Fix: Resolve linting issues (#5011)

## Description
This pull request addresses and resolves several linting issues,
primarily focusing on `line-too-long` errors reported by `pylint` and
`yapf` formatting conflicts.

### Problem
Initially, running `python butler.py lint` reported `C0301: Line too
long` errors in `src/local/butler/common.py`. Attempts to manually break
these lines were reverted by `yapf` during the formatting step, creating
a loop where `yapf` would reformat the lines to be long, and `pylint`
would then flag them again.

Further investigation revealed that long comments were also contributing
to the `line-too-long` errors.

### Solution
1. **Manual Line Breaking:** The excessively long lines in
`src/local/butler/common.py` were manually broken into multiple lines to
comply with the 80-character limit.
2. **Comment Refactoring:** Long comments that exceeded the line length
limit were refactored and broken into multiple lines for better
readability and to satisfy linting rules.
3. **Re-running Formatters:** After manual adjustments, `python
butler.py format` was executed to ensure consistency with the project's
formatting guidelines. This step confirmed that the manual line breaks
were preserved and no new `line-too-long` issues were introduced by
`yapf`.

### Verification
After applying the fixes and re-running the formatters, `python
butler.py lint` was executed again, and all linting checks passed
successfully.

This ensures that the codebase now adheres to the established style
guidelines without conflicts between the linter and formatter.

Author: hunsche

.github/workflows/tests.yaml

@@ -23,8 +23,9 @@ jobs:
 
     steps:
       - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
+      - run: |  # Needed for git diff to work.
+          git fetch origin master --depth 1
+          git symbolic-ref refs/remotes/origin/HEAD refs/remotes/origin/master
 
       - name: Setup python environment
         uses: actions/setup-python@b55428b1882923874294fa556849718a1d7f2ca5

local/polymer_bundler.py

@@ -36,14 +36,12 @@ def build_file(filename):
   """Build a single file using polymer-bundler."""
   input_filename = os.path.join('private', 'templates', filename)
   output_filename = os.path.join('templates', filename)
-  subprocess.run([
-      'polymer-bundler',
-      '--inline-scripts',
-      '--inline-css',
-      '--strip-comments',
-      f'--out-file={output_filename}',
-      input_filename
-  ], check=True)
+  subprocess.run(
+      [
+          'polymer-bundler', '--inline-scripts', '--inline-css',
+          '--strip-comments', f'--out-file={output_filename}', input_filename
+      ],
+      check=True)
 
   if os.path.exists(output_filename) and os.path.getsize(output_filename):
     return True

src/appengine/handlers/corpora.py

@@ -86,12 +86,12 @@ def post(self):
     template_values = {
         'title':
             'Success',
-        'message':
-            ('Upload data to the corpus using: ' +
-             ('gcloud storage rsync -r <local_corpus_directory> {bucket_url}'
-              if gsutil.use_gcloud_for_command('rsync') else
-              'gsutil -d -m rsync -r <local_corpus_directory> {bucket_url}'
-             ).format(bucket_url=bucket_url)),
+        'message': (
+            'Upload data to the corpus using: ' +
+            ('gcloud storage rsync -r <local_corpus_directory> {bucket_url}'
+             if gsutil.use_gcloud_for_command('rsync') else
+             'gsutil -d -m rsync -r <local_corpus_directory> {bucket_url}'
+            ).format(bucket_url=bucket_url)),
     }
     return self.render('message.html', template_values)
 

src/appengine/handlers/testcase_detail/show.py

@@ -633,6 +633,7 @@ def post(self):
     testcase_id = flask.request.get('testcaseId')
     return self.render_json(get_testcase_detail_by_id(testcase_id))
 
+
 class TaskLogHandler(base_handler.Handler):
   """Handler for downloading a task's log."""
 

