-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcleanup-discogs.py
executable file
·1402 lines (1265 loc) · 82.1 KB
/
cleanup-discogs.py
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
#!/usr/bin/env python3
# Tool to discover 'smells' in the Discogs data dump. It prints a list of URLs
# of releases that need to be fixed.
#
# The results that are printed by this script are
# by no means complete or accurate
#
# Licensed under the terms of the General Public License version 3
#
# SPDX-License-Identifier: GPL-3.0-only
#
# Copyright 2017-2025 - Armijn Hemel
import configparser
import datetime
import gzip
import pathlib
import re
import sys
import xml.etree.ElementTree as orig_et
from dataclasses import dataclass
import defusedxml.ElementTree as et
import click
import discogssmells
ISRC_TRANSLATE = str.maketrans({'-': None, ' ': None, '.': None,
':': None, '–': None,})
# a list of possible label code false positives. These are
# used when checking the catalog numbers.
LABEL_CODE_FALSE_POSITIVES = set([654, 1005, 1060, 2495, 5320, 11358, 20234, 20561, 22804, 23541,
29480, 38653, 39161, 54361, 63510, 66210, 97031, 113617, 123839,
127100, 130286, 163947, 185266, 199380, 226480, 237745, 238695,
251227, 253128, 253548, 487381, 498544, 510628, 511917, 593249,
605295, 620121, 645109, 646715, 656580, 762933, 810881, 943057,
1210375, 1446781, 1624446, 1674048])
RIGHTS_SOCIETY_DELIMITERS = ['/', '|', '\\', '-', '—', '•', '·', ',', ':', ' ', '&', '+']
# a quick and dirty translation table to see if rights society values
# are correct. This is just for the first big sweep.
RIGHTS_SOCIETY_TRANSLATE_QND = str.maketrans({'.': None, ' ': None, '•': None,
'[': None, ']': None, '(': None,
')': None})
SID_INVALID_FORMATS = set(['Vinyl', 'Cassette', 'Shellac', 'File',
'VHS', 'DCC', 'Memory Stick', 'Edison Disc'])
# SID descriptions (either Mastering or Mould)
SID_DESCRIPTIONS = ['source identification code', 'sid', 'sid code', 'sid-code']
SPARS_TRANSLATE = str.maketrans({'.': None, ' ': None, '•': None, '·': None,
'∙': None, '᛫': None, '[': None, ']': None,
'-': None, '|': None, '︱': None, '/': None,
'\\': None})
# Translation table for SID codes as some people
# insist on using ƒ/⨍ instead of f or ρ/ƥ instead of p
SID_TRANSLATE = str.maketrans({' ': None, '-': None,
'⨍': 'f', 'ƒ': 'f',
'ρ': 'p', 'ƥ': 'p'})
TRACKLIST_CHECK_FORMATS = ['Vinyl', 'Cassette', 'Shellac', '8-Track Cartridge']
