from moviepy.editor import VideoFileClip, concatenate_videoclips,vfx
from moviepy.editor import AudioFileClip, CompositeAudioClip#, TextClip
# from moviepy.video.tools.subtitles import SubtitlesClip
import os 

# import torch
# import soundfile as sf
# from transformers import pipeline

# synthesiser = pipeline("text-to-audio", "facebook/musicgen-stereo-small")
# sampling_rate = model.config.audio_encoder.sampling_rate



def combine_videos(folder_name, length_speech):

    # length = len(os.listdir(folder_name))

    def check_len(dir):
        if len(dir) < len(length_speech):
            return check_len(dir*2)
        else:
            return dir

    vid_dir = os.listdir(folder_name)
    if len(vid_dir) == 0:
        raise Exception("Canot find any video! Please try different words")
        
    vid_dir = check_len(vid_dir)

    vids = [VideoFileClip(os.path.join(folder_name,x)) for x in sorted(vid_dir)]

    print(vids, len(vid_dir), len(length_speech))
    
    combined = concatenate_videoclips(
        [vid.subclip(0,ls).fx(vfx.fadein,0.5).fx(vfx.fadeout,0.5) if vid.duration > ls else vid.fx(vfx.fadein,0.5).fx(vfx.fadeout,0.5) for vid, ls in zip(vids, length_speech)],
        # [VideoFileClip(os.path.join(folder_name,x)).subclip(0,7).fx(vfx.fadein,0.5).fx(vfx.fadeout,0.5) for x in sorted(os.listdir(folder_name))], 
        "compose",bg_color=None, padding=0
    )
    combined.write_videofile(os.path.join(folder_name, "Final_Ad_Video.mp4"))
    
#     if length <= 6:
#         combined = concatenate_videoclips([VideoFileClip(os.path.join(folder_name,x)).subclip(0,10) for x in os.listdir(folder_name)])
#         combined.write_videofile(os.path.join(folder_name, "Ad_Video.mp4"))
#     else :
#         combined = concatenate_videoclips([VideoFileClip(os.path.join(folder_name,x)).subclip(0,60//length) for x in os.listdir(folder_name)])
#         combined.write_videofile(os.path.join(folder_name, "Ad_Video.mp4"))
    print("Done! Your ads video has been created")


def combine_audio_video(folder_name, vid, speech, sentences, length_speech):
    videoclip = VideoFileClip(vid)
    audioclip = AudioFileClip(speech)

    # music = synthesiser("lo-fi music with a soothing melody", forward_params={"max_new_tokens": sampling_rate//sum(length_speech)})

    # sf.write("musicgen_out.wav", music["audio"][0].T, music["sampling_rate"])


    #generator = lambda txt: TextClip(txt, font='Arial', fontsize=24, color='white')
    # subs = [((0, 4), 'subs1'),
    #         ((4, 9), 'subs2'),
    #         ((9, 12), 'subs3'),
    #         ((12, 16), 'subs4')]

    # ls = [0] + length_speech
    # subs = [ ( (ls[i],ls[i+1]), sub) for i,sub in enumerate(sentences)]
    
    # subtitles = SubtitlesClip(subs, generator)

    
    # videoclip = CompositeVideoClip([videoclip, subtitles.set_pos(('center','bottom'))])

    new_audioclip = CompositeAudioClip([audioclip])
    videoclip.audio = new_audioclip
    # videoclip.audio = CompositeAudioClip([audioclip, AudioFileClip("musicgen_out.wav")])
    videoclip.write_videofile(os.path.join(folder_name,"new_filename.mp4"))