efro.dataclassio

Functionality for importing, exporting, and validating dataclasses.

This allows complex nested dataclasses to be flattened to json-compatible data and restored from said data. It also gracefully handles and preserves unrecognized attribute data, allowing older clients to interact with newer data formats in a nondestructive manner.

 1# Released under the MIT License. See LICENSE for details.
 2#
 3"""Functionality for importing, exporting, and validating dataclasses.
 4
 5This allows complex nested dataclasses to be flattened to json-compatible
 6data and restored from said data. It also gracefully handles and preserves
 7unrecognized attribute data, allowing older clients to interact with newer
 8data formats in a nondestructive manner.
 9"""
10
11from __future__ import annotations
12
13from efro.util import set_canonical_module_names
14from efro.dataclassio._base import (
15    Codec,
16    IOAttrs,
17    IOExtendedData,
18    IOMultiType,
19    EXTRA_ATTRS_ATTR,
20)
21from efro.dataclassio._prep import (
22    ioprep,
23    ioprepped,
24    will_ioprep,
25    is_ioprepped_dataclass,
26)
27from efro.dataclassio._pathcapture import DataclassFieldLookup
28from efro.dataclassio._api import (
29    JsonStyle,
30    dataclass_to_dict,
31    dataclass_to_json,
32    dataclass_from_dict,
33    dataclass_from_json,
34    dataclass_validate,
35    dataclass_hash,
36)
37
38__all__ = [
39    'Codec',
40    'DataclassFieldLookup',
41    'EXTRA_ATTRS_ATTR',
42    'IOAttrs',
43    'IOExtendedData',
44    'IOMultiType',
45    'JsonStyle',
46    'dataclass_from_dict',
47    'dataclass_from_json',
48    'dataclass_to_dict',
49    'dataclass_to_json',
50    'dataclass_validate',
51    'dataclass_hash',
52    'ioprep',
53    'ioprepped',
54    'is_ioprepped_dataclass',
55    'will_ioprep',
56]
57
58# Have these things present themselves cleanly as 'thismodule.SomeClass'
59# instead of 'thismodule._internalmodule.SomeClass'
60set_canonical_module_names(globals())
class Codec(enum.Enum):
29class Codec(Enum):
30    """Specifies expected data format exported to or imported from."""
31
32    # Use only types that will translate cleanly to/from json: lists,
33    # dicts with str keys, bools, ints, floats, and None.
34    JSON = 'json'
35
36    # Mostly like JSON but passes bytes and datetime objects through
37    # as-is instead of converting them to json-friendly types.
38    FIRESTORE = 'firestore'

Specifies expected data format exported to or imported from.

JSON = <Codec.JSON: 'json'>
FIRESTORE = <Codec.FIRESTORE: 'firestore'>
Inherited Members
enum.Enum
name
value
class DataclassFieldLookup(typing.Generic[~T]):
 61class DataclassFieldLookup(Generic[T]):
 62    """Get info about nested dataclass fields in type-safe way."""
 63
 64    def __init__(self, cls: type[T]) -> None:
 65        self.cls = cls
 66
 67    def path(self, callback: Callable[[T], Any]) -> str:
 68        """Look up a path on child dataclass fields.
 69
 70        example:
 71          DataclassFieldLookup(MyType).path(lambda obj: obj.foo.bar)
 72
 73        The above example will return the string 'foo.bar' or something
 74        like 'f.b' if the dataclasses have custom storage names set.
 75        It will also be static-type-checked, triggering an error if
 76        MyType.foo.bar is not a valid path. Note, however, that the
 77        callback technically allows any return value but only nested
 78        dataclasses and their fields will succeed.
 79        """
 80
 81        # We tell the type system that we are returning an instance
 82        # of our class, which allows it to perform type checking on
 83        # member lookups. In reality, however, we are providing a
 84        # special object which captures path lookups, so we can build
 85        # a string from them.
 86        if not TYPE_CHECKING:
 87            out = callback(_PathCapture(self.cls))
 88            if not isinstance(out, _PathCapture):
 89                raise TypeError(
 90                    f'Expected a valid path under'
 91                    f' the provided object; got a {type(out)}.'
 92                )
 93            return out.path
 94        return ''
 95
 96    def paths(self, callback: Callable[[T], list[Any]]) -> list[str]:
 97        """Look up multiple paths on child dataclass fields.
 98
 99        Functionality is identical to path() but for multiple paths at once.
100
101        example:
102          DataclassFieldLookup(MyType).paths(lambda obj: [obj.foo, obj.bar])
103        """
104        outvals: list[str] = []
105        if not TYPE_CHECKING:
106            outs = callback(_PathCapture(self.cls))
107            assert isinstance(outs, list)
108            for out in outs:
109                if not isinstance(out, _PathCapture):
110                    raise TypeError(
111                        f'Expected a valid path under'
112                        f' the provided object; got a {type(out)}.'
113                    )
114                outvals.append(out.path)
115        return outvals

Get info about nested dataclass fields in type-safe way.

