I have a SQLAlchemy model:
class Ticket(db.Model):
__tablename__ = 'ticket'
id = db.Column(INTEGER(unsigned=True), primary_key=True, nullable=False,
autoincrement=True)
cluster = db.Column(db.VARCHAR(128))
#classmethod
def get(cls, cluster=None):
query = db.session.query(Ticket)
if cluster is not None:
query = query.filter(Ticket.cluster==cluster)
return query.one()
If I add a new column and would like to extend the get method, I have to add one if xxx is not None like this below:
#classmethod
def get(cls, cluster=None, user=None):
query = db.session.query(Ticket)
if cluster is not None:
query = query.filter(Ticket.cluster==cluster)
if user is not None:
query = query.filter(Ticket.user==user)
return query.one()
Is there any way I could make this more efficient? If I have too many columns, the get method would become so ugly.
As always, if you don't want to write something repetitive, use a loop:
#classmethod
def get(cls, **kwargs):
query = db.session.query(Ticket)
for k, v in kwargs.items():
query = query.filter(getattr(table, k) == v)
return query.one()
Because we're no longer setting the cluster=None/user=None as defaults (but instead depending on things that weren't specified by the caller simply never being added to kwargs), we no longer need to prevent filters for null values from being added: The only way a null value will end up in the argument list is if the user actually asked to search for a value of None; so this new code is able to honor that request should it ever take place.
If you prefer to retain the calling convention where cluster and user can be passed positionally (but the user can't search for a value of None), see the initial version of this answer.
(Django 2.0, Python 3.6, Django Rest Framework 3.8)
I'm trying to override Django's save() method to post multiple instances when a single instance is created. I have a loop that changes the unique_id which I have saved as a randomly generated string, and the datetime value which is updated through another function called onDay().
My thinking was, that if I changed the unique_id each time I looped around, Django would save the instance as a new instance in the database. But, I keep getting back an infinite recursion error when I run it though. When I checked it with pdb.set_trace(), everything does what it's supposed to until I hit the save() value in the for loop. Once that happens, I just get taken back to the line if self.recurrent_type == "WEEKLY":.
I've used super() in a similar way (without looping) to override the save() function for a separate model, and it worked as expected. I think there's just something I'm misunderstanding about the super() function.
Here is what I have so far:
Overriding save()
def save(self, *args, **kwargs):
if not self.pk: # if there is not yet a pk for it
# import pdb; pdb.set_trace()
if self.recurrent_type == "WEEKLY":
LIST_OF_DAYS = self.days_if_recurring["days"]
HOW_MANY_DAYS_FOR_ONE_WEEK = len(LIST_OF_DAYS)
REPEATS = HOW_MANY_DAYS_FOR_ONE_WEEK * self.number_of_times_recurring
RESET_COUNTER = 0
for i in range(REPEATS):
self.id = ''.join(random.choices(string.ascii_letters, k=30))
self.calendarydays = onDay(self.calendarydays, LIST_OF_DAYS[RESET_COUNTER])
if RESET_COUNTER == HOW_MANY_DAYS_FOR_ONE_WEEK - 1:
RESET_COUNTER = 0
self.save()
else:
self.id = ''.join(random.choices(string.ascii_letters, k=30))
self.save()
return super(Bookings, self).save(*args, **kwargs)
onDay()
def onDay(date, day): # this function finds next day of week, and skips ahead one week if today's time has already passed
utc = pytz.UTC
check_right_now = utc.localize(datetime.datetime.now())
if check_right_now > date:
forward_day = date + datetime.timedelta(days=(day - date.weekday() + 7) % 7) + datetime.timedelta(days=7)
else:
forward_day = date + datetime.timedelta(days=(day - date.weekday() + 7) % 7)
return forward_day
As always, any help is greatly appreciated.
You should call super(Bookings, self).save(*args, **kwargs) instead of self.save(). The super save will call django's actual model save which is what you want. Calling self.save() will just call your overridden save which doesn't do anything in the database. But yeah what #AamirAdnan said should fix your problem.
The idea of the code below should be that it only fires if the field verification_pin is empty i.e. on a new record. However, it seems that every time I save the model it generates a new pin ignoring if instance.verification_pin is None statement, why, what have I missed?
