Update updated_word.py

updated_word.py

@@ -673,8 +673,150 @@ def process_single_column_sections(cell, field_name, flat_json):
                 return cell_replacements
     return 0
 
+# 🎯 FINAL FIX 1: Add this function to handle Attendance List (unchanged)
+def handle_attendance_list_fix(table, flat_json):
+    """FINAL FIX: Handle Attendance List table specifically"""
+    replacements_made = 0
+    
+    # Look for attendance list table
+    for row_idx, row in enumerate(table.rows):
+        if len(row.cells) >= 1:
+            cell_text = get_clean_text(row.cells[0]).lower()
+            
+            # Check if this is the attendance list header
+            if "attendance list" in cell_text and "names and position titles" in cell_text:
+                print(f"    🎯 FINAL FIX: Attendance List table detected at row {row_idx + 1}")
+                
+                # The content should be in the same cell, look for red text
+                if has_red_text(row.cells[0]):
+                    # Try to find attendance list data
+                    attendance_value = None
+                    for field_attempt in ["Attendance List (Names and Position Titles)", "attendance list", "Attendance List"]:
+                        attendance_value = find_matching_json_value(field_attempt, flat_json)
+                        if attendance_value is not None:
+                            break
+                    
+                    if attendance_value is not None:
+                        attendance_text = get_value_as_string(attendance_value)
+                        # Handle list format for attendance
+                        if isinstance(attendance_value, list):
+                            attendance_text = "\n".join(str(item) for item in attendance_value)
+                        
+                        cell_replacements = replace_red_text_in_cell(row.cells[0], attendance_text)
+                        replacements_made += cell_replacements
+                        print(f"        ✅ Fixed Attendance List: '{attendance_text[:50]}...'")
+                
+                break  # Found the table, stop looking
+    
+    return replacements_made
+
+# 🎯 FINAL FIX 2: Generic Management Summary fix for ALL types (Mass, Fatigue, Maintenance)
+def handle_management_summary_fix(cell, flat_json):
+    """FINAL FIX: Handle ANY Management Summary section (Mass/Fatigue/Maintenance) - RED TEXT ONLY"""
+    if not has_red_text(cell):
+        return 0
+    
+    # Check if this cell contains any Management Summary
+    cell_text = get_clean_text(cell).lower()
+    
+    # Detect which type of management summary this is
+    management_type = None
+    if "mass management" in cell_text and "summary" in cell_text:
+        management_type = "Mass Management"
+    elif "fatigue management" in cell_text and "summary" in cell_text:
+        management_type = "Fatigue Management"
+    elif "maintenance management" in cell_text and "summary" in cell_text:
+        management_type = "Maintenance Management"
+    
+    if not management_type:
+        return 0
+    
+    print(f"    🎯 FINAL FIX: {management_type} Summary processing - RED TEXT ONLY")
+    
+    # ONLY process red text segments, not the entire cell text
+    red_segments = extract_red_text_segments(cell)
+    replacements_made = 0
+    
+    # Try to replace ONLY the red text segments
+    for segment in red_segments:
+        segment_text = segment['text'].strip()
+        if not segment_text:
+            continue
+        
+        print(f"        🔍 Processing red text segment: '{segment_text[:50]}...'")
+        
+        # Try multiple variations based on the management type
+        summary_value = None
+        field_attempts = [
+            f"{management_type} Summary of Audit findings",
+            f"{management_type} Summary",
+            f"{management_type.lower()} summary",
+            management_type.lower(),
+            segment_text  # Also try the exact red text
+        ]
+        
+        # Also try variations without "Management"
+        base_type = management_type.replace(" Management", "")
+        field_attempts.extend([
+            f"{base_type} Management Summary of Audit findings",
+            f"{base_type} Summary of Audit findings",
+            f"{base_type} Summary",
+            f"{base_type.lower()} summary"
+        ])
+        
+        for field_attempt in field_attempts:
+            summary_value = find_matching_json_value(field_attempt, flat_json)
+            if summary_value is not None:
+                print(f"        ✅ Found match with field: '{field_attempt}'")
+                break
+        
+        if summary_value is not None:
+            replacement_text = get_value_as_string(summary_value, segment_text)
+            if isinstance(summary_value, list):
+                replacement_text = "\n".join(str(item) for item in summary_value if str(item).strip())
+            
+            success = replace_single_segment(segment, replacement_text)
+            if success:
+                replacements_made += 1
+                print(f"        ✅ Fixed {management_type} Summary segment: '{segment_text[:30]}...' -> '{replacement_text[:30]}...'")
+        else:
+            print(f"        ❌ No match found for red text: '{segment_text[:30]}...'")
+    
+    # If no individual segment matches, try combined approach on red text only
+    if replacements_made == 0 and red_segments:
+        combined_red_text = " ".join(seg['text'] for seg in red_segments).strip()
+        print(f"        🔄 Trying combined red text match: '{combined_red_text[:50]}...'")
+        
+        # Try combined text matching with all field variations
+        field_attempts = [
+            f"{management_type} Summary of Audit findings",
+            f"{management_type} Summary",
+            f"{management_type.lower()} summary",
+            combined_red_text
+        ]
+        
+        base_type = management_type.replace(" Management", "")
+        field_attempts.extend([
+            f"{base_type} Management Summary of Audit findings",
+            f"{base_type} Summary of Audit findings",
+            f"{base_type} Summary"
+        ])
+        
+        for field_attempt in field_attempts:
+            summary_value = find_matching_json_value(field_attempt, flat_json)
+            if summary_value is not None:
+                replacement_text = get_value_as_string(summary_value, combined_red_text)
+                if isinstance(summary_value, list):
+                    replacement_text = "\n".join(str(item) for item in summary_value if str(item).strip())
+                
+                replacements_made = replace_all_red_segments(red_segments, replacement_text)
+                print(f"        ✅ Fixed {management_type} Summary combined red text with field: '{field_attempt}'")
+                break
+    
+    return replacements_made
+
 def process_tables(document, flat_json):
-    """Your original function with minimal surgical fixes added"""
+    """Your original function with ALL surgical fixes added"""
     replacements_made = 0
     
