path: root/packages/meshbay-node/tests/test_stream_video_transcode.py

"""
A video the browser cannot decode is re-encoded to H264, never refused and
never copied. There are two kinds of those, and both are here.

**A codec string that is real but useless.** A real HEVC/EAC3 WEB-DL streamed
fine over MNP (ffprobe/VLC play it) but the browser reported "Codec not
supported for streaming: hev1.1.6.L93.B0,mp4a.40.2" from
MediaSource.isTypeSupported — Chrome has no HEVC decoder on most non-Apple
platforms. "-c:v copy" on such a codec is not a mux failure the way EAC3 audio
is (test_stream_audio_transcode.py); ffmpeg happily remuxes it, and the browser
is the one that then refuses it, silently, at playback rather than at
stream_init. That is what BROWSER_INCOMPATIBLE_VIDEO_CODECS names.

**No codec string at all.** MPEG-4 Part 2 (Xvid, DivX), MPEG-2, VC-1, WMV and
Theora have no MediaSource decoder anywhere, so `probe_video` maps them to
None — there is nothing to put in `stream_init` for the client to check. Until
2026-09-09 the streaming path read that None as "unsupported" and refused, with
"Unsupported video codec", on files ffmpeg re-encodes in real time. Reported
live against an episode rip in a `.avi` — mpeg4 video, mp3 audio, 720x404 —
which the reporting machine re-encodes at about six times playback speed. The setting
that governs it, `transcode_incompatible_video`, was documented from the start
as covering "HEVC *and other browser-incompatible video codecs*" (draft-v6
§2.11); only HEVC was ever wired up.

These tests spawn real ffmpeg/ffprobe against small synthetic files (lavfi
test sources, ~1s), the same style as test_stream_audio_transcode.py.
"""

import shutil
import subprocess
from pathlib import Path

import pytest
from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey

from meshbay_common.crypto import generate_gek
from meshbay_common.webcrypto import chunk_key_aes, decrypt_chunk_aes
from meshbay_node.indexer.group_index import GroupIndex
from meshbay_node.transport.webrtc_server import WebRTCPeerSession, _probe_video

from conftest import needs_subprocess, one_root

_HAVE_FFMPEG = shutil.which("ffmpeg") and shutil.which("ffprobe")
_ENCODERS = subprocess.run(["ffmpeg", "-hide_banner", "-encoders"],
                           capture_output=True).stdout if _HAVE_FFMPEG else b""
# libx265 gates the HEVC cases and only those: an ffmpeg without it still
# encodes MPEG-4 Part 2 (a built-in) and can therefore still prove the half of
# this policy that has no codec string. Marking the whole module on it skipped
# the reported defect on any box without x265.
_HAVE_HEVC_ENCODER = b"libx265" in _ENCODERS
_HAVE_MP3_ENCODER = b"libmp3lame" in _ENCODERS
pytestmark = [
    pytest.mark.asyncio,
    pytest.mark.skipif(not _HAVE_FFMPEG, reason="ffmpeg/ffprobe not installed"),
    needs_subprocess,
]
needs_hevc = pytest.mark.skipif(not _HAVE_HEVC_ENCODER,
                                reason="ffmpeg built without libx265")
needs_mp3 = pytest.mark.skipif(not _HAVE_MP3_ENCODER,
                               reason="ffmpeg built without libmp3lame")


def _make_mpeg4_clip(path: Path) -> None:
    """~1s of Xvid-style MPEG-4 Part 2 video + MP3 audio in an AVI.