DataclassFieldLookup(cls: type[~T])
64    def __init__(self, cls: type[T]) -> None:
65        self.cls = cls
cls
def path(self, callback: Callable[[~T], Any]) -> str:
67    def path(self, callback: Callable[[T], Any]) -> str:
68        """Look up a path on child dataclass fields.
69
70        example:
71          DataclassFieldLookup(MyType).path(lambda obj: obj.foo.bar)
72
73        The above example will return the string 'foo.bar' or something
74        like 'f.b' if the dataclasses have custom storage names set.
75        It will also be static-type-checked, triggering an error if
76        MyType.foo.bar is not a valid path. Note, however, that the
77        callback technically allows any return value but only nested
78        dataclasses and their fields will succeed.
79        """
80
81        # We tell the type system that we are returning an instance
82        # of our class, which allows it to perform type checking on
83        # member lookups. In reality, however, we are providing a
84        # special object which captures path lookups, so we can build
85        # a string from them.
86        if not TYPE_CHECKING:
87            out = callback(_PathCapture(self.cls))
88            if not isinstance(out, _PathCapture):
89                raise TypeError(
90                    f'Expected a valid path under'
91                    f' the provided object; got a {type(out)}.'
92                )
93            return out.path
94        return ''

Look up a path on child dataclass fields.

example: DataclassFieldLookup(MyType).path(lambda obj: obj.foo.bar)

The above example will return the string 'foo.bar' or something like 'f.b' if the dataclasses have custom storage names set. It will also be static-type-checked, triggering an error if MyType.foo.bar is not a valid path. Note, however, that the callback technically allows any return value but only nested dataclasses and their fields will succeed.

def paths(self, callback: Callable[[~T], list[Any]]) -> list[str]:
 96    def paths(self, callback: Callable[[T], list[Any]]) -> list[str]:
 97        """Look up multiple paths on child dataclass fields.
 98
 99        Functionality is identical to path() but for multiple paths at once.
100
101        example:
102          DataclassFieldLookup(MyType).paths(lambda obj: [obj.foo, obj.bar])
103        """
104        outvals: list[str] = []
105        if not TYPE_CHECKING:
106            outs = callback(_PathCapture(self.cls))
107            assert isinstance(outs, list)
108            for out in outs:
109                if not isinstance(out, _PathCapture):
110                    raise TypeError(
111                        f'Expected a valid path under'
112                        f' the provided object; got a {type(out)}.'
113                    )
114                outvals.append(out.path)
115        return outvals

Look up multiple paths on child dataclass fields.

Functionality is identical to path() but for multiple paths at once.

example: DataclassFieldLookup(MyType).paths(lambda obj: [obj.foo, obj.bar])

EXTRA_ATTRS_ATTR = '_DCIOEXATTRS'
class IOAttrs:
138class IOAttrs:
139    """For specifying io behavior in annotations.
140
141    'storagename', if passed, is the name used when storing to json/etc.
142    'store_default' can be set to False to avoid writing values when equal
143        to the default value. Note that this requires the dataclass field
144        to define a default or default_factory or for its IOAttrs to
145        define a soft_default value.
146    'whole_days', if True, requires datetime values to be exactly on day
147        boundaries (see efro.util.utc_today()).
148    'whole_hours', if True, requires datetime values to lie exactly on hour
149        boundaries (see efro.util.utc_this_hour()).
150    'whole_minutes', if True, requires datetime values to lie exactly on minute
151        boundaries (see efro.util.utc_this_minute()).
152    'soft_default', if passed, injects a default value into dataclass
153        instantiation when the field is not present in the input data.
154        This allows dataclasses to add new non-optional fields while
155        gracefully 'upgrading' old data. Note that when a soft_default is
156        present it will take precedence over field defaults when determining
157        whether to store a value for a field with store_default=False
158        (since the soft_default value is what we'll get when reading that
159        same data back in when the field is omitted).
160    'soft_default_factory' is similar to 'default_factory' in dataclass
161        fields; it should be used instead of 'soft_default' for mutable types
162        such as lists to prevent a single default object from unintentionally
163        changing over time.
164    """
165
166    # A sentinel object to detect if a parameter is supplied or not.  Use
167    # a class to give it a better repr.
168    class _MissingType:
169        pass
170
171    MISSING = _MissingType()
172
173    storagename: str | None = None
174    store_default: bool = True
175    whole_days: bool = False
176    whole_hours: bool = False
177    whole_minutes: bool = False
178    soft_default: Any = MISSING
179    soft_default_factory: Callable[[], Any] | _MissingType = MISSING
180
181    def __init__(
182        self,
183        storagename: str | None = storagename,
184        store_default: bool = store_default,
185        whole_days: bool = whole_days,
186        whole_hours: bool = whole_hours,
187        whole_minutes: bool = whole_minutes,
188        soft_default: Any = MISSING,
189        soft_default_factory: Callable[[], Any] | _MissingType = MISSING,
190    ):
191        # Only store values that differ from class defaults to keep
192        # our instances nice and lean.
193        cls = type(self)
194        if storagename != cls.storagename:
195            self.storagename = storagename
196        if store_default != cls.store_default:
197            self.store_default = store_default
198        if whole_days != cls.whole_days:
199            self.whole_days = whole_days
200        if whole_hours != cls.whole_hours:
201            self.whole_hours = whole_hours
202        if whole_minutes != cls.whole_minutes:
203            self.whole_minutes = whole_minutes
204        if soft_default is not cls.soft_default:
205            # Do what dataclasses does with its default types and
206            # tell the user to use factory for mutable ones.
207            if isinstance(soft_default, (list, dict, set)):
208                raise ValueError(
209                    f'mutable {type(soft_default)} is not allowed'
210                    f' for soft_default; use soft_default_factory.'
211                )
212            self.soft_default = soft_default
213        if soft_default_factory is not cls.soft_default_factory:
214            self.soft_default_factory = soft_default_factory
215            if self.soft_default is not cls.soft_default:
216                raise ValueError(
217                    'Cannot set both soft_default and soft_default_factory'
218                )
219
220    def validate_for_field(self, cls: type, field: dataclasses.Field) -> None:
221        """Ensure the IOAttrs instance is ok to use with the provided field."""
222
223        # Turning off store_default requires the field to have either
224        # a default or a default_factory or for us to have soft equivalents.
225
226        if not self.store_default:
227            field_default_factory: Any = field.default_factory
228            if (
229                field_default_factory is dataclasses.MISSING
230                and field.default is dataclasses.MISSING
231                and self.soft_default is self.MISSING
232                and self.soft_default_factory is self.MISSING
233            ):
234                raise TypeError(
235                    f'Field {field.name} of {cls} has'
236                    f' neither a default nor a default_factory'
237                    f' and IOAttrs contains neither a soft_default'
238                    f' nor a soft_default_factory;'
239                    f' store_default=False cannot be set for it.'
240                )
241
242    def validate_datetime(
243        self, value: datetime.datetime, fieldpath: str
244    ) -> None:
245        """Ensure a datetime value meets our value requirements."""
246        if self.whole_days:
247            if any(
248                x != 0
249                for x in (
250                    value.hour,
251                    value.minute,
252                    value.second,
253                    value.microsecond,
254                )
255            ):
256                raise ValueError(
257                    f'Value {value} at {fieldpath} is not a whole day.'
258                )
259        elif self.whole_hours:
260            if any(
261                x != 0 for x in (value.minute, value.second, value.microsecond)
262            ):
263                raise ValueError(
264                    f'Value {value} at {fieldpath}' f' is not a whole hour.'
265                )
266        elif self.whole_minutes:
267            if any(x != 0 for x in (value.second, value.microsecond)):
268                raise ValueError(
269                    f'Value {value} at {fieldpath}' f' is not a whole minute.'
270                )

For specifying io behavior in annotations.

'storagename', if passed, is the name used when storing to json/etc. 'store_default' can be set to False to avoid writing values when equal to the default value. Note that this requires the dataclass field to define a default or default_factory or for its IOAttrs to define a soft_default value. 'whole_days', if True, requires datetime values to be exactly on day boundaries (see efro.util.utc_today()). 'whole_hours', if True, requires datetime values to lie exactly on hour boundaries (see efro.util.utc_this_hour()). 'whole_minutes', if True, requires datetime values to lie exactly on minute boundaries (see efro.util.utc_this_minute()). 'soft_default', if passed, injects a default value into dataclass instantiation when the field is not present in the input data. This allows dataclasses to add new non-optional fields while gracefully 'upgrading' old data. Note that when a soft_default is present it will take precedence over field defaults when determining whether to store a value for a field with store_default=False (since the soft_default value is what we'll get when reading that same data back in when the field is omitted). 'soft_default_factory' is similar to 'default_factory' in dataclass fields; it should be used instead of 'soft_default' for mutable types such as lists to prevent a single default object from unintentionally changing over time.

IOAttrs( storagename: str | None = None, store_default: bool = True, whole_days: bool = False, whole_hours: bool = False, whole_minutes: bool = False, soft_default: Any = <efro.dataclassio._base.IOAttrs._MissingType object>, soft_default_factory: Union[Callable[[], Any], efro.dataclassio._base.IOAttrs._MissingType] = <efro.dataclassio._base.IOAttrs._MissingType object>)
181    def __init__(
182        self,
183        storagename: str | None = storagename,
184        store_default: bool = store_default,
185        whole_days: bool = whole_days,
186        whole_hours: bool = whole_hours,
187        whole_minutes: bool = whole_minutes,
188        soft_default: Any = MISSING,
189        soft_default_factory: Callable[[], Any] | _MissingType = MISSING,
190    ):
191        # Only store values that differ from class defaults to keep
192        # our instances nice and lean.
193        cls = type(self)
194        if storagename != cls.storagename:
195            self.storagename = storagename
196        if store_default != cls.store_default:
197            self.store_default = store_default
198        if whole_days != cls.whole_days:
199            self.whole_days = whole_days
200        if whole_hours != cls.whole_hours:
201            self.whole_hours = whole_hours
202        if whole_minutes != cls.whole_minutes:
203            self.whole_minutes = whole_minutes
204        if soft_default is not cls.soft_default:
205            # Do what dataclasses does with its default types and
206            # tell the user to use factory for mutable ones.
207            if isinstance(soft_default, (list, dict, set)):
208                raise ValueError(
209                    f'mutable {type(soft_default)} is not allowed'
210                    f' for soft_default; use soft_default_factory.'
211                )
212            self.soft_default = soft_default
213        if soft_default_factory is not cls.soft_default_factory:
214            self.soft_default_factory = soft_default_factory
215            if self.soft_default is not cls.soft_default:
216                raise ValueError(
217                    'Cannot set both soft_default and soft_default_factory'
218                )
MISSING = <efro.dataclassio._base.IOAttrs._MissingType object>
storagename: str | None = None
store_default: bool = True
whole_days: bool = False
whole_hours: bool = False
whole_minutes: bool = False
soft_default: Any = <efro.dataclassio._base.IOAttrs._MissingType object>
soft_default_factory: Union[Callable[[], Any], efro.dataclassio._base.IOAttrs._MissingType] = <efro.dataclassio._base.IOAttrs._MissingType object>
def validate_for_field(self, cls: type, field: dataclasses.Field) -> None:
220    def validate_for_field(self, cls: type, field: dataclasses.Field) -> None:
221        """Ensure the IOAttrs instance is ok to use with the provided field."""
222
223        # Turning off store_default requires the field to have either
224        # a default or a default_factory or for us to have soft equivalents.
225
226        if not self.store_default:
227            field_default_factory: Any = field.default_factory
228            if (
229                field_default_factory is dataclasses.MISSING
230                and field.default is dataclasses.MISSING
231                and self.soft_default is self.MISSING
232                and self.soft_default_factory is self.MISSING
233            ):
234                raise TypeError(
235                    f'Field {field.name} of {cls} has'
236                    f' neither a default nor a default_factory'
237                    f' and IOAttrs contains neither a soft_default'
238                    f' nor a soft_default_factory;'
239                    f' store_default=False cannot be set for it.'
240                )

Ensure the IOAttrs instance is ok to use with the provided field.

def validate_datetime(self, value: datetime.datetime, fieldpath: str) -> None:
242    def validate_datetime(
243        self, value: datetime.datetime, fieldpath: str
244    ) -> None:
245        """Ensure a datetime value meets our value requirements."""
246        if self.whole_days:
247            if any(
248                x != 0
249                for x in (
250                    value.hour,
251                    value.minute,
252                    value.second,
253                    value.microsecond,
254                )
255            ):
256                raise ValueError(
257                    f'Value {value} at {fieldpath} is not a whole day.'
258                )
259        elif self.whole_hours:
260            if any(
261                x != 0 for x in (value.minute, value.second, value.microsecond)
262            ):
263                raise ValueError(
264                    f'Value {value} at {fieldpath}' f' is not a whole hour.'
265                )
266        elif self.whole_minutes:
267            if any(x != 0 for x in (value.second, value.microsecond)):
268                raise ValueError(
269                    f'Value {value} at {fieldpath}' f' is not a whole minute.'
270                )

Ensure a datetime value meets our value requirements.

class IOExtendedData:
41class IOExtendedData:
42    """A class that data types can inherit from for extra functionality."""
43
44    def will_output(self) -> None:
45        """Called before data is sent to an outputter.
46
47        Can be overridden to validate or filter data before
48        sending it on its way.
49        """
50
51    @classmethod
52    def will_input(cls, data: dict) -> None:
53        """Called on raw data before a class instance is created from it.
54
55        Can be overridden to migrate old data formats to new, etc.
56        """
57
58    def did_input(self) -> None:
59        """Called on a class instance after created from data.
60
61        Can be useful to correct values from the db, etc. in the
62        type-safe form.
63        """
64
65    # pylint: disable=useless-return
66
67    @classmethod
68    def handle_input_error(cls, exc: Exception) -> Self | None:
69        """Called when an error occurs during input decoding.
70
71        This allows a type to optionally return substitute data
72        to be used in place of the failed decode. If it returns
73        None, the original exception is re-raised.
74
75        It is generally a bad idea to apply catch-alls such as this,
76        as it can lead to silent data loss. This should only be used
77        in specific cases such as user settings where an occasional
78        reset is harmless and is preferable to keeping all contained
79        enums and other values backward compatible indefinitely.
80        """
81        del exc  # Unused.
82
83        # By default we let things fail.
84        return None
85
86    # pylint: enable=useless-return

A class that data types can inherit from for extra functionality.

def will_output(self) -> None:
44    def will_output(self) -> None:
45        """Called before data is sent to an outputter.
46
47        Can be overridden to validate or filter data before
48        sending it on its way.
49        """

Called before data is sent to an outputter.