#receiver(pre_save, sender=CompanyUser)
def my_callback(sender, instance, *args, **kwargs):
if instance.verification_pin is None:
instance.verification_pin = instance.generate_pin()
instance.is_active = False
instance.send_verification_pin()
Model:
class CompanyUser(User):
verification_pin = models.IntegerField(max_length=4, null=True)
objects = UserManager()
def generate_pin(self):
"""
Returns a random four digit pin.
"""
return random.randint(999, 9999)
def send_verification_pin(self):
self.email_user(
subject="Test",
message="Your pin: %s" % self.verification_pin,
from_email=settings.DEFAULT_FROM_EMAIL
)
You can set the default value for a field to a callable object.
Or, you might try using a post_save handler instead, where you can check if created is True. Also, it might be helpful to check the value in verification_pin after saving, to see if it really got set or not.
In order to make a simple captacha-like field, I tried the following:
class CaptchaField(IntegerField):
def __init__(self, *args, **kwargs):
super(CaptchaField, self).__init__(*args, **kwargs)
self.reset()
def reset(self):
self.int_1 = random.randint(1, 10)
self.int_2 = random.randint(1, 10)
self.label = '{0} + {1}'.format(self.int_1, self.int_2)
def clean(self, value):
value = super(CaptchaField, self).clean(value)
if value != self.int_1 + self.int_2:
self.reset()
raise ValidationError(_("Enter the result"), code='captcha_fail')
return True
Every time my answer is wrong, the label is changed as expected but the test is performed against the first values of int_1 and int_2 and not against the newly randomly generated values.
I don't understand how Field object are created and why I can't access the values of my field.
Thanks in advance
Have a think about how this works in your view. When you render the form, the field is instantiated and sets the label to your random values, which is fine. Now, the user posts back to the view: what happens? Well, the form is instantiated again, as is the field, and the field is set to two new random values. Not surprisingly, this won't match up to the previous value, because you haven't stored that anywhere.
To do anything like this, you need to store state somewhere so it is preserved between requests. You could try putting it in the session, perhaps: or, a better way might be to hash the two values together and put them in a hidden field, then on submit hash the submitted value and compare it against the one in the hidden field. This would probably need to managed at the form level, not the field.
I want to get an object from the database if it already exists (based on provided parameters) or create it if it does not.
Django's get_or_create (or source) does this. Is there an equivalent shortcut in SQLAlchemy?
I'm currently writing it out explicitly like this:
def get_or_create_instrument(session, serial_number):
instrument = session.query(Instrument).filter_by(serial_number=serial_number).first()
if instrument:
return instrument
else:
instrument = Instrument(serial_number)
session.add(instrument)
return instrument
Following the solution of #WoLpH, this is the code that worked for me (simple version):
def get_or_create(session, model, **kwargs):
instance = session.query(model).filter_by(**kwargs).first()
if instance:
return instance
else:
instance = model(**kwargs)
session.add(instance)
session.commit()
return instance
With this, I'm able to get_or_create any object of my model.
Suppose my model object is :
class Country(Base):
__tablename__ = 'countries'
id = Column(Integer, primary_key=True)
name = Column(String, unique=True)
To get or create my object I write :
myCountry = get_or_create(session, Country, name=countryName)
That's basically the way to do it, there is no shortcut readily available AFAIK.
You could generalize it ofcourse:
def get_or_create(session, model, defaults=None, **kwargs):
instance = session.query(model).filter_by(**kwargs).one_or_none()
if instance:
return instance, False
else:
params = {k: v for k, v in kwargs.items() if not isinstance(v, ClauseElement)}
params.update(defaults or {})
instance = model(**params)
try:
session.add(instance)
session.commit()
except Exception: # The actual exception depends on the specific database so we catch all exceptions. This is similar to the official documentation: https://docs.sqlalchemy.org/en/latest/orm/session_transaction.html
session.rollback()
instance = session.query(model).filter_by(**kwargs).one()
return instance, False
else:
return instance, True
2020 update (Python 3.9+ ONLY)
Here is a cleaner version with Python 3.9's the new dict union operator (|=)
def get_or_create(session, model, defaults=None, **kwargs):
instance = session.query(model).filter_by(**kwargs).one_or_none()
if instance:
return instance, False
else:
kwargs |= defaults or {}
instance = model(**kwargs)
try:
session.add(instance)
session.commit()
except Exception: # The actual exception depends on the specific database so we catch all exceptions. This is similar to the official documentation: https://docs.sqlalchemy.org/en/latest/orm/session_transaction.html
session.rollback()
instance = session.query(model).filter_by(**kwargs).one()
return instance, False
else:
return instance, True
Note:
Similar to the Django version this will catch duplicate key constraints and similar errors. If your get or create is not guaranteed to return a single result it can still result in race conditions.