# grab the current year. Make sure to set the clock of your machine
# to the correct date or use NTP!
CURRENT_YEAR = datetime.datetime.now(datetime.UTC).year
pkd_re = re.compile(r"\d{1,2}/((?:19|20)?\d{2})")
@dataclass
class CleanupConfig:
'''Default cleanup configuration'''
artist: bool = False
asin: bool = True
cd_plus_g: bool = True
creative_commons: bool = False
credits: bool = False
czechoslovak_dates: bool = True
czechoslovak_dates_strict: bool = False
czechoslovak_spelling: bool = True
debug: bool = False
deposito_legal: bool = True
greek_license: bool = True
indian_pkd: bool = True
isrc: bool = True
label_code: bool = True
label_name: bool = True
labels: bool = True
mastering_sid: bool = True
matrix: bool = True
month_valid: bool = False
mould_sid: bool = True
mould_sid_strict: bool = False
pressing_plants: bool = True
report_all: bool = False
rights_society: bool = True
spars: bool = True
tracklisting: bool = True
url_in_html: bool = True
year_valid: bool = False
def print_error(counter, reason, release_id):
'''Helper method for printing errors'''
print(f'{counter: 8} -- {reason}: https://www.discogs.com/release/{release_id}')
sys.stdout.flush()
def check_role(role):
'''Helper method for checking roles'''
pass
def check_spars(value, year):
'''Helper method for checking SPARS codes'''
wrong_spars = False
errors = []
# check if the code is valid
if value not in discogssmells.validsparscodes:
wrong_spars = True
errors.append(f'Invalid SPARS: {value}')
for s in value:
if ord(s) > 256:
wrong_spars = True
errors.append(f'wrong character set: {value}')
break
if not wrong_spars:
if year is not None:
if year < 1984:
errors.append(f"impossible year: {year}")
return errors
def check_rights_society(value):
'''Helper method for checking rights societies'''
errors = []
value = value.translate(RIGHTS_SOCIETY_TRANSLATE_QND)
if value in discogssmells.rights_societies_wrong:
errors.append(f"possible wrong value: {value}")
if value in discogssmells.rights_societies_wrong_char:
errors.append(f"wrong character set: {value}")
return errors
@click.group()
def app():
pass
@app.command(short_help='open Discogs datadump file and pretty print a single release')
@click.option('--datadump', '-d', 'datadump', required=True, help='discogs data dump file',
type=click.Path(exists=True))
@click.option('--release', '-r', 'requested_release', required=True,
help='release number to scan', type=int)
def pretty_print(datadump, requested_release):
'''Search the data set for a specific release number.
This assumes that the XML dump is ordered by release
number (ascending).
'''
try:
with gzip.open(datadump, "rb") as dumpfile:
counter = 1
prev_counter = 1
for event, element in et.iterparse(dumpfile):
if element.tag == 'release':
# store the current release id
release_id = int(element.get('id'))
if requested_release == release_id:
orig_et.indent(element)
print(et.tostring(element).decode())
break
if requested_release > release_id:
# reduce memory usage
element.clear()
continue
if requested_release < release_id:
print(f'Release {requested_release} cannot be found in data set!',
file=sys.stderr)
sys.exit(1)
except:
pass
@app.command(short_help='process Discogs datadump files and print errors found')
@click.option('--config-file', '-c', 'cfg', required=True, help='configuration file',
type=click.File('r'))
@click.option('--datadump', '-d', 'datadump', required=True, help='discogs data dump file',
type=click.Path(exists=True))
@click.option('--release', '-r', 'requested_release', help='release number to scan', type=int)
def check(cfg, datadump, requested_release):
'''Read the Discogs XML dump and sanity check all releases or a single release.'''
config = configparser.ConfigParser()
try:
config.read_file(cfg)
except Exception:
print("Cannot read configuration file", file=sys.stderr)
sys.exit(1)
# process the configuration file and store settings.
# Most of the defaults (but not all!) are set to 'True'
settings = CleanupConfig()
# store settings for depósito legal checks
try:
settings.deposito_legal = config.getboolean('cleanup', 'deposito')
except:
pass
# store settings for rights society checks
try:
settings.rights_society = config.getboolean('cleanup', 'rights_society')
except:
pass
# store settings for label code checks
try:
settings.label_code = config.getboolean('cleanup', 'label_code')
except:
pass
# store settings for label name checks
try:
settings.label_name = config.getboolean('cleanup', 'label_name')
except:
pass
# store settings for ISRC checks
try:
settings.isrc = config.getboolean('cleanup', 'isrc')
except:
pass
# store settings for ASIN checks
try:
settings.asin = config.getboolean('cleanup', 'asin')
except:
pass
# store settings for mastering SID checks
try:
settings.mastering_sid = config.getboolean('cleanup', 'mastering_sid')
