Blacken code by default (#8611)

Make the Black workflow just run black with default settings. Instead of
including specific directories, exclude the ones that haven't been
blackened yet via `pyproject.toml`.

Leave a few small files out of the exclusion list; blacken them instead.

This is one step towards project-wide code formatting. It also makes it
easier to format your entire patch when you touch multiple components,
since you don't have to remember which directories to apply `black` to.

.github/workflows/black.yml

@@ -5,38 +5,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
-      - id: files
-        uses: tj-actions/[email protected]
-        with:
-          files: |
-              cvat-sdk/**/*.py
-              cvat-cli/**/*.py
-              tests/python/**/*.py
-              cvat/apps/quality_control/**/*.py
-              cvat/apps/analytics_report/**/*.py
-          dir_names: true
 
       - name: Run checks
-        env:
-          PR_FILES_AM: ${{ steps.files.outputs.added_modified }}
-          PR_FILES_RENAMED: ${{ steps.files.outputs.renamed }}
         run: |
-          # If different modules use different Black configs,
-          # we need to run Black for each python component group separately.
-          # Otherwise, they all will use the same config.
+          pipx install $(grep "^black" ./cvat-cli/requirements/development.txt)
 
-          UPDATED_DIRS="${{steps.files.outputs.all_changed_files}}"
+          echo "Black version: $(black --version)"
 
-          if [[ ! -z $UPDATED_DIRS ]]; then
-            pipx install $(egrep "black.*" ./cvat-cli/requirements/development.txt)
-
-            echo "Black version: "$(black --version)
-            echo "The dirs will be checked: $UPDATED_DIRS"
-            EXIT_CODE=0
-            for DIR in $UPDATED_DIRS; do
-              black --check --diff $DIR || EXIT_CODE=$(($? | $EXIT_CODE)) || true
-            done
-            exit $EXIT_CODE
-          else
-            echo "No files with the \"py\" extension found"
-          fi
+          black --check --diff .

cvat/__init__.py

@@ -4,6 +4,6 @@
 
 from cvat.utils.version import get_version
 
-VERSION = (2, 22, 0, 'alpha', 0)
+VERSION = (2, 22, 0, "alpha", 0)
 
 __version__ = get_version(VERSION)

cvat/apps/profiler.py

@@ -1,13 +1,16 @@
 from django.apps import apps
 
-if apps.is_installed('silk'):
+if apps.is_installed("silk"):
     from silk.profiling.profiler import silk_profile  # pylint: disable=unused-import
 else:
     from functools import wraps
+
     def silk_profile(name=None):
         def profile(f):
             @wraps(f)
             def wrapped(*args, **kwargs):
                 return f(*args, **kwargs)
+
             return wrapped
+
         return profile

cvat/asgi.py

@@ -24,6 +24,7 @@
 
 
 if debug.is_debugging_enabled():
+
     class DebuggerApp(ASGIHandler):
         """
         Support for VS code debugger

cvat/rq_patching.py

@@ -32,18 +32,25 @@ def custom_started_job_registry_cleanup(self, timestamp: Optional[float] = None)
     job_ids = self.get_expired_job_ids(score)
 
     if job_ids:
-        failed_job_registry = rq.registry.FailedJobRegistry(self.name, self.connection, serializer=self.serializer)
+        failed_job_registry = rq.registry.FailedJobRegistry(
+            self.name, self.connection, serializer=self.serializer
+        )
         queue = self.get_queue()
 
         with self.connection.pipeline() as pipeline:
             for job_id in job_ids:
                 try:
-                    job = self.job_class.fetch(job_id, connection=self.connection, serializer=self.serializer)
+                    job = self.job_class.fetch(
+                        job_id, connection=self.connection, serializer=self.serializer
+                    )
                 except NoSuchJobError:
                     continue
 
                 job.execute_failure_callback(
-                    self.death_penalty_class, AbandonedJobError, AbandonedJobError(), traceback.extract_stack()
+                    self.death_penalty_class,
+                    AbandonedJobError,
+                    AbandonedJobError(),
+                    traceback.extract_stack(),
                 )
 
