Convert PDF to Markdown using `pdf_oxide`

pdf_oxide_pdf2md.py

"""Simple CLI example: convert a PDF file to Markdown using pdf_oxide."""

from pathlib import Path

import typer

from pdf_oxide import PdfDocument


app = typer.Typer(
    help="Convert a PDF file to Markdown using pdf_oxide (all pages by default).",
    add_completion=False,
)


@app.command()
def convert(
    pdf_path: Path = typer.Argument(..., help="Path to the input PDF file."),
    output: Path | None = typer.Option(
        None,
        "--output",
        "-o",
        help="Output Markdown file path. Defaults to <input_stem>.md in current directory.",
    ),
    detect_headings: bool = typer.Option(
        True,
        "--detect-headings/--no-detect-headings",
        help="Detect headings based on font size.",
    ),
    include_images: bool = typer.Option(
        False,
        "--include-images/--no-include-images",
        help="Include images in Markdown output.",
    ),
    preserve_layout: bool = typer.Option(
        False,
        "--preserve-layout/--no-preserve-layout",
        help="Preserve visual layout in conversion.",
    ),
) -> None:
    """Convert a specified PDF file into Markdown."""
    if not pdf_path.exists():
        typer.secho(f"Input file not found: {pdf_path}", fg=typer.colors.RED, err=True)
        raise typer.Exit(code=1)

    if not pdf_path.is_file():
        typer.secho(f"Input path is not a file: {pdf_path}", fg=typer.colors.RED, err=True)
        raise typer.Exit(code=1)

    if pdf_path.suffix.lower() != ".pdf":
        typer.secho(
            f"Warning: input file does not end with .pdf: {pdf_path.name}",
            fg=typer.colors.YELLOW,
            err=True,
        )

    output_path = output if output is not None else Path.cwd() / f"{pdf_path.stem}.md"

    try:
        doc = PdfDocument(str(pdf_path))
        markdown = doc.to_markdown_all(
            preserve_layout=preserve_layout,
            detect_headings=detect_headings,
            include_images=include_images,
        )
    except (OSError, RuntimeError) as exc:
        typer.secho(f"Conversion failed: {exc}", fg=typer.colors.RED, err=True)
        raise typer.Exit(code=1) from exc

    try:
        output_path.parent.mkdir(parents=True, exist_ok=True)
        output_path.write_text(markdown, encoding="utf-8")
    except OSError as exc:
        typer.secho(f"Failed to write output file: {exc}", fg=typer.colors.RED, err=True)
        raise typer.Exit(code=1) from exc

    typer.secho(f"Wrote Markdown to: {output_path}", fg=typer.colors.GREEN)
    typer.echo(f"Characters written: {len(markdown)}")


if __name__ == "__main__":
    app()