Update app.py

app.py

@@ -1,150 +1,3 @@
-# import gradio as gr
-# import json
-# import os
-# import tempfile
-# import img2pdf
-# from pathlib import Path
-
-# # ==============================
-# # PIPELINE IMPORT
-# # ==============================
-# try:
-#     from working_yolo_pipeline import run_document_pipeline, DEFAULT_LAYOUTLMV3_MODEL_PATH, WEIGHTS_PATH
-# except ImportError:
-#     print("Warning: 'working_yolo_pipeline.py' not found. Using dummy paths.")
-#     def run_document_pipeline(*args):
-#         return {"error": "Placeholder pipeline function called."}
-#     DEFAULT_LAYOUTLMV3_MODEL_PATH = "./models/layoutlmv3_model"
-#     WEIGHTS_PATH = "./weights/yolo_weights.pt"
-
-# def process_file(uploaded_files, layoutlmv3_model_path=None):
-#     """
-#     Converts multiple images into a single PDF (if necessary) and routes 
-#     the result to the YOLO/OCR pipeline as a single entity.
-#     """
-#     if not uploaded_files:
-#         return "❌ Error: No files uploaded.", None
-
-#     # Ensure we are working with a list of files (Gradio file_count="multiple" returns a list)
-#     if not isinstance(uploaded_files, list):
-#         uploaded_files = [uploaded_files]
-
-#     # 1. Resolve all file paths
-#     resolved_paths = []
-#     for f in uploaded_files:
-#         if hasattr(f, 'path'):
-#             resolved_paths.append(f.path)
-#         elif isinstance(f, dict):
-#             resolved_paths.append(f.get("path"))
-#         else:
-#             resolved_paths.append(str(f))
-
-#     # 2. Determine if we should merge into a single PDF
-#     # We merge if there are multiple files OR if the single file is an image
-#     first_file = Path(resolved_paths[0])
-#     is_image = first_file.suffix.lower() in ['.jpg', '.jpeg', '.png', '.bmp', '.webp', '.tiff']
-    
-#     processing_path = None
-    
-#     try:
-#         if len(resolved_paths) > 1 or (len(resolved_paths) == 1 and is_image):
-#             print(f"📦 Converting {len(resolved_paths)} image(s) to a single PDF entity...")
-#             temp_pdf = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
-#             # img2pdf.convert converts a list of image paths into PDF bytes
-#             with open(temp_pdf.name, "wb") as f:
-#                 f.write(img2pdf.convert(resolved_paths))
-#             processing_path = temp_pdf.name
-#         else:
-#             # It's a single PDF, process directly
-#             processing_path = resolved_paths[0]
-
-#         # 3. Standard Pipeline Checks
-#         if not layoutlmv3_model_path:
-#             layoutlmv3_model_path = DEFAULT_LAYOUTLMV3_MODEL_PATH
-
-#         if not os.path.exists(layoutlmv3_model_path):
-#             return f"❌ Error: LayoutLMv3 model not found at {layoutlmv3_model_path}", None
-
-#         if not os.path.exists(WEIGHTS_PATH):
-#             return f"❌ Error: YOLO weights not found at {WEIGHTS_PATH}", None
-
-#         print(f"🚀 Starting pipeline for merged entity: {processing_path}")
-
-#         # 4. Call the pipeline
-#         result = run_document_pipeline(processing_path, layoutlmv3_model_path)
-
-#         if result is None:
-#             return "❌ Error: Pipeline failed to process the document.", None
-
-#         # 5. Prepare output
-#         temp_output = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.json', prefix='analysis_')
-#         with open(temp_output.name, 'w', encoding='utf-8') as f:
-#             json.dump(result, f, indent=2, ensure_ascii=False)
-
-#         json_display = json.dumps(result, indent=2, ensure_ascii=False)
-#         return json_display, temp_output.name
-
-#     except Exception as e:
-#         import traceback
-#         traceback.print_exc()
-#         return f"❌ Error during processing: {str(e)}", None
-
-# # ==============================
-# # GRADIO INTERFACE
-# # ==============================
-# with gr.Blocks(title="Document Analysis Pipeline") as demo:
-
-#     gr.Markdown("""
-#     # 📄 Document & Image Analysis Pipeline
-#     Upload **multiple images** or a **PDF**. Multiple images will be processed together as a single continuous document.
-#     """)
-
-#     with gr.Row():
-#         with gr.Column(scale=1):
-#             file_input = gr.File(
-#                 label="Upload PDFs or Images",
-#                 file_types=[".pdf", ".jpg", ".jpeg", ".png", ".bmp", ".webp", ".tiff"],
-#                 type="filepath",
-#                 file_count="multiple"  # ALLOWS MULTIPLE FILES
-#             )
-
-#             model_path_input = gr.Textbox(
-#                 label="LayoutLMv3 Model Path (optional)",
-#                 placeholder=DEFAULT_LAYOUTLMV3_MODEL_PATH,
-#                 value=DEFAULT_LAYOUTLMV3_MODEL_PATH,
-#                 interactive=True
-#             )
-
-#             process_btn = gr.Button("🚀 Process Files", variant="primary", size="lg")
-
-#         with gr.Column(scale=2):
-#             json_output = gr.Code(
-#                 label="Combined Structured JSON Output",
-#                 language="json",
-#                 lines=25
-#             )
-
-#             download_output = gr.File(
-#                 label="Download Full JSON",
-#                 interactive=False
-#             )
-
-#     # UI Logic
-#     process_btn.click(
-#         fn=process_file,
-#         inputs=[file_input, model_path_input],
-#         outputs=[json_output, download_output],
-#         api_name="process_document"
-#     )
-
-# if __name__ == "__main__":
-#     demo.launch(
-#         server_name="0.0.0.0",
-#         server_port=7860,
-#         share=False,
-#         show_error=True
-#     )
-
 
 
 
@@ -154,6 +7,7 @@ import json
 import os
 import tempfile
 import img2pdf
+from img2pdf import Rotation
 from pathlib import Path
 
 # ==============================
@@ -213,7 +67,9 @@ def process_file(uploaded_files, layoutlmv3_model_path=None):
             print(f"📦 Converting {len(resolved_paths)} image(s) to a single PDF...")
             temp_pdf = tempfile.NamedTemporaryFile(delete=False, suffix=".pdf")
             with open(temp_pdf.name, "wb") as f_out:
-                f_out.write(img2pdf.convert(resolved_paths))
+                # f_out.write(img2pdf.convert(resolved_paths))
+                f_out.write(img2pdf.convert(resolved_paths, rotation=Rotation.ifvalid))
+
             processing_path = temp_pdf.name
         else:
             # It's a single PDF