     for table_idx, table in enumerate(document.tables):
@@ -695,6 +837,13 @@ def process_tables(document, flat_json):
             replacements_made += vehicle_replacements
             continue
         
+        # 🎯 FINAL FIX 1: Enhanced attendance list detection
+        if "attendance list" in table_text and "names and position titles" in table_text:
+            print(f"    👥 Detected Attendance List table")
+            attendance_replacements = handle_attendance_list_fix(table, flat_json)
+            replacements_made += attendance_replacements
+            continue
+        
         # Enhanced print accreditation detection
         print_accreditation_indicators = ["print name", "position title"]
         indicator_count = sum(1 for indicator in print_accreditation_indicators if indicator in table_text)
@@ -779,8 +928,13 @@ def process_tables(document, flat_json):
                         if cell_replacements == 0:
                             surgical_fix = handle_nature_business_multiline_fix(cell, flat_json)
                             replacements_made += surgical_fix
+                        
+                        # 🎯 FINAL FIX 2: Only if still no replacements were made, try ANY Management Summary fix
+                        if cell_replacements == 0 and surgical_fix == 0:
+                            management_summary_fix = handle_management_summary_fix(cell, flat_json)
+                            replacements_made += management_summary_fix
     
-    # 🎯 SURGICAL FIX 2: Handle Operator Declaration tables (only check last few tables)
+    # 🎯 SURGICAL FIX 3: Handle Operator Declaration tables (only check last few tables)
     print(f"\n🎯 SURGICAL FIX: Checking for Operator/Auditor Declaration tables...")
     for table in document.tables[-3:]:  # Only check last 3 tables
         if len(table.rows) <= 4:  # Only small tables