When saving, how can you check if a field has changed?

Viewed 217003

In my model I have :

class Alias(MyBaseModel):
remote_image = models.URLField(
    max_length=500, null=True,
    help_text='''
        A URL that is downloaded and cached for the image.
        Only used when the alias is made
    '''
)
    image = models.ImageField(
        upload_to='alias', default='alias-default.png',
        help_text="An image representing the alias"
    )

    
    def save(self, *args, **kw):
        if (not self.image or self.image.name == 'alias-default.png') and self.remote_image :
            try :
                data = utils.fetch(self.remote_image)
                image = StringIO.StringIO(data)
                image = Image.open(image)
                buf = StringIO.StringIO()
                image.save(buf, format='PNG')
                self.image.save(
                    hashlib.md5(self.string_id).hexdigest() + ".png", ContentFile(buf.getvalue())
                )
            except IOError :
                pass

Which works great for the first time the remote_image changes.

How can I fetch a new image when someone has modified the remote_image on the alias? And secondly, is there a better way to cache a remote image?

28 Answers

There is an attribute __dict__ which have all the fields as the keys and value as the field values. So we can just compare two of them

Just change the save function of model to the function below

def save(self, force_insert=False, force_update=False, using=None, update_fields=None):
    if self.pk is not None:
        initial = A.objects.get(pk=self.pk)
        initial_json, final_json = initial.__dict__.copy(), self.__dict__.copy()
        initial_json.pop('_state'), final_json.pop('_state')
        only_changed_fields = {k: {'final_value': final_json[k], 'initial_value': initial_json[k]} for k in initial_json if final_json[k] != initial_json[k]}
        print(only_changed_fields)
    super(A, self).save(force_insert=False, force_update=False, using=None, update_fields=None)

Example Usage:

class A(models.Model):
    name = models.CharField(max_length=200, null=True, blank=True)
    senior = models.CharField(choices=choices, max_length=3)
    timestamp = models.DateTimeField(null=True, blank=True)

    def save(self, force_insert=False, force_update=False, using=None, update_fields=None):
        if self.pk is not None:
            initial = A.objects.get(pk=self.pk)
            initial_json, final_json = initial.__dict__.copy(), self.__dict__.copy()
            initial_json.pop('_state'), final_json.pop('_state')
            only_changed_fields = {k: {'final_value': final_json[k], 'initial_value': initial_json[k]} for k in initial_json if final_json[k] != initial_json[k]}
            print(only_changed_fields)
        super(A, self).save(force_insert=False, force_update=False, using=None, update_fields=None)

yields output with only those fields that have been changed

{'name': {'initial_value': '1234515', 'final_value': 'nim'}, 'senior': {'initial_value': 'no', 'final_value': 'yes'}}

Very late to the game, but this is a version of Chris Pratt's answer that protects against race conditions while sacrificing performance, by using a transaction block and select_for_update()

@receiver(pre_save, sender=MyModel)
@transaction.atomic
def do_something_if_changed(sender, instance, **kwargs):
    try:
        obj = sender.objects.select_for_update().get(pk=instance.pk)
    except sender.DoesNotExist:
        pass # Object is new, so field hasn't technically changed, but you may want to do something else here.
    else:
        if not obj.some_field == instance.some_field: # Field has changed
            # do something

My take on @iperelivskiy's solution: on large scale, creating the _initial dict for every __init__ is expensive, and most of the time - unnecessary. I have changed the mixin slightly such that it records changes only when you explicitly tell it to do so (by calling instance.track_changes):

from typing import KeysView, Optional
from django.forms import model_to_dict

class TrackChangesMixin:
    _snapshot: Optional[dict] = None

    def track_changes(self):
        self._snapshot = self.as_dict

    @property
    def diff(self) -> dict:
        if self._snapshot is None:
            raise ValueError("track_changes wasn't called, can't determine diff.")
        d1 = self._snapshot
        d2 = self.as_dict
        diffs = [(k, (v, d2[k])) for k, v in d1.items() if str(v) != str(d2[k])]
        return dict(diffs)

    @property
    def has_changed(self) -> bool:
        return bool(self.diff)

    @property
    def changed_fields(self) -> KeysView:
        return self.diff.keys()

    @property
    def as_dict(self) -> dict:
        return model_to_dict(self, fields=[field.name for field in self._meta.fields])

I have found this package django-lifecycle. It uses django signals to define @hook decorator, which is very robust and reliable. I used it and it is a bliss.

Here is another way of doing it.

class Parameter(models.Model):

    def __init__(self, *args, **kwargs):
        super(Parameter, self).__init__(*args, **kwargs)
        self.__original_value = self.value

    def clean(self,*args,**kwargs):
        if self.__original_value == self.value:
            print("igual")
        else:
            print("distinto")

    def save(self,*args,**kwargs):
        self.full_clean()
        return super(Parameter, self).save(*args, **kwargs)
        self.__original_value = self.value

    key = models.CharField(max_length=24, db_index=True, unique=True)
    value = models.CharField(max_length=128)

As per documentation: validating objects

"The second step full_clean() performs is to call Model.clean(). This method should be overridden to perform custom validation on your model. This method should be used to provide custom model validation, and to modify attributes on your model if desired. For instance, you could use it to automatically provide a value for a field, or to do validation that requires access to more than a single field:"

If you do not find interest in overriding save method, you can do

  model_fields = [f.name for f in YourModel._meta.get_fields()]
  valid_data = {
        key: new_data[key]
        for key in model_fields
        if key in new_data.keys()
  }

  for (key, value) in valid_data.items():
        if getattr(instance, key) != value:
           print ('Data has changed')

        setattr(instance, key, value)

 instance.save()

Sometimes I want to check for changes on the same specific fields on multiple models that share those fields, so I define a list of those fields and use a signal. In this case, geocoding addresses only if something has changed, or if the entry is new:

from django.db.models.signals import pre_save
from django.dispatch import receiver

@receiver(pre_save, sender=SomeUserProfileModel)
@receiver(pre_save, sender=SomePlaceModel)
@receiver(pre_save, sender=SomeOrganizationModel)
@receiver(pre_save, sender=SomeContactInfoModel)
def geocode_address(sender, instance, *args, **kwargs):

    input_fields = ['address_line', 'address_line_2', 'city', 'state', 'postal_code', 'country']

    try:
        orig = sender.objects.get(id=instance.id)
        if orig:
            changes = 0
            for field in input_fields:
                if not (getattr(instance, field)) == (getattr(orig, field)):
                    changes += 1
            if changes > 0:
                # do something here because at least one field changed...
                my_geocoder_function(instance)
    except:
        # do something here because there is no original, or pass.
        my_geocoder_function(instance)

Writing it once and attaching with "@receiver" sure beats overriding multiple model save methods, but perhaps some others have better ideas.

Related