Fix syntax errors preventing black formatting

- Fix missing commas in dictionaries (gemini_qa.py)
- Fix unterminated docstring in data_retrieval.py
- Fix indentation errors in test files (test_api_utils.py, test_integration.py,
  test_cache_manager.py, test_text_processing.py, test_api_endpoints.py,
  test_integration_workflow.py)
- Update CI lint job to use Docker for black and flake8 (avoids venv setup)

All files now pass Python syntax validation and should format correctly with black.

Author: RonaldRonnie

.github/workflows/ci.yml

@@ -129,24 +129,20 @@ jobs:
     - name: Checkout code
       uses: actions/checkout@v4
 
-    - name: Set up Python
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ env.PYTHON_DEFAULT_VERSION }}
-        cache: 'pip'
-    
-    - name: Install linting dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install black>=23.0.0 flake8>=6.0.0
-    
-    - name: Check code formatting with Black
-      run: |
-        black --check --diff app/ tests/ cli.py main.py
-    
-    - name: Lint with flake8
-      run: |
-        flake8 app/ tests/ cli.py main.py --max-line-length=120 --extend-ignore=E203,W503,E501 --exclude=__pycache__,*.pyc
+    - name: Lint with Black and flake8 using Docker
+      run: |
+        docker run --rm \
+          -v ${{ github.workspace }}:/workspace \
+          -w /workspace \
+          python:3.11-slim \
+          bash -c "
+            apt-get update -qq && apt-get install -y -qq gcc > /dev/null 2>&1 && \
+            pip install --quiet --no-cache-dir black>=23.0.0 flake8>=6.0.0 && \
+            echo '=== Running Black (check mode) ===' && \
+            black --check --diff app/ tests/ cli.py main.py && \
+            echo '=== Running flake8 ===' && \
+            flake8 app/ tests/ cli.py main.py --max-line-length=120 --extend-ignore=E203,W503,E501 --exclude=__pycache__,*.pyc
+          "
 
   type-check:
     name: Type Check

app/models/gemini_qa.py

@@ -356,7 +356,7 @@ async def analyze_paper(self, paper_content: Dict[str, str]) -> Dict[str, Union[
                     {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_ONLY_HIGH"},
                     {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_ONLY_HIGH"},
                     {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_ONLY_HIGH"},
-                    {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_ONLY_HIGH"}
+                    {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_ONLY_HIGH"},
                 ]
             )
             analysis_text = response.text.strip()
@@ -640,7 +640,7 @@ def _validate_and_normalize_json(self, parsed_json: Dict) -> Dict:
             "condition": {"description": "Unknown", "confidence": 0.0, "status": "ABSENT", "reason_if_missing": "Field not found in analysis", "suggestions_for_curation": "Review paper for condition information"},
             "sequencing_type": {"method": "Unknown", "confidence": 0.0, "status": "ABSENT", "reason_if_missing": "Field not found in analysis", "suggestions_for_curation": "Review paper for sequencing method information"},
             "taxa_level": {"level": "Unknown", "confidence": 0.0, "status": "ABSENT", "reason_if_missing": "Field not found in analysis", "suggestions_for_curation": "Review paper for taxonomic level information"},
-            "sample_size": {"size": "Unknown", "confidence": 0.0, "status": "ABSENT", "reason_if_missing": "Field not found in analysis", "suggestions_for_curation": "Review paper for sample size information"}
+            "sample_size": {"size": "Unknown", "confidence": 0.0, "status": "ABSENT", "reason_if_missing": "Field not found in analysis", "suggestions_for_curation": "Review paper for sample size information"},
         }
 
         for field_name, default_structure in required_fields.items():

app/services/data_retrieval.py

@@ -67,7 +67,8 @@ def _verify_connectivity(self, retries: int = 3) -> None:
                     logger.warning(f"Unable to reach NCBI E-utilities after retries: {safe_error}. App will continue with limited functionality.")
 
     def _make_request(self, endpoint: str, params: Dict[str, Any], retries: int = None) -> Optional[str]:
-        """Make request to NCBI E-utilities with retry logic and rate limiting."""
+        """
+        Make request to NCBI E-utilities with retry logic and rate limiting.
             
