import csv
from pathlib import Path


DATA_FILE = Path("")


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):
    """將數字欄位轉成整數或浮點數；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:
        try:
            return float(cleaned)
        except ValueError:
            return None


def analyze_extremes(rows, field):
    """找出指定欄位在各統計期中最高與最低的年份與數值。"""
    valid_rows = []
    for row in rows:
        period = row.get("統計期", "").strip()
        val = parse_count(row.get(field))
        if period and val is not None:
            valid_rows.append((period, val))
    
    if not valid_rows:
        return None, None
    
    max_item = max(valid_rows, key=lambda item: item[1])
    min_item = min(valid_rows, key=lambda item: item[1])
    return max_item, min_item


def print_text_chart(rows, field, label, limit=10):
    """在 Console 印出簡單長條圖，讓數字趨勢便於檢視。"""
    valid_rows = []
    for row in rows:
        period = row.get("統計期", "").strip()
        val = parse_count(row.get(field))
        if period and val is not None:
            valid_rows.append((period, val))
            
    if not valid_rows:
        print(f"沒有符合條件的資料：{label}")
        return

    visible = valid_rows[-limit:]
    largest = max(value for _, value in visible)
    print(f"\n=== {label} 近期趨勢與長條圖 ===")
    print(f"統計期       人數 | 比例長條")
    for period, value in visible:
        bar_length = round(value / largest * 24) if largest else 0
        print(f"{period:<6} {value:>10,} | {'█' * bar_length}")


def main():
    rows = load_rows()
    fields = list(rows[0]) if rows else []
    print("=== 資料分析：人口統計資料 ===")
    print(f"讀入 {len(rows)} 列資料")
    print(f"欄位：{', '.join(fields)}")
    print()

    targets = [
        ("", "全部總計人口"),
        ("", "男性人口"),
        ("", "女性人口")
    ]

    for field, label in targets:
        max_item, min_item = analyze_extremes(rows, field)
        if max_item and min_item:
            print(f"【{label}分析】")
            print(f"  - 最高：{max_item[0]}（共 {max_item[1]:,} 人）")
            print(f"  - 最低：{min_item[0]}（共 {min_item[1]:,} 人）")
            print()

    # 範例：印出總計人口的近期長條圖
    # print_text_chart(rows, "人口數/總計[人]", "全部總計人口")


if __name__ == "__main__":
    main()