src/io_utils.py

from pathlib import Path


def read_job_description(path: str | Path) -> str:
    path = Path(path)
    suffix = path.suffix.lower()

    if suffix == ".txt":
        return path.read_text(encoding="utf-8")

    if suffix == ".docx":
        from docx import Document

        document = Document(path)
        paragraphs = [paragraph.text.strip() for paragraph in document.paragraphs if paragraph.text.strip()]
        return "\n".join(paragraphs)

    raise ValueError(f"Unsupported job description format: {path.suffix}")