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

Question

I\'ve models for Books, Chapters and Pages. They are all written by a User:

from django.db import models
         


        

Answer 1

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}'