Can be overridden to validate or filter data before sending it on its way.

@classmethod
def will_input(cls, data: dict) -> None:
51    @classmethod
52    def will_input(cls, data: dict) -> None:
53        """Called on raw data before a class instance is created from it.
54
55        Can be overridden to migrate old data formats to new, etc.
56        """

Called on raw data before a class instance is created from it.

Can be overridden to migrate old data formats to new, etc.

def did_input(self) -> None:
58    def did_input(self) -> None:
59        """Called on a class instance after created from data.
60
61        Can be useful to correct values from the db, etc. in the
62        type-safe form.
63        """

Called on a class instance after created from data.

Can be useful to correct values from the db, etc. in the type-safe form.

@classmethod
def handle_input_error(cls, exc: Exception) -> Optional[Self]:
67    @classmethod
68    def handle_input_error(cls, exc: Exception) -> Self | None:
69        """Called when an error occurs during input decoding.
70
71        This allows a type to optionally return substitute data
72        to be used in place of the failed decode. If it returns
73        None, the original exception is re-raised.
74
75        It is generally a bad idea to apply catch-alls such as this,
76        as it can lead to silent data loss. This should only be used
77        in specific cases such as user settings where an occasional
78        reset is harmless and is preferable to keeping all contained
79        enums and other values backward compatible indefinitely.
80        """
81        del exc  # Unused.
82
83        # By default we let things fail.
84        return None

Called when an error occurs during input decoding.

This allows a type to optionally return substitute data to be used in place of the failed decode. If it returns None, the original exception is re-raised.

It is generally a bad idea to apply catch-alls such as this, as it can lead to silent data loss. This should only be used in specific cases such as user settings where an occasional reset is harmless and is preferable to keeping all contained enums and other values backward compatible indefinitely.

class IOMultiType(typing.Generic[~EnumT]):
 92class IOMultiType(Generic[EnumT]):
 93    """A base class for types that can map to multiple dataclass types.
 94
 95    This enables usage of high level base classes (for example
 96    a 'Message' type) in annotations, with dataclassio automatically
 97    serializing & deserializing dataclass subclasses based on their
 98    type ('MessagePing', 'MessageChat', etc.)
 99
100    Standard usage involves creating a class which inherits from this
101    one which acts as a 'registry', and then creating dataclass classes
102    inheriting from that registry class. Dataclassio will then do the
103    right thing when that registry class is used in type annotations.
104
105    See tests/test_efro/test_dataclassio.py for examples.
106    """
107
108    @classmethod
109    def get_type(cls, type_id: EnumT) -> type[Self]:
110        """Return a specific subclass given a type-id."""
111        raise NotImplementedError()
112
113    @classmethod
114    def get_type_id(cls) -> EnumT:
115        """Return the type-id for this subclass."""
116        raise NotImplementedError()
117
118    @classmethod
119    def get_type_id_type(cls) -> type[EnumT]:
120        """Return the Enum type this class uses as its type-id."""
121        out: type[EnumT] = cls.__orig_bases__[0].__args__[0]  # type: ignore
122        assert issubclass(out, Enum)
123        return out
124
125    @classmethod
126    def get_type_id_storage_name(cls) -> str:
127        """Return the key used to store type id in serialized data.
128
129        The default is an obscure value so that it does not conflict
130        with members of individual type attrs, but in some cases one
131        might prefer to serialize it to something simpler like 'type'
132        by overriding this call. One just needs to make sure that no
133        encompassed types serialize anything to 'type' themself.
134        """
135        return '_dciotype'

A base class for types that can map to multiple dataclass types.

This enables usage of high level base classes (for example a 'Message' type) in annotations, with dataclassio automatically serializing & deserializing dataclass subclasses based on their type ('MessagePing', 'MessageChat', etc.)

Standard usage involves creating a class which inherits from this one which acts as a 'registry', and then creating dataclass classes inheriting from that registry class. Dataclassio will then do the right thing when that registry class is used in type annotations.

See tests/test_efro/test_dataclassio.py for examples.

@classmethod
def get_type(cls, type_id: ~EnumT) -> type[typing.Self]:
108    @classmethod
109    def get_type(cls, type_id: EnumT) -> type[Self]:
110        """Return a specific subclass given a type-id."""
111        raise NotImplementedError()

Return a specific subclass given a type-id.

@classmethod
def get_type_id(cls) -> ~EnumT:
113    @classmethod
114    def get_type_id(cls) -> EnumT:
115        """Return the type-id for this subclass."""
116        raise NotImplementedError()

Return the type-id for this subclass.

@classmethod
def get_type_id_type(cls) -> type[~EnumT]:
118    @classmethod
119    def get_type_id_type(cls) -> type[EnumT]:
120        """Return the Enum type this class uses as its type-id."""
121        out: type[EnumT] = cls.__orig_bases__[0].__args__[0]  # type: ignore
122        assert issubclass(out, Enum)
123        return out

Return the Enum type this class uses as its type-id.

@classmethod
def get_type_id_storage_name(cls) -> str:
125    @classmethod
126    def get_type_id_storage_name(cls) -> str:
127        """Return the key used to store type id in serialized data.
128
129        The default is an obscure value so that it does not conflict
130        with members of individual type attrs, but in some cases one
131        might prefer to serialize it to something simpler like 'type'
132        by overriding this call. One just needs to make sure that no
133        encompassed types serialize anything to 'type' themself.
134        """
135        return '_dciotype'

Return the key used to store type id in serialized data.

The default is an obscure value so that it does not conflict with members of individual type attrs, but in some cases one might prefer to serialize it to something simpler like 'type' by overriding this call. One just needs to make sure that no encompassed types serialize anything to 'type' themself.

class JsonStyle(enum.Enum):
28class JsonStyle(Enum):
29    """Different style types for json."""
30
31    # Single line, no spaces, no sorting. Not deterministic.
32    # Use this where speed is more important than determinism.
33    FAST = 'fast'
34
35    # Single line, no spaces, sorted keys. Deterministic.
36    # Use this when output may be hashed or compared for equality.
37    SORTED = 'sorted'
38
39    # Multiple lines, spaces, sorted keys. Deterministic.
40    # Use this for pretty human readable output.
41    PRETTY = 'pretty'

Different style types for json.

FAST = <JsonStyle.FAST: 'fast'>
SORTED = <JsonStyle.SORTED: 'sorted'>
PRETTY = <JsonStyle.PRETTY: 'pretty'>
Inherited Members
enum.Enum
name
value
def dataclass_from_dict( cls: type[~T], values: dict, codec: Codec = <Codec.JSON: 'json'>, coerce_to_float: bool = True, allow_unknown_attrs: bool = True, discard_unknown_attrs: bool = False) -> ~T:
100def dataclass_from_dict(
101    cls: type[T],
102    values: dict,
103    codec: Codec = Codec.JSON,
104    coerce_to_float: bool = True,
105    allow_unknown_attrs: bool = True,
106    discard_unknown_attrs: bool = False,
107) -> T:
108    """Given a dict, return a dataclass of a given type.
109
110    The dict must be formatted to match the specified codec (generally
111    json-friendly object types). This means that sequence values such as
112    tuples or sets should be passed as lists, enums should be passed as
113    their associated values, nested dataclasses should be passed as dicts,
114    etc.
115
116    All values are checked to ensure their types/values are valid.
117
118    Data for attributes of type Any will be checked to ensure they match
119    types supported directly by json. This does not include types such
120    as tuples which are implicitly translated by Python's json module
121    (as this would break the ability to do a lossless round-trip with
122    data).
123
124    If coerce_to_float is True, int values passed for float typed fields
125    will be converted to float values. Otherwise, a TypeError is raised.
126
127    If `allow_unknown_attrs` is False, AttributeErrors will be raised for
128    attributes present in the dict but not on the data class. Otherwise,
129    they will be preserved as part of the instance and included if it is
130    exported back to a dict, unless `discard_unknown_attrs` is True, in
131    which case they will simply be discarded.
132    """
133    val = _Inputter(
134        cls,
135        codec=codec,
136        coerce_to_float=coerce_to_float,
137        allow_unknown_attrs=allow_unknown_attrs,
138        discard_unknown_attrs=discard_unknown_attrs,
139    ).run(values)
140    assert isinstance(val, cls)
141    return val

Given a dict, return a dataclass of a given type.

The dict must be formatted to match the specified codec (generally json-friendly object types). This means that sequence values such as tuples or sets should be passed as lists, enums should be passed as their associated values, nested dataclasses should be passed as dicts, etc.

All values are checked to ensure their types/values are valid.

Data for attributes of type Any will be checked to ensure they match types supported directly by json. This does not include types such as tuples which are implicitly translated by Python's json module (as this would break the ability to do a lossless round-trip with data).

If coerce_to_float is True, int values passed for float typed fields will be converted to float values. Otherwise, a TypeError is raised.

If allow_unknown_attrs is False, AttributeErrors will be raised for attributes present in the dict but not on the data class. Otherwise, they will be preserved as part of the instance and included if it is exported back to a dict, unless discard_unknown_attrs is True, in which case they will simply be discarded.

def dataclass_from_json( cls: type[~T], json_str: str, coerce_to_float: bool = True, allow_unknown_attrs: bool = True, discard_unknown_attrs: bool = False) -> ~T:
144def dataclass_from_json(
145    cls: type[T],
146    json_str: str,
147    coerce_to_float: bool = True,
148    allow_unknown_attrs: bool = True,
149    discard_unknown_attrs: bool = False,
150) -> T:
151    """Return a dataclass instance given a json string.
152
153    Basically dataclass_from_dict(json.loads(...))
154    """
155
156    return dataclass_from_dict(
157        cls=cls,
158        values=json.loads(json_str),
159        coerce_to_float=coerce_to_float,
160        allow_unknown_attrs=allow_unknown_attrs,
161        discard_unknown_attrs=discard_unknown_attrs,
162    )

Return a dataclass instance given a json string.

Basically dataclass_from_dict(json.loads(...))

def dataclass_to_dict( obj: Any, codec: Codec = <Codec.JSON: 'json'>, coerce_to_float: bool = True, discard_extra_attrs: bool = False) -> dict:
44def dataclass_to_dict(
45    obj: Any,
46    codec: Codec = Codec.JSON,
47    coerce_to_float: bool = True,
48    discard_extra_attrs: bool = False,
49) -> dict:
50    """Given a dataclass object, return a json-friendly dict.
51
52    All values will be checked to ensure they match the types specified
53    on fields. Note that a limited set of types and data configurations is
54    supported.
55
56    Values with type Any will be checked to ensure they match types supported
57    directly by json. This does not include types such as tuples which are
58    implicitly translated by Python's json module (as this would break
59    the ability to do a lossless round-trip with data).
60
61    If coerce_to_float is True, integer values present on float typed fields
62    will be converted to float in the dict output. If False, a TypeError
63    will be triggered.
64    """
65
66    out = _Outputter(
67        obj,
68        create=True,
69        codec=codec,
70        coerce_to_float=coerce_to_float,
71        discard_extra_attrs=discard_extra_attrs,
72    ).run()
73    assert isinstance(out, dict)
74    return out

Given a dataclass object, return a json-friendly dict.

All values will be checked to ensure they match the types specified on fields. Note that a limited set of types and data configurations is supported.

Values with type Any will be checked to ensure they match types supported directly by json. This does not include types such as tuples which are implicitly translated by Python's json module (as this would break the ability to do a lossless round-trip with data).

If coerce_to_float is True, integer values present on float typed fields will be converted to float in the dict output. If False, a TypeError will be triggered.

def dataclass_to_json( obj: Any, coerce_to_float: bool = True, pretty: bool = False, sort_keys: bool | None = None) -> str:
77def dataclass_to_json(
78    obj: Any,
79    coerce_to_float: bool = True,
80    pretty: bool = False,
81    sort_keys: bool | None = None,
82) -> str:
83    """Utility function; return a json string from a dataclass instance.
84
85    Basically json.dumps(dataclass_to_dict(...)).
86    By default, keys are sorted for pretty output and not otherwise, but
87    this can be overridden by supplying a value for the 'sort_keys' arg.
88    """
89
90    jdict = dataclass_to_dict(
91        obj=obj, coerce_to_float=coerce_to_float, codec=Codec.JSON
92    )
93    if sort_keys is None:
94        sort_keys = pretty
95    if pretty:
96        return json.dumps(jdict, indent=2, sort_keys=sort_keys)
97    return json.dumps(jdict, separators=(',', ':'), sort_keys=sort_keys)

Utility function; return a json string from a dataclass instance.

Basically json.dumps(dataclass_to_dict(...)). By default, keys are sorted for pretty output and not otherwise, but this can be overridden by supplying a value for the 'sort_keys' arg.

def dataclass_validate( obj: Any, coerce_to_float: bool = True, codec: Codec = <Codec.JSON: 'json'>, discard_extra_attrs: bool = False) -> None:
165def dataclass_validate(
166    obj: Any,
167    coerce_to_float: bool = True,
168    codec: Codec = Codec.JSON,
169    discard_extra_attrs: bool = False,
170) -> None:
171    """Ensure that values in a dataclass instance are the correct types."""
172
173    # Simply run an output pass but tell it not to generate data;
174    # only run validation.
175    _Outputter(
176        obj,
177        create=False,
178        codec=codec,
179        coerce_to_float=coerce_to_float,
180        discard_extra_attrs=discard_extra_attrs,
181    ).run()

Ensure that values in a dataclass instance are the correct types.

def dataclass_hash(obj: Any, coerce_to_float: bool = True) -> str:
184def dataclass_hash(obj: Any, coerce_to_float: bool = True) -> str:
185    """Calculate a hash for the provided dataclass.
186
187    Basically this emits json for the dataclass (with keys sorted
188    to keep things deterministic) and hashes the resulting string.
189    """
190    import hashlib
191    from base64 import urlsafe_b64encode
192
193    json_dict = dataclass_to_dict(
194        obj, codec=Codec.JSON, coerce_to_float=coerce_to_float
195    )
196
197    # Need to sort keys to keep things deterministic.
198    json_str = json.dumps(json_dict, separators=(',', ':'), sort_keys=True)
199
200    sha = hashlib.sha256()
201    sha.update(json_str.encode())
202
203    # Go with urlsafe base64 instead of the usual hex to save some
204    # space, and kill those ugly padding chars at the end.
205    return urlsafe_b64encode(sha.digest()).decode().strip('=')

Calculate a hash for the provided dataclass.

