I'm defining an PostgreSQL table using an SQLAlchemy declarative base, like this:
from sqlalchemy import Column, String, BigInteger
from sqlalchemy.ext.declarative import declarative_base
Base = declarative_base()
class MyTable(Base):
__tablename__ = 'my_table'
id = Column('id', BigInteger, primary_key=True)
some_string = Column('some_string', String(256), nullable=False)
The nullable constraint guarantees that some_string cannot be null. However, I'd additionally like to give some_string a minimum length, or just forbid it from being the empty string. How can I do this?
Ideally we want the validation to be applied both at the database layer via a constraint and also in our model by rejecting attempts to set the property to a string that's too short even before trying to save it to the database. We can do the former with a CheckConstraint using the char_length function, and the latter by adding a validator. Below is an example that enforces a minimum length of 3 characters on some_string:
from sqlalchemy import Column, String, BigInteger
from sqlalchemy.schema import CheckConstraint
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import validates
Base = declarative_base()
class MyTable(Base):
__tablename__ = 'my_table'
id = Column('id', BigInteger, primary_key=True)
some_string = Column('some_string', String(256), nullable=False)
__table_args__ = (
CheckConstraint('char_length(some_string) > 2',
name='some_string_min_length'),
)
#validates('some_string')
def validate_some_string(self, key, some_string) -> str:
if len(some_string) <= 2:
raise ValueError('some_string too short')
return some_string
Related
Consider the following sqlalchemy model that validates the primary_email field:
from sqlalchemy import Column, String
from sqlalchemy.orm import validates
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.dialects import postgresql
from sqlalchemy.ext.mutable import MutableList
Base = declarative_base()
class Test(Base):
id = Column(Integer, primary_key=True)
primary_email = Column(String(128))
#validates('primary_email')
def valid_email(self, key, value):
if not '#' in value:
raise ValueError(f"Invalid {key}: '{value}'")
return value
def __init__(self, email):
primary_email = email
It works as expected but now I want to add another column
secondary_email = Column(MutableList.as_mutable(postgresql.ARRAY(String(128))))
How do I perform validation on secondary_email.append(email) call?
When I add 'secondary_email' to validates decorator, it only gets triggered on assignment operations like
self.secondary_email = ['example#me.com']
I believe this is something that can be achieved with a custom class but I wonder if there is a simpler and more generic solution?
Here is an absurd problem with sqlalchemy that seems easy! First, this is my config file for connecting to mysql database:
from sqlalchemy import create_engine
from sqlalchemy.ext.declarative import declarative_base
Base = declarative_base()
engine = create_engine('mysql://root:#localhost:3306/digi')
and then, I am trying to create a table called 'sale-history' :
from config import *
from sqlalchemy import *
class Sale(Base):
__tablename__ = 'sale-history'
order_id = column(Integer, primary_key= True)
customer_id = column(Integer)
item_id = column(Integer) #froeign key with product list
cartFinalize_dateTime = column(DATETIME)
amount_ordrered = column(Integer)
city_name = column(String(191))
quantity_ordered = column(Integer)
def __repr__(self):
return "<Sale(city_name='%s')>" % (self.city_name)
Sale.__table__
Base.metadata.create_all(engine)
Now, what I wonder is that
Sale.__table__
and
Base.metadata.create_all(engine)
are not known to my code. More accurate, these are not in suggestion options showed by pycharm editor. Debugging the code does not throw any error(returns 0). What should I do to create tables?
I appreciate your consideration so much!
The code is using column to define columns in the table but it should be using Column (note the upper-case "C").
A few tips/comments
Pycharm may provide better support if you avoid the from module import * idiom. You can alias module names if they are to long to type, for example import sqlalchemy as sa
You can see the SQL generated by the engine by passing echo=True to create_engine
Tablenames with hyphens need to be quoted with backticks to be valid. Sqlalchemy does this automatically, but other applications may not. Using underscores instead may be more convenient.
