src/parsers.py

from typing import List, Tuple
from pypdf import PdfReader
from docx import Document

def read_pdf(path: str) -> List[Tuple[int, str]]:
    reader = PdfReader(path)
    pages = []
    for i, page in enumerate(reader.pages):
        text = (page.extract_text() or "").strip()
        if text:
            pages.append((i + 1, text))
    return pages

def read_docx(path: str) -> List[Tuple[int, str]]:
    doc = Document(path)
    text = "\n".join(p.text for p in doc.paragraphs if p.text.strip()).strip()
    return [(1, text)] if text else []