Skip to content

Pyaudio replaced by sounddevice library to fix some errors #84

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Pyaudio replaced by sounddevice library to fix some errors #84

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,8 @@ def install_package(package):

if "--with-audio" in sys.argv:
install_package('opencv-python')
install_package('pyaudio')
install_package('soundfile')
install_package('sounddevice')
sys.argv.remove("--with-audio")
else:
install_package('opencv-python')
Expand Down
135 changes: 51 additions & 84 deletions video_to_ascii/render_strategy/ascii_strategy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,24 +8,19 @@
import cv2
import tempfile

PLATFORM = 0
if sys.platform != 'win32':
PLATFORM = 1

from threading import Thread
from . import render_strategy as re
if PLATFORM:
from . import image_processor as ipe
else:
from . import image_processor_win as ipe
from . import image_processor as ipe
from os import get_terminal_size as _term_size
DEFAULT_TERMINAL_SIZE = _term_size().columns, _term_size().lines


class AsciiStrategy(re.RenderStrategy):
"""Print each frame in the terminal using ascii characters"""

def convert_frame_pixels_to_ascii(self, frame, dimensions=DEFAULT_TERMINAL_SIZE, new_line_chars=False):
"""
Replace all pixels with colored chars and return the resulting string
Replace all pixeles with colored chars and return the resulting string

This method iterates each pixel of one video frame
respecting the dimensions of the printing area
Expand Down Expand Up @@ -64,19 +59,43 @@ def convert_frame_pixels_to_ascii(self, frame, dimensions=DEFAULT_TERMINAL_SIZE,
msg += "\r\n"
return msg


def apply_pixel_to_ascii_strategy(self, pixel):
return ipe.pixel_to_ascii(pixel)


def apply_end_line_modifier(self, msg):
return msg

def render(self, cap, output=None, output_format=None, with_audio=False):

def play_audio(self):
"""
Handle and play the video audio

"""
import soundfile as sf
import sounddevice as sd

temp_dir = tempfile.gettempdir()
temp_file_path = temp_dir + "/temp-audiofile-for-vta.wav"
data, samplerate = sf.read(temp_file_path)

with sf.SoundFile(temp_file_path) as f:
data = f.read(dtype='float32')
with sd.Stream(
samplerate=samplerate,
channels=2,
) as stream:
stream.write(data)


def render(self, cap, output=None, with_audio=False):
"""
Iterate each video frame to print a set of ascii chars

This method reads each video frame from a opencv video capture
resizing the frame and truncate the width if necessary to
print correctly the final string built with the method
print correcly the final string builded with the method
convert_frame_pixels_to_ascii.
Finally each final string is printed correctly, if the process
was done too fast will sleep the necessary time to comply
Expand All @@ -94,57 +113,29 @@ def render(self, cap, output=None, output_format=None, with_audio=False):
fps = fps or 30

if with_audio:
import pyaudio
import wave

temp_dir = tempfile.gettempdir()
temp_file_path = temp_dir + "/temp-audiofile-for-vta.wav"
wave_file = wave.open(temp_file_path, 'rb')
chunk = int(wave_file.getframerate() / fps)
p = pyaudio.PyAudio()

stream = p.open(format =
p.get_format_from_width(wave_file.getsampwidth()),
channels = wave_file.getnchannels(),
rate = wave_file.getframerate(),
output = True)

data = wave_file.readframes(chunk)

Thread(target=self.play_audio).start()

if output is not None:
file = open(output, 'w+')

if output_format == 'sh':
file.write("#!/bin/bash \n")
file.write("echo -en '\033[2J' \n")
file.write("echo -en '\u001b[0;0H' \n")
file.write("#!/bin/bash \n")
file.write("echo -en '\033[2J' \n")
file.write("echo -en '\u001b[0;0H' \n")

time_delta = 1./fps
counter=0
if PLATFORM:
sys.stdout.write("echo -en '\033[2J' \n")
else:
sys.stdout.write('\033[2J')
sys.stdout.write("echo -en '\033[2J' \n")
# read each frame


while cap.isOpened():
t0 = time.process_time()
if PLATFORM:
rows, cols = os.popen('stty size', 'r').read().split()
else:
cols, rows = os.get_terminal_size()
rows, cols = os.popen('stty size', 'r').read().split()
_ret, frame = cap.read()
if frame is None:
break
if with_audio:
data = wave_file.readframes(chunk)
stream.write(data)
# sleep if the process was too fast

if output is None:
if PLATFORM:
sys.stdout.write('\u001b[0;0H')
else:
sys.stdout.write("\x1b[0;0H")
sys.stdout.write('\u001b[0;0H')
# scale each frame according to terminal dimensions
resized_frame = self.resize_frame(frame, (cols, rows))
# convert frame pixels to colored string
Expand All @@ -154,45 +145,20 @@ def render(self, cap, output=None, output_format=None, with_audio=False):
if delta > 0:
time.sleep(delta)
sys.stdout.write(msg) # Print the final string

else:
print(self.build_progress(counter, length))
if PLATFORM:
print("\u001b[2A")
else:
print("\x1b[2A")

if output_format == 'sh':
resized_frame = self.resize_frame(frame)
msg = self.convert_frame_pixels_to_ascii(resized_frame, new_line_chars=True)
file.write("sleep 0.033 \n")
file.write("echo -en '" + msg + "'" + "\n" )
file.write("echo -en '\u001b[0;0H' \n")
elif output_format == 'json':
# scale each frame according to terminal dimensions
resized_frame = self.resize_frame(frame, (cols, rows))
msg = self.convert_frame_pixels_to_ascii(resized_frame, (cols, rows), new_line_chars=True)
lines = msg.split("\n")
# remove last line breaks (\n\r) which generate two extra unwanted array elements
lines = lines[0:-2]
# opening brackets
file.write("[[\n" if counter == 0 else ",[\n")
for i in range(len(lines)):
file.write(f"\"{lines[i]}\"")
# closing brackets
file.write("]\n" if i == (len(lines) - 1) else ",\n")

print("\u001b[2A")
resized_frame = self.resize_frame(frame)
msg = self.convert_frame_pixels_to_ascii(resized_frame, new_line_chars=True)
file.write("sleep 0.033 \n")
file.write("echo -en '" + msg + "'" + "\n" )
file.write("echo -en '\u001b[0;0H' \n")

counter += 1
if with_audio:
stream.close()
p.terminate()
if PLATFORM:
sys.stdout.write("echo -en '\033[2J' \n")
else:
os.system('cls') or None
sys.stdout.write("echo -en '\033[2J' \n")


# close the frame array
if output is not None and output_format == 'json':
file.write(f"]\n")

def build_progress(self, progress, total):
"""Build a progress bar in the terminal"""
Expand Down Expand Up @@ -225,3 +191,4 @@ def resize_frame(self, frame, dimensions=DEFAULT_TERMINAL_SIZE):
resized_frame = cv2.resize(frame, dimension, interpolation=cv2.INTER_LINEAR)
return resized_frame