appv1.py

import gradio as gr
import fitz  # PyMuPDF
from docx import Document
import io

def extract_text_from_pdf(uploaded_file):
    try:
        # Fix: handle both bytes and file-like
        file_bytes = uploaded_file if isinstance(uploaded_file, bytes) else uploaded_file.read()
        doc = fitz.open(stream=file_bytes, filetype="pdf")
        text = ""
        for page in doc:
            page_text = page.get_text()
            if page_text.strip():
                text += page_text + "\n"
        return text.strip()
    except Exception as e:
        return f"Error extracting text: {str(e)}"

def extract_los(lo_file):
    try:
        file_bytes = lo_file if isinstance(lo_file, bytes) else lo_file.read()
        name = getattr(lo_file, "name", "")
        ext = name.lower().split('.')[-1] if name else "docx"

        if ext == "txt":
            return file_bytes.decode("utf-8").splitlines()
        elif ext == "docx":
            file_stream = io.BytesIO(file_bytes)
            doc = Document(file_stream)
            return [p.text.strip() for p in doc.paragraphs if p.text.strip()]
        else:
            return []
    except Exception as e:
        return [f"Error loading LOs: {str(e)}"]

def compare_handouts(old_pdf, new_pdf, lo_file):
    old_text = extract_text_from_pdf(old_pdf)
    new_text = extract_text_from_pdf(new_pdf)
    los = extract_los(lo_file)

    if not old_text or not new_text:
        return "❗ One or both PDFs may not contain extractable text."

    old_lines = set(old_text.splitlines())
    new_lines = set(new_text.splitlines())

    added = new_lines - old_lines
    removed = old_lines - new_lines
    total_lines = max(len(old_lines.union(new_lines)), 1)
    change_percent = ((len(added) + len(removed)) / total_lines) * 100

    lo_summary = ""
    if los:
        lo_summary = "\n".join([f"• {lo}" for lo in los])
    else:
        lo_summary = "No learning outcomes detected."

    return f"🔍 **Change Summary:**\n- Added lines: {len(added)}\n- Removed lines: {len(removed)}\n- Change %: {change_percent:.2f}%\n\n📘 **Learning Outcomes:**\n{lo_summary}"

iface = gr.Interface(
    fn=compare_handouts,
    inputs=[
        gr.File(label="📤 Old Handout PDF", type="binary"),
        gr.File(label="📥 New Handout PDF", type="binary"),
        gr.File(label="📚 Learning Outcomes (.docx or .txt)", type="binary")
    ],
    outputs="text",
    title="📊 Handout Comparison & Learning Outcome Checker",
    description="Upload old & new PDFs with optional LOs to see update percentage and coverage."
)

iface.launch()