"""File parsing for uploaded documents (pdf / markdown / txt)."""
from __future__ import annotations

from pathlib import Path


class ParseError(Exception):
    pass


def parse_pdf(path: Path) -> str:
    import fitz  # PyMuPDF

    try:
        doc = fitz.open(path)
    except Exception as exc:
        raise ParseError(f"cannot open PDF: {exc}") from exc
    parts = []
    for page in doc:
        parts.append(page.get_text())
    doc.close()
    return "\n".join(parts)


def parse_text(path: Path) -> str:
    import chardet

    raw = path.read_bytes()
    # Try utf-8 first, else detect encoding
    try:
        return raw.decode("utf-8")
    except UnicodeDecodeError:
        pass
    guess = chardet.detect(raw)
    enc = guess.get("encoding") or "utf-8"
    try:
        return raw.decode(enc, errors="replace")
    except Exception:
        return raw.decode("utf-8", errors="replace")


def parse_document(path: Path) -> str:
    ext = path.suffix.lower().lstrip(".")
    if ext == "pdf":
        return parse_pdf(path)
    return parse_text(path)