secator 0.0.1__py3-none-any.whl → 0.3.5__py3-none-any.whl

secator/.gitignore

@@ -0,0 +1,162 @@
+# ---> Python
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

secator/celery.py

@@ -3,11 +3,10 @@ import logging
 import traceback
 from time import sleep
 
-import celery
-from celery import chain, chord, signals
+from celery import Celery, chain, chord, signals
 from celery.app import trace
 from celery.result import AsyncResult, allow_join_result
-# from pyinstrument import Profiler
+# from pyinstrument import Profiler  # TODO: make pyinstrument optional
 from rich.logging import RichHandler
 
 from secator.definitions import (CELERY_BROKER_CONNECTION_TIMEOUT,
@@ -20,11 +19,10 @@ from secator.rich import console
 from secator.runners import Scan, Task, Workflow
 from secator.runners._helpers import run_extractors
 from secator.utils import (TaskError, debug, deduplicate,
-						   discover_external_tasks, discover_internal_tasks,
 						   flatten)
 
 # from pathlib import Path
-# import memray
+# import memray  # TODO: conditional memray tracing
 
 rich_handler = RichHandler(rich_tracebacks=True)
 rich_handler.setLevel(logging.INFO)
@@ -42,9 +40,8 @@ logger = logging.getLogger(__name__)
 trace.LOG_SUCCESS = """\
 Task %(name)s[%(id)s] succeeded in %(runtime)ss\
 """
-COMMANDS = discover_internal_tasks() + discover_external_tasks()
 
-app = celery.Celery(__name__)
+app = Celery(__name__)
 app.conf.update({
 	# Worker config
 	'worker_send_task_events': True,
@@ -56,6 +53,7 @@ app.conf.update({
 	'broker_transport_options': {
 		'data_folder_in': CELERY_DATA_FOLDER,
 		'data_folder_out': CELERY_DATA_FOLDER,
+		'control_folder': CELERY_DATA_FOLDER,
 		'visibility_timeout': CELERY_BROKER_VISIBILITY_TIMEOUT,
 	},
 	'broker_connection_retry_on_startup': True,
@@ -109,7 +107,7 @@ def void(*args, **kwargs):
 
 def revoke_task(task_id):
 	console.print(f'Revoking task {task_id}')
-	return app.control.revoke(task_id, terminate=True, signal='SIGKILL')
+	return app.control.revoke(task_id, terminate=True, signal='SIGINT')
 
 
 #--------------#
@@ -322,11 +320,6 @@ def run_command(self, results, name, targets, opts={}):
 			else:  # full traceback
 				exc_str = ' '.join(traceback.format_exception(task_exc, value=task_exc, tb=task_exc.__traceback__))
 			state['meta'][msg_type] = exc_str
-			if task:
-				color = 'bold red' if msg_type == 'error' else 'green'
-				task._print(exc_str, color=color)
-			else:
-				console.log(exc_str)
 
 		# Update task state with final status
 		self.update_state(**state)
@@ -371,11 +364,6 @@ def forward_results(results):
 # Celery result utils #
 #---------------------#
 
-def find_root_task(result):
-	while (result.parent is not None):
-		result = result.parent
-	return result
-
 
 def poll_task(result, seen=[]):
 	"""Poll Celery result tree recursively to get results live.
@@ -423,60 +411,12 @@ def poll_task(result, seen=[]):
 			yield from poll_task(result, seen=seen)
 
 
-def get_results(result):
-	"""Get all intermediate results from Celery result object.
-
-	Use this when running complex workflows with .si() i.e not passing results
-	between tasks.
-
-	Args:
-		result (Union[AsyncResult, GroupResult]): Celery result.
-
-	Returns:
-		list: List of results.
-	"""
-	while not result.ready():
-		continue
-	results = []
-	get_nested_results(result, results=results)
-	return results
-
-
-def get_nested_results(result, results=[]):
-	"""Get results recursively from Celery result object by parsing result tree
-	in reverse order. Also gets results from GroupResult children.
-
-	Args:
-		result (Union[AsyncResult, GroupResult]): Celery result object.
-
-	Returns:
-		list: List of results.
-	"""
-	if result is None:
-		return
-
-	if isinstance(result, celery.result.GroupResult):
-		console.log(repr(result))
-		get_nested_results(result.parent, results=results)
-		for child in result.children:
-			get_nested_results(child, results=results)
-
-	elif isinstance(result, celery.result.AsyncResult):
-		console.log(repr(result))
-		res = result.get()
-		console.log(f'-> Found {len(res)} results.')
-		console.log(f'-> {res}')
-		if res is not None:
-			results.extend(res)
-		get_nested_results(result.parent, results=results)
-
-
 def is_celery_worker_alive():
 	"""Check if a Celery worker is available."""
 	result = app.control.broadcast('ping', reply=True, limit=1, timeout=1)
 	result = bool(result)
 	if result:
 		console.print('Celery worker is alive !', style='bold green')
-	else:
-		console.print('No Celery worker alive.', style='bold red')
+	# else:
+		# console.print('No Celery worker alive.', style='bold red')
 	return result