349 lines
15 KiB
Python
349 lines
15 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
import tempfile
|
|
import unittest
|
|
|
|
from review_floor_events import (
|
|
CandidateRepository,
|
|
ReviewStore,
|
|
expand_candidate_paths,
|
|
load_candidates,
|
|
parse_byte_range,
|
|
stream_file_range,
|
|
)
|
|
|
|
|
|
class FloorEventReviewTests(unittest.TestCase):
|
|
def _fixture(self, root: Path) -> tuple[Path, Path]:
|
|
dataset = root / "dataset"
|
|
video_dir = dataset / "Main" / "Video_Compressed" / "Session_4"
|
|
transcript_dir = dataset / "Main" / "Speech_Transcriptions" / "Session_4"
|
|
video_dir.mkdir(parents=True)
|
|
transcript_dir.mkdir(parents=True)
|
|
(video_dir / "00-00-000.mp4").write_bytes(b"mock-video")
|
|
(transcript_dir / "00-00-000.json").write_text(
|
|
json.dumps(
|
|
[
|
|
{
|
|
"Start_Frame": 1,
|
|
"End_Frame": 20,
|
|
"Participant_ID": 4,
|
|
"Transcription": "Are you coming?",
|
|
"Target_of_Speech": [2],
|
|
},
|
|
{
|
|
"Start_Frame": 25,
|
|
"End_Frame": 40,
|
|
"Participant_ID": 2,
|
|
"Transcription": "Yes.",
|
|
"Target_of_Speech": [4],
|
|
},
|
|
]
|
|
),
|
|
encoding="utf-8",
|
|
)
|
|
events = root / "candidates.jsonl"
|
|
events.write_text(
|
|
json.dumps(
|
|
{
|
|
"uid": "Session_4/00-00-000/0001",
|
|
"session": "Session_4",
|
|
"split": "train",
|
|
"event_type": "ordinary_switch",
|
|
"confidence": "timing",
|
|
"participant_role": "wearer",
|
|
"clip_stem": "00-00-000",
|
|
"source_start_frame": 25,
|
|
"dense_start_seconds": 1.2,
|
|
"event_time": 1.2,
|
|
"candidate_source": "WEARER_ONSET",
|
|
"task": "wearer_entry",
|
|
"ai_verdict": "POSITIVE",
|
|
"ai_event_type": "WEARER_ENTRY",
|
|
"ai_subtype": None,
|
|
"speaker_timeline": [
|
|
{
|
|
"uid": "Session_4/00-00-000/0001",
|
|
"participant_id": 2,
|
|
"participant_role": "wearer",
|
|
"start_seconds": 1.2,
|
|
"end_seconds": 2.0,
|
|
"transcription": "Yes.",
|
|
}
|
|
],
|
|
}
|
|
)
|
|
+ "\n",
|
|
encoding="utf-8",
|
|
)
|
|
(root / "easycom_session_timelines.json").write_text(
|
|
json.dumps({"schema_version": 1, "sessions": {"Session_4": [
|
|
{"participant_id": 4, "participant_role": "other", "start_seconds": 0.0, "end_seconds": 1.0},
|
|
{"participant_id": 2, "participant_role": "wearer", "start_seconds": 1.2, "end_seconds": 2.0},
|
|
]}}),
|
|
encoding="utf-8",
|
|
)
|
|
return dataset, events
|
|
|
|
def test_candidate_detail_resolves_media_and_transcript(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
dataset, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
repository = CandidateRepository(
|
|
candidates,
|
|
dataset,
|
|
context_before_seconds=3.0,
|
|
context_after_seconds=3.0,
|
|
)
|
|
detail = repository.detail(candidates[0])
|
|
self.assertTrue(detail["media_available"])
|
|
self.assertEqual(detail["event_local_seconds"], 1.2)
|
|
self.assertEqual(len(detail["transcript"]), 2)
|
|
self.assertTrue(detail["transcript"][1]["is_anchor"])
|
|
self.assertEqual(detail["transcript"][1]["participant_role"], "wearer")
|
|
self.assertEqual(detail["transcript"][1]["uid"], "Session_4/00-00-000/0001")
|
|
self.assertEqual(len(repository.session_timelines["Session_4"]), 2)
|
|
|
|
def test_review_store_writes_resumable_jsonl_and_csv(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
output = root / "reviews" / "reviews.jsonl"
|
|
store = ReviewStore(output, candidates)
|
|
review = {
|
|
"human_action": "accept",
|
|
"human_verdict": None,
|
|
"human_event_type": None,
|
|
"human_subtype": None,
|
|
"exclude_reason": None,
|
|
"boundary_correction_seconds": None,
|
|
"confidence": "high",
|
|
"notes": "clear acknowledgement",
|
|
}
|
|
store.save(candidates[0].candidate_id, review)
|
|
self.assertTrue(output.is_file())
|
|
self.assertTrue(output.with_suffix(".csv").is_file())
|
|
resumed = ReviewStore(output, candidates)
|
|
self.assertEqual(
|
|
resumed.reviews[candidates[0].candidate_id]["review"]["human_event_type"],
|
|
"WEARER_ENTRY",
|
|
)
|
|
self.assertFalse(resumed.reviews[candidates[0].candidate_id]["review"]["relabeled"])
|
|
self.assertEqual(resumed.reviews[candidates[0].candidate_id]["review"]["reviewer"], "")
|
|
|
|
def test_directory_expansion_excludes_output(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
candidate = root / "Session_4.events.jsonl"
|
|
output = root / "reviews.jsonl"
|
|
candidate.write_text("{}\n", encoding="utf-8")
|
|
output.write_text("{}\n", encoding="utf-8")
|
|
self.assertEqual(
|
|
expand_candidate_paths([root], output_path=output),
|
|
[candidate.resolve()],
|
|
)
|
|
|
|
def test_primary_queue_keeps_nonoverlap_wearer_offset_for_semantics(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
path = Path(temporary) / "legacy.jsonl"
|
|
rows = [
|
|
{
|
|
"uid": "Session_4/wearer_offset/00000285",
|
|
"candidate_source": "WEARER_OFFSET",
|
|
"task": "int_yield",
|
|
"temporal_evidence": {
|
|
"active_other_ids_before_offset": [],
|
|
"active_other_ids_after_offset": [],
|
|
},
|
|
},
|
|
{
|
|
"uid": "Session_4/wearer_onset/00000338",
|
|
"candidate_source": "WEARER_ONSET",
|
|
"task": "wearer_entry",
|
|
},
|
|
]
|
|
path.write_text(
|
|
"".join(json.dumps(row) + "\n" for row in rows), encoding="utf-8"
|
|
)
|
|
primary = load_candidates([path])
|
|
all_rows = load_candidates([path], include_offset_controls=True)
|
|
self.assertEqual([row.uid for row in primary], [row["uid"] for row in rows])
|
|
self.assertEqual(len(all_rows), 2)
|
|
|
|
def test_relabel_preserves_ai_and_records_human_decision(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
store = ReviewStore(root / "reviews.jsonl", candidates)
|
|
record = store.save(candidates[0].candidate_id, {
|
|
"human_action": "relabel",
|
|
"human_verdict": "HARD_NEGATIVE",
|
|
"human_event_type": None,
|
|
"human_subtype": "ENTRY_WEARER_BACKCHANNEL",
|
|
"exclude_reason": None,
|
|
"boundary_correction_seconds": None,
|
|
"confidence": "medium",
|
|
"reviewer": "r2",
|
|
"notes": "brief acknowledgement",
|
|
})
|
|
self.assertEqual(record["ai_event_type"], "WEARER_ENTRY")
|
|
self.assertEqual(record["review"]["human_subtype"], "ENTRY_WEARER_BACKCHANNEL")
|
|
self.assertTrue(record["review"]["relabeled"])
|
|
|
|
def test_removed_verdicts_cannot_be_accepted_or_reintroduced(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
candidate = candidates[0]
|
|
store = ReviewStore(root / "reviews.jsonl", candidates)
|
|
base = {
|
|
"human_event_type": None, "human_subtype": None,
|
|
"selected_opportunity_uid": None, "exclude_reason": None,
|
|
"boundary_correction_seconds": None, "confidence": "medium",
|
|
"notes": "legacy fallback",
|
|
}
|
|
for verdict in ("UNSURE", "NOT_APPLICABLE"):
|
|
with self.subTest(action="relabel", verdict=verdict), self.assertRaisesRegex(
|
|
ValueError, "Invalid human_verdict"
|
|
):
|
|
store.save(candidate.candidate_id, {
|
|
**base, "human_action": "relabel", "human_verdict": verdict,
|
|
})
|
|
|
|
candidate.payload["ai_verdict"] = verdict
|
|
with self.subTest(action="accept", verdict=verdict), self.assertRaisesRegex(
|
|
ValueError, "Accept requires an AI pre-label"
|
|
):
|
|
store.save(candidate.candidate_id, {
|
|
**base, "human_action": "accept", "human_verdict": None,
|
|
})
|
|
|
|
candidate.payload["ai_verdict"] = "POSITIVE"
|
|
|
|
def test_relabel_subtype_must_match_candidate_family(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
store = ReviewStore(root / "reviews.jsonl", candidates)
|
|
with self.assertRaisesRegex(ValueError, "ENTRY candidate requires ENTRY_"):
|
|
store.save(candidates[0].candidate_id, {
|
|
"human_action": "relabel", "human_verdict": "HARD_NEGATIVE",
|
|
"human_event_type": None, "human_subtype": "INT_OTHER_BACKCHANNEL",
|
|
"selected_opportunity_uid": None, "exclude_reason": None,
|
|
"boundary_correction_seconds": None, "confidence": "medium",
|
|
"notes": "wrong family",
|
|
})
|
|
|
|
def test_normal_completion_can_be_excluded_as_out_of_scope(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
store = ReviewStore(root / "reviews.jsonl", candidates)
|
|
record = store.save(candidates[0].candidate_id, {
|
|
"human_action": "exclude", "human_verdict": None,
|
|
"human_event_type": None, "human_subtype": None,
|
|
"selected_opportunity_uid": None,
|
|
"exclude_reason": "OUT_OF_SCOPE_NORMAL_COMPLETION",
|
|
"boundary_correction_seconds": None, "confidence": "high",
|
|
"notes": "wearer completed; laughter did not take over",
|
|
})
|
|
self.assertEqual(record["review"]["human_verdict"], "EXCLUDE")
|
|
self.assertEqual(
|
|
record["review"]["exclude_reason"], "OUT_OF_SCOPE_NORMAL_COMPLETION"
|
|
)
|
|
self.assertEqual(record["review"]["exclude_reason_group"], "OUT_OF_SCOPE")
|
|
|
|
def test_accept_ai_exclude_preserves_reason_taxonomy(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
candidate = candidates[0]
|
|
candidate.payload.update(
|
|
ai_verdict="EXCLUDE",
|
|
ai_event_type=None,
|
|
ai_subtype=None,
|
|
ai_exclude_reason="DATA_MISSING_CONTEXT",
|
|
ai_exclude_reason_group="DATA_QUALITY",
|
|
llm_suggestion={
|
|
"verdict": "EXCLUDE",
|
|
"event_type": None,
|
|
"subtype": None,
|
|
"exclude_reason": "DATA_MISSING_CONTEXT",
|
|
},
|
|
)
|
|
store = ReviewStore(root / "reviews.jsonl", candidates)
|
|
record = store.save(candidate.candidate_id, {
|
|
"human_action": "accept", "human_verdict": None,
|
|
"human_event_type": None, "human_subtype": None,
|
|
"selected_opportunity_uid": None, "exclude_reason": None,
|
|
"boundary_correction_seconds": None, "confidence": "medium",
|
|
"notes": "context is truncated",
|
|
})
|
|
self.assertEqual(record["review"]["exclude_reason"], "DATA_MISSING_CONTEXT")
|
|
self.assertEqual(record["review"]["exclude_reason_group"], "DATA_QUALITY")
|
|
|
|
def test_entry_review_may_select_only_a_supplied_opportunity_anchor(self) -> None:
|
|
with tempfile.TemporaryDirectory() as temporary:
|
|
root = Path(temporary)
|
|
_, events = self._fixture(root)
|
|
candidates = load_candidates([events])
|
|
candidate = candidates[0]
|
|
candidate.payload["temporal_evidence"] = {
|
|
"opportunity_options": [
|
|
{"uid": "release-1", "anchor_seconds": 1.0, "participant_id": 4}
|
|
]
|
|
}
|
|
store = ReviewStore(root / "reviews.jsonl", candidates)
|
|
base = {
|
|
"human_action": "relabel", "human_verdict": "POSITIVE",
|
|
"human_event_type": "WEARER_ENTRY", "human_subtype": None,
|
|
"exclude_reason": None, "boundary_correction_seconds": None,
|
|
"confidence": "high", "notes": "clear response",
|
|
}
|
|
record = store.save(
|
|
candidate.candidate_id, {**base, "selected_opportunity_uid": "release-1"}
|
|
)
|
|
self.assertEqual(record["review"]["selected_opportunity_uid"], "release-1")
|
|
self.assertEqual(
|
|
record["review"]["valid_prediction_interval_seconds"], [1.0, 1.2]
|
|
)
|
|
with self.assertRaisesRegex(ValueError, "only a supplied"):
|
|
store.save(
|
|
candidate.candidate_id,
|
|
{**base, "selected_opportunity_uid": "invented"},
|
|
)
|
|
optional = store.save(
|
|
candidate.candidate_id, {**base, "selected_opportunity_uid": None}
|
|
)
|
|
self.assertIsNone(optional["review"]["selected_opportunity_uid"])
|
|
|
|
def test_byte_ranges(self) -> None:
|
|
self.assertEqual(parse_byte_range("bytes=2-5", 10), (2, 5))
|
|
self.assertEqual(parse_byte_range("bytes=7-", 10), (7, 9))
|
|
self.assertEqual(parse_byte_range("bytes=-3", 10), (7, 9))
|
|
with self.assertRaises(ValueError):
|
|
parse_byte_range("bytes=20-30", 10)
|
|
|
|
def test_cancelled_media_stream_is_not_an_error(self) -> None:
|
|
class Reader:
|
|
def read(self, _: int) -> bytes:
|
|
return b"video"
|
|
|
|
def disconnected(_: bytes) -> None:
|
|
raise BrokenPipeError(32, "Broken pipe")
|
|
|
|
self.assertFalse(stream_file_range(Reader(), disconnected, 5))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|