Update app.py

fix qp_extraction

app.py

@@ -213,32 +213,30 @@ def gemini_generate_content(model, prompt_text, file_upload_obj=None, image_obj=
     return raw_text 
 
 # ---------------- PARSERS ---------------- 
-def extract_question_ids_from_qpms(text): 
-    """ 
-    Extract question IDs from QP+MS transcript output. 
-    We expect the QP+MS prompt to produce lines like 'Question: <id>' 
-    Return a list of IDs in order of appearance, including duplicates. 
-    """ 
-    print("🔎 Extracting question IDs from QP+MS transcript using regex...") 
-    ids = [] 
-    for m in re.finditer(r"(?im)^\s*Question\s*:\s*([0-9]+(?:(?:\.[a-zA-Z0-9]+)+|(?:\([a-zA-Z0-9]+\))+|[a-zA-Z])*)\b", text): 
-        qid = m.group(1).strip() 
-        ids.append(qid) 
-    if ids: 
-        print(f"✅ Extracted {len(ids)} question IDs.") 
-        print("IDs:", ids) 
-        return ids 
-
-    # fallback scans 
-    for m in re.finditer(r"(?m)^\s*([0-9]+(?:(?:\.[a-zA-Z0-9]+)+|(?:\([a-zA-Z0-9]+\))+|[a-zA-Z])*)\s*[\.\):\-]\s", text): 
-        qid = m.group(1).strip() 
-        ids.append(qid) 
-    if ids: 
-        print(f"✅ Extracted {len(ids)} question IDs (fallback heuristic).") 
-        print("IDs:", ids) 
-    else: 
-        print("⚠️ No question IDs extracted; will send NA placeholder.") 
-    return ids 
+def extract_question_ids_from_qpms(text: str):
+    """Extract question IDs from QP+MS transcript.
+    Two-step approach: explicit 'Question X' lines, then fallback numbered lists.
+    Robust to hidden whitespace and simple unicode spaces."""
+    print("🔎 Extracting question IDs from QP+MS transcript using regex...")
+    
+    # Normalize spaces/tabs/non-breaking spaces
+    clean_text = text.replace("\u00A0", " ").replace("\t", " ")
+    
+    # Step 1: Look for explicit "Question X" lines
+    primary_matches = re.findall(r"^\s*Question\s*[:\s]\s*([\dA-Za-z.()]+)", clean_text, re.MULTILINE)
+    if primary_matches:
+        print(f"✅ Extracted {len(primary_matches)} question IDs from explicit 'Question X' lines.")
+        print("IDs:", primary_matches)
+        return primary_matches
+    
+    # Step 2: Fallback — numbered/sub-question lists
+    fallback_matches = re.findall(r"^\s*(\d+(?:[.)]|\([a-zA-Z0-9]+\))?[a-zA-Z0-9]*)", clean_text, re.MULTILINE)
+    if fallback_matches:
+        print(f"✅ Extracted {len(fallback_matches)} question IDs (fallback numbered lists).")
+        print("IDs:", fallback_matches)
+    else:
+        print("⚠️ No question IDs extracted; will send NA placeholder.")
+    return fallback_matches 
 
 # Update AS prompt builder to include graph detection