ingestion_engine/pdf_extractor.py

"""PDF text extraction using PyMuPDF."""

import fitz


def extract(file_path: str) -> str:
    """Extract text from all pages of a PDF file."""
    doc = fitz.open(file_path)
    pages = []
    for page in doc:
        text = page.get_text()
        if text.strip():
            pages.append(text)
    doc.close()
    return "\n\n".join(pages)