from transformers import pipeline
import fitz  # PyMuPDF
import gradio as gr

# Load summarization model
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

# Extract text from PDF
def extract_text_from_pdf(pdf_file):
    try:
        doc = fitz.open(pdf_file.name)
        text = ""
        for page in doc:
            text += page.get_text()
        return text
    except Exception as e:
        return f"Error extracting text from PDF: {e}"

# Main summarizer function
def summarize_input(text, pdf_file):
    if pdf_file is not None:
        text = extract_text_from_pdf(pdf_file)
        if text.startswith("Error"):
            return text

    if not text or len(text.strip()) < 30:
        return "Please provide more text or a valid PDF."

    if len(text) > 3000:
        text = text[:3000]

    try:
        summary = summarizer(text, max_length=120, min_length=30, do_sample=False)
        return summary[0]['summary_text']
    except Exception as e:
        return f"Summarization failed: {e}"

# Gradio interface
app = gr.Interface(
    fn=summarize_input,
    inputs=[
        gr.Textbox(label="Enter Text (leave blank if uploading PDF)", lines=10),
        gr.File(label="Upload PDF File", file_types=[".pdf"]),
    ],
    outputs=gr.Textbox(label="Summary"),
    title="Text & PDF Summarizer",
    description="Paste text or upload a PDF to summarize using BART model from Hugging Face."
)

app.launch()