Basically this emits json for the dataclass (with keys sorted to keep things deterministic) and hashes the resulting string.

def ioprep(cls: type, globalns: dict | None = None) -> None:
47def ioprep(cls: type, globalns: dict | None = None) -> None:
48    """Prep a dataclass type for use with this module's functionality.
49
50    Prepping ensures that all types contained in a data class as well as
51    the usage of said types are supported by this module and pre-builds
52    necessary constructs needed for encoding/decoding/etc.
53
54    Prepping will happen on-the-fly as needed, but a warning will be
55    emitted in such cases, as it is better to explicitly prep all used types
56    early in a process to ensure any invalid types or configuration are caught
57    immediately.
58
59    Prepping a dataclass involves evaluating its type annotations, which,
60    as of PEP 563, are stored simply as strings. This evaluation is done
61    with localns set to the class dict (so that types defined in the class
62    can be used) and globalns set to the containing module's class.
63    It is possible to override globalns for special cases such as when
64    prepping happens as part of an execed string instead of within a
65    module.
66    """
67    PrepSession(explicit=True, globalns=globalns).prep_dataclass(
68        cls, recursion_level=0
69    )

Prep a dataclass type for use with this module's functionality.

Prepping ensures that all types contained in a data class as well as the usage of said types are supported by this module and pre-builds necessary constructs needed for encoding/decoding/etc.

Prepping will happen on-the-fly as needed, but a warning will be emitted in such cases, as it is better to explicitly prep all used types early in a process to ensure any invalid types or configuration are caught immediately.

Prepping a dataclass involves evaluating its type annotations, which, as of PEP 563, are stored simply as strings. This evaluation is done with localns set to the class dict (so that types defined in the class can be used) and globalns set to the containing module's class. It is possible to override globalns for special cases such as when prepping happens as part of an execed string instead of within a module.

def ioprepped(cls: type[~T]) -> type[~T]:
72def ioprepped(cls: type[T]) -> type[T]:
73    """Class decorator for easily prepping a dataclass at definition time.
74
75    Note that in some cases it may not be possible to prep a dataclass
76    immediately (such as when its type annotations refer to forward-declared
77    types). In these cases, dataclass_prep() should be explicitly called for
78    the class as soon as possible; ideally at module import time to expose any
79    errors as early as possible in execution.
80    """
81    ioprep(cls)
82    return cls

Class decorator for easily prepping a dataclass at definition time.

Note that in some cases it may not be possible to prep a dataclass immediately (such as when its type annotations refer to forward-declared types). In these cases, dataclass_prep() should be explicitly called for the class as soon as possible; ideally at module import time to expose any errors as early as possible in execution.

def is_ioprepped_dataclass(obj: Any) -> bool:
102def is_ioprepped_dataclass(obj: Any) -> bool:
103    """Return whether the obj is an ioprepped dataclass type or instance."""
104    cls = obj if isinstance(obj, type) else type(obj)
105    return dataclasses.is_dataclass(cls) and hasattr(cls, PREP_ATTR)

Return whether the obj is an ioprepped dataclass type or instance.

def will_ioprep(cls: type[~T]) -> type[~T]:
85def will_ioprep(cls: type[T]) -> type[T]:
86    """Class decorator hinting that we will prep a class later.
87
88    In some cases (such as recursive types) we cannot use the @ioprepped
89    decorator and must instead call ioprep() explicitly later. However,
90    some of our custom pylint checking behaves differently when the
91    @ioprepped decorator is present, in that case requiring type annotations
92    to be present and not simply forward declared under an "if TYPE_CHECKING"
93    block. (since they are used at runtime).
94
95    The @will_ioprep decorator triggers the same pylint behavior
96    differences as @ioprepped (which are necessary for the later ioprep() call
97    to work correctly) but without actually running any prep itself.
98    """
99    return cls

Class decorator hinting that we will prep a class later.

In some cases (such as recursive types) we cannot use the @ioprepped decorator and must instead call ioprep() explicitly later. However, some of our custom pylint checking behaves differently when the @ioprepped decorator is present, in that case requiring type annotations to be present and not simply forward declared under an "if TYPE_CHECKING" block. (since they are used at runtime).

The @will_ioprep decorator triggers the same pylint behavior differences as @ioprepped (which are necessary for the later ioprep() call to work correctly) but without actually running any prep itself.