How to dinamicaly create multiple Table Classes in SQLAlchemy? - python

I'm trying to create multiple classes in SQLAlchemy to generate specific tables.
I found different things here and more on https://docs.python.org/3/library/functions.html#import and https://python-course.eu/oop/dynamically-creating-classes-with-type.php
It seems clear enough, but their examples is using global opeartions, and I don't understand exactly how can I use as a sub function in something like this:
class _Table(Base):
__tablename__ = '_table'
id = Column(Integer, primary_key=True, autoincrement=True)
name = Column(String)
table_list = ['Table1', 'Table2']
def table_class_generator(table_list):
# here I need to create the tables
def tables_operators():
# here I make operations on tables
So I need this one to convert globally to something like:
class Table1(Base):
__tablename__ = 'table1'
id = ...
name = ...
class Table2(Base):
__tablename__ = 'table2'
id = ...
name = ...
def table_operators():
#

Thanks #Gord Thompson because he gave me another track.
I believe the solution will be this, I only test the init of database.
def tables_constructor(names: list) -> list:
"""
Creates all tables in the database
:return:
"""
engine = get_engine()
metadata_obj = MetaData()
table_names = []
for name in names:
name_obj = Table(
name,
metadata_obj,
Column('id', Integer, primary_key=True, autoincrement=True),
Column('timestamp', Integer)
)
table_names.append(name_obj)
metadata_obj.create_all(engine)
return table_names
def do_something()
#
def start_app():
names = ["Table_1", "Table_2"]
tables = tables_constructor(symbols)
do_something(tables)
Now I think I can do things in tables as they are mapped to table objects.
Would be cool to improve to define table columns somewhere else. I tried but isn't working.

Related

How to use sqlAlchemy table shema to load data

I have two scripts schema.py and load_data.py. In schema.py, I define the schema for over 20 tables using sqlAlchemy Base. Two of the tables look like:
schema.py
Base = declarative_base()
meta = MetaData()
class Table1(Base):
__tablename__ = 'table1'
id = Column(Integer, primary_key=True)
name = Column(String)
class Table2(Base):
__tablename__ = 'table2'
id = Column(Integer, primary_key=True)
bdate = Column(Date)
...
class Table20(Base):
__tablename__ = 'table20'
id = Column(Integer, primary_key=True)
bdate = Column(Date)
I want to use my load_data.py to copy those ~20 tables from one database to another. My question is how to create the table in load_data.py using the schema I defined in schema.py?? Following the examples in Introductory Tutorial of Python’s SQLAlchemy, I use import to load all the table schema class, but I find it too messy. Is there any better way to handle this situation??? I am new to sqlAlchemy,please bear me if this question seems too naive.
load_data.py
from schema import Base, Table1, Table2, Table3, Table4, Table5, Table6, Table7, Table8, Table9, Table10,..., Table20
src_engine = create_engine('sqlite:// sqlite_test.db')
dst_engine = create_engine('postgresql:///postgresql_test.db')
Base.metadata.create_all(dst_engine)
tables = Base.metadata.tables
for tbl in tables:
data = src_engine.execute(tables[tbl].select()).fetchall()
for a in data: print(a)
if data:
dst_engine.execute( tables[tbl].insert(), data)
Try from schema import *, which imports all members from a module. See also these answers regarding the difference between import schema and from schema import x.

Create a Full Text Search index with SQLAlchemy on PostgreSQL

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).

Dynamically setting __tablename__ for sharding in SQLAlchemy?

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)

