parser.py

import fitz
from docx import Document
import os

def extract_text_from_pdf(pdf_path):
    """Extract text from PDF using PyMuPDF."""
    try:
        doc = fitz.open(pdf_path)
        text = ""
        for page in doc:
            text += page.get_text()
        return text
    except Exception as e:
        print(f"Error reading PDF {pdf_path}: {e}")
        return ""

def extract_text_from_docx(docx_path):
    """Extract text from DOCX using python-docx."""
    try:
        doc = Document(docx_path)
        return "\n".join([para.text for para in doc.paragraphs])
    except Exception as e:
        print(f"Error reading DOCX {docx_path}: {e}")
        return ""

def load_documents(folder="data"):
    """Load all supported documents from a folder."""
    texts = []
    for file in os.listdir(folder):
        path = os.path.join(folder, file)
        if file.endswith(".pdf"):
            texts.append(extract_text_from_pdf(path))
        elif file.endswith(".docx"):
            texts.append(extract_text_from_docx(path))
        else:
            print(f"⚠ Skipped unsupported file: {file}")
    return texts