import collections.abc import copy import datetime import decimal import math import operator import uuid import warnings from base64 import b64decode, b64encode from functools import partialmethod, total_ordering from django import forms from django.apps import apps from django.conf import settings from django.core import checks, exceptions, validators from django.db import connection, connections, router from django.db.models.constants import LOOKUP_SEP from django.db.models.query_utils import DeferredAttribute, RegisterLookupMixin from django.utils import timezone from django.utils.datastructures import DictWrapper from django.utils.dateparse import ( parse_date, parse_datetime, parse_duration, parse_time, ) from django.utils.duration import duration_microseconds, duration_string from django.utils.functional import Promise, cached_property from django.utils.ipv6 import clean_ipv6_address from django.utils.itercompat import is_iterable from django.utils.text import capfirst from django.utils.translation import gettext_lazy as _ __all__ = [ "AutoField", "BLANK_CHOICE_DASH", "BigAutoField", "BigIntegerField", "BinaryField", "BooleanField", "CharField", "CommaSeparatedIntegerField", "DateField", "DateTimeField", "DecimalField", "DurationField", "EmailField", "Empty", "Field", "FilePathField", "FloatField", "GenericIPAddressField", "IPAddressField", "IntegerField", "NOT_PROVIDED", "NullBooleanField", "PositiveBigIntegerField", "PositiveIntegerField", "PositiveSmallIntegerField", "SlugField", "SmallAutoField", "SmallIntegerField", "TextField", "TimeField", "URLField", "UUIDField", ] class Empty: pass class NOT_PROVIDED: pass # The values to use for "blank" in SelectFields. Will be appended to the start # of most "choices" lists. BLANK_CHOICE_DASH = [("", "---------")] def _load_field(app_label, model_name, field_name): return apps.get_model(app_label, model_name)._meta.get_field(field_name) # A guide to Field parameters: # # * name: The name of the field specified in the model. # * attname: The attribute to use on the model object. This is the same as # "name", except in the case of ForeignKeys, where "_id" is # appended. # * db_column: The db_column specified in the model (or None). # * column: The database column for this field. This is the same as # "attname", except if db_column is specified. # # Code that introspects values, or does other dynamic things, should use # attname. For example, this gets the primary key value of object "obj": # # getattr(obj, opts.pk.attname) def _empty(of_cls): new = Empty() new.__class__ = of_cls return new def return_None(): return None @total_ordering class Field(RegisterLookupMixin): """Base class for all field types""" # Designates whether empty strings fundamentally are allowed at the # database level. empty_strings_allowed = True empty_values = list(validators.EMPTY_VALUES) # These track each time a Field instance is created. Used to retain order. # The auto_creation_counter is used for fields that Django implicitly # creates, creation_counter is used for all user-specified fields. creation_counter = 0 auto_creation_counter = -1 default_validators = [] # Default set of validators default_error_messages = { "invalid_choice": _("Value %(value)r is not a valid choice."), "null": _("This field cannot be null."), "blank": _("This field cannot be blank."), "unique": _("%(model_name)s with this %(field_label)s already exists."), # Translators: The 'lookup_type' is one of 'date', 'year' or 'month'. # Eg: "Title must be unique for pub_date year" "unique_for_date": _( "%(field_label)s must be unique for " "%(date_field_label)s %(lookup_type)s." ), } system_check_deprecated_details = None system_check_removed_details = None # Field flags hidden = False many_to_many = None many_to_one = None one_to_many = None one_to_one = None related_model = None descriptor_class = DeferredAttribute # Generic field type description, usually overridden by subclasses def _description(self): return _("Field of type: %(field_type)s") % { "field_type": self.__class__.__name__ } description = property(_description) def __init__( self, verbose_name=None, name=None, primary_key=False, max_length=None, unique=False, blank=False, null=False, db_index=False, rel=None, default=NOT_PROVIDED, editable=True, serialize=True, unique_for_date=None, unique_for_month=None, unique_for_year=None, choices=None, help_text="", db_column=None, db_tablespace=None, auto_created=False, validators=(), error_messages=None, ): self.name = name self.verbose_name = verbose_name # May be set by set_attributes_from_name self._verbose_name = verbose_name # Store original for deconstruction self.primary_key = primary_key self.max_length, self._unique = max_length, unique self.blank, self.null = blank, null self.remote_field = rel self.is_relation = self.remote_field is not None self.default = default self.editable = editable self.serialize = serialize self.unique_for_date = unique_for_date self.unique_for_month = unique_for_month self.unique_for_year = unique_for_year if isinstance(choices, collections.abc.Iterator): choices = list(choices) self.choices = choices self.help_text = help_text self.db_index = db_index self.db_column = db_column self._db_tablespace = db_tablespace self.auto_created = auto_created # Adjust the appropriate creation counter, and save our local copy. if auto_created: self.creation_counter = Field.auto_creation_counter Field.auto_creation_counter -= 1 else: self.creation_counter = Field.creation_counter Field.creation_counter += 1 self._validators = list(validators) # Store for deconstruction later self._error_messages = error_messages # Store for deconstruction later def __str__(self): """ Return "app_label.model_label.field_name" for fields attached to models. """ if not hasattr(self, "model"): return super().