                 retry = job.retries_left and job.retries_left > 0
@@ -54,8 +61,8 @@ def custom_started_job_registry_cleanup(self, timestamp: Optional[float] = None)
                 else:
                     exc_string = f"due to {AbandonedJobError.__name__}"
                     rq.registry.logger.warning(
-                        f'{self.__class__.__name__} cleanup: Moving job to {rq.registry.FailedJobRegistry.__name__} '
-                        f'({exc_string})'
+                        f"{self.__class__.__name__} cleanup: Moving job to {rq.registry.FailedJobRegistry.__name__} "
+                        f"({exc_string})"
                     )
                     job.set_status(JobStatus.FAILED)
                     job._exc_info = f"Moved to {rq.registry.FailedJobRegistry.__name__}, {exc_string}, at {datetime.now()}"
@@ -69,7 +76,8 @@ def custom_started_job_registry_cleanup(self, timestamp: Optional[float] = None)
 
     return job_ids
 
+
 def update_started_job_registry_cleanup() -> None:
     # don't forget to check if the issue https://github.com/rq/rq/issues/2006 has been resolved in upstream
-    assert VERSION == '1.16.0'
+    assert VERSION == "1.16.0"
     rq.registry.StartedJobRegistry.cleanup = custom_started_job_registry_cleanup

cvat/rqworker.py

@@ -42,12 +42,14 @@ def execute_job(self, *args, **kwargs):
         # errors during debugging
         # https://stackoverflow.com/questions/8242837/django-multiprocessing-and-database-connections/10684672#10684672
         from django import db
+
         db.connections.close_all()
 
         return self.perform_job(*args, **kwargs)
 
 
 if debug.is_debugging_enabled():
+
     class RemoteDebugWorker(SimpleWorker):
         """
         Support for VS code debugger
@@ -68,6 +70,7 @@ def execute_job(self, *args, **kwargs):
 
 if os.environ.get("COVERAGE_PROCESS_START"):
     import coverage
+
     default_exit = os._exit
 
     def coverage_exit(*args, **kwargs):

cvat/urls.py

@@ -23,31 +23,31 @@
 from django.urls import path, include
 
 urlpatterns = [
-    path('admin/', admin.site.urls),
-    path('', include('cvat.apps.engine.urls')),
-    path('django-rq/', include('django_rq.urls')),
+    path("admin/", admin.site.urls),
+    path("", include("cvat.apps.engine.urls")),
+    path("django-rq/", include("django_rq.urls")),
 ]
 
-if apps.is_installed('cvat.apps.log_viewer'):
-    urlpatterns.append(path('', include('cvat.apps.log_viewer.urls')))
+if apps.is_installed("cvat.apps.log_viewer"):
+    urlpatterns.append(path("", include("cvat.apps.log_viewer.urls")))
 
-if apps.is_installed('cvat.apps.events'):
-    urlpatterns.append(path('api/', include('cvat.apps.events.urls')))
+if apps.is_installed("cvat.apps.events"):
+    urlpatterns.append(path("api/", include("cvat.apps.events.urls")))
 
-if apps.is_installed('cvat.apps.lambda_manager'):
-    urlpatterns.append(path('', include('cvat.apps.lambda_manager.urls')))
+if apps.is_installed("cvat.apps.lambda_manager"):
+    urlpatterns.append(path("", include("cvat.apps.lambda_manager.urls")))
 
-if apps.is_installed('cvat.apps.webhooks'):
-    urlpatterns.append(path('api/', include('cvat.apps.webhooks.urls')))
+if apps.is_installed("cvat.apps.webhooks"):
+    urlpatterns.append(path("api/", include("cvat.apps.webhooks.urls")))
 
-if apps.is_installed('cvat.apps.quality_control'):
-    urlpatterns.append(path('api/', include('cvat.apps.quality_control.urls')))
+if apps.is_installed("cvat.apps.quality_control"):
+    urlpatterns.append(path("api/", include("cvat.apps.quality_control.urls")))
 
-if apps.is_installed('silk'):
-    urlpatterns.append(path('profiler/', include('silk.urls')))
+if apps.is_installed("silk"):
+    urlpatterns.append(path("profiler/", include("silk.urls")))
 
-if apps.is_installed('health_check'):
-    urlpatterns.append(path('api/server/health/', include('health_check.urls')))
+if apps.is_installed("health_check"):
+    urlpatterns.append(path("api/server/health/", include("health_check.urls")))
 
-if apps.is_installed('cvat.apps.analytics_report'):
-    urlpatterns.append(path('api/', include('cvat.apps.analytics_report.urls')))
+if apps.is_installed("cvat.apps.analytics_report"):
+    urlpatterns.append(path("api/", include("cvat.apps.analytics_report.urls")))

cvat/utils/background_jobs.py

@@ -7,12 +7,9 @@
 
 import django_rq
 
+
 def schedule_job_with_throttling(
-    queue_name: str,
-    job_id_base: str,
-    scheduled_time: datetime,
-    func: Callable,
-    **func_kwargs
+    queue_name: str, job_id_base: str, scheduled_time: datetime, func: Callable, **func_kwargs
 ) -> None:
     """
     This function schedules an RQ job to run at `scheduled_time`,

cvat/utils/http.py

@@ -19,11 +19,12 @@
 
 if settings.SMOKESCREEN_ENABLED:
     PROXIES_FOR_UNTRUSTED_URLS = {
-        'http': 'http://localhost:4750',
-        'https': 'http://localhost:4750',
+        "http": "http://localhost:4750",
+        "https": "http://localhost:4750",
     }
 
+
 def make_requests_session() -> requests.Session:
     session = requests.Session()
-    session.headers['User-Agent'] = _CVAT_USER_AGENT
+    session.headers["User-Agent"] = _CVAT_USER_AGENT
     return session

cvat/utils/remote_debugger.py

@@ -6,7 +6,8 @@
 
 
 def is_debugging_enabled() -> bool:
-    return os.environ.get('CVAT_DEBUG_ENABLED') == 'yes'
+    return os.environ.get("CVAT_DEBUG_ENABLED") == "yes"
+
 
 if is_debugging_enabled():
     import debugpy
@@ -21,8 +22,8 @@ class RemoteDebugger:
         Read more: https://modwsgi.readthedocs.io/en/develop/user-guides/debugging-techniques.html
         """
 
-        ENV_VAR_PORT = 'CVAT_DEBUG_PORT'
-        ENV_VAR_WAIT = 'CVAT_DEBUG_WAIT'
+        ENV_VAR_PORT = "CVAT_DEBUG_PORT"
+        ENV_VAR_WAIT = "CVAT_DEBUG_WAIT"
         __debugger_initialized = False
 
         @classmethod
@@ -35,7 +36,7 @@ def _singleton_init(cls):
 
                 # The only intended use is in Docker.
                 # Using 127.0.0.1 will not allow host connections
-                addr = ('0.0.0.0', port)  # nosec - B104:hardcoded_bind_all_interfaces
+                addr = ("0.0.0.0", port)  # nosec - B104:hardcoded_bind_all_interfaces
 
                 # Debugpy is a singleton
                 # We put it in the main thread of the process and then report new threads
@@ -45,7 +46,7 @@ def _singleton_init(cls):
                 # Feel free to enable if needed.
                 debugpy.configure({"subProcess": False})
 
-                if os.environ.get(cls.ENV_VAR_WAIT) == 'yes':
+                if os.environ.get(cls.ENV_VAR_WAIT) == "yes":
                     debugpy.wait_for_client()
             except Exception as ex:
                 raise Exception("failed to set debugger") from ex

cvat/utils/version.py

@@ -11,6 +11,7 @@
 import os
 import subprocess
 
+
 def get_version(version):
     """Return a PEP 440-compliant version number from VERSION."""
     # Now build the two parts of the version number:
@@ -20,21 +21,23 @@ def get_version(version):
 
     main = get_main_version(version)
 
