Fix SonarCloud MINOR CODE_SMELL issues: S7508, S6353, S7504, S7500, S8521, S7519, S7494

- Fix python:S7508 (redundant list() before sorted()) in anonymized_rollups.py,
  credentials_anonymized_rollup.py, events_modules_anonymized_rollup.py,
  test_jobs_anonymized_rollups.py, test_multiple_files.py, report/base.py:
  Removed unnecessary list() wrapping since sorted() accepts any iterable.
- Fix python:S6353 (use \w instead of [A-Za-z0-9_]) in events_modules_anonymized_rollup.py:
  Simplified regex patterns to use \w shorthand.
- Fix python:S7504 (unnecessary list() on iterable) in renewal_guidance.py:
  Removed redundant list() in list comprehension iteration.
- Fix python:S7500 (replace comprehension with collection constructor) in
  conftest.py and report_saver_s3.py: Simplified unnecessary comprehension wrappers.
- Fix python:S8521 (unnecessary .keys() call) in test_gathering.py and test_slicing.py:
  Removed .keys() calls since dict membership testing is implicit.
- Fix python:S7519 (use dict.fromkeys) in management_utility.py: Replaced dict
  comprehension with dict.fromkeys() call.
- Fix python:S7494 (use set comprehension) in main_jobevent_service.py: Replaced
  set() constructor with generator with a set comprehension literal.

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>

Author: cshiels-ie

metrics_utility/anonymized_rollups/anonymized_rollups.py

@@ -275,7 +275,7 @@ def _merge_ansible_versions(jobs_by_job_type: List[Dict[str, Any]]) -> List[str]
         ansible_versions = job.get('ansible_versions', [])
         if isinstance(ansible_versions, list):
             ansible_versions_set.update(ansible_versions)
-    return sorted(list(ansible_versions_set)) if ansible_versions_set else []
+    return sorted(ansible_versions_set) if ansible_versions_set else []
 
 
 def _calculate_execution_environments_total(execution_environments: Dict[str, Any]) -> Any:

metrics_utility/anonymized_rollups/credentials_anonymized_rollup.py

@@ -67,7 +67,7 @@ def merge(self, data_all, data_new):
         credential_types_new = set(data_new.get('credential_types', []))
 
         # Union the sets and convert back to sorted list
-        credential_types_merged = sorted(list(credential_types_all.union(credential_types_new)))
+        credential_types_merged = sorted(credential_types_all.union(credential_types_new))
 
         return {
             'credential_types': credential_types_merged,

metrics_utility/anonymized_rollups/events_modules_anonymized_rollup.py

@@ -11,8 +11,8 @@
 
 # Regex pattern to match collection names (e.g., namespace.collection.role or namespace.collection.role.task)
 # Pattern is safe from reDOS: uses non-capturing groups and non-nested quantifiers
-_COLLECTION_RE = re.compile(r'^([A-Za-z0-9_]+)\.([A-Za-z0-9_]+)\.[A-Za-z0-9_]+(?:\.[A-Za-z0-9_]+)*$')
-_COLLECTION_PATTERN = r'^([A-Za-z0-9_]+\.[A-Za-z0-9_]+)\.[A-Za-z0-9_]+(?:\.[A-Za-z0-9_]+)*$'
+_COLLECTION_RE = re.compile(r'^(\w+)\.(\w+)\.\w+(?:\.\w+)*$')
+_COLLECTION_PATTERN = r'^(\w+\.\w+)\.\w+(?:\.\w+)*$'
 
 
 def extract_collection_name(x: str | None) -> str | None:
@@ -138,7 +138,7 @@ def _merge_list_columns(self, item_all, item_new, merged_item):
             list_new = item_new.get(col) if item_new.get(col) is not None else []
             set_all = set(list_all) if isinstance(list_all, list) else set()
             set_new = set(list_new) if isinstance(list_new, list) else set()
-            merged_item[col] = sorted(list(set_all.union(set_new)))
+            merged_item[col] = sorted(set_all.union(set_new))
 
     def _merge_single_item(self, item_all, item_new):
         """Merge a single item from all and new data."""
@@ -184,7 +184,7 @@ def _merge_unique_modules(self, data_all, data_new):
         """Merge unique_modules lists (union and sort)."""
         unique_modules_all = set(data_all.get('unique_modules', []))
         unique_modules_new = set(data_new.get('unique_modules', []))
-        return sorted(list(unique_modules_all.union(unique_modules_new)))
+        return sorted(unique_modules_all.union(unique_modules_new))
 
