Duplicate Django model instance without modifying python object - python

I am trying to create a method to duplicate a model instance
new_object = old_object.duplicate_in_db()
According to Django 3.2 documentation model instance can be duplicated in database by setting entity pk and/or id to None :
# Model method
def duplicate_in_db(self):
self.pk = None
self._state.adding = True
# Some other duplication steps happens here e.g. duplicating OneToOneFields attributes
# ...
self.save()
However a side effect is that original object has its id changed (along other attributes...)
old_object_pk = old_object.pk
new_object = old_object.duplicate_in_db()
print(old_object_pk == old_object.pk) # False
What would be an effective duplicate method/function without any side effect?

Refreshing from db with correct id do the job, Downside is having to do multiple database call.
def duplicate_from_db(self):
old_pk = self.pk # storing for refreshing latter
self.pk = None
self._state.adding = True
self.save()
new_pk = self.pk
self.pk = old_pk
self.refresh_from_db()
return MyModel.objects.get(pk=new_pk)

Related

DRF - overrige Serializer.update to update related set

I'm trying to override update method of ModelSerializer so I can update the related set of objects while updating the instance.
The problem is that validated_data doesn't include ids of these objects even when I'm passing there to the serializer.
def update(self, instance, validated_data):
subcontracts = validated_data.pop('subcontracts') # THERE ARE NO IDS HERE
contract = super().update(instance,validated_data)
instance.subcontracts.exclude(id__in=[x.get('id',None) for x in subcontracts if x is not None]).delete()
for subcontract in subcontracts:
_id = subcontract.get('id',None)
if _id:
sc = SubContract.objects.get(id=_id)
else:
sc = SubContract()
for attr, value in subcontract.items():
setattr(sc, attr, value)
sc.contract = instance
sc.save()
return contract
Basically, what I want to do:
{id:4, some_data..., subcontracts:[{id:1,description:'xxx'},{id:2,description:'yyy'}]}
This data would (except updating the instance) delete related subcontracts not having id 1 or 2 and update the rest.
Do you know what to do?

ModelForm saving over model data with empty fields

I'm building an Edit form for a model in my database using a ModelForm in Django. Each field in the form is optional as the user may want to only edit one field.
The problem I am having is that when I call save() in the view, any empty fields are being saved over the instance's original values (e.g. if I only enter a new first_name, the last_name and ecf_code fields will save an empty string in the corresponding instance.)
The form:
class EditPlayerForm(forms.ModelForm):
class Meta:
model = Player
fields = ['first_name', 'last_name', 'ecf_code']
def __init__(self, *args, **kwargs):
super(EditPlayerForm, self).__init__(*args, **kwargs)
self.fields['first_name'].required = False
self.fields['last_name'].required = False
self.fields['ecf_code'].required = False
The view:
def view(request, player_pk = ''):
edit_player_form = forms.EditPlayerForm(auto_id="edit_%s")
if "edit_player_form" in request.POST:
if not player_pk:
messages.error(request, "No player pk given.")
else:
try:
selected_player = Player.objects.get(pk = player_pk)
except Player.DoesNotExist:
messages.error(request, "The selected player could not be found in the database.")
return redirect("players:management")
else:
edit_player_form = forms.EditPlayerForm(
request.POST,
instance = selected_player
)
if edit_player_form.is_valid():
player = edit_player_form.save()
messages.success(request, "The changes were made successfully.")
return redirect("players:management")
else:
form_errors.convert_form_errors_to_messages(edit_player_form, request)
return render(
request,
"players/playerManagement.html",
{
"edit_player_form": edit_player_form,
"players": Player.objects.all(),
}
)
I've tried overriding the save() method of the form to explicitly check which fields have values in the POST request but that didn't seem to make any difference either.
Attempt at overriding the save method:
def save(self, commit = True):
# Tried this way to get instance as well
# instance = super(EditPlayerForm, self).save(commit = False)
self.cleaned_data = dict([ (k,v) for k,v in self.cleaned_data.items() if v != "" ])
try:
self.instance.first_name = self.cleaned_data["first_name"]
except KeyError:
pass
try:
self.instance.last_name = self.cleaned_data["last_name"]
except KeyError:
pass
try:
self.instance.ecf_code = self.cleaned_data["ecf_code"]
except KeyError:
pass
if commit:
self.instance.save()
return self.instance
I also do not have any default values for the Player model as the docs say the ModeForm will use these for values absent in the form submission.
EDIT:
Here is the whole EditPlayerForm:
class EditPlayerForm(forms.ModelForm):
class Meta:
model = Player
fields = ['first_name', 'last_name', 'ecf_code']
def __init__(self, *args, **kwargs):
super(EditPlayerForm, self).__init__(*args, **kwargs)
self.fields['first_name'].required = False
self.fields['last_name'].required = False
self.fields['ecf_code'].required = False
def save(self, commit = True):
# If I print instance variables here they've already
# been updated with the form values
self.cleaned_data = [ k for k,v in self.cleaned_data.items() if v ]
self.instance.save(update_fields = self.cleaned_data)
if commit:
self.instance.save()
return self.instance
EDIT:
Ok so here is the solution, I figured I'd put it here as it might be useful to other people (I've certainly learned a bit from this).
So it turns out that the is_valid() method of the model form actually makes the changes to the instance you pass into the form, ready for the save() method to save them. So in order to fix this problem, I extended the clean() method of the form:
def clean(self):
if not self.cleaned_data.get("first_name"):
self.cleaned_data["first_name"] = self.instance.first_name
if not self.cleaned_data.get("last_name"):
self.cleaned_data["last_name"] = self.instance.last_name
if not self.cleaned_data.get("ecf_code"):
self.cleaned_data["ecf_code"] = self.instance.ecf_code
This basically just checks to see if the fields are empty and if a field is empty, fill it with the existing value from the given instance. clean() gets called before the instance variables are set with the new form values, so this way, any empty fields were actually filled with the corresponding existing instance data.
You could maybe use the update() method instead of save()
or the argument update_field
self.instance.save(update_fields=['fields_to_update'])
by building the list ['fields_to_update'] only with the not empty values.
It should even work with the comprehension you've tried :
self.cleaned_data = [ k for k,v in self.cleaned_data.items() if v ]
self.instance.save(update_fields=self.cleaned_data)
EDIT :
Without overriding the save method (and commenting out this attempt in the form):
not_empty_data = [ k for k,v in edit_player_form.cleaned_data.items() if v ]
print(not_empty_data)
player = edit_player_form.save(update_fields=not_empty_data)
You could check the values if it's not empty in your view without overriding save()
if edit_player_form.is_valid():
if edit_player_form.cleaned_data["first_name"]:
selected_player.first_name = edit_player_form.cleaned_data["first_name"]
if edit_player_form.cleaned_data["last_name"]:
selected_player.last_name= edit_player_form.cleaned_data["last_name"]
if edit_player_form.cleaned_data["ecf_code"]:
selected_player.ecf_code= edit_player_form.cleaned_data["ecf_code"]
selected_player.save()
This should work fine with what you want. I'm not sure if it's the best way to do it but it should work fine.

