-
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
// Copyright 2014 The Gogs Authors. All rights reserved.
// Copyright 2019 The Gitea Authors. All rights reserved.
// Use of this source code is governed by a MIT-style
// license that can be found in the LICENSE file.
package gitdiff
import (
"bufio"
"bytes"
"context"
"fmt"
"html"
"html/template"
"io"
"net/url"
"os"
"regexp"
"sort"
"strings"
"time"
"code.gitea.io/gitea/models/db"
git_model "code.gitea.io/gitea/models/git"
issues_model "code.gitea.io/gitea/models/issues"
pull_model "code.gitea.io/gitea/models/pull"
user_model "code.gitea.io/gitea/models/user"
"code.gitea.io/gitea/modules/analyze"
"code.gitea.io/gitea/modules/base"
"code.gitea.io/gitea/modules/charset"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/highlight"
"code.gitea.io/gitea/modules/lfs"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/setting"
"github.com/sergi/go-diff/diffmatchpatch"
stdcharset "golang.org/x/net/html/charset"
"golang.org/x/text/encoding"
"golang.org/x/text/transform"
)
// DiffLineType represents the type of a DiffLine.
type DiffLineType uint8
// DiffLineType possible values.
const (
DiffLinePlain DiffLineType = iota + 1
DiffLineAdd
DiffLineDel
DiffLineSection
)
// DiffFileType represents the type of a DiffFile.
type DiffFileType uint8
// DiffFileType possible values.
const (
DiffFileAdd DiffFileType = iota + 1
DiffFileChange
DiffFileDel
DiffFileRename
DiffFileCopy
)
// DiffLineExpandDirection represents the DiffLineSection expand direction
type DiffLineExpandDirection uint8
// DiffLineExpandDirection possible values.
const (
DiffLineExpandNone DiffLineExpandDirection = iota + 1
DiffLineExpandSingle
DiffLineExpandUpDown
DiffLineExpandUp
DiffLineExpandDown
)
// DiffLine represents a line difference in a DiffSection.
type DiffLine struct {
LeftIdx int
RightIdx int
Match int
Type DiffLineType
Content string
Comments []*issues_model.Comment
SectionInfo *DiffLineSectionInfo
}
// DiffLineSectionInfo represents diff line section meta data
type DiffLineSectionInfo struct {
Path string
LastLeftIdx int
LastRightIdx int
LeftIdx int
RightIdx int
LeftHunkSize int
RightHunkSize int
}
// BlobExcerptChunkSize represent max lines of excerpt
const BlobExcerptChunkSize = 20
// GetType returns the type of a DiffLine.
func (d *DiffLine) GetType() int {
return int(d.Type)
}
// CanComment returns whether or not a line can get commented
func (d *DiffLine) CanComment() bool {
return len(d.Comments) == 0 && d.Type != DiffLineSection
}
// GetCommentSide returns the comment side of the first comment, if not set returns empty string
func (d *DiffLine) GetCommentSide() string {
if len(d.Comments) == 0 {
return ""
}
return d.Comments[0].DiffSide()
}
// GetLineTypeMarker returns the line type marker
func (d *DiffLine) GetLineTypeMarker() string {
if strings.IndexByte(" +-", d.Content[0]) > -1 {
return d.Content[0:1]
}
return ""
}
// GetBlobExcerptQuery builds query string to get blob excerpt
func (d *DiffLine) GetBlobExcerptQuery() string {
query := fmt.Sprintf(
"last_left=%d&last_right=%d&"+
"left=%d&right=%d&"+
"left_hunk_size=%d&right_hunk_size=%d&"+
"path=%s",
d.SectionInfo.LastLeftIdx, d.SectionInfo.LastRightIdx,
d.SectionInfo.LeftIdx, d.SectionInfo.RightIdx,
d.SectionInfo.LeftHunkSize, d.SectionInfo.RightHunkSize,
url.QueryEscape(d.SectionInfo.Path))
return query
}
// GetExpandDirection gets DiffLineExpandDirection
func (d *DiffLine) GetExpandDirection() DiffLineExpandDirection {
if d.Type != DiffLineSection || d.SectionInfo == nil || d.SectionInfo.RightIdx-d.SectionInfo.LastRightIdx <= 1 {
return DiffLineExpandNone
}
if d.SectionInfo.LastLeftIdx <= 0 && d.SectionInfo.LastRightIdx <= 0 {
return DiffLineExpandUp
} else if d.SectionInfo.RightIdx-d.SectionInfo.LastRightIdx > BlobExcerptChunkSize && d.SectionInfo.RightHunkSize > 0 {
return DiffLineExpandUpDown
} else if d.SectionInfo.LeftHunkSize <= 0 && d.SectionInfo.RightHunkSize <= 0 {
return DiffLineExpandDown
}
return DiffLineExpandSingle
}
func getDiffLineSectionInfo(treePath, line string, lastLeftIdx, lastRightIdx int) *DiffLineSectionInfo {
leftLine, leftHunk, rightLine, righHunk := git.ParseDiffHunkString(line)
return &DiffLineSectionInfo{
Path: treePath,
LastLeftIdx: lastLeftIdx,
LastRightIdx: lastRightIdx,
LeftIdx: leftLine,
RightIdx: rightLine,
LeftHunkSize: leftHunk,
RightHunkSize: righHunk,
}
}
// escape a line's content or return <br> needed for copy/paste purposes
func getLineContent(content string) DiffInline {
if len(content) > 0 {
return DiffInlineWithUnicodeEscape(template.HTML(html.EscapeString(content)))
}
return DiffInline{Content: "<br>"}
}
// DiffSection represents a section of a DiffFile.
type DiffSection struct {
file *DiffFile
FileName string
Name string
Lines []*DiffLine
}
var (
addedCodePrefix = []byte(`<span class="added-code">`)
removedCodePrefix = []byte(`<span class="removed-code">`)
codeTagSuffix = []byte(`</span>`)
)
var (
unfinishedtagRegex = regexp.MustCompile(`<[^>]*$`)
trailingSpanRegex = regexp.MustCompile(`<span\s*[[:alpha:]="]*?[>]?$`)
entityRegex = regexp.MustCompile(`&[#]*?[0-9[:alpha:]]*$`)
)
// shouldWriteInline represents combinations where we manually write inline changes
func shouldWriteInline(diff diffmatchpatch.Diff, lineType DiffLineType) bool {
if true &&
diff.Type == diffmatchpatch.DiffEqual ||
diff.Type == diffmatchpatch.DiffInsert && lineType == DiffLineAdd ||
diff.Type == diffmatchpatch.DiffDelete && lineType == DiffLineDel {
return true
}
return false
}
func fixupBrokenSpans(diffs []diffmatchpatch.Diff) []diffmatchpatch.Diff {
// Create a new array to store our fixed up blocks
fixedup := make([]diffmatchpatch.Diff, 0, len(diffs))
// semantically label some numbers
const insert, delete, equal = 0, 1, 2
// record the positions of the last type of each block in the fixedup blocks
last := []int{-1, -1, -1}
operation := []diffmatchpatch.Operation{diffmatchpatch.DiffInsert, diffmatchpatch.DiffDelete, diffmatchpatch.DiffEqual}
// create a writer for insert and deletes
toWrite := []strings.Builder{
{},
{},
}
// make some flags for insert and delete
unfinishedTag := []bool{false, false}
unfinishedEnt := []bool{false, false}
// store stores the provided text in the writer for the typ
store := func(text string, typ int) {
(&(toWrite[typ])).WriteString(text)
}
// hasStored returns true if there is stored content
hasStored := func(typ int) bool {
return (&toWrite[typ]).Len() > 0
}
// stored will return that content
stored := func(typ int) string {
return (&toWrite[typ]).String()
}
// empty will empty the stored content
empty := func(typ int) {
(&toWrite[typ]).Reset()
}
// pop will remove the stored content appending to a diff block for that typ
pop := func(typ int, fixedup []diffmatchpatch.Diff) []diffmatchpatch.Diff {
if hasStored(typ) {
if last[typ] > last[equal] {
fixedup[last[typ]].Text += stored(typ)
} else {
fixedup = append(fixedup, diffmatchpatch.Diff{
Type: operation[typ],
Text: stored(typ),
})
}
empty(typ)
}
return fixedup
}
// Now we walk the provided diffs and check the type of each block in turn
for _, diff := range diffs {
typ := delete // flag for handling insert or delete typs
switch diff.Type {
case diffmatchpatch.DiffEqual:
// First check if there is anything stored
if hasStored(insert) || hasStored(delete) {
// There are two reasons for storing content:
// 1. Unfinished Entity <- Could be more efficient here by not doing this if we're looking for a tag
if unfinishedEnt[insert] || unfinishedEnt[delete] {
// we look for a ';' to finish an entity
idx := strings.IndexRune(diff.Text, ';')
if idx >= 0 {
// if we find a ';' store the preceding content to both insert and delete
store(diff.Text[:idx+1], insert)
store(diff.Text[:idx+1], delete)
// and remove it from this block
diff.Text = diff.Text[idx+1:]
// reset the ent flags
unfinishedEnt[insert] = false
unfinishedEnt[delete] = false
} else {
// otherwise store it all on insert and delete
store(diff.Text, insert)
store(diff.Text, delete)
// and empty this block
diff.Text = ""
}
}
// 2. Unfinished Tag
if unfinishedTag[insert] || unfinishedTag[delete] {
// we look for a '>' to finish a tag
idx := strings.IndexRune(diff.Text, '>')
if idx >= 0 {
store(diff.Text[:idx+1], insert)
store(diff.Text[:idx+1], delete)
diff.Text = diff.Text[idx+1:]
unfinishedTag[insert] = false
unfinishedTag[delete] = false
} else {
store(diff.Text, insert)
store(diff.Text, delete)
diff.Text = ""
}
}
// If we've completed the required tag/entities
if !(unfinishedTag[insert] || unfinishedTag[delete] || unfinishedEnt[insert] || unfinishedEnt[delete]) {
// pop off the stack
fixedup = pop(insert, fixedup)
fixedup = pop(delete, fixedup)
}
// If that has left this diff block empty then shortcut
if len(diff.Text) == 0 {
continue
}
}
// check if this block ends in an unfinished tag?
idx := unfinishedtagRegex.FindStringIndex(diff.Text)
if idx != nil {
unfinishedTag[insert] = true
unfinishedTag[delete] = true
} else {
// otherwise does it end in an unfinished entity?
idx = entityRegex.FindStringIndex(diff.Text)
if idx != nil {
unfinishedEnt[insert] = true
unfinishedEnt[delete] = true
}
}
// If there is an unfinished component
if idx != nil {
// Store the fragment
store(diff.Text[idx[0]:], insert)
store(diff.Text[idx[0]:], delete)
// and remove it from this block
diff.Text = diff.Text[:idx[0]]
}
// If that hasn't left the block empty
if len(diff.Text) > 0 {
// store the position of the last equal block and store it in our diffs
last[equal] = len(fixedup)
fixedup = append(fixedup, diff)
}
continue
case diffmatchpatch.DiffInsert:
typ = insert
fallthrough
case diffmatchpatch.DiffDelete:
// First check if there is anything stored for this type
if hasStored(typ) {
// if there is prepend it to this block, empty the storage and reset our flags
diff.Text = stored(typ) + diff.Text
empty(typ)
unfinishedEnt[typ] = false
unfinishedTag[typ] = false
}
// check if this block ends in an unfinished tag
idx := unfinishedtagRegex.FindStringIndex(diff.Text)
if idx != nil {
unfinishedTag[typ] = true
} else {
// otherwise does it end in an unfinished entity
idx = entityRegex.FindStringIndex(diff.Text)
if idx != nil {
unfinishedEnt[typ] = true
}
}
// If there is an unfinished component
if idx != nil {
// Store the fragment
store(diff.Text[idx[0]:], typ)
// and remove it from this block
diff.Text = diff.Text[:idx[0]]
}
// If that hasn't left the block empty
if len(diff.Text) > 0 {
// if the last block of this type was after the last equal block
if last[typ] > last[equal] {
// store this blocks content on that block
fixedup[last[typ]].Text += diff.Text
} else {
// otherwise store the position of the last block of this type and store the block
last[typ] = len(fixedup)
fixedup = append(fixedup, diff)
}
}
continue
}
}
// pop off any remaining stored content
fixedup = pop(insert, fixedup)
fixedup = pop(delete, fixedup)
return fixedup
}
func diffToHTML(fileName string, diffs []diffmatchpatch.Diff, lineType DiffLineType) DiffInline {
buf := bytes.NewBuffer(nil)
match := ""
diffs = fixupBrokenSpans(diffs)
for _, diff := range diffs {
if shouldWriteInline(diff, lineType) {
if len(match) > 0 {
diff.Text = match + diff.Text
match = ""
}
// Chroma HTML syntax highlighting is done before diffing individual lines in order to maintain consistency.
// Since inline changes might split in the middle of a chroma span tag or HTML entity, make we manually put it back together
// before writing so we don't try insert added/removed code spans in the middle of one of those
// and create broken HTML. This is done by moving incomplete HTML forward until it no longer matches our pattern of
// a line ending with an incomplete HTML entity or partial/opening <span>.
// EX:
// diffs[{Type: dmp.DiffDelete, Text: "language</span><span "},
// {Type: dmp.DiffEqual, Text: "c"},
// {Type: dmp.DiffDelete, Text: "lass="p">}]
// After first iteration
// diffs[{Type: dmp.DiffDelete, Text: "language</span>"}, //write out
// {Type: dmp.DiffEqual, Text: "<span c"},
// {Type: dmp.DiffDelete, Text: "lass="p">,</span>}]
// After second iteration
// {Type: dmp.DiffEqual, Text: ""}, // write out
// {Type: dmp.DiffDelete, Text: "<span class="p">,</span>}]
// Final
// {Type: dmp.DiffDelete, Text: "<span class="p">,</span>}]
// end up writing <span class="removed-code"><span class="p">,</span></span>
// Instead of <span class="removed-code">lass="p",</span></span>
m := trailingSpanRegex.FindStringSubmatchIndex(diff.Text)
if m != nil {
match = diff.Text[m[0]:m[1]]
diff.Text = strings.TrimSuffix(diff.Text, match)
}
m = entityRegex.FindStringSubmatchIndex(diff.Text)
if m != nil {
match = diff.Text[m[0]:m[1]]
diff.Text = strings.TrimSuffix(diff.Text, match)
}
// Print an existing closing span first before opening added/remove-code span so it doesn't unintentionally close it
if strings.HasPrefix(diff.Text, "</span>") {
buf.WriteString("</span>")
diff.Text = strings.TrimPrefix(diff.Text, "</span>")
}
// If we weren't able to fix it then this should avoid broken HTML by not inserting more spans below
// The previous/next diff section will contain the rest of the tag that is missing here
if strings.Count(diff.Text, "<") != strings.Count(diff.Text, ">") {
buf.WriteString(diff.Text)
continue
}
}
switch {
case diff.Type == diffmatchpatch.DiffEqual:
buf.WriteString(diff.Text)
case diff.Type == diffmatchpatch.DiffInsert && lineType == DiffLineAdd:
buf.Write(addedCodePrefix)
buf.WriteString(diff.Text)
buf.Write(codeTagSuffix)
case diff.Type == diffmatchpatch.DiffDelete && lineType == DiffLineDel:
buf.Write(removedCodePrefix)
buf.WriteString(diff.Text)
buf.Write(codeTagSuffix)
}
}
return DiffInlineWithUnicodeEscape(template.HTML(buf.String()))
}
// GetLine gets a specific line by type (add or del) and file line number
func (diffSection *DiffSection) GetLine(lineType DiffLineType, idx int) *DiffLine {
var (
difference = 0
addCount = 0
delCount = 0
matchDiffLine *DiffLine
)
LOOP:
for _, diffLine := range diffSection.Lines {
switch diffLine.Type {
case DiffLineAdd:
addCount++
case DiffLineDel:
delCount++
default:
if matchDiffLine != nil {
break LOOP
}
difference = diffLine.RightIdx - diffLine.LeftIdx
addCount = 0
delCount = 0
}
switch lineType {
case DiffLineDel:
if diffLine.RightIdx == 0 && diffLine.LeftIdx == idx-difference {
matchDiffLine = diffLine
}
case DiffLineAdd:
if diffLine.LeftIdx == 0 && diffLine.RightIdx == idx+difference {
matchDiffLine = diffLine
}
}
}
if addCount == delCount {
return matchDiffLine
}
return nil
}
var diffMatchPatch = diffmatchpatch.New()
func init() {
diffMatchPatch.DiffEditCost = 100
}
// DiffInline is a struct that has a content and escape status
type DiffInline struct {
EscapeStatus charset.EscapeStatus
Content template.HTML
}
// DiffInlineWithUnicodeEscape makes a DiffInline with hidden unicode characters escaped
func DiffInlineWithUnicodeEscape(s template.HTML) DiffInline {
status, content := charset.EscapeControlString(string(s))
return DiffInline{EscapeStatus: status, Content: template.HTML(content)}
}
// DiffInlineWithHighlightCode makes a DiffInline with code highlight and hidden unicode characters escaped
func DiffInlineWithHighlightCode(fileName, language, code string) DiffInline {
status, content := charset.EscapeControlString(highlight.Code(fileName, language, code))
return DiffInline{EscapeStatus: status, Content: template.HTML(content)}
}
// GetComputedInlineDiffFor computes inline diff for the given line.
func (diffSection *DiffSection) GetComputedInlineDiffFor(diffLine *DiffLine) DiffInline {
if setting.Git.DisableDiffHighlight {
return getLineContent(diffLine.Content[1:])
}
var (
compareDiffLine *DiffLine
diff1 string
diff2 string
)
language := ""
if diffSection.file != nil {
language = diffSection.file.Language
}
// try to find equivalent diff line. ignore, otherwise
switch diffLine.Type {
case DiffLineSection:
return getLineContent(diffLine.Content[1:])
case DiffLineAdd:
compareDiffLine = diffSection.GetLine(DiffLineDel, diffLine.RightIdx)
if compareDiffLine == nil {
return DiffInlineWithHighlightCode(diffSection.FileName, language, diffLine.Content[1:])
}
diff1 = compareDiffLine.Content