     def _merge_modules_per_playbook(self, data_all, data_new):
         """Merge modules_per_playbook dicts (union lists per playbook)."""
@@ -197,14 +197,14 @@ def _merge_modules_per_playbook(self, data_all, data_new):
             list_new = modules_per_playbook_new.get(playbook, []) or []
             set_all = set(list_all) if isinstance(list_all, list) else set()
             set_new = set(list_new) if isinstance(list_new, list) else set()
-            modules_per_playbook[playbook] = sorted(list(set_all.union(set_new)))
+            modules_per_playbook[playbook] = sorted(set_all.union(set_new))
         return modules_per_playbook
 
     def _merge_unique_hosts(self, data_all, data_new):
         """Merge unique_hosts lists (union and sort)."""
         unique_hosts_all = set(data_all.get('unique_hosts', []))
         unique_hosts_new = set(data_new.get('unique_hosts', []))
-        return sorted(list(unique_hosts_all.union(unique_hosts_new)))
+        return sorted(unique_hosts_all.union(unique_hosts_new))
 
     def merge(self, data_all, data_new):
         """
@@ -515,7 +515,7 @@ def _compute_all_stats(self, task_summary):
     def _convert_set_or_list_to_sorted_list(value):
         """Convert set or list to sorted list, return empty list for other types."""
         if isinstance(value, set):
-            return sorted(list(value))
+            return sorted(value)
         if isinstance(value, list):
             return value
         return []
@@ -557,15 +557,15 @@ def _convert_stats_to_json(self, module_stats, collection_stats, role_stats):
 
     def _compute_unique_metadata(self, task_summary):
         """Compute unique_modules, modules_per_playbook, and unique_hosts."""
-        unique_modules = sorted(list(set(task_summary['module_name'].dropna().unique())))
+        unique_modules = sorted(set(task_summary['module_name'].dropna().unique()))
 
         modules_per_playbook = {}
         for playbook in task_summary['playbook'].dropna().unique():
-            modules_in_playbook = sorted(list(set(task_summary[task_summary['playbook'] == playbook]['module_name'].dropna().unique())))
+            modules_in_playbook = sorted(set(task_summary[task_summary['playbook'] == playbook]['module_name'].dropna().unique()))
             modules_per_playbook[playbook] = modules_in_playbook
 
         host_sets = [s for s in task_summary['host_ids'].dropna() if isinstance(s, set)]
-        unique_hosts = sorted(list(set().union(*host_sets))) if host_sets else []
+        unique_hosts = sorted(set().union(*host_sets)) if host_sets else []
 
         return unique_modules, modules_per_playbook, unique_hosts
 

metrics_utility/automation_controller_billing/dedup/renewal_guidance.py

@@ -47,7 +47,7 @@ def _build_deduped_record(self, dupes, latest_hostname, dupes_clean=None):
 
     def stringify(self, value):
         """Convert a set of values to a comma-separated string, filtering out None."""
-        return ', '.join([v for v in list(value) if v is not None])
+        return ', '.join([v for v in value if v is not None])
 
     def run(self):
         """Abstract method to be implemented by subclasses."""

metrics_utility/automation_controller_billing/report/base.py

@@ -86,14 +86,14 @@ def add_dedup_labels_if_needed(self, labels, column_names):
     def convert_cell(self, cell):
         # If the cell is a dictionary, convert each set value to a sorted list, then dump as a JSON string.
         if isinstance(cell, dict):
-            new_cell = {k: sorted(list(v)) if isinstance(v, set) else v for k, v in cell.items()}
+            new_cell = {k: sorted(v) if isinstance(v, set) else v for k, v in cell.items()}
             return json.dumps(new_cell)
         # If the cell itself is a set, convert it to a sorted list and then to a JSON string.
         elif isinstance(cell, set):
-            return json.dumps(sorted(list(cell)))
+            return json.dumps(sorted(cell))
         # If the cell is a list, convert any set elements inside to sorted lists and dump as a JSON string.
         elif isinstance(cell, list):
-            new_cell = [sorted(list(item)) if isinstance(item, set) else item for item in cell]
+            new_cell = [sorted(item) if isinstance(item, set) else item for item in cell]
             # Sort the list itself if it contains strings
             if new_cell and all(isinstance(item, str) for item in new_cell):
                 new_cell = sorted(new_cell)