except:
pass
# store settings for mould SID checks
try:
settings.mould_sid = config.getboolean('cleanup', 'mould_sid')
except:
pass
# store settings for mould SID strict checks
try:
settings.mould_sid_strict = config.getboolean('cleanup', 'mould_sid_strict')
except:
pass
# store settings for SPARS Code checks
try:
settings.spars = config.getboolean('cleanup', 'spars')
except:
pass
# store settings for Indian PKD checks
try:
settings.indian_pkd = config.getboolean('cleanup', 'pkd')
except:
pass
# store settings for Greek license number checks
try:
settings.greek_license = config.getboolean('cleanup', 'greek_license_number')
except:
pass
# store settings for CD+G checks
try:
settings.cd_plus_g = config.getboolean('cleanup', 'cdg')
except:
pass
# store settings for Matrix checks
try:
settings.matrix = config.getboolean('cleanup', 'matrix')
except:
pass
# store settings for label checks
try:
settings.labels = config.getboolean('cleanup', 'labels')
except:
pass
# store settings for manufacturing plant checks
try:
settings.pressing_plants = config.getboolean('cleanup', 'plants')
except:
pass
# check for Czechoslovak manufacturing dates
try:
settings.czechoslovak_dates = config.getboolean('cleanup', 'manufacturing_date_cs')
except:
pass
# check for strict Czechoslovak manufacturing dates
try:
settings.czechoslovak_dates_strict = config.getboolean('cleanup', 'manufacturing_date_cs_strict')
except:
pass
# check for Czechoslovak and Czech spelling (0x115 used instead of 0x11B)
try:
settings.czechoslovak_spelling = config.getboolean('cleanup', 'spelling_cs')
except:
pass
# store settings for tracklisting checks, default True
try:
settings.tracklisting = config.getboolean('cleanup', 'tracklisting')
except:
pass
# store settings for artists, default False
try:
settings.artist = config.getboolean('cleanup', 'artist')
except:
pass
# store known valid credits
credit_roles = set()
# store settings for credits list checks, implies artist checks
# This only makes sense if there is a valid credits file
try:
if config.get('cleanup', 'credits') == 'yes':
creditsfile = pathlib.Path(config.get('cleanup', 'creditsfile'))
if creditsfile.exists():
settings.credits = True
with open(creditsfile, 'r') as open_file:
credit_roles = set(map(lambda x: x.strip(), open_file.readlines()))
if credit_roles != set():
settings.artist = True
else:
settings.credits = False
except:
pass
# store settings for URLs in Notes checks
try:
settings.url_in_html = config.getboolean('cleanup', 'html')
except:
pass
# month is 00 check: default is False
try:
settings.month_valid = config.getboolean('cleanup', 'month')
except:
pass
# year is wrong check: default is False
try:
settings.year_valid = config.getboolean('cleanup', 'year')
except:
pass
# reporting all: default is False
try:
settings.report_all = config.getboolean('cleanup', 'reportall')
except:
pass
# debug: default is False
try:
settings.debug = config.getboolean('cleanup', 'debug')
except:
pass
# report creative commons references: default is False
try:
settings.creative_commons = config.getboolean('cleanup', 'creative_commons')
except:
pass
# read the actual XML dump file
try:
with gzip.open(datadump, "rb") as dumpfile:
counter = 1
prev_counter = 1
last_release_checked = 0
ignore_status = ['Deleted', 'Draft', 'Rejected']
for event, element in et.iterparse(dumpfile):
if element.tag == 'release':
# store the release id
release_id = int(element.get('id'))
# skip the release if -r was passed on the command line
if requested_release is not None:
if requested_release > release_id:
# reduce memory usage
element.clear()
continue
if requested_release < release_id:
print(f'Release {requested_release} cannot be found in data set!',
file=sys.stderr)
sys.exit(1)
# first see if a release is worth looking at
status = element.get('status')
if status in ignore_status:
continue
# then store various things about the release
country = ""
deposito_found = False
deposito_found_in_notes = False
year = None
formats = set()
num_formats = 0
is_cd = False
# data structures specific for detecting reuse of
# ISRC codes and descriptions.
isrcs_seen = set()
isrc_descriptions_seen = set()
# genres, currently not used in a check
genres = set()
# first store the country to make sure it is always available
# for for various country checks (like Czech misspellings)
for child in element:
if child.tag == 'country':
country = child.text
break
for child in element:
if child.tag == 'released':
if child.text:
if child.text != '':
try:
year = int(child.text.split('-', 1)[0])
except ValueError:
pass
break
# and process the different elements
for child in element:
if settings.report_all:
if release_id == last_release_checked:
break
if country in ['Czechoslovakia', 'Czech Republic']:
if settings.czechoslovak_spelling:
