Update Django Haystack search index for prepared field - django

I'm using Django Haystack.
Here is my code:
settings.py
HAYSTACK_CONNECTIONS = {
'default': {
'ENGINE': 'haystack.backends.elasticsearch_backend.ElasticsearchSearchEngine',
'URL': 'http://127.0.0.1:9200/',
'INDEX_NAME': 'haystack',
},
}
HAYSTACK_SIGNAL_PROCESSOR = 'haystack.signals.RealtimeSignalProcessor'
search_indexes.py
class PostIndex(indexes.SearchIndex, indexes.Indexable):
text = indexes.CharField(document=True, use_template=True)
owner = indexes.CharField(model_attr='owner')
image_url = indexes.CharField()
def get_model(self):
return Post
def prepare_image_url(self, obj):
# Get first images for resulted search objects
return [image.image_main_page.url for image in obj.images.order_by('id')[:1]]
def index_queryset(self, using=None):
"""Used when the entire index for model is updated."""
return self.get_model().objects.all()
As you see I use RealtimeSignalProcessor to make it index on Post instance creation or update. And it actually does index the instance on creation except image_url field which is using prepare method. It indexed though on instance update.
Question is why it isn't being indexed on creation?
Any pointers are appreciated.

I ended up with custom signal processor like so:
class RelatedRealtimeSignalProcessor(RealtimeSignalProcessor):
"""
Extension to haystack's RealtimeSignalProcessor not only causing the
search_index to update on saved model, but also for image url, which is needed to show
images on search results
"""
def handle_save(self, sender, instance, **kwargs):
if hasattr(instance, 'reindex_related'):
for related in instance.reindex_related:
related_obj = getattr(instance, related)
self.handle_save(related_obj.__class__, related_obj)
return super(RelatedRealtimeSignalProcessor, self).handle_save(sender, instance, **kwargs)
def handle_delete(self, sender, instance, **kwargs):
if hasattr(instance, 'reindex_related'):
for related in instance.reindex_related:
related_obj = getattr(instance, related)
self.handle_delete(related_obj.__class__, related_obj)
return super(RelatedRealtimeSignalProcessor, self).handle_delete(sender, instance, **kwargs)
And pointed to it in settings:
HAYSTACK_SIGNAL_PROCESSOR = 'your_app.signals.RelatedRealtimeSignalProcessor'

Related

How to save checkbox values to Django database from admin panel?

In the Django admin panel, all fields are saved to the database, except for the flags field of the SubscriberPlan model. That is, I can (un)check any flag and try to thus update a record, but the flag statuses won't be saved to the database.
If I run python manage.py shell, import SubscriberPlan, do something like
plan = SubscriberPlan.objects.all()[0],
plan.flags = "a"
plan.save()
then the database will be updated and the Active flag will be displayed in the Admin panel, but, still, it won't be possible to update it from the Admin panel.
So, how is it possible in Django to save this kind of a field to the database from the Admin panel? To be honest, I don't understand why it's not saved by default, while other fields are saved. It seems that the Admin panel, for some reason, doesn't pass the checkmark values in its form.
admin.py
from django.contrib import admin
from django.utils.safestring import mark_safe
class SubscriberPlanFlagsWidget(forms.Widget):
available_flags = (
('a', ('Active')),
('n', ('New')),
('p', ('Popular')),
def render(self, name, value, attrs=None, renderer=None):
html = []
for f in self.available_flags:
html.append('<li><input type="checkbox" id="flag_%(key)s" %(checked)s key="%(key)s"/><label for="flag_%(key)s">%(name)s</label></li>' % {
'key': f[0], 'name': f[1], 'checked': 'checked' if f[0] in value.lower() else ''})
html = '<input type="hidden" name="%s" value="%s"/><ul class="checkbox flags">%s</ul>' % (name, value, ''.join(html))
return mark_safe(html)
class SubscriberPlanAdmin(admin.ModelAdmin):
def formfield_for_dbfield(self, db_field, **kwargs):
if db_field.name == 'flags':
kwargs['widget'] = SubscriberPlanFlagsWidget
return super(SubscriberPlanAdmin, self).formfield_for_dbfield(db_field, **kwargs)
models.py
from django.db import models
class SubscriberPlan(models.Model):
name = models.CharField(max_length=50, verbose_name=("Name"))
price = models.DecimalField(max_digits=15, decimal_places=2,
verbose_name=("Price"))
flags = models.CharField(max_length=30, verbose_name=("Flags"),
default='', blank=True)
def _check_flag(self, name):
return name in self.flags.lower()
def active(self):
return self._check_flag('a')
def new(self):
return self._check_flag('n')
def popular(self):
return self._check_flag('p')
Your widget's render method translates the flags field into checkboxes on the form, but when the form is submitted you need to go the other direction, and translate the checkboxes back into flags. The widget doesn't know how to do that automatically. From looking at the django source code and the docs, you need to override the value_from_datadict method. Give this a try:
class SubscriberPlanFlagsWidget(forms.Widget):
...
def value_from_datadict(self, data, files, name):
value = ''
for f in self.available_flags:
if f[1] in data:
value += f[0]
return value

Get Django CMS plugin information from Haystack search results

My search results page needs to display information about the Plugins where the query was found, too. I found this question with a similar problem, but I don't only need the contents, I need to know stuff about the plugin - i.e. what's it called, where it is on the page and stuff. Basically I would like a reference to the plugin where the query was located, but I can only find information about the page and title. I haven't been able to find it anywhere on the SearchQuerySet object and in the vicinity - also coming up empty in the documentation for Haystack. Is it possible and how?
Stack I'm using: Elasticsearch 2.4, django-haystack 2.8, aldryn-search 1.0 (for CMS indexing).
I ended up writing a new index for CMSPlugins. Not sure how much use my code is, but maybe it'll help someone out.
from django.conf import settings
from aldryn_search.helpers import get_plugin_index_data
from aldryn_search.utils import clean_join, get_index_base
from cms.models import CMSPlugin
class CMSPluginIndex(get_index_base()):
haystack_use_for_indexing = True
index_title = True
object_actions = ('publish', 'unpublish')
def get_model(self):
return CMSPlugin
def get_index_queryset(self, language):
return CMSPlugin.objects.select_related(
'placeholder'
).prefetch_related(
'placeholder__page_set'
).filter(
placeholder__page__publisher_is_draft=False,
language=language
).exclude(
plugin_type__in=settings.HAYSTACK_EXCLUDED_PLUGINS
).distinct()
def get_search_data(self, obj, language, request):
current_page = obj.placeholder.page
text_bits = []
plugin_text_content = self.get_plugin_search_text(obj, request)
text_bits.append(plugin_text_content)
page_meta_description = current_page.get_meta_description(fallback=False, language=language)
if page_meta_description:
text_bits.append(page_meta_description)
page_meta_keywords = getattr(current_page, 'get_meta_keywords', None)
if callable(page_meta_keywords):
text_bits.append(page_meta_keywords())
return clean_join(' ', text_bits)
def get_plugin_search_text(self, base_plugin, request):
plugin_content_bits = get_plugin_index_data(base_plugin, request)
return clean_join(' ', plugin_content_bits)
def prepare_pub_date(self, obj):
return obj.placeholder.page.publication_date
def prepare_login_required(self, obj):
return obj.placeholder.page.login_required
def get_url(self, obj):
parent_obj = self.ancestors_queryset(obj).first()
if not parent_obj:
return obj.placeholder.page.get_absolute_url()
return # however you get the URL in your project
def get_page_title_obj(self, obj):
return obj.placeholder.page.title_set.get(
publisher_is_draft=False,
language=obj.language
)
def ancestors_queryset(self, obj):
return obj.get_ancestors().filter(
plugin_type=# Some plugins that I wanted to find
).order_by(
'-depth'
)
def get_title(self, obj):
parent_obj = self.ancestors_queryset(obj).first()
if not parent_obj:
return self.get_page_title_obj(obj).title
return # get title from parent obj if you want to
def prepare_site_id(self, obj):
return obj.placeholder.page.node.site_id
def get_description(self, obj):
return self.get_page_title_obj(obj).meta_description or None
If you are using aldryn-search, you only need to define in PLACEHOLDERS_SEARCH_LIST all the placeholders you want to check, therefore all plugins inside will be checked:
PLACEHOLDERS_SEARCH_LIST = {
'*': {
'include': ['content'],
'exclude': [''],
},
}

Django Admin prevent delete on last record

I'm new to django and learning as I go.
I have a model that must have 1 record, therefore I want to prevent delete for the last record.
model.py
class SliderContent (models.Model):
name = models.CharField(max_length=40)
image = models.ImageField(upload_to='image')
I tried the following in admin.py
class SliderContentAdmin(admin.ModelAdmin):
.....
def delete_model(self, request, obj):
if last_record:
storage = messages.get_messages(request)
storage.used = True
messages.error(request, 'Cannot delete last record.')
else:
obj.delete()
This didn't work, I have also looked at a pre_delete receiver but from what I have read this won't work as I'm using the build in Admin views.
What is the best way to do this?
Override the has_delete_permission() method:
from django.contrib.admin import helpers
class SliderContentAdmin(admin.ModelAdmin):
min_objects = 1
def has_delete_permission(self, request, obj):
queryset = self.model.objects.all()
# If we're running the bulk delete action, estimate the number
# of objects after we delete the selected items
selected = request.POST.getlist(helpers.ACTION_CHECKBOX_NAME)
if selected:
queryset = queryset.exclude(pk__in=selected)
if queryset.count() <= self.min_objects:
message = 'There should be at least {} object(s) left.'
self.message_user(request, message.format(self.min_objects))
return False
return super(SliderContentAdmin, self).has_delete_permission(request, obj)

