#!/usr/bin/env python3
"""从 ToneOZ-Pinyin-WenKai-Regular.ttf 中提取拼音/字母/数字字符，生成新的字体文件。"""

from fontTools.ttLib import TTFont
from fontTools.subset import Subsetter
from pathlib import Path

BASE = Path(__file__).resolve().parent
INPUT = BASE / "input-fonts" / "ToneOZ-Pinyin-WenKai-Regular.ttf"
OUTPUT = BASE / "output-fonts" / "ToneOZ-Pinyin-Kai-Regular.ttf"

# Unicode 码点范围
RANGES = [
    (0x0020, 0x007E),  # 基本 ASCII（字母、数字、标点）
    (0x00C0, 0x00FF),  # 拉丁字母-1 补充
    (0x0100, 0x017F),  # 拉丁字母扩展 A
    (0x01D6, 0x01DC),  # ü 的四个声调变体
]


def build_unicodes():
    codepoints = set()
    for start, end in RANGES:
        for cp in range(start, end + 1):
            codepoints.add(cp)
    return sorted(codepoints)


def main():
    font = TTFont(INPUT)
    unicodes = build_unicodes()

    # 使用 fonttools Subsetter 提取指定字符
    sub = Subsetter()
    sub.populate(unicodes=unicodes)
    sub.subset(font)

    OUTPUT.parent.mkdir(parents=True, exist_ok=True)
    font.save(OUTPUT)
    print(f"提取完成: {OUTPUT}")
    print(f"包含 {len(unicodes)} 个码点")

    # 输出范围统计
    for start, end in RANGES:
        name = f"U+{start:04X}-U+{end:04X}"
        glyphs_in_range = sum(
            1 for cp in range(start, end + 1) if cp in set(unicodes)
        )
        print(f"  {name}: {glyphs_in_range} 个字符")


if __name__ == "__main__":
    main()