# People use 0x115 instead of 0x11B, which look very similar
# but 0x115 is not valid in the Czech alphabet. Check for all
# data except the YouTube playlist.
# https://www.discogs.com/group/thread/757556
if child.tag != 'videos':
czech_error_found = False
for iter_child in child.iter():
for i in ['description', 'value']:
free_text = iter_child.get(i, '').lower()
if chr(0x115) in free_text:
print_error(counter, 'Czech character (0x115)', release_id)
counter += 1
czech_error_found = True
break
if czech_error_found:
break
if child.tag in ['artists', 'extraartists']:
if settings.artist:
for artist_elem in child:
# set to "no artist" as a place holder
artist_id = 0
artist_name = ''
for artist in artist_elem:
if artist.text:
if artist.tag == 'id':
artist_id = int(artist.text)
# TODO: check for genres, as No Artist is
# often confused with Unknown Artist
#if artist_id == 118760:
# if genres:
# print_error(counter, f'https://www.discogs.com/artist/{artist_id}' release_id)
# counter += 1
elif artist.tag == 'name':
artist_name = artist.text
elif artist.tag == 'role':
'''
if artist_id == 0:
wrong_role_for_noartist = True
for r in ['Other', 'Artwork By', 'Executive Producer', 'Photography', 'Written By']:
if r in artist.text.strip():
wrong_role_for_noartist = False
break
if wrong_role_for_noartist:
pass
#print(self.contentbuffer.strip(), " -- https://www.discogs.com/release/%s" % str(self.release))
'''
if settings.credits:
role_data = artist.text
if role_data is None:
continue
role_data = role_data.strip()
if role_data != '':
if '[' not in role_data:
roles = map(lambda x: x.strip(), role_data.split(','))
for role in roles:
if role == '':
continue
if role not in credit_roles:
print_error(counter, f'Role \'{role}\' invalid', release_id)
counter += 1
else:
# sometimes there is an additional description
# in the role in between [ and ]. TODO: rework this
rolesplit = role_data.split('[')
for rs in rolesplit:
if ']' in rs:
rs_tmp = rs
while ']' in rs_tmp:
rs_tmp = rs_tmp.split(']', 1)[1]
roles = map(lambda x: x.strip(), rs_tmp.split(','))
for role in roles:
if role == '':
continue
# ugly hack because sometimes the extra
# data between [ and ] appears halfway the
# words in a role, sigh.
if role == 'By':
continue
if role not in credit_roles:
print_error(counter, f'Role \'{role}\' invalid', release_id)
counter += 1
if artist_id == 0:
print_error(counter, f'Artist \'{artist_name}\' not in database', release_id)
counter += 1
elif child.tag == 'companies':
if year is not None:
for companies in child:
for company in companies:
if company.tag == 'id':
if company.text:
company_nr = int(company.text)
if settings.labels:
# check for:
# https://www.discogs.com/label/205-Fontana
# https://www.discogs.com/label/7704-Philips
if company_nr == 205:
if year < 1957:
print_error(counter, f'Label (wrong year {year})', release_id)
counter += 1
elif company_nr == 7704:
if year < 1950:
print_error(counter, f'Label (wrong year {year})', release_id)
counter += 1
if settings.pressing_plants:
'''
## https://www.discogs.com/label/34825-Sony-DADC
if company_nr == 34825:
if year < 2000:
print_error(counter, f'Pressing Plant Sony DADC (wrong year {year})', release_id)
counter += 1
'''
for pl in discogssmells.plants:
if company_nr == pl[0]:
if year < pl[1]:
print_error(counter, f'Pressing Plant {pl[2]} (possibly wrong year {year})', release_id)
counter += 1
break
for pl in discogssmells.plants_compact_disc:
if company_nr == pl[0]:
if 'CD' in formats:
if year < pl[1]:
print_error(counter, f'Pressing Plant {pl[2]} (possibly wrong year {year})', release_id)
counter += 1
break
elif child.tag == 'formats':
for release_format in child:
current_format = None
# first check the attributes
for (key, value) in release_format.items():
if key == 'name':
if value == 'CD':
is_cd = True
formats.add(value)
current_format = value
'''
# https://en.wikipedia.org/wiki/Phonograph_record#Microgroove_and_vinyl_era
if current_format == 'Vinyl' and year is not None:
if year < 1948:
print(counter, f'Impossible year '{year}' for vinyl', release_id)
counter += 1
'''
elif key == 'qty':
