"""PDF parser entry point — delegates to the PyMuPDF pipeline."""

from __future__ import annotations

import os
from pathlib import Path

from rag_cut.models import Block
from rag_cut.parsers.base import BaseParser
from rag_cut.parsers.mineru_adapter import parse_pdf_with_mineru
from rag_cut.parsers.pdf.noise_filter import filter_noise_blocks
from rag_cut.parsers.pdf.pipeline import parse_pdf


class PdfParser(BaseParser):
    def parse(self, path: Path, assets_dir: Path) -> list[Block]:
        engine = os.getenv("RAG_CUT_PDF_ENGINE", "auto").strip().lower()
        if engine not in {"auto", "mineru", "pymupdf"}:
            engine = "auto"

        blocks: list[Block] | None = None
        if engine in {"auto", "mineru"}:
            blocks = parse_pdf_with_mineru(path, assets_dir)
            if blocks is None and engine == "mineru":
                raise RuntimeError("MinerU parsing failed or MinerU is not installed")

        if blocks is None:
            blocks = parse_pdf(path, assets_dir)

        # filter_noise_blocks already includes TOC removal.
        return filter_noise_blocks(blocks)