Update ord.py

ord.py

@@ -11,6 +11,18 @@ from docx.enum.section import WD_SECTION
 from docx.oxml import parse_xml
 from docx.oxml.ns import nsdecls
 from docx.oxml.shared import OxmlElement, qn
+from concurrent.futures import ThreadPoolExecutor
+from functools import lru_cache
+from concurrent.futures import ThreadPoolExecutor
+import threading
+
+# Thread pool for I/O operations
+_io_executor = ThreadPoolExecutor(max_workers=4)
+
+@lru_cache(maxsize=128)
+def _cached_excel_read(file_path, sheet_name):
+    """Cache Excel reads"""
+    return pd.read_excel(file_path, sheet_name=sheet_name)
 
 THEME_COLOR_HEX = "5FFFDF"  # Hex version for XML elements
 THEME_COLOR = RGBColor.from_string(THEME_COLOR_HEX)
@@ -1468,7 +1480,23 @@ def process_excel_to_word(excel_file_path, output_word_path, display_name=None,
     # Read the Excel file
     xls = pd.ExcelFile(excel_file_path)
     first_sheet_name = xls.sheet_names[0]  # Get the first sheet name
-    questions_df = pd.read_excel(excel_file_path, sheet_name=first_sheet_name)
+    all_sheets = xls.sheet_names
+
+    with ThreadPoolExecutor(max_workers=min(len(all_sheets), 8)) as executor:
+        future_to_sheet = {
+            executor.submit(pd.read_excel, excel_file_path, sheet_name=sheet): sheet
+            for sheet in all_sheets[:10]  # Limit to first 10 sheets
+        }
+
+        sheets_data = {}
+        for future in future_to_sheet:
+            sheet = future_to_sheet[future]
+            try:
+                sheets_data[sheet] = future.result()
+            except Exception as e:
+                print(f"Error reading {sheet}: {e}")
+
+        questions_df = sheets_data[first_sheet_name]
 
     # Extract display name if not provided
     if display_name is None:
@@ -1519,12 +1547,19 @@ def process_excel_to_word(excel_file_path, output_word_path, display_name=None,
     modules_data = {}
     xls = pd.ExcelFile(excel_file_path)
 
-    for module in modules:
-        try:
-            cours_titles_for_module = read_course_titles_from_module_sheet(excel_file_path, module)
-            modules_data[module] = cours_titles_for_module
-        except Exception as e:
-            print(f"DEBUG: Error reading module '{module}': {e}")
+    # Parallel module reading
+    with ThreadPoolExecutor(max_workers=min(len(modules), 8)) as executor:
+        future_to_module = {
+            executor.submit(read_course_titles_from_module_sheet, excel_file_path, module): module
+            for module in modules
+        }
+    
+        for future in future_to_module:
+            module = future_to_module[future]
+            try:
+                modules_data[module] = future.result()
+            except Exception as e:
+                print(f"DEBUG: Error reading module '{module}': {e}")
 
     # Clean column names
     questions_df.columns = questions_df.columns.str.strip()
@@ -1532,6 +1567,10 @@ def process_excel_to_word(excel_file_path, output_word_path, display_name=None,
     # Create Word document
     doc = Document()
 
+    # CRITICAL: Disable slow style updates
+    doc.settings.update_fields_on_open = False
+    doc.settings.odd_and_even_pages_header_footer = False
+
     core_props = doc.core_properties
     core_props.author = "Natural Killer"
     core_props.title = "Manhattan Project"