__str__() model = self.model return "%s.%s" % (model._meta.label, self.name) def __repr__(self): """Display the module, class, and name of the field.""" path = "%s.%s" % (self.__class__.__module__, self.__class__.__qualname__) name = getattr(self, "name", None) if name is not None: return "<%s: %s>" % (path, name) return "<%s>" % path def check(self, **kwargs): return [ *self._check_field_name(), *self._check_choices(), *self._check_db_index(), *self._check_null_allowed_for_primary_keys(), *self._check_backend_specific_checks(**kwargs), *self._check_validators(), *self._check_deprecation_details(), ] def _check_field_name(self): """ Check if field name is valid, i.e. 1) does not end with an underscore, 2) does not contain "__" and 3) is not "pk". """ if self.name.endswith("_"): return [ checks.Error( "Field names must not end with an underscore.", obj=self, id="fields.E001", ) ] elif LOOKUP_SEP in self.name: return [ checks.Error( 'Field names must not contain "%s".' % LOOKUP_SEP, obj=self, id="fields.E002", ) ] elif self.name == "pk": return [ checks.Error( "'pk' is a reserved word that cannot be used as a field name.", obj=self, id="fields.E003", ) ] else: return [] @classmethod def _choices_is_value(cls, value): return isinstance(value, (str, Promise)) or not is_iterable(value) def _check_choices(self): if not self.choices: return [] if not is_iterable(self.choices) or isinstance(self.choices, str): return [ checks.Error( "'choices' must be an iterable (e.g., a list or tuple).", obj=self, id="fields.E004", ) ] choice_max_length = 0 # Expect [group_name, [value, display]] for choices_group in self.choices: try: group_name, group_choices = choices_group except (TypeError, ValueError): # Containing non-pairs break try: if not all( self._choices_is_value(value) and self._choices_is_value(human_name) for value, human_name in group_choices ): break if self.max_length is not None and group_choices: choice_max_length = max( [ choice_max_length, *( len(value) for value, _ in group_choices if isinstance(value, str) ), ] ) except (TypeError, ValueError): # No groups, choices in the form [value, display] value, human_name = group_name, group_choices if not self._choices_is_value(value) or not self._choices_is_value( human_name ): break if self.max_length is not None and isinstance(value, str): choice_max_length = max(choice_max_length, len(value)) # Special case: choices=['ab'] if isinstance(choices_group, str): break else: if self.max_length is not None and choice_max_length > self.max_length: return [ checks.Error( "'max_length' is too small to fit the longest value " "in 'choices' (%d characters)." % choice_max_length, obj=self, id="fields.E009", ), ] return [] return [ checks.Error( "'choices' must be an iterable containing " "(actual value, human readable name) tuples.", obj=self, id="fields.E005", ) ] def _check_db_index(self): if self.db_index not in (None, True, False): return [ checks.Error( "'db_index' must be None, True or False.", obj=self, id="fields.E006", ) ] else: return [] def _check_null_allowed_for_primary_keys(self): if ( self.primary_key and self.null and not connection.features.interprets_empty_strings_as_nulls ): # We cannot reliably check this for backends like Oracle which # consider NULL and '' to be equal (and thus set up # character-based fields a little differently). return [ checks.Error( "Primary keys must not have null=True.", hint=( "Set null=False on the field, or " "remove primary_key=True argument." ), obj=self, id="fields.E007", ) ] else: return [] def _check_backend_specific_checks(self, databases=None, **kwargs): if databases is None: return [] app_label = self.model._meta.app_label errors = [] for alias in databases: if router.allow_migrate( alias, app_label, model_name=self.model._meta.model_name ): errors.extend(connections[alias].validation.check_field(self, **kwargs)) return errors def _check_validators(self): errors = [] for i, validator in enumerate(self.validators): if not callable(validator): errors.append( checks.Error( "All 'validators' must be callable.", hint=( "validators[{i}] ({repr}) isn't a function or " "instance of a validator class.".format( i=i, repr=repr(validator), ) ), obj=self, id="fields.E008", ) ) return errors def _check_deprecation_details(self): if self.system_check_removed_details is not None: return [ checks.Error( self.system_check_removed_details.get( "msg", "%s has been removed except for support in historical " "migrations." % self.__class__.