fields_in_init_order(fields): + # Returns the fields as __init__ will output them. It returns 2 tuples: + # the first for normal args, and the second for keyword args. + + return (tuple(f for f in fields if f.init and not f.kw_only), + tuple(f for f in fields if f.init and f.kw_only) + ) def _tuple_str(obj_name, fields): @@ -398,7 +430,6 @@ def _create_fn(name, args, body, *, globals=None, locals=None, local_vars = ', '.join(locals.keys()) txt = f"def __create_fn__({local_vars}):\n{txt}\n return {name}" - ns = {} exec(txt, globals, ns) return ns['__create_fn__'](**locals) @@ -416,7 +447,7 @@ def _field_assign(frozen, name, value, self_name): return f'{self_name}.{name}={value}' -def _field_init(f, frozen, globals, self_name): +def _field_init(f, frozen, globals, self_name, slots): # Return the text of the line in the body of __init__ that will # initialize this field. @@ -456,9 +487,15 @@ def _field_init(f, frozen, globals, self_name): globals[default_name] = f.default value = f.name else: - # This field does not need initialization. Signify that - # to the caller by returning None. - return None + # If the class has slots, then initialize this field. + if slots and f.default is not MISSING: + globals[default_name] = f.default + value = default_name + else: + # This field does not need initialization: reading from it will + # just use the class attribute that contains the default. + # Signify that to the caller by returning None. + return None # Only test this now, so that we can create variables for the # default. However, return None to signify that we're not going @@ -489,7 +526,8 @@ def _init_param(f): return f'{f.name}:_type_{f.name}{default}' -def _init_fn(fields, frozen, has_post_init, self_name, globals): +def _init_fn(fields, std_fields, kw_only_fields, frozen, has_post_init, + self_name, globals, slots): # fields contains both real fields and InitVar pseudo-fields. # Make sure we don't have fields without defaults following fields @@ -497,9 +535,10 @@ def _init_fn(fields, frozen, has_post_init, self_name, globals): # function source code, but catching it here gives a better error # message, and future-proofs us in case we build up the function # using ast. + seen_default = False - for f in fields: - # Only consider fields in the __init__ call. + for f in std_fields: + # Only consider the non-kw-only fields in the __init__ call. if f.init: if not (f.default is MISSING and f.default_factory is MISSING): seen_default = True @@ -515,7 +554,7 @@ def _init_fn(fields, frozen, has_post_init, self_name, globals): body_lines = [] for f in fields: - line = _field_init(f, frozen, locals, self_name) + line = _field_init(f, frozen, locals, self_name, slots) # line is None means that this field doesn't require # initialization (it's a pseudo-field). Just skip it. if line: @@ -531,8 +570,15 @@ def _init_fn(fields, frozen, has_post_init, self_name, globals): if not body_lines: body_lines = ['pass'] + _init_params = [_init_param(f) for f in std_fields] + if kw_only_fields: + # Add the keyword-only args. Because the * can only be added if + # there's at least one keyword-only arg, there needs to be a test here + # (instead of just concatenting the lists together). + _init_params += ['*'] + _init_params += [_init_param(f) for f in kw_only_fields] return _create_fn('__init__', - [self_name] + [_init_param(f) for f in fields if f.init], + [self_name] + _init_params, body_lines, locals=locals, globals=globals, @@ -611,6 +657,9 @@ def _is_initvar(a_type, dataclasses): return (a_type is dataclasses.InitVar or type(a_type) is dataclasses.InitVar) +def _is_kw_only(a_type, dataclasses): + return a_type is dataclasses.KW_ONLY + def _is_type(annotation, cls, a_module, a_type, is_type_predicate): # Given a type annotation string, does it refer to a_type in @@ -671,10 +720,11 @@ def _is_type(annotation, cls, a_module, a_type, is_type_predicate): return False -def _get_field(cls, a_name, a_type): - # Return a Field object for this field name and type. ClassVars - # and InitVars are also returned, but marked as such (see - # f._field_type). +def _get_field(cls, a_name, a_type, default_kw_only): + # Return a Field object for this field name and type. ClassVars and + # InitVars are also returned, but marked as such (see f._field_type). + # default_kw_only is the value of kw_only to use if there isn't a field() + # that defines it. # If the default value isn't derived from Field, then it's only a # normal default value. Convert it to a Field(). @@ -745,6 +795,19 @@ def _get_field(cls, a_name, a_type): # init=)? It makes no sense for # ClassVar and InitVar to specify init=. + # kw_only validation and assignment. + if f._field_type in (_FIELD, _FIELD_INITVAR): + # For real and InitVar fields, if kw_only wasn't specified use the + # default value. + if f.kw_only is MISSING: + f.kw_only = default_kw_only + else: + # Make sure kw_only isn't set for ClassVars + assert f._field_type is _FIELD_CLASSVAR + if f.kw_only is not MISSING: + raise TypeError(f'field {f.name} is a ClassVar but specifies ' + 'kw_only') + # For real fields, disallow mutable defaults for known types. if f._field_type is _FIELD and isinstance(f.default, (list, dict, set)): raise ValueError(f'mutable default {type(f.default)} for field ' @@ -752,12 +815,19 @@ def _get_field(cls, a_name, a_type): return f +def _set_qualname(cls, value): + # Ensure that the functions returned from _create_fn uses the proper + # __qualname__ (the class they belong to). + if isinstance(value, FunctionType): + value.__qualname__ = f"{cls.__qualname__}.{value.__name__}" + return value def _set_new_attribute(cls, name, value): # Never overwrites an existing attribute. Returns True if the # attribute already exists. if name in cls.__dict__: return True + _set_qualname(cls, value) setattr(cls, name, value) return False @@ -772,7 +842,7 @@ def _hash_set_none(cls, fields, globals): def _hash_add(cls, fields, globals): flds = [f for f in fields if (f.compare if f.hash is None else f.hash)] - return _hash_fn(flds, globals) + return _set_qualname(cls, _hash_fn(flds, globals)) def _hash_exception(cls, fields, globals): # Raise an exception. @@ -809,7 +879,8 @@ _hash_action = {(False, False, False, False): None, # version of this table. -def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen): +def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen, + match_args, kw_only, slots): # Now that dicts retain insertion order, there's no reason to use # an ordered dict. I am leveraging that ordering here, because # derived class fields overwrite base class fields, but the order @@ -863,8 +934,27 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen): # Now find fields in our class. While doing so, validate some # things, and set the default values (as class attributes) where # we can. - cls_fields = [_get_field(cls, name, type) - for name, type in cls_annotations.items()] + cls_fields = [] + # Get a reference to this module for the _is_kw_only() test. + KW_ONLY_seen = False + dataclasses = sys.modules[__name__] + for name, type in cls_annotations.items(): + # See if this is a marker to change the value of kw_only. + if (_is_kw_only(type, dataclasses) + or (isinstance(type, str) + and _is_type(type, cls, dataclasses, dataclasses.KW_ONLY, + _is_kw_only))): + # Switch the default to kw_only=True, and ignore this + # annotation: it's not a real field. + if KW_ONLY_seen: + raise TypeError(f'{name!r} is KW_ONLY, but KW_ONLY ' + 'has already been specified') + KW_ONLY_seen = True + kw_only = True + else: + # Otherwise it's a field of some type. + cls_fields.append(_get_field(cls, name, type, kw_only)) + for f in cls_fields: fields[f.name] = f @@ -919,15 +1009,22 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen): if order and not eq: raise ValueError('eq must be true if order is true') + # Include InitVars and regular fields (so, not ClassVars). This is + # initialized here, outside of the "if init:" test, because std_init_fields + # is used with match_args, below. + all_init_fields = [f for f in fields.values() + if f._field_type in (_FIELD, _FIELD_INITVAR)] + (std_init_fields, + kw_only_init_fields) = _fields_in_init_order(all_init_fields) + if init: # Does this class have a post-init function? has_post_init = hasattr(cls, _POST_INIT_NAME) - # Include InitVars and regular fields (so, not ClassVars). - flds = [f for f in fields.values() - if f._field_type in (_FIELD, _FIELD_INITVAR)] _set_new_attribute(cls, '__init__', - _init_fn(flds, + _init_fn(all_init_fields, + std_init_fields, + kw_only_init_fields, frozen, has_post_init, # The name to use for the "self" @@ -936,6 +1033,7 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen): '__dataclass_self__' if 'self' in fields else 'self', globals, + slots, )) # Get the fields as a list, and include only real fields. This is @@ -947,7 +1045,7 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen): _set_new_attribute(cls, '__repr__', _repr_fn(flds, globals)) if eq: - # Create _eq__ method. There's no need for a __ne__ method, + # Create __eq__ method. There's no need for a __ne__ method, # since python will call __eq__ and negate it. flds = [f for f in field_list if f.compare] self_tuple = _tuple_str('self', flds) @@ -995,11 +1093,70 @@ def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen): cls.