serve_l2_dashboard.py
51.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
#!/usr/bin/env python3
"""Local server for the L2 lyric review dashboard."""
from __future__ import annotations
import argparse
import csv
import json
import mimetypes
import os
import subprocess
import sys
import time
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from urllib.parse import parse_qs, unquote, urlparse
import pymysql
import requests
from dotenv import load_dotenv
ROOT = Path(__file__).resolve().parent
REPORT_DIR = ROOT / "output" / "reports"
DASHBOARD = ROOT / "l2_review_dashboard.html"
REPORT_DIR.mkdir(parents=True, exist_ok=True)
GROUP_INDEX_CACHE: dict[tuple[str, int, int, str], list[dict[str, object]]] = {}
load_dotenv(ROOT / ".env")
REVIEW_CLAIM_TTL_SECONDS = max(60, int(os.getenv("REVIEW_CLAIM_TTL_SECONDS", "600")))
TARGET_DB_CONFIG = {
"host": os.getenv("TARGET_DB_HOST"),
"port": int(os.getenv("TARGET_DB_PORT", 3306)),
"user": os.getenv("TARGET_DB_USER"),
"password": os.getenv("TARGET_DB_PASSWORD"),
"database": os.getenv("TARGET_DB_NAME"),
"charset": "utf8mb4",
"cursorclass": pymysql.cursors.DictCursor,
}
TARGET_TABLE_NAME = os.getenv("TARGET_TABLE_NAME", "hk_songs")
TARGET_TABLE_NAME_TMP = os.getenv("TARGET_TABLE_NAME_TMP", f"{TARGET_TABLE_NAME}_import_staging")
STAGING_DB_PATH = "__staging_db__"
TARGET_COLUMNS = [
"id", "name", "lyricist", "composer", "issue_status", "intro",
"audio_url", "accompany_url", "lyrics_url", "lrc_url",
"song_time", "song_start", "song_end",
"creation_url", "opern_url", "cover_version", "issue_time",
"cover_url", "animation_type", "bpm_class", "review_status",
"in_status", "song_status", "commit_time", "review_time",
"shelf_time", "review_remark", "create_time", "creator",
"modify_time", "modifier", "deleted", "cooperate_type", "singer",
"off_shelf_remark", "musician_id", "commit_id", "sheet_music",
"commit_desc", "price", "source_table_name", "source_song_id",
"lyric_archive_element_id", "melody_archive_element_id", "audio_fingerprint",
]
REVIEW_SCHEMA_COLUMNS = {
"review_claimed_by": "varchar(64) DEFAULT NULL COMMENT '当前领取审核人'",
"review_claim_token": "varchar(64) DEFAULT NULL COMMENT '领取会话凭证'",
"review_claimed_at": "datetime DEFAULT NULL COMMENT '领取时间'",
"review_claim_expires_at": "datetime DEFAULT NULL COMMENT '领取过期时间'",
"review_version": "bigint(20) NOT NULL DEFAULT '0' COMMENT '审核乐观锁版本'",
}
class ReviewConflictError(Exception):
"""The staging row changed or is owned by another review session."""
def __init__(self, message: str, current_record: dict[str, object] | None = None) -> None:
super().__init__(message)
self.current_record = current_record or {}
def _conflict_response(handler: BaseHTTPRequestHandler, exc: ReviewConflictError) -> None:
_json_response(
handler,
{
"error": str(exc),
"code": "review_conflict",
"current_record": exc.current_record,
},
status=409,
)
def _json_response(handler: BaseHTTPRequestHandler, payload: object, status: int = 200) -> None:
body = json.dumps(payload, ensure_ascii=False, default=str).encode("utf-8")
try:
handler.send_response(status)
handler.send_header("Content-Type", "application/json; charset=utf-8")
handler.send_header("Cache-Control", "no-store")
handler.send_header("Content-Length", str(len(body)))
handler.end_headers()
handler.wfile.write(body)
except (BrokenPipeError, ConnectionResetError):
return
def _error(handler: BaseHTTPRequestHandler, message: str, status: int = 400) -> None:
_json_response(handler, {"error": message}, status=status)
def _safe_path(raw_path: str) -> Path:
path = Path(unquote(raw_path)).expanduser()
if not path.is_absolute():
path = ROOT / path
resolved = path.resolve()
allowed_roots = [ROOT.resolve(), REPORT_DIR.resolve()]
if not any(resolved == base or base in resolved.parents for base in allowed_roots):
raise ValueError(f"path is outside workspace: {raw_path}")
if not resolved.exists() or not resolved.is_file():
raise FileNotFoundError(str(resolved))
return resolved
def _read_csv(path: Path) -> list[dict[str, str]]:
with open(path, "r", encoding="utf-8-sig", newline="") as f:
return list(csv.DictReader(f))
def _iter_csv(path: Path):
with open(path, "r", encoding="utf-8-sig", newline="") as f:
yield from csv.DictReader(f)
def _target_conn():
return pymysql.connect(**TARGET_DB_CONFIG)
def _ensure_review_schema(apply_migration: bool = False) -> None:
"""Validate or add the columns required by collaborative reviewing."""
