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

Question

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?

Answer 1

Essentially, you want to override the __init__ method of models.Model so that you keep a copy of the original value. This makes it so that you don't have to do another DB lookup (which is always a good thing).

    class Person(models.Model):
        name = models.CharField()

        __original_name = None

        def __init__(self, *args, **kwargs):
            super().__init__(*args, **kwargs)
            self.__original_name = self.name

        def save(self, force_insert=False, force_update=False, *args, **kwargs):
            if self.name != self.__original_name:
                # name changed - do something here

            super().save(force_insert, force_update, *args, **kwargs)
            self.__original_name = self.name

Answer 2

I use following mixin:

from django.forms.models import model_to_dict


class ModelDiffMixin(object):
    """
    A model mixin that tracks model fields' values and provide some useful api
    to know what fields have been changed.
    """

    def __init__(self, *args, **kwargs):
        super(ModelDiffMixin, self).__init__(*args, **kwargs)
        self.__initial = self._dict

    @property
    def diff(self):
        d1 = self.__initial
        d2 = self._dict
        diffs = [(k, (v, d2[k])) for k, v in d1.items() if v != d2[k]]
        return dict(diffs)

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

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

    def get_field_diff(self, field_name):
        """
        Returns a diff for field if it's changed and None otherwise.
        """
        return self.diff.get(field_name, None)

    def save(self, *args, **kwargs):
        """
        Saves model and set initial state.
        """
        super(ModelDiffMixin, self).save(*args, **kwargs)
        self.__initial = self._dict

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

Usage:

>>> p = Place()
>>> p.has_changed
False
>>> p.changed_fields
[]
>>> p.rank = 42
>>> p.has_changed
True
>>> p.changed_fields
['rank']
>>> p.diff
{'rank': (0, 42)}
>>> p.categories = [1, 3, 5]
>>> p.diff
{'categories': (None, [1, 3, 5]), 'rank': (0, 42)}
>>> p.get_field_diff('categories')
(None, [1, 3, 5])
>>> p.get_field_diff('rank')
(0, 42)
>>>

---

Note

Please note that this solution works well in context of current request only. Thus it's suitable primarily for simple cases. In concurrent environment where multiple requests can manipulate the same model instance at the same time, you definitely need a different approach.

Answer 3

Best way is with a pre_save signal. May not have been an option back in '09 when this question was asked and answered, but anyone seeing this today should do it this way:

@receiver(pre_save, sender=MyModel)
def do_something_if_changed(sender, instance, **kwargs):
    try:
        obj = sender.objects.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

Answer 4

And now for direct answer: one way to check if the value for the field has changed is to fetch original data from database before saving instance. Consider this example:

class MyModel(models.Model):
    f1 = models.CharField(max_length=1)

    def save(self, *args, **kw):
        if self.pk is not None:
            orig = MyModel.objects.get(pk=self.pk)
            if orig.f1 != self.f1:
                print 'f1 changed'
        super(MyModel, self).save(*args, **kw)

The same thing applies when working with a form. You can detect it at the clean or save method of a ModelForm:

class MyModelForm(forms.ModelForm):

    def clean(self):
        cleaned_data = super(ProjectForm, self).clean()
        #if self.has_changed():  # new instance or existing updated (form has data to save)
        if self.instance.pk is not None:  # new instance only
            if self.instance.f1 != cleaned_data['f1']:
                print 'f1 changed'
        return cleaned_data

    class Meta:
        model = MyModel
        exclude = []

Answer 5

Since Django 1.8 released, you can use from_db classmethod to cache old value of remote_image. Then in save method you can compare old and new value of field to check if the value has changed.

@classmethod
def from_db(cls, db, field_names, values):
    new = super(Alias, cls).from_db(db, field_names, values)
    # cache value went from the base
    new._loaded_remote_image = values[field_names.index('remote_image')]
    return new

def save(self, force_insert=False, force_update=False, using=None,
         update_fields=None):
    if (self._state.adding and self.remote_image) or \
        (not self._state.adding and self._loaded_remote_image != self.remote_image):
        # If it is first save and there is no cached remote_image but there is new one, 
        # or the value of remote_image has changed - do your stuff!

