/usr/lib/python3.7/dataclasses.py is in libpython3.7-stdlib 3.7.0~b3-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 | import sys
import copy
import types
import inspect
__all__ = ['dataclass',
'field',
'Field',
'FrozenInstanceError',
'InitVar',
'MISSING',
# Helper functions.
'fields',
'asdict',
'astuple',
'make_dataclass',
'replace',
'is_dataclass',
]
# Conditions for adding methods. The boxes indicate what action the
# dataclass decorator takes. For all of these tables, when I talk
# about init=, repr=, eq=, order=, unsafe_hash=, or frozen=, I'm
# referring to the arguments to the @dataclass decorator. When
# checking if a dunder method already exists, I mean check for an
# entry in the class's __dict__. I never check to see if an
# attribute is defined in a base class.
# Key:
# +=========+=========================================+
# + Value | Meaning |
# +=========+=========================================+
# | <blank> | No action: no method is added. |
# +---------+-----------------------------------------+
# | add | Generated method is added. |
# +---------+-----------------------------------------+
# | raise | TypeError is raised. |
# +---------+-----------------------------------------+
# | None | Attribute is set to None. |
# +=========+=========================================+
# __init__
#
# +--- init= parameter
# |
# v | | |
# | no | yes | <--- class has __init__ in __dict__?
# +=======+=======+=======+
# | False | | |
# +-------+-------+-------+
# | True | add | | <- the default
# +=======+=======+=======+
# __repr__
#
# +--- repr= parameter
# |
# v | | |
# | no | yes | <--- class has __repr__ in __dict__?
# +=======+=======+=======+
# | False | | |
# +-------+-------+-------+
# | True | add | | <- the default
# +=======+=======+=======+
# __setattr__
# __delattr__
#
# +--- frozen= parameter
# |
# v | | |
# | no | yes | <--- class has __setattr__ or __delattr__ in __dict__?
# +=======+=======+=======+
# | False | | | <- the default
# +-------+-------+-------+
# | True | add | raise |
# +=======+=======+=======+
# Raise because not adding these methods would break the "frozen-ness"
# of the class.
# __eq__
#
# +--- eq= parameter
# |
# v | | |
# | no | yes | <--- class has __eq__ in __dict__?
# +=======+=======+=======+
# | False | | |
# +-------+-------+-------+
# | True | add | | <- the default
# +=======+=======+=======+
# __lt__
# __le__
# __gt__
# __ge__
#
# +--- order= parameter
# |
# v | | |
# | no | yes | <--- class has any comparison method in __dict__?
# +=======+=======+=======+
# | False | | | <- the default
# +-------+-------+-------+
# | True | add | raise |
# +=======+=======+=======+
# Raise because to allow this case would interfere with using
# functools.total_ordering.
# __hash__
# +------------------- unsafe_hash= parameter
# | +----------- eq= parameter
# | | +--- frozen= parameter
# | | |
# v v v | | |
# | no | yes | <--- class has explicitly defined __hash__
# +=======+=======+=======+========+========+
# | False | False | False | | | No __eq__, use the base class __hash__
# +-------+-------+-------+--------+--------+
# | False | False | True | | | No __eq__, use the base class __hash__
# +-------+-------+-------+--------+--------+
# | False | True | False | None | | <-- the default, not hashable
# +-------+-------+-------+--------+--------+
# | False | True | True | add | | Frozen, so hashable, allows override
# +-------+-------+-------+--------+--------+
# | True | False | False | add | raise | Has no __eq__, but hashable
# +-------+-------+-------+--------+--------+
# | True | False | True | add | raise | Has no __eq__, but hashable
# +-------+-------+-------+--------+--------+
# | True | True | False | add | raise | Not frozen, but hashable
# +-------+-------+-------+--------+--------+
# | True | True | True | add | raise | Frozen, so hashable
# +=======+=======+=======+========+========+
# For boxes that are blank, __hash__ is untouched and therefore
# inherited from the base class. If the base is object, then
# id-based hashing is used.
# Note that a class may already have __hash__=None if it specified an
# __eq__ method in the class body (not one that was created by
# @dataclass).
# See _hash_action (below) for a coded version of this table.
# Raised when an attempt is made to modify a frozen class.
class FrozenInstanceError(AttributeError): pass
# A sentinel object for default values to signal that a
# default factory will be used.
# This is given a nice repr() which will appear in the function
# signature of dataclasses' constructors.
class _HAS_DEFAULT_FACTORY_CLASS:
def __repr__(self):
return '<factory>'
_HAS_DEFAULT_FACTORY = _HAS_DEFAULT_FACTORY_CLASS()
# A sentinel object to detect if a parameter is supplied or not. Use
# a class to give it a better repr.
class _MISSING_TYPE:
pass
MISSING = _MISSING_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({})
# Markers for the various kinds of fields and pseudo-fields.
_FIELD = object() # An actual field.
_FIELD_CLASSVAR = object() # Not a field, but a ClassVar.
_FIELD_INITVAR = object() # Not a field, but an InitVar.
# The name of an attribute on the class where we store the Field
# objects. Also used to check if a class is a Data Class.
_FIELDS = '__dataclass_fields__'
# The name of an attribute on the class that stores the parameters to
# @dataclass.
_PARAMS = '__dataclass_params__'
# The name of the function, that if it exists, is called at the end of
# __init__.
_POST_INIT_NAME = '__post_init__'
class _InitVarMeta(type):
def __getitem__(self, params):
return self
class InitVar(metaclass=_InitVarMeta):
pass
# Instances of Field are only ever created from within this module,
# and only from the field() function, although Field instances are
# exposed externally as (conceptually) read-only objects.
# name and type are filled in after the fact, not in __init__. They're
# not known at the time this class is instantiated, but it's
# convenient if they're available later.
# When cls._FIELDS is filled in with a list of Field objects, the name
# and type fields will have been populated.
class Field:
__slots__ = ('name',
'type',
'default',
'default_factory',
'repr',
'hash',
'init',
'compare',
'metadata',
'_field_type', # Private: not to be used by user code.
)
def __init__(self, default, default_factory, init, repr, hash, compare,
metadata):
self.name = None
self.type = None
self.default = default
self.default_factory = default_factory
self.init = init
self.repr = repr
self.hash = hash
self.compare = compare
self.metadata = (_EMPTY_METADATA
if metadata is None or len(metadata) == 0 else
types.MappingProxyType(metadata))
self._field_type = None
def __repr__(self):
return ('Field('
f'name={self.name!r},'
f'type={self.type},'
f'default={self.default},'
f'default_factory={self.default_factory},'
f'init={self.init},'
f'repr={self.repr},'
f'hash={self.hash},'
f'compare={self.compare},'
f'metadata={self.metadata}'
')')
# This is used to support the PEP 487 __set_name__ protocol in the
# case where we're using a field that contains a descriptor as a
# defaul value. For details on __set_name__, see
# https://www.python.org/dev/peps/pep-0487/#implementation-details.
# Note that in _process_class, this Field object is overwritten with
# the default value, so the end result is a descriptor that had
# __set_name__ called on it at the right time.
def __set_name__(self, owner, name):
func = getattr(self.default, '__set_name__', None)
if func:
# There is a __set_name__ method on the descriptor,
# call it.
func(owner, name)
class _DataclassParams:
__slots__ = ('init',
'repr',
'eq',
'order',
'unsafe_hash',
'frozen',
)
def __init__(self, init, repr, eq, order, unsafe_hash, frozen):
self.init = init
self.repr = repr
self.eq = eq
self.order = order
self.unsafe_hash = unsafe_hash
self.frozen = frozen
def __repr__(self):
return ('_DataclassParams('
f'init={self.init},'
f'repr={self.repr},'
f'eq={self.eq},'
f'order={self.order},'
f'unsafe_hash={self.unsafe_hash},'
f'frozen={self.frozen}'
')')
# This function is used instead of exposing Field creation directly,
# 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):
"""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.
It is an error to specify both default and default_factory.
"""
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)
def _tuple_str(obj_name, fields):
# Return a string representing each field of obj_name as a tuple
# member. So, if fields is ['x', 'y'] and obj_name is "self",
# return "(self.x,self.y)".
# Special case for the 0-tuple.
if not fields:
return '()'
# Note the trailing comma, needed if this turns out to be a 1-tuple.
return f'({",".join([f"{obj_name}.{f.name}" for f in fields])},)'
def _create_fn(name, args, body, *, globals=None, locals=None,
return_type=MISSING):
# Note that we mutate locals when exec() is called. Caller beware!
# The only callers are internal to this module, so no worries
# about external callers.
if locals is None:
locals = {}
return_annotation = ''
if return_type is not MISSING:
locals['_return_type'] = return_type
return_annotation = '->_return_type'
args = ','.join(args)
body = '\n'.join(f' {b}' for b in body)
# Compute the text of the entire function.
txt = f'def {name}({args}){return_annotation}:\n{body}'
exec(txt, globals, locals)
return locals[name]
def _field_assign(frozen, name, value, self_name):
# If we're a frozen class, then assign to our fields in __init__
# via object.__setattr__. Otherwise, just use a simple
# assignment.
# self_name is what "self" is called in this function: don't
# hard-code "self", since that might be a field name.
if frozen:
return f'object.__setattr__({self_name},{name!r},{value})'
return f'{self_name}.{name}={value}'
def _field_init(f, frozen, globals, self_name):
# Return the text of the line in the body of __init__ that will
# initialize this field.
default_name = f'_dflt_{f.name}'
if f.default_factory is not MISSING:
if f.init:
# This field has a default factory. If a parameter is
# given, use it. If not, call the factory.
globals[default_name] = f.default_factory
value = (f'{default_name}() '
f'if {f.name} is _HAS_DEFAULT_FACTORY '
f'else {f.name}')
else:
# This is a field that's not in the __init__ params, but
# has a default factory function. It needs to be
# initialized here by calling the factory function,
# because there's no other way to initialize it.
# For a field initialized with a default=defaultvalue, the
# class dict just has the default value
# (cls.fieldname=defaultvalue). But that won't work for a
# default factory, the factory must be called in __init__
# and we must assign that to self.fieldname. We can't
# fall back to the class dict's value, both because it's
# not set, and because it might be different per-class
# (which, after all, is why we have a factory function!).
globals[default_name] = f.default_factory
value = f'{default_name}()'
else:
# No default factory.
if f.init:
if f.default is MISSING:
# There's no default, just do an assignment.
value = f.name
elif f.default is not MISSING:
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
# Only test this now, so that we can create variables for the
# default. However, return None to signify that we're not going
# to actually do the assignment statement for InitVars.
if f._field_type == _FIELD_INITVAR:
return None
# Now, actually generate the field assignment.
return _field_assign(frozen, f.name, value, self_name)
def _init_param(f):
# Return the __init__ parameter string for this field.
# For example, the equivalent of 'x:int=3' (except instead of 'int',
# reference a variable set to int, and instead of '3', reference a
# variable set to 3).
if f.default is MISSING and f.default_factory is MISSING:
# There's no default, and no default_factory, just
# output the variable name and type.
default = ''
elif f.default is not MISSING:
# There's a default, this will be the name that's used to look it up.
default = f'=_dflt_{f.name}'
elif f.default_factory is not MISSING:
# There's a factory function. Set a marker.
default = '=_HAS_DEFAULT_FACTORY'
return f'{f.name}:_type_{f.name}{default}'
def _init_fn(fields, frozen, has_post_init, self_name):
# fields contains both real fields and InitVar pseudo-fields.
# Make sure we don't have fields without defaults following fields
# with defaults. This actually would be caught when exec-ing the
# 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.
if f.init:
if not (f.default is MISSING and f.default_factory is MISSING):
seen_default = True
elif seen_default:
raise TypeError(f'non-default argument {f.name!r} '
'follows default argument')
globals = {'MISSING': MISSING,
'_HAS_DEFAULT_FACTORY': _HAS_DEFAULT_FACTORY}
body_lines = []
for f in fields:
line = _field_init(f, frozen, globals, self_name)
# line is None means that this field doesn't require
# initialization (it's a pseudo-field). Just skip it.
if line:
body_lines.append(line)
# Does this class have a post-init function?
if has_post_init:
params_str = ','.join(f.name for f in fields
if f._field_type is _FIELD_INITVAR)
body_lines.append(f'{self_name}.{_POST_INIT_NAME}({params_str})')
