Merge pull request #320 from Pseudo-Lab/fix/apply-format

fix: apply user csv format

Author: soohyunme

getcloser/backend/app/scripts/user_data_to_question.py

@@ -7,14 +7,25 @@
 rows = []
 id_counter = 1
 
-with open(input_file, newline="", encoding="utf-8") as f:
+with open(input_file, newline="", encoding="utf-8-sig") as f:
     reader = csv.DictReader(f)
 
     for row in reader:
         user_id = row["idx"]
+        if user_id == "idx":
+            # Skip duplicated header row in data.
+            continue
 
         # category 1: 관심사 키워드 (JSON 리스트)
-        interests = json.loads(row["interest_keywords"])
+        raw_interest_keywords = (row.get("interest_keywords") or "").strip()
+        if raw_interest_keywords:
+            try:
+                interests = json.loads(raw_interest_keywords)
+            except json.JSONDecodeError:
+                # Fallback for non-JSON input like "a,b,c"
+                interests = [value.strip() for value in raw_interest_keywords.split(",") if value.strip()]
+        else:
+            interests = []
         for interest in interests:
             rows.append([
                 id_counter,