How to access serializer.data on ListSerializer parent class in DRF?

Question

I'm getting an error when trying to access serializer.data before returning it in the Response(serializer.data, status=something):

Getting KeyError when attempting to get a value for field <field> on serializer <serializer>.

This occurs on all fields (because it turns out I'm trying to access .data on the parent and not the child, see below)

The class definition looks like this:

class BulkProductSerializer(serializers.ModelSerializer):

    list_serializer_class = CustomProductListSerializer

    user = serializers.CharField(source='fk_user.username', read_only=False)

    class Meta:
        model = Product
        fields = (
            'user',
            'uuid',
            'product_code',
            ...,
        )

CustomProductListSerializer is a serializers.ListSerializer and has an overridden save() method that allows it to correctly handle bulk create and update.

Here's an example view from the bulk Product ViewSet:

def partial_update(self, request):

    serializer = self.get_serializer(data=request.data,
                        many=isinstance(request.data, list),
                        partial=True)
    if not serializer.is_valid():
        return Response(serializer.errors, status=status.HTTP_400_BAD_REQUEST)
    serializer.save()
    pdb.set_trace()
    return Response(serializer.data, status=status.HTTP_200_OK)

Trying to access serializer.data at the trace (or the line after, obviously) causes the error. Here's the full trace (tl;dr skip below where I diagnose with debugger):

 Traceback (most recent call last):
  File "/lib/python3.5/site-packages/django/core/handlers/exception.py", line 41, in inner
    response = get_response(request)
  File "/lib/python3.5/site-packages/django/core/handlers/base.py", line 249, in _legacy_get_response
    response = self._get_response(request)
  File "/lib/python3.5/site-packages/django/core/handlers/base.py", line 187, in _get_response
    response = self.process_exception_by_middleware(e, request)
  File "/lib/python3.5/site-packages/django/core/handlers/base.py", line 185, in _get_response
    response = wrapped_callback(request, *callback_args, **callback_kwargs)
  File "/lib/python3.5/site-packages/django/views/decorators/csrf.py", line 58, in wrapped_view
    return view_func(*args, **kwargs)
  File "/lib/python3.5/site-packages/rest_framework/viewsets.py", line 86, in view
    return self.dispatch(request, *args, **kwargs)
  File "/lib/python3.5/site-packages/rest_framework/views.py", line 489, in dispatch
    response = self.handle_exception(exc)
  File "/lib/python3.5/site-packages/rest_framework/views.py", line 449, in handle_exception
    self.raise_uncaught_exception(exc)
  File "/lib/python3.5/site-packages/rest_framework/views.py", line 486, in dispatch
    response = handler(request, *args, **kwargs)
  File "/application/siop/views/API/product.py", line 184, in partial_update
    return Response(serializer.data, status=status.HTTP_200_OK)
  File "/lib/python3.5/site-packages/rest_framework/serializers.py", line 739, in data
    ret = super(ListSerializer, self).data
  File "/lib/python3.5/site-packages/rest_framework/serializers.py", line 265, in data
    self._data = self.to_representation(self.validated_data)
  File "/lib/python3.5/site-packages/rest_framework/serializers.py", line 657, in to_representation
    self.child.to_representation(item) for item in iterable
  File "/lib/python3.5/site-packages/rest_framework/serializers.py", line 657, in <listcomp>
    self.child.to_representation(item) for item in iterable
  File "/lib/python3.5/site-packages/rest_framework/serializers.py", line 488, in to_representation
    attribute = field.get_attribute(instance)
  File "/lib/python3.5/site-packages/rest_framework/fields.py", line 464, in get_attribute
    raise type(exc)(msg)
KeyError: "Got KeyError when attempting to get a value for field `user` on serializer `BulkProductSerializer`.\nThe serializer field might be named incorrectly and not match any attribute or key on the `OrderedDict` instance.\nOriginal exception text was: 'fk_user'."

At the L657 of the traceback (source here) I've got:

iterable = data.all() if isinstance(data, models.Manager) else data
return [
    self.child.to_representation(item) for item in iterable
]

This made me wonder (digging further down in the trace) why the serializer.fields were not available. I suspected it was because the serializer was a CustomProductListSerializer parent, and not a BulkProductSerializer child, and I was right. In the pdb trace just before returning the Response(serializer.data):

(Pdb) serializer.fields
*** AttributeError: 'CustomProductListSerializer' object has no attribute 'fields'
(Pdb) serializer.child.fields
{'uuid': UUIDField(read_only=False, required=False, validators=[]) ...(etc)}
(Pdb) 'user' in serializer.child.fields
True
(Pdb) serializer.data
*** KeyError: "Got KeyError when attempting to get a value for field `user` on serializer `BulkProductSerializer`.\nThe serializer field might be named incorrectly and not match any attribute or key on the `OrderedDict` instance.\nOriginal exception text was: 'fk_user'."
(Pdb) serializer.child.data
{'uuid': '08ec13c0-ab6c-45d4-89ab-400019874c63', ...(etc)}

OK, so what's the right way to get the complete serializer.data and return it in the resopnse for the parent serializer class in the situation described by partial_update in my ViewSet?

Edit:

class CustomProductListSerializer(serializers.ListSerializer):

    def save(self):
        instances = []
        result = []
        pdb.set_trace()
        for obj in self.validated_data:
            uuid = obj.get('uuid', None)
            if uuid:
                instance = get_object_or_404(Product, uuid=uuid)
                # Specify which fields to update, otherwise save() tries to SQL SET all fields.
                # Gotcha: remove the primary key, because update_fields will throw exception.
                # see https://stackoverflow.com/a/45494046
                update_fields = [k for k,v in obj.items() if k != 'uuid']
                for k, v in obj.items():
                    if k != 'uuid':
                        setattr(instance, k, v)
                instance.save(update_fields=update_fields)
                result.append(instance)
            else:
                instances.append(Product(**obj))

        if len(instances) > 0:
            Product.objects.bulk_create(instances)
            result += instances

        return result

Answer 1

At the point in the trace where I try to access serializer.data and get the KeyError, I note that serializer.data only contains key/vaule pairs from the initial_data, not the instance data (hence, I suppose, the KeyError; some model fields' keys are not present as it is a partial_update request). However, serializer.child.data does contain all the instance data for the last child in the list.

So, I go to the rest_framework/serializers.py source where data is defined:

249    @property
250    def data(self):
251        if hasattr(self, 'initial_data') and not hasattr(self, '_validated_data'):
252            msg = (
253                'When a serializer is passed a `data` keyword argument you '
254                'must call `.is_valid()` before attempting to access the '
255                'serialized `.data` representation.\n'
256                'You should either call `.is_valid()` first, '
257                'or access `.initial_data` instead.'
258            )
259            raise AssertionError(msg)
260
261        if not hasattr(self, '_data'):
262            if self.instance is not None and not getattr(self, '_errors', None):
263                self._data = self.to_representation(self.instance)
264            elif hasattr(self, '_validated_data') and not getattr(self, '_errors', None):
265                self._data = self.to_representation(self.validated_data)
266            else:
267                self._data = self.get_initial()
268        return self._data

Line 265 is problematic. I can replicate the error by calling serializer.child.to_representation({'uuid': '87956604-fbcb-4244-bda3-9e39075d510a', 'product_code': 'foobar'}) at the breakpoint.

Calling partial_update() works fine on a single instance (because self.instance is set, self.to_representation(self.instance) works). However, for a bulk partial_update() implementation, self.validated_data is missing model fields, and to_representation() won't work, so I won't be able to access the .data property.

One option would be to maintain some sort of self.instances list of Product instances, and override the definition of data on line 265:

self._data = self.to_representation(self.instances)

I'd really prefer an answer from someone more experienced in this sort of problem though, as I'm not sure if that's a sensible solution, hence I'm leaving the bounty open in the hope that someone can suggest something smarter to do.

Answer 2

As mentioned in the comment i still think the exception could be because of the user field in BulkProductSerializer class, not really anything to do with ListSerializer

There might be another minor error (but important) in the serializer DRF as mentioned in the documentation here. Here is how to specify a list_serializer_class:

class CustomListSerializer(serializers.ListSerializer):
    ...

class CustomSerializer(serializers.Serializer):
    ...
    class Meta:
        list_serializer_class = CustomListSerializer

Note that it's specified inside of the Meta class, not outside. So i think in your code, it will not understand to switch to the List Serializer with many=True. That should cause the not-updating problem.

Update - Add example for updating nested list serializer

It seems that the question was more about a generic way to implement updating for nested List Serializer rather than the actual error. Therefore, i will try to provide a sample code.

Some notes:

• If we use ModelViewSet, the list route won't allow PUT or PATCH, so neither update nor partial_update will be called (reference). Therefore i use POST directly, this is much simpler.
• If you want to use PUT/PATCH, then see this answer here
• We can always add a query parameter like allow_update or partial directly to the Post request to differentiate between POST/PUT/PATCH
• Instead of using uuid like the question i will use the normal id, it should be very much the same

It was rather simple

For reference, models look like this:

class Product(models.Model):
    name = models.CharField(max_length=200)
    user = models.ForeignKey(User, null=True, blank=True)

    def __unicode__(self):
        return self.name

Step 1: Make sure serializer change to ListSerializer

class ProductViewSet(viewsets.ModelViewSet):
    serializer_class = ProductSerializer
    queryset = Product.objects.all()

    def get_serializer(self, *args, **kwargs):
        # checking for post only so that 'get' won't be affected
        if self.request.method.lower() == 'post':
            data = kwargs.get('data')
            kwargs['many'] = isinstance(data, list)
        return super(ProductViewSet, self).get_serializer(*args, **kwargs)

Step 2: Implement the ListSerializer by overriding create function

class ProductListSerializer(serializers.ListSerializer):
    def create(self, validated_data):
        new_products = [Product(**p) for p in validated_data if not p.get('id')]
        updating_data = {p.get('id'): p for p in validated_data if p.get('id')}
        # query old products
        old_products = Product.objects.filter(id__in=updating_data.keys())
        with transaction.atomic():
            # create new products
            all_products = Product.objects.bulk_create(new_products)
            # update old products
            for p in old_products:
                data = updating_data.get(p.id, {})
                # pop id to remove
                data.pop('id')
                updated_p = Product(id=p.id, **data)
                updated_p.save()
                all_products.append(updated_p)
        return all_products


class ProductSerializer(serializers.ModelSerializer):
    user = serializers.SlugRelatedField(slug_field='username', queryset=User.objects.all())
    id = serializers.IntegerField(required=False)

    class Meta:
        model = Product
        fields = '__all__'
        list_serializer_class = ProductListSerializer