# app.py

##################################################### Import necessary libraries #####################################################
import os, shutil, time, json, sys, warnings
import gradio as gr
from pathlib import Path
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
warnings.filterwarnings("ignore")
from KeyFrameSelection.FeatureExtraction import process_video, save_records
from KeyFrameSelection.Similarties import hash_filter, clip_filter
from FrameProcessor.utils.io_utils import get_frames_from_folder, save_description_to_csv
from FrameProcessor.graph.workflow import frame_processor
from config.paths import output_csv_file, output_json_file


##################################################### Define the main summarization function #####################################################
def summarize_video(video_path):
    keyframe_dir = "outputs/keyframes"
    csv_path = "outputs/keyframes.csv"

    if os.path.exists("outputs"):
        shutil.rmtree("outputs")
    os.makedirs("outputs/final_output", exist_ok=True)

    start = time.time()

    # Step 1: Extract raw keyframes
    records, fps = process_video(video_path, interval_sec=10)

    # Step 2: Filter
    min_frames = 10
    max_iterations = 20
    iteration = 0
    hash_threshold = 5
    ssim_threshold = 0.95
    clip_threshold = 0.90
    filtered = records

    while len(filtered) >= min_frames and iteration < max_iterations:
        filtered = hash_filter(filtered, hash_threshold, ssim_threshold, 5)
        filtered = clip_filter(filtered, clip_threshold, 5)
        hash_threshold = max(1, hash_threshold - 1)
        ssim_threshold = max(0.5, ssim_threshold - 0.05)
        clip_threshold = min(0.99, clip_threshold + 0.03)
        iteration += 1

    save_records(filtered, keyframe_dir, csv_path, fps)
    frame_paths = get_frames_from_folder(keyframe_dir)

    # Step 3: Graph processing on each frame
    results = []
    for frame_path in frame_paths:
        state = {
            "frame_path": frame_path,
            "frame_data": {},
            "frame_features": {},
            "importance": "not_important",
            "reason": "",
            "description": {},
            "next_step": "describe_frame"
        }

        try:
            result = frame_processor.invoke(state)
            results.append(result)

            # time.sleep(4.1)  # ✅ Add delay here # this is to avoid rate limits

            if result["importance"] == "important":
                save_description_to_csv(result)

        except Exception as e:
            results.append({
                "frame_path": frame_path,
                "importance": "error",
                "reason": str(e)
            })

    important = [r for r in results if r["importance"] == "important"]

    with open(output_json_file, "w") as f:
        json.dump(results, f, indent=2, ensure_ascii=False)

    end = time.time()
    return f"✅ Processed {len(important)} important frames out of {len(results)} in {end - start:.2f}s."


###################################################### Gradio UI #####################################################
def process_uploaded_video(video_file):
    if not video_file:
        raise gr.Error("Please upload a video first.")
    return summarize_video(video_file)

with gr.Blocks(theme=gr.themes.Soft()) as demo:
    google_key = os.getenv("GOOGLE_API_KEY")
    gemini_key = os.getenv("GEMINI_API_KEY")

    google_short = google_key if google_key else "Not found"
    gemini_short = gemini_key if gemini_key else "Not found"

    gr.Markdown(
        """
        <div style='display: flex; justify-content: center; align-items: center; flex-direction: column; color: #e91e63; line-height: 1.8; margin-bottom: 30px;'>
            <h1 style='margin: 0;'>🎞️ Video Summarization</h1>
            <p>Upload your lecture or tutorial video</p>
            <p>Click <b>Summarize</b> to extract important frames and their content</p>
        </div>
        """,
        elem_id="title-section"
    )

    with gr.Row():
        with gr.Column(scale=1, min_width=400):
            video_upload = gr.File(label="🎥 Upload Video", file_types=["video"], type="filepath")
            summarize_btn = gr.Button("✨ Summarize", variant="primary")
            result_box = gr.Textbox(label="📄 Summary Result")

    summarize_btn.click(
        fn=process_uploaded_video,
        inputs=[video_upload],
        outputs=[result_box]
    )


####################################################### Launch the app #####################################################
if __name__ == "__main__":
    demo.launch()