Django - Create object if field not in database

I want to create an object only if there's no other object with the same ID already in the database. The code below would create the same item if one the parameters below like the State was modified.
returns = Return.objects.all()
for ret in returns:
obj, created = Return.objects.get_or_create(ItemID="UUID",
ItemName="Hodaddy", State="Started")
obj.save()
get_or_create works off all the arguments provided to find the object.
What you need to do instead is use the special defaults argument to provide the new value for a field that you don't want to filter on.
In your case, you only want the UUID field to be unique, and so you provide the other two members as defaults.
obj, created = Return.objects.get_or_create(ItemID="UUID",
defaults={ItemName:"Hodaddy", State:"Started"})
Then you can make further decisions based on the value of created. I am not sure why you're iterating over all the Returns in the original question?
If you know the id, you can query for it:
In your question, you have:
returns = Return.objects.all()
for ret in returns:
return_in_database = Return.objects.filter(ItemId="UUID").exists()
if not return_in_database:
obj, created = Return.objects.get_or_create(ItemID="UUID",
ItemName="Hodaddy", State="Started")
obj.save()
This can be done as:
if not Return.objects.filter(ItemId="UUID").exists():
obj, created = Return.objects.get_or_create(ItemID="UUID",
ItemName="Hodaddy", State="Started")
obj.save()
As you can see, I've removed the for loop, as you were not using the variable ret anywhere, so no need to iterate over all Return objects. The above is functionally equivalent to what you had. :)
OR:
You can write your own manager with a create_or_update method inside your models.py
class ReturnManager(models.Manager):
def create_or_update(self, **kwargs):
new_return = Return(**kwargs)
existing = Return.objects.filter(ItemId=new_returns.ItemID).first()
if existing:
new_return.pk = existing.pk
new_return.id = existing.id
new_return.save()
return new_return
You would then assign this to your Return model
class Return(model.Models):
# your object fields here
objects = ReturnManager()
You need to change the param in the query, to just constraint the object lookup on ItemID. Once, a new object is returned you can update the ItemName and State
obj, created = Return.objects.get_or_create(ItemID="UUID")
if created:
obj.ItemName="<item-name>"
obj.State="<Started>"
obj.save()

Python - Unable to modify the serializer.data dictionary in Django Rest Framework

I have tried to add a key serializer.data['test'] = 'asdf', this does not appear to do anything.
I want to transform the representation of a key's value. To do this, I'm trying to use the value to calculate a new value and replace the old one in the dictionary.
This is what I want to accomplish, but I don't know why the value is not being replaced. There are no errors thrown, and the resulting dictionary has no evidence that I've tried to replace anything:
class PlaceDetail(APIView):
def get(self, request, pk, format=None):
place = Place.objects.select_related().get(pk=pk)
serializer = PlaceSerializer(place)
#serializer.data['tags'] = pivot_tags(serializer.data['tags'])
serializer.data['test'] = 'asdf'
print(serializer.data['test'])
return Response(serializer.data)
Terminal: KeyError: 'test'
I have observed by printing that serializer.data is a dictionary.
I have also tested that the syntax I'm trying to use should work:
>>> test = {'a': 'Alpha'}
>>> test
{'a': 'Alpha'}
>>> test['a']
'Alpha'
>>> test['a'] = 'asdf'
>>> test
{'a': 'asdf'}
How can I properly modify the serializer.data dictionary?
The Serializer.data property returns an OrderedDict which is constructed using serializer._data. The return value is not serializer._data itself.
Thus changing the return value of serializer.data does not change serializer._data member. As a consequence, the following calls to serializer.data are not changed.
# In class Serializer(BaseSerializer)
#property
def data(self):
ret = super(Serializer, self).data
return ReturnDict(ret, serializer=self)
# In class ReturnDict(OrderedDict)
def __init__(self, *args, **kwargs):
self.serializer = kwargs.pop('serializer')
super(ReturnDict, self).__init__(*args, **kwargs)
You can keep a copy of the return value of serializer.data, which is an ordered dictionary, and manipulate it as you wish.
Example:
# keep the return value of serializer.data
serialized_data = serializer.data
# Manipulate it as you wish
serialized_data['test'] = 'I am cute'
# Return the manipulated dict
return Response(serialized_data)
Why:
If you look at the source code of Django Restframework, you will see that in Serializer class,
Serializer._data is just a normal dictionary.
Serializer.data is a method decorated to act like a property. It returns a ReturnDict object, which is a customized class derived from OrderedDict. The returned ReturnDict object is initialized using key/value pairs in Serializer._data.
If Serializer.data returns Serializer._data directly, then your original method will work as you expected. But it won't work since it's returning another dictionary-like object constructed using Serializer._data.
Just keep in mind that the return value of Serializer.data is not Serializer._data, but an ordered dictionary-like object. Manipulating the return value does not change Serializer._data.
I believe the reason why serializer.data does not return serializer._data directly is to avoid accidental change of the data and to return a pretty representation of serializer._data.
You'll want to use SerializerMethodField instead of explicitly overwrite the representations.
Building further on #yuwang's answer, I used SerializerMethodField to modify value of a particular field in the serializer. Here's an example:
The field that I wanted to modify, let us call it is_modifyable. This field is present on the Django Model as models.BooleanField and hence it was not present in the list of fields on serializer definition and simply mentioned in the class Meta: definition under within the serializer definition.
So here's how my code looked before:
# in models.py
# Model definition
class SomeModel(models.Model):
is_modifyable = models.BooleanField(default=True)
# in serializers.py
# Serializer definition
class SomeModelSerializer(serializers.ModelSerializer):
class Meta:
model = SomeModel
fields = ('is_modifyable',)
As a result of the above, the value for the field is_modifyable was always fetched on the basis of what the value was in the record of SomeModel object. However, for some testing purpose, I wanted the value of this field to be returned as False during the development phase, hence I modified the code to be as follows:
# in models.py
# Model definition (Left unchanged)
class SomeModel(models.Model):
is_modifyable = models.BooleanField(default=True)
# in serializers.py
# Serializer definition (This was updated)
class SomeModelSerializer(serializers.ModelSerializer):
# This line was added new
is_modifyable = serializers.SerializerMethodField(read_only=True)
class Meta:
model = SomeModel
fields = ('is_modifyable',)
# get_is_modifyable function was added new
def get_is_modifyable(self, obj) -> bool:
"""
Dummy method to always return False for test purpose
Returns: False
"""
return False
Once the above code was in, the API call always returned the value of serializer field is_modifyable as False.

