app.py

import gradio as gr
import re
from transformers import pipeline, AutoTokenizer
from PyPDF2 import PdfReader

# =========================
# Model setup (CPU-safe)
# =========================
MODEL_NAME = "sshleifer/distilbart-cnn-12-6"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
summarizer = pipeline(
    "summarization",
    model=MODEL_NAME,
    tokenizer=tokenizer,
    device=-1  # CPU only
)

CHUNK_SIZE = 900  # safe margin

# =========================
# Utilities
# =========================
def clean_text(text: str) -> str:
    """Fix quotes, spacing, repetition, and broken punctuation."""
    text = text.replace("‘", "'").replace("’", "'")
    text = text.replace("“", '"').replace("”", '"')
    text = re.sub(r"[.]{2,}", ".", text)
    text = re.sub(r"[']{2,}", "'", text)
    text = re.sub(r"\s+", " ", text)
    sentences = re.split(r'(?<=[.!?])\s+', text)
    seen = set()
    result = []
    for s in sentences:
        key = s.strip().lower()
        if key and key not in seen:
            seen.add(key)
            result.append(s.strip())
    return " ".join(result)


def chunk_text(text: str):
    """Token-aware chunking to avoid model overflow."""
    tokens = tokenizer.encode(text, add_special_tokens=False)
    chunks = []
    for i in range(0, len(tokens), CHUNK_SIZE):
        chunk_tokens = tokens[i:i + CHUNK_SIZE]
        chunk_text = tokenizer.decode(chunk_tokens, skip_special_tokens=True)
        chunks.append(chunk_text)
    return chunks


def summarize_long_text(text: str) -> str:
    """Summarize arbitrarily long text safely."""
    if not text or len(text.strip()) == 0:
        return "No text provided."
   
    chunks = chunk_text(text)
    summaries = []
   
    for chunk in chunks:
        summary = summarizer(
            chunk,
            max_length=150,
            min_length=40,
            do_sample=False
        )[0]["summary_text"]
        summaries.append(summary)
   
    merged = " ".join(summaries)
    cleaned_summary = clean_text(merged)
    
    # Add study advice section
    study_advice = """
    
---

### 📚 How to Study This Summary Effectively

Here are some proven techniques to help you learn and remember the material better:

- **Active Recall** — Cover the summary (or close your eyes) and try to explain each main point in your own words. This is one of the most powerful ways to strengthen memory.
- **Spaced Repetition** — Review this summary today, again in 2–3 days, then in one week. Use free apps like Anki or Quizlet to turn key points into flashcards.
- **Feynman Technique** — Pretend you're teaching this topic to a friend (or a 12-year-old). Explaining it simply reveals what you truly understand.
- **Self-Testing** — Create 3–5 questions from the summary (e.g. “What is…?”, “Why does…?”, “Give an example of…”). Answer them without looking.
- **Make Connections** — Draw a quick mind map or diagram linking the main ideas together. This helps see the big picture.
- **Apply It** — If possible, solve related problems, write a short paragraph, or discuss the topic with someone.

Re-reading alone is weak — **active engagement** is what makes information stick!

Good luck with your studies! 🚀
"""
    
    return cleaned_summary + study_advice


def read_pdf(file) -> str:
    """Safely extract text from PDF."""
    try:
        reader = PdfReader(file)
        pages = [page.extract_text() or "" for page in reader.pages]
        return " ".join(pages)
    except Exception as e:
        return f"PDF read error: {e}"


# =========================
# Main handler
# =========================
def process_input(text, file):
    if file is not None:
        text = read_pdf(file)
    return summarize_long_text(text)


# =========================
# Gradio UI
# =========================
with gr.Blocks() as demo:
    gr.Markdown("# 📄 Long Text Summarizer (Free-Tier Safe)")
    gr.Markdown(
        "• Handles **thousands of words**\n"
        "• Supports **PDF upload**\n"
        "• Optimized for **CPU / free tier**\n"
        "• Includes **study tips** to help you learn better"
    )
   
    text_input = gr.Textbox(
        lines=15,
        label="Paste text (optional)",
        placeholder="Paste your lecture notes, article, or book chapter here..."
    )
   
    file_input = gr.File(
        label="Upload PDF (optional)",
        file_types=[".pdf"]
    )
   
    output = gr.Textbox(
        lines=14,
        label="Summary + Study Advice",
        placeholder="Your summary and learning tips will appear here..."
    )
   
    summarize_btn = gr.Button("Summarize & Get Study Tips", variant="primary")
   
    summarize_btn.click(
        fn=process_input,
        inputs=[text_input, file_input],
        outputs=output
    )

demo.launch()