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(f"SHOW COLUMNS FROM {TARGET_TABLE_NAME_TMP}")
existing_columns = {str(row["Field"]) for row in cursor.fetchall()}
missing = [name for name in REVIEW_SCHEMA_COLUMNS if name not in existing_columns]
if missing and not apply_migration:
names = ", ".join(missing)
raise RuntimeError(
f"暂存表缺少多人审核字段: {names}。"
"请先使用 --migrate-review-schema 启动一次。"
)
for name in missing:
cursor.execute(
f"ALTER TABLE {TARGET_TABLE_NAME_TMP} "
f"ADD COLUMN `{name}` {REVIEW_SCHEMA_COLUMNS[name]}"
)
cursor.execute(f"SHOW INDEX FROM {TARGET_TABLE_NAME_TMP} WHERE Key_name = %s", ("idx_staging_review_claim",))
if not cursor.fetchone():
if not apply_migration:
raise RuntimeError(
"暂存表缺少索引 idx_staging_review_claim。"
"请先使用 --migrate-review-schema 启动一次。"
)
cursor.execute(
f"ALTER TABLE {TARGET_TABLE_NAME_TMP} "
"ADD KEY `idx_staging_review_claim` (`biz_review_status`, `review_claim_expires_at`)"
)
if apply_migration:
conn.commit()
def _staging_summary() -> list[dict[str, str]]:
sql = f"""
SELECT
COUNT(DISTINCT source_song_id) AS total_count,
SUM(CASE WHEN dedup_action = 'new' THEN 1 ELSE 0 END) AS new_count,
SUM(CASE WHEN dedup_action = 'merge' THEN 1 ELSE 0 END) AS merge_count,
SUM(CASE WHEN dedup_action = 'review' THEN 1 ELSE 0 END) AS review_count,
SUM(CASE WHEN dedup_action = 'skip' THEN 1 ELSE 0 END) AS skip_count,
SUM(CASE WHEN dedup_action = 'review' AND (biz_review_status IS NULL OR biz_review_status IN ('pending', 'unsure')) THEN 1 ELSE 0 END) AS pending_review_count,
SUM(CASE WHEN biz_review_status = 'approved_import' THEN 1 ELSE 0 END) AS approved_count,
SUM(CASE WHEN biz_review_status = 'rejected_duplicate' THEN 1 ELSE 0 END) AS rejected_count,
SUM(CASE WHEN biz_review_status = 'deleted' THEN 1 ELSE 0 END) AS deleted_count,
SUM(CASE WHEN biz_review_status IN ('approved_import', 'rejected_duplicate', 'deleted') AND staging_status <> 'imported' THEN 1 ELSE 0 END) AS reviewed_count,
SUM(CASE WHEN biz_review_status IN ('approved_import', 'rejected_duplicate', 'deleted') AND staging_status = 'imported' THEN 1 ELSE 0 END) AS submitted_count
FROM (
SELECT source_song_id, dedup_action, biz_review_status, staging_status
FROM {TARGET_TABLE_NAME_TMP}
WHERE (source_song_id, staging_id) IN (
SELECT source_song_id, MAX(staging_id)
FROM {TARGET_TABLE_NAME_TMP}
GROUP BY source_song_id
)
) latest
"""
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(sql)
row = cursor.fetchone() or {}
return [{
"top_k": "staging",
"elapsed_seconds": "-",
"throughput_per_second": "-",
"avg_recalled_candidates": "-",
"hit_count": str((row.get("merge_count") or 0) + (row.get("review_count") or 0)),
"duplicate_count": str(row.get("merge_count") or 0),
"review_count": str(row.get("review_count") or 0),
"skip_count": str(row.get("skip_count") or 0),
"new_count": str(row.get("new_count") or 0),
"total_count": str(row.get("total_count") or 0),
"approved_count": str(row.get("approved_count") or 0),
"rejected_count": str(row.get("rejected_count") or 0),
"deleted_count": str(row.get("deleted_count") or 0),
"reviewed_count": str(row.get("reviewed_count") or 0),
"submitted_count": str(row.get("submitted_count") or 0),
"pending_review_count": str(row.get("pending_review_count") or 0),
}]
def _staging_dashboard_row(row: dict[str, object]) -> dict[str, str]:
lyrics_url = str(row.get("lyrics_url") or "")
# 若 lyrics_url 不是有效 URL/路径,说明是原始歌词文本(skip_oss 模式),加前缀供前端直接使用
if lyrics_url and not lyrics_url.startswith(("http://", "https://", "/")):
lyrics_url = f"_raw:{lyrics_url}"
return {
"top_k": "staging",
"rank": "1",
"query_source_id": str(row.get("source_song_id") or ""),
"query_name": str(row.get("name") or ""),
"query_lyricist": str(row.get("lyricist") or ""),
"query_composer": str(row.get("composer") or ""),
"query_lyrics_path": lyrics_url,
"candidate_id": str(row.get("matched_song_id") or ""),
"candidate_name": "",
"candidate_lyricist": "",
"candidate_composer": "",
"candidate_lyrics_path": "",
"candidate_decision": str(row.get("dedup_action") or ""),
"candidate_confidence": str(row.get("dedup_confidence") or ""),
"candidate_reason": str(row.get("dedup_reason") or ""),
"decision": str(row.get("dedup_action") or ""),
"action": str(row.get("dedup_action") or ""),
"source_id": str(row.get("source_song_id") or ""),
"staging_id": str(row.get("staging_id") or ""),
"review_status": str(row.get("biz_review_status") or ""),
"review_note": str(row.get("biz_review_note") or ""),
"reviewed_by": str(row.get("reviewed_by") or ""),
"reviewed_at": str(row.get("reviewed_at") or ""),
"review_version": str(row.get("review_version") or 0),
"review_claimed_by": str(row.get("review_claimed_by") or ""),
"review_claim_expires_at": str(row.get("review_claim_expires_at") or ""),
"staging_status": str(row.get("staging_status") or ""),
"l1_metadata_match": "1" if row.get("l1_matched_id") else "0",
"l1_l2_conflict": "0",
"audio_url": str(row.get("audio_url") or ""),
}
def _staging_groups_response(
mode: str,
term: str,
page: int,
page_size: int,
decision: str = "",
client_token: str = "",
) -> dict[str, object]:
where_clauses = []
params: list[object] = []
if term:
where_clauses.append("(CAST(s.source_song_id AS CHAR) LIKE %s OR s.name LIKE %s OR s.lyricist LIKE %s OR s.composer LIKE %s)")
like = f"%{term}%"
params.extend([like, like, like, like])
# hits 模式下只展示有命中的记录(merge/review)
if mode == "hits":
where_clauses.append("s.dedup_action IN ('merge', 'review')")
# 决策筛选:l1_hit / l2_hit / conflict / new / skip
if decision == 'l1_hit':
where_clauses.append("s.l1_matched_id IS NOT NULL")
elif decision == 'l2_duplicate':
where_clauses.append("s.dedup_action = 'merge'")
elif decision == 'l2_review':
where_clauses.append("s.dedup_action = 'review'")
elif decision == 'conflict':
where_clauses.append("(s.l1_matched_id IS NOT NULL AND s.dedup_action = 'new') OR (s.l1_matched_id IS NULL AND s.dedup_action IN ('merge', 'review'))")
elif decision == 'new':
where_clauses.append("s.dedup_action = 'new' AND s.l1_matched_id IS NULL")
elif decision == 'skip':
where_clauses.append("s.dedup_action = 'skip'")
elif decision == 'reviewed':
where_clauses.append("s.biz_review_status IN ('approved_import', 'rejected_duplicate', 'deleted')")
where_clauses.append("s.staging_status <> 'imported'")
elif decision == 'submitted':
where_clauses.append("s.biz_review_status IN ('approved_import', 'rejected_duplicate', 'deleted')")
where_clauses.append("s.staging_status = 'imported'")
elif decision == 'pending':
where_clauses.append("(s.biz_review_status IS NULL OR s.biz_review_status IN ('pending', 'unsure'))")
where_clauses.append("s.dedup_action = 'review'")
where_clauses.append("s.staging_status <> 'imported'")
where_clauses.append(
"(s.review_claim_expires_at IS NULL OR s.review_claim_expires_at <= NOW() OR s.review_claim_token = %s)"
)
params.append(client_token)
# 兼容旧的 dedup_action 筛选
elif decision and decision in ('merge', 'review'):
where_clauses.append("s.dedup_action = %s")
params.append(decision)
where = "WHERE " + " AND ".join(where_clauses) if where_clauses else ""
# 同一首歌可能因多次导入批次产生多行,按 source_song_id 去重取最新一行
latest_join = f"""
FROM {TARGET_TABLE_NAME_TMP} s
INNER JOIN (
SELECT source_song_id, MAX(staging_id) AS max_staging_id
FROM {TARGET_TABLE_NAME_TMP}
GROUP BY source_song_id
) latest ON s.staging_id = latest.max_staging_id
"""
count_sql = f"SELECT COUNT(*) AS n {latest_join} {where}"
sql = f"""
SELECT s.staging_id, s.source_song_id, s.name, s.lyricist, s.composer, s.dedup_action,
s.biz_review_status, s.staging_status, s.l1_matched_id, s.review_version,
CASE WHEN s.review_claim_expires_at > NOW() THEN s.review_claimed_by ELSE NULL END AS review_claimed_by,
s.review_claim_expires_at,
CASE WHEN s.review_claim_token = %s AND s.review_claim_expires_at > NOW() THEN 1 ELSE 0 END AS claimed_by_me
{latest_join}
{where}
ORDER BY
CASE s.dedup_action WHEN 'review' THEN 0 WHEN 'merge' THEN 1 ELSE 2 END,
s.staging_create_time DESC
LIMIT %s OFFSET %s
"""
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(count_sql, params)
total = (cursor.fetchone() or {}).get("n", 0)
cursor.execute(sql, [client_token, *params, page_size, max(0, (page - 1) * page_size)])
raw_rows = cursor.fetchall()
# Python 层面再去重,防止 SQL 层面因数据库版本或数据异常未能完全去重
seen_source_ids: set[str] = set()
rows = []
for row in raw_rows:
sid = str(row.get("source_song_id") or "")
if sid not in seen_source_ids:
seen_source_ids.add(sid)
rows.append(row)
groups = [
{
"id": str(row.get("source_song_id") or ""),
"query_source_id": str(row.get("source_song_id") or ""),
"query_name": row.get("name") or "",
"query_lyricist": row.get("lyricist") or "",
"query_composer": row.get("composer") or "",
"count": 1,
"has_hit": row.get("dedup_action") in {"merge", "review"},
"has_conflict": False,
"has_l1_hint": bool(row.get("l1_matched_id")),
"decision": row.get("dedup_action") or "",
"reviewed": row.get("biz_review_status") in {"approved_import", "rejected_duplicate", "deleted"},
"submitted": (
row.get("biz_review_status") in {"approved_import", "rejected_duplicate", "deleted"}
and row.get("staging_status") == "imported"
),
"staging_id": str(row.get("staging_id") or ""),
"review_version": int(row.get("review_version") or 0),
"review_claimed_by": str(row.get("review_claimed_by") or ""),
"review_claim_expires_at": str(row.get("review_claim_expires_at") or ""),
"claimed_by_me": bool(row.get("claimed_by_me")),
}
for row in rows
]
end = page * page_size
return {"total": total, "page": page, "page_size": page_size, "has_more": end < total, "groups": groups}
def _staging_query_rows(query_id: str) -> dict[str, object]:
sql = f"SELECT * FROM {TARGET_TABLE_NAME_TMP} WHERE source_song_id = %s ORDER BY staging_id DESC LIMIT 1"
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(sql, (query_id,))
row = cursor.fetchone()
if not row:
return {"rows": []}
matched_song_id = row.get("matched_song_id")
matched_row = None
if matched_song_id:
# 先尝试目标表查找(matched_id 是目标库 ID 的情况)
cursor.execute(
f"SELECT name, lyricist, composer, lyrics_url, audio_url FROM {TARGET_TABLE_NAME} WHERE id = %s",
(matched_song_id,),
)
matched_row = cursor.fetchone()
# 目标表找不到时,回退到暂存表查找(同批次内匹配,matched_id 是源库 source_song_id)
if not matched_row:
cursor.execute(
f"SELECT name, lyricist, composer, lyrics_url, audio_url FROM {TARGET_TABLE_NAME_TMP}"
f" WHERE source_song_id = %s ORDER BY staging_id DESC LIMIT 1",
(str(matched_song_id),),
)
matched_row = cursor.fetchone()
dashboard_row = _staging_dashboard_row(row)
has_main_match = bool(matched_song_id)
# 主行 rank:仅 merge/review 有主匹配时显示 "1",new 样本置空以便召回候选从 1 开始编号
dashboard_row["rank"] = "1" if has_main_match else ""
if matched_row:
dashboard_row["candidate_name"] = str(matched_row.get("name") or "")
dashboard_row["candidate_lyricist"] = str(matched_row.get("lyricist") or "")
dashboard_row["candidate_composer"] = str(matched_row.get("composer") or "")
cand_lyrics = str(matched_row.get("lyrics_url") or "")
if cand_lyrics and not cand_lyrics.startswith(("http://", "https://", "/")):
cand_lyrics = f"_raw:{cand_lyrics}"
dashboard_row["candidate_lyrics_path"] = cand_lyrics
dashboard_row["candidate_audio_url"] = str(matched_row.get("audio_url") or "")
rows = [dashboard_row]
# 解析 recalled_candidates JSON,为每个召回候选生成一张卡片
recalled_json = row.get("recalled_candidates")
if recalled_json:
try:
recalled_list = json.loads(recalled_json) if isinstance(recalled_json, str) else recalled_json
main_candidate_id = str(matched_song_id or "")
# 批量查找召回候选的歌词 URL(目标表 + 暂存表 fallback)
recalled_ids_str = [
str(c.get("id") or "")
for c in recalled_list
if c.get("id") and str(c.get("id")) != main_candidate_id
]
# 转 int 避免 bigint/string 类型不匹配导致 IN 查询返空
recalled_ids_int: list[int] = []
for rid in recalled_ids_str:
try:
recalled_ids_int.append(int(rid))
except (ValueError, TypeError):
pass
lyrics_map: dict[str, dict] = {}
if recalled_ids_int:
placeholders = ",".join(["%s"] * len(recalled_ids_int))
with _target_conn() as tconn, tconn.cursor() as tcursor:
# 目标表查找
tcursor.execute(
f"SELECT id, name, lyricist, composer, lyrics_url, audio_url"
f" FROM {TARGET_TABLE_NAME} WHERE id IN ({placeholders})",
recalled_ids_int,
)
for mrow in tcursor.fetchall():
lyrics_map[str(mrow.get("id"))] = mrow
# 暂存表 fallback:目标表找不到的 ID 从暂存表补查
missing_ids = [rid for rid in recalled_ids_int if str(rid) not in lyrics_map]
if missing_ids:
ph2 = ",".join(["%s"] * len(missing_ids))
tcursor.execute(
f"SELECT source_song_id, name, lyricist, composer, lyrics_url, audio_url"
f" FROM {TARGET_TABLE_NAME_TMP}"
f" WHERE source_song_id IN ({ph2})"
f" ORDER BY staging_id DESC",
[str(mid) for mid in missing_ids],
)
for mrow in tcursor.fetchall():
sid = str(mrow.get("source_song_id"))
if sid not in lyrics_map:
lyrics_map[sid] = mrow
rank = 2 if has_main_match else 1
for cand in recalled_list:
cand_id = str(cand.get("id") or "")
# 跳过已经是主匹配候选的(避免重复显示)
if cand_id and cand_id == main_candidate_id:
continue
cand_row = dict(dashboard_row)
cand_row["rank"] = str(rank)
cand_row["candidate_id"] = cand_id
# 优先用目标表/暂存表查到的元数据,回退到 JSON 中的信息
target_info = lyrics_map.get(cand_id)
if target_info:
cand_row["candidate_name"] = str(target_info.get("name") or cand.get("name") or "")
cand_row["candidate_lyricist"] = str(target_info.get("lyricist") or cand.get("lyricist") or "")
cand_row["candidate_composer"] = str(target_info.get("composer") or cand.get("composer") or "")
cand_lyrics = str(target_info.get("lyrics_url") or "")
if cand_lyrics and not cand_lyrics.startswith(("http://", "https://", "/")):
cand_lyrics = f"_raw:{cand_lyrics}"
cand_row["candidate_lyrics_path"] = cand_lyrics
cand_row["candidate_audio_url"] = str(target_info.get("audio_url") or "")
else:
cand_row["candidate_name"] = str(cand.get("name") or "")
cand_row["candidate_lyricist"] = str(cand.get("lyricist") or "")
cand_row["candidate_composer"] = str(cand.get("composer") or "")
cand_row["candidate_lyrics_path"] = ""
cand_row["candidate_audio_url"] = ""
cand_row["candidate_decision"] = str(cand.get("decision") or "new")
cand_row["candidate_confidence"] = str(cand.get("confidence") or "")
cand_row["candidate_jaccard"] = str(cand.get("jaccard") or "")
cand_row["candidate_line_coverage"] = str(cand.get("line_coverage") or "")
cand_row["candidate_reason"] = ""
rows.append(cand_row)
rank += 1
except (json.JSONDecodeError, TypeError):
pass
return {"rows": rows}
def _review_snapshot(cursor, staging_id: int) -> dict[str, object]:
cursor.execute(
f"""
SELECT staging_id, source_song_id, dedup_action, biz_review_status, biz_review_note,