Duplicating model instances and their related objects in Django / Algorithm for recusrively duplicating an object

I've models for Books, Chapters and Pages. They are all written by a User:
from django.db import models
class Book(models.Model)
author = models.ForeignKey('auth.User')
class Chapter(models.Model)
author = models.ForeignKey('auth.User')
book = models.ForeignKey(Book)
class Page(models.Model)
author = models.ForeignKey('auth.User')
book = models.ForeignKey(Book)
chapter = models.ForeignKey(Chapter)
What I'd like to do is duplicate an existing Book and update it's User to someone else. The wrinkle is I would also like to duplicate all related model instances to the Book - all it's Chapters and Pages as well!
Things get really tricky when look at a Page - not only will the new Pages need to have their author field updated but they will also need to point to the new Chapter objects!
Does Django support an out of the box way of doing this? What would a generic algorithm for duplicating a model look like?
Cheers,
John
Update:
The classes given above are just an example to illustrate the problem I'm having!
This no longer works in Django 1.3 as CollectedObjects was removed. See changeset 14507
I posted my solution on Django Snippets. It's based heavily on the django.db.models.query.CollectedObject code used for deleting objects:
from django.db.models.query import CollectedObjects
from django.db.models.fields.related import ForeignKey
def duplicate(obj, value, field):
"""
Duplicate all related objects of `obj` setting
`field` to `value`. If one of the duplicate
objects has an FK to another duplicate object
update that as well. Return the duplicate copy
of `obj`.
"""
collected_objs = CollectedObjects()
obj._collect_sub_objects(collected_objs)
related_models = collected_objs.keys()
root_obj = None
# Traverse the related models in reverse deletion order.
for model in reversed(related_models):
# Find all FKs on `model` that point to a `related_model`.
fks = []
for f in model._meta.fields:
if isinstance(f, ForeignKey) and f.rel.to in related_models:
fks.append(f)
# Replace each `sub_obj` with a duplicate.
sub_obj = collected_objs[model]
for pk_val, obj in sub_obj.iteritems():
for fk in fks:
fk_value = getattr(obj, "%s_id" % fk.name)
# If this FK has been duplicated then point to the duplicate.
if fk_value in collected_objs[fk.rel.to]:
dupe_obj = collected_objs[fk.rel.to][fk_value]
setattr(obj, fk.name, dupe_obj)
# Duplicate the object and save it.
obj.id = None
setattr(obj, field, value)
obj.save()
if root_obj is None:
root_obj = obj
return root_obj
For django >= 2 there should be some minimal changes. so the output will be like this:
def duplicate(obj, value=None, field=None, duplicate_order=None):
"""
Duplicate all related objects of obj setting
field to value. If one of the duplicate
objects has an FK to another duplicate object
update that as well. Return the duplicate copy
of obj.
duplicate_order is a list of models which specify how
the duplicate objects are saved. For complex objects
this can matter. Check to save if objects are being
saved correctly and if not just pass in related objects
in the order that they should be saved.
"""
from django.db.models.deletion import Collector
from django.db.models.fields.related import ForeignKey
collector = Collector(using='default')
collector.collect([obj])
collector.sort()
related_models = collector.data.keys()
data_snapshot = {}
for key in collector.data.keys():
data_snapshot.update(
{key: dict(zip([item.pk for item in collector.data[key]], [item for item in collector.data[key]]))})
root_obj = None
# Sometimes it's good enough just to save in reverse deletion order.
if duplicate_order is None:
duplicate_order = reversed(related_models)
for model in duplicate_order:
# Find all FKs on model that point to a related_model.
fks = []
for f in model._meta.fields:
if isinstance(f, ForeignKey) and f.remote_field.related_model in related_models:
fks.append(f)
# Replace each `sub_obj` with a duplicate.
if model not in collector.data:
continue
sub_objects = collector.data[model]
for obj in sub_objects:
for fk in fks:
fk_value = getattr(obj, "%s_id" % fk.name)
# If this FK has been duplicated then point to the duplicate.
fk_rel_to = data_snapshot[fk.remote_field.related_model]
if fk_value in fk_rel_to:
dupe_obj = fk_rel_to[fk_value]
setattr(obj, fk.name, dupe_obj)
# Duplicate the object and save it.
obj.id = None
if field is not None:
setattr(obj, field, value)
obj.save()
if root_obj is None:
root_obj = obj
return root_obj
Here's an easy way to copy your object.
Basically:
(1) set the id of your original object to None:
book_to_copy.id = None
(2) change the 'author' attribute and save the ojbect:
book_to_copy.author = new_author
book_to_copy.save()
(3) INSERT performed instead of UPDATE
(It doesn't address changing the author in the Page--I agree with the comments regarding re-structuring the models)
I haven't tried it in django but python's deepcopy might just work for you
EDIT:
You can define custom copy behavior for your models if you implement functions:
__copy__() and __deepcopy__()
this is an edit of http://www.djangosnippets.org/snippets/1282/