metrics_utility/automation_controller_billing/report_saver/report_saver_s3.py

@@ -16,7 +16,7 @@ def __init__(self, extra_params):
         self.s3_handler = S3Handler(params=self.extra_params)
 
     def report_exist(self):
-        return len([file for file in self.s3_handler.list_files(self.report_spreadsheet_destination_path)]) > 0
+        return len(list(self.s3_handler.list_files(self.report_spreadsheet_destination_path))) > 0
 
     def save(self, report_spreadsheet):
         with tempfile.TemporaryDirectory(prefix='report_saver_billing_data_') as temp_dir:

metrics_utility/library/collectors/controller/main_jobevent_service.py

@@ -31,7 +31,7 @@ def main_jobevent_service(*, db=None, since=None, until=None, output=DataframeOu
     # We are loading the finished jobs then we are filtering
     # for the job_created, this cannot be done by simple joins because
     # job_created is partitioned and partitions pruning dont work with joins
-    job_ids_set = set(job_id for job_id, _ in jobs)
+    job_ids_set = {job_id for job_id, _ in jobs}
 
     # Extract unique hour boundaries from job_created timestamps
     # This reduces potentially 100K timestamps down to ~100-1000 hourly ranges

metrics_utility/management_utility.py

@@ -77,7 +77,7 @@ def fetch_command(self, subcommand):
     def get_commands():
         commands = {}
         path = os.path.join(os.path.dirname(__file__), 'management')
-        commands.update({name: 'metrics_utility' for name in management.find_commands(path)})
+        commands.update(dict.fromkeys(management.find_commands(path), 'metrics_utility'))
         return commands
 
     def run_subcommand(self, subcommand, argv):

metrics_utility/test/base/functional/test_gathering.py

@@ -43,8 +43,8 @@ def test_json_collections(collector):
             files[member.name] = archive.extractfile(member)
 
         assert_common_files(files)
-        assert './json_collection_1.json' in files.keys()
-        assert './json_collection_2.json' in files.keys()
+        assert './json_collection_1.json' in files
+        assert './json_collection_2.json' in files
 
         assert json.loads(files['./config.json'].read()) == {'version': '1.0'}
         assert json.loads(files['./json_collection_1.json'].read()) == {'json1': 'True'}
@@ -64,9 +64,9 @@ def test_small_csvs(collector):
             files[member.name] = archive.extractfile(member)
 
         assert_common_files(files)
-        assert './csv_collection_1.csv' in files.keys()
-        assert './csv_collection_2.csv' in files.keys()
-        assert './csv_collection_3.csv' in files.keys()
+        assert './csv_collection_1.csv' in files
+        assert './csv_collection_2.csv' in files
+        assert './csv_collection_3.csv' in files
 
         # length defined by @registered function
         assert len(files['./csv_collection_1.csv'].read()) == 100
@@ -97,13 +97,13 @@ def test_jsons_with_csvs_with_slicing(collector):
 
             assert_common_files(files)
             if i == 0:
-                assert './json_collection_1.json' in files.keys()
-                assert './json_collection_2.json' in files.keys()
-                assert './csv_slicing_1.csv' in files.keys()
+                assert './json_collection_1.json' in files
+                assert './json_collection_2.json' in files
+                assert './csv_slicing_1.csv' in files
             if i == 1:
-                assert './csv_slicing_2.csv' in files.keys()
+                assert './csv_slicing_2.csv' in files
             if i == 2:
-                assert './csv_slicing_2.csv' in files.keys()
+                assert './csv_slicing_2.csv' in files
 
 
 def test_one_csv_collection_splitted_by_size(collector):
@@ -119,7 +119,7 @@ def test_one_csv_collection_splitted_by_size(collector):
 
             assert_common_files(files)
             assert len(files.keys()) == 1 + _common_files_count()
-            assert './big_table.csv' in files.keys()
+            assert './big_table.csv' in files
             assert len(files['./big_table.csv'].read()) == 1000
 
