Update CI things

Author: evz

genealogy/management/commands/demo_ocr.py

@@ -6,12 +6,11 @@
     python manage.py demo_ocr --clear  # Clear previous demo data first
 """
 
-import os
 from pathlib import Path
 
+from django.conf import settings
 from django.core.files import File
 from django.core.management.base import BaseCommand
-from django.conf import settings
 
 from genealogy.models import Document, DocumentPage
 from genealogy.tasks import process_page_ocr
@@ -28,7 +27,7 @@ def add_arguments(self, parser):
         )
         parser.add_argument(
             "--sync",
-            action="store_true", 
+            action="store_true",
             help="Run OCR synchronously instead of using Celery tasks",
         )
 
@@ -95,18 +94,17 @@ def _clear_demo_data(self):
     def _create_demo_document(self, file_path: Path, description: str) -> Document:
         """Create a document for demo purposes"""
         title = f"Demo: {file_path.stem} - {description}"
-        
-        document = Document.objects.create(
+
+        return Document.objects.create(
             title=title,
             languages="eng",  # Default to English for demo
         )
-        return document
 
     def _create_pages_for_document(self, document: Document, file_path: Path) -> int:
         """Create document pages from the PDF file"""
         with open(file_path, "rb") as f:
             django_file = File(f, name=file_path.name)
-            
+
             # For demo, treat each PDF as a single page
             # In reality, the admin interface would handle multi-page PDFs
             page = DocumentPage.objects.create(
@@ -115,65 +113,71 @@ def _create_pages_for_document(self, document: Document, file_path: Path) -> int
                 image_file=django_file,
                 original_filename=file_path.name,
             )
-            
+
         return 1
 
     def _process_ocr_sync(self, document: Document):
         """Process OCR synchronously for immediate results"""
         self.stdout.write("   🔄 Processing OCR (synchronous)...")
-        
+
         for page in document.pages.all():
             try:
                 page.validate_for_ocr()
-                
+
                 # Import here to avoid import issues
                 from genealogy.ocr_processor import OCRProcessor
-                
+
                 processor = OCRProcessor()
                 file_path = page.image_file.path
-                
+
                 text, confidence, rotation = processor.process_file(file_path)
-                
+
                 page.ocr_text = text
                 page.ocr_confidence = confidence
                 page.rotation_applied = rotation
                 page.ocr_completed = True
                 page.save()
-                
+
                 self.stdout.write(
                     f"   ✅ OCR complete - {confidence:.1f}% confidence, "
                     f"{len(text)} characters extracted"
                 )
-                
+
                 # Show first 100 characters of extracted text
                 preview = text[:100].replace("\n", " ").strip()
                 if len(text) > 100:
                     preview += "..."
                 self.stdout.write(f"   📝 Preview: {preview}")
-                
+
             except Exception as e:
                 self.stdout.write(
-                    self.style.ERROR(f"   ❌ OCR failed for page {page.page_number}: {e}")
+                    self.style.ERROR(
+                        f"   ❌ OCR failed for page {page.page_number}: {e}"
+                    )
                 )
 
     def _process_ocr_async(self, document: Document):
         """Process OCR using Celery tasks"""
         self.stdout.write("   🔄 Queuing OCR tasks (asynchronous)...")
-        
+
         task_count = 0
         for page in document.pages.all():
             try:
                 page.validate_for_ocr()
                 task = process_page_ocr.delay(str(page.id))
                 task_count += 1
-                self.stdout.write(f"   📋 Queued OCR task {task.id} for page {page.page_number}")
+                self.stdout.write(
+                    f"   📋 Queued OCR task {task.id} for page {page.page_number}"
+                )
             except Exception as e:
                 self.stdout.write(
-                    self.style.ERROR(f"   ❌ Failed to queue OCR for page {page.page_number}: {e}")
+                    self.style.ERROR(
+                        f"   ❌ Failed to queue OCR for page {page.page_number}: {e}"
+                    )
                 )
-        
+
         if task_count > 0:
             self.stdout.write(
                 f"   ⏱️ {task_count} OCR task(s) queued. "
                 "Check the admin interface to see results as they complete."
-            )
+            )

genealogy_extractor/settings.py

@@ -11,6 +11,7 @@
 """
 
 import os
+import sys
 from pathlib import Path
 
 # Build paths inside the project like this: BASE_DIR / 'subdir'.
@@ -21,7 +22,10 @@
 # See https://docs.djangoproject.com/en/5.2/howto/deployment/checklist/
 
 # SECURITY WARNING: keep the secret key used in production secret!
-SECRET_KEY = os.getenv("DJANGO_SECRET_KEY", "django-insecure-*+%i+f9ifcd+hnu==udvxo_qc03_7x8y&nijs6)kp#5u!cct%u")
+SECRET_KEY = os.getenv(
+    "DJANGO_SECRET_KEY",
+    "django-insecure-*+%i+f9ifcd+hnu==udvxo_qc03_7x8y&nijs6)kp#5u!cct%u",
+)
 
 # SECURITY WARNING: don't run with debug turned on in production!
 DEBUG = os.getenv("DEBUG", "False").lower() in ("true", "1", "yes")
@@ -136,7 +140,9 @@
 
 # Celery configuration
 CELERY_BROKER_URL = f"redis://{os.environ['REDIS_HOST']}:{os.environ['REDIS_PORT']}/0"
-CELERY_RESULT_BACKEND = f"redis://{os.environ['REDIS_HOST']}:{os.environ['REDIS_PORT']}/0"
+CELERY_RESULT_BACKEND = (
+    f"redis://{os.environ['REDIS_HOST']}:{os.environ['REDIS_PORT']}/0"
+)
 CELERY_ACCEPT_CONTENT = ["json"]
 CELERY_TASK_SERIALIZER = "json"
 CELERY_RESULT_SERIALIZER = "json"
@@ -146,3 +152,26 @@
 # https://docs.djangoproject.com/en/5.2/ref/settings/#default-auto-field
 
 DEFAULT_AUTO_FIELD = "django.db.models.BigAutoField"
+
+# Logging configuration
+LOGGING = {
+    "version": 1,
+    "disable_existing_loggers": False,
+    "handlers": {
+        "console": {
+            "class": "logging.StreamHandler",
+            "stream": sys.stdout,
+        },
+    },
+    "root": {
+        "handlers": ["console"],
+        "level": "WARNING" if "test" in sys.argv else "INFO",
+    },
+    "loggers": {
+        "genealogy": {
+            "handlers": ["console"],
+            "level": "WARNING" if "test" in sys.argv else "INFO",
+            "propagate": False,
+        },
+    },
+}

requirements-dev.txt

@@ -1,3 +1,4 @@
 ruff==0.1.9
 mypy==1.8.0
-bandit==1.7.5
+bandit==1.7.5
+django-stubs==4.2.7