from fastapi import UploadFile

MAX_UPLOAD_BYTES = 10 * 1024 * 1024  # 10 MB — statements are a few hundred KB


async def read_pdf_upload(
    file: UploadFile, max_bytes: int = MAX_UPLOAD_BYTES
) -> bytes:
    """Read an uploaded PDF with a size cap and magic-byte check.

    Raises ValueError with a user-readable, filename-prefixed message —
    upload endpoints surface these in their per-file `errors` list.
    """
    filename = file.filename or "unknown.pdf"
    data = await file.read(max_bytes + 1)
    if len(data) > max_bytes:
        raise ValueError(
            f"{filename}: file exceeds the {max_bytes // (1024 * 1024)} MB limit"
        )
    if not data.startswith(b"%PDF"):
        raise ValueError(f"{filename}: not a PDF file")
    return data