JMR-devandClaude Sonnet 5
b23995f218
The distribution, console script and import package are now audio-scribe / audio_scribe (src/audio_scribe). Everything named for the old project follows: - CcnError -> AudioScribeError, and its code "ccn_error" -> "audio_scribe_error" (the code is never persisted, so existing job state still loads) - CCN_LIVE -> AUDIO_SCRIBE_LIVE for the live-GPU tests - OpenVINO kernel cache moves to <cache>/audio-scribe/ov_cache; the first run after upgrading recompiles kernels, and the old directory is left in place - README, build-binary.sh, hatch/coverage config and uv.lock updated to match Breaking: the command is now `audio-scribe`; reinstall any tool install of the old name with `uv tool uninstall ccn-transcribe && uv tool install .`. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
131 lines
4.7 KiB
Python
131 lines
4.7 KiB
Python
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from audio_scribe.jobs.plan import Stage, Verdicts, plan_stages
|
|
from audio_scribe.jobs.verify import Verdict
|
|
|
|
OK = Verdict.OK
|
|
GONE = Verdict.SATISFIED_ABSENT
|
|
MISS = Verdict.MISSING
|
|
PART = Verdict.PARTIAL
|
|
BAD = Verdict.CORRUPT
|
|
|
|
|
|
def plan(video: Verdict, audio: Verdict, outputs: Verdict, **kw: object) -> tuple[Stage, ...]:
|
|
return plan_stages(Verdicts(video=video, audio=audio, outputs=outputs), **kw) # type: ignore[arg-type]
|
|
|
|
|
|
class TestNothingToDo:
|
|
def test_everything_present_is_a_no_op(self) -> None:
|
|
assert plan(OK, OK, OK) == ()
|
|
|
|
def test_media_deleted_by_policy_is_still_a_no_op(self) -> None:
|
|
# The whole point of --no-retain: done is done, do not re-fetch.
|
|
assert plan(GONE, GONE, OK) == ()
|
|
|
|
|
|
class TestEntryPoint:
|
|
def test_missing_outputs_with_good_audio_skips_download(self) -> None:
|
|
assert plan(OK, OK, MISS) == (Stage.TRANSCRIBE, Stage.OUTPUTS)
|
|
|
|
def test_policy_deleted_video_does_not_trigger_a_download(self) -> None:
|
|
assert plan(GONE, OK, MISS) == (Stage.TRANSCRIBE, Stage.OUTPUTS)
|
|
|
|
def test_missing_audio_with_good_video_extracts_only(self) -> None:
|
|
assert plan(OK, MISS, MISS) == (Stage.AUDIO, Stage.TRANSCRIBE, Stage.OUTPUTS)
|
|
|
|
def test_nothing_present_runs_everything(self) -> None:
|
|
assert plan(MISS, MISS, MISS) == (
|
|
Stage.DOWNLOAD,
|
|
Stage.AUDIO,
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
def test_a_partial_download_still_enters_at_download(self) -> None:
|
|
assert plan(PART, MISS, MISS)[0] is Stage.DOWNLOAD
|
|
|
|
def test_a_corrupt_video_is_re_downloaded(self) -> None:
|
|
assert plan(BAD, MISS, MISS)[0] is Stage.DOWNLOAD
|
|
|
|
def test_a_corrupt_audio_is_re_extracted(self) -> None:
|
|
assert plan(OK, BAD, MISS) == (Stage.AUDIO, Stage.TRANSCRIBE, Stage.OUTPUTS)
|
|
|
|
|
|
class TestSegmentReuse:
|
|
def test_outputs_alone_are_re_rendered_when_segments_survive(self) -> None:
|
|
# Deleting transcript.srt should not cost a re-transcription of a
|
|
# two-hour lecture when transcript.json still holds the segments.
|
|
assert plan(OK, OK, MISS, segments_available=True) == (Stage.OUTPUTS,)
|
|
|
|
def test_policy_deleted_audio_is_fine_when_segments_survive(self) -> None:
|
|
assert plan(GONE, GONE, MISS, segments_available=True) == (Stage.OUTPUTS,)
|
|
|
|
def test_changed_params_ignore_saved_segments(self) -> None:
|
|
assert Stage.TRANSCRIBE in plan(OK, OK, MISS, segments_available=True, params_changed=True)
|
|
|
|
|
|
class TestParamsChanged:
|
|
def test_a_new_language_forces_a_re_transcription(self) -> None:
|
|
assert plan(OK, OK, OK, params_changed=True) == (Stage.TRANSCRIBE, Stage.OUTPUTS)
|
|
|
|
def test_it_re_extracts_audio_that_was_policy_deleted(self) -> None:
|
|
assert plan(OK, GONE, OK, params_changed=True) == (
|
|
Stage.AUDIO,
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
def test_it_re_downloads_when_both_were_policy_deleted(self) -> None:
|
|
# A stage that is re-running is NOT satisfied by a policy deletion.
|
|
assert plan(GONE, GONE, OK, params_changed=True) == (
|
|
Stage.DOWNLOAD,
|
|
Stage.AUDIO,
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
|
|
class TestForce:
|
|
def test_forcing_transcribe_reruns_it(self) -> None:
|
|
assert plan(OK, OK, OK, force=frozenset({Stage.TRANSCRIBE})) == (
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
def test_forcing_transcribe_walks_back_past_policy_deletions(self) -> None:
|
|
assert plan(GONE, GONE, OK, force=frozenset({Stage.TRANSCRIBE})) == (
|
|
Stage.DOWNLOAD,
|
|
Stage.AUDIO,
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
def test_forcing_download_reruns_the_whole_pipeline(self) -> None:
|
|
assert plan(OK, OK, OK, force=frozenset({Stage.DOWNLOAD})) == (
|
|
Stage.DOWNLOAD,
|
|
Stage.AUDIO,
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
def test_forcing_audio_keeps_the_existing_download(self) -> None:
|
|
assert plan(OK, OK, OK, force=frozenset({Stage.AUDIO})) == (
|
|
Stage.AUDIO,
|
|
Stage.TRANSCRIBE,
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
def test_forcing_outputs_only_re_renders(self) -> None:
|
|
assert plan(OK, OK, OK, force=frozenset({Stage.OUTPUTS}), segments_available=True) == (
|
|
Stage.OUTPUTS,
|
|
)
|
|
|
|
|
|
class TestStageOrder:
|
|
@pytest.mark.parametrize("segments", [True, False])
|
|
def test_stages_always_come_out_in_pipeline_order(self, segments: bool) -> None:
|
|
got = plan(MISS, MISS, MISS, segments_available=segments)
|
|
assert list(got) == sorted(got, key=list(Stage).index)
|