Answer 6

Note that field change tracking is available in django-model-utils.

https://django-model-utils.readthedocs.org/en/latest/index.html

Answer 7

If you are using a form, you can use Form's changed_data (docs):

class AliasForm(ModelForm):

    def save(self, commit=True):
        if 'remote_image' in self.changed_data:
            # do things
            remote_image = self.cleaned_data['remote_image']
            do_things(remote_image)
        super(AliasForm, self).save(commit)

    class Meta:
        model = Alias

Answer 8

I am a bit late to the party but I found this solution also: Django Dirty Fields

Answer 9

Another late answer, but if you're just trying to see if a new file has been uploaded to a file field, try this: (adapted from Christopher Adams's comment on the link http://zmsmith.com/2010/05/django-check-if-a-field-has-changed/ in zach's comment here)

Updated link: https://web.archive.org/web/20130101010327/http://zmsmith.com:80/2010/05/django-check-if-a-field-has-changed/

def save(self, *args, **kw):
    from django.core.files.uploadedfile import UploadedFile
    if hasattr(self.image, 'file') and isinstance(self.image.file, UploadedFile) :
        # Handle FileFields as special cases, because the uploaded filename could be
        # the same as the filename that's already there even though there may
        # be different file contents.

        # if a file was just uploaded, the storage model with be UploadedFile
        # Do new file stuff here
        pass

Answer 10

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'}}

Answer 11

As of Django 1.8, there's the from_db method, as Serge mentions. In fact, the Django docs include this specific use case as an example:

https://docs.djangoproject.com/en/dev/ref/models/instances/#customizing-model-loading

Below is an example showing how to record the initial values of fields that are loaded from the database

Answer 12

This works for me in Django 1.8

def clean(self):
    if self.cleaned_data['name'] != self.initial['name']:
        # Do something

Answer 13

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

Answer 14

You can use django-model-changes to do this without an additional database lookup:

from django.dispatch import receiver
from django_model_changes import ChangesMixin

class Alias(ChangesMixin, MyBaseModel):
   # your model

@receiver(pre_save, sender=Alias)
def do_something_if_changed(sender, instance, **kwargs):
    if 'remote_image' in instance.changes():
        # do something

Answer 15

The optimal solution is probably one that does not include an additional database read operation prior to saving the model instance, nor any further django-library. This is why laffuste's solutions is preferable. In the context of an admin site, one can simply override the save_model-method, and invoke the form's has_changed method there, just as in Sion's answer above. You arrive at something like this, drawing on Sion's example setting but using changed_data to get every possible change:

class ModelAdmin(admin.ModelAdmin):
   fields=['name','mode']
   def save_model(self, request, obj, form, change):
     form.changed_data #output could be ['name']
     #do somethin the changed name value...
     #call the super method
     super(self,ModelAdmin).save_model(request, obj, form, change)

• Override save_model:

https://docs.djangoproject.com/en/1.10/ref/contrib/admin/#django.contrib.admin.ModelAdmin.save_model

• Built-in changed_data-method for a Field:

https://docs.djangoproject.com/en/1.10/ref/forms/api/#django.forms.Form.changed_data

Answer 16

While this doesn't actually answer your question, I'd go about this in a different way.

Simply clear the remote_image field after successfully saving the local copy. Then in your save method you can always update the image whenever remote_image isn't empty.

If you'd like to keep a reference to the url, you could use an non-editable boolean field to handle the caching flag rather than remote_image field itself.

Answer 17

improving @josh answer for all fields:

class Person(models.Model):
  name = models.CharField()

def __init__(self, *args, **kwargs):
    super(Person, self).__init__(*args, **kwargs)
    self._original_fields = dict([(field.attname, getattr(self, field.attname))
        for field in self._meta.local_fields if not isinstance(field, models.ForeignKey)])

def save(self, *args, **kwargs):
  if self.id:
    for field in self._meta.local_fields:
      if not isinstance(field, models.ForeignKey) and\
        self._original_fields[field.name] != getattr(self, field.name):
        # Do Something    
  super(Person, self).save(*args, **kwargs)

just to clarify, the getattr works to get fields like person.name with strings (i.e. getattr(person, "name")

Answer 18

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])

Answer 19

I had this situation before my solution was to override the pre_save() method of the target field class it will be called only if the field has been changed
useful with FileField example:

class PDFField(FileField):
    def pre_save(self, model_instance, add):
        # do some operations on your file 
        # if and only if you have changed the filefield

disadvantage:
not useful if you want to do any (post_save) operation like using the created object in some job (if certain field has changed)

