gnommo/tests/test_chunking_v2.py

#!/usr/bin/env python3
"""Plan-level validation for chunking v2 (docs/chunking_v2.md).

Verifies the transformer now INCLUDES clips that span a chunk boundary and seeks
into them (skip_override / src_offset), instead of the v1 behaviour that dropped
them. This is a pure plan-level check — the ffmpeg concat-seam (frame alignment via
-c copy) still needs a real render on the rig to confirm.

Run:  ./venv/bin/python tests/test_chunking_v2.py
"""
import sys
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

from gnommo.transformer import (
    MarkerTiming,
    _extract_audio_events,
    _extract_video_events,
    AUDIO_OFFSET_SECONDS,
)
from gnommo.models import AudioDefinition, VideoSource, CutoutDefinition, SlideDefinition

_fails = []


def check(name, cond, detail=""):
    print(f"  {'PASS' if cond else 'FAIL'}  {name}" + (f"  — {detail}" if detail and not cond else ""))
    if not cond:
        _fails.append(name)


# ── audio ────────────────────────────────────────────────────────────────────
def test_audio():
    print("audio events:")
    audio = {
        "music": AudioDefinition(file="music.mp3", loop=True, duration=90.0),
        "sfx": AudioDefinition(file="sfx.wav", loop=False, duration=500.0),
        "blip": AudioDefinition(file="blip.wav", loop=False, duration=50.0),
    }
    # music triggers at t=0, sfx at t=10, blip at t=10
    markers = [
        MarkerTiming(marker_id="Amusic", timestamp=0.0, context="", confidence=1.0),
        MarkerTiming(marker_id="Asfx", timestamp=10.0, context="", confidence=1.0),
        MarkerTiming(marker_id="Ablip", timestamp=10.0, context="", confidence=1.0),
    ]

    # Chunk window [300, 600): all three started earlier.
    evs = {e.audio_id: e for e in _extract_audio_events(markers, audio, time_range=(300.0, 600.0))}

    # Looping music: included, resumes at loop phase. astart = max(0, 0-1)=0; into=300;
    # phase = 300 % 90 = 30.
    check("looping music spanning boundary is INCLUDED (v1 dropped it)", "music" in evs)
    if "music" in evs:
        m = evs["music"]
        check("music clamped to window start", abs(m.start_time - 300.0) < 1e-6, f"start={m.start_time}")
        check("music seeks to loop phase 30.0", abs(m.src_offset - 30.0) < 1e-6, f"src_offset={m.src_offset}")

    # One-shot still playing at the window: included, linear seek.
    # astart = max(0,10-1)=9; aend=9+500=509 > 300 → spans. into=300-9=291.
    check("one-shot still playing is INCLUDED", "sfx" in evs)
    if "sfx" in evs:
        s = evs["sfx"]
        check("sfx linear seek 291.0", abs(s.src_offset - 291.0) < 1e-6, f"src_offset={s.src_offset}")

    # One-shot that ended before the window: excluded (aend=9+50=59 < 300).
    check("one-shot ended before window is EXCLUDED", "blip" not in evs)

    # Full render (no range): everything from the start, no seek.
    full = {e.audio_id: e for e in _extract_audio_events(markers, audio, time_range=None)}
    check("full render includes music with no seek", "music" in full and full["music"].src_offset == 0.0)


# ── video ────────────────────────────────────────────────────────────────────
def test_video():
    print("video events:")
    cutouts = {"fullscreen": CutoutDefinition(x=0, y=0, height=1080, width=1920)}
    videos = {
        "bg": VideoSource(
            source_file="bg.mp4", cutout="fullscreen", layer="below",
            duration=90.0, skip=0.0, end_on="next_video",
        )
    }
    slides = {f"S{i}": SlideDefinition(image=f"S{i}.png", type="slide") for i in range(1, 11)}
    markers = [MarkerTiming(marker_id=f"S{i}", timestamp=(i - 1) * 60.0, context="", confidence=1.0)
               for i in range(1, 11)]
    # Background overlay starts at slide-7 time (360) and, as the only video with
    # end_on next_video, runs to total_duration (600).
    markers.append(MarkerTiming(marker_id="vfm:bg", timestamp=360.0, context="", confidence=1.0))

    total = 600.0
    # Chunk window that STARTS AFTER the video began: [420, 600) (slides 8-10).
    evs, _ = _extract_video_events(markers, videos, cutouts, slides, total, time_range=(420.0, 600.0))
    bg = next((e for e in evs if e.video_id == "bg"), None)

    check("spanning background video is INCLUDED in the later chunk (v1 dropped it)", bg is not None)
    if bg is not None:
        check("bg clamped to window start", abs(bg.start_time - 420.0) < 1e-6, f"start={bg.start_time}")
        # into = 420-360 = 60; playable = 90-0 = 90; 60 < 90 → linear seek 60.
        check("bg linear seek 60.0 (first play-through)", abs((bg.skip_override or 0) - 60.0) < 1e-6,
              f"skip_override={bg.skip_override}")

    # Window starting deep enough that the 90s clip has looped once: [480, 600).
    # into = 480-360 = 120; 120 >= 90 → phase = 120 % 90 = 30.
    evs2, _ = _extract_video_events(markers, videos, cutouts, slides, total, time_range=(480.0, 600.0))
    bg2 = next((e for e in evs2 if e.video_id == "bg"), None)
    check("looped background resumes at phase 30.0", bg2 is not None and abs((bg2.skip_override or 0) - 30.0) < 1e-6,
          f"skip_override={getattr(bg2, 'skip_override', None)}")

    # Full render: no seek.
    evs3, _ = _extract_video_events(markers, videos, cutouts, slides, total, time_range=None)
    bg3 = next((e for e in evs3 if e.video_id == "bg"), None)
    check("full render includes bg with no seek", bg3 is not None and bg3.skip_override is None)


if __name__ == "__main__":
    test_audio()
    test_video()
    print()
    if _fails:
        print(f"FAILED: {len(_fails)} check(s): {', '.join(_fails)}")
        sys.exit(1)
    print("All chunking-v2 plan-level checks passed.")