# If no body lines, use 'pass'.
if not body_lines:
body_lines = ['pass']
locals = {f'_type_{f.name}': f.type for f in fields}
return _create_fn('__init__',
[self_name] + [_init_param(f) for f in fields if f.init],
body_lines,
locals=locals,
globals=globals,
return_type=None)
def _repr_fn(fields):
return _create_fn('__repr__',
('self',),
['return self.__class__.__qualname__ + f"(' +
', '.join([f"{f.name}={{self.{f.name}!r}}"
for f in fields]) +
')"'])
def _frozen_get_del_attr(cls, fields):
# XXX: globals is modified on the first call to _create_fn, then the
# modified version is used in the second call. Is this okay?
globals = {'cls': cls,
'FrozenInstanceError': FrozenInstanceError}
if fields:
fields_str = '(' + ','.join(repr(f.name) for f in fields) + ',)'
else:
# Special case for the zero-length tuple.
fields_str = '()'
return (_create_fn('__setattr__',
('self', 'name', 'value'),
(f'if type(self) is cls or name in {fields_str}:',
' raise FrozenInstanceError(f"cannot assign to field {name!r}")',
f'super(cls, self).__setattr__(name, value)'),
globals=globals),
_create_fn('__delattr__',
('self', 'name'),
(f'if type(self) is cls or name in {fields_str}:',
' raise FrozenInstanceError(f"cannot delete field {name!r}")',
f'super(cls, self).__delattr__(name)'),
globals=globals),
)
def _cmp_fn(name, op, self_tuple, other_tuple):
# Create a comparison function. If the fields in the object are
# named 'x' and 'y', then self_tuple is the string
# '(self.x,self.y)' and other_tuple is the string
# '(other.x,other.y)'.
return _create_fn(name,
('self', 'other'),
[ 'if other.__class__ is self.__class__:',
f' return {self_tuple}{op}{other_tuple}',
'return NotImplemented'])
def _hash_fn(fields):
self_tuple = _tuple_str('self', fields)
return _create_fn('__hash__',
('self',),
[f'return hash({self_tuple})'])
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).
# If the default value isn't derived from Field, then it's
# only a normal default value. Convert it to a Field().
default = getattr(cls, a_name, MISSING)
if isinstance(default, Field):
f = default
else:
if isinstance(default, types.MemberDescriptorType):
# This is a field in __slots__, so it has no default value.
default = MISSING
f = field(default=default)
# Assume it's a normal field until proven otherwise.
f._field_type = _FIELD
# Only at this point do we know the name and the type. Set them.
f.name = a_name
f.type = a_type
# If typing has not been imported, then it's impossible for
# any annotation to be a ClassVar. So, only look for ClassVar
# if typing has been imported.
typing = sys.modules.get('typing')
if typing is not None:
# This test uses a typing internal class, but it's the best
# way to test if this is a ClassVar.
if (type(a_type) is typing._GenericAlias and
a_type.__origin__ is typing.ClassVar):
# This field is a ClassVar, so it's not a field.
f._field_type = _FIELD_CLASSVAR
if f._field_type is _FIELD:
# Check if this is an InitVar.
if a_type is InitVar:
# InitVars are not fields, either.
f._field_type = _FIELD_INITVAR
# Validations for fields. This is delayed until now, instead of
# in the Field() constructor, since only here do we know the field
# name, which allows better error reporting.
# Special restrictions for ClassVar and InitVar.
if f._field_type in (_FIELD_CLASSVAR, _FIELD_INITVAR):
if f.default_factory is not MISSING:
raise TypeError(f'field {f.name} cannot have a '
'default factory')
# Should I check for other field settings? default_factory
# seems the most serious to check for. Maybe add others.
# For example, how about init=False (or really,
# init=<not-the-default-init-value>)? It makes no sense for
# ClassVar and InitVar to specify init=<anything>.
# 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 '
f'{f.name} is not allowed: use default_factory')
return f
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
setattr(cls, name, value)
return False
# Decide if/how we're going to create a hash function. Key is
# (unsafe_hash, eq, frozen, does-hash-exist). Value is the action to
# take. The common case is to do nothing, so instead of providing a
# function that is a no-op, use None to signify that.
def _hash_set_none(cls, fields):
return None
def _hash_add(cls, fields):
flds = [f for f in fields if (f.compare if f.hash is None else f.hash)]
return _hash_fn(flds)
def _hash_exception(cls, fields):
# Raise an exception.
raise TypeError(f'Cannot overwrite attribute __hash__ '
f'in class {cls.__name__}')
#
# +-------------------------------------- unsafe_hash?
# | +------------------------------- eq?
# | | +------------------------ frozen?
# | | | +---------------- has-explicit-hash?
# | | | |
# | | | | +------- action
# | | | | |
# v v v v v
_hash_action = {(False, False, False, False): None,
(False, False, False, True ): None,
(False, False, True, False): None,
(False, False, True, True ): None,
(False, True, False, False): _hash_set_none,
(False, True, False, True ): None,
(False, True, True, False): _hash_add,
(False, True, True, True ): None,
(True, False, False, False): _hash_add,
(True, False, False, True ): _hash_exception,
(True, False, True, False): _hash_add,
(True, False, True, True ): _hash_exception,
(True, True, False, False): _hash_add,
(True, True, False, True ): _hash_exception,
(True, True, True, False): _hash_add,
(True, True, True, True ): _hash_exception,
}
# See https://bugs.python.org/issue32929#msg312829 for an if-statement
# version of this table.
def _process_class(cls, init, repr, eq, order, unsafe_hash, frozen):
# 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
# is defined by the base class, which is found first.
fields = {}
setattr(cls, _PARAMS, _DataclassParams(init, repr, eq, order,
unsafe_hash, frozen))
# Find our base classes in reverse MRO order, and exclude
# ourselves. In reversed order so that more derived classes
# override earlier field definitions in base classes.
# As long as we're iterating over them, see if any are frozen.
any_frozen_base = False
has_dataclass_bases = False
for b in cls.__mro__[-1:0:-1]:
# Only process classes that have been processed by our
# decorator. That is, they have a _FIELDS attribute.
base_fields = getattr(b, _FIELDS, None)
if base_fields:
has_dataclass_bases = True
for f in base_fields.values():
fields[f.name] = f
if getattr(b, _PARAMS).frozen:
any_frozen_base = True
# Annotations that are defined in this class (not in base
# classes). If __annotations__ isn't present, then this class
# adds no new annotations. We use this to compute fields that
# are added by this class.
# Fields are found from cls_annotations, which is guaranteed to be
# ordered. Default values are from class attributes, if a field
# has a default. If the default value is a Field(), then it
# contains additional info beyond (and possibly including) the
# actual default value. Pseudo-fields ClassVars and InitVars are
# included, despite the fact that they're not real fields.
# That's dealt with later.
cls_annotations = cls.__dict__.get('__annotations__', {})
# 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()]
for f in cls_fields:
fields[f.name] = f
# If the class attribute (which is the default value for
# this field) exists and is of type 'Field', replace it
# with the real default. This is so that normal class
# introspection sees a real default value, not a Field.
if isinstance(getattr(cls, f.name, None), Field):
if f.default is MISSING:
# If there's no default, delete the class attribute.
# This happens if we specify field(repr=False), for
# example (that is, we specified a field object, but
# no default value). Also if we're using a default
# factory. The class attribute should not be set at
# all in the post-processed class.
delattr(cls, f.name)
else:
setattr(cls, f.name, f.default)
# Do we have any Field members that don't also have annotations?
for name, value in cls.__dict__.items():
if isinstance(value, Field) and not name in cls_annotations:
raise TypeError(f'{name!r} is a field but has no type annotation')
# Check rules that apply if we are derived from any dataclasses.
if has_dataclass_bases:
# Raise an exception if any of our bases are frozen, but we're not.
if any_frozen_base and not frozen:
raise TypeError('cannot inherit non-frozen dataclass from a '
'frozen one')
# Raise an exception if we're frozen, but none of our bases are.
if not any_frozen_base and frozen:
raise TypeError('cannot inherit frozen dataclass from a '
'non-frozen one')
# Remember all of the fields on our class (including bases). This also
# marks this class as being a dataclass.
setattr(cls, _FIELDS, fields)
# Was this class defined with an explicit __hash__? Note that if
# __eq__ is defined in this class, then python will automatically
# set __hash__ to None. This is a heuristic, as it's possible
# that such a __hash__ == None was not auto-generated, but it
# close enough.
class_hash = cls.__dict__.get('__hash__', MISSING)
has_explicit_hash = not (class_hash is MISSING or
(class_hash is None and '__eq__' in cls.__dict__))
# If we're generating ordering methods, we must be generating
# the eq methods.
if order and not eq:
raise ValueError('eq must be true if order is true')
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,
frozen,
has_post_init,
# The name to use for the "self" param
# in __init__. Use "self" if possible.
'__dataclass_self__' if 'self' in fields
else 'self',
))
# Get the fields as a list, and include only real fields. This is
# used in all of the following methods.
field_list = [f for f in fields.values() if f._field_type is _FIELD]
if repr:
flds = [f for f in field_list if f.repr]
_set_new_attribute(cls, '__repr__', _repr_fn(flds))
if eq:
# 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)
other_tuple = _tuple_str('other', flds)
_set_new_attribute(cls, '__eq__',
_cmp_fn('__eq__', '==',
self_tuple, other_tuple))
if order:
# Create and set the ordering methods.
flds = [f for f in field_list if f.compare]
self_tuple = _tuple_str('self', flds)
other_tuple = _tuple_str('other', flds)
for name, op in [('__lt__', '<'),
('__le__', '<='),
('__gt__', '>'),
('__ge__', '>='),
]:
if _set_new_attribute(cls, name,
_cmp_fn(name, op, self_tuple, other_tuple)):
raise TypeError(f'Cannot overwrite attribute {name} '
f'in class {cls.__name__}. Consider using '
'functools.total_ordering')
if frozen:
for fn in _frozen_get_del_attr(cls, field_list):
if _set_new_attribute(cls, fn.__name__, fn):
raise TypeError(f'Cannot overwrite attribute {fn.__name__} '
f'in class {cls.__name__}')
# Decide if/how we're going to create a hash function.
hash_action = _hash_action[bool(unsafe_hash),
bool(eq),
bool(frozen),
has_explicit_hash]
if hash_action:
# No need to call _set_new_attribute here, since by the time
# we're here the overwriting is unconditional.
cls.__hash__ = hash_action(cls, field_list)
if not getattr(cls, '__doc__'):
# Create a class doc-string.
cls.__doc__ = (cls.__name__ +
str(inspect.signature(cls)).replace(' -> None', ''))
return cls
# _cls should never be specified by keyword, so start it with an
# underscore. The presence of _cls is used to detect if this
# decorator is being called with parameters or not.
def dataclass(_cls=None, *, init=True, repr=True, eq=True, order=False,
unsafe_hash=False, frozen=False):
"""Returns the same class as was passed in, with dunder methods
added based on the fields defined in the class.
Examines PEP 526 __annotations__ to determine fields.
If init is true, an __init__() method is added to the class. If
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.
"""
def wrap(cls):
return _process_class(cls, init, repr, eq, order, unsafe_hash, frozen)
# See if we're being called as @dataclass or @dataclass().
if _cls is None:
# We're called with parens.
return wrap
# We're called as @dataclass without parens.
return wrap(_cls)
def fields(class_or_instance):
"""Return a tuple describing the fields of this dataclass.
Accepts a dataclass or an instance of one. Tuple elements are of
type Field.
"""
# Might it be worth caching this, per class?
try:
fields = getattr(class_or_instance, _FIELDS)
except AttributeError:
raise TypeError('must be called with a dataclass type or instance')
# Exclude pseudo-fields. Note that fields is sorted by insertion
# order, so the order of the tuple is as the fields were defined.
return tuple(f for f in fields.values() if f._field_type is _FIELD)
def _is_dataclass_instance(obj):
"""Returns True if obj is an instance of a dataclass."""
return not isinstance(obj, type) and hasattr(obj, _FIELDS)
def is_dataclass(obj):
"""Returns True if obj is a dataclass or an instance of a
dataclass."""
return hasattr(obj, _FIELDS)
def asdict(obj, *, dict_factory=dict):
"""Return the fields of a dataclass instance as a new dictionary mapping
field names to field values.
Example usage:
@dataclass
class C:
x: int
y: int
c = C(1, 2)
assert asdict(c) == {'x': 1, 'y': 2}
If given, 'dict_factory' will be used instead of built-in dict.
The function applies recursively to field values that are
dataclass instances. This will also look into built-in containers:
tuples, lists, and dicts.