if num_formats == 0:
num_formats = max(num_formats, int(value))
else:
num_formats += int(value)
elif key == 'text':
if value != '':
value_lower = value.lower().strip()
if settings.spars:
tmp_spars = value_lower
tmp_spars = tmp_spars.translate(SPARS_TRANSLATE)
if tmp_spars in discogssmells.validsparscodes:
print_error(counter, f"Possible SPARS Code ({value}, in Format)", release_id)
counter += 1
if settings.label_code:
if value_lower.startswith('lc'):
if discogssmells.labelcodere.match(value_lower) is not None:
print_error(counter, f"Possible Label Code ({value}, in Format)", release_id)
counter += 1
if settings.cd_plus_g:
if value_lower == 'cd+g':
print_error(counter, 'CD+G (in Format)', release_id)
counter += 1
if value_lower == 'DMM':
if current_format != 'Vinyl':
print_error(f'DMM ({current_format}, in Format)', release_id)
counter += 1
# then process any children
for ch in release_format:
if ch.tag == 'descriptions':
for description in ch:
if 'Styrene' in description.text:
pass
elif child.tag == 'genres':
for genre in child:
genres.add(genre.text)
elif child.tag == 'identifiers':
# Here things get very hairy, as every check
# potentially has to be done multiple times: once
# in the 'correct' field (example: rights society
# in a 'Rights Society' field) and then in all the
# other fields as well.
#
# The checks in the 'correct' field tend to be more
# thorough, as the chances that this is indeed the
# correct field are high.
#
# Sometimes the "description" attribute needs to be
# checked as well as people tend to hide information
# there too.
for identifier in child:
identifier_type = identifier.get('type')
# ASIN
if settings.asin:
if identifier_type == 'ASIN':
try:
value = identifier.get('value').strip()
except:
continue
# temporary hack, move to own configuration option
asin_strict = False
if not asin_strict:
tmpasin = value.replace('-', '')
else:
tmpasin = value
if not len(tmpasin.split(':')[-1].strip()) == 10:
print_error(counter, 'ASIN (wrong length)', release_id)
counter += 1
else:
description = identifier.get('description', '').strip()
if description.startswith('asin'):
print_error(counter, f'ASIN (in {identifier})', release_id)
counter += 1
# creative commons, check value and description
if settings.creative_commons:
try:
description = identifier.get('description', '').strip().lower()
value = identifier.get('value', '').strip().lower()
except:
continue
if 'creative commons' in description:
print_error(counter, 'Creative Commons reference', release_id)
counter += 1
if 'creative commons' in value:
print_error(counter, 'Creative Commons reference', release_id)
counter += 1
if country == 'Czechoslovakia' and year is not None:
if settings.czechoslovak_dates:
try:
description = identifier.get('description', '').strip().lower()
value = identifier.get('value', '').strip().lower()
except:
continue
if 'date' in description:
manufacturing_date_res = re.search(r"(\d{2})\s+\d$", value)
if manufacturing_date_res is not None:
manufacturing_year = int(manufacturing_date_res.groups()[0])
if manufacturing_year < 100:
manufacturing_year += 1900
if manufacturing_year > year:
print_error(counter, 'Czechoslovak manufacturing date (release year wrong)', release_id)
counter += 1
# possibly this check makes sense, but not always
elif manufacturing_year < year and settings.czechoslovak_dates_strict:
print_error(counter, 'Czechoslovak manufacturing date (release year possibly wrong)', release_id)
counter += 1
# Depósito Legal, only check for releases from Spain
if country == 'Spain':
if settings.deposito_legal:
try:
value = identifier.get('value').strip()
except:
continue
if identifier_type == 'Depósito Legal':
deposito_found = True
if value.endswith('.'):
print_error(counter, "Depósito Legal (formatting)", release_id)
counter += 1
if year is not None:
# now try to find the year
deposito_year = None
if value.endswith('℗'):
print_error(counter, "Depósito Legal (formatting, has ℗)", release_id)
counter += 1
# ugly hack, remove ℗ to make at least be able to do some sort of check
year_value = value.rsplit('℗', 1)[0].strip()