Answer 20

I have extended the mixin of @livskiy as follows:

class ModelDiffMixin(models.Model):
    """
    A model mixin that tracks model fields' values and provide some useful api
    to know what fields have been changed.
    """
    _dict = DictField(editable=False)
    def __init__(self, *args, **kwargs):
        super(ModelDiffMixin, self).__init__(*args, **kwargs)
        self._initial = self._dict

    @property
    def diff(self):
        d1 = self._initial
        d2 = self._dict
        diffs = [(k, (v, d2[k])) for k, v in d1.items() if v != d2[k]]
        return dict(diffs)

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

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

    def get_field_diff(self, field_name):
        """
        Returns a diff for field if it's changed and None otherwise.
        """
        return self.diff.get(field_name, None)

    def save(self, *args, **kwargs):
        """
        Saves model and set initial state.
        """
        object_dict = model_to_dict(self,
               fields=[field.name for field in self._meta.fields])
        for field in object_dict:
            # for FileFields
            if issubclass(object_dict[field].__class__, FieldFile):
                try:
                    object_dict[field] = object_dict[field].path
                except :
                    object_dict[field] = object_dict[field].name

            # TODO: add other non-serializable field types
        self._dict = object_dict
        super(ModelDiffMixin, self).save(*args, **kwargs)

    class Meta:
        abstract = True

and the DictField is:

class DictField(models.TextField):
    __metaclass__ = models.SubfieldBase
    description = "Stores a python dict"

    def __init__(self, *args, **kwargs):
        super(DictField, self).__init__(*args, **kwargs)

    def to_python(self, value):
        if not value:
            value = {}

        if isinstance(value, dict):
            return value

        return json.loads(value)

    def get_prep_value(self, value):
        if value is None:
            return value
        return json.dumps(value)

    def value_to_string(self, obj):
        value = self._get_val_from_obj(obj)
        return self.get_db_prep_value(value)

it can be used by extending it in your models a _dict field will be added when you sync/migrate and that field will store the state of your objects

Answer 21

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.

Answer 22

How about using David Cramer's solution:

http://cramer.io/2010/12/06/tracking-changes-to-fields-in-django/

I've had success using it like this:

@track_data('name')
class Mode(models.Model):
    name = models.CharField(max_length=5)
    mode = models.CharField(max_length=5)

    def save(self, *args, **kwargs):
        if self.has_changed('name'):
            print 'name changed'

    # OR #

    @classmethod
    def post_save(cls, sender, instance, created, **kwargs):
        if instance.has_changed('name'):
            print "Hooray!"

Answer 23

A modification to @ivanperelivskiy's answer:

@property
def _dict(self):
    ret = {}
    for field in self._meta.get_fields():
        if isinstance(field, ForeignObjectRel):
            # foreign objects might not have corresponding objects in the database.
            if hasattr(self, field.get_accessor_name()):
                ret[field.get_accessor_name()] = getattr(self, field.get_accessor_name())
            else:
                ret[field.get_accessor_name()] = None
        else:
            ret[field.attname] = getattr(self, field.attname)
    return ret

This uses django 1.10's public method get_fields instead. This makes the code more future proof, but more importantly also includes foreign keys and fields where editable=False.

For reference, here is the implementation of .fields

@cached_property
def fields(self):
    """
    Returns a list of all forward fields on the model and its parents,
    excluding ManyToManyFields.

    Private API intended only to be used by Django itself; get_fields()
    combined with filtering of field properties is the public API for
    obtaining this field list.
    """
    # For legacy reasons, the fields property should only contain forward
    # fields that are not private or with a m2m cardinality. Therefore we
    # pass these three filters as filters to the generator.
    # The third lambda is a longwinded way of checking f.related_model - we don't
    # use that property directly because related_model is a cached property,
    # and all the models may not have been loaded yet; we don't want to cache
    # the string reference to the related_model.
    def is_not_an_m2m_field(f):
        return not (f.is_relation and f.many_to_many)

    def is_not_a_generic_relation(f):
        return not (f.is_relation and f.one_to_many)

    def is_not_a_generic_foreign_key(f):
        return not (
            f.is_relation and f.many_to_one and not (hasattr(f.remote_field, 'model') and f.remote_field.model)
        )

    return make_immutable_fields_list(
        "fields",
        (f for f in self._get_fields(reverse=False)
         if is_not_an_m2m_field(f) and is_not_a_generic_relation(f) and is_not_a_generic_foreign_key(f))
    )

Answer 24

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:"