fix: suppress pdfminer warnings to prevent upload halting

- Added warning suppression for pdfminer warnings during Docling PDF processing
- Suppresses 'Cannot set gray non-stroke color' warnings that cause uploads to halt
- Temporarily sets pdfminer logger to ERROR level during document processing
- Fixes issue where files ~34MB would fail due to pdfminer warning spam

Resolves issue where PDF uploads would halt with repeated pdfminer warnings

Author: codeBunny2022

surfsense_backend/app/tasks/document_processors/file_processors.py

@@ -886,13 +886,40 @@ async def process_file_in_background(
                 )
 
                 # Use Docling service for document processing
+                import warnings
+
                 from app.services.docling_service import create_docling_service
 
                 # Create Docling service
                 docling_service = create_docling_service()
 
-                # Process the document
-                result = await docling_service.process_document(file_path, filename)
+                # Suppress pdfminer warnings that can cause processing to hang
+                # These warnings are harmless but can spam logs and potentially halt processing
+                # Suppress both Python warnings and logging warnings from pdfminer
+                pdfminer_logger = logging.getLogger("pdfminer")
+                original_level = pdfminer_logger.level
+                
+                with warnings.catch_warnings():
+                    warnings.filterwarnings(
+                        "ignore", category=UserWarning, module="pdfminer"
+                    )
+                    warnings.filterwarnings(
+                        "ignore",
+                        message=".*Cannot set gray non-stroke color.*",
+                    )
+                    warnings.filterwarnings(
+                        "ignore", message=".*invalid float value.*"
+                    )
+                    
+                    # Temporarily suppress pdfminer logging warnings
+                    pdfminer_logger.setLevel(logging.ERROR)
+                    
+                    try:
+                        # Process the document
+                        result = await docling_service.process_document(file_path, filename)
+                    finally:
+                        # Restore original logging level
+                        pdfminer_logger.setLevel(original_level)
 
                 # Clean up the temp file
                 import os

surfsense_backend/pyproject.toml

@@ -1,3 +1,14 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = ["app"]
+include-package-data = false
+
+[tool.setuptools.package-data]
+app = ["**/*"]
+
 [project]
 name = "surf-new-backend"
 version = "0.0.8"