"""資料分析：讀取公開資料，查詢各縣市學生人數。"""

import csv
from pathlib import Path


DATA_FILE = Path("data/students_by_county.csv")
SAMPLE_YEAR = "114"
SAMPLE_FIELD = "國小[人]"


def load_rows(path=DATA_FILE):
    """讀取 CSV；utf-8-sig 也能正確處理政府資料常見的 BOM。"""
    with open(path, encoding="utf-8-sig", newline="") as file:
        return list(csv.DictReader(file))


def parse_count(value):
    """將有人數的欄位轉成整數；空白或非數字代表未知，不當成 0。"""
    cleaned = (value or "").strip().replace(",", "")
    if not cleaned or cleaned == "-":
        return None
    try:
        return int(cleaned)
    except ValueError:
        return None


def count_by_county(rows, school_year, field):
    """依學年度篩選，再回傳各縣市的人數排序。"""
    totals = {}
    for row in rows:
        if row.get("學年度", "").strip() != str(school_year):
            continue

        count = parse_count(row.get(field))
        county = row.get("縣市別", "").strip()
        if county and count is not None:
            totals[county] = count

    return sorted(totals.items(), key=lambda item: item[1], reverse=True)


def get_count(rows, school_year, county, field):
    """取得指定學年度、縣市及欄位的人數；找不到時回傳 None。"""
    for row in rows:
        if row.get("學年度", "").strip() != str(school_year):
            continue
        if row.get("縣市別", "").strip() == county:
            return parse_count(row.get(field))
    return None


def print_text_chart(results, limit=8):
    """在 Console 印出簡單長條圖，讓每筆數字都能被核對。"""
    if not results:
        print("沒有符合條件的資料，請檢查學年度和欄位名稱。")
        return

    visible = results[:limit]
    largest = max(value for _, value in visible)
    print("縣市       人數 | 比例長條")
    for county, value in visible:
        bar_length = round(value / largest * 24) if largest else 0
        print(f"{county:<6} {value:>8,} | {'█' * bar_length}")


def main():
    rows = load_rows()
    fields = list(rows[0]) if rows else []
    print("=== 資料分析：縣市學生人數 ===")
    print(f"讀入 {len(rows)} 列資料")
    print(f"欄位：{', '.join(fields)}")
    print()

    # 範例問題：114 學年度，哪些縣市的國小學生人數最多？
    question = f"{SAMPLE_YEAR} 學年度，哪些縣市的 {SAMPLE_FIELD} 最多？"
    results = count_by_county(rows, SAMPLE_YEAR, SAMPLE_FIELD)
    print(f"範例問題：{question}")
    print_text_chart(results)

    # 你的下一步：換一個學年度、教育階段或可比較的欄位，
    # 先寫下預測，再執行並核對其中一筆原始資料。


if __name__ == "__main__":
    main()