src/clusterfuzz/_internal/base/tasks/__init__.py

@@ -321,10 +321,16 @@ def get_postprocess_task():
 
 
 def allow_all_tasks():
+  """Returns True if the bot should be allowed to execute any task.
+
+  Preemptible bots are not allowed to execute all tasks, because some tasks
+  are not safe to be preempted.
+  """
   return not environment.get_value('PREEMPTIBLE')
 
 
 def get_preprocess_task():
+  """Get a preprocess task."""
   queue_name = PREPROCESS_QUEUE
   base_os_version = environment.get_value('BASE_OS_VERSION')
   if base_os_version:

src/clusterfuzz/_internal/cron/grouper.py

@@ -359,27 +359,23 @@ def _compare_testcases_crash_states(testcase_1, testcase_2) -> bool:
       testcase_2.crash_type in data_types.CRASH_TYPES_WITH_UNIQUE_STATE):
 
     # For grouping, make sure that both crash type and state match exactly.
-    return (
-      testcase_1.crash_type == testcase_2.crash_type and
-      testcase_1.crash_state == testcase_2.crash_state
-    )
+    return (testcase_1.crash_type == testcase_2.crash_type and
+            testcase_1.crash_state == testcase_2.crash_state)
 
   crash_comparer_type = CrashComparer(
-      testcase_1.crash_type, testcase_2.crash_type,
-      CRASH_COMPARER_THRESHOLD, CRASH_COMPARER_SAME_FRAMES)
+      testcase_1.crash_type, testcase_2.crash_type, CRASH_COMPARER_THRESHOLD,
+      CRASH_COMPARER_SAME_FRAMES)
   crash_comparer_state = CrashComparer(
-      testcase_1.crash_state, testcase_2.crash_state,
-      CRASH_COMPARER_THRESHOLD, CRASH_COMPARER_SAME_FRAMES)
+      testcase_1.crash_state, testcase_2.crash_state, CRASH_COMPARER_THRESHOLD,
+      CRASH_COMPARER_SAME_FRAMES)
 
   # Rule: Security bugs: Only the crash state matters, if any.
   if (testcase_1.security_flag and testcase_1.crash_state != 'NULL' and
       testcase_2.security_flag and testcase_2.crash_state != 'NULL'):
     return crash_comparer_state.is_similar()
 
-  return (
-      crash_comparer_state.is_similar() and
-      crash_comparer_type.is_similar()
-  )
+  return (crash_comparer_state.is_similar() and
+          crash_comparer_type.is_similar())
 
 
 def _group_testcases_with_similar_states(testcase_map):

src/clusterfuzz/_internal/google_cloud_utils/gsutil.py

@@ -28,8 +28,7 @@
 
 def use_gcloud_for_command(command):
   """Returns whether to use gcloud storage for the given command."""
-  return bool(
-      environment.get_value(f'USE_GCLOUD_STORAGE_{command.upper()}'))
+  return bool(environment.get_value(f'USE_GCLOUD_STORAGE_{command.upper()}'))
 
 
 def get_gcloud_path():
@@ -133,14 +132,10 @@ def _get_runner_and_args(self, use_gcloud_storage, quiet=False):
 
     return runner, additional_args
 
-  def run_gsutil(self,
-                 arguments,
-                 use_gcloud_storage,
-                 quiet=False,
-                 **kwargs):
+  def run_gsutil(self, arguments, use_gcloud_storage, quiet=False, **kwargs):
     """Run GSUtil or gcloud storage."""
-    runner, additional_args = self._get_runner_and_args(
-        use_gcloud_storage, quiet)
+    runner, additional_args = self._get_runner_and_args(use_gcloud_storage,
+                                                        quiet)
     arguments = additional_args + arguments
 
     env = os.environ.copy()
@@ -178,15 +173,13 @@ def rsync(self,
         _filter_path(destination, write=True),
     ])
 