__doc__ = (cls.__name__ + str(inspect.signature(cls)).replace(' -> None', '')) + if match_args: + # I could probably compute this once + _set_new_attribute(cls, '__match_args__', + tuple(f.name for f in std_init_fields)) + + if slots: + cls = _add_slots(cls, frozen) + + abc.update_abstractmethods(cls) + + return cls + + +# _dataclass_getstate and _dataclass_setstate are needed for pickling frozen +# classes with slots. These could be slighly more performant if we generated +# the code instead of iterating over fields. But that can be a project for +# another day, if performance becomes an issue. +def _dataclass_getstate(self): + return [getattr(self, f.name) for f in fields(self)] + + +def _dataclass_setstate(self, state): + for field, value in zip(fields(self), state): + # use setattr because dataclass may be frozen + object.__setattr__(self, field.name, value) + + +def _add_slots(cls, is_frozen): + # Need to create a new class, since we can't set __slots__ + # after a class has been created. + + # Make sure __slots__ isn't already set. + if '__slots__' in cls.__dict__: + raise TypeError(f'{cls.__name__} already specifies __slots__') + + # Create a new dict for our new class. + cls_dict = dict(cls.__dict__) + field_names = tuple(f.name for f in fields(cls)) + cls_dict['__slots__'] = field_names + for field_name in field_names: + # Remove our attributes, if present. They'll still be + # available in _MARKER. + cls_dict.pop(field_name, None) + + # Remove __dict__ itself. + cls_dict.pop('__dict__', None) + + # And finally create the class. + qualname = getattr(cls, '__qualname__', None) + cls = type(cls)(cls.__name__, cls.__bases__, cls_dict) + if qualname is not None: + cls.__qualname__ = qualname + + if is_frozen: + # Need this for pickling frozen classes with slots. + cls.__getstate__ = _dataclass_getstate + cls.__setstate__ = _dataclass_setstate + return cls def dataclass(cls=None, /, *, init=True, repr=True, eq=True, order=False, - unsafe_hash=False, frozen=False): + unsafe_hash=False, frozen=False, match_args=True, + kw_only=False, slots=False): """Returns the same class as was passed in, with dunder methods added based on the fields defined in the class. @@ -1009,11 +1166,15 @@ def dataclass(cls=None, /, *, init=True, repr=True, eq=True, order=False, repr is true, a __repr__() method is added. If order is true, rich comparison dunder methods are added. If unsafe_hash is true, a __hash__() method function is added. If frozen is true, fields may - not be assigned to after instance creation. + not be assigned to after instance creation. If match_args is true, + the __match_args__ tuple is added. If kw_only is true, then by + default all fields are keyword-only. If slots is true, an + __slots__ attribute is added. """ def wrap(cls): - return _process_class(cls, init, repr, eq, order, unsafe_hash, frozen) + return _process_class(cls, init, repr, eq, order, unsafe_hash, + frozen, match_args, kw_only, slots) # See if we're being called as @dataclass or @dataclass(). if cls is None: @@ -1050,7 +1211,7 @@ def _is_dataclass_instance(obj): def is_dataclass(obj): """Returns True if obj is a dataclass or an instance of a dataclass.""" - cls = obj if isinstance(obj, type) else type(obj) + cls = obj if isinstance(obj, type) and not isinstance(obj, GenericAlias) else type(obj) return hasattr(cls, _FIELDS) @@ -1172,7 +1333,7 @@ def _astuple_inner(obj, tuple_factory): def make_dataclass(cls_name, fields, *, bases=(), namespace=None, init=True, repr=True, eq=True, order=False, unsafe_hash=False, - frozen=False): + frozen=False, match_args=True, kw_only=False, slots=False): """Return a new dynamically created dataclass. The dataclass name will be 'cls_name'. 'fields' is an iterable @@ -1198,14 +1359,12 @@ def make_dataclass(cls_name, fields, *, bases=(), namespace=None, init=True, if namespace is None: namespace = {} - else: - # Copy namespace since we're going to mutate it. - namespace = namespace.copy() # While we're looking through the field names, validate that they # are identifiers, are not keywords, and not duplicates. seen = set() - anns = {} + annotations = {} + defaults = {} for item in fields: if isinstance(item, str): name = item @@ -1214,7 +1373,7 @@ def make_dataclass(cls_name, fields, *, bases=(), namespace=None, init=True, name, tp, = item elif len(item) == 3: name, tp, spec = item - namespace[name] = spec + defaults[name] = spec else: raise TypeError(f'Invalid field: {item!r}') @@ -1226,17 +1385,25 @@ def make_dataclass(cls_name, fields, *, bases=(), namespace=None, init=True, raise TypeError(f'Field name duplicated: {name!r}') seen.add(name) - anns[name] = tp + annotations[name] = tp + + # Update 'ns' with the user-supplied namespace plus our calculated values. + def exec_body_callback(ns): + ns.update(namespace) + ns.update(defaults) + ns['__annotations__'] = annotations - namespace['__annotations__'] = anns # We use `types.new_class()` instead of simply `type()` to allow dynamic creation - # of generic dataclassses. - cls = types.new_class(cls_name, bases, {}, lambda ns: ns.update(namespace)) + # of generic dataclasses. + cls = types.new_class(cls_name, bases, {}, exec_body_callback) + + # Apply the normal decorator. return dataclass(cls, init=init, repr=repr, eq=eq, order=order, - unsafe_hash=unsafe_hash, frozen=frozen) + unsafe_hash=unsafe_hash, frozen=frozen, + match_args=match_args, kw_only=kw_only, slots=slots) -def replace(*args, **changes): +def replace(obj, /, **changes): """Return a new object replacing specified fields with new values. This is especially useful for frozen classes. Example usage: @@ -1250,17 +1417,6 @@ def replace(*args, **changes): c1 = replace(c, x=3) assert c1.x == 3 and c1.y == 2 """ - if len(args) > 1: - raise TypeError(f'replace() takes 1 positional argument but {len(args)} were given') - if args: - obj, = args - elif 'obj' in changes: - obj = changes.pop('obj') - import warnings - warnings.warn("Passing 'obj' as keyword argument is deprecated", - DeprecationWarning, stacklevel=2) - else: - raise TypeError("replace() missing 1 required positional argument: 'obj'") # We're going to mutate 'changes', but that's okay because it's a # new dict, even if called with 'replace(obj, **my_changes)'. @@ -1296,4 +1452,3 @@ def replace(*args, **changes): # changes that aren't fields, this will correctly raise a # TypeError. return obj.__class__(**changes) -replace.__text_signature__ = '(obj, /, **kwargs)' diff --git a/Lib/test/dataclass_module_1.py b/Lib/test/dataclass_module_1.py new file mode 100644 index 000000000..87a33f819 --- /dev/null +++ b/Lib/test/dataclass_module_1.py @@ -0,0 +1,32 @@ +#from __future__ import annotations +USING_STRINGS = False + +# dataclass_module_1.py and dataclass_module_1_str.py are identical +# except only the latter uses string annotations. + +import dataclasses +import typing + +T_CV2 = typing.ClassVar[int] +T_CV3 = typing.ClassVar + +T_IV2 = dataclasses.InitVar[int] +T_IV3 = dataclasses.InitVar + +@dataclasses.dataclass +class CV: + T_CV4 = typing.ClassVar + cv0: typing.ClassVar[int] = 20 + cv1: typing.ClassVar = 30 + cv2: T_CV2 + cv3: T_CV3 + not_cv4: T_CV4 # When using string annotations, this field is not recognized as a ClassVar. + +@dataclasses.dataclass +class IV: + T_IV4 = dataclasses.InitVar + iv0: dataclasses.InitVar[int] + iv1: dataclasses.InitVar + iv2: T_IV2 + iv3: T_IV3 + not_iv4: T_IV4 # When using string annotations, this field is not recognized as an InitVar. diff --git a/Lib/test/dataclass_module_1_str.py b/Lib/test/dataclass_module_1_str.py new file mode 100644 index 000000000..6de490b7a --- /dev/null +++ b/Lib/test/dataclass_module_1_str.py @@ -0,0 +1,32 @@ +from __future__ import annotations +USING_STRINGS = True + +# dataclass_module_1.py and dataclass_module_1_str.py are identical +# except only the latter uses string annotations. + +import dataclasses +import typing + +T_CV2 = typing.ClassVar[int] +T_CV3 = typing.ClassVar + +T_IV2 = dataclasses.InitVar[int] +T_IV3 = dataclasses.InitVar + +@dataclasses.dataclass +class CV: + T_CV4 = typing.ClassVar + cv0: typing.ClassVar[int] = 20 + cv1: typing.ClassVar = 30 + cv2: T_CV2 + cv3: T_CV3 + not_cv4: T_CV4 # When using string annotations, this field is not recognized as a ClassVar. + +@dataclasses.dataclass +class IV: + T_IV4 = dataclasses.InitVar + iv0: dataclasses.InitVar[int] + iv1: dataclasses.InitVar + iv2: T_IV2 + iv3: T_IV3 + not_iv4: T_IV4 # When using string annotations, this field is not recognized as an InitVar. diff --git a/Lib/test/dataclass_module_2.py b/Lib/test/dataclass_module_2.py new file mode 100644 index 000000000..68fb733e2 --- /dev/null +++ b/Lib/test/dataclass_module_2.py @@ -0,0 +1,32 @@ +#from __future__ import annotations +USING_STRINGS = False + +# dataclass_module_2.py and dataclass_module_2_str.py are identical +# except only the latter uses string annotations. + +from dataclasses import dataclass, InitVar +from typing import ClassVar + +T_CV2 = ClassVar[int] +T_CV3 = ClassVar + +T_IV2 = InitVar[int] +T_IV3 = InitVar + +@dataclass +class CV: + T_CV4 = ClassVar + cv0: ClassVar[int] = 20 + cv1: ClassVar = 30 + cv2: T_CV2 + cv3: T_CV3 + not_cv4: T_CV4 # When using string annotations, this field is not recognized as a ClassVar. + +@dataclass +class IV: + T_IV4 = InitVar + iv0: InitVar[int] + iv1: InitVar + iv2: T_IV2 + iv3: T_IV3 + not_iv4: T_IV4 # When using string annotations, this field is not recognized as an InitVar. diff --git a/Lib/test/dataclass_module_2_str.py b/Lib/test/dataclass_module_2_str.py new file mode 100644 index 000000000..b363d17c1 --- /dev/null +++ b/Lib/test/dataclass_module_2_str.py @@ -0,0 +1,32 @@ +from __future__ import annotations +USING_STRINGS = True + +# dataclass_module_2.py and dataclass_module_2_str.py are identical +# except only the latter uses string annotations. + +from dataclasses import dataclass, InitVar +from typing import ClassVar + +T_CV2 = ClassVar[int] +T_CV3 = ClassVar + +T_IV2 = InitVar[int] +T_IV3 = InitVar + +@dataclass +class CV: + T_CV4 = ClassVar + cv0: ClassVar[int] = 20 + cv1: ClassVar = 30 + cv2: T_CV2 + cv3: T_CV3 + not_cv4: T_CV4 # When using string annotations, this field is not recognized as a ClassVar. + +@dataclass +class IV: + T_IV4 = InitVar + iv0: InitVar[int] + iv1: InitVar + iv2: T_IV2 + iv3: T_IV3 + not_iv4: T_IV4 # When using string annotations, this field is not recognized as an InitVar. diff --git a/Lib/test/dataclass_textanno.py b/Lib/test/dataclass_textanno.py new file mode 100644 index 000000000..3eb6c943d --- /dev/null +++ b/Lib/test/dataclass_textanno.py @@ -0,0 +1,12 @@ +from __future__ import annotations + +import dataclasses + + +class Foo: + pass + + +@dataclasses.dataclass +class Bar: + foo: Foo diff --git a/Lib/test/test_dataclasses.py b/Lib/test/test_dataclasses.py index ed3370ff4..0694a5d05 100644 --- a/Lib/test/test_dataclasses.py +++ b/Lib/test/test_dataclasses.py @@ -4,12 +4,14 @@ from dataclasses import * +import abc import pickle import inspect import builtins +import types import unittest from unittest.mock import Mock -from typing import ClassVar, Any, List, Union, Tuple, Dict, Generic, TypeVar, Optional +from typing import ClassVar, Any, List, Union, Tuple, Dict, Generic, TypeVar, Optional, Protocol from typing import get_type_hints from collections import deque, OrderedDict, namedtuple from functools import total_ordering @@ -60,6 +62,7 @@ class TestCase(unittest.TestCase): f"default=1,default_factory={MISSING!r}," \ "init=True,repr=False,hash=None," \ "compare=True,metadata=mappingproxy({})," \ + f"kw_only={MISSING!r}," \ "_field_type=None)" self.assertEqual(repr_output, expected_output) @@ -1124,6 +1127,10 @@ class TestCase(unittest.TestCase): self.assertEqual(repr(InitVar[int]), 'dataclasses.InitVar[int]') self.assertEqual(repr(InitVar[List[int]]), 'dataclasses.InitVar[typing.List[int]]') + self.assertEqual(repr(InitVar[list[int]]), + 'dataclasses.InitVar[list[int]]') + self.assertEqual(repr(InitVar[int|str]), + 'dataclasses.InitVar[int | str]') def test_init_var_inheritance(self): # Note that this deliberately tests that a dataclass need not @@ -1348,6 +1355,17 @@ class TestCase(unittest.TestCase): with self.assertRaisesRegex(TypeError, 'should be called on dataclass instances'): replace(obj, x=0) + def test_is_dataclass_genericalias(self): + @dataclass + class A(types.GenericAlias): + origin: type + args: type + self.assertTrue(is_dataclass(A)) + a = A(list, int) + self.assertTrue(is_dataclass(type(a))) + self.assertTrue(is_dataclass(a)) + + def test_helper_fields_with_class_instance(self): # Check that we can call fields() on either a class or instance, # and get back the same thing. @@ -1907,9 +1925,7 @@ class TestCase(unittest.TestCase): # Check MRO resolution. self.assertEqual(Child.__mro__, (Child, Parent, Generic, object)) - # TODO: RUSTPYTHON - @unittest.expectedFailure - def test_dataclassses_pickleable(self): + def test_dataclasses_pickleable(self): global P, Q, R @dataclass class P: @@ -1938,6 +1954,30 @@ class TestCase(unittest.TestCase): self.assertEqual(new_sample.x, another_new_sample.x) self.assertEqual(sample.y, another_new_sample.y) + def test_dataclasses_qualnames(self): + @dataclass(order=True, unsafe_hash=True, frozen=True) + class A: + x: int + y: int + + self.assertEqual(A.__init__.__name__, "__init__") + for function in ( + '__eq__', + '__lt__', + '__le__', + '__gt__', + '__ge__', + '__hash__', + '__init__', + '__repr__', + '__setattr__', + '__delattr__', + ): + self.assertEqual(getattr(A, function).__qualname__, f"TestCase.test_dataclasses_qualnames..A.{function}") + + with self.assertRaisesRegex(TypeError, r"A\.__init__\(\) missing"): + A() + class TestFieldNoAnnotation(unittest.TestCase): def test_field_without_annotation(self): @@ -2034,7 +2074,7 @@ class TestDocString(unittest.TestCase): class C: x: Union[int, type(None)] = None - self.assertDocStrEqual(C.__doc__, "C(x:Union[int, NoneType]=None)") + self.assertDocStrEqual(C.