It's now compatible with the Collector which replaced CollectedObjects in 1.3.
I didn't really test this too heavily, but did test it with an object with about 20,000 sub-objects, but in only about three layers of foreign-key depth. Use at your own risk of course.
For the ambitious guy who reads this post, you should consider subclassing Collector (or copying the entire class to remove this dependency on this unpublished section of the django API) to a class called something like "DuplicateCollector" and writing a .duplicate method that works similarly to the .delete method. that would solve this problem in a real way.
from django.db.models.deletion import Collector
from django.db.models.fields.related import ForeignKey
def duplicate(obj, value=None, field=None, duplicate_order=None):
"""
Duplicate all related objects of obj setting
field to value. If one of the duplicate
objects has an FK to another duplicate object
update that as well. Return the duplicate copy
of obj.
duplicate_order is a list of models which specify how
the duplicate objects are saved. For complex objects
this can matter. Check to save if objects are being
saved correctly and if not just pass in related objects
in the order that they should be saved.
"""
collector = Collector({})
collector.collect([obj])
collector.sort()
related_models = collector.data.keys()
data_snapshot = {}
for key in collector.data.keys():
data_snapshot.update({ key: dict(zip([item.pk for item in collector.data[key]], [item for item in collector.data[key]])) })
root_obj = None
# Sometimes it's good enough just to save in reverse deletion order.
if duplicate_order is None:
duplicate_order = reversed(related_models)
for model in duplicate_order:
# Find all FKs on model that point to a related_model.
fks = []
for f in model._meta.fields:
if isinstance(f, ForeignKey) and f.rel.to in related_models:
fks.append(f)
# Replace each `sub_obj` with a duplicate.
if model not in collector.data:
continue
sub_objects = collector.data[model]
for obj in sub_objects:
for fk in fks:
fk_value = getattr(obj, "%s_id" % fk.name)
# If this FK has been duplicated then point to the duplicate.
fk_rel_to = data_snapshot[fk.rel.to]
if fk_value in fk_rel_to:
dupe_obj = fk_rel_to[fk_value]
setattr(obj, fk.name, dupe_obj)
# Duplicate the object and save it.
obj.id = None
if field is not None:
setattr(obj, field, value)
obj.save()
if root_obj is None:
root_obj = obj
return root_obj
EDIT: Removed a debugging "print" statement.
In Django 1.5 this works for me:
thing.id = None
thing.pk = None
thing.save()
Using the CollectedObjects snippet above no longer works but can be done with the following modification:
from django.contrib.admin.util import NestedObjects
from django.db import DEFAULT_DB_ALIAS
and
collector = NestedObjects(using=DEFAULT_DB_ALIAS)
instead of CollectorObjects
I tried a few of the answers in Django 2.2/Python 3.6 and they didn't seem to copy one-to-many and many-to-many related objects. Also, many included hardcoding / incorporated foreknowledge of the data structures.
I wrote a way to do this in a more generic fashion, handling one-to-many and many-to-many related objects. Comments included, and I'm looking to improve upon it if you have suggestions:
def duplicate_object(self):
"""
Duplicate a model instance, making copies of all foreign keys pointing to it.
There are 3 steps that need to occur in order:
1. Enumerate the related child objects and m2m relations, saving in lists/dicts
2. Copy the parent object per django docs (doesn't copy relations)
3a. Copy the child objects, relating to the copied parent object
3b. Re-create the m2m relations on the copied parent object
"""
related_objects_to_copy = []
relations_to_set = {}
# Iterate through all the fields in the parent object looking for related fields
for field in self._meta.get_fields():
if field.one_to_many:
# One to many fields are backward relationships where many child
# objects are related to the parent. Enumerate them and save a list
# so we can copy them after duplicating our parent object.
print(f'Found a one-to-many field: {field.name}')
# 'field' is a ManyToOneRel which is not iterable, we need to get
# the object attribute itself.
related_object_manager = getattr(self, field.name)
related_objects = list(related_object_manager.all())
if related_objects:
print(f' - {len(related_objects)} related objects to copy')
related_objects_to_copy += related_objects
elif field.many_to_one:
# In testing, these relationships are preserved when the parent
# object is copied, so they don't need to be copied separately.
print(f'Found a many-to-one field: {field.name}')
elif field.many_to_many:
# Many to many fields are relationships where many parent objects
# can be related to many child objects. Because of this the child
# objects don't need to be copied when we copy the parent, we just
# need to re-create the relationship to them on the copied parent.
print(f'Found a many-to-many field: {field.name}')
related_object_manager = getattr(self, field.name)
relations = list(related_object_manager.all())
if relations:
print(f' - {len(relations)} relations to set')