         Returns:
             Response text or None if all retries failed

tests/test_api_endpoints.py

@@ -7,7 +7,7 @@
 # Try to import FastAPI-dependent modules, skip tests if not available
 try:
     from fastapi.testclient import TestClient
-from app.api.app import app
+    from app.api.app import app
     FASTAPI_AVAILABLE = True
 except ImportError:
     FASTAPI_AVAILABLE = False

tests/test_api_utils.py

@@ -7,14 +7,14 @@
 # Try to import FastAPI-dependent modules, skip tests if not available
 try:
     from fastapi import FastAPI
-from app.api.utils.api_utils import (
-    extract_taxa,
-    create_default_field_structure,
-    validate_field_structure,
-    create_comprehensive_fallback_analysis,
-    generate_curation_summary,
-    get_current_timestamp
-)
+    from app.api.utils.api_utils import (
+        extract_taxa,
+        create_default_field_structure,
+        validate_field_structure,
+        create_comprehensive_fallback_analysis,
+        generate_curation_summary,
+        get_current_timestamp
+    )
     FASTAPI_AVAILABLE = True
 except ImportError:
     FASTAPI_AVAILABLE = False

tests/test_cache_manager.py

@@ -10,7 +10,7 @@
 # Import CacheManager directly to avoid import chain issues
 try:
     # Try direct import first
-from app.services.cache_manager import CacheManager
+    from app.services.cache_manager import CacheManager
 except ImportError:
     # If that fails, try importing the module directly
     import sys

tests/test_integration.py

@@ -8,8 +8,8 @@
 
 # Try to import FastAPI-dependent modules, skip tests if not available
 try:
-from fastapi.testclient import TestClient
-from app.api.app import app
+    from fastapi.testclient import TestClient
+    from app.api.app import app
     FASTAPI_AVAILABLE = True
 except ImportError:
     FASTAPI_AVAILABLE = False
@@ -82,7 +82,7 @@ def test_cache_and_retrieval_workflow(self):
         """Test that caching and retrieval work together."""
         # Import CacheManager directly to avoid import chain issues
         try:
-        from app.services.cache_manager import CacheManager
+            from app.services.cache_manager import CacheManager
         except ImportError:
             # Fallback: use importlib to load directly from file
             import sys
@@ -202,7 +202,7 @@ class TestTextProcessingIntegration:
     def test_text_cleaning_and_processing_workflow(self):
         """Test that text cleaning and processing work together."""
         try:
-        from app.utils.text_processing import AdvancedTextProcessor
+            from app.utils.text_processing import AdvancedTextProcessor
         except ImportError:
             pytest.skip("torch not available")
 
@@ -223,7 +223,7 @@ def test_text_cleaning_and_processing_workflow(self):
     def test_text_encoding_decoding_workflow(self):
         """Test that encoding and decoding work together."""
         try:
-        from app.utils.text_processing import AdvancedTextProcessor
+            from app.utils.text_processing import AdvancedTextProcessor
         except ImportError:
             pytest.skip("torch not available")
 
@@ -301,7 +301,7 @@ def test_cache_error_handling(self):
         """Test that cache errors are handled gracefully."""
         # Import CacheManager directly to avoid import chain issues
         try:
-        from app.services.cache_manager import CacheManager
+            from app.services.cache_manager import CacheManager
         except ImportError:
             # Fallback: use importlib to load directly from file
             import sys
@@ -359,7 +359,7 @@ def test_data_flow_from_api_to_cache(self):
         """Test data flow from API request through to cache."""
         # Import CacheManager directly to avoid import chain issues
         try:
-        from app.services.cache_manager import CacheManager
+            from app.services.cache_manager import CacheManager
         except ImportError:
             # Fallback: use importlib to load directly from file
             import sys
@@ -417,7 +417,7 @@ async def test_async_cache_operations(self):
         """Test that async cache operations work correctly."""
         # Import CacheManager directly to avoid import chain issues
         try:
-        from app.services.cache_manager import CacheManager
+            from app.services.cache_manager import CacheManager
         except ImportError:
             # Fallback: use importlib to load directly from file
             import sys

tests/test_integration_workflow.py

@@ -10,11 +10,11 @@
 # Try to import services, skip tests if FastAPI not available
 try:
     from fastapi import FastAPI
-from app.services.web_scraper import WebScraperService
-from app.services.image_processor import ImageProcessorService
-from app.services.converter_service import ConverterService
-from app.services.vector_store_service import VectorStoreService
-from app.utils.chunking import ChunkingService
+    from app.services.web_scraper import WebScraperService
+    from app.services.image_processor import ImageProcessorService
+    from app.services.converter_service import ConverterService
+    from app.services.vector_store_service import VectorStoreService
+    from app.utils.chunking import ChunkingService
     FASTAPI_AVAILABLE = True
 except ImportError:
     FASTAPI_AVAILABLE = False

tests/test_text_processing.py

@@ -5,8 +5,8 @@
 
 # Try to import torch and the module, skip tests if not available
 try:
-import torch
-from app.utils.text_processing import AdvancedTextProcessor
+    import torch
+    from app.utils.text_processing import AdvancedTextProcessor
     TORCH_AVAILABLE = True
 except ImportError:
     TORCH_AVAILABLE = False