"""PPT/PPTX parser: convert to PDF, then reuse PdfParser."""

from __future__ import annotations

from pathlib import Path

from rag_cut.models import Block
from rag_cut.parsers.base import BaseParser
from rag_cut.parsers.office_to_pdf import convert_to_pdf
from rag_cut.parsers.pdf_parser import PdfParser


class PptParser(BaseParser):
    """Parse presentations by converting to PDF and delegating to PdfParser."""

    def __init__(self) -> None:
        self._pdf_parser = PdfParser()

    def parse(self, path: Path, assets_dir: Path) -> list[Block]:
        assets_dir.mkdir(parents=True, exist_ok=True)
        pdf_dir = assets_dir / "_conversion"
        pdf_path = convert_to_pdf(path, pdf_dir)

        blocks = self._pdf_parser.parse(pdf_path, assets_dir)
        source_fmt = path.suffix.lower().lstrip(".")
        for block in blocks:
            block.meta.setdefault("source_format", source_fmt)
            if page := block.meta.get("page"):
                block.meta["slide"] = page
        return blocks