reviewed_by, reviewed_at, review_version, review_claimed_by,
review_claim_expires_at, staging_status
FROM {TARGET_TABLE_NAME_TMP}
WHERE staging_id = %s
""",
(staging_id,),
)
return cursor.fetchone() or {}
def _claim_staging_review(staging_id: int, reviewer: str, client_token: str) -> dict[str, object]:
if not reviewer or not client_token:
raise ValueError("reviewer and client_token are required")
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(
f"""
UPDATE {TARGET_TABLE_NAME_TMP}
SET review_claimed_by = %s,
review_claim_token = %s,
review_claimed_at = NOW(),
review_claim_expires_at = DATE_ADD(NOW(), INTERVAL %s SECOND),
review_version = review_version + 1
WHERE staging_id = %s
AND staging_status <> 'imported'
AND (
biz_review_status IN ('pending', 'unsure')
OR biz_review_status = 'not_required'
OR biz_review_status IN ('approved_import', 'rejected_duplicate', 'deleted')
)
AND (
review_claim_expires_at IS NULL
OR review_claim_expires_at <= NOW()
OR review_claim_token = %s
)
""",
(reviewer, client_token, REVIEW_CLAIM_TTL_SECONDS, staging_id, client_token),
)
if cursor.rowcount != 1:
current = _review_snapshot(cursor, staging_id)
conn.rollback()
if not current:
message = f"找不到 staging_id={staging_id},请刷新页面后重试"
elif current.get("staging_status") == "imported":
message = "该记录已经入库,只能浏览,不能再领取审核"
elif current.get("review_claimed_by"):
message = f"该记录已由 {current['review_claimed_by']} 领取"
else:
message = f"该记录当前状态为 {current.get('biz_review_status') or '-'},不能领取"
raise ReviewConflictError(message, current)
current = _review_snapshot(cursor, staging_id)
conn.commit()
return current
def _heartbeat_staging_review(staging_id: int, client_token: str) -> dict[str, object]:
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(
f"""
UPDATE {TARGET_TABLE_NAME_TMP}
SET review_claim_expires_at = DATE_ADD(NOW(), INTERVAL %s SECOND)
WHERE staging_id = %s
AND review_claim_token = %s
AND review_claim_expires_at > NOW()
""",
(REVIEW_CLAIM_TTL_SECONDS, staging_id, client_token),
)
if cursor.rowcount != 1:
current = _review_snapshot(cursor, staging_id)
conn.rollback()
raise ReviewConflictError("审核领取已过期或已转给其他审核人", current)
current = _review_snapshot(cursor, staging_id)
conn.commit()
return current
def _review_statuses(staging_ids: list[int], client_token: str = "") -> list[dict[str, object]]:
if not staging_ids:
return []
placeholders = ",".join(["%s"] * len(staging_ids))
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(
f"""
SELECT staging_id, source_song_id, biz_review_status, staging_status, reviewed_by, reviewed_at,
review_version,
CASE WHEN review_claim_expires_at > NOW() THEN review_claimed_by ELSE NULL END AS review_claimed_by,
review_claim_expires_at,
CASE WHEN review_claim_token = %s AND review_claim_expires_at > NOW() THEN 1 ELSE 0 END AS claimed_by_me
FROM {TARGET_TABLE_NAME_TMP}
WHERE staging_id IN ({placeholders})
""",
[client_token, *staging_ids],
)
return cursor.fetchall()
def _update_staging_review(
staging_id: int,
decision: str,
note: str,
reviewer: str,
expected_version: int,
client_token: str,
) -> dict[str, object]:
"""Persist one claimed review using optimistic concurrency control."""
if decision == "pending":
status_fields = """
biz_review_status = 'pending', reviewed_by = NULL, reviewed_at = NULL,
staging_status = CASE WHEN staging_status = 'deleted' THEN 'staged' ELSE staging_status END
"""
elif decision == "deleted":
status_fields = """
biz_review_status = 'deleted', reviewed_by = %s, reviewed_at = NOW(),
staging_status = 'deleted'
"""
else:
status_fields = "biz_review_status = %s, reviewed_by = %s, reviewed_at = NOW()"
params: list[object]
if decision == "pending":
params = [note, staging_id, expected_version, client_token, reviewer]
elif decision == "deleted":
params = [reviewer, note, staging_id, expected_version, client_token, reviewer]
else:
params = [decision, reviewer, note, staging_id, expected_version, client_token, reviewer]
with _target_conn() as conn, conn.cursor() as cursor:
cursor.execute(
f"""
UPDATE {TARGET_TABLE_NAME_TMP}
SET {status_fields},
biz_review_note = NULLIF(%s, ''),
review_version = review_version + 1,
review_claimed_by = NULL,
review_claim_token = NULL,
review_claimed_at = NULL,
review_claim_expires_at = NULL
WHERE staging_id = %s
AND review_version = %s
AND review_claim_token = %s
AND review_claimed_by = %s
AND review_claim_expires_at > NOW()
""",
params,
)
if cursor.rowcount != 1:
current = _review_snapshot(cursor, staging_id)
conn.rollback()
raise ReviewConflictError("记录已被其他人修改,当前提交未覆盖数据库", current)
current = _review_snapshot(cursor, staging_id)
conn.commit()
return current
def _import_approved_staging(source_ids: list[str] | None = None) -> dict[str, object]:
"""Import approved rows while holding staging-row locks to prevent duplicate imports."""
