Suppose you have the following models
class User:
pass
class Tag:
pass
class UserTag: # user is interested in tag
user = models.ForeignKey(User)
tag = models.ForeignKey(Tag)
class Blog:
tags = models.ManyToManyField(Tag)
For a given user, I want to get all blogs that user expressed his interests by UserTag
something like
Blog.objects.filter(tags__usertag_set__user=user_id)
I can do this in multiple steps but is it the best way to do it?
user_tags = UserTag.objects.filter(user=user)
result = Blog.objects.none()
for user_tag in user_tags:
tag = user_tag.tag
q = tag.blog_set.all()
result = result | q
This inevitably iterates all user_tags and bad...
you can do
user_tags = list(UserTag.objects.filter(creator=user).values_list('id', flat=True))
Blog.objects.filter(tags__in=user_tag)
Related
I have the following models:
## Tags for issues
class issueTags(models.Model):
name = models.CharField(max_length=400)
class issues(models.Model):
tags = models.ManyToManyField(issueTags,blank = True)
In my view I get an array from some client side JavaScript i.e.
(Pdb) array_data = request.POST['arr']
(Pdb) array_data
'["2","3"]'
How should I filter my issues object to find all issues which match all tags in the array? (the 2,3 are the ID values for tag__id.
If there is a better way to arrange the objects that would also work so I can search in this fashion.
At the time of writing this, the existing answers are either incorrect (e.g. filtering matching all Issues that have any of the specified tags and the correct tag count) or inefficient (e.g. attaching filters in a loop).
For the following models:
class IssueTag(models.Model):
name = models.CharField(max_length=400, blank=True)
class Issue(models.Model):
label = models.CharField(max_length=50, blank=True)
tags = models.ManyToManyField(IssueTag, related_name='issues')
I suggest using Django Annotation in conjunction with a filter like so:
from django.db.models import Count, Q
tags_to_match = ['tag1', 'tag2']
issues_containing_all_tags = Issue.objects \
.annotate(num_correct_tags=Count('tags',
filter=Q(tags__name__in=tags_to_match))) \
.filter(num_correct_tags=2)
to get all Issues that have all required tags (but may have additional tags, as is required in the question).
This will produce the following SQL query, that resolves all tag matching in a single IN clause:
SELECT "my_app_issue"."id", "my_app_issue"."label",
COUNT("my_app_issue_tags"."issuetag_id")
FILTER (WHERE "my_app_issuetag"."name" IN ('tag1', 'tag2'))
AS "num_correct_tags"
FROM "my_app_issue"
LEFT OUTER JOIN "my_app_issue_tags" ON ("my_app_issue"."id" = "my_app_issue_tags"."issue_id")
LEFT OUTER JOIN "my_app_issuetag" ON ("my_app_issue_tags"."issuetag_id" = "my_app_issuetag"."id")
GROUP BY "my_app_issue"."id", "my_app_issue"."label"
HAVING COUNT("my_app_issue_tags"."issuetag_id")
FILTER (WHERE ("my_app_issuetag"."name" IN ('tag1', 'tag2'))) = 2;
args=('tag1', 'tag2', 'tag1', 'tag2', 2)
I haven't tested this, but I think you could do the following:
from django.db.models import Q
array_data = array_data.split(',')
issues.objects.filter(
tags__in=array_data,
).exclude(
# Exclude any that aren't in array_data
~Q(tags__in=array_data)
).annotate(
matches=Count(tags, distinct=True)
).filter(
# Make sure the number found is right.
matches=len(array_data)
)
FYI, you should be using Issue, IssueTag for your model names to follow Django's naming pattern.
It isn't most elegant solution or pythonic but I ended up just looping around the resulting filter.
def filter_on_category(issue_object,array_of_tags):
#keep filtering to make an and
i = 0
current_filter = issue_object
while (i < (len(array_of_tags))):
#lets filter again
current_filter=current_filter.filter(tags__id__in=array_of_tags[i])
i=i+1
return current_filter
Django field lookups argument (__) for many-to-many fields needs list argument. I have created a dummy list for each array element of IssueTags and pass it to lookups argument and it works as expected.