relations_to_set[field.name] = relations
# Duplicate the parent object
self.pk = None
self.save()
print(f'Copied parent object ({str(self)})')
# Copy the one-to-many child objects and relate them to the copied parent
for related_object in related_objects_to_copy:
# Iterate through the fields in the related object to find the one that
# relates to the parent model.
for related_object_field in related_object._meta.fields:
if related_object_field.related_model == self.__class__:
# If the related_model on this field matches the parent
# object's class, perform the copy of the child object and set
# this field to the parent object, creating the new
# child -> parent relationship.
related_object.pk = None
setattr(related_object, related_object_field.name, self)
related_object.save()
text = str(related_object)
text = (text[:40] + '..') if len(text) > 40 else text
print(f'|- Copied child object ({text})')
# Set the many-to-many relations on the copied parent
for field_name, relations in relations_to_set.items():
# Get the field by name and set the relations, creating the new
# relationships.
field = getattr(self, field_name)
field.set(relations)
text_relations = []
for relation in relations:
text_relations.append(str(relation))
print(f'|- Set {len(relations)} many-to-many relations on {field_name} {text_relations}')
return self
If there's just a couple copies in the database you're building, I've found you can just use the back button in the admin interface, change the necessary fields and save the instance again. This has worked for me in cases where, for instance, I need to build a "gimlet" and a "vodka gimlet" cocktail where the only difference is replacing the name and an ingredient. Obviously, this requires a little foresight of the data and isn't as powerful as overriding django's copy/deepcopy - but it may do the trick for some.
Django does have a built-in way to duplicate an object via the admin - as answered here:
In the Django admin interface, is there a way to duplicate an item?
Simple non generic way
Proposed solutions didn't work for me, so I went the simple, not clever way. This is only useful for simple cases.
For a model with the following structure
Book
|__ CroppedFace
|__ Photo
|__ AwsReco
|__ AwsLabel
|__ AwsFace
|__ AwsEmotion
this works
def duplicate_book(book: Book, new_user: MyUser):
# AwsEmotion, AwsFace, AwsLabel, AwsReco, Photo, CroppedFace, Book
old_cropped_faces = book.croppedface_set.all()
old_photos = book.photo_set.all()
book.pk = None
book.user = new_user
book.save()
for cf in old_cropped_faces:
cf.pk = None
cf.book = book
cf.save()
for photo in old_photos:
photo.pk = None
photo.book = book
photo.save()
if hasattr(photo, 'awsreco'):
reco = photo.awsreco
old_aws_labels = reco.awslabel_set.all()
old_aws_faces = reco.awsface_set.all()
reco.pk = None
reco.photo = photo
reco.save()
for label in old_aws_labels:
label.pk = None
label.reco = reco
label.save()
for face in old_aws_faces:
old_aws_emotions = face.awsemotion_set.all()
face.pk = None
face.reco = reco
face.save()
for emotion in old_aws_emotions:
emotion.pk = None
emotion.aws_face = face
emotion.save()
return book
Here is a somewhat simple-minded solution. This does not depend on any undocumented Django APIs. It assumes that you want to duplicate a single parent record, along with its child, grandchild, etc. records. You pass in a whitelist of classes that should actually be duplicated, in the form of a list of names of the one-to-many relationships on each parent object that point to its child objects. This code assumes that, given the above whitelist, the entire tree is self-contained, with no external references to worry about.
This solution doesn't do anything special for the author field above. I'm not sure if it would work with that. Like others have said, that author field probably shouldn't be repeated in different model classes.
One more thing about this code: it is truly recursive, in that it calls itself for each new level of descendants.
from collections import OrderedDict
def duplicate_model_with_descendants(obj, whitelist, _new_parent_pk=None):
kwargs = {}
children_to_clone = OrderedDict()
for field in obj._meta.get_fields():
if field.name == "id":
pass
elif field.one_to_many:
if field.name in whitelist:
these_children = list(getattr(obj, field.name).all())
if children_to_clone.has_key(field.name):
children_to_clone[field.name] |= these_children
else:
children_to_clone[field.name] = these_children
else:
pass
elif field.many_to_one:
if _new_parent_pk:
kwargs[field.name + '_id'] = _new_parent_pk
elif field.concrete:
kwargs[field.name] = getattr(obj, field.name)
else:
pass
new_instance = obj.__class__(**kwargs)
new_instance.save()
new_instance_pk = new_instance.pk
for ky in children_to_clone.keys():
child_collection = getattr(new_instance, ky)
for child in children_to_clone[ky]:
child_collection.add(duplicate_model_with_descendants(child, whitelist=whitelist, _new_parent_pk=new_instance_pk))
return new_instance
Example usage:
from django.db import models
class Book(models.Model)
author = models.ForeignKey('auth.User')
class Chapter(models.Model)
