"""修正 WPS 写错的字体字符集：中文字体（名字含汉字，或是常见中文字体英文名）被标成 SYMBOL(02) 时改成 GB2312(86)。
输入、输出都是 DOCX。用法：python -I fix_charset.py in.docx out.docx"""
import re, sys, zipfile

CJK_LATIN = {"SimSun", "NSimSun", "SimHei", "FangSong", "KaiTi", "Microsoft YaHei", "DengXian"}

def is_cjk_font(name: str) -> bool:
    return bool(re.search(r"[一-鿿]", name)) or name in CJK_LATIN

def fix_font_table(xml: str) -> tuple[str, list[str]]:
    fixed = []
    def repl(m):
        name, body = m.group(1), m.group(2)
        if is_cjk_font(name) and re.search(r'w:charset w:val="02"', body):
            fixed.append(name)
            body = body.replace('w:charset w:val="02"', 'w:charset w:val="86"')
        return f'<w:font w:name="{name}">{body}</w:font>'
    return re.sub(r'<w:font w:name="([^"]+)">(.*?)</w:font>', repl, xml, flags=re.S), fixed

def main(src, dst):
    with zipfile.ZipFile(src) as zin, zipfile.ZipFile(dst, "w", zipfile.ZIP_DEFLATED) as zout:
        for item in zin.infolist():
            data = zin.read(item.filename)
            if item.filename == "word/fontTable.xml":
                xml, fixed = fix_font_table(data.decode("utf-8"))
                data = xml.encode("utf-8")
                print("fixed:", fixed)
            zout.writestr(item, data)

if __name__ == "__main__":
    main(sys.argv[1], sys.argv[2])