     collector._gather_cleanup()
@@ -141,15 +141,15 @@ def test_multiple_collections_multiple_tarballs(mocker, collector):
             assert_common_files(files)
             if i == 0:
                 assert len(files.keys()) == 2 + _common_files_count()
-                assert './big_table_2.csv' in files.keys()
-                assert './csv_collection_1.csv' in files.keys()
+                assert './big_table_2.csv' in files
+                assert './csv_collection_1.csv' in files
             elif i == 1:
                 assert len(files.keys()) == 2 + _common_files_count()
-                assert './big_table_2.csv' in files.keys()
-                assert './csv_collection_2.csv' in files.keys()
+                assert './big_table_2.csv' in files
+                assert './csv_collection_2.csv' in files
             elif i == 2:
                 assert len(files.keys()) == 1 + _common_files_count()
-                assert './big_table_2.csv' in files.keys()
+                assert './big_table_2.csv' in files
 
     collector._gather_cleanup()
 
@@ -173,51 +173,51 @@ def test_multiple_collections_and_distributions(collector):
 
             assert_common_files(files)
             if i == 0:
-                assert './simple_json1.json' in files.keys()
+                assert './simple_json1.json' in files
             else:
-                assert './simple_json1.json' not in files.keys()
+                assert './simple_json1.json' not in files
 
             # CSVs with no slicing start at index 0
             if 0 <= i <= 1:
-                assert './csv_no_slicing_1-2x.csv' in files.keys()
+                assert './csv_no_slicing_1-2x.csv' in files
             else:
-                assert './csv_no_slicing_1-2x.csv' not in files.keys()
+                assert './csv_no_slicing_1-2x.csv' not in files
 
             if i == 0:
-                assert './csv_no_slicing_2-1x.csv' in files.keys()
+                assert './csv_no_slicing_2-1x.csv' in files
             else:
-                assert './csv_no_slicing_2-1x.csv' not in files.keys()
+                assert './csv_no_slicing_2-1x.csv' not in files
 
             if 0 <= i <= 9:
-                assert './csv_no_slicing_3-10x.csv' in files.keys()
+                assert './csv_no_slicing_3-10x.csv' in files
             else:
-                assert './csv_no_slicing_3-10x.csv' not in files.keys()
+                assert './csv_no_slicing_3-10x.csv' not in files
 
             if 0 <= i <= 11:
-                assert './csv_no_slicing_4-12x.csv' in files.keys()
+                assert './csv_no_slicing_4-12x.csv' in files
             else:
-                assert './csv_no_slicing_4-12x.csv' not in files.keys()
+                assert './csv_no_slicing_4-12x.csv' not in files
 
             # CSVs with slicing start after index next to previous slice
             if 0 <= i <= 4:
-                assert './csv_with_slicing_1-5x.csv' in files.keys()
+                assert './csv_with_slicing_1-5x.csv' in files
             else:
-                assert './csv_with_slicing_1-5x.csv' not in files.keys()
+                assert './csv_with_slicing_1-5x.csv' not in files
 
             if 5 <= i <= 7:
-                assert './csv_with_slicing_2-3x.csv' in files.keys()
+                assert './csv_with_slicing_2-3x.csv' in files
             else:
-                assert './csv_with_slicing_2-3x.csv' not in files.keys()
+                assert './csv_with_slicing_2-3x.csv' not in files
 
             if 8 <= i <= 9:
-                assert './csv_with_slicing_3-2x.csv' in files.keys()
+                assert './csv_with_slicing_3-2x.csv' in files
             else:
-                assert './csv_with_slicing_3-2x.csv' not in files.keys()
+                assert './csv_with_slicing_3-2x.csv' not in files
 
             if 10 <= i <= 12:
-                assert './csv_with_slicing_4-3x.csv' in files.keys()
+                assert './csv_with_slicing_4-3x.csv' in files
             else:
-                assert './csv_with_slicing_4-3x.csv' not in files.keys()
+                assert './csv_with_slicing_4-3x.csv' not in files
 
 
 def test_manifest_and_status(collector):

metrics_utility/test/base/functional/test_slicing.py

@@ -47,7 +47,7 @@ def test_slices_by_date(collector):
                 files[member.name] = archive.extractfile(member)
 
             assert_common_files(files)
-            assert './csv_one_day_slicing_1.csv' in files.keys()
+            assert './csv_one_day_slicing_1.csv' in files
 
             lines = files['./csv_one_day_slicing_1.csv'].readlines()
             _header = lines.pop(0)