The final code might look like this:
config
from sqlalchemy import create_engine
from sqlalchemy.ext.declarative import declarative_base
Base = declarative_base()
engine = create_engine('mysql://root:#localhost:3306/test', echo=True)
Model
import sqlachemy as sa
import config
class Sale(Base):
__tablename__ = 'sale-history'
order_id = sa.Column(sa.Integer, primary_key=True)
customer_id = sa.Column(sa.Integer)
item_id = sa.Column(sa.Integer) # foreign key with product list
cartFinalize_dateTime = sa.Column(sa.DATETIME)
amount_ordrered = sa.Column(sa.Integer)
city_name = sa.Column(sa.String(191))
quantity_ordered = sa.Column(sa.Integer)
def __repr__(self):
return "<Sale(city_name='%s')>" % (self.city_name)
Base.metadata.create_all(config.engine)
It looks like SQLAlchemy defaults to creating VARCHAR2 columns as CHAR. How can I have it create with BYTE instead?
from sqlalchemy import MetaData, Column, String
from sqlalchemy.ext.declarative import declarative_base
metadata = MetaData()
Base = declarative_base(metadata=metadata)
class Foo(Base):
__tablename__ = 'foo'
name = Column(String(10), primary_key=True)
Foo.__table__.create(bind=engine)
This creates the following table:
CREATE TABLE XXMD.FOO
(
NAME VARCHAR2(10 CHAR) NOT NULL
)
Instead, I would like it to create the following:
CREATE TABLE XXMD.FOO
(
NAME VARCHAR2(10 BYTE) NOT NULL
)
Thanks to Mike Bayer:
from sqlalchemy.ext.compiler import compiles
class VARCHAR2Byte(String):
pass
#compiles(VARCHAR2Byte)
def compile_varchar2_byte(type_, compiler, **kw):
len = type_.length
return 'VARCHAR2(%i BYTE)' % len
I need to create a PostgreSQL Full Text Search index in Python with SQLAlchemy. Here's what I want in SQL:
CREATE TABLE person ( id INTEGER PRIMARY KEY, name TEXT );
CREATE INDEX person_idx ON person USING GIN (to_tsvector('simple', name));
Now how do I do the second part with SQLAlchemy when using the ORM:
class Person(db.Model):
id = db.Column(db.Integer, primary_key=True)
name = db.Column(db.String)
You could create index using Index in __table_args__. Also I use a function to create ts_vector to make it more tidy and reusable if more than one field is required. Something like below:
from sqlalchemy.dialects import postgresql
def create_tsvector(*args):
exp = args[0]
for e in args[1:]:
exp += ' ' + e
return func.to_tsvector('english', exp)
class Person(db.Model):
id = db.Column(db.Integer, primary_key=True)
name = db.Column(db.String)
__ts_vector__ = create_tsvector(
cast(func.coalesce(name, ''), postgresql.TEXT)
)
__table_args__ = (
Index(
'idx_person_fts',
__ts_vector__,
postgresql_using='gin'
)
)
Update:
A sample query using index (corrected based on comments):
people = Person.query.filter(Person.__ts_vector__.match(expressions, postgresql_regconfig='english')).all()
The answer from #sharez is really useful (especially if you need to concatenate columns in your index). For anyone looking to create a tsvector GIN index on a single column, you can simplify the original answer approach with something like:
from sqlalchemy import Column, Index, Integer, String
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.sql import func
Base = declarative_base()
class Example(Base):
__tablename__ = 'examples'
id = Column(Integer, primary_key=True)
textsearch = Column(String)
__table_args__ = (
Index(
'ix_examples_tsv',
func.to_tsvector('english', textsearch),
postgresql_using='gin'
),
)
Note that the comma following Index(...) in __table_args__ is not a style choice, the value of __table_args__ must be a tuple, dictionary, or None.
If you do need to create a tsvector GIN index on multiple columns, here is another way to get there using text().
from sqlalchemy import Column, Index, Integer, String, text
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.sql import func
Base = declarative_base()
def to_tsvector_ix(*columns):
s = " || ' ' || ".join(columns)
return func.to_tsvector('english', text(s))
class Example(Base):
__tablename__ = 'examples'
id = Column(Integer, primary_key=True)
atext = Column(String)
btext = Column(String)
__table_args__ = (
Index(
'ix_examples_tsv',
to_tsvector_ix('atext', 'btext'),
postgresql_using='gin'
),
)
Thanks for this question and answers.