    The same shape as the reported file, down to the container: ffprobe reports
    `codec_name: mpeg4`, which is what an Xvid encoder produces and what
    `probe_video` has no MSE string for.
    """
    subprocess.run(
        ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y",
         "-f", "lavfi", "-i", "testsrc=size=320x240:rate=25:duration=1",
         "-f", "lavfi", "-i", "sine=frequency=440:duration=1:sample_rate=48000",
         "-c:v", "mpeg4", "-c:a", "libmp3lame",
         str(path)],
        check=True, capture_output=True,
    )


def _make_hevc_clip(path: Path) -> None:
    """~1s of HEVC video + AAC audio — a minimal stand-in for a real HEVC WEB-DL."""
    subprocess.run(
        ["ffmpeg", "-hide_banner", "-loglevel", "error", "-y",
         "-f", "lavfi", "-i", "testsrc=size=320x240:rate=25:duration=1",
         "-f", "lavfi", "-i", "sine=frequency=440:duration=1:sample_rate=48000",
         "-c:v", "libx265", "-preset", "ultrafast", "-c:a", "aac",
         str(path)],
        check=True, capture_output=True,
    )


def _session(video_path: Path, gek: bytes, *, transcode_incompatible_video: bool = True):
    import blake3
    file_bytes = video_path.read_bytes()
    file_id = blake3.blake3(file_bytes).hexdigest()

    sk_node = Ed25519PrivateKey.generate()
    index = GroupIndex(group_id="g" * 32, sk_node=sk_node, gek=gek)
    from meshbay_common.protocol import IndexEntry
    index.add_entry(IndexEntry(
        id=file_id, name=video_path.name, path=video_path.parent.name,
        size=len(file_bytes), type="video", added_at=0))

    session = WebRTCPeerSession.__new__(WebRTCPeerSession)
    session._ctx = {
        "roots": one_root(video_path.parent),
        "index": index,
        "gek": gek,
        "sk_node": sk_node,
        "max_concurrent_streams": 4,
        "transcode_incompatible_video": transcode_incompatible_video,
    }
    session._group_id = None
    session._user_id = "tester"
    session._stream_stopped = False
    session._stream_keepalives = 0
    session.sent = []
    session._send = session.sent.append
    session._audit = lambda *a, **k: None
    return session, file_id


def _reassemble(sent: list[dict], gek: bytes, file_id: str) -> bytes:
    file_hash = bytes.fromhex(file_id)
    segments = sorted(
        (m for m in sent if m.get("type") == "stream_data"),
        key=lambda m: m["segment_index"])
    out = b""
    for m in segments:
        key = chunk_key_aes(gek, file_hash, m["segment_index"])
        out += decrypt_chunk_aes(key, m["nonce"], m["ct"])
    return out


def _output_video_codec(path: Path) -> str:
    probe = subprocess.run(
        ["ffprobe", "-v", "error", "-select_streams", "v:0",
         "-show_entries", "stream=codec_name", "-of", "csv=p=0", str(path)],
        check=True, capture_output=True, text=True)
    return probe.stdout.strip()


@needs_hevc
async def test_hevc_video_is_transcoded_to_h264_by_default(tmp_path):
    clip = tmp_path / "clip.mkv"
    _make_hevc_clip(clip)
    gek = generate_gek()
    session, file_id = _session(clip, gek)

    await session._stream_video_inner({"file_id": file_id, "start": 0, "credits": 0})

    errors = [m for m in session.sent if m.get("type") == "error"]
    assert not errors, f"streaming must not fail: {errors}"

    init = next(m for m in session.sent if m.get("type") == "stream_init")
    assert init["codec"].startswith("avc1."), (
        "the reported codec must be the transcoded H264 string, never the "
        f"source's hev1 string a browser cannot decode: {init['codec']}")

    remuxed = _reassemble(session.sent, gek, file_id)
    out_path = tmp_path / "out.mp4"
    out_path.write_bytes(remuxed)
    assert _output_video_codec(out_path) == "h264", \
        "the bytes on the wire must actually be H264, not just the reported label"