Let you have this models:
class IssueTags(models.Model):
name = models.CharField(max_length=400)
class Issues(models.Model):
tags = models.ManyToManyField(IssueTags,blank = True)
You want to get Issues which contains all of these IssueTags = ["1","2","3"]
issue_tags_array = ["1","2","3"]
#First initialize queryset
queryset = Issues.objects.all()
i = 0
while i < len(issue_tags_array):
#dummy issue_tag list
issue_tag = [issue_tags_array[i]]
#lets filter again
queryset = queryset.filter(tags__id__in=issue_tag)
i=i+1
return queryset
My models are:
models.User:
id = pk
username = text
models.Offer
id = pk
description = text
publicationDate = Date
user = Fk(User)
my serializer is:
class UserOfferSerializer(ModelSerializer):
offers = OfferSerializerAll(many=True, read_only=True)
class Meta:
model = User
fields = ('id', 'username', 'offers')
I am trying to apply more than one filter on the queryset:
users = users.filter(offers__publicationDate__range=[startdate, enddate]). prefetch_related(Prefetch('offers', queryset=Offer.objects.filter(
publicationDate__range=[startdate, enddate]))).distinct()
then
users = users.filter(offers__description__icontains=sometext).prefetch_related(Prefetch('offers', queryset=Offer.objects.filter(description__icontains=sometext))).distinct()
First one works fine and the other one throws the following exception:
ValueError: 'offers' lookup was already seen with a different queryset. You may need to adjust the ordering of your lookups.
Update:
My current code is:
if (offerBeginDate != None and offerEndDate != None):
b = offerBeginDate.split('-')
e = offerEndDate.split('-')
startdate = datetime.date(int(b[0]), int(b[1]), int(b[2]))
enddate = datetime.date(int(e[0]), int(e[1]), int(e[2]))
users = users.filter(offers__publicationDate__range=[startdate, enddate])
offers = offers.filter(publicationDate__range=[startdate, enddate])
if (descriptionText != None):
users = users.filter(offers__functionDescription__icontains=descriptionText.strip())
offers = offers.filter(functionDescription__icontains=descriptionText.strip())
users = users.prefetch_related('offers', Prefetch(queryset=offers))
Any help? Thank you all :)))
You can use to_attr argument of Prefetch object to prefetch additional queryset:
users = users.filter(offers__description__icontains=sometext).prefetch_related(
Prefetch('offers', queryset=Offer.objects.filter(
publicationDate__range=[startdate, enddate]), to_attr='date_offers'),
Prefetch('offers', queryset=Offer.objects.filter(description__icontains=sometext), to_attr='description_offers')).distinct()
UPD
If you need dynamically add filters to prefetched queryset you can define it separately like this:
if some_case:
users = users.filter(offers__description__icontains=sometext)
offers=Offer.objects.filter(description__icontains=sometext)
if some_case_2:
users = users.filter(**conditions)
offers = offers.filter(**conditions)
users = users.prefetch_related(Prefetch('offers', queryset=offers))
Now each user in users queryset will have two attributes: user.date_offers and user.description_offers.
I have a simple Relation model, where a user can follow a tag just like stackoverflow.
class Relation(models.Model):
user = AutoOneToOneField(User)
follows_tag = models.ManyToManyField(Tag, blank=True, null=True, through='TagRelation')
class TagRelation(models.Model):
user = models.ForeignKey(Relation, on_delete=models.CASCADE)
following_tag = models.ForeignKey(Tag, on_delete=models.CASCADE)
pub_date = models.DateTimeField(default=timezone.now)
class Meta:
unique_together = ['user', 'following_tag']
Now, to get the results of all the tags a user is following:
kakar = CustomUser.objects.get(email="kakar#gmail.com")
tags_following = kakar.relation.follows_tag.all()
This is fine.
But, to access intermediate fields I have to go through a big list of other queries. Suppose I want to display when the user started following a tag, I will have to do something like this:
kakar = CustomUser.objects.get(email="kakar#gmail.com")
kakar_relation = Relation.objects.get(user=kakar)
t1 = kakar.relation.follows_tag.all()[0]
kakar_t1_relation = TagRelation.objects.get(user=kakar_relation, following_tag=t1)
kakar_t1_relation.pub_date
As you can see, just to get the date I have to go through so much query. Is this the only way to get intermediate values, or this can be optimized? Also, I am not sure if this model design is the way to go, so if you have any recomendation or advice I would be very grateful. Thank you.
You need to use Double underscore i.e. ( __ ) for ForeignKey lookup,
Like this :
user_tags = TagRelation.objects.filter(user__user__email="kakar#gmail.com").values("following_tag__name", "pub_date")
If you need the name of the tag, you can use following_tag__name in the query and if you need id you can use following_tag__id.
And for that you need to iterate through the result of above query set, like this:
for items in user_tags:
print items['following_tag__name']
print items['pub_date']
One more thing,The key word values will return a list of dictionaries and you can iterate it through above method and if you are using values_list in the place of values, it will return a list of tuples. Read further from here .
I want to build an webapp like Quora or Medium, where a user can follow users or some topics.
eg: userA is following (userB, userC, tag-Health, tag-Finance).
These are the models:
class Relationship(models.Model):
user = AutoOneToOneField('auth.user')
follows_user = models.ManyToManyField('Relationship', related_name='followed_by')
follows_tag = models.ManyToManyField(Tag)
class Activity(models.Model):
actor_type = models.ForeignKey(ContentType, related_name='actor_type_activities')
actor_id = models.PositiveIntegerField()
actor = GenericForeignKey('actor_type', 'actor_id')
verb = models.CharField(max_length=10)
target_type = models.ForeignKey(ContentType, related_name='target_type_activities')
target_id = models.PositiveIntegerField()
target = GenericForeignKey('target_type', 'target_id')
tags = models.ManyToManyField(Tag)
Now, this would give the following list:
following_user = userA.relationship.follows_user.all()
following_user
[<Relationship: userB>, <Relationship: userC>]
following_tag = userA.relationship.follows_tag.all()
following_tag
[<Tag: tag-job>, <Tag: tag-finance>]
To filter I tried this way:
Activity.objects.filter(Q(actor__in=following_user) | Q(tags__in=following_tag))
But since actor is a GenericForeignKey I am getting an error:
FieldError: Field 'actor' does not generate an automatic reverse relation and therefore cannot be used for reverse querying. If it is a GenericForeignKey, consider adding a GenericRelation.
How can I filter the activities that will be unique, with the list of users and list of tags that the user is following? To be specific, how will I filter GenericForeignKey with the list of the objects to get the activities of the following users.
You should just filter by ids.
First get ids of objects you want to filter on
following_user = userA.relationship.follows_user.all().values_list('id', flat=True)
following_tag = userA.relationship.follows_tag.all()
Also you will need to filter on actor_type. It can be done like this for example.
actor_type = ContentType.objects.get_for_model(userA.__class__)
Or as #Todor suggested in comments. Because get_for_model accepts both model class and model instance
actor_type = ContentType.objects.get_for_model(userA)
And than you can just filter like this.
Activity.objects.filter(Q(actor_id__in=following_user, actor_type=actor_type) | Q(tags__in=following_tag))
What the docs are suggesting is not a bad thing.
The problem is that when you are creating Activities you are using auth.User as an actor, therefore you can't add GenericRelation to auth.User (well maybe you can by monkey-patching it, but that's not a good idea).
So what you can do?
#Sardorbek Imomaliev solution is very good, and you can make it even better if you put all this logic into a custom QuerySet class. (the idea is to achieve DRY-ness and reausability)
class ActivityQuerySet(models.QuerySet):
def for_user(self, user):
return self.filter(
models.Q(
actor_type=ContentType.objects.get_for_model(user),
actor_id__in=user.relationship.follows_user.values_list('id', flat=True)
)|models.Q(
tags__in=user.relationship.follows_tag.all()
)
)
class Activity(models.Model):
#..
objects = ActivityQuerySet.as_manager()
#usage
user_feed = Activity.objects.for_user(request.user)
but is there anything else?
1. Do you really need GenericForeignKey for actor? I don't know your business logic, so probably you do, but using just a regular FK for actor (just like for the tags) will make it possible to do staff like actor__in=users_following.
2. Did you check if there isn't an app for that? One example for a package already solving your problem is django-activity-steam check on it.