A Category model which creates proxy models for related model admin

So I'm having a bit of trouble with trying to create a model that will define dynamic proxy models that manage a related model in the admin site. I know that sentence was confusing, so I'll just share my code instead.
models.py
class Cateogry(models.Model):
name = models.CharField(...)
class Tag(models.Model):
name = models.CharField(...)
category = models.ForeignKey(Cateogry)
What I want to achieve is that in the admin site, instead of having one ModelAdmin for the Tag model, for each category I will have a modeladmin for all related tags. I have achieved this using this answer. Say I have a category named A:
def create_modeladmin(modeladmin, model, name = None):
class Meta:
proxy = True
app_label = model._meta.app_label
attrs = {'__module__': '', 'Meta': Meta}
newmodel = type(name, (model,), attrs)
admin.site.register(newmodel, modeladmin)
return modeladmin
class CatA(TagAdmin):
def queryset(self, request):
qs = super(CatA, self).queryset(request)
return qs.filter(cateogry = Cateogry.objects.filter(name='A'))
create_modeladmin(CatA, name='CategoryAtags', model=Tag)
But this is not good enough, because obviously I still need to manually subclass the TagAdmin model and then run create_modeladmin. What I need to do, is loop over all Category objects, for each one create a dynamic subclass for Tagadmin (named after the category), then create a dynamic proxy model from that, and this is where my head starts spinning.
for cat in Category.objects.all():
NewSubClass = #somehow create subclass of TagAdmin, the name should be '<cat.name>Admin' instead of NewSubClass
create_modeladmin(NewSubClass, name=cat.name, model=Tag)
Any guidance or help would be much appreciated
Dynamic ModelAdmins don't work well together with the way admin registeres models.
I suggest to create subviews in the CategoryAdmin.
from django.conf.urls import patterns, url
from django.contrib import admin
from django.contrib.admin.options import csrf_protect_m
from django.contrib.admin.util import unquote
from django.core.urlresolvers import reverse
from demo_project.demo.models import Category, Tag
class TagAdmin(admin.ModelAdmin):
# as long as the CategoryTagAdmin class has no custom change_list template
# there needs to be a default admin for Tags
pass
admin.site.register(Tag, TagAdmin)
class CategoryTagAdmin(admin.ModelAdmin):
""" A ModelAdmin invoked by a CategoryAdmin"""
read_only_fields = ('category',)
def __init__(self, model, admin_site, category_admin, category_id):
self.model = model
self.admin_site = admin_site
self.category_admin = category_admin
self.category_id = category_id
super(CategoryTagAdmin, self).__init__(model, admin_site)
def queryset(self, request):
return super(CategoryTagAdmin, self).queryset(request).filter(category=self.category_id)
class CategoryAdmin(admin.ModelAdmin):
list_display = ('name', 'tag_changelist_link')
def tag_changelist_link(self, obj):
info = self.model._meta.app_label, self.model._meta.module_name
return '<a href="%s" >Tags</a>' % reverse('admin:%s_%s_taglist' % info, args=(obj.id,))
tag_changelist_link.allow_tags = True
tag_changelist_link.short_description = 'Tags'
#csrf_protect_m
def tag_changelist(self, request, *args, **kwargs):
obj_id = unquote(args[0])
info = self.model._meta.app_label, self.model._meta.module_name
category = self.get_object(request, obj_id)
tag_admin = CategoryTagAdmin(Tag, self.admin_site, self, category_id=obj_id )
extra_context = {
'parent': {
'has_change_permission': self.has_change_permission(request, obj_id),
'opts': self.model._meta,
'object': category,
},
}
return tag_admin.changelist_view(request, extra_context)
def get_urls(self):
info = self.model._meta.app_label, self.model._meta.module_name
urls= patterns('',
url(r'^(.+)/tags/$', self.admin_site.admin_view(self.tag_changelist), name='%s_%s_taglist' % info )
)
return urls + super(CategoryAdmin, self).get_urls()
admin.site.register(Category, CategoryAdmin)
The items in the categories changelist have an extra column with a link made by the tag_changelist_link pointing to the CategoryAdmin.tag_changelist. This method creates a CategoryTagAdmin instance with some extras and returns its changelist_view.
This way you have a filtered tag changelist on every category. To fix the breadcrumbs of the tag_changelist view you need to set the CategoryTagAdmin.change_list_template to a own template that {% extends 'admin/change_list.html' %} and overwrites the {% block breadcrumbs %}. That is where you will need the parent variable from the extra_context to create the correct urls.
If you plan to implement a tag_changeview and tag_addview method you need to make sure that the links rendered in variouse admin templates point to the right url (e.g. calling the change_view with a form_url as paramter).
A save_model method on the CategoryTagAdmin can set the default category when adding new tags.
def save_model(self, request, obj, form, change):
obj.category_id = self.category_id
super(CategoryTagAdmin, self).__init__(request, obj, form, change)
If you still want to stick to the apache restart aproach ... Yes you can restart Django. It depends on how you are deploying the instance.
On an apache you can touch the wsgi file that will reload the instance os.utime(path/to/wsgi.py.
When using uwsgi you can use uwsgi.reload().
You can check the source code of Rosetta how they are restarting the instance after the save translations (views.py).
So I found a half-solution.
def create_subclass(baseclass, name):
class Meta:
app_label = 'fun'
attrs = {'__module__': '', 'Meta': Meta, 'cat': name }
newsub = type(name, (baseclass,), attrs)
return newsub
class TagAdmin(admin.ModelAdmin):
list_display = ('name', 'category')
def get_queryset(self, request):
return Tag.objects.filter(category = Category.objects.filter(name=self.cat))
for cat in Category.objects.all():
newsub = create_subclass(TagAdmin, str(cat.name))
create_modeladmin(newsub, model=Tag, name=str(cat.name))
It's working. But every time you add a new category, you need to refresh the server before it shows up (because admin.py is evaluated at runtime). Does anyone know a decent solution to this?

