Update app.py

app.py

@@ -575,12 +575,12 @@ def extract_graph_answers_from_as(text: str):
 
 def extract_marks_from_grading(grading_text): 
     """ 
-    Parse the grading markdown and extract marks per question. 
+    Parse the grading markdown and extract marks per question from the Awarded column only.
     """ 
     print("🔎 Extracting awarded marks from grading output...") 
     grading_json = {"grading": []} 
 
-    question_blocks = re.split(r"##\s*Question\s+", grading_text) 
+    question_blocks = re.split(r"###\s*Question\s+", grading_text) 
     for block in question_blocks[1:]: 
         first_line = block.strip().splitlines()[0].strip() if block.strip().splitlines() else "" 
         q_id_match = re.match(r"([0-9]+(?:[a-zA-Z]|\([^)]+\)|(?:\.[a-zA-Z0-9]+))*)", first_line) 
@@ -588,7 +588,20 @@ def extract_marks_from_grading(grading_text):
             q_id = first_line.split()[0] if first_line else "" 
         else: 
             q_id = q_id_match.group(1).strip() 
-        awarded = re.findall(r"\b(M\d+|A\d+|R\d+|M0|A0|R0)\b", block) 
+        
+        # Extract marks only from the "Awarded" column (4th column in the table)
+        awarded = []
+        lines = block.split('\n')
+        for line in lines:
+            if '|' in line:
+                parts = [p.strip() for p in line.split('|')]
+                # Check if this is a data row (not header or separator) and has at least 5 columns
+                if len(parts) >= 5 and not parts[1].startswith('-'):
+                    awarded_col = parts[4]  # 4th column (index 4 because of leading empty from split)
+                    # Extract mark codes from the awarded column
+                    marks = re.findall(r"\b([MABCR]\d+|[MABCR]0)\b", awarded_col)
+                    awarded.extend(marks)
+        
         grading_json["grading"].append({ 
             "question": q_id, 
             "marks_awarded": awarded