# author = models.ForeignKey('auth.User')
book = models.ForeignKey(Book, related_name='chapters')
class Page(models.Model)
# author = models.ForeignKey('auth.User')
# book = models.ForeignKey(Book)
chapter = models.ForeignKey(Chapter, related_name='pages')
WHITELIST = ['books', 'chapters', 'pages']
original_record = models.Book.objects.get(pk=1)
duplicate_record = duplicate_model_with_descendants(original_record, WHITELIST)
I think you'd be happier with a simpler data model, also.
Is it really true that a Page is in some Chapter but a different book?
userMe = User( username="me" )
userYou= User( username="you" )
bookMyA = Book( userMe )
bookYourB = Book( userYou )
chapterA1 = Chapter( book= bookMyA, author=userYou ) # "me" owns the Book, "you" owns the chapter?
chapterB2 = Chapter( book= bookYourB, author=userMe ) # "you" owns the book, "me" owns the chapter?
page1 = Page( book= bookMyA, chapter= chapterB2, author=userMe ) # Book and Author aggree, chapter doesn't?
It seems like your model is too complex.
I think you'd be happier with something simpler. I'm just guessing at this, since I don't your know entire problem.
class Book(models.Model)
name = models.CharField(...)
class Chapter(models.Model)
name = models.CharField(...)
book = models.ForeignKey(Book)
class Page(models.Model)
author = models.ForeignKey('auth.User')
chapter = models.ForeignKey(Chapter)
Each page has distinct authorship. Each chapter, then, has a collection of authors, as does the book. Now you can duplicate Book, Chapter and Pages, assigning the cloned Pages to the new Author.
Indeed, you might want to have a many-to-many relationship between Page and Chapter, allowing you to have multiple copies of just the Page, without cloning book and Chapter.
I had no luck with any of the answers here with Django 2.1.2, so I created a generic way of performing a deep copy of a database model that is heavily based on the answers posted above.
The key differences from the answers above is that ForeignKey no longer has an attribute called rel, so it has to be changed to f.remote_field.model etc.
Furthermore, because of the difficulty of knowing the order the database models should be copied in, I created a simple queuing system that pushes the current model to the end of the list if it is unsuccessfully copied. The code is postet below:
import queue
from django.contrib.admin.utils import NestedObjects
from django.db.models.fields.related import ForeignKey
def duplicate(obj, field=None, value=None, max_retries=5):
# Use the Nested Objects collector to retrieve the related models
collector = NestedObjects(using='default')
collector.collect([obj])
related_models = list(collector.data.keys())
# Create an object to map old primary keys to new ones
data_snapshot = {}
model_queue = queue.Queue()
for key in related_models:
data_snapshot.update(
{key: {item.pk: None for item in collector.data[key]}}
)
model_queue.put(key)
# For each of the models in related models copy their instances
root_obj = None
attempt_count = 0
while not model_queue.empty():
model = model_queue.get()
root_obj, success = copy_instances(model, related_models, collector, data_snapshot, root_obj)
# If the copy is not a success, it probably means that not
# all the related fields for the model has been copied yet.
# The current model is therefore pushed to the end of the list to be copied last
if not success:
# If the last model is unsuccessful or the number of max retries is reached, raise an error
if model_queue.empty() or attempt_count > max_retries:
raise DuplicationError(model)
model_queue.put(model)
attempt_count += 1
return root_obj
def copy_instances(model, related_models, collector, data_snapshot, root_obj):
# Store all foreign keys for the model in a list
fks = []
for f in model._meta.fields:
if isinstance(f, ForeignKey) and f.remote_field.model in related_models:
fks.append(f)
# Iterate over the instances of the model
for obj in collector.data[model]:
# For each of the models foreign keys check if the related object has been copied
# and if so, assign its personal key to the current objects related field
for fk in fks:
pk_field = f"{fk.name}_id"
fk_value = getattr(obj, pk_field)
# Fetch the dictionary containing the old ids
fk_rel_to = data_snapshot[fk.remote_field.model]
# If the value exists and is in the dictionary assign it to the object
if fk_value is not None and fk_value in fk_rel_to:
dupe_pk = fk_rel_to[fk_value]
# If the desired pk is none it means that the related object has not been copied yet
# so the function returns unsuccessful
if dupe_pk is None:
return root_obj, False
setattr(obj, pk_field, dupe_pk)
# Store the old pk and save the object without an id to create a shallow copy of the object
old_pk = obj.id
obj.id = None
if field is not None:
setattr(obj, field, value)
obj.save()
# Store the new id in the data snapshot object for potential use on later objects
data_snapshot[model][old_pk] = obj.id
if root_obj is None:
root_obj = obj
return root_obj, True
I hope it is of any help :)
The duplication error is just a simple exception extension:
class DuplicationError(Exception):
"""
Is raised when a duplication operation did not succeed
Attributes:
model -- The database model that failed
"""
def __init__(self, model):
self.error_model = model
def __str__(self):
return f'Was not able to duplicate database objects for model {self.error_model}'
There is an option to create a duplicate/clone/save-as-new in django admin.
Create a ModelAdmin class of the model you want to clone in admin.py
In the class add an admin action like:
#admin.register(Book)
class BookAdmin(models.ModelAdmin):
save_as = True
and this will create a "Save as New" button in your admin panel to completely clone the model object with all it's related fields.
django-clone library works perfectly for me with ManyToMany relationships. Just:
Make the model you want to clone a subclass of CloneModel:
from django.db import models
from model_clone.models import CloneModel
class MyModel(CloneModel):
name = models.CharField(max_length=50)
tags = models.ManyToManyField(Tag)
# You must specify all the ManyToManyField fields
_clone_m2m_fields = ['tags']
Then just call make_clone method:
obj = MyModel.objects.get(pk=some_pk)
cloned = obj.make_clone()
You can also define specific values for the cloned object. Read the docs for more!
I experimented the Stephen G Tuggy's solution and I found it very clever but, unfortunatly, it won't work in some special situations.
Let's suppose the following scenario:
class FattAqp(models.Model):
descr = models.CharField('descrizione', max_length=200)
ef = models.ForeignKey(Esercizio, ...)
forn = models.ForeignKey(Fornitore, ...)
class Periodo(models.Model):
# id usato per identificare i documenti
# periodo rilevato in fattura
data_i_p = models.DateField('data inizio', blank=True)
idfatt = models.ForeignKey(FattAqp, related_name='periodo')
class Lettura(models.Model):
mc_i = models.DecimalField(max_digits=7, ...)
faqp = models.ForeignKey(FattAqp, related_name='lettura')
an_im = models.ForeignKey('cnd.AnagImm', ..)
class DettFAqp(models.Model):
imponibile = models.DecimalField(...)
voce = models.ForeignKey(VoceAqp, ...)
periodo = models.ForeignKey(Periodo, related_name='dettfaqp')
In this case, if we try to deep-copy a FattAqp instance, ef, forn, an_im and voce fields will not correctly set; on the other hand idfatt, faqp, periodo will.
I solved the problem by adding one more parameter to the function and with a slight modification to the code. I tested it with Python 3.6 and Django 2.2
Here is it:
def duplicate_model_with_descendants(obj, whitelist, _new_parent_pk=None, static_fk=None):
kwargs = {}
children_to_clone = OrderedDict()
for field in obj._meta.get_fields():
if field.name == "id":
pass
elif field.one_to_many:
if field.name in whitelist:
these_children = list(getattr(obj, field.name).all())
if field.name in children_to_clone:
children_to_clone[field.name] |= these_children
else:
children_to_clone[field.name] = these_children
else:
pass
elif field.many_to_one:
name_with_id = field.name + '_id'
if _new_parent_pk:
kwargs[name_with_id] = _new_parent_pk
if name_with_id in static_fk:
kwargs[name_with_id] = getattr(obj, name_with_id)
elif field.concrete:
kwargs[field.name] = getattr(obj, field.name)
else:
pass
new_instance = obj.__class__(**kwargs)
new_instance.save()
new_instance_pk = new_instance.pk
for ky in children_to_clone.keys():
child_collection = getattr(new_instance, ky)
for child in children_to_clone[ky]:
child_collection.add(
duplicate_model_with_descendants(child, whitelist=whitelist, _new_parent_pk=new_instance_pk,static_fk=static_fk))
Example usage:
original_record = FattAqp.objects.get(pk=4)
WHITELIST = ['lettura', 'periodo', 'dettfaqp']
STATIC_FK = ['fornitore_id','ef_id','an_im_id', 'voce_id']
duplicate_record = duplicate_model_with_descendants(original_record, WHITELIST, static_fk=STATIC_FK)
Elaborated based on previous answers:
def derive(obj):
import copy
from django.contrib.admin.utils import NestedObjects
from django.db import DEFAULT_DB_ALIAS
from django.db.models.fields.related import ForeignKey
"""
Derive a new model instance from previous one,
and duplicate all related fields to point to the new instance
"""
obj2 = copy.copy(obj)
obj2.pk = None
obj2.save()
collector = NestedObjects(using=DEFAULT_DB_ALIAS)
collector.collect([obj])
collector.sort()
related_models = collector.data.keys()
data_snapshot = {}
for key in collector.data.keys():
data_snapshot.update({
key: dict(
zip(
[item.pk for item in collector.data[key]],
[item for item in collector.data[key]]
)
)
})
duplicate_order = reversed(related_models)
for model in duplicate_order:
# Find all FKs on model that point to a related_model.
fks = []
for f in model._meta.fields:
if isinstance(f, ForeignKey) and f.rel.to in related_models:
fks.append(f)
# Replace each `sub_obj` with a duplicate.
if model not in collector.data:
continue
sub_objects = collector.data[model]
for obj in sub_objects:
for fk in fks:
dupe_obj = copy.copy(obj)
setattr(dupe_obj, fk.name, obj2)
dupe_obj.pk = None
dupe_obj.save()
return obj2
Suggestion of Julio Marins works! Thnx!
For Django >= 2.* this line:
if isinstance(f, ForeignKey) and f.rel.to in related_models:
Should be replaced with:
if isinstance(f, ForeignKey) and f.remote_field.model in related_models:

Categories

Resources