@needs_hevc
async def test_hevc_transcode_can_be_disabled_by_the_operator(tmp_path):
    clip = tmp_path / "clip.mkv"
    _make_hevc_clip(clip)
    gek = generate_gek()
    session, file_id = _session(clip, gek, transcode_incompatible_video=False)

    await session._stream_video_inner({"file_id": file_id, "start": 0, "credits": 0})

    assert not [m for m in session.sent if m.get("type") == "error"]
    init = next(m for m in session.sent if m.get("type") == "stream_init")
    assert init["codec"].startswith("hev1."), (
        "with the fallback disabled, the source is copied as-is and the "
        f"original HEVC codec string must be reported unchanged: {init['codec']}")

    remuxed = _reassemble(session.sent, gek, file_id)
    out_path = tmp_path / "out.mp4"
    out_path.write_bytes(remuxed)
    assert _output_video_codec(out_path) == "hevc", \
        "with the fallback disabled, the wire bytes must still be copied HEVC"


@needs_hevc
async def test_probe_video_reports_raw_codec_name_for_hevc(tmp_path):
    clip = tmp_path / "clip.mkv"
    _make_hevc_clip(clip)

    probe = await _probe_video(str(clip))

    assert probe.raw_codec_name == "hevc"
    assert probe.codec is not None and probe.codec.startswith("hev1.")


@needs_mp3
async def test_probe_video_reports_no_codec_string_for_mpeg4(tmp_path):
    """The other shape, and the reason the streaming path has to read it as
    "re-encode this" rather than as a verdict on the file: there is no MSE
    string for MPEG-4 Part 2 because no browser has a decoder to give one to.
    The raw name is still reported, which is what the caller decides on."""
    clip = tmp_path / "clip.avi"
    _make_mpeg4_clip(clip)

    probe = await _probe_video(str(clip))

    assert probe.raw_codec_name == "mpeg4"
    assert probe.codec is None, (
        "a codec string for MPEG-4 Part 2 would be one no browser can act on")
    assert probe.has_audio is True
    assert (probe.width, probe.height) == (320, 240)


@needs_mp3
async def test_a_codec_with_no_mse_string_is_transcoded_not_refused(tmp_path):
    """The reported defect.

    An Xvid/MP3 .avi answered "Unsupported video codec" — a refusal, on a file
    ffmpeg re-encodes faster than it plays. Nothing about the source changed;
    the node simply never reached its own re-encode path.
    """
    clip = tmp_path / "clip.avi"
    _make_mpeg4_clip(clip)
    gek = generate_gek()
    session, file_id = _session(clip, gek)

    await session._stream_video_inner({"file_id": file_id, "start": 0, "credits": 0})

    errors = [m for m in session.sent if m.get("type") == "error"]
    assert not errors, (
        f"a source with no MSE codec string was refused instead of re-encoded: "
        f"{errors}")

    init = next(m for m in session.sent if m.get("type") == "stream_init")
    assert init["codec"].startswith("avc1."), (
        "stream_init must advertise the H264 the client is about to receive; "
        f"there is no string for the source and none may be invented: {init['codec']}")

    remuxed = _reassemble(session.sent, gek, file_id)
    out_path = tmp_path / "out.mp4"
    out_path.write_bytes(remuxed)
    assert _output_video_codec(out_path) == "h264", (
        "the bytes on the wire must actually be H264, not just the label")


@needs_mp3
async def test_the_operator_can_refuse_the_re_encode_and_says_so(tmp_path):
    """`transcode_incompatible_video = false` still means what it says.

    HEVC falls back to a copy there (the case above), because there is a codec
    string to report. Here there is none, so a copy is not a lesser answer —
    it is a stream_init the client refuses before the first byte. The refusal
    has to name the setting: "Unsupported video codec" is what sent the last
    reader to look at a file that was fine.
    """
    clip = tmp_path / "clip.avi"
    _make_mpeg4_clip(clip)
    gek = generate_gek()
    session, file_id = _session(clip, gek, transcode_incompatible_video=False)

    await session._stream_video_inner({"file_id": file_id, "start": 0, "credits": 0})

    errors = [m for m in session.sent if m.get("type") == "error"]
    assert errors, "a stream that cannot be produced must be refused, not started"
    detail = errors[0]["detail"]
    assert "transcoding" in detail, (
        f"the refusal must point at the setting that caused it: {detail!r}")
    assert not [m for m in session.sent if m.get("type") == "stream_init"], (
        "a stream_init went out with no codec string the client could check")