-    return self.run_gsutil(
-        command, use_gcloud, timeout=timeout, quiet=True)
+    return self.run_gsutil(command, use_gcloud, timeout=timeout, quiet=True)
 
   def download_file(self, gcs_url, file_path, timeout=None):
     """Download a file from GCS."""
     use_gcloud = use_gcloud_for_command('cp')
     command = ['cp', _filter_path(gcs_url), file_path]
-    result = self.run_gsutil(
-        command, use_gcloud, timeout=timeout)
+    result = self.run_gsutil(command, use_gcloud, timeout=timeout)
     if result.return_code:
       logs.error('GSUtilRunner.download_file failed:\nCommand: %s\n'
                  'Url: %s\n'
@@ -212,8 +205,7 @@ def upload_file(self,
         cp_command.append('--gzip-in-flight-all')
 
       cp_command.extend([file_path, _filter_path(gcs_url, write=True)])
-      result = self.run_gsutil(
-          cp_command, use_gcloud, timeout=timeout)
+      result = self.run_gsutil(cp_command, use_gcloud, timeout=timeout)
 
       if result.return_code != 0:
         logs.error('GSUtilRunner.upload_file (cp step) failed:\nCommand: %s\n'
@@ -233,8 +225,7 @@ def upload_file(self,
         # pylint: disable=line-too-long
         update_command.append(','.join(metadata_args))
 
-        result = self.run_gsutil(
-            update_command, use_gcloud, timeout=timeout)
+        result = self.run_gsutil(update_command, use_gcloud, timeout=timeout)
         if result.return_code != 0:
           logs.error(
               'GSUtilRunner.upload_file (update metadata step) failed:\nCommand: %s\n'
@@ -258,8 +249,7 @@ def upload_file(self,
       command.append('-Z')
 
     command.extend([file_path, _filter_path(gcs_url, write=True)])
-    result = self.run_gsutil(
-        command, use_gcloud, timeout=timeout)
+    result = self.run_gsutil(command, use_gcloud, timeout=timeout)
 
     if result.return_code:
       logs.error('GSUtilRunner.upload_file failed:\nCommand: %s\n'

src/clusterfuzz/_internal/scripts/copy_corpus.py

@@ -87,7 +87,8 @@ def _copy_corpus(source_bucket, source_project, target_bucket, target_project):
     target_url = '%s/%s' % (url_part, fuzz_target)
 
     _run_command(
-        [GSUTIL_CMD, '-m', 'rsync', '-d', '-r', source_url, target_url], 'rsync')
+        [GSUTIL_CMD, '-m', 'rsync', '-d', '-r', source_url, target_url],
+        'rsync')
 
   print('Copy corpus finished successfully.')
 

src/clusterfuzz/_internal/tests/appengine/handlers/cron/grouper_test.py

@@ -84,6 +84,7 @@ def test_same_crash_different_security(self):
   # Regression test for https://issues.chromium.org/issues/443261679
   def test_security_crash_state_null(self):
     """Test grouping of crashes with NULL state for security issues"""
+
     def group():
       """Helper to group and return testcase ids."""
       for t in self.testcases:
@@ -118,7 +119,6 @@ def group():
     self.testcases[1].crash_type = 'Heap-buffer-overflow'
     self.assertEqual(len(group()), 2)
 
-
   def test_same_crash_same_security(self):
     """Test that crashes with same crash states and same security flags get
     de-duplicated with one of them removed."""

src/clusterfuzz/_internal/tests/core/crash_analysis/stack_parsing/stack_analyzer_test.py

@@ -2862,8 +2862,7 @@ def test_check_eq_multiline(self):
     expected_state = (
         'std::string_view(content::indexed_db::EncodeSortableIDBKey(key)) == input (0wwwy\n'
         'InvokeCallback\n'
-        '~Cleanup\n'
-    )
+        '~Cleanup\n')
     expected_stacktrace = data
     expected_security_flag = False
 
@@ -2880,8 +2879,7 @@ def test_check_eq_multiline2(self):
     expected_state = (
         'std::string_view(content::indexed_db::EncodeSortableIDBKey(key)) == input in ind\n'
         'InvokeCallback\n'
-        '~Cleanup\n'
-    )
+        '~Cleanup\n')
     expected_stacktrace = data
     expected_security_flag = False