import re
import sys
import zipfile
from pathlib import Path


PLACEHOLDER_PATTERNS = [
    r"<p:sp\b(?:(?!</p:sp>).)*?<p:ph\b[^>]*(?:type=\"sldNum\"|type=\"dt\"|type=\"ftr\")[^>]*/>(?:(?!</p:sp>).)*?</p:sp>",
    r"<p:sp\b(?:(?!</p:sp>).)*?<a:t>Slide Number</a:t>(?:(?!</p:sp>).)*?</p:sp>",
    r"<p:sp\b(?:(?!</p:sp>).)*?<a:t>Date Placeholder</a:t>(?:(?!</p:sp>).)*?</p:sp>",
    r"<p:sp\b(?:(?!</p:sp>).)*?<a:t>Footer</a:t>(?:(?!</p:sp>).)*?</p:sp>",
]


def scrub_xml(xml: str) -> str:
    for pattern in PLACEHOLDER_PATTERNS:
        xml = re.sub(pattern, "", xml, flags=re.DOTALL)
    xml = re.sub(r"\s+sldNum=\"[^\"]*\"", "", xml)
    return xml


def main() -> None:
    if len(sys.argv) != 3:
        raise SystemExit("Usage: python scrub_pptx_placeholders.py <input.pptx> <output.pptx>")

    src = Path(sys.argv[1])
    dst = Path(sys.argv[2])
    dst.parent.mkdir(parents=True, exist_ok=True)

    with zipfile.ZipFile(src, "r") as zin, zipfile.ZipFile(dst, "w", zipfile.ZIP_DEFLATED) as zout:
        for item in zin.infolist():
            data = zin.read(item.filename)
            if item.filename.endswith(".xml") and (
                item.filename.startswith("ppt/notesSlides/")
                or item.filename.startswith("ppt/notesMasters/")
                or item.filename.startswith("ppt/slideMasters/")
            ):
                text = data.decode("utf-8")
                data = scrub_xml(text).encode("utf-8")
            zout.writestr(item, data)


if __name__ == "__main__":
    main()