Test the reliability of your favourite source filter

seek-test.py

# Usage:
# python3 seek-test.py file.mkv [start_frame end_frame]
#
# Change the source filter as needed.

# Note: this script is slow because making the source filter decode frames randomly is slow.

import hashlib
import random
import sys

import vapoursynth as vs
from vapoursynth import core


def hash_frame(frame):
    sha256 = hashlib.sha256()
    for plane in range(frame.format.num_planes):
        sha256.update(frame[plane].tobytes())
    return sha256.hexdigest()


clip = core.bs.VideoSource(sys.argv[1], cachesize=0)
# clip = core.d2v.Source(sys.argv[1], rff=False)
# clip = core.dgdecode.MPEG2Source(sys.argv[1])
# clip = core.dgdecodenv.DGSource(sys.argv[1])
# clip = core.ffms2.Source(sys.argv[1])
# clip = core.lsmas.LWLibavSource(sys.argv[1], repeat=0)

if len(sys.argv) == 4:
    start = int(sys.argv[2])
    end = int(sys.argv[3])
    clip = clip.std.Trim(start, end)

print(f"Clip has {clip.num_frames} frames.")

reference = []
for i in range(clip.num_frames):
    reference.append(hash_frame(clip.get_frame(i)))

    if i % 10 == 0:
        print(f"Hashing: {i * 100 // (clip.num_frames - 1)}%", end="\r")

print("\nClip hashed.\n")

test = list(range(clip.num_frames))
random.shuffle(test)

for i in test:
    try:
        result = hash_frame(clip.get_frame(i))
        if result != reference[i]:
            print(f"Requested frame {i}, ", end="")
            try:
                print(f"got frame {reference.index(result)}.")
            except ValueError:
                print(f"got new frame with hash {result}.")

        if test.index(i) % 10 == 0:
            print(f"Seeking: {test.index(i) * 100 // (clip.num_frames - 1)}%", end="\r")
    except vs.Error as e:
        print(f"requesting frame {i} broke source filter. total: {len(test)}")
        raise e

print("Test complete.")