# several separators seen in the DL codes,
# including some Unicode ones.
# TODO: rewrite/improve
for sep in ['-', '–', '/', '.', ' ', '\'', '_']:
try:
deposito_year_text = year_value.rsplit(sep, 1)[-1]
if sep == '.' and len(deposito_year_text) == 3:
continue
if '.' in deposito_year_text:
deposito_year_text = deposito_year_text.replace('.', '')
deposito_year = int(deposito_year_text)
if deposito_year < 100:
# correct the year. This won't work correctly after 2099.
if deposito_year <= CURRENT_YEAR - 2000:
deposito_year += 2000
else:
deposito_year += 1900
break
except ValueError:
pass
# TODO, also allow (year), example: https://www.discogs.com/release/265497
if deposito_year is not None:
if deposito_year < 1900:
print_error(counter, f"Depósito Legal (impossible year: {deposito_year})", release_id)
counter += 1
elif deposito_year > CURRENT_YEAR:
print_error(counter, f"Depósito Legal (impossible year: {deposito_year})", release_id)
counter += 1
elif year < deposito_year:
print_error(counter, "Depósito Legal (release date earlier)", release_id)
counter += 1
else:
print_error(counter, "Depósito Legal (year not found)", release_id)
counter += 1
else:
value_lower = value.lower()
try:
description = identifier.get('description', '').strip()
except:
continue
description_lower = description.lower()
if not deposito_found:
for depositovalre in discogssmells.depositovalres:
if depositovalre.match(value_lower) is not None:
print_error(counter, f"Depósito Legal (in {identifier_type})", release_id)
counter += 1
deposito_found = True
break
# check for a DL hint in the description field
if description != '':
if not deposito_found:
for d in discogssmells.depositores:
result = d.search(description_lower)
if result is not None:
print_error(counter, f"Depósito Legal (in {identifier_type} (description))", release_id)
counter += 1
deposito_found = True
break
if not deposito_found and settings.debug:
# print descriptions for debugging. Careful.
print(f'Depósito Legal debug: {release_id}, {description}')
# sometimes the depósito value itself can be
# found in the free text field
if not deposito_found:
for depositovalre in discogssmells.depositovalres:
deposres = depositovalre.match(description_lower)
if deposres is not None:
print_error(counter, f"Depósito Legal (in {identifier_type} (description))", release_id)
counter += 1
deposito_found = True
break
# Greek license numbers
if country == 'Greece':
if settings.greek_license:
try:
description = identifier.get('description', '').strip().lower()
value = identifier.get('value', '').strip()
except:
continue
if "license" in description.strip() and year is not None:
for sep in ['/', ' ', '-', ')', '\'', '.']:
try:
license_year = int(value.rsplit(sep, 1)[1])
if license_year < 100:
license_year += 1900
if license_year > year:
print_error(counter, 'Greek license year wrong', release_id)
counter += 1
break
except:
pass
# India PKD
if country == 'India':
if settings.indian_pkd:
try:
value = identifier.get('value', '').lower()
except:
continue
if 'pkd' in value or "production date" in value:
if year is not None:
# try a few variants
pkdres = pkd_re.search(value)
if pkdres is not None:
pkdyear = int(pkdres.groups()[0])
if pkdyear < 100:
# correct the year. This won't work correctly after 2099.
if pkdyear <= CURRENT_YEAR - 2000:
pkdyear += 2000
else:
pkdyear += 1900
if pkdyear < 1900 or pkdyear > CURRENT_YEAR:
print_error(counter, 'Indian PKD (impossible year)', release_id)
counter += 1
elif year < pkdyear:
print_error(counter, 'Indian PKD (release date earlier)', release_id)
counter += 1
else:
print_error(counter, 'India PKD code (no year)', release_id)
counter += 1
# ISRC
if settings.isrc:
try:
description = identifier.get('description', '').strip()
except:
continue
description_lower = description.lower()
if identifier_type == 'ISRC':
