src/utils.py

import base64
import os
from os import path as osp
from PIL import Image
from io import BytesIO
from io import StringIO, BytesIO
import textwrap
from typing import Iterator, TextIO, List, Dict, Any, Optional, Sequence, Union
import urllib.parse  # Add this if missing
import yt_dlp  # Add this - it's missing!

import glob
from tqdm import tqdm
from pytubefix import YouTube, Stream
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import WebVTTFormatter
from transformers import BridgeTowerProcessor, BridgeTowerForContrastiveLearning
import torch
import cv2


# encoding image at given path or PIL Image using base64
def encode_image(image_path_or_PIL_img):
    if isinstance(image_path_or_PIL_img, Image.Image):
        # this is a PIL image
        buffered = BytesIO()
        image_path_or_PIL_img.save(buffered, format="JPEG")
        return base64.b64encode(buffered.getvalue()).decode('utf-8')
    else:
        # this is a image_path
        with open(image_path_or_PIL_img, "rb") as image_file:
            return base64.b64encode(image_file.read()).decode('utf-8')
        

# checking whether the given string is base64 or not
def isBase64(sb):
    try:
        if isinstance(sb, str):
                # If there's any unicode here, an exception will be thrown and the function will return false
                sb_bytes = bytes(sb, 'ascii')
        elif isinstance(sb, bytes):
                sb_bytes = sb
        else:
                raise ValueError("Argument must be string or bytes")
        return base64.b64encode(base64.b64decode(sb_bytes)) == sb_bytes
    except Exception:
            return False
    

def create_dummy_image(size=(224, 224)):
    """Creates a blank white image to be used as a dummy input when no real image is provided."""
    return Image.new("RGB", size, (255, 255, 255))

def bt_embeddings(prompt, base64_image=None):
    # Load the processor and model
    processor = BridgeTowerProcessor.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc")
    model = BridgeTowerForContrastiveLearning.from_pretrained("BridgeTower/bridgetower-large-itm-mlm-itc")

    if base64_image:
        if not isBase64(base64_image):
            raise TypeError("Image input must be in base64 encoding!")
        try:
            image_data = base64.b64decode(base64_image)
            image = Image.open(BytesIO(image_data)).convert("RGB")
        except Exception as e:
            raise ValueError("Invalid image data!") from e
    else:
        image = create_dummy_image()  # Use a dummy white image for text-only input

    texts = [prompt]
    images = [image]

    inputs = processor(images=images, text=texts, padding=True, return_tensors="pt")

    with torch.no_grad():
        outputs = model(**inputs)

    if base64_image:
        embeddings = outputs.cross_embeds  # Use cross-modal embeddings when an image is provided
    else:
        embeddings = outputs.text_embeds  # Extract unimodal text embeddings

    return embeddings.squeeze().tolist()


# Resizes a image and maintains aspect ratio
def maintain_aspect_ratio_resize(image, width=None, height=None, inter=cv2.INTER_AREA):
    # Grab the image size and initialize dimensions
    dim = None
    (h, w) = image.shape[:2]

    # Return original image if no need to resize
    if width is None and height is None:
        return image

    # We are resizing height if width is none
    if width is None:
        # Calculate the ratio of the height and construct the dimensions
        r = height / float(h)
        dim = (int(w * r), height)
    # We are resizing width if height is none
    else:
        # Calculate the ratio of the width and construct the dimensions
        r = width / float(w)
        dim = (width, int(h * r))

    # Return the resized image
    return cv2.resize(image, dim, interpolation=inter)

# a help function that helps to convert a specific time written as a string in format `webvtt` into a time in miliseconds
def str2time(strtime):
    # strip character " if exists
    strtime = strtime.strip('"')
    # get hour, minute, second from time string
    hrs, mins, seconds = [float(c) for c in strtime.split(':')]
    # get the corresponding time as total seconds 
    total_seconds = hrs * 60**2 + mins * 60 + seconds
    total_miliseconds = total_seconds * 1000
    return total_miliseconds


# helper function for convert time in second to time format for .vtt or .srt file
def format_timestamp(seconds: float, always_include_hours: bool = False, fractionalSeperator: str = '.'):
    assert seconds >= 0, "non-negative timestamp expected"
    milliseconds = round(seconds * 1000.0)

    hours = milliseconds // 3_600_000
    milliseconds -= hours * 3_600_000

    minutes = milliseconds // 60_000
    milliseconds -= minutes * 60_000

    seconds = milliseconds // 1_000
    milliseconds -= seconds * 1_000

    hours_marker = f"{hours:02d}:" if always_include_hours or hours > 0 else ""
    return f"{hours_marker}{minutes:02d}:{seconds:02d}{fractionalSeperator}{milliseconds:03d}"


def _processText(text: str, maxLineWidth=None):
    if (maxLineWidth is None or maxLineWidth < 0):
        return text

    lines = textwrap.wrap(text, width=maxLineWidth, tabsize=4)
    return '\n'.join(lines)

# helper function to convert transcripts generated by whisper to .vtt file
def write_vtt(transcript: Iterator[dict], file: TextIO, maxLineWidth=None):
    print("WEBVTT\n", file=file)
    for segment in transcript:
        text = _processText(segment['text'], maxLineWidth).replace('-->', '->')

        print(
            f"{format_timestamp(segment['start'])} --> {format_timestamp(segment['end'])}\n"
            f"{text}\n",
            file=file,
            flush=True,
        )

# helper function to convert transcripts generated by whisper to .srt file
def write_srt(transcript: Iterator[dict], file: TextIO, maxLineWidth=None):
    """
    Write a transcript to a file in SRT format.
    Example usage:
        from pathlib import Path
        from whisper.utils import write_srt
        result = transcribe(model, audio_path, temperature=temperature, **args)
        # save SRT
        audio_basename = Path(audio_path).stem
        with open(Path(output_dir) / (audio_basename + ".srt"), "w", encoding="utf-8") as srt:
            write_srt(result["segments"], file=srt)
    """
    for i, segment in enumerate(transcript, start=1):
        text = _processText(segment['text'].strip(), maxLineWidth).replace('-->', '->')

        # write srt lines
        print(
            f"{i}\n"
            f"{format_timestamp(segment['start'], always_include_hours=True, fractionalSeperator=',')} --> "
            f"{format_timestamp(segment['end'], always_include_hours=True, fractionalSeperator=',')}\n"
            f"{text}\n",
            file=file,
            flush=True,
        )

def getSubs(segments: Iterator[dict], format: str, maxLineWidth: int=-1) -> str:
    segmentStream = StringIO()

    if format == 'vtt':
        write_vtt(segments, file=segmentStream, maxLineWidth=maxLineWidth)
    elif format == 'srt':
        write_srt(segments, file=segmentStream, maxLineWidth=maxLineWidth)
    else:
        raise Exception("Unknown format " + format)

    segmentStream.seek(0)
    return segmentStream.read()

def download_video(video_url, path='/tmp/'):
    print(f'Getting video information for {video_url}')
    if not video_url.startswith('http'):
        return os.path.join(path, video_url)

    filepath = glob.glob(os.path.join(path, '*.mp4'))
    if len(filepath) > 0:
        return filepath[0]

    def progress_callback(stream: Stream, data_chunk: bytes, bytes_remaining: int) -> None:
        pbar.update(len(data_chunk))
    
    yt = YouTube(video_url, on_progress_callback=progress_callback)
    stream = yt.streams.filter(progressive=True, file_extension='mp4', res='720p').desc().first()
    if stream is None:
        stream = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first()
    if not os.path.exists(path):
        os.makedirs(path)
    filepath = os.path.join(path, stream.default_filename)
    if not os.path.exists(filepath):   
        print('Downloading video from YouTube...')
        pbar = tqdm(desc='Downloading video from YouTube', total=stream.filesize, unit="bytes")
        stream.download(path)
        pbar.close()
    return filepath

def get_video_id_from_url(video_url):
    """
    Examples:
    - http://youtu.be/SA2iWivDJiE
    - http://www.youtube.com/watch?v=_oPAwA_Udwc&feature=feedu
    - http://www.youtube.com/embed/SA2iWivDJiE
    - http://www.youtube.com/v/SA2iWivDJiE?version=3&amp;hl=en_US
    """
    import urllib.parse
    url = urllib.parse.urlparse(video_url)
    if url.hostname == 'youtu.be':
        return url.path[1:]
    if url.hostname in ('www.youtube.com', 'youtube.com'):
        if url.path == '/watch':
            p = urllib.parse.parse_qs(url.query)
            return p['v'][0]
        if url.path[:7] == '/embed/':
            return url.path.split('/')[2]
        if url.path[:3] == '/v/':
            return url.path.split('/')[2]

    return video_url

# if this has transcript then download
def get_transcript_vtt(video_url, path='/tmp'):
    video_id = get_video_id_from_url(video_url)
    filepath = os.path.join(path,'captions.vtt')
    if os.path.exists(filepath):
        return filepath

    transcript = YouTubeTranscriptApi.get_transcript(video_id, languages=['en-GB', 'en'])
    formatter = WebVTTFormatter()
    webvtt_formatted = formatter.format_transcript(transcript)
    
    with open(filepath, 'w', encoding='utf-8') as webvtt_file:
        webvtt_file.write(webvtt_formatted)
    webvtt_file.close()

    return filepath

# if this has transcript then download
def download_youtube_subtitle(video_url, path='./shared_data/videos/video1'):
    video_id = video_url.split('v=')[-1]
    output_path = os.path.join(path, f"{video_id}.en.vtt")

    if os.path.exists(output_path):
        return output_path

    os.makedirs(path, exist_ok=True)
    
    ydl_opts = {
        'skip_download': True,
        'writesubtitles': True,
        'subtitleslangs': ['en'],
        'subtitlesformat': 'vtt',
        'outtmpl': os.path.join(path, '%(id)s.%(ext)s'),
    }

    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
        ydl.download([video_url])

    return output_path