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

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?
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
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.
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
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 = []
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!
Note that field change tracking is available in django-model-utils.
https://django-model-utils.readthedocs.org/en/latest/index.html
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
I am a bit late to the party but I found this solution also:
Django Dirty Fields
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
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'}}
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
This works for me in Django 1.8
def clean(self):
if self.cleaned_data['name'] != self.initial['name']:
# Do something
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
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
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
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.
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)
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
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")
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.
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!"
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))
)
as an extension of SmileyChris' answer, you can add a datetime field to the model for last_updated, and set some sort of limit for the max age you'll let it get to before checking for a change
The mixin from #ivanlivski is great.
I've extended it to
Ensure it works with Decimal fields.
Expose properties to simplify usage
The updated code is available here:
https://github.com/sknutsonsf/python-contrib/blob/master/src/django/utils/ModelDiffMixin.py
To help people new to Python or Django, I'll give a more complete example.
This particular usage is to take a file from a data provider and ensure the records in the database reflect the file.
My model object:
class Station(ModelDiffMixin.ModelDiffMixin, models.Model):
station_name = models.CharField(max_length=200)
nearby_city = models.CharField(max_length=200)
precipitation = models.DecimalField(max_digits=5, decimal_places=2)
# <list of many other fields>
def is_float_changed (self,v1, v2):
''' Compare two floating values to just two digit precision
Override Default precision is 5 digits
'''
return abs (round (v1 - v2, 2)) > 0.01
The class that loads the file has these methods:
class UpdateWeather (object)
# other methods omitted
def update_stations (self, filename):
# read all existing data
all_stations = models.Station.objects.all()
self._existing_stations = {}
# insert into a collection for referencing while we check if data exists
for stn in all_stations.iterator():
self._existing_stations[stn.id] = stn
# read the file. result is array of objects in known column order
data = read_tabbed_file(filename)
# iterate rows from file and insert or update where needed
for rownum in range(sh.nrows):
self._update_row(sh.row(rownum));
# now anything remaining in the collection is no longer active
# since it was not found in the newest file
# for now, delete that record
# there should never be any of these if the file was created properly
for stn in self._existing_stations.values():
stn.delete()
self._num_deleted = self._num_deleted+1
def _update_row (self, rowdata):
stnid = int(rowdata[0].value)
name = rowdata[1].value.strip()
# skip the blank names where data source has ids with no data today
if len(name) < 1:
return
# fetch rest of fields and do sanity test
nearby_city = rowdata[2].value.strip()
precip = rowdata[3].value
if stnid in self._existing_stations:
stn = self._existing_stations[stnid]
del self._existing_stations[stnid]
is_update = True;
else:
stn = models.Station()
is_update = False;
# object is new or old, don't care here
stn.id = stnid
stn.station_name = name;
stn.nearby_city = nearby_city
stn.precipitation = precip
# many other fields updated from the file
if is_update == True:
# we use a model mixin to simplify detection of changes
# at the cost of extra memory to store the objects
if stn.has_changed == True:
self._num_updated = self._num_updated + 1;
stn.save();
else:
self._num_created = self._num_created + 1;
stn.save()
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.