# Check the length of ISRC fields. According to the
# specifications these should be 12 in length. Some
# ISRC identifiers that have been recorded in the
# database cover a range of tracks. These will be
# reported as wrong ISRC codes. It is unclear what
# needs to be done with those.
# first get rid of cruft
value_upper = identifier.get('value').strip().upper()
isrc_tmp = value_upper
if isrc_tmp.startswith('ISRC'):
isrc_tmp = isrc_tmp.split('ISRC')[-1].strip()
if isrc_tmp.startswith('CODE'):
isrc_tmp = isrc_tmp.split('CODE')[-1].strip()
# Chinese ISRC, see https://www.discogs.com/forum/thread/799845
if '/A.J6' in isrc_tmp:
isrc_tmp = isrc_tmp.rsplit('/', 1)[0].strip()
# replace a few characters
isrc_tmp = isrc_tmp.translate(ISRC_TRANSLATE)
if len(isrc_tmp) != 12:
print_error(counter, 'ISRC (wrong length)', release_id)
counter += 1
else:
valid_isrc = True
if isrc_tmp in isrcs_seen:
print_error(counter, f'ISRC (duplicate {isrc_tmp})', release_id)
counter += 1
else:
isrcs_seen.add(isrc_tmp)
isrcres = re.match(r"\w{5}(\d{2})\d{5}", isrc_tmp)
if isrcres is None:
print_error(counter, 'ISRC (wrong format)', release_id)
counter += 1
valid_isrc = False
if year is not None and valid_isrc:
isrcyear = int(isrcres.groups()[0])
if isrcyear < 100:
# correct the year. This won't work
# correctly after 2099.
if isrcyear <= CURRENT_YEAR - 2000:
isrcyear += 2000
else:
isrcyear += 1900
if isrcyear > CURRENT_YEAR:
print_error(counter, f'ISRC (impossible year: {isrcyear})', release_id)
counter += 1
elif year < isrcyear:
print_error(counter, f'ISRC (date earlier: {isrcyear})', release_id)
counter += 1
# check the descriptions
# TODO: match with the actual track list
if description_lower != '':
if description_lower in isrc_descriptions_seen:
print_error(counter, f'ISRC code (description reuse: {description})', release_id)
counter += 1
isrc_descriptions_seen.add(description_lower)
else:
# specifically check the description
if description_lower != '':
if description_lower.startswith('isrc'):
print_error(counter, f'ISRC Code (in {identifier_type})', release_id)
counter += 1
elif description_lower.startswith('issrc'):
print_error(counter, f'ISRC Code (in {identifier_type})', release_id)
counter += 1
else:
for isrc in discogssmells.isrc_ftf:
if isrc in description_lower:
print_error(counter, f'ISRC Code (in {identifier_type})', release_id)
counter += 1
break
# Label Code
if settings.label_code:
try:
value = identifier.get('value').lower()
description = identifier.get('description', '').lower()
except:
continue
if identifier_type == 'Label Code':
# check how many people use 'O' instead of '0'
if value.startswith('lc'):
if 'O' in value:
print_error(counter, "Spelling error (in Label Code)", release_id)
counter += 1
if discogssmells.labelcodere.match(value) is None:
print_error(counter, "Label Code (value)", release_id)
counter += 1
else:
if value.startswith('lc'):
if discogssmells.labelcodere.match(value) is not None:
print_error(counter, f"Label Code (in {identifier_type})", release_id)
counter += 1
if description in discogssmells.label_code_ftf:
print_error(counter, f"Label Code (in {identifier_type})", release_id)
counter += 1
# Matrix / Runout
if settings.matrix:
try:
value = identifier.get('value')
except:
continue
if identifier_type == 'Matrix / Runout':
for pdmc in discogssmells.pmdc_misspellings:
if pdmc in value:
print_error(counter, 'Matrix (PDMC instead of PMDC)', release_id)
counter += 1
if year is not None:
if 'MFG BY CINRAM' in value and '#' in value and 'USA' not in value:
cinramres = re.search(r'#(\d{2})', value)
if cinramres is not None:
cinramyear = int(cinramres.groups()[0])
# correct the year. This won't work correctly after 2099.
if cinramyear <= CURRENT_YEAR - 2000:
cinramyear += 2000
else:
cinramyear += 1900
if cinramyear > CURRENT_YEAR:
print_error(counter, f'Matrix (impossible year: {year})', release_id)