__doc__, "C(x:Optional[int]=None)") def test_docstring_list_field(self): @dataclass @@ -2134,6 +2174,26 @@ class TestInit(unittest.TestCase): self.x = 2 * x self.assertEqual(C(5).x, 10) + def test_inherit_from_protocol(self): + # Dataclasses inheriting from protocol should preserve their own `__init__`. + # See bpo-45081. + + class P(Protocol): + a: int + + @dataclass + class C(P): + a: int + + self.assertEqual(C(5).a, 5) + + @dataclass + class D(P): + def __init__(self, a): + self.a = a * 2 + + self.assertEqual(D(5).a, 10) + class TestRepr(unittest.TestCase): def test_repr(self): @@ -2769,6 +2829,107 @@ class TestSlots(unittest.TestCase): # We can add a new field to the derived instance. d.z = 10 + def test_generated_slots(self): + @dataclass(slots=True) + class C: + x: int + y: int + + c = C(1, 2) + self.assertEqual((c.x, c.y), (1, 2)) + + c.x = 3 + c.y = 4 + self.assertEqual((c.x, c.y), (3, 4)) + + with self.assertRaisesRegex(AttributeError, "'C' object has no attribute 'z'"): + c.z = 5 + + def test_add_slots_when_slots_exists(self): + with self.assertRaisesRegex(TypeError, '^C already specifies __slots__$'): + @dataclass(slots=True) + class C: + __slots__ = ('x',) + x: int + + def test_generated_slots_value(self): + @dataclass(slots=True) + class Base: + x: int + + self.assertEqual(Base.__slots__, ('x',)) + + @dataclass(slots=True) + class Delivered(Base): + y: int + + self.assertEqual(Delivered.__slots__, ('x', 'y')) + + @dataclass + class AnotherDelivered(Base): + z: int + + self.assertTrue('__slots__' not in AnotherDelivered.__dict__) + + def test_returns_new_class(self): + class A: + x: int + + B = dataclass(A, slots=True) + self.assertIsNot(A, B) + + self.assertFalse(hasattr(A, "__slots__")) + self.assertTrue(hasattr(B, "__slots__")) + + # Can't be local to test_frozen_pickle. + @dataclass(frozen=True, slots=True) + class FrozenSlotsClass: + foo: str + bar: int + + @dataclass(frozen=True) + class FrozenWithoutSlotsClass: + foo: str + bar: int + + def test_frozen_pickle(self): + # bpo-43999 + + self.assertEqual(self.FrozenSlotsClass.__slots__, ("foo", "bar")) + for proto in range(pickle.HIGHEST_PROTOCOL + 1): + with self.subTest(proto=proto): + obj = self.FrozenSlotsClass("a", 1) + p = pickle.loads(pickle.dumps(obj, protocol=proto)) + self.assertIsNot(obj, p) + self.assertEqual(obj, p) + + obj = self.FrozenWithoutSlotsClass("a", 1) + p = pickle.loads(pickle.dumps(obj, protocol=proto)) + self.assertIsNot(obj, p) + self.assertEqual(obj, p) + + def test_slots_with_default_no_init(self): + # Originally reported in bpo-44649. + @dataclass(slots=True) + class A: + a: str + b: str = field(default='b', init=False) + + obj = A("a") + self.assertEqual(obj.a, 'a') + self.assertEqual(obj.b, 'b') + + def test_slots_with_default_factory_no_init(self): + # Originally reported in bpo-44649. + @dataclass(slots=True) + class A: + a: str + b: str = field(default_factory=lambda:'b', init=False) + + obj = A("a") + self.assertEqual(obj.a, 'a') + self.assertEqual(obj.b, 'b') + class TestDescriptors(unittest.TestCase): def test_set_name(self): # See bpo-33141. @@ -2840,6 +3001,115 @@ class TestDescriptors(unittest.TestCase): self.assertEqual(D.__set_name__.call_count, 1) + def test_init_calls_set(self): + class D: + pass + + D.__set__ = Mock() + + @dataclass + class C: + i: D = D() + + # Make sure D.__set__ is called. + D.__set__.reset_mock() + c = C(5) + self.assertEqual(D.__set__.call_count, 1) + + def test_getting_field_calls_get(self): + class D: + pass + + D.__set__ = Mock() + D.__get__ = Mock() + + @dataclass + class C: + i: D = D() + + c = C(5) + + # Make sure D.__get__ is called. + D.__get__.reset_mock() + value = c.i + self.assertEqual(D.__get__.call_count, 1) + + def test_setting_field_calls_set(self): + class D: + pass + + D.__set__ = Mock() + + @dataclass + class C: + i: D = D() + + c = C(5) + + # Make sure D.__set__ is called. + D.__set__.reset_mock() + c.i = 10 + self.assertEqual(D.__set__.call_count, 1) + + def test_setting_uninitialized_descriptor_field(self): + class D: + pass + + D.__set__ = Mock() + + @dataclass + class C: + i: D + + # D.__set__ is not called because there's no D instance to call it on + D.__set__.reset_mock() + c = C(5) + self.assertEqual(D.__set__.call_count, 0) + + # D.__set__ still isn't called after setting i to an instance of D + # because descriptors don't behave like that when stored as instance vars + c.i = D() + c.i = 5 + self.assertEqual(D.