# data/loader.py – load 1_Year_U_1.jsonl

import os
import json
from typing import List, Dict, Any

DATA_PATH = "data/1_Year_U_1.jsonl"

ENTRIES: List[Dict[str, Any]] = []
RAW_KNOWLEDGE: str = ""


if os.path.exists(DATA_PATH):
    with open(DATA_PATH, "r", encoding="utf-8") as f:
        for line in f:
            line = line.strip()
            if not line:
                continue
            try:
                obj = json.loads(line)
                if "text" in obj:
                    ENTRIES.append(obj)
            except json.JSONDecodeError:
                continue

    if ENTRIES:
        RAW_KNOWLEDGE = "\n\n".join(e["text"] for e in ENTRIES)
    else:
        RAW_KNOWLEDGE = "ຍັງບໍ່ມີຂໍ້ມູນປະຫວັດສາດທີ່ອ່ານໄດ້."
else:
    RAW_KNOWLEDGE = "ຍັງບໍ່ມີຂໍ້ມູນປະຫວັດສາດຖືກໂຫຼດ."