__name__, ), hint=self.system_check_removed_details.get("hint"), obj=self, id=self.system_check_removed_details.get("id", "fields.EXXX"), ) ] elif self.system_check_deprecated_details is not None: return [ checks.Warning( self.system_check_deprecated_details.get( "msg", "%s has been deprecated." % self.__class__.__name__ ), hint=self.system_check_deprecated_details.get("hint"), obj=self, id=self.system_check_deprecated_details.get("id", "fields.WXXX"), ) ] return [] def get_col(self, alias, output_field=None): if alias == self.model._meta.db_table and ( output_field is None or output_field == self ): return self.cached_col from django.db.models.expressions import Col return Col(alias, self, output_field) @cached_property def cached_col(self): from django.db.models.expressions import Col return Col(self.model._meta.db_table, self) def select_format(self, compiler, sql, params): """ Custom format for select clauses. For example, GIS columns need to be selected as AsText(table.col) on MySQL as the table.col data can't be used by Django. """ return sql, params def deconstruct(self): """ Return enough information to recreate the field as a 4-tuple: * The name of the field on the model, if contribute_to_class() has been run. * The import path of the field, including the class, e.g. django.db.models.IntegerField. This should be the most portable version, so less specific may be better. * A list of positional arguments. * A dict of keyword arguments. Note that the positional or keyword arguments must contain values of the following types (including inner values of collection types): * None, bool, str, int, float, complex, set, frozenset, list, tuple, dict * UUID * datetime.datetime (naive), datetime.date * top-level classes, top-level functions - will be referenced by their full import path * Storage instances - these have their own deconstruct() method This is because the values here must be serialized into a text format (possibly new Python code, possibly JSON) and these are the only types with encoding handlers defined. There's no need to return the exact way the field was instantiated this time, just ensure that the resulting field is the same - prefer keyword arguments over positional ones, and omit parameters with their default values. """ # Short-form way of fetching all the default parameters keywords = {} possibles = { "verbose_name": None, "primary_key": False, "max_length": None, "unique": False, "blank": False, "null": False, "db_index": False, "default": NOT_PROVIDED, "editable": True, "serialize": True, "unique_for_date": None, "unique_for_month": None, "unique_for_year": None, "choices": None, "help_text": "", "db_column": None, "db_tablespace": None, "auto_created": False, "validators": [], "error_messages": None, } attr_overrides = { "unique": "_unique", "error_messages": "_error_messages", "validators": "_validators", "verbose_name": "_verbose_name", "db_tablespace": "_db_tablespace", } equals_comparison = {"choices", "validators"} for name, default in possibles.items(): value = getattr(self, attr_overrides.get(name, name)) # Unroll anything iterable for choices into a concrete list if name == "choices" and isinstance(value, collections.abc.Iterable): value = list(value) # Do correct kind of comparison if name in equals_comparison: if value != default: keywords[name] = value else: if value is not default: keywords[name] = value # Work out path - we shorten it for known Django core fields path = "%s.%s" % (self.__class__.__module__, self.__class__.__qualname__) if path.startswith("django.db.models.fields.related"): path = path.replace("django.db.models.fields.related", "django.db.models") elif path.startswith("django.db.models.fields.files"): path = path.replace("django.db.models.fields.files", "django.db.models") elif path.startswith("django.db.models.fields.json"): path = path.replace("django.db.models.fields.json", "django.db.models") elif path.startswith("django.db.models.fields.proxy"): path = path.replace("django.db.models.fields.proxy", "django.db.models") elif path.startswith("django.db.models.fields"): path = path.replace("django.db.models.fields", "django.db.models") # Return basic info - other fields should override this. return (self.name, path, [], keywords) def clone(self): """ Uses deconstruct() to clone a new copy of this Field. Will not preserve any class attachments/attribute names. """ name, path, args, kwargs = self.deconstruct() return self.__class__(*args, **kwargs) def __eq__(self, other): # Needed for @total_ordering if isinstance(other, Field): return self.creation_counter == other.creation_counter and getattr( self, "model", None ) == getattr(other, "model", None) return NotImplemented def __lt__(self, other): # This is needed because bisect does not take a comparison function. # Order by creation_counter first for backward compatibility. if isinstance(other, Field): if ( self.creation_counter != other.creation_counter or not hasattr(self, "model") and not hasattr(other, "model") ): return self.creation_counter < other.creation_counter elif hasattr(self, "model") != hasattr(other, "model"): return not hasattr(self, "model") # Order no-model fields first else: # creation_counter's are equal, compare only models. return (self.model._meta.app_label, self.model._meta.model_name) < ( other.model._meta.app_label, other.model._meta.model_name, ) return NotImplemented def __hash__(self): return hash(self.creation_counter) def __deepcopy__(self, memodict): # We don't have to deepcopy very much here, since most things are not # intended to be altered after initial creation. obj = copy.copy(self) if self.remote_field: obj.remote_field = copy.copy(self.remote_field) if hasattr(self.remote_field, "field") and self.remote_field.field is self: obj.remote_field.field = obj memodict[id(self)] = obj return obj def __copy__(self): # We need to avoid hitting __reduce__, so define this # slightly weird copy construct. obj = Empty() obj.__class__ = self.__class__ obj.__dict__ = self.__dict__.copy() return obj def __reduce__(self): """ Pickling should return the model._meta.fields instance of the field, not a new copy of that field. So, use the app registry to load the model and then the field back. """ if not hasattr(self, "model"): # Fields are sometimes used without attaching them to models (for # example in aggregation). In this case give back a plain field # instance. The code below will create a new empty instance of # class self.__class__, then update its dict with self.__dict__ # values - so, this is very close to normal pickle. state = self.__dict__.copy() # The _get_default cached_property can't be pickled due to lambda # usage. state.pop("_get_default", None) return _empty, (self.__class__,), state return _load_field, ( self.model._meta.app_label, self.model._meta.object_name, self.name, ) def get_pk_value_on_save(self, instance): """ Hook to generate new PK values on save. This method is called when saving instances with no primary key value set. If this method returns something else than None, then the returned value is used when saving the new instance. """ if self.default: return self.get_default() return None def to_python(self, value): """ Convert the input value into the expected Python data type, raising django.core.exceptions.ValidationError if the data can't be converted. Return the converted value. Subclasses should override this. """ return value @cached_property def error_messages(self): messages = {} for c in reversed(self.__class__.__mro__): messages.update(getattr(c, "default_error_messages", {})) messages.update(self._error_messages or {}) return messages @cached_property def validators(self): """ Some validators can't be created at field initialization time. This method provides a way to delay their creation until required. """ return [*self.default_validators, *self._validators] def run_validators(self, value): if value in self.empty_values: return errors = [] for v in self.validators: try: v(value) except exceptions.ValidationError as e: if hasattr(e, "code") and e.code in self.error_messages: e.message = self.error_messages[e.code] errors.extend(e.error_list) if errors: raise exceptions.ValidationError(errors) def validate(self, value, model_instance): """ Validate value and raise ValidationError if necessary. Subclasses should override this to provide validation logic. """ if not self.editable: # Skip validation for non-editable fields. return if self.choices is not None and value not in self.empty_values: for option_key, option_value in self.choices: if isinstance(option_value, (list, tuple)): # This is an optgroup, so look inside the group for # options. for optgroup_key, optgroup_value in option_value: if value == optgroup_key: return elif value == option_key: return raise exceptions.ValidationError( self.error_messages["invalid_choice"], code="invalid_choice", params={"value": value}, ) if value is None and not self.null: raise exceptions.ValidationError(self.error_messages["null"], code="null") if not self.blank and value in self.empty_values: raise exceptions.ValidationError(self.error_messages["blank"], code="blank") def clean(self, value, model_instance): """ Convert the value's type and run validation. Validation errors from to_python() and validate() are propagated. Return the correct value if no error is raised. """ value = self.to_python(value) self.validate(value, model_instance) self.run_validators(value) return value def db_type_parameters(self, connection): return DictWrapper(self.__dict__, connection.ops.quote_name, "qn_") def db_check(self, connection): """ Return the database column check constraint for this field, for the provided connection. Works the same way as db_type() for the case that get_internal_type() does not map to a preexisting model field. """ data = self.db_type_parameters(connection) try: return ( connection.data_type_check_constraints[self.get_internal_type()] % data ) except KeyError: return None def db_type(self, connection): """ Return the database column data type for this field, for the provided connection. """ # The default implementation of this method looks at the # backend-specific data_types dictionary, looking up the field by its # "internal type". # # A Field class can implement the get_internal_type() method to specify # which *preexisting* Django Field class it's most similar to -- i.e., # a custom field might be represented by a TEXT column type, which is # the same as the TextField Django field type, which means the custom # field's get_internal_type() returns 'TextField'. # # But the limitation of the get_internal_type() / data_types approach # is that it cannot handle database column types that aren't already # mapped to one of the built-in Django field types. In this case, you # can implement db_type() instead of get_internal_type() to specify # exactly which wacky database column type you want to use. data = self.db_type_parameters(connection) try: return connection.data_types[self.get_internal_type()] % data except KeyError: return None def rel_db_type(self, connection): """ Return the data type that a related field pointing to this field should use. For example, this method is called by ForeignKey and OneToOneField to determine its data type. """ return self.db_type(connection) def cast_db_type(self, connection): """Return the data type to use in the Cast() function.""" db_type = connection.ops.cast_data_types.get(self.get_internal_type()) if db_type: return db_type % self.db_type_parameters(connection) return self.db_type(connection) def db_parameters(self, connection): """ Extension of db_type(), providing a range of different return values (type, checks). This will look at db_type(), allowing custom model fields to override it. """ type_string = self.db_type(connection) check_string = self.db_check(connection) return { "type": type_string, "check": check_string, } def db_type_suffix(self, connection): return connection.data_types_suffix.get(self.get_internal_type()) def get_db_converters(self, connection): if hasattr(self, "from_db_value"): return [self.from_db_value] return [] @property def unique(self): return self._unique or self.primary_key @property def db_tablespace(self): return self._db_tablespace or settings.DEFAULT_INDEX_TABLESPACE @property def db_returning(self): """ Private API intended only to be used by Django itself. Currently only the PostgreSQL backend supports returning multiple fields on a model. """ return False def set_attributes_from_name(self, name): self.name = self.name or name self.attname, self.column = self.get_attname_column() self.concrete = self.column is not None if self.verbose_name is None and self.name: self.verbose_name = self.name.replace("_", " ") def contribute_to_class(self, cls, name, private_only=False): """ Register the field with the model class it belongs to. If private_only is True, create a separate instance of this field for every subclass of cls, even if cls is not an abstract model. """ self.set_attributes_from_name(name) self.model = cls cls._meta.add_field(self, private=private_only) if self.column: setattr(cls, self.attname, self.descriptor_class(self)) if self.choices is not None: # Don't override a get_FOO_display() method defined explicitly on # this class, but don't check methods derived from inheritance, to # allow overriding inherited choices. For more complex inheritance # structures users should override contribute_to_class(). if "get_%s_display" % self.name not in cls.__dict__: setattr( cls, "get_%s_display" % self.name, partialmethod(cls._get_FIELD_display, field=self), ) def get_filter_kwargs_for_object(self, obj): """ Return a dict that when passed as kwargs to self.model.filter(), would yield all instances having the same value for this field as obj has. """ return {self.name: getattr(obj, self.attname)} def get_attname(self): return self.name def get_attname_column(self): attname = self.get_attname() column = self.db_column or attname return attname, column def get_internal_type(self): return self.__class__.__name__ def pre_save(self, model_instance, add): """Return field's value just before saving.""" return getattr(model_instance, self.attname) def get_prep_value(self, value): """Perform preliminary non-db specific value checks and conversions.""" if isinstance(value, Promise): value = value._proxy____cast() return value def get_db_prep_value(self, value, connection, prepared=False): """ Return field's value prepared for interacting with the database backend. Used by the default implementations of get_db_prep_save(). """ if not prepared: value = self.get_prep_value(value) return value def get_db_prep_save(self, value, connection): """Return field's value prepared for saving into a database.""" return self.get_db_prep_value(value, connection=connection, prepared=False) def has_default(self): """Return a boolean of whether this field has a default value.""" return self.default is not NOT_PROVIDED def get_default(self): """Return the default value for this field.""" return self._get_default() @cached_property def _get_default(self): if self.has_default(): if callable(self.default): return self.default return lambda: self.default if ( not self.empty_strings_allowed or self.null and not connection.features.interprets_empty_strings_as_nulls ): return return_None return str # return empty string def get_choices( self, include_blank=True, blank_choice=BLANK_CHOICE_DASH, limit_choices_to=None, ordering=(), ): """ Return choices with a default blank choices included, for use as