Version Python Requires License CI Test Coverage Code style: black Downloads
utype is a data types declaration & parsing library based on Python type annotations, enforce types and constraints for classes and functions at runtime
- Documentation: https://utype.io
- 中文文档: https://utype.io/zh
- Source Code: https://github.com/utilmeta/utype
- Author: @voidZXL
- License: Apache 2.0
- Enforce types, data classes, function params and result parsing at runtime based on Python type annotation
- Support a variety of constraints, logical operators and flexible parsing options
- Highly extensible, all type transformer can be register, extend and override
pip install -U utype
utype requires Python >= 3.7
The utype support to add constraints on types, such as
from utype import Rule, exc class PositiveInt(int, Rule): gt = 0 assert PositiveInt(b'3') == 3 try: PositiveInt(-0.5) except exc.ParseError as e: print(e) """ Constraint: 0 violated """
Data that conforms to the type and constraints will complete the conversion, otherwise will throw a parse error indicating what went wrong
utype supports the "dataclass" usage that convert a dict or JSON to a class instance, similar to pydantic and attrs
from utype import Schema, Field, exc from datetime import datetime class UserSchema(Schema): username: str = Field(regex='[0-9a-zA-Z]{3,20}') signup_time: datetime # 1. Valid input data = {'username': 'bob', 'signup_time': '2022-10-11 10:11:12'} print(UserSchema(**data)) #> UserSchema(username='bob', signup_time=datetime.datetime(2022, 10, 11, 10, 11, 12)) # 2. Invalid input try: UserSchema(username='@invalid', signup_time='2022-10-11 10:11:12') except exc.ParseError as e: print(e) """ parse item: ['username'] failed: Constraint: <regex>: '[0-9a-zA-Z]{3,20}' violated """
After a simple declaration, you can get
- Automatic
__init__to take input data, perform validation and attribute assignment - Providing
__repr__and__str__to get the clearly print output of the instance - parse and protect attribute assignment and deletion to avoid dirty data
utype can also parse function params and result
import utype from typing import Optional class PositiveInt(int, utype.Rule): gt = 0 class ArticleSchema(utype.Schema): id: Optional[PositiveInt] title: str = utype.Field(max_length=100) slug: str = utype.Field(regex=r"[a-z0-9]+(?:-[a-z0-9]+)*") @utype.parse def get_article(id: PositiveInt = None, title: str = '') -> ArticleSchema: return { 'id': id, 'title': title, 'slug': '-'.join([''.join( filter(str.isalnum, v)) for v in title.split()]).lower() } print(get_article('3', title=b'My Awesome Article!')) #> ArticleSchema(id=3, title='My Awesome Article!', slug='my-awesome-article') try: get_article('-1') except utype.exc.ParseError as e: print(e) """ parse item: ['id'] failed: Constraint: : 0 violated """ try: get_article(title='*' * 101) except utype.exc.ParseError as e: print(e) """ parse item: ['<return>'] failed: parse item: ['title'] failed: Constraint: <max_length>: 100 violated """
You can easily get type checking and code completion of IDEs (such as Pycharm, VS Code) during development
utype supports not only normal functions, but also generator functions, asynchronous functions, and asynchronous generator functions with the same usage
import utype import asyncio from typing import AsyncGenerator @utype.parse async def waiter(rounds: int = utype.Param(gt=0)) -> AsyncGenerator[int, float]: assert isinstance(rounds, int) i = rounds while i: wait = yield str(i) if wait: assert isinstance(wait, float) print(f'sleep for: {wait} seconds') await asyncio.sleep(wait) i -= 1 async def wait(): wait_gen = waiter('2') async for index in wait_gen: assert isinstance(index, int) try: await wait_gen.asend(b'0.5') # sleep for: 0.5 seconds except StopAsyncIteration: return if __name__ == '__main__': asyncio.run(wait())
The
AsyncGeneratortype is used to annotate the return value of the asynchronous generator, which has two parameters: the type of the value output byyield, type of the value sent byasend
As you can see, the parameters passed to the function and the value received from yield were all converted to the expected type as declared
utype supports logical operations on types and data structures using Python-native logical operators
from utype import Schema, Field from typing import Tuple class User(Schema): name: str = Field(max_length=10) age: int one_of_user = User ^ Tuple[str, int] print(one_of_user({'name': 'test', 'age': '1'})) # > User(name='test', age=1) print(one_of_user([b'test', '1'])) # > ('test', 1)
The example uses the ^ exclusive or symbol to logically combine User and Tuple[str, int], and the new logical type gains the ability to convert data to one of those
Type transformation and validation strictness required by each project may be different, so in utype, all types support registraton, extension and override, such as
from utype import Rule, Schema, register_transformer from typing import Type class Slug(str, Rule): regex = r"[a-z0-9]+(?:-[a-z0-9]+)*" @register_transformer(Slug) def to_slug(transformer, value, t: Type[Slug]): str_value = transformer(value, str) return t('-'.join([''.join( filter(str.isalnum, v)) for v in str_value.split()]).lower()) class ArticleSchema(Schema): slug: Slug print(dict(ArticleSchema(slug=b'My Awesome Article!'))) # > {'slug': 'my-awesome-article'}
You can register transformers not only for custom types, but also for basic types (such as str, int, etc.) Or types in the standard library (such as datetime, Enum, etc.) To customize the conversion behavior
utype is still growing, and the following features are planned for implementation in the new version
- Improve the handling mechanism of parsing errors, including error handling hook functions, etc.
- Support the declaration and parse command line parameters
- Support for Python generics, type variables, and more type annotation syntax
- Develop Pycharm/VS Code plugin that supports IDE detection and hints for constraints, logical types, and nested types
You are also welcome to contribute features or submit issues.
UtilMeta Python Framework is a progressive meta-framework for backend applications, which efficiently builds declarative APIs based on the Python type annotation standard, and supports the integration of mainstream Python frameworks as runtime backend
- Homepage: https://utilmeta.com/py
- Source Code: https://github.com/utilmeta/utilmeta-py
utype is a project of UtilMeta, so you can join the community in