Automatically Build Database Table based on a Class with SQLAlchemy

I'm really new to SQLAlchemy, and I love it. Right now I'm doing a lot of things manually and I want to do things more 'pythonically' and dynamic.
So as an example, I have this short script that manually creates/defines a table and then a function that inserts data into that table.
database connection
import os
from sqlalchemy import *
from sqlalchemy import schema, types
from sqlalchemy.ext.declarative import declarative_base
db_url = os.environ.get('DATABASE_URL')
engine = create_engine(db_url)
Base = declarative_base(engine)
meta = Base.metadata
table definition
file_paths = Table('file_paths', meta,
Column('table_id', Integer, primary_key = True),
Column('fullpath', String(255)),
Column('filename', String(255)),
Column('extension', String(255)),
Column('created', String(255)),
Column('modified', String(255)),
Column('size', Integer),
Column('owner', String(255)),
Column('permissions', Integer),
mysql_engine='InnoDB',
)
file_paths.drop(engine, checkfirst = False)
file_paths.create(engine, checkfirst = True)
insert function takes a string and a list as arguments
def push_to_db(fullpath, fileInfo):
i = file_paths.insert()
i.execute( fullpath = str(fullpath),
filename = str(fileInfo[0]),
extension = str(fileInfo[1]),
created = str(fileInfo[2]),
modified = str(fileInfo[3]),
size = str(fileInfo[4]),
owner = str(fileInfo[5]),
permissions = str(fileInfo[6]),
)
This works but it's ugly and taken right out of a tutorial I found somewhere online. My goal is to make these operations dynamic.
example class
class FileMeta(object):
def __init__(self, fullPathFileName, filename):
self.fullPathFileName = fullPathFileName
self.filename = filename
self.extension = os.path.splitext(self.filename)[1].lower()
...
def fileMetaList(self):
return [self.filename, self.extension, self.created, self.modified,\
self.size, self.owner, self.permissions]
So here's the scenario: given a class object
define the table dynamically according to the class member variables
column numbers and names should correspond to variable names
or correspond to the index of that variable in a list of class variables
write a function that can insert data from the class into the corresponding dynamically created table
My intuition tells me this is what SQLAlchemy would be good for. Can someone tell me a good tutorial or reference that can outline this process?
You want to use the declarative extension instead:
from sqlalchemy.ext.declarative import declarative_base
Base = declarative_base()
class FilePaths(Base):
__tablename__ = 'file_paths'
__table_args__ = {'mysql_engine':'InnoDB'}
table_id = Column(Integer, primary_key=True)
fullpath = Column(String(255))
filename = Column(String(255))
extension = Column(String(255))
created = Column(String(255))
modified = Column(String(255))
size = Column(Integer)
owner = Column(String(255))
permissions = Column(Integer)
Base.metadata.create_all(engine)
You can define your own __init__() as needed, as well other methods, then create instances of these to insert new rows.
See the SQLAlchemy's own ORM tutorial.
Add Automap extension :
from sqlalchemy.ext.automap import automap_base
# SQLAlchemy
engine = create_engine(DATABASE_URL)
metadata = MetaData()
Base = automap_base()
Base.prepare(engine, reflect=True)

SQLAlchemy exclude_properties not working in Declarative

In declarative approach, I want to exclude one property, its working properly when my column name and property name are same. But if I give different name then its not working.
Here is my sample code.
Base = declarative_base()
class tblUser(Base):
__tablename__ = 'tblUser'
User_Id = Column('User_Id', String(100), primary_key=True)
SequenceNo = Column('Sequence_No', Integer)
FullName = Column('FullName', String(50))
__mapper_args__ = {'exclude_properties' :['Sequence_No']}
user = tblUser()
user.User_Id = '1000001'
user.SequenceNo = 101
session.add(user)
session.commit()
In the above sample I don't want the SequenceNo property to be updated in database even if I assign some value to it. So I used exclude_properties but still its updating the value in db. But if I change the property name from SequenceNo to Sequence_No (same as the column name) then its working as per the behaviour. Can anyone help me?
Thanks
Adhi
Unfortunately, __mapper_args__ is probably the wrong approach. It is intended to control the reflection of an existing database table into a mapper, not make a column 'read-only'.
I think a better approach would be to use a hybrid property:
from sqlalchemy.ext.hybrid import hybrid_property
Base = declarative_base()
class tblUser(Base):
__tablename__ = 'tblUser'
User_Id = Column('User_Id', String(100), primary_key=True)
FullName = Column('FullName', String(50))
_Sequence_No = Column('Sequence_No', Integer)
_local_Sequence_No = None
#hybrid_property
#property
def SequenceNo(self):
if self._local_Sequence_No is not None:
return self._local_Sequence_No
return self._SequenceNo
#SequenceNo.setter
def SequenceNo(self, value):
self._local_Sequence_No = value
The original Sequence_No column is available via a private attribute, and the SequenceNo property intercepts writes and stores them on the instance to be re-used later, but not written to the database.

Categories

Resources