utils.py

import os
from io import StringIO, BytesIO
from typing import Iterator, TextIO, List, Dict, Any, Optional, Sequence, Union
import base64
import glob
from tqdm import tqdm
from pytubefix import YouTube, Stream
import cv2
import json
import textwrap

# 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,
        )

# Taken from the course: https://www.deeplearning.ai/short-courses/multimodal-rag-chat-with-videos/
def getSubs(segments: Iterator[dict], format: str, maxLineWidth: int=-1) -> str:
    segmentStream = StringIO()

    if format == 'vtt':
        write_vtt(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

# 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

# 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)

def load_json_file(file_path):
    # Open the JSON file in read mode
    with open(file_path, 'r') as file:
        data = json.load(file)
    return data