3. IF you don't use auth.User as an actor you can do exactly what the docs suggest -> adding a GenericRelation field. In fact, your Relationship class is suitable for this purpose, but I would really rename it to something like UserProfile or at least UserRelation. Consider we have renamed Relation to UserProfile and we create new Activities using userprofile instead. The idea is:
class UserProfile(models.Model):
user = AutoOneToOneField('auth.user')
follows_user = models.ManyToManyField('UserProfile', related_name='followed_by')
follows_tag = models.ManyToManyField(Tag)
activies_as_actor = GenericRelation('Activity',
content_type_field='actor_type',
object_id_field='actor_id',
related_query_name='userprofile'
)
class ActivityQuerySet(models.QuerySet):
def for_userprofile(self, userprofile):
return self.filter(
models.Q(
userprofile__in=userprofile.follows_user.all()
)|models.Q(
tags__in=userprofile.relationship.follows_tag.all()
)
)
class Activity(models.Model):
#..
objects = ActivityQuerySet.as_manager()
#usage
#1st when you create activity use UserProfile
Activity.objects.create(actor=request.user.userprofile, ...)
#2nd when you fetch.
#Check how `for_userprofile` is implemented this time
Activity.objects.for_userprofile(request.user.userprofile)
As stated in the documentation:
Due to the way GenericForeignKey is implemented, you cannot use such fields directly with filters (filter() and exclude(), for example) via the database API. Because a GenericForeignKey isn’t a normal field object, these examples will not work:
You could follow what the error message is telling you, I think you'll have to add a GenericRelation relation to do that. I do not have experience doing that, and I'd have to study it but...
Personally I think this solution is too complex to what you're trying to achieve. If only the user model can follow a tag or authors, why not include a ManyToManyField on it. It would be something like this:
class Person(models.Model):
user = models.ForeignKey(User)
follow_tag = models.ManyToManyField('Tag')
follow_author = models.ManyToManyField('Author')
You could query all followed tag activities per Person like this:
Activity.objects.filter(tags__in=person.follow_tag.all())
And you could search 'persons' following a tag like this:
Person.objects.filter(follow_tag__in=[<tag_ids>])
The same would apply to authors and you could use querysets to do OR, AND, etc.. on your queries.
If you want more models to be able to follow a tag or author, say a System, maybe you could create a Following model that does the same thing Person is doing and then you could add a ForeignKey to Follow both in Person and System
Note that I'm using this Person to meet this recomendation.
You can query seperately for both usrs and tags and then combine them both to get what you are looking for. Please do something like below and let me know if this works..
usrs = Activity.objects.filter(actor__in=following_user)
tags = Activity.objects.filter(tags__in=following_tag)
result = usrs | tags
You can use annotate to join the two primary keys as a single string then use that to filter your queryset.
from django.db.models import Value, TextField
from django.db.models.functions import Concat
following_actor = [
# actor_type, actor
(1, 100),
(2, 102),
]
searchable_keys = [str(at) + "__" + str(actor) for at, actor in following_actor]
result = MultiKey.objects.annotate(key=Concat('actor_type', Value('__'), 'actor_id',
output_field=TextField()))\
.filter(Q(key__in=searchable_keys) | Q(tags__in=following_tag))
I have the following query:
prefetch = Prefetch('books', queryset=Book.objects.filter(is_published=True),
to_attr='published_books')
profiles = Profile.objects.prefetch_related(prefetch)
This selects all profiles and populates them with published books.
However, I want only profiles, that actually have published books (in other words len(profile.published_books) > 0).
How can I achieve it in orm?
UPDATE:
class Book(Model):
profile = ForeignKey(Profile, related_name="books", related_query_name="book")
name = CharField(max_length=250)
is_published = BooleanField(default=True)
class Meta:
unique_together = (('profile', 'name'),)
profile_ids = Profile.objects.filter(book__is_published=True).values_list("pk", flat=True).distinct()
profiles = Profile.objects.filter(pk__in=profile_ids).prefetch_related(prefetch)
this will result a subquery that locate correct profile ids and then return any profile that match one of these ids.
use of distinct function has no effect on result but I am guessing it could improve performance (not really sure)