Add original_filename parameter to preserve user's filename

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>

app/api/files.py

@@ -472,20 +472,20 @@ async def ui_upload(request: Request, file: UploadFile = File(...)):
     
     if is_pdf:
         # If it's a PDF, process directly
-        task = process_document.delay(target_path)
+        task = process_document.delay(target_path, original_filename=safe_filename)
         logger.info(f"Enqueued PDF for processing: {target_path}")
     elif mime_type in IMAGE_MIME_TYPES or any(file_ext.endswith(ext) for ext in ['.jpg', '.jpeg', '.png', '.gif', '.bmp', '.tiff', '.webp', '.svg']):
         # If it's an image, convert to PDF first
-        task = convert_to_pdf.delay(target_path)
+        task = convert_to_pdf.delay(target_path, original_filename=safe_filename)
         logger.info(f"Enqueued image for PDF conversion: {target_path}")
     elif mime_type in ALLOWED_MIME_TYPES or any(file_ext.endswith(ext) for ext in ['.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx', '.odt', '.ods', '.odp', '.rtf', '.txt', '.csv']):
         # If it's an office document, convert to PDF first
-        task = convert_to_pdf.delay(target_path)
+        task = convert_to_pdf.delay(target_path, original_filename=safe_filename)
         logger.info(f"Enqueued office document for PDF conversion: {target_path}")
     else:
         # For any other file type, attempt conversion but log a warning
         logger.warning(f"Unsupported MIME type {mime_type} for {target_path}, attempting conversion")
-        task = convert_to_pdf.delay(target_path)
+        task = convert_to_pdf.delay(target_path, original_filename=safe_filename)
     
     return {
         "task_id": task.id, 

app/tasks/convert_to_pdf.py

@@ -12,11 +12,15 @@ from app.utils import log_task_progress
 logger = logging.getLogger(__name__)
 
 @shared_task(bind=True)
-def convert_to_pdf(self, file_path):
+def convert_to_pdf(self, file_path, original_filename=None):
     """
     Converts a file to PDF using Gotenberg's API.
     Determines the appropriate Gotenberg endpoint based on the file's MIME type.
     On success, saves the PDF locally and enqueues it for processing.
+    
+    Args:
+        file_path: Path to the file to convert
+        original_filename: Optional original filename (if different from path basename)
     """
     task_id = self.request.id
     logger.info(f"[{task_id}] Starting PDF conversion: {file_path}")
@@ -174,8 +178,14 @@ def convert_to_pdf(self, file_path):
             log_task_progress(task_id, "call_gotenberg", "success", "PDF conversion successful")
             log_task_progress(task_id, "convert_to_pdf", "success", f"Converted to PDF: {os.path.basename(converted_file_path)}")
             
-            # Enqueue the PDF for further processing
-            process_document.delay(converted_file_path)
+            # Enqueue the PDF for further processing, preserving original filename if provided
+            if original_filename:
+                # Change extension to .pdf for the original filename
+                original_base = os.path.splitext(original_filename)[0]
+                pdf_original_filename = f"{original_base}.pdf"
+                process_document.delay(converted_file_path, original_filename=pdf_original_filename)
+            else:
+                process_document.delay(converted_file_path)
             
             return converted_file_path
         else:

app/tasks/process_document.py

@@ -22,10 +22,14 @@ logger = logging.getLogger(__name__)
 
 
 @celery.task(base=BaseTaskWithRetry, bind=True)
-def process_document(self, original_local_file: str):
+def process_document(self, original_local_file: str, original_filename: str = None):
     """
     Process a document file and trigger appropriate text extraction.
 
+    Args:
+        original_local_file: Path to the file on disk
+        original_filename: Optional original filename (if different from path basename)
+
     Steps:
       1. Check if we have a FileRecord entry (via SHA-256 hash). If found, skip re-processing.
       2. If not found, insert a new DB row and continue with the pipeline:
@@ -51,7 +55,9 @@ def process_document(self, original_local_file: str):
     logger.info(f"[{task_id}] Computing file hash...")
     log_task_progress(task_id, "hash_file", "in_progress", "Computing file hash")
     filehash = hash_file(original_local_file)
-    original_filename = os.path.basename(original_local_file)
+    # Use provided original_filename or fall back to basename of path
+    if original_filename is None:
+        original_filename = os.path.basename(original_local_file)
     file_size = os.path.getsize(original_local_file)
     mime_type, _ = mimetypes.guess_type(original_local_file)
     if not mime_type: