aboutsummaryrefslogtreecommitdiff
path: root/sbosrcarch
blob: e7f1a2b5806c2f366ccd3291d29a68051d09018d (plain)
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
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
#!/usr/bin/perl

# choose your poison:
our $DEBUG_HTTP = 0;
#our $DEBUG_HTTP = 1;

# hack to work around the fact that the download filenames for
# a few builds are the same filename, but different files.
# this list could be populated automatically, but it wouldn't have
# changed in the past 3 years, so might as well hard-code it.
our %url_filename_collisions = (
	'http://hgwdev.cse.ucsc.edu/~kent/exe/opteron/blatSuite.34.zip' => 'blatSuite.34.zip.x86_64',
	'https://www.perforce.com/downloads/perforce/r18.1/bin.linux26x86_64/p4' => 'p4.x86_64',
	'https://www.perforce.com/downloads/perforce/r18.1/bin.linux26x86_64/p4d' => 'p4d.x86_64',
	'https://ftp.mirrorservice.org/sites/download.salixos.org/x86_64/extra-14.2/source/libraries/p4api/p4api.tgz' => 'p4api.tgz.x86_64'
);

# TODO create_mode stats are wrong

# TODO based on feedback from ttkp and pink_mist on IRC:
# - IPC::Open3 instead of open my $fh, "wget ...|"? At least use
#   open my $fh, "-|", "wget", @args or such, to avoid quoting issues.
#   However, avoiding the shell means being unable to redirect
#   stderr & stdout to the same place. Hm.

# Also, stuff added with "add" sometimes ends up as separate files
# instead of hardlinks. Not sure how to replicate this. It hasn't
# actually happened in ages, so probably I fixed it while working
# on something else...

# Ideas for future features:
# - autopurge option for update. It only needs to purge the dirs that
#   got updated, so should be quick.... except what happens if two builds
#   use the same source file, one gets updated and the other doesn't? if
#   the purge doesn't parse all the info files in the repo, it can't know
#   not to delete the by-md5 in that case. Ugh.

=pod

=head1 NAME

sbosrcarch - Create and maintain an archive of source code for SBo builds

=head1 SYNOPSIS

sbosrcarch [-c configfile] <create|update|trim|purge|check>

sbosrcarch [-c configfile] add [-f] [<category/prgnam>] [<file> ...]

sbosrcarch [-c configfile] rm <category/prgnam>

=head1 DESCRIPTION

sbosrcarch creates and maintains an archive of source code files linked
to by DOWNLOAD= and DOWNLOAD_x86_64= URLs in SlackBuilds.org .info files.

The archive contains only source code from upstream sites. No content
from slackbuilds.org itself is included.

Since a full archive would be pretty large (45GB or so), sbosrcarch
allows limiting the size of the archive (but only indirectly, by
limiting the max file size it will download). This means we won't have
a full archive of every source tarball, but even a partial mirror is
still useful.

Rough guideline for choosing filesize:

 Max filesize | Approx. total archive size | Coverage
        1.0M  |                    803.1M  |  68%
        2.0M  |                      1.4G  |  77%
        5.0M  |                      2.7G  |  85%
       10.0M  |                      4.3G  |  90%
       20.0M  |                      6.6G  |  93%
       35.0M  |                      8.9G  |  95%
       50.0M  |                     11.6G  |  96%
      100.0M  |                     16.6G  |  98%
   unlimited  |                     43.0G  | 100%

Note: these numbers will tend to increase over time, as the SBo repository
grows. To be safe, add 25% or so to the total sizes above.

"Coverage" is the percentage of all the URLs in all the .info files
that will be kept in this archive. Notice that about 60% of the storage
space is eaten up by 2% of the files, in the unlimited case. These
large files are mostly games, if that influences your decision any.

=head1 OPTIONS

=over

=item B<-c> I<config-file>

Read specified config file instead of searching in the default locations
for it. See B<CONFIG FILE> section below for default. This option must
appear first on the command line, if used.

=item B<create>

Create archive. Used for initial archive creation, and for downloading
new files to an existing archive when the size limit ($maxfilemegs,
see B<CONFIG FILE>) is increased.

Should be run interactively, from a login shell. Takes a long time to
run and uses a lot of bandwidth. Log output goes to stdout, and is pretty
verbose (redirecting to a file is recommended).

If the archive already exists, existing files will be kept instead of
being re-downloaded (provided of course their md5sums are correct).

=item B<update>

Update archive, by checking the SBo git log and parsing any .info files that
have changed since the last create or update.

Should be run daily or weekly as a cron job.

If there are are few or no changed download URLs, update should run
quickly and not eat many resources. For each new URL, the file is
downloaded and added to the archive, but the old file is *not* deleted
(use 'sbosrcarch purge' to do that).

=item B<purge> I<[-r|--rebuild]>|I<[-f|--fake]>

Purge files from the archive that are no longer referenced by any
.info file. Should be run monthly or quarterly as a cron job. This is
more resource-intensive than an update, as it must read and parse every
.info file in the SBo repository.

If -r or --rebuild is given, the entire by-md5 tree is deleted and
recreated. This shouldn't be needed unless $symlinks (see B<CONFIG FILE>)
is changed, or something catastrophic happens to the by-md5 tree. Don't
do this automatically from cron: while it's running, your archive users
will see an incomplete by-md5 tree.

If -f or --fake is given, a list of files to be purged will be produced,
but nothing will actually be deleted. This option B<cannot> be combined
with -r/--rebuild, and no warning will be given if it's tried: whichever
option occurs first will take effect, and the other one will be ignored!

=item B<trim>

Gets rid of files that are in the archive, but are larger than the size
limit. Should be run manually after lowering $maxfilemegs; there's no
reason to run it any other time.

=item B<check> I<[-v]>

Checks the integrity and coverage of the archive. Reports at least these conditions:

 - dangling symlinks
 - invalid md5sums
 - files present in only one of by-name or by-md5 but not the other
 - count extraneous files in the tree (or list, with -v)
 - generates a status report, giving the total size and coverage.
 - lists all SlackBuilds not covered by the archive.

Will not modify the archive in any way, but might recommend fixes.

With -v, lists all extraneous files: those that are present in the
archive, but not mentioned in any .info files. These are usually older
versions of the source, left over when the build was updated and the
new sources added to the archive.

<check> is quite I/O and CPU intensive, as it must read and md5sum every
file in the archive.

Blacklisted builds are not included in the status report, so the "Total
SlackBuilds" number might not match the number of builds in the git repo.
This is a feature (otherwise it would be impossible to see 100% coverage).

=item B<status> I<[-v]>

Checks the coverage of the archive. Like B<check>, but doesn't md5sum the
files (it just assumes they're correct). Use this as a quick way to get
a status report.

=item B<add> I<[-f] <category/prgnam> [<file> ...]>

Manually add (possibly already downloaded) files to the archive.

Use -f to skip the size limit checking, so your archive can include a
few large files (perhaps because they're for builds you maintain).

Files added this way will still be deleted by 'sbosrcarch trim', if
they're larger than the limit.

This is intended to let the mirror operator keep a few large files (over
the maxfilemegs limit), or save bandwidth by using already-downloaded
copies (e.g. of stuff that was built recently).

If files are given after the category/prgnam argument, they will be
used instead of downloading the URLs in the .info file (provided their
md5sums match the .info file). Size limits are not checked for files
added this way.

=item B<add> I<<file> [...]>

Manually add local file(s) to the archive. As above, but the
category/prgnam is discovered by parsing all the .info files and
matching md5sums. This is a good bit slower, but it can handle files
for many different category/prgnam at once. It's especially useful if
you already have an archive of SBo sources that you want to convert to
sbosrcarch format.

The -f option is not supported (or needed) with this form of the add
command.

=item B<rm> I<<category/prgnam>>

Manually remove files from the archive. All the files referenced by the
.info file for <category>/<prgnam> will be removed.

...but the next update will re-add anything you remove, if it's less than
the size limit. Mostly this is useful for manually-added files that are
over the limit.

=back

=head1 CONFIG FILE

By default, B<sbosrcarch.conf> (or B<.sbosrcarch.conf>) is the config
file for sbosrcarch. It's searched for under both names in the current
directory, the user's home directory, /etc/sbosrcarch, and /etc (in
order).

To specify a different config file, use B<-c> -I<config-file>.

Config file options are documented in comments in the sample config file.

=head1 FILES

The archive created by sbosrcarch consists of two top-level directories
called B<by-name> and B<by-md5>. All files are present in both hierarchies
(but the by-md5 tree is hard or symbolic links, to save space).

B<by-name> is organized by the familiar category and PRGNAM, like SBo
itself. Example:

  by-name/network/ifstatus/ifstatus-v1.1.0.tar.gz

This makes it easy for humans to browse the archive and find the source
file they're looking for.

B<by-md5> contains the same files, but organized in a hierarchy based on
the md5sum of the file, for automated systems to easily find the exact
file needed. The same file as the example above would be found at:

by-md5/f/4/f4d413f880754fd6677290160f8bc5d7/ifstatus-v1.1.0.tar.gz

Notice there are two layers of subdirectory, named after the first two
hex digits in the md5sum. Also, notice that the actual SlackBuilds and
.info files are not present in the archive.

There is one other directory of files used/maintained by sbosrcarch:
a git clone of SBo's master git branch. This is cloned and updated
automatically as needed, and shouldn't need to be messed with. If you
need a git clone of SBo for some other purpose, create a separate one
to avoid confusing sbosrcarch with your changes and pulls.

=head1 SERVER CONFIGURATION

If you're planning to host a public archive, you'll need to make the
$archivedir available via whatever protocols you support (HTTP, FTP,
rsync, etc). This is the directory containing B<by-name> and B<by-md5>.
The git clone directory doesn't need to be served to the public.

TODO: example Apache, proftpd, etc configs for serving up the archive.

=head1 CLIENT-SIDE EXAMPLE

The following shell script is intended to be run from an extracted
SlackBuild directory. It attempts to download the source files from
the by-md5/ tree of the archive.


	#!/bin/sh
	
	# sbosrcarch client example script. tested with bash, ash, zsh, ksh.
	
	# path to the root of your archive (contains the by-name and
	# by-md5 directories):
	ARCHIVE=http://yoursite.com/sbosrc
	
	. $( pwd )/*.info || ( echo "no .info file in current dir" 1>&2 && exit 1 )
	
	if [ "$ARCH" = "x86_64" -a "$MD5SUM_x86_64" != "" ]; then
		MD5SUM="$MD5SUM_x86_64"
		DOWNLOAD="$DOWNLOAD_x86_64"
	fi
	
	set $MD5SUM
	
	for url in $DOWNLOAD; do
		file="$( echo "$url" | sed 's,.*/,,' )"
		md5=$1
		shift
	
		echo "Downloading $file ($md5)"
	
		a=$( echo $md5 | cut -b1 )
		b=$( echo $md5 | cut -b2 )
	
		wget -O "$file" "$ARCHIVE/by-md5/$a/$b/$md5/$file"
	
		if [ -e "$file" -a "$( md5sum "$file" | cut -d' ' -f1 )" = "$md5" ]; then
			echo "downloaded, md5sum matches"
		else
			echo "download failed"
			fail=1
		fi
	done
	
	if [ "$fail" != "1" ]; then
		echo "All files found and downloaded successfully"
		exit 0
	else
		exit 1
	fi

### end of script

The perldoc format requires literal code blocks to be prefixed with
a tab on each line, so copy/pasting the above script will result in a
mess. Instead, extract it with:

	sed -n '/^\t#!\/bin\/sh/,/^### end/p' sbosrcarch | cut -f2- > script.sh

=head1 NOTES

sbosrcarch is written in perl, and is intended to work on at least
Slackware 13.0 through 14.1, using only perl modules that ship with the OS
(so no CPAN dependencies), plus an external curl or wget executable for
downloading files. If you want to run it on some other OS, it might need
some extra packages installed and/or some slight porting work. If you want
to keep a SBo source archive on your non-Slackware server, it might be
easier to just rsync someone else's (that they build using this script).

Note that there's no need to run sbosrcarch as root. In fact, it's
recommended not to. Good choices for a user to run it as:
 - your everyday user you log in as
 - apache
 - nobody

=head1 BUGS/LIMITATIONS

Plenty of these, see FIXME TODO XXX comments in the code. Here are some
that I'm not planning to address any time soon:

No threading. Not likely to change. It would be possible to spawn wget
or curl processes in the background, but I'm not going to complicate it
that way. It would mainly be useful for create mode, and hopefully each
archive site only needs to do that once.

Anything that checks referer header or otherwise tries to stop automated
downloads, will stop us. This isn't really a bug (sbopkg can't handle
them either). Usually the README will say "you must download the file
with a browser" or such. You can still download the file manually
and use "sbosrcarch add category/prgnam filename.tar.gz" to add it
to the archive...  but please pay attention to licensing! Some files
(e.g. Oracle's Java) don't allow redistribution, so please don't include
them in your archive.

For URLs that won't give us a Content-Length header, we can't determine
the file size. If $maxfilemegs is zero (unlimited), this doesn't matter:
everything gets downloaded. If there's a size limit, and we can't
determine the size, we download them 'incrementally', stopping the
download if the file size limit is set. Unfortunately this can waste a
lot of bandwidth, if the limit is high.

=head1 AUTHOR

B. Watson <yalhcru@gmail.com>

=cut

# use only modules that ship with Slackware, which pretty much
# means only modules that ship with core perl.
# use the 'legacy' 2.0 API for File::Path, since we want to support
# the older perl in Slackware 13.0.
use warnings;
use strict; # I hate strict, but I'll use it anyway...
use File::Temp qw/tempfile tempdir/;
use File::Find;
use Digest::MD5;
use Net::FTP;
use POSIX 'getcwd';
use File::Path qw/mkpath rmtree/;
use File::Copy qw/copy move/;

# 20151016 bkw: migrating to curl
our $use_curl = 1;

our($sbogiturl, $sbogitdir, $archivedir, $maxfilemegs, $wget,
    $wgetargs, $symlinks, $wgetrc_contents, $wgetrc, %user_agent_overrides,
    @trim_empty_dirs, $skipcount, $urlcount, $archivecount,
    $attemptcount, $failcount, $dlcount, $nowarchived, $coverage,
    $purgebytes, $purgefiles, $trimcount, $trimbytes,
    %keep_filenames, %keep_md5sums, $fake_purge);
our ($curl, $curlopts);
our (%whitehash, %blackhash, $use_bwlist);
our @whitelist = ();
our @blacklist = ();
our $quickcheck; # used by check_mode() and its *wanted helpers
our $verbosecheck;
our $extraneous_byname = 0;
our $extraneous_bymd5 = 0;

our %infofilecount;
our %parsedinfo;
our %allmd5sums;
our $symlinkcount = 0;
our $hardlinkcount = 0;
our $filecount = 0;
our $md5_filecount = 0;
our $filebytes = 0;
our $actualfilecount = 0;
our $totalfiles = 0;

sub read_config {
	my $conf_used;

	my @configdirs = (
			".",
			$ENV{HOME},
			"/etc/sbosrcarch",
			"/etc",
	);

	if(@ARGV && $ARGV[0] =~ /^-c(.*)$/) {
		shift @ARGV;
		if($1) {
			$conf_used = $1;
		} elsif(@ARGV && $ARGV[0]) {
			$conf_used = shift @ARGV;
		} else {
			die "-c option requires argument\n";
		}
		do $conf_used;
		die "$conf_used: $!\n" if $!;
		die "reading config file $conf_used: $@" if $@;
	} else {
		for my $dir (@configdirs) {
			for my $file (qw/.sbosrcarch.conf sbosrcarch.conf/) {
				$_ = "$dir/$file";
				next unless -e $_;
				do $_;
				next if $!;
				die "reading config file $_: $@" if $@;
				$conf_used = $_;
				last;
			}
		}
	}

	if($conf_used) {
		print "read config file: $conf_used\n";
	} else {
		die "can't find .sbosrcarch.conf or sbosrcarch.conf in any of the\n" .
			"following directories (and no -c option), giving up:\n" .
			join ("\n", @configdirs) . "\n" .
			"\nTry 'sbosrcarch --help' or 'perldoc sbosrcarch' for help.\n";
	}

# required stuff in the conf file:
	die "config file missing \$sbogiturl\n" unless defined $sbogiturl;
	die "config file missing \$sbogitdir\n" unless defined $sbogitdir;
	die "config file missing \$archivedir\n" unless defined $archivedir;

# not required, but warn if it's missing:
	if((not defined $maxfilemegs) || ($maxfilemegs < 0)) {
		print "config file missing/invalid \$maxfilemegs, defaulting to 10\n";
		$maxfilemegs = 10;
	}

# quietly use defaults if missing:
	$wget = "wget" unless defined $wget;
	$curl = "curl" unless defined $curl;
	$use_curl = 1 unless defined $use_curl;
	$wgetargs = "" unless defined $wgetargs;
	$symlinks = "" unless defined $symlinks;

	if($use_curl && !defined($curlopts)) {
		die "\$\$use_curl is true, but curlopts is missing from config file\n";
	}

	if(not defined $wgetrc_contents) {
		$wgetrc_contents = <<EOF;
robots = off
user_agent = Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)
check_certificate = off
content_disposition = off
EOF
	}

	if(not %user_agent_overrides) {
		%user_agent_overrides = (
			qr/(?:sourceforge|sf)\.net/ => 'wget',
		);
	}

# white and black lists are configured as arrays, but internally
# stored as hashtables for quicker lookups.
	$whitehash{$_}++ for @whitelist;
	for(@blacklist) {
		if($whitehash{$_}) {
			warn "$_ in both \@blacklist and \@whitelist, ignoring\n";
			delete $whitehash{$_};
			next;
		}

		$blackhash{$_}++;
	}
}

# in: ($category, $prgnam) *or* "$category/$prgnam" *or" "./$cat/$prg/$prg.info"
# out: ($category, "$category/$prgnam")
sub catbuild {
	my($cat, $prgnam);
	if(defined($_[1])) {
		($cat, $prgnam) = @_;
	} else {
		$_[0] =~ s,^\./,,;
		$_[0] =~ s,/[^/]*\.info$,,;
		($cat, $prgnam) = split /\//, $_[0];
	}
	return ($cat, $cat . '/' . $prgnam);
}

sub whitelisted {
	return 0 unless $use_bwlist;
	my ($cat, $build) = catbuild(@_);
	return 1 if $whitehash{$build};
	return 1 if $whitehash{$cat} && !$blackhash{$build};
	return 0;
}

sub blacklisted {
	return 0 unless $use_bwlist;
	my ($cat, $build) = catbuild(@_);
	return 1 if $blackhash{$build};
	return 1 if $blackhash{$cat} && !$whitehash{$build};
	return 0;
}

# url_to_filename, gets the filename part of a URL (after the last slash)
# and un-escapes any %XX sequences.
# Note: we *don't* do plus-to-space conversion here, as that's only
# for CGI params, not URLs in general. There are quite a few files
# called e.g. "c++-utils.tar.gz" that would get broken by it.
sub url_to_filename {
	my $u = shift;

	my $v = $url_filename_collisions{$u};
	return $v if $v;

	$u =~ s,.*/,,;
	$u =~ s,%([0-9A-F]{2}),chr(hex($1)),ge;
	return $u;
}

# parse a single .info file, return a hashref where keys = URL(s)
# and values are their md5sums.
sub parse_info {
	local $/ = "";
	my $file = shift;

	open my $fh, "<", $file or do {
		warn "$file: $!";
		return undef;
	};

	my $got = <$fh>;

	$got =~ s/\\\s*\n//gs; # join \ continuation lines
	$got =~ s/[ \t]+/ /g;  # condense whitespace

	my @urllines = ($got =~ /DOWNLOAD(?:_x86_64)?="\s*((?:htt|ft)[^"]+)"/g);
	my @md5lines = ($got =~ /MD5SUM(?:_x86_64)?="\s*([0-9a-f][^"]+)"/g);
	my @urls = split " ", join " ", @urllines;
	my @md5s = split " ", join " ", @md5lines;

	my %ret;

	for(@urls) {
		my $m = shift @md5s;
		#next if /^un(test|support)ed$/i; # no longer need
		print "bad URL in $file (backtick)\n", next if /`/; # backticks should never occur!
		$ret{$_} = $m;
	}

	close $fh;
	return \%ret;
}

# the download_* subs return:
# 0 - file too big (so skip it)
# positive integer - file size
# undef - download error (404, failed DNS, etc).
# FIXME: the above isn't really true, and the calling code doesn't
# check the return values as it should.

# 20151016 bkw: migrating to curl
sub curl_download_http {
	my $url = shift;
	my $filename = url_to_filename($url);
	our($curl, $curlopts);

	my $tmpdir = $ENV{TMPDIR} || $ENV{TMP} || "/tmp";
	my ($fh, $outfile) = tempfile("curl.out.XXXXXXXX", DIR => $tmpdir, UNLINK => 1);
	close $fh;

	# first, dump the headers only. --head -X GET makes curl use a GET
	# request, but act like HEAD (exit after headers are read).
	# for github URLs, we retry if we got no Content-Length. for whatever
	# reason, if the length is missing in a request, it'll generally be
	# there the next time around... or the time after that (3 tries here).
	# bitbucket seems to do the same thing.

	my $httpstatus;
	my $httpstatusline;
	my $size;

	if($maxfilemegs) { # only check size if there's a size limit!
		# TODO: do this bit in download_http, not here (so it happens for wget too)
		# (either that, or rip out the wget code)
		my $tries = ($url =~ /github\.com|bitbucket\.org/) ? 3 : 1;

		for(1..$tries) {
			my $cmd =
				  "$curl $curlopts "  .
					user_agent($url) .
					" --head -X GET " .
					wget_quote_url($url) .
					" 2>$outfile |";
			warn "* $cmd\n" if $DEBUG_HTTP;
			open my $fh, $cmd or die $!;

			local $/ = "\r\n";
			while(<$fh>) {
				chomp;
				warn "* $_\n" if $DEBUG_HTTP;

				$httpstatus = $1, $httpstatusline = $_ if /^HTTP\/\S+\s+(\d+)/;

				# grr. forja.rediris.es returns Content-length (lowercase L)
				$size = $1 if /^Content-Length:\s+(\d+)/i;
			}
			close $fh;
			last if $size;
			sleep 2;
		}

		if(not defined $httpstatus) {
			open my $fh, "<$outfile";
			while(<$fh>) {
				print "! $_";
			}
			close $fh;
			return undef; # connection refused, DNS lookup failed, etc
		}

		if($httpstatus ne "200") {
			print "! $httpstatusline\n";
			return undef;
		}

		if(not defined($size)) {
#			print "? couldn't determine file size, skipping\n";
#			return undef;
			return curl_incremental_download($url);
		} elsif(toobig($size)) {
			printf "+ file too large: %0.2fMB\n", $size / (1024 * 1024);
			$skipcount++;
			return undef;
		}
	}

	# now download the file: either the size is known to be under the
	# limit, or else there was no limit.
	$attemptcount++;
	my $cmd = "$curl $curlopts "  .
			user_agent($url) .
			" -o'$filename' --retry 2 " .
			wget_quote_url($url) .
			" -D $outfile.hdr " .
			" > $outfile 2>&1";
	warn "* $cmd\n" if $DEBUG_HTTP;
	my $retval = system($cmd);

	print "curl retval==$retval\n" if $DEBUG_HTTP;

	if($retval != 0) {
		open my $fh, "<$outfile";
		while(<$fh>) {
			print " ! $_";
		}
		close $fh;
	}

	open $fh, "<$outfile.hdr";
	while(<$fh>) {
		$_ =~ s,[\r\n],,g;
		next unless /^HTTP\/\S+\s+(\d+)/;
		$httpstatusline = $_, $httpstatus = $1;
	}
	close $fh;

	unlink($outfile);
	unlink("$outfile.hdr");

	if(defined $httpstatus && ($httpstatus ne "200")) {
		print "! $httpstatusline\n";
		unlink $filename;
		return undef;
	}

	if(-f $filename) {
		$size = -s _;
		warn "* $filename exists, $size bytes\n" if $DEBUG_HTTP;
	}

	return $size;
}

# The calling code has already checked the HTTP status, and it's
# known to be 200 OK... but the server refuses to give us a Content-Length
# header. This happens for less than 1% of the URLs. What we'll do
# is start the download, writing to the output file... and either it
# finishes before the limit, or we stop & rm the file when we hit
# the limit.
# This sub doesn't report curl errors.
sub curl_incremental_download {
	my $url = shift;
	my $filename = url_to_filename($url);
	my $maxbytes = $maxfilemegs * 1024 * 1024;
	my $buffer;
	my $bufsiz = 16 * 1024;
	my $bytecount = 0;
	my  $readbytes;

	print "? couldn't determine file size, trying incremental download\n";

	open my $fh, "$curl $curlopts --no-show-error " . wget_quote_url($url) . " |"
		or return undef;
	binmode $fh;

	open my $out, ">$filename" or warn "$!\n", return undef;
	binmode $out;

	while($readbytes = read $fh, $buffer, $bufsiz) {
		syswrite($out, $buffer, $readbytes);
		$bytecount += $readbytes;
		if($bytecount > $maxbytes) {
			close $fh;
			close $out;
			unlink($filename);
			$skipcount++;
			printf "+ file too large\n";
			return 0;
		}
	}

	close $fh;
	close $out;
	return $bytecount;
}

sub download_http {
	my $url = shift;
	my $size = wget($url, 1); # HEAD request first

	# $size will be 0 for 'too big' or undef if the HEAD failed.

	if($size) {
		$size = wget($url, 0);
	}
	return $size;
}

sub download_file {
	my $url = shift;
	my $dlresult;

	if($url =~ /^ftp:/) {
		$dlresult = download_ftp($url);
	} elsif($use_curl) {
		$dlresult = curl_download_http($url);
	} else {
		$dlresult = download_http($url);
	}

	return $dlresult;
}

# see %user_agent_overrides
# this is called by both wget() and curl_download_http(), fortunately
# wget and curl happen to use the same argument for user-agent.
sub user_agent {
	my $url = shift;

	my $ua = "";
	$url =~ m,^\w+://([^/]*)/,;
	my $site = $1;
	for (keys %user_agent_overrides) {
		$site =~ /$_/ && do {
			$ua = $user_agent_overrides{$_};
		};
	}
	$ua = "--user-agent '$ua'" if $ua;
	return $ua;
}

# return true if limit set and file size > limit.
# return false if no limit set, or file size <= limit.
sub toobig {
	return 0 if $maxfilemegs <= 0; # no limit
	return $_[0] > ($maxfilemegs * 1024 * 1024);
}

# wget_fake_head: What is a fake HEAD request?

# Various cloud-ey web servers don't support HEAD requests:

# github.com and bitbucket.org download links redirect to amazonaws.com,
# which returns 403 Forbidden for any HEAD request.

# googlecode.com always returns 404 Not Found for a HEAD request.

# some other servers don't return a Content-Length header for a HEAD
# request, but they do for a GET.

# We really want to know the file size, so we can decide whether or
# not to download it. If a HEAD request fails, we'll do a GET request
# instead, but stop the transfer as soon as we get the Content-Length
# header from wget.

# Due to buffering, wget still downloads the first 16K or so of the file,
# which gets discarded when we close its filehandle. We could do better
# than this by implementing the HTTP protocol in terms of IO::Socket::INET
# or such, but I'm not writing & debugging the mess that would turn into.
# Plus, core perl (and Slackware's perl) lacks SSL support.

# This gets called for any URL that doesn't return a Content-Length header
# in its HEAD request (for whatever reason, including because of a 404
# not found). Of course, a GET might not return a length header either,
# in which case the file won't be downloaded.

# It might be nice if wget supported a --fake-head option itself. Maybe I'll
# code it up & send a patch to the wget maintainers?

# I've just discovered a better way to do this:
# curl --head -L -sS -X GET $url
# Stops downloading and exits after the headers are received.
# Not as familiar with curl as I am with wget, have to see about
# options... and if this works as well as I expect, there's never going
# to be a need to do a real HEAD request!

# update: the above has been implemented, see curl_download_http()

sub wget_fake_head {
	my $url = shift;
	our $wget_config_arg;
	my $cmd = "$wget $wget_config_arg " .
		"--tries 1 --quiet -O- --save-headers " .
		user_agent($url) . " " .
		" $wgetargs " .
		wget_quote_url($url);

	#print "real HEAD failed, trying fake HEAD request: $cmd\n";

	# TODO: open3?
	open my $fh, "$cmd|" or return undef;
	my $size;
	while(<$fh>) {
		s/\r//;
		chomp;
		last if /^$/;
		$size = $1 if /^Content-Length:\s+(\d+)/i;
	}
	close $fh;

	if($size && toobig($size)) {
		printf "+ file too large: %0.2fMB\n", $size / (1024 * 1024);
		$skipcount++;
		$size = 0;
	} elsif(not defined $size) {
		print "? can't determine file size, skipping\n";
	}

	return $size;
}

# return url, in single quotes.
sub wget_quote_url {
	my $url = shift;

# At one time I thought this was necessary to get dropbox URLs to
# work. Turns out user_agent_overrides works better.
#	if($url =~ m,https?://(?:\w+\.)dropbox\.com/,) {
#		$url =~ s,\?dl=\d$,,;
#		$url .= "?dl=1";
#	}

	return "'$url'";
}

# wget() does a HEAD (or fake head, if HEAD fails), or GET (download),
# using an external wget process. Return value is the file size in bytes,
# or 0 for "too big", or undef for any error.
sub wget {
	my $url = shift;
	our $wget_config_arg;

	if($url =~ /'/) {
		print "! refusing to deal with URL \"$url\" due to embedded single-quote.\n" .
			"! please contact the maintainer of the SlackBuild to have this fixed.\n";
		return undef;
	}

	my $head = shift; # boolean, 0 = download (GET), 1 = HEAD request only
	$attemptcount++ if !$head;

	my $size;
	my $fh;

	my $tmpdir = $ENV{TMPDIR} || $ENV{TMP} || "/tmp";

	if(not defined $wgetrc) {
		($fh, $wgetrc) = tempfile("wgetrc.XXXXXXXX", DIR => $tmpdir, UNLINK => 1);
		print $fh $wgetrc_contents;
		close $fh;
	}

	if(not defined $wget_config_arg) {
		$wget_config_arg = "";
		open my $fh, "$wget --help|" or die "can't run wget: $!\n";
		while(<$fh>) {
			$wget_config_arg = "--config=$wgetrc" if /--config/;
		}
		close $fh;
		if(not $wget_config_arg) {
			print "| wget version is too old to support --config option.\n";
			print "| continuing without it...\n";
		}
	}

	my $outfile;
	($fh, $outfile) = tempfile("wget.out.XXXXXXXX", DIR => $tmpdir, UNLINK => 1);
	close $fh;

	# TODO: open3?
	# the -O is there to force the filename, in case of a redirect. newer
	# versions of wget don't actually need this, but it doesn't hurt.
	my $cmd = "$wget $wget_config_arg " .
		user_agent($url) . " " .
		($head ? "--spider --tries 1" : "-O '" . url_to_filename($url) . "'") .
		" $wgetargs " .
		wget_quote_url($url) . " " .
		">$outfile 2>&1";

		#" --referer='$url' " . # don't use, it breaks sourceforge

	my $retval = system($cmd);
	print "$cmd\n" if $retval != 0;

	open $fh, "<", "$outfile";
	while(<$fh>) {
		print " ! $_" if $retval != 0;

		/^Length:\s*(\d+).*\[(.*?)\]/ && do {
			$size = $1; # TODO: $content_type = $2, check for text/html or such
			if(toobig($size)) {
				printf "+ file too large: %0.2fMB\n", $size / (1024 * 1024);
				$skipcount++;
				$size = 0;
			}
		};
	}
	close $fh;
	unlink $outfile;

	# Grr. Some sites refuse HEAD requests, and some allow them but
	# don't return a Content-Length header. So we must resort to more
	# drastic measures.
	# FIXME: don't bother doing this if we got a DNS error from the HEAD.
	if($head && not(defined($size))) {
		return wget_fake_head($url);
	}

	return $size; # which might be undef!
}

# we could use wget for FTP links too, but doing it this way
# lets us check the filesize and do the download with only one
# FTP session.
sub download_ftp {
	my ($server, $dir, $filename) = ($_[0] =~ m,
		^ftp://   # proto
		([^/]+)   # server (no slashes)
		(/.*?)?   # optional path (always at least the initial slash)
		([^/]+)$  # filename (everything after last slash)
		,x);

	print "* download_ftp $_[0] " .
		"(server $server, dir $dir, filename $filename\n" if $DEBUG_HTTP;
	my $size = undef;
	eval {
		my $ftp = Net::FTP->new($server, Debug => 0)
			or die "Can't connect to $server: $@";
		print "* connected\n" if $DEBUG_HTTP;
		$ftp->login("anonymous",'-anonymous@')
			or die "Can't log in to $server: ", $ftp->message;
		print "* logged in as anonymous\n" if $DEBUG_HTTP;
		$ftp->cwd($dir)
			or die "Can't chdir($dir) on $server: ", $ftp->message;
		print "* chdir $dir OK\n" if $DEBUG_HTTP;
		$ftp->binary;
		$size = $ftp->size($filename)
			or die "Can't get $filename size from $server: ", $ftp->message;
		print "* $filename is $size bytes\n" if $DEBUG_HTTP;

		if(toobig($size)) {
			printf "+ file too large: %0.2fMB\n", $size / (1024 * 1024);
			$skipcount++;
			$size = 0;
		} else {
			$attemptcount++;
			$ftp->get($filename)
				or die "Can't download $filename from server: ",
					($ftp->message ? $ftp->message : "(no message, timed out?)"), "\n";
			print "* get finished\n" if $DEBUG_HTTP;
		}

		$ftp->quit;
		print "* \$ftp->quit\n" if $DEBUG_HTTP;
	};

	if($@) {
		print "! $@";
		undef $size;
	}

	return $size;
}

sub git_clone {
	system('git', 'clone', $sbogiturl, $sbogitdir);
}

sub git_pull {
	return !system('git', 'pull');
}

sub md5_dir {
	my $md5 = shift;
	return "$archivedir/by-md5/" .
		substr($md5, 0, 1) .
		"/" .
		substr($md5, 1, 1) .
		"/" .
		$md5 .
		"/";
}

sub name_dir {
	my ($cat, $prg) = @_;
	return "$archivedir/by-name/$cat/$prg/";
}

sub md5sum_file {
	my $filename = shift;
	open my $fh, "<", $filename or do {
		print "can't get md5sum of $filename: $!\n";
		return undef;
	};
	binmode($fh);
	my $ret = Digest::MD5->new->addfile($fh)->hexdigest;
	close $fh;
	return $ret;
}

sub already_exists {
	my ($filename, $category, $prgnam, $md5) = @_;

	my $n = name_dir($category, $prgnam) . "/" . $filename;
	my $m = md5_dir($md5) . "/" . $filename;

	return
		-e $n &&
		-e $m &&
		($md5 eq md5sum_file($n)) &&
		($md5 eq md5sum_file($n));
}

sub store_file {
	my ($filename, $category, $prgnam, $md5) = @_;

	#warn "store_file($filename, $category, $prgnam, $md5);\n";

	my $md5dir = md5_dir($md5);
	my $namedir = name_dir($category, $prgnam);

	mkpath($md5dir);
	mkpath($namedir);
	unlink($namedir . "/" . $filename); # rm -f old copy, if any
	move($filename, $namedir . "/" . $filename);
	if($symlinks) {
		symlink("../../../../by-name/" . $category . "/" . $prgnam . "/" . $filename,
				$md5dir . "/" . $filename);
	} else {
		link($namedir . "/" . $filename, $md5dir . "/" . $filename);
	}
}

# handle_info_file() is used as the 'wanted' sub for File::Find, but
# it's also called from add and update modes, so it doesn't use any of
# the File::Find stuff. Call while cd'ed to $sbogitdir, with $_ set to
# the relative path to the .info file.
sub handle_info_file {
	return unless /\.info$/;

	s,^\./,,; # strip leading ./, if present
	my ($category, $prgnam) = split /\//, $_;
	print "=== $category/$prgnam\n";

	if(blacklisted($category, $prgnam)) {
		print "- blacklisted, skipping\n";
		return;
	}

	my $dls = parse_info($_);
	for(keys %$dls) {
		$urlcount++;
		my $url = $_;
		my $md5 = $dls->{$_};
		my $filename = url_to_filename($url);
		print ": $url\n";

		if(already_exists($filename, $category, $prgnam, $md5)) {
			print "  already in archive, OK\n";
			$archivecount++;
		} else {
			{
				local $maxfilemegs = 0 if whitelisted($category, $prgnam);
				download_file($url); # TODO: check result!
			}
			if(! -f $filename || -z $filename) {
				unlink($filename);
				$failcount++;
				print "- not downloaded\n";
				next;
			}

			if(md5sum_file($filename) ne $md5) {
				$failcount++;
				print "! md5sum failed\n";
				unlink($filename);
				next;
			}

			print "  downloaded, OK\n";
			$dlcount++;
			store_file($filename, $category, $prgnam, $md5);
		}
	}
}

sub init_git {
	chdir($sbogitdir) && -d ".git" ||
		die "SBo git dir $sbogitdir not a git checkout, " .
			"do you need to run 'sbosrcarch create?'\n";
}

sub create_mode {
	chdir($sbogitdir) or git_clone;
	chdir($sbogitdir) or die "can't find or create SBo git dir $sbogitdir\n";
	git_clone() unless -d ".git";
	git_pull() or die "git pull failed, check $sbogitdir\n";

	$use_bwlist = 1;
	$skipcount = $attemptcount = $urlcount =
	$archivecount = $dlcount = $failcount = $nowarchived = 0;

	find({wanted => \&handle_info_file, no_chdir => 1}, ".");

	$nowarchived = $dlcount + $archivecount;
	$coverage = sprintf("%.1d", ($nowarchived * 100 / $urlcount));
	print <<EOF;

---
Total URLs: $urlcount
Already archived: $archivecount
Skipped downloads due to size limit: $skipcount
Attempted downloads: $attemptcount
Successful downloads: $dlcount
Failed downloads: $failcount
Now archived: $nowarchived
Coverage: $coverage%
EOF
	exit 0;
}

sub update_mode {
	my $oldcommit;

	init_git();

	$use_bwlist = 1;

	open my $fh, "git log|" or die "$!";
	my $logline = <$fh>;
	(undef, $oldcommit) = split /\s+/, $logline;
	print "git repo was at commit $oldcommit\n";
	close $fh;

	git_pull();

	open $fh, "git diff --numstat $oldcommit|" or die "$!";
	while(<$fh>) {
		(undef, undef, $_) = split /\s+/;
		next unless /\.info$/;
		print "$_ was removed from repo\n", next unless -f;
		handle_info_file();
	}
	close $fh;

	# if the STATUS file exists, extract the list of builds with
	# missing files, and retry them. most of the time the retries
	# will fail, but it doesn't hurt to try.

	if(open $fh, "<$archivedir/STATUS") {
		print "STATUS file exists, retrying missing builds\n";
		my $retries = 0;
		while(<$fh>) {
			chomp;
			next unless /^  ([^\/]+)\/([^\/]+)$/;
			$_ = "$1/$2/$2.info";
			handle_info_file();
			$retries++;
		}
		close $fh;
		if($retries) {
			print "Retried $retries builds from STATUS file\n";
		} else {
			print "No missing builds in STATUS, we are at 100%\n";
		}
	}

	exit 0;
}

# purge_mode() does 3 or 4 passes:

# 1. get all the filenames from all the info files, build hashes of filenames
#    and md5sums that we want to keep.
# 2. walk the archive tree with File::Find and rm any file that's in a
#    category/name dir, but not mentioned in the filename hash

# If --rebuild not given:
# 3. walk the archive tree with File::Find and rm any file that's in a
#    by-md5 dir, but whose md5sum is not mentioned in the md5sum hash.
# 4. do a trim_post() pass to delete any empty dirs and/or dangling symlinks

# If --rebuild is given:
# 3. delete the entire by-md5 tree and recreate it. should not be done on a
#    regular basis, only if something drastic happened to the by-md5 tree.

# If --fake is given, the 4 passes are all done, but nothing is deleted. Not
# possible to combine --rebuild and --fake!

sub purge_mode {
	my $rebuild = 0;

	shift @ARGV;
	if($ARGV[0]) {
		if($ARGV[0] =~ /^--?r(?:ebuild)?/) {
			$rebuild = 1;
		} elsif($ARGV[0] =~ /^--?f(?:ake)?/) {
			$fake_purge = 1;
		} else {
			die "Unknown option: $ARGV[0]\n";
		}
	}

	init_git();

	$purgebytes = $purgefiles = 0;

	# pass 1; build list of all source files, by parsing all .info files
	%keep_filenames = %keep_md5sums = (); # populated by the find():
	find({wanted => \&purge_pass_1_wanted, no_chdir => 1}, ".");

#	for(keys %keep_filenames) {
#		warn "keep $_\n";
#	}

	# pass 2: find all source files, delete any that aren't mentioned in any
	# .info files (using list from above)
	chdir($archivedir) or die "$archivedir: $!\n";
	find({wanted => \&purge_pass_2_wanted, no_chdir => 1}, "by-name");

	if($rebuild) {
		# pass 3: delete & recreate entire by-md5 tree
		rmtree("by-md5");
		print "Removed by-md5 tree, rebuilding\n";
		find({wanted => \&rebuild_wanted, no_chdir => 1}, "by-name");
	} else {
		# pass 3: find all by-md5 files, delete any whose md5sums aren't found
		# in any .info file.
		find({wanted => \&purge_pass_3_wanted, no_chdir => 1}, "by-md5");

		# pass 4: clean out (remove) any empty directories.
		trim_post();
	}

	printf("Purged $purgefiles files, %.1fMB\n", ($purgebytes / (1024 * 1024)));
	exit 0;
}

# helper for purge_mode, populates %keep_filenames and %keep_md5sums
sub purge_pass_1_wanted {
	return unless /\.info$/;
	my $dls = parse_info($_);
	my ($undef, $cat, $name, undef) = split /\//, $_;
	for(keys %$dls) {
		my $path = "by-name/$cat/$name/" . url_to_filename($_);
		$keep_filenames{$path}++;
		$keep_md5sums{$$dls{$_}}++;
	}
}

# helper for purge_mode, removes all files in category/prgnam/
# dirs that aren't listed in %keep_filenames
sub purge_pass_2_wanted {
	s,^\./,,; # remove leading ./
	my (undef, $cat, $name, $file) = split /\//, $_;
	return unless defined $file;
	return if $keep_filenames{"by-name/$cat/$name/$file"};

	$purgebytes += -s $_;
	$purgefiles++;

	my $namepath = name_dir($cat, $name) . "$file";
	#my $md5path = md5_dir(md5sum_file($namepath)) . "$file";

	#print "purge $namepath $md5path\n";
	print "purge $namepath\n";

	unlink $namepath unless $fake_purge;
	#unlink $md5path;
}

# helper for purge_mode, removes all files in by-md5
# dirs that aren't listed in %keep_md5sums
sub purge_pass_3_wanted {
	s,^\./,,; # remove leading ./
	my (undef, undef, undef, $md5sum, $filename) = split /\//, $_;
	return unless defined $md5sum; # only want the last dir...
	return if defined $filename; # and skip if it's not the dir

	if($keep_md5sums{$md5sum}) {
		#print "keep md5sum: $md5sum\n";
	} else {
		print "purge $_\n";
		rmtree(md5_dir($_)) unless $fake_purge;
	}
}

sub rebuild_wanted {
	return unless -f;

	s,^\./,,; # remove leading ./
	my $md5dir = md5_dir(md5sum_file($_));
	my (undef, $category, $prgnam, $filename) = split /\//, $_;

	mkpath($md5dir);

	if($symlinks) {
		symlink("../../../../by-name/" . $category . "/" . $prgnam . "/" . $filename,
				$md5dir . "/" . $filename);
	} else {
		link($_, $md5dir . "/" . $filename);
	}
}

# helper for trim_mode
sub trim_wanted {
	return unless -f $_;
	my $size = -s _;
	if(toobig($size)) {
		unlink($_);
		$trimcount++;
		$trimbytes += $size;
	}
}

# helper for trim_post
sub trim_post_wanted {
	return if $fake_purge;
	unlink $_ if -l $_ && ! -e _;
	return unless -d _;
	push @trim_empty_dirs, $_ if !<*>;
}

# pass 2 of trim_mode, also called by purge_mode. removes
# empty directories and dangling symlinks.
sub trim_post {
	chdir($archivedir) or die "$archivedir: $!\n";

	# can't rmdir from within find's wanted sub, or we get
	# lots of 'Can't opendir()' warnings. So collect all the
	# empty dirs in an array during the find, then rmdir them
	# all in one swell foop afterwards.
	@trim_empty_dirs = ();

	# remove dangling symlinks and make a list of empty dirs
	find({wanted => \&trim_post_wanted, no_chdir => 1}, ".");

	rmdir $_ for @trim_empty_dirs; # the aforementioned swell foop
}

# this mode doesn't know/care about the git stuff, it operates purely
# on the archive file tree.
sub trim_mode {
	chdir($archivedir) or die "$archivedir: $!\n";

	$trimcount = $trimbytes = 0;

	# first pass: remove files that are too big
	find({wanted => \&trim_wanted, no_chdir => 1}, ".");

	# 2nd pass
	trim_post();

	printf("Trimmed $trimcount files, %.1fMB\n", ($trimbytes / (1024 * 1024)));
	exit 0;
}

# in: "category/name"
# out: "category/name/name.info"
sub find_info_file {
	my $info = shift;
	$info =~ s,/([^/]+)$,/$1/$1.info,;
	return $info;
}

# FIXME: this will fail if @localfiles are absolute paths!
sub local_add {
	my ($oldcwd, $catname, $info, @localfiles) = @_;
	$catname =~ s,^\./,,;
	my ($category, $prgnam) = split /\//, $catname;
	my %localmd5s;

	for(@localfiles) {
		$localmd5s{md5sum_file("$oldcwd/$_")} = "$oldcwd/$_";
	}

	my $dls = parse_info($info);

	chdir($archivedir) or die "$archivedir: $!";
	for(keys %$dls) {
		my $targetfile = url_to_filename($_);

		my $md5 = $dls->{$_};
		my $localfile = $localmd5s{$md5};
		next unless $localfile;

		delete $localmd5s{$md5};

		copy($localfile, $targetfile);
		store_file($targetfile, $category, $prgnam, $md5);
		print "added $targetfile for $category/$prgnam\n";
	}

	for(keys %localmd5s) {
		print "$localmd5s{$_} ($_) ignored: doesn't match any md5sum in $info\n";
	}
}

sub add_by_md5_wanted {
	our %md5_to_dl;
	return unless /\.info/;
	s,\./,,;
	my ($category, $prgnam, undef) = split /\//;
	my $dls = parse_info($_);
	$md5_to_dl{$_} = "$category/$prgnam" for values %$dls;
}

sub add_by_md5 {
	print "no category/prgnam, adding file(s) by md5sum\n";
	my $oldcwd = shift;
	our %md5_to_dl;
	find({wanted => \&add_by_md5_wanted, no_chdir => 1}, ".");

	for my $filename (@_) {
		my $infile = $filename;
		$infile = "$oldcwd/$infile" unless $infile =~ m,^/,;

		my $md5 = md5sum_file($infile);
		next unless defined $md5;

		my $catname = $md5_to_dl{$md5} or do {
			print "$filename ($md5) doesn't match any .info file, skipping\n";
			next;
		};

		my $info = find_info_file($catname) or do {
			print "can't find info file for $catname";
			next;
		};

		local_add($oldcwd, $catname, $info, $filename);
		chdir($sbogitdir);
	}
}

sub add_or_rm_mode {
	my $oldcwd = POSIX::getcwd();
	init_git();
	my $mode = shift @ARGV;

	if($mode eq 'add' && @ARGV && (-f $ARGV[0] || -f "$oldcwd/$ARGV[0]")) {
		add_by_md5($oldcwd, @ARGV);
		exit 0;
	}

	my $catname = shift @ARGV or usage();

	$use_bwlist = 0;
	if($catname eq '-f') {
		$maxfilemegs = 0;
		$catname = shift(@ARGV) or usage();
	}

	my $info = find_info_file($catname);
	if(! -f $info) {
		die "Can't find $info in repo\n";
	}

	if($mode eq "add") {
		if(!@ARGV) { # no args, use URL(s) in .info file
			$_ = $info;
			handle_info_file();
		} else {
			local_add($oldcwd, $catname, $info, @ARGV);
		}
	} elsif($mode eq "rm") {
		my $dls = parse_info($info);
		for(keys %$dls) {
			my $md5 = $dls->{$_};
			my $filename = url_to_filename($_);
			my ($category, $prgname) = split /\//, $catname;
			unlink(name_dir($category, $prgname) . "/$filename");
			rmdir(name_dir($category, $prgname));
			unlink(md5_dir($md5) . "/$filename");
			rmdir(md5_dir($md5));
		}
	} else {
		die "this never happens";
	}
	exit 0;
}

# check_mode() needs to do this:

# Find/parse all info files, building hashes of filenames and md5sums

# Find all files in by-name, make sure the md5sums match, make sure the
# by-md5 file exists and is either a hardlink or symlink to the by-name
# file. If the size is over the limit, make a note of it. If the file
# isn't found in the hash of filenames, it's extraneous (and so is its
# by-md5 counterpart).

# Do the same thing for the by-md5 tree, more or less. If both hard and
# symolic links are found, that fact will get reported (but only once!)

# Print a report.

sub check_byname_wanted {
	if(-d) {
		my (undef, $category, $prgnam, $extra) = split /\//;

		if(defined($extra)) {
			print "misplaced dir (not a category/prgnam): $_\n";
		}

		return;
	}

	return unless -f _;

	$filecount++;

	my $size = -s _;
	$filebytes += $size;

	s,^\./,,;
	my (undef,  $category, $prgnam, $filename, $extra) = split /\//;

	if(!defined($filename) || defined($extra)) {
		print "misplaced file (not in a category/prgnam dir): $_\n";
		$filecount--;
		return;
	}

	my $shortname = join("/", $category, $prgnam, $filename);

	my $info = join("/", $sbogitdir, $category, $prgnam, $prgnam . ".info");
	if(!-f $info) {
		print "$shortname extraneous: no info file for $category/$prgnam\n" if $verbosecheck;
		$filecount--;
		$extraneous_byname++;
		return;
	}

	my $dls = $parsedinfo{"$category/$prgnam"};
	my $md5 = md5sum_file($_) unless $quickcheck;
	my $foundfile;

	# make $info and printable (relative path only)
	$info = join("/", $category, $prgnam, $prgnam . ".info");

	for my $dl (keys %$dls) {
		my $infofilename = url_to_filename($dl);
		if($infofilename eq $filename) {
			$foundfile++;
			if(!$quickcheck) {
				if($md5 ne $dls->{$dl}) {
					print "$info: $shortname: wrong md5sum (should be $dls->{$dl})\n";
				} else {
# check by-md5 file existence only (check_bymd5_wanted will do more)
					my $md5file = md5_dir($md5) . "/" . $filename;
					if(! -e $md5file) {
						print "$info: $shortname: missing $md5file\n";
					}
				}
			}
		}
	}

	if($foundfile) {
		$infofilecount{"$category/$prgnam"}--;
	} else {
		print "$shortname extraneous: not mentioned in $info (sbosrcarch purge)\n" if $verbosecheck;
		$filecount--;
		$extraneous_byname++;
	}

	if(blacklisted($category, $prgnam)) {
		print "$category/$prgnam blacklisted, but present in archive (sbosrcarch rm $category/$prgnam)?\n";
	}

	if(toobig($size)) {
		$size = sprintf("%.1f", $size / (1024 * 1024));
		print "$shortname (${size}MB) exceeds file size limit ${maxfilemegs}MB (add to whitelist or sbosrcarch rm $category/$prgnam)?\n";
	}
}

sub check_bymd5_wanted {
	return if -d;

	s,^\./,,;

	if(-l $_ && (! -e $_)) {
		print "dangling symlink: $_\n";
		return;
	}

	my (undef, $a, $b, $md5dir, $filename, $extra) = split /\//;

	if(!defined($filename) || defined($extra)) {
		print "$_: misplaced file (not in a a/b/md5sum dir)\n";
		return;
	}

	if(-l $_) {
		our $symlinkcount++;
	} else {
		my (undef, undef, undef, $nlink) = stat $_;
		if($nlink >= 2) {
			our $hardlinkcount++;
		} else {
			print "$_: not a symlink or hardlink\n" if $verbosecheck;
		}
	}

	if(!$quickcheck) {
		my $realmd5 = md5sum_file($_) || return;
		my $reala = substr($realmd5, 0, 1);
		my $realb = substr($realmd5, 1, 1);
		if($reala ne $a || $realb ne $b) {
			print "$_: wrong subdir (should be $reala/$realb/$realmd5)\n";
			return;
		}

		if($realmd5 ne $md5dir) {
			print "$_: md5sum mismatch\n";
			return;
		}
	}

	if($allmd5sums{$md5dir}) {
		$md5_filecount++;
		$allmd5sums{$md5dir} = 0; # don't count twice
	} else {
		print "$_ extraneous: not mentioned in any .info file\n" if $verbosecheck;
		$extraneous_bymd5++;
	}
}

sub check_info_wanted {
	return unless /\.info/;
	s,\./,,;

	my ($category, $prgnam, $file) = split /\//;

	if(blacklisted("$category/$prgnam")) {
		print "  $category/$prgnam blacklisted, skipping\n" if $verbosecheck;
		return;
	}

	# 20180604 bkw: games/mrboom has a file named "mrboom_libretro.info"
	# which isn't an SBo info file. In general it's allowed for builds to
	# include other files with .info filenames, so this bit is to make
	# sure we're only looking at the real prgnam.info file:
	return unless $file eq ($prgnam . ".info");

	my $dls = parse_info($_);
	$totalfiles += keys %$dls;
	$infofilecount{"$category/$prgnam"} += keys %$dls;
	$parsedinfo{"$category/$prgnam"} = $dls;
	#$allmd5sums{$_}++ for values %$dls;
	push @{$allmd5sums{$_}}, "$category/$prgnam" for values %$dls;
}

# write status results to STATUS file in the root of the archive
# dir. errors will be silently ignored (e.g. permission denied).
sub write_status_file {
	my $content = shift;

	init_git();

	# git is lovely, but all those options mean it takes a minute to
	# find what you wanted in the man page...
	chomp(my $logline = `TZ=UTC git log --date=format-local:'%a %Y-%m-%d %H:%M:%S %Z' --pretty=format:'%h %cd: %an, %s' -n1`);

	chdir($archivedir) or die "$archivedir: $!";
	open(my $fh, '>', "STATUS") or return;

	chomp(my $timestamp = `TZ=UTC date '+%a %Y-%m-%d %H:%M:%S %Z'`);

	print $fh <<EOF;
Status report for sbosrcarch archive
------------------------------------

This report was generated on $timestamp.

Last SBo git commit was:
$logline

$content
EOF

	close $fh;
}

sub check_mode {
	$quickcheck = shift; # 1 = don't md5sum stuff
	shift @ARGV;
	$verbosecheck = ($ARGV[0] && $ARGV[0] =~ /^-*v(?:erbose)?$/);
	our %missingmd5builds;

	$use_bwlist = 1;
	init_git();

	print "* Parsing .info files...\n";
	find({wanted => \&check_info_wanted, no_chdir => 1}, ".");

	chdir($archivedir) or die "$archivedir: $!";

	print "* Checking by-name tree...\n";
	find({wanted => \&check_byname_wanted, no_chdir => 1}, "by-name");

	print "* Checking by-md5 tree...\n";
	find({wanted => \&check_bymd5_wanted, no_chdir => 1}, "by-md5");

	my @missingfilebuilds;
	for(keys %infofilecount) {
		my $count = $infofilecount{$_};
		push @missingfilebuilds, $_ if $count;
	}

	if($symlinkcount && $hardlinkcount) {
		print "by-md5 contains both symlinks and hardlinks (harmless but messy)\n";
	}

	my $totalbuildcount = keys %infofilecount;
	my $missingbuildcount = @missingfilebuilds;
	my $completebuildcount = $totalbuildcount - $missingbuildcount;
	my $coverage = sprintf("%.2f", ($completebuildcount * 100 / $totalbuildcount));
	my $filemegs = sprintf("%.1fMB", $filebytes / (1024 * 1024));
	my $missingfiles = $totalfiles - $filecount;
	my $filecoverage = sprintf("%.2f", $filecount * 100 / $totalfiles);

	my $md5_totalfiles = keys %allmd5sums;
	my $md5_missingfiles = $md5_totalfiles - $md5_filecount;
	my $md5_filecoverage = sprintf("%.2f", $md5_filecount * 100 / $md5_totalfiles);

	my $output = <<EOF;

--- by-name status:
Total source files: $totalfiles
Archived files: $filecount
Archive size: $filemegs
Missing files: $missingfiles
Extraneous files: $extraneous_byname
File coverage: $filecoverage%

--- SlackBuild status (based on by-name):
Total SlackBuilds: $totalbuildcount
SlackBuilds with all files present: $completebuildcount
SlackBuilds missing at least one file: $missingbuildcount
SlackBuild coverage: $coverage%
EOF

	if(@missingfilebuilds) {
		$output .= "Following SlackBuilds are missing by-name files:\n";
		$output .= "  $_\n" for sort { $a cmp $b } @missingfilebuilds;
	} else {
		$output .= "All SlackBuild download files present in by-name.\n";
	}

	$output .= <<EOF;

--- by-md5 status:
Total source files: $md5_totalfiles
Archived files: $md5_filecount
Missing files: $md5_missingfiles
Extraneous files: $extraneous_bymd5
File coverage: $md5_filecoverage%
EOF

	my @list;
	for(keys %allmd5sums) {
		push @list, @{$allmd5sums{$_}} if ref $allmd5sums{$_};
	}
	if(@list) {
		$output .= "Following SlackBuilds are missing by-md5 files:\n";
		$output .= "  $_\n" for sort { $a cmp $b } @list;
	} else {
		$output .= "All SlackBuild download files present in by-md5.\n";
	}

	print $output;
	write_status_file($output);
	exit 0;
}

# test code for black/white lists, remove?
sub bwlist_mode {
	shift @ARGV;

	$use_bwlist = 1;

	print "\nblacklist:\n";
	print "\t(empty)\n" unless %blackhash;
	print "\t$_\n" for sort keys %blackhash;
	print "whitelist:\n";
	print "\t(empty)\n" unless %whitehash;
	print "\t$_\n" for sort keys %whitehash;
	print "\n";

	for(@ARGV) {
		print "$_: ";
		if(whitelisted($_)) {
			print "whitelisted";
		} elsif(blacklisted($_)) {
			print "blacklisted";
		} else {
			print "not listed in whitelist or blacklist";
		}
		print "\n";
	}

	exit 0;
}

sub usage {
	my $self = $0;
	$self =~ s,.*/,,;

	print <<EOF;
$self - create and maintain SBo source archive

Usage: $self <mode>

<mode> is one of:

  create
  update
  purge
  trim
  check
  add <category/prgname> [<file> ...]
  rm <category/prgname>

For full documentation try:
  perldoc $self
EOF

	exit 1
}

#main()

$|++;
usage() unless (defined $ARGV[0] && $ARGV[0] !~ /^-+h(?:elp)?/);
read_config();
for ($ARGV[0]) {
	/create/ && do { create_mode();    };
	/update/ && do { update_mode();    };
	/purge/  && do { purge_mode();     };
	/add/    && do { add_or_rm_mode(); };
	/rm/     && do { add_or_rm_mode(); };
	/trim/   && do { trim_mode();      };
	/check/  && do { check_mode(0);    };
	/status/ && do { check_mode(1);    };
	/bwlist/ && do { bwlist_mode();    };
	usage();
}

__END__