__set__.call_count, 0) + + def test_default_value(self): + class D: + def __get__(self, instance: Any, owner: object) -> int: + if instance is None: + return 100 + + return instance._x + + def __set__(self, instance: Any, value: int) -> None: + instance._x = value + + @dataclass + class C: + i: D = D() + + c = C() + self.assertEqual(c.i, 100) + + c = C(5) + self.assertEqual(c.i, 5) + + def test_no_default_value(self): + class D: + def __get__(self, instance: Any, owner: object) -> int: + if instance is None: + raise AttributeError() + + return instance._x + + def __set__(self, instance: Any, value: int) -> None: + instance._x = value + + @dataclass + class C: + i: D = D() + + with self.assertRaisesRegex(TypeError, 'missing 1 required positional argument'): + c = C() class TestStringAnnotations(unittest.TestCase): def test_classvar(self): @@ -2849,7 +3119,7 @@ class TestStringAnnotations(unittest.TestCase): # These tests assume that both "import typing" and "from # typing import *" have been run in this file. for typestr in ('ClassVar[int]', - 'ClassVar [int]' + 'ClassVar [int]', ' ClassVar [int]', 'ClassVar', ' ClassVar ', @@ -3176,13 +3446,6 @@ class TestReplace(unittest.TestCase): self.assertEqual(c1.x, 3) self.assertEqual(c1.y, 2) - self.assertRaises(TypeError, replace) - self.assertRaises(TypeError, replace, c, c) - with self.assertWarns(DeprecationWarning): - c1 = replace(obj=c, x=3) - self.assertEqual(c1.x, 3) - self.assertEqual(c1.y, 2) - # TODO: RUSTPYTHON @unittest.expectedFailure def test_frozen(self): @@ -3405,6 +3668,381 @@ class TestReplace(unittest.TestCase): ## replace(c, x=5) +class TestAbstract(unittest.TestCase): + def test_abc_implementation(self): + class Ordered(abc.ABC): + @abc.abstractmethod + def __lt__(self, other): + pass + + @abc.abstractmethod + def __le__(self, other): + pass + + @dataclass(order=True) + class Date(Ordered): + year: int + month: 'Month' + day: 'int' + + self.assertFalse(inspect.isabstract(Date)) + self.assertGreater(Date(2020,12,25), Date(2020,8,31)) + + def test_maintain_abc(self): + class A(abc.ABC): + @abc.abstractmethod + def foo(self): + pass + + @dataclass + class Date(A): + year: int + month: 'Month' + day: 'int' + + self.assertTrue(inspect.isabstract(Date)) + msg = 'class Date with abstract method foo' + self.assertRaisesRegex(TypeError, msg, Date) + + +class TestMatchArgs(unittest.TestCase): + def test_match_args(self): + @dataclass + class C: + a: int + self.assertEqual(C(42).__match_args__, ('a',)) + + def test_explicit_match_args(self): + ma = () + @dataclass + class C: + a: int + __match_args__ = ma + self.assertIs(C(42).__match_args__, ma) + + def test_bpo_43764(self): + @dataclass(repr=False, eq=False, init=False) + class X: + a: int + b: int + c: int + self.assertEqual(X.__match_args__, ("a", "b", "c")) + + def test_match_args_argument(self): + @dataclass(match_args=False) + class X: + a: int + self.assertNotIn('__match_args__', X.__dict__) + + @dataclass(match_args=False) + class Y: + a: int + __match_args__ = ('b',) + self.assertEqual(Y.__match_args__, ('b',)) + + @dataclass(match_args=False) + class Z(Y): + z: int + self.assertEqual(Z.__match_args__, ('b',)) + + # Ensure parent dataclass __match_args__ is seen, if child class + # specifies match_args=False. + @dataclass + class A: + a: int + z: int + @dataclass(match_args=False) + class B(A): + b: int + self.assertEqual(B.__match_args__, ('a', 'z')) + + def test_make_dataclasses(self): + C = make_dataclass('C', [('x', int), ('y', int)]) + self.assertEqual(C.__match_args__, ('x', 'y')) + + C = make_dataclass('C', [('x', int), ('y', int)], match_args=True) + self.assertEqual(C.__match_args__, ('x', 'y')) + + C = make_dataclass('C', [('x', int), ('y', int)], match_args=False) + self.assertNotIn('__match__args__', C.__dict__) + + C = make_dataclass('C', [('x', int), ('y', int)], namespace={'__match_args__': ('z',)}) + self.assertEqual(C.__match_args__, ('z',)) + + +class TestKeywordArgs(unittest.TestCase): + def test_no_classvar_kwarg(self): + msg = 'field a is a ClassVar but specifies kw_only' + with self.assertRaisesRegex(TypeError, msg): + @dataclass + class A: + a: ClassVar[int] = field(kw_only=True) + + with self.assertRaisesRegex(TypeError, msg): + @dataclass + class A: + a: ClassVar[int] = field(kw_only=False) + + with self.assertRaisesRegex(TypeError, msg): + @dataclass(kw_only=True) + class A: + a: ClassVar[int] = field(kw_only=False) + + def test_field_marked_as_kwonly(self): + ####################### + # Using dataclass(kw_only=True) + @dataclass(kw_only=True) + class A: + a: int + self.assertTrue(fields(A)[0].kw_only) + + @dataclass(kw_only=True) + class A: + a: int = field(kw_only=True) + self.assertTrue(fields(A)[0].kw_only) + + @dataclass(kw_only=True) + class A: + a: int = field(kw_only=False) + self.assertFalse(fields(A)[0].kw_only) + + ####################### + # Using dataclass(kw_only=False) + @dataclass(kw_only=False) + class A: + a: int + self.assertFalse(fields(A)[0].kw_only) + + @dataclass(kw_only=False) + class A: + a: int = field(kw_only=True) + self.assertTrue(fields(A)[0].kw_only) + + @dataclass(kw_only=False) + class A: + a: int = field(kw_only=False) + self.assertFalse(fields(A)[0].kw_only) + + ####################### + # Not specifying dataclass(kw_only) + @dataclass + class A: + a: int + self.assertFalse(fields(A)[0].kw_only) + + @dataclass + class A: + a: int = field(kw_only=True) + self.assertTrue(fields(A)[0].kw_only) + + @dataclass + class A: + a: int = field(kw_only=False) + self.assertFalse(fields(A)[0].kw_only) + + def test_match_args(self): + # kw fields don't show up in __match_args__. + @dataclass(kw_only=True) + class C: + a: int + self.assertEqual(C(a=42).__match_args__, ()) + + @dataclass + class C: + a: int + b: int = field(kw_only=True) + self.assertEqual(C(42, b=10).__match_args__, ('a',)) + + def test_KW_ONLY(self): + @dataclass + class A: + a: int + _: KW_ONLY + b: int + c: int + A(3, c=5, b=4) + msg = "takes 2 positional arguments but 4 were given" + with self.assertRaisesRegex(TypeError, msg): + A(3, 4, 5) + + + @dataclass(kw_only=True) + class B: + a: int + _: KW_ONLY + b: int + c: int + B(a=3, b=4, c=5) + msg = "takes 1 positional argument but 4 were given" + with self.assertRaisesRegex(TypeError, msg): + B(3, 4, 5) + + # Explicitly make a field that follows KW_ONLY be non-keyword-only. + @dataclass + class C: + a: int + _: KW_ONLY + b: int + c: int = field(kw_only=False) + c = C(1, 2, b=3) + self.assertEqual(c.a, 1) + self.assertEqual(c.b, 3) + self.assertEqual(c.c, 2) + c = C(1, b=3, c=2) + self.assertEqual(c.a, 1) + self.assertEqual(c.b, 3) + self.assertEqual(c.c, 2) + c = C(1, b=3, c=2) + self.assertEqual(c.a, 1) + self.assertEqual(c.b, 3) + self.assertEqual(c.c, 2) + c = C(c=2, b=3, a=1) + self.assertEqual(c.a, 1) + self.assertEqual(c.b, 3) + self.assertEqual(c.c, 2) + + def test_KW_ONLY_as_string(self): + @dataclass + class A: + a: int + _: 'dataclasses.KW_ONLY' + b: int + c: int + A(3, c=5, b=4) + msg = "takes 2 positional arguments but 4 were given" + with self.assertRaisesRegex(TypeError, msg): + A(3, 4, 5) + + def test_KW_ONLY_twice(self): + msg = "'Y' is KW_ONLY, but KW_ONLY has already been specified" + + with self.assertRaisesRegex(TypeError, msg): + @dataclass + class A: + a: int + X: KW_ONLY + Y: KW_ONLY + b: int + c: int + + with self.assertRaisesRegex(TypeError, msg): + @dataclass + class A: + a: int + X: KW_ONLY + b: int + Y: KW_ONLY + c: int + + with self.assertRaisesRegex(TypeError, msg): + @dataclass + class A: + a: int + X: KW_ONLY + b: int + c: int + Y: KW_ONLY + + # But this usage is okay, since it's not using KW_ONLY. + @dataclass + class A: + a: int + _: KW_ONLY + b: int + c: int = field(kw_only=True) + + # And if inheriting, it's okay. + @dataclass + class A: + a: int + _: KW_ONLY + b: int + c: int + @dataclass + class B(A): + _: KW_ONLY + d: int + + # Make sure the error is raised in a derived class. + with self.assertRaisesRegex(TypeError, msg): + @dataclass + class A: + a: int + _: KW_ONLY + b: int + c: int + @dataclass + class B(A): + X: KW_ONLY + d: int + Y: KW_ONLY + + + def test_post_init(self): + @dataclass + class A: + a: int + _: KW_ONLY + b: InitVar[int] + c: int + d: InitVar[int] + def __post_init__(self, b, d): + raise CustomError(f'{b=} {d=}') + with self.assertRaisesRegex(CustomError, 'b=3 d=4'): + A(1, c=2, b=3, d=4) + + @dataclass + class B: + a: int + _: KW_ONLY + b: InitVar[int] + c: int + d: InitVar[int] + def __post_init__(self, b, d): + self.a = b + self.c = d + b = B(1, c=2, b=3, d=4) + self.assertEqual(asdict(b), {'a': 3, 'c': 4}) + + def test_defaults(self): + # For kwargs, make sure we can have defaults after non-defaults. + @dataclass + class A: + a: int = 0 + _: KW_ONLY + b: int + c: int = 1 + d: int + + a = A(d=4, b=3) + self.assertEqual(a.a, 0) + self.assertEqual(a.b, 3) + self.assertEqual(a.c, 1) + self.assertEqual(a.d, 4) + + # Make sure we still check for non-kwarg non-defaults not following + # defaults. + err_regex = "non-default argument 'z' follows default argument" + with self.assertRaisesRegex(TypeError, err_regex): + @dataclass + class A: + a: int = 0 + z: int + _: KW_ONLY + b: int + c: int = 1 + d: int + + def test_make_dataclass(self): + A = make_dataclass("A", ['a'], kw_only=True) + self.assertTrue(fields(A)[0].kw_only) + + B = make_dataclass("B", + ['a', ('b', int, field(kw_only=False))], + kw_only=True) + self.assertTrue(fields(B)[0].kw_only) + self.assertFalse(fields(B)[1].kw_only) + if __name__ == '__main__': unittest.main()