Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

gokart.build(reset_register=False) can use PandasTypeConfig #335

Merged
merged 5 commits into from
Nov 21, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions gokart/build.py
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@

import luigi

import gokart
from gokart.task import TaskOnKart


Expand Down Expand Up @@ -38,8 +39,11 @@ def _get_output(task: TaskOnKart) -> Any:


def _reset_register(keep={'gokart', 'luigi'}):
luigi.task_register.Register._reg = [x for x in luigi.task_register.Register._reg
if x.__module__.split('.')[0] in keep] # avoid TaskClassAmbigiousException
"""reset luigi.task_register.Register._reg everytime gokart.build called to avoid TaskClassAmbigiousException"""
luigi.task_register.Register._reg = [
x for x in luigi.task_register.Register._reg if ((x.__module__.split('.')[0] in keep) # keep luigi and gokart
or (issubclass(x, gokart.PandasTypeConfig))) # PandasTypeConfig should be kept
]


def build(task: TaskOnKart, return_value: bool = True, reset_register: bool = True, log_level: int = logging.ERROR, **env_params) -> Optional[Any]:
Expand Down
3 changes: 2 additions & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,8 @@ types-redis = "*"
[tool.flake8]
# B006: Do not use mutable data structures for argument defaults. They are created during function definition time. All calls to the function reuse this one instance of that data structure, persisting changes between them.
# B008 Do not perform function calls in argument defaults. The call is performed only once at function definition time. All calls to your function will reuse the result of that definition-time function call. If this is intended, assign the function call to a module-level variable and use that variable as a default value.
ignore = "B006,B008"
# W503 line break before binary operator. We use W504(line break after binary operator) rather than W503
ignore = "B006,B008,W503"
max-line-length = 160
exclude = "venv/*,tox/*"

Expand Down
25 changes: 14 additions & 11 deletions test/test_pandas_type_check_framework.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import logging
import unittest
from logging import getLogger
from typing import Any, Dict
Expand All @@ -8,6 +9,7 @@
from luigi.mock import MockFileSystem, MockTarget

import gokart
from gokart.build import GokartBuildError
from gokart.pandas_type_config import PandasTypeConfig

logger = getLogger(__name__)
Expand Down Expand Up @@ -63,28 +65,29 @@ def setUp(self) -> None:
luigi.setup_logging.DaemonLogging._configured = False
luigi.setup_logging.InterfaceLogging._configured = False
MockFileSystem().clear()
# same way as luigi https://github.com/spotify/luigi/blob/fe7ecf4acf7cf4c084bd0f32162c8e0721567630/test/helpers.py#L175
self._stashed_reg = luigi.task_register.Register._get_reg()

def tearDown(self) -> None:
luigi.setup_logging.DaemonLogging._configured = False
luigi.setup_logging.InterfaceLogging._configured = False
luigi.task_register.Register._set_reg(self._stashed_reg)

@patch('sys.argv', new=['main', 'test_pandas_type_check_framework._DummyFailTask', '--log-level=CRITICAL', '--local-scheduler', '--no-lock'])
@patch('luigi.LocalTarget', new=lambda path, **kwargs: MockTarget(path, **kwargs))
def test_fail(self):
def test_fail_with_gokart_run(self):
with self.assertRaises(SystemExit) as exit_code:
gokart.run()
self.assertNotEqual(exit_code.exception.code, 0) # raise Error

@patch('sys.argv', new=['main', 'test_pandas_type_check_framework._DummyFailWithNoneTask', '--log-level=CRITICAL', '--local-scheduler', '--no-lock'])
@patch('luigi.LocalTarget', new=lambda path, **kwargs: MockTarget(path, **kwargs))
def test_fail(self):
with self.assertRaises(GokartBuildError):
gokart.build(_DummyFailTask(), log_level=logging.CRITICAL)

def test_fail_with_None(self):
with self.assertRaises(SystemExit) as exit_code:
gokart.run()
self.assertNotEqual(exit_code.exception.code, 0) # raise Error
with self.assertRaises(GokartBuildError):
gokart.build(_DummyFailWithNoneTask(), log_level=logging.CRITICAL)

@patch('sys.argv', new=['main', 'test_pandas_type_check_framework._DummySuccessTask', '--log-level=CRITICAL', '--local-scheduler', '--no-lock'])
@patch('luigi.LocalTarget', new=lambda path, **kwargs: MockTarget(path, **kwargs))
def test_success(self):
with self.assertRaises(SystemExit) as exit_code:
gokart.run()
self.assertEqual(exit_code.exception.code, 0)
gokart.build(_DummySuccessTask())
# no error