I'd like to add a bit more in case ppl using alembic to manage versions by
using autogenerate
which creating the index seems not be detected.
We might end up writing our own alter script which look like.
"""add fts idx
Revision ID: e3ce1ce23d7a
Revises: 079c4455d54d
Create Date:
"""
# revision identifiers, used by Alembic.
revision = 'e3ce1ce23d7a'
down_revision = '079c4455d54d'
from alembic import op
import sqlalchemy as sa
def upgrade():
op.create_index('idx_content_fts', 'table_name',
[sa.text("to_tsvector('english', content)")],
postgresql_using='gin')
def downgrade():
op.drop_index('idx_content_fts')
It has been answered already by #sharez and #benvc. I needed to make it work with weights though. This is how I did it based on their answers :
from sqlalchemy import Column, func, Index, String
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.sql.operators import op
CONFIG = 'english'
Base = declarative_base()
def create_tsvector(*args):
field, weight = args[0]
exp = func.setweight(func.to_tsvector(CONFIG, field), weight)
for field, weight in args[1:]:
exp = op(exp, '||', func.setweight(func.to_tsvector(CONFIG, field), weight))
return exp
class Example(Base):
__tablename__ = 'example'
foo = Column(String)
bar = Column(String)
__ts_vector__ = create_tsvector(
(foo, 'A'),
(bar, 'B')
)
__table_args__ = (
Index('my_index', __ts_vector__, postgresql_using='gin'),
)
Previous answers here were helpful for pointing in the right direction.
Below, a distilled & simplified approach using ORM approach & TSVectorType helper from sqlalchemy-utils (that is quite basic and can be simply copy/pasted to avoid external dependencies if needed https://sqlalchemy-utils.readthedocs.io/en/latest/_modules/sqlalchemy_utils/types/ts_vector.html):
Defining a TSVECTOR column (TSVectorType) in your ORM model (declarative) populated automatically from the source text field(s)
import sqlalchemy as sa
from sqlalchemy_utils.types.ts_vector import TSVectorType
# ^-- https://sqlalchemy-utils.readthedocs.io/en/latest/_modules/sqlalchemy_utils/types/ts_vector.html
class MyModel(Base):
__tablename__ = 'mymodel'
id = sa.Column(sa.Integer, primary_key=True)
content = sa.Column(sa.String, nullable=False)
content_tsv = sa.Column(
TSVectorType("content", regconfig="english"),
sa.Computed("to_tsvector('english', \"content\")", persisted=True))
# ^-- equivalent for SQL:
# COLUMN content_tsv TSVECTOR GENERATED ALWAYS AS (to_tsvector('english', "content")) STORED;
__table_args__ = (
# Indexing the TSVector column
sa.Index("idx_mymodel_content_tsv", content_tsv, postgresql_using="gin"),
)
For additional details on querying using ORM, see https://stackoverflow.com/a/73999486/11750716 (there is an important difference between SQLAlchemy 1.4 and SQLAlchemy 2.0).
In order to handle a growing database table, we are sharding on table name. So we could have database tables that are named like this:
table_md5one
table_md5two
table_md5three
All tables have the exact same schema.
How do we use SQLAlchemy and dynamically specify the tablename for the class that corresponds to this? Looks like the declarative_base() classes need to have tablename pre-specified.
There will eventually be too many tables to manually specify derived classes from a parent/base class. We want to be able to build a class that can have the tablename set up dynamically (maybe passed as a parameter to a function.)
OK, we went with the custom SQLAlchemy declaration rather than the declarative one.
So we create a dynamic table object like this:
from sqlalchemy import MetaData, Table, Column
def get_table_object(self, md5hash):
metadata = MetaData()
table_name = 'table_' + md5hash
table_object = Table(table_name, metadata,
Column('Column1', DATE, nullable=False),
Column('Column2', DATE, nullable=False)
)
clear_mappers()
mapper(ActualTableObject, table_object)
return ActualTableObject
Where ActualTableObject is the class mapping to the table.