-    sub = ''
-    if version[3] == 'alpha' and version[4] == 0:
+    sub = ""
+    if version[3] == "alpha" and version[4] == 0:
         git_changeset = get_git_changeset()
         if git_changeset:
-            sub = '.dev%s' % git_changeset
+            sub = ".dev%s" % git_changeset
 
-    elif version[3] != 'final':
-        mapping = {'alpha': 'a', 'beta': 'b', 'rc': 'rc'}
+    elif version[3] != "final":
+        mapping = {"alpha": "a", "beta": "b", "rc": "rc"}
         sub = mapping[version[3]] + str(version[4])
 
     return main + sub
 
+
 def get_main_version(version):
     """Return main version (X.Y.Z) from VERSION."""
-    return '.'.join(str(x) for x in version[:3])
+    return ".".join(str(x) for x in version[:3])
+
 
 def get_git_changeset():
     """Return a numeric identifier of the latest git changeset.
@@ -44,14 +47,16 @@ def get_git_changeset():
     so it's sufficient for generating the development version numbers.
     """
     repo_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
-    git_log = subprocess.Popen( # nosec: B603, B607
-        ['git', 'log', '--pretty=format:%ct', '--quiet', '-1', 'HEAD'],
-        stdout=subprocess.PIPE, stderr=subprocess.PIPE,
-        cwd=repo_dir, universal_newlines=True,
+    git_log = subprocess.Popen(  # nosec: B603, B607
+        ["git", "log", "--pretty=format:%ct", "--quiet", "-1", "HEAD"],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        cwd=repo_dir,
+        universal_newlines=True,
     )
     timestamp = git_log.communicate()[0]
     try:
         timestamp = datetime.datetime.fromtimestamp(int(timestamp), tz=datetime.timezone.utc)
     except ValueError:
         return None
-    return timestamp.strftime('%Y%m%d%H%M%S')
+    return timestamp.strftime("%Y%m%d%H%M%S")

dev/check_changelog_fragments.py

@@ -6,17 +6,18 @@
 
 REPO_ROOT = Path(__file__).resolve().parents[1]
 
+
 def main():
     scriv_config = configparser.ConfigParser()
-    scriv_config.read(REPO_ROOT / 'changelog.d/scriv.ini')
+    scriv_config.read(REPO_ROOT / "changelog.d/scriv.ini")
 
-    scriv_section = scriv_config['scriv']
-    assert scriv_section['format'] == 'md'
+    scriv_section = scriv_config["scriv"]
+    assert scriv_section["format"] == "md"
 
-    md_header_level = int(scriv_section['md_header_level'])
-    md_header_prefix = '#' * md_header_level + '# '
+    md_header_level = int(scriv_section["md_header_level"])
+    md_header_prefix = "#" * md_header_level + "# "
 
-    categories = {s.strip() for s in scriv_section['categories'].split(',')}
+    categories = {s.strip() for s in scriv_section["categories"].split(",")}
 
     success = True
 
@@ -25,12 +26,12 @@ def complain(message):
         success = False
         print(f"{fragment_path.relative_to(REPO_ROOT)}:{line_index+1}: {message}", file=sys.stderr)
 
-    for fragment_path in REPO_ROOT.glob('changelog.d/*.md'):
+    for fragment_path in REPO_ROOT.glob("changelog.d/*.md"):
         with open(fragment_path) as fragment_file:
             for line_index, line in enumerate(fragment_file):
                 if not line.startswith(md_header_prefix):
                     # The first line should be a header, and all headers should be of appropriate level.
-                    if line_index == 0 or line.startswith('#'):
+                    if line_index == 0 or line.startswith("#"):
                         complain(f"line should start with {md_header_prefix!r}")
                     continue
 
@@ -40,4 +41,5 @@ def complain(message):
 
     sys.exit(0 if success else 1)
 
+
 main()