To alleviate some of that issue you would need to add another one_or_none() style fetch right after the session.commit(). This still is no 100% guarantee against race conditions unless you also use a with_for_update() or serializable transaction mode.
I've been playing with this problem and have ended up with a fairly robust solution:
def get_one_or_create(session,
model,
create_method='',
create_method_kwargs=None,
**kwargs):
try:
return session.query(model).filter_by(**kwargs).one(), False
except NoResultFound:
kwargs.update(create_method_kwargs or {})
created = getattr(model, create_method, model)(**kwargs)
try:
session.add(created)
session.flush()
return created, True
except IntegrityError:
session.rollback()
return session.query(model).filter_by(**kwargs).one(), False
I just wrote a fairly expansive blog post on all the details, but a few quite ideas of why I used this.
It unpacks to a tuple that tells you if the object existed or not. This can often be useful in your workflow.
The function gives the ability to work with #classmethod decorated creator functions (and attributes specific to them).
The solution protects against Race Conditions when you have more than one process connected to the datastore.
EDIT: I've changed session.commit() to session.flush() as explained in this blog post. Note that these decisions are specific to the datastore used (Postgres in this case).
EDIT 2: I’ve updated using a {} as a default value in the function as this is typical Python gotcha. Thanks for the comment, Nigel! If your curious about this gotcha, check out this StackOverflow question and this blog post.
A modified version of erik's excellent answer
def get_one_or_create(session,
model,
create_method='',
create_method_kwargs=None,
**kwargs):
try:
return session.query(model).filter_by(**kwargs).one(), True
except NoResultFound:
kwargs.update(create_method_kwargs or {})
try:
with session.begin_nested():
created = getattr(model, create_method, model)(**kwargs)
session.add(created)
return created, False
except IntegrityError:
return session.query(model).filter_by(**kwargs).one(), True
Use a nested transaction to only roll back the addition of the new item instead of rolling back everything (See this answer to use nested transactions with SQLite)
Move create_method. If the created object has relations and it is assigned members through those relations, it is automatically added to the session. E.g. create a book, which has user_id and user as corresponding relationship, then doing book.user=<user object> inside of create_method will add book to the session. This means that create_method must be inside with to benefit from an eventual rollback. Note that begin_nested automatically triggers a flush.
Note that if using MySQL, the transaction isolation level must be set to READ COMMITTED rather than REPEATABLE READ for this to work. Django's get_or_create (and here) uses the same stratagem, see also the Django documentation.
This SQLALchemy recipe does the job nice and elegant.
The first thing to do is to define a function that is given a Session to work with, and associates a dictionary with the Session() which keeps track of current unique keys.
def _unique(session, cls, hashfunc, queryfunc, constructor, arg, kw):
cache = getattr(session, '_unique_cache', None)
if cache is None:
session._unique_cache = cache = {}
key = (cls, hashfunc(*arg, **kw))
if key in cache:
return cache[key]
else:
with session.no_autoflush:
q = session.query(cls)
q = queryfunc(q, *arg, **kw)
obj = q.first()
if not obj:
obj = constructor(*arg, **kw)
session.add(obj)
cache[key] = obj
return obj
An example of utilizing this function would be in a mixin:
class UniqueMixin(object):
#classmethod
def unique_hash(cls, *arg, **kw):
raise NotImplementedError()
#classmethod
def unique_filter(cls, query, *arg, **kw):
raise NotImplementedError()
#classmethod
def as_unique(cls, session, *arg, **kw):
return _unique(
session,
cls,
cls.unique_hash,
cls.unique_filter,
cls,
arg, kw
)
And finally creating the unique get_or_create model:
from sqlalchemy import Column, Integer, String, create_engine
from sqlalchemy.orm import sessionmaker
from sqlalchemy.ext.declarative import declarative_base
Base = declarative_base()
engine = create_engine('sqlite://', echo=True)
Session = sessionmaker(bind=engine)
class Widget(UniqueMixin, Base):
__tablename__ = 'widget'
id = Column(Integer, primary_key=True)
name = Column(String, unique=True, nullable=False)
#classmethod
def unique_hash(cls, name):
return name
#classmethod
def unique_filter(cls, query, name):
return query.filter(Widget.name == name)
Base.metadata.create_all(engine)
session = Session()
w1, w2, w3 = Widget.as_unique(session, name='w1'), \
Widget.as_unique(session, name='w2'), \
Widget.as_unique(session, name='w3')
w1b = Widget.as_unique(session, name='w1')
assert w1 is w1b
assert w2 is not w3
assert w2 is not w1
session.commit()
The recipe goes deeper into the idea and provides different approaches but I've used this one with great success.
