POD-2631: Add GitHub Action to run Linting (#22)

* add github action to run linting

* separate checks

* remove pre-commit, use tools directly

* reformat to pass mypy errors

* reformat to pass mypy errors

Author: sahakiann

Diff for: .github/workflows/check-coverage.yml

@@ -17,7 +17,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.11'
+          python-version: "3.11"
 
       - name: Install dependencies
         run: |

Diff for: .github/workflows/docs.yml

@@ -21,7 +21,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.13'
+          python-version: "3.13"
 
       # ADJUST THIS: install all dependencies (including pdoc)
       - run: |

Diff for: .github/workflows/lint.yml

@@ -0,0 +1,55 @@
+name: Linting and Static Analysis
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  lint:
+    name: Lint (flake8)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Install flake8
+        run: pip install flake8
+      - name: Run flake8
+        run: flake8 . --max-line-length=120 --exclude=docs,ops_utils/tests
+
+  type-check:
+    name: Type Checking (mypy)
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.11"
+      - name: Install mypy and stubs
+        run: |
+          pip install mypy types-requests types-python-dateutil types-pytz
+      - name: Run mypy
+        run: |
+          mypy . \
+            --disallow-untyped-defs \
+            --disallow-incomplete-defs \
+            --disallow-untyped-calls \
+            --ignore-missing-imports \
+            --python-version=3.11 \
+            --exclude '^(docs/|ops_utils/tests/)'
+
+  yaml-check:
+    name: YAML Syntax Check
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install PyYAML
+        run: pip install pyyaml
+      - name: Validate YAML files
+        run: |
+          find . -name "*.yml" -o -name "*.yaml" | while read file; do
+            echo "Checking $file"
+            python -c "import yaml, sys; yaml.safe_load(open('$file'))"
+          done

Diff for: .pre-commit-config.yaml

@@ -39,7 +39,7 @@ repos:
   hooks:
     - id: flake8
       additional_dependencies: [flake8]
-      args: [--max-line-length=120]  # <-- customize your preferred max length
+      args: [--max-line-length=120, ]  # <-- customize your preferred max length
 
 # Excludes these directories globally (i.e. no hooks will be applied to the docs/ or ops_utils/test/ dirs)
 exclude: ^(docs/|ops_utils/tests/)

Diff for: VERSION.txt

@@ -1,3 +1,2 @@
-1.6.0
-- Add documentation link to README
-- Add build badges to README
+1.7.0
+- Add GitHub action to run linting checks

Diff for: ops_utils/azure_utils.py

@@ -30,7 +30,7 @@ def get_blob_details(self, max_per_page: int = 500) -> list[dict]:
             logging.info(
                 f"Getting page {page_count} of max {max_per_page} blobs")
             for blob in blob_page:
-                blob_client = container_client.get_blob_client(blob)
+                blob_client = container_client.get_blob_client(blob)  # type: ignore[arg-type]
                 props = blob_client.get_blob_properties()
                 if not blob.name.endswith('/'):
                     md5_hash = base64.b64encode(props.content_settings.content_md5).decode(

Diff for: ops_utils/gcp_utils.py

@@ -25,7 +25,7 @@ def __init__(self, project: Optional[str] = None) -> None:
         Initialize the GCPCloudFunctions class.
         Authenticates using the default credentials and sets up the storage client.
         """
-        from google.cloud import storage
+        from google.cloud import storage  # type: ignore[attr-defined]
         from google.auth import default
         credentials, default_project = default()
         if not project:

Diff for: ops_utils/jira_util.py

@@ -57,7 +57,7 @@ def get_issues_by_criteria(
             max_results: int = 200,
             fields: Optional[Union[list, str]] = None,
             expand_info: Optional[str] = None
-    ) -> dict:
+    ) -> list[dict]:
         logging.info(f"Getting issues by criteria: {criteria}")
         if fields:
             return self.jira.search_issues(criteria, fields=fields, maxResults=max_results, expand=expand_info)

Diff for: ops_utils/tdr_utils/tdr_api_utils.py

@@ -835,7 +835,7 @@ def create_dataset(  # type: ignore[return]
         if additional_dataset_properties:
             dataset_properties.update(additional_dataset_properties)
         try:
-            CreateDatasetSchema(**dataset_properties)
+            CreateDatasetSchema(**dataset_properties)  # type: ignore[arg-type]
         except ValidationError as e:
             raise ValueError(f"Schema validation error: {e}")
         uri = f"{self.TDR_LINK}/datasets"

Diff for: ops_utils/tdr_utils/tdr_ingest_utils.py

@@ -464,8 +464,7 @@ def _reformat_metric(self, row_dict: dict) -> Optional[dict]:
                     reformatted_dict[key] = update_value
                     if not valid:
                         row_valid = False
-        reformatted_dict["last_modified_date"] = datetime.now(
-            tz=pytz.UTC).strftime("%Y-%m-%dT%H:%M:%S")  # type: ignore[assignment]
+        reformatted_dict["last_modified_date"] = datetime.now(tz=pytz.UTC).strftime("%Y-%m-%dT%H:%M:%S")  # type: ignore[assignment] # noqa: E501
         if row_valid:
             return reformatted_dict
         else: