Add manuscript-aligned EasyCom EOT INT review workflow

2026-09-14 16:29:25 +08:00
parent f4a7c01552
commit 7d9db4af58
12 changed files with 3112 additions and 0 deletions
@@ -0,0 +1,134 @@
+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,
+)
+
+
+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,
+                }
+            )
+            + "\n",
+            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"])
+
+    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 = {
+                "protocol_disposition": "positive",
+                "hard_negative_type": "not_applicable",
+                "validity": "valid",
+                "onset_function": "backchannel",
+                "context": "addressed_wearer",
+                "offset_outcome": "not_applicable",
+                "anchor_adjustment_bins": 0,
+                "behavior_adjustment_bins": 0,
+                "region_end_adjustment_bins": None,
+                "confidence": "high",
+                "reviewer": "r1",
+                "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"]["onset_function"],
+                "backchannel",
+            )
+
+    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_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)
+
+
+if __name__ == "__main__":
+    unittest.main()