"""
if not _is_dataclass_instance(obj):
raise TypeError("asdict() should be called on dataclass instances")
return _asdict_inner(obj, dict_factory)
def _asdict_inner(obj, dict_factory):
if _is_dataclass_instance(obj):
result = []
for f in fields(obj):
value = _asdict_inner(getattr(obj, f.name), dict_factory)
result.append((f.name, value))
return dict_factory(result)
elif isinstance(obj, (list, tuple)):
return type(obj)(_asdict_inner(v, dict_factory) for v in obj)
elif isinstance(obj, dict):
return type(obj)((_asdict_inner(k, dict_factory), _asdict_inner(v, dict_factory))
for k, v in obj.items())
else:
return copy.deepcopy(obj)
def astuple(obj, *, tuple_factory=tuple):
"""Return the fields of a dataclass instance as a new tuple of field values.
Example usage::
@dataclass
class C:
x: int
y: int
c = C(1, 2)
assert astuple(c) == (1, 2)
If given, 'tuple_factory' will be used instead of built-in tuple.
The function applies recursively to field values that are
dataclass instances. This will also look into built-in containers:
tuples, lists, and dicts.
"""
if not _is_dataclass_instance(obj):
raise TypeError("astuple() should be called on dataclass instances")
return _astuple_inner(obj, tuple_factory)
def _astuple_inner(obj, tuple_factory):
if _is_dataclass_instance(obj):
result = []
for f in fields(obj):
value = _astuple_inner(getattr(obj, f.name), tuple_factory)
result.append(value)
return tuple_factory(result)
elif isinstance(obj, (list, tuple)):
return type(obj)(_astuple_inner(v, tuple_factory) for v in obj)
elif isinstance(obj, dict):
return type(obj)((_astuple_inner(k, tuple_factory), _astuple_inner(v, tuple_factory))
for k, v in obj.items())
else:
return copy.deepcopy(obj)
def make_dataclass(cls_name, fields, *, bases=(), namespace=None, init=True,
repr=True, eq=True, order=False, unsafe_hash=False,
frozen=False):
"""Return a new dynamically created dataclass.
The dataclass name will be 'cls_name'. 'fields' is an iterable
of either (name), (name, type) or (name, type, Field) objects. If type is
omitted, use the string 'typing.Any'. Field objects are created by
the equivalent of calling 'field(name, type [, Field-info])'.
C = make_dataclass('C', ['x', ('y', int), ('z', int, field(init=False))], bases=(Base,))
is equivalent to:
@dataclass
class C(Base):
x: 'typing.Any'
y: int
z: int = field(init=False)
For the bases and namespace parameters, see the builtin type() function.
The parameters init, repr, eq, order, unsafe_hash, and frozen are passed to
dataclass().
"""
if namespace is None:
namespace = {}
else:
# Copy namespace since we're going to mutate it.
namespace = namespace.copy()
anns = {}
for item in fields:
if isinstance(item, str):
name = item
tp = 'typing.Any'
elif len(item) == 2:
name, tp, = item
elif len(item) == 3:
name, tp, spec = item
namespace[name] = spec
anns[name] = tp
namespace['__annotations__'] = anns
cls = type(cls_name, bases, namespace)
return dataclass(cls, init=init, repr=repr, eq=eq, order=order,
unsafe_hash=unsafe_hash, frozen=frozen)
def replace(obj, **changes):
"""Return a new object replacing specified fields with new values.
This is especially useful for frozen classes. Example usage:
@dataclass(frozen=True)
class C:
x: int
y: int
c = C(1, 2)
c1 = replace(c, x=3)
assert c1.x == 3 and c1.y == 2
"""
# We're going to mutate 'changes', but that's okay because it's a new
# dict, even if called with 'replace(obj, **my_changes)'.
if not _is_dataclass_instance(obj):
raise TypeError("replace() should be called on dataclass instances")
# It's an error to have init=False fields in 'changes'.
# If a field is not in 'changes', read its value from the provided obj.
for f in getattr(obj, _FIELDS).values():
if not f.init:
# Error if this field is specified in changes.
if f.name in changes:
raise ValueError(f'field {f.name} is declared with '
'init=False, it cannot be specified with '
'replace()')
continue
if f.name not in changes:
changes[f.name] = getattr(obj, f.name)
# Create the new object, which calls __init__() and
# __post_init__() (if defined), using all of the init fields
# we've added and/or left in 'changes'. If there are values
# supplied in changes that aren't fields, this will correctly
# raise a TypeError.
return obj.__class__(**changes)
|