Update working_yolo_pipeline.py

working_yolo_pipeline.py

@@ -2514,6 +2514,53 @@ def run_document_pipeline( input_pdf_path: str, layoutlmv3_model_path: str, stru
 
 
 
+# if __name__ == "__main__":
+#     parser = argparse.ArgumentParser(description="Complete Pipeline")
+#     parser.add_argument("--input_pdf", type=str, required=True, help="Input PDF")
+#     parser.add_argument("--layoutlmv3_model_path", type=str, default=DEFAULT_LAYOUTLMV3_MODEL_PATH, help="Model Path")
+
+#     # --- ADDED ARGUMENT FOR DEBUGGING ---
+#     parser.add_argument("--raw_preds_path", type=str, default='BIO_debug.json',
+#                         help="Debug path for raw BIO tag predictions (JSON).")
+#     # ------------------------------------
+#     args = parser.parse_args()
+
+#     pdf_name = os.path.splitext(os.path.basename(args.input_pdf))[0]
+#     final_output_path = os.path.abspath(f"{pdf_name}_final_output_embedded.json")
+
+#     # --- CALCULATE RAW PREDICTIONS OUTPUT PATH (Kept commented as per original script) ---
+#     # raw_predictions_output_path = os.path.abspath(
+#     #     args.raw_preds_path if args.raw_preds_path else f"{pdf_name}_raw_predictions_debug.json")
+#     # ---------------------------------------------
+
+#     # --- UPDATED FUNCTION CALL ---
+#     final_json_data = run_document_pipeline(
+#         args.input_pdf,
+#         args.layoutlmv3_model_path )
+#     # -----------------------------
+
+#     # 🛑 CRITICAL FINAL FIX: CUSTOM JSON SAVING TO REMOVE ESCAPING 🛑
+#     if final_json_data:
+#         # 1. Dump the Python object to a standard JSON string.
+#         # This converts the in-memory single backslash ('\') into the JSON escaped double backslash ('\\').
+#         json_str = json.dumps(final_json_data, indent=2, ensure_ascii=False)
+
+#         # 2. **UNDO ESCAPING:** The string currently contains '\\' where you need '\' for LaTeX.
+#         # We replace the JSON-escaped double backslash ('\\') with a single literal backslash ('\').
+#         final_output_content = json_str.replace('\\\\', '\\')
+
+#         # 3. Write the corrected string content to the file.
+#         with open(final_output_path, 'w', encoding='utf-8') as f:
+#             f.write(final_output_content)
+            
+#         print(f"\n✅ Final Data Saved: {final_output_path}")
+#     else:
+#         print("\n❌ Pipeline Failed.")
+#         sys.exit(1)
+
+
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Complete Pipeline")
     parser.add_argument("--input_pdf", type=str, required=True, help="Input PDF")
@@ -2539,15 +2586,17 @@ if __name__ == "__main__":
         args.layoutlmv3_model_path )
     # -----------------------------
 
-    # 🛑 CRITICAL FINAL FIX: CUSTOM JSON SAVING TO REMOVE ESCAPING 🛑
+    # 🛑 CRITICAL FINAL FIX: AGGRESSIVE CUSTOM JSON SAVING 🛑
     if final_json_data:
         # 1. Dump the Python object to a standard JSON string.
-        # This converts the in-memory single backslash ('\') into the JSON escaped double backslash ('\\').
+        # This converts the in-memory double backslash ('\\') into a quadruple backslash ('\\\\')
+        # in the raw json_str string content.
         json_str = json.dumps(final_json_data, indent=2, ensure_ascii=False)
 
-        # 2. **UNDO ESCAPING:** The string currently contains '\\' where you need '\' for LaTeX.
-        # We replace the JSON-escaped double backslash ('\\') with a single literal backslash ('\').
-        final_output_content = json_str.replace('\\\\', '\\')
+        # 2. **AGGRESSIVE UNDO ESCAPING:** We assume we have quadruple backslashes and
+        # replace them with the double backslashes needed for the LaTeX command to work.
+        # This operation essentially replaces four literal backslashes with two literal backslashes.
+        final_output_content = json_str.replace('\\\\\\\\', '\\\\')
 
         # 3. Write the corrected string content to the file.
         with open(final_output_path, 'w', encoding='utf-8') as f: