from pathlib import Path

from docx import Document
from pypdf import PdfReader


class DocumentParser:
    @staticmethod
    def parse_file(file_path: str) -> str:
        path = Path(file_path)
        suffix = path.suffix.lower()
        if suffix == ".txt":
            return path.read_text(encoding="utf-8", errors="ignore")
        if suffix == ".docx":
            doc = Document(file_path)
            return "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
        if suffix == ".pdf":
            reader = PdfReader(file_path)
            pages = [page.extract_text() or "" for page in reader.pages]
            return "\n".join(pages)
        return path.read_text(encoding="utf-8", errors="ignore")