columns = ", ".join(f"`{column}`" for column in TARGET_COLUMNS)
select_columns = ", ".join(f"s.`{column}`" for column in TARGET_COLUMNS)
with _target_conn() as conn, conn.cursor() as cursor:
source_filter = ""
lock_params: list[object] = []
if source_ids:
source_placeholders = ",".join(["%s"] * len(source_ids))
source_filter = f" AND s.source_song_id IN ({source_placeholders})"
lock_params.extend(source_ids)
cursor.execute(
f"""
SELECT s.staging_id, s.source_song_id
FROM {TARGET_TABLE_NAME_TMP} s
INNER JOIN (
SELECT source_song_id, MAX(staging_id) AS max_staging_id
FROM {TARGET_TABLE_NAME_TMP}
GROUP BY source_song_id
) latest ON s.staging_id = latest.max_staging_id
WHERE s.dedup_action = 'review'
AND s.biz_review_status = 'approved_import'
AND s.staging_status = 'staged'
AND (s.review_claim_expires_at IS NULL OR s.review_claim_expires_at <= NOW())
{source_filter}
ORDER BY staging_id
FOR UPDATE
""",
lock_params,
)
approved_rows = cursor.fetchall()
if not approved_rows:
conn.rollback()
raise ValueError("没有可入库的审核通过样本")
staging_ids = [row["staging_id"] for row in approved_rows]
approved_source_ids = [str(row["source_song_id"]) for row in approved_rows]
staging_placeholders = ",".join(["%s"] * len(staging_ids))
cursor.execute(
f"""
INSERT INTO {TARGET_TABLE_NAME} ({columns})
SELECT {select_columns}
FROM {TARGET_TABLE_NAME_TMP} s
WHERE s.staging_id IN ({staging_placeholders})
""",
staging_ids,
)
inserted_count = cursor.rowcount
source_placeholders = ",".join(["%s"] * len(approved_source_ids))
cursor.execute(
f"""
SELECT source_song_id, id AS target_id
FROM {TARGET_TABLE_NAME}
WHERE source_song_id IN ({source_placeholders})
""",
approved_source_ids,
)
id_map = {str(row["source_song_id"]): row["target_id"] for row in cursor.fetchall()}
imported_updated = 0
for approved_row in approved_rows:
sid = str(approved_row["source_song_id"])
target_id = id_map.get(sid)
if target_id is None:
raise RuntimeError(f"入库后未找到目标记录: source_song_id={sid}")
cursor.execute(
f"""
UPDATE {TARGET_TABLE_NAME_TMP}
SET staging_status = 'imported', imported_song_id = %s, error_message = NULL,
review_version = review_version + 1
WHERE staging_id = %s AND staging_status = 'staged'
""",
(target_id, approved_row["staging_id"]),
)
imported_updated += cursor.rowcount
conn.commit()
return {
"approved_count": len(approved_rows),
"inserted_count": inserted_count,
"imported_song_ids_updated": imported_updated,
"source_ids": approved_source_ids,
}
def _report_runs() -> list[dict[str, str]]:
summaries = {
path.name.replace("l2_topk_benchmark_summary_", "").removesuffix(".csv"): path
for path in REPORT_DIR.glob("l2_topk_benchmark_summary_*.csv")
}
retrievals = {
path.name.replace("l2_topk_retrieval_top10_", "").removesuffix(".csv"): path
for path in REPORT_DIR.glob("l2_topk_retrieval_top10_*.csv")
}
hits = {
path.name.replace("l2_topk_duplicate_hits_", "").removesuffix(".csv"): path
for path in REPORT_DIR.glob("l2_topk_duplicate_hits_*.csv")
}
run_ids = sorted(set(summaries) & set(retrievals) & set(hits), reverse=True)
benchmark_runs = [
{
"id": run_id,
"type": "benchmark",
"summary": str(summaries[run_id]),
"retrieval": str(retrievals[run_id]),
"hits": str(hits[run_id]),
}
for run_id in run_ids
]
review_runs = [
{
"id": path.name.replace("review_decisions_", "").removesuffix(".csv"),
"type": "import",
"summary": str(path),
"retrieval": str(path),
"hits": str(path),
"review": str(path),
}
for path in sorted(REPORT_DIR.glob("review_decisions_*.csv"), reverse=True)
]
staging_run = {
"id": "staging-db",
"type": "staging",
"summary": STAGING_DB_PATH,
"retrieval": STAGING_DB_PATH,
"hits": STAGING_DB_PATH,
"review": STAGING_DB_PATH,
}
return [staging_run] + review_runs + benchmark_runs
def _row_decision(row: dict[str, str]) -> str:
return row.get("action") or row.get("decision") or row.get("candidate_decision") or ""
def _is_import_review_row(row: dict[str, str]) -> bool:
return "source_id" in row and "action" in row and "query_source_id" not in row
def _dashboard_row(row: dict[str, str]) -> dict[str, str]:
if not _is_import_review_row(row):
return row
source_id = row.get("source_id", "")
action = row.get("action", "")
return {
**row,
"top_k": "import",
"rank": "1",
"query_source_id": source_id,
"query_name": row.get("name", ""),
"query_lyricist": row.get("lyricist", ""),
"query_composer": row.get("composer", ""),
"query_lyrics_path": row.get("query_lyrics_path", ""),
"candidate_id": row.get("matched_id", ""),
"candidate_name": row.get("matched_name", ""),
"candidate_lyricist": row.get("matched_lyricist", ""),
"candidate_composer": row.get("matched_composer", ""),
"candidate_lyrics_path": row.get("matched_lyrics_path", ""),
"candidate_decision": action,
"candidate_confidence": row.get("confidence", ""),
"candidate_reason": row.get("reason", ""),
"decision": action,
"l1_metadata_match": "1" if row.get("l1_matched_id") else "0",
"l1_l2_conflict": "0",
}
def _review_summary(path: Path) -> list[dict[str, str]]:
counts = {"new": 0, "merge": 0, "review": 0}
total = 0
for row in _iter_csv(path):
total += 1
action = row.get("action", "")
if action in counts:
counts[action] += 1
return [{
"top_k": "import",
"elapsed_seconds": "-",
"throughput_per_second": "-",
"avg_recalled_candidates": "-",
"hit_count": str(counts["merge"] + counts["review"]),
"duplicate_count": str(counts["merge"]),
"review_count": str(counts["review"]),
"new_count": str(counts["new"]),
"total_count": str(total),
}]
def _norm(value: str | None) -> str:
return (value or "").strip().lower()
def _matches_term(row: dict[str, object], term: str) -> bool:
if not term:
return True
haystack = " ".join(
[
row.get("query_source_id", ""),
row.get("query_name", ""),
row.get("query_lyricist", ""),
row.get("query_composer", ""),
]
).lower()
return term in haystack
def _group_index(path: Path, top_k: str) -> list[dict[str, object]]:
stat = path.stat()
cache_key = (str(path), stat.st_mtime_ns, stat.st_size, top_k)
cached = GROUP_INDEX_CACHE.get(cache_key)
if cached is not None:
return cached
groups_by_id: dict[str, dict[str, object]] = {}
order = 0
for raw_row in _iter_csv(path):
row = _dashboard_row(raw_row)
if top_k and str(row.get("top_k", "")) != top_k:
continue
query_id = row.get("query_source_id", "")
if not query_id:
continue
group = groups_by_id.get(query_id)
if group is None:
group = {
"id": query_id,
"_order": order,
"query_source_id": query_id,
"query_name": row.get("query_name", ""),
"query_lyricist": row.get("query_lyricist", ""),
"query_composer": row.get("query_composer", ""),
"count": 0,
"has_hit": False,
"has_conflict": False,
"has_l1_hint": False,
"decision": _row_decision(row),
}
groups_by_id[query_id] = group
order += 1
group["count"] = int(group["count"]) + 1
decision = _row_decision(row)
l1_match = row.get("l1_metadata_match") == "1"
conflict = row.get("l1_l2_conflict") == "1"
group["has_hit"] = bool(group["has_hit"]) or decision in {"duplicate", "review"}
group["has_conflict"] = bool(group["has_conflict"]) or conflict
group["has_l1_hint"] = bool(group["has_l1_hint"]) or (decision == "new" and l1_match)
groups = sorted(
groups_by_id.values(),
key=lambda group: (
0 if group["has_conflict"] else 1,
0 if group["has_l1_hint"] else 1,
0 if group["has_hit"] else 1,
int(group["_order"]),
),
)
GROUP_INDEX_CACHE.clear()
GROUP_INDEX_CACHE[cache_key] = groups
return groups
def _groups_response(path: Path, top_k: str, mode: str, term: str, page: int, page_size: int, decision: str = '') -> dict[str, object]:
groups = _group_index(path, top_k)
# hits 模式下只展示有命中的记录(merge/review),排除纯 new
if mode == "hits":
groups = [g for g in groups if g.get("has_hit")]
# 决策筛选
if decision == 'l1_hit':
groups = [g for g in groups if g.get("has_l1_hint")]
elif decision == 'l2_duplicate':
groups = [g for g in groups if g.get("decision") == "merge"]
elif decision == 'l2_review':
groups = [g for g in groups if g.get("decision") == "review"]
elif decision == 'conflict':
groups = [g for g in groups if g.get("has_conflict")]
elif decision == 'new':
groups = [g for g in groups if g.get("decision") == "new" and not g.get("has_l1_hint")]
elif decision == 'skip':
groups = [g for g in groups if g.get("decision") == "skip"]
elif decision == 'reviewed':
groups = [g for g in groups if g.get("reviewed")]
elif decision == 'pending':
groups = [g for g in groups if not g.get("reviewed")]
elif decision and decision in ('merge', 'review', 'duplicate'):
groups = [g for g in groups if g.get("decision") == decision]
filtered = [group for group in groups if _matches_term(group, term)]
start = max(0, (page - 1) * page_size)
end = start + page_size
page_groups = filtered[start:end]
return {
"total": len(filtered),
"page": page,
"page_size": page_size,
"has_more": end < len(filtered),
"groups": [{key: value for key, value in group.items() if not key.startswith("_")} for group in page_groups],
}
def _query_rows_response(path: Path, top_k: str, query_id: str) -> dict[str, object]:
rows = []
found = False
for raw_row in _iter_csv(path):
row = _dashboard_row(raw_row)
if str(row.get("top_k", "")) != top_k:
continue
current_query_id = row.get("query_source_id", "")
if current_query_id == query_id:
found = True
rows.append(row)
continue
if found:
break
return {"rows": rows}
def _write_review_import_csv(rows: list[dict[str, str]]) -> Path:
path = REPORT_DIR / f"review_import_approved_{time.strftime('%Y%m%d_%H%M%S')}.csv"
with open(path, "w", encoding="utf-8", newline="") as f:
writer = csv.DictWriter(f, fieldnames=["source_id", "review_decision", "review_note"])
writer.writeheader()
for row in rows:
writer.writerow({
"source_id": row.get("source_id", ""),
"review_decision": row.get("review_decision", ""),
"review_note": row.get("review_note", ""),
})
return path
def _run_import(review_csv: Path) -> dict[str, object]:
cmd = [
"uv",
"run",
"python",
"import_hk_songs.py",
"--review-result-csv",
str(review_csv),
"--load-existing-lyrics",
"--skip-media-oss",
]
result = subprocess.run(
cmd,
cwd=ROOT,
text=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
check=False,
)
return {
"command": " ".join(cmd),
"returncode": result.returncode,
"output": result.stdout[-12000:],
}
class Handler(BaseHTTPRequestHandler):
def log_message(self, fmt: str, *args: object) -> None:
print(f"{self.address_string()} - {fmt % args}")
def do_GET(self) -> None:
parsed = urlparse(self.path)
if parsed.path == "/":
self._serve_file(DASHBOARD)
return
if parsed.path == "/api/reports":
_json_response(self, {"runs": _report_runs()})
return
if parsed.path == "/api/csv":
params = parse_qs(parsed.query)
raw_path = params.get("path", [""])[0]
try:
if raw_path == STAGING_DB_PATH:
_json_response(self, {"path": raw_path, "rows": _staging_summary()})
return
path = _safe_path(raw_path)
if path.name.startswith("review_decisions_"):
_json_response(self, {"path": str(path), "rows": _review_summary(path)})
else:
_json_response(self, {"path": str(path), "rows": _read_csv(path)})
except Exception as exc: # noqa: BLE001 - local diagnostic API
print(f"[ERROR] /api/csv 异常: {exc}")
_error(self, str(exc), status=404)
return
if parsed.path == "/api/groups":
params = parse_qs(parsed.query)
try:
raw_path = params.get("path", [""])[0]
top_k = params.get("top_k", [""])[0]
mode = params.get("mode", ["retrieval"])[0]
term = _norm(params.get("q", [""])[0])
decision = _norm(params.get("decision", [""])[0])
client_token = params.get("client_token", [""])[0].strip()
page = max(1, int(params.get("page", ["1"])[0]))
page_size = min(200, max(10, int(params.get("page_size", ["50"])[0])))
if raw_path == STAGING_DB_PATH:
_json_response(
self,
_staging_groups_response(mode, term, page, page_size, decision, client_token),
)
return
path = _safe_path(raw_path)
_json_response(self, _groups_response(path, top_k, mode, term, page, page_size, decision))
except Exception as exc: # noqa: BLE001 - local diagnostic API
_error(self, str(exc), status=404)
return
if parsed.path == "/api/review-statuses":
params = parse_qs(parsed.query)
try:
raw_ids = params.get("staging_ids", [""])[0]
staging_ids = [int(value) for value in raw_ids.split(",") if value.strip()]
if len(staging_ids) > 200:
raise ValueError("最多同步 200 条记录")
client_token = params.get("client_token", [""])[0].strip()
_json_response(self, {"rows": _review_statuses(staging_ids, client_token)})
except Exception as exc: # noqa: BLE001
_error(self, str(exc), status=400)
return
if parsed.path == "/api/query":
params = parse_qs(parsed.query)
try:
raw_path = params.get("path", [""])[0]
top_k = params.get("top_k", [""])[0]
query_id = params.get("query_id", [""])[0]
if raw_path == STAGING_DB_PATH:
_json_response(self, _staging_query_rows(query_id))
return
path = _safe_path(raw_path)
_json_response(self, _query_rows_response(path, top_k, query_id))
except Exception as exc: # noqa: BLE001 - local diagnostic API
_error(self, str(exc), status=404)
return
if parsed.path == "/api/text":
params = parse_qs(parsed.query)
raw_path = params.get("path", [""])[0]
try:
if raw_path.startswith(("http://", "https://")):
resp = requests.get(raw_path, timeout=10)
resp.raise_for_status()
_json_response(self, {"path": raw_path, "text": resp.content.decode("utf-8", errors="replace")})
return
path = _safe_path(raw_path)
text = path.read_text(encoding="utf-8", errors="replace")
_json_response(self, {"path": str(path), "text": text})
except Exception as exc: # noqa: BLE001 - local diagnostic API
_error(self, str(exc), status=404)
return
if parsed.path.startswith("/static/"):
self._serve_file(ROOT / parsed.path.lstrip("/"))
return
_error(self, "not found", status=404)
def do_POST(self) -> None:
parsed = urlparse(self.path)
if parsed.path in {"/api/review-claim", "/api/review-heartbeat"}:
try:
length = int(self.headers.get("Content-Length", "0"))
payload = json.loads(self.rfile.read(length).decode("utf-8") or "{}")
staging_id = int(payload.get("staging_id") or 0)
client_token = str(payload.get("client_token") or "").strip()
if not staging_id:
raise ValueError("staging_id is required")
if parsed.path == "/api/review-claim":
reviewer = str(payload.get("reviewer") or "").strip()
current = _claim_staging_review(staging_id, reviewer, client_token)
else:
current = _heartbeat_staging_review(staging_id, client_token)
_json_response(self, {"record": current})
except ReviewConflictError as exc:
_conflict_response(self, exc)
except Exception as exc: # noqa: BLE001
_error(self, str(exc), status=400)
return
if parsed.path == "/api/staging-review":
try:
length = int(self.headers.get("Content-Length", "0"))
payload = json.loads(self.rfile.read(length).decode("utf-8") or "{}")
staging_id = int(payload.get("staging_id") or 0)
decision = str(payload.get("decision", "")).strip()
note = str(payload.get("note", "")).strip()
reviewer = str(payload.get("reviewer") or "").strip()
client_token = str(payload.get("client_token") or "").strip()
expected_version = int(payload.get("expected_version", -1))
if not staging_id:
raise ValueError("staging_id is required")
if not reviewer or not client_token or expected_version < 0:
raise ValueError("reviewer, client_token and expected_version are required")
if decision not in ("approved_import", "rejected_duplicate", "unsure", "pending", "deleted"):
raise ValueError(f"invalid decision: {decision}")
result = _update_staging_review(
staging_id, decision, note, reviewer, expected_version, client_token
)
_json_response(self, {"record": result})
except ReviewConflictError as exc:
_conflict_response(self, exc)
except Exception as exc: # noqa: BLE001
_error(self, str(exc), status=400)
return
if parsed.path != "/api/import-reviewed":
_error(self, "not found", status=404)
return
try:
length = int(self.headers.get("Content-Length", "0"))
payload = json.loads(self.rfile.read(length).decode("utf-8") or "{}")
source_ids = payload.get("source_ids")
if source_ids is not None and not isinstance(source_ids, list):
raise ValueError("source_ids must be a list")
result = _import_approved_staging(
[str(value).strip() for value in source_ids if str(value).strip()]
if source_ids
else None
)
approved = [
{"source_id": source_id, "review_decision": "import", "review_note": ""}
for source_id in result["source_ids"]
]
review_csv = _write_review_import_csv(approved)
_json_response(self, {"review_csv": str(review_csv), **result})
except Exception as exc: # noqa: BLE001 - local diagnostic API
_error(self, str(exc), status=400)
def _serve_file(self, path: Path) -> None:
if not path.exists() or not path.is_file():
_error(self, "not found", status=404)
return
content_type = mimetypes.guess_type(path.name)[0] or "application/octet-stream"
body = path.read_bytes()
self.send_response(200)
self.send_header("Content-Type", content_type)
if path.suffix.lower() in {".html", ".js", ".css"}:
self.send_header("Cache-Control", "no-cache")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def main() -> None:
parser = argparse.ArgumentParser(description="Serve L2 lyric review dashboard")
parser.add_argument("--host", default="127.0.0.1")
parser.add_argument("--port", type=int, default=8765)
parser.add_argument(
"--migrate-review-schema",
action="store_true",
help="add the staging-table columns/index required for collaborative reviewing",
)
args = parser.parse_args()
_ensure_review_schema(apply_migration=args.migrate_review_schema)
server = ThreadingHTTPServer((args.host, args.port), Handler)
print(f"L2 dashboard: http://{args.host}:{args.port}")
server.serve_forever()
if __name__ == "__main__":
try:
main()
except KeyboardInterrupt:
sys.exit(0)