import gradio as gr
import pandas as pd
import fitz  # PyMuPDF
import os
from huggingface_hub import HfApi, HfHubHTTPError
import requests
import time

def extract_paragraphs_with_headers(pdf_path, progress=None):
    doc = fitz.open(pdf_path)
    data = []

    total_pages = len(doc)
    for page_num, page in enumerate(doc):
        if progress:
            progress((page_num + 1) / total_pages, desc=f"Processing Page {page_num + 1}/{total_pages}")

        blocks = page.get_text("dict")["blocks"]
        for block in blocks:
            if "lines" in block:
                text = ""
                for line in block["lines"]:
                    for span in line["spans"]:
                        text += span["text"] + " "

                text = text.strip()

                # Detect headers based on font size
                is_header = any(span["size"] > 15 for line in block["lines"] for span in line["spans"])

                data.append({
                    "page_num": page_num + 1,
                    "text": text,
                    "is_header": is_header
                })

    return data

def upload_with_progress(file_path, repo_id, token, progress):
    """
    Upload file to Hugging Face Dataset with progress tracking.
    """
    file_size = os.path.getsize(file_path)
    url = f"https://huggingface.co/api/datasets/{repo_id}/upload"

    headers = {
        "Authorization": f"Bearer {token}"
    }

    with open(file_path, 'rb') as f:
        chunk_size = 1024 * 1024  # 1MB
        uploaded = 0

        while True:
            chunk = f.read(chunk_size)
            if not chunk:
                break

            response = requests.put(
                url,
                headers=headers,
                data=chunk
            )

            uploaded += len(chunk)
            progress(uploaded / file_size, desc=f"Uploading... {uploaded // (1024 * 1024)}MB/{file_size // (1024 * 1024)}MB")
            time.sleep(0.1)  # Simulate delay for progress update

            if response.status_code != 200:
                raise Exception(f"Upload failed: {response.text}")

    return f"✅ Successfully uploaded to {repo_id}"

def pdf_to_parquet_and_upload(pdf_files, hf_token, dataset_repo_id, action_choice, progress=gr.Progress()):
    all_data = []

    # Process each uploaded PDF
    for pdf_file in pdf_files:
        extracted_data = extract_paragraphs_with_headers(pdf_file.name, progress=progress)
        for item in extracted_data:
            all_data.append({
                'filename': os.path.basename(pdf_file.name),
                'page_num': item['page_num'],
                'text': item['text'],
                'is_header': item['is_header']
            })

    # Convert to DataFrame
    df = pd.DataFrame(all_data)

    # Save as Parquet
    parquet_file = 'papers_with_headers.parquet'
    df.to_parquet(parquet_file, engine='pyarrow', index=False)

    upload_message = ""

    # Only upload if the user selects it
    if action_choice in ["Upload to Hugging Face", "Both"]:
        try:
            upload_message = upload_with_progress(parquet_file, dataset_repo_id, hf_token, progress)
        except Exception as e:
            upload_message = f"❌ Upload failed: {str(e)}"

    # Return Parquet file and status message
    return parquet_file, upload_message

# Gradio Interface
iface = gr.Interface(
    fn=pdf_to_parquet_and_upload,
    inputs=[
        gr.File(file_types=[".pdf"], file_count="multiple", label="Upload PDFs (Drag & Drop or Search)"),
        gr.Textbox(label="Hugging Face API Token", type="password", placeholder="Enter your Hugging Face API token"),
        gr.Textbox(label="Your Dataset Repo ID (e.g., username/research-dataset)", placeholder="username/research-dataset"),
        gr.Radio(["Download Locally", "Upload to Hugging Face", "Both"], label="Action", value="Download Locally")
    ],
    outputs=[
        gr.File(label="Download Parquet File"), 
        gr.Textbox(label="Status")
    ],
    title="PDF to Parquet Converter with Upload Progress",
    description="Upload your PDFs (drag & drop or search), convert them to Parquet, and upload to your own Hugging Face Dataset repo with real-time progress tracking."
)

iface.launch()