In Augmenting the Base you find a way of using a custom Base class that can, for example, calculate the __tablename__ attribure dynamically:
class Base(object):
#declared_attr
def __tablename__(cls):
return cls.__name__.lower()
The only problem here is that I don't know where your hash comes from, but this should give a good starting point.
If you require this algorithm not for all your tables but only for one you could just use the declared_attr on the table you are interested in sharding.
Because I insist to use declarative classes with their __tablename__ dynamically specified by given parameter, after days of failing with other solutions and hours of studying SQLAlchemy internals, I come up with the following solution that I believe is simple, elegant and race-condition free.
def get_model(suffix):
DynamicBase = declarative_base(class_registry=dict())
class MyModel(DynamicBase):
__tablename__ = 'table_{suffix}'.format(suffix=suffix)
id = Column(Integer, primary_key=True)
name = Column(String)
...
return MyModel
Since they have their own class_registry, you will not get that warning saying:
This declarative base already contains a class with the same class name and module name as mypackage.models.MyModel, and will be replaced in the string-lookup table.
Hence, you will not be able to reference them from other models with string lookup. However, it works perfectly fine to use these on-the-fly declared models for foreign keys as well:
ParentModel1 = get_model(123)
ParentModel2 = get_model(456)
class MyChildModel(BaseModel):
__tablename__ = 'table_child'
id = Column(Integer, primary_key=True)
name = Column(String)
parent_1_id = Column(Integer, ForeignKey(ParentModel1.id))
parent_2_id = Column(Integer, ForeignKey(ParentModel2.id))
parent_1 = relationship(ParentModel1)
parent_2 = relationship(ParentModel2)
If you only use them to query/insert/update/delete without any reference left such as foreign key reference from another table, they, their base classes and also their class_registry will be garbage collected, so no trace will be left.
you can write a function with tablename parameter and send back the class with setting appropriate attributes.
def get_class(table_name):
class GenericTable(Base):
__tablename__ = table_name
ID= Column(types.Integer, primary_key=True)
def funcation(self):
......
return GenericTable
Then you can create a table using:
get_class("test").__table__.create(bind=engine) # See sqlachemy.engine
Try this
import zlib
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy import Column, Integer, BigInteger, DateTime, String
from datetime import datetime
BASE = declarative_base()
ENTITY_CLASS_DICT = {}
class AbsShardingClass(BASE):
__abstract__ = True
def get_class_name_and_table_name(hashid):
return 'ShardingClass%s' % hashid, 'sharding_class_%s' % hashid
def get_sharding_entity_class(hashid):
"""
#param hashid: hashid
#type hashid: int
#rtype AbsClientUserAuth
"""
if hashid not in ENTITY_CLASS_DICT:
class_name, table_name = get_class_name_and_table_name(hashid)
cls = type(class_name, (AbsShardingClass,),
{'__tablename__': table_name})
ENTITY_CLASS_DICT[hashid] = cls
return ENTITY_CLASS_DICT[hashid]
cls = get_sharding_entity_class(1)
print session.query(cls).get(100)
Instead of using imperative creating Table object, you can use usual declarative_base and make a closure to set a table name as the following:
def make_class(Base, table_name):
class User(Base):
__tablename__ = table_name
id = Column(Integer, primary_key=True)
name= Column(String)
return User
Base = declarative_base()
engine = make_engine()
custom_named_usertable = make_class(Base, 'custom_name')
Base.metadata.create_all(engine)
session = make_session(engine)
new_user = custom_named_usertable(name='Adam')
session.add(new_user)
session.commit()
session.close()
engine.dispose()
just you need to create class object for Base.
from sqlalchemy.ext.declarative import declarative_base, declared_attr
class Base(object):
#declared_attr
def __tablename__(cls):
return cls.__name.lower()
Base = declarative_base(cls=Base)