The closest semantically is probably:
def get_or_create(model, **kwargs):
"""SqlAlchemy implementation of Django's get_or_create.
"""
session = Session()
instance = session.query(model).filter_by(**kwargs).first()
if instance:
return instance, False
else:
instance = model(**kwargs)
session.add(instance)
session.commit()
return instance, True
not sure how kosher it is to rely on a globally defined Session in sqlalchemy, but the Django version doesn't take a connection so...
The tuple returned contains the instance and a boolean indicating if the instance was created (i.e. it's False if we read the instance from the db).
Django's get_or_create is often used to make sure that global data is available, so I'm committing at the earliest point possible.
I slightly simplified #Kevin. solution to avoid wrapping the whole function in an if/else statement. This way there's only one return, which I find cleaner:
def get_or_create(session, model, **kwargs):
instance = session.query(model).filter_by(**kwargs).first()
if not instance:
instance = model(**kwargs)
session.add(instance)
return instance
There is a Python package that has #erik's solution as well as a version of update_or_create(). https://github.com/enricobarzetti/sqlalchemy_get_or_create
Depending on the isolation level you adopted, none of the above solutions would work.
The best solution I have found is a RAW SQL in the following form:
INSERT INTO table(f1, f2, unique_f3)
SELECT 'v1', 'v2', 'v3'
WHERE NOT EXISTS (SELECT 1 FROM table WHERE f3 = 'v3')
This is transactionally safe whatever the isolation level and the degree of parallelism are.
Beware: in order to make it efficient, it would be wise to have an INDEX for the unique column.
One problem I regularly encounter is when a field has a max length (say, STRING(40)) and you'd like to perform a get or create with a string of large length, the above solutions will fail.
Building off of the above solutions, here's my approach:
from sqlalchemy import Column, String
def get_or_create(self, add=True, flush=True, commit=False, **kwargs):
"""
Get the an entity based on the kwargs or create an entity with those kwargs.
Params:
add: (default True) should the instance be added to the session?
flush: (default True) flush the instance to the session?
commit: (default False) commit the session?
kwargs: key, value pairs of parameters to lookup/create.
Ex: SocialPlatform.get_or_create(**{'name':'facebook'})
returns --> existing record or, will create a new record
---------
NOTE: I like to add this as a classmethod in the base class of my tables, so that
all data models inherit the base class --> functionality is transmitted across
all orm defined models.
"""
# Truncate values if necessary
for key, value in kwargs.items():
# Only use strings
if not isinstance(value, str):
continue
# Only use if it's a column
my_col = getattr(self.__table__.columns, key)
if not isinstance(my_col, Column):
continue
# Skip non strings again here
if not isinstance(my_col.type, String):
continue
# Get the max length
max_len = my_col.type.length
if value and max_len and len(value) > max_len:
# Update the value
value = value[:max_len]
kwargs[key] = value
# -------------------------------------------------
# Make the query...
instance = session.query(self).filter_by(**kwargs).first()
if instance:
return instance
else:
# Max length isn't accounted for here.
# The assumption is that auto-truncation will happen on the child-model
# Or directtly in the db
instance = self(**kwargs)
# You'll usually want to add to the session
if add:
session.add(instance)
# Navigate these with caution
if add and commit:
try:
session.commit()
except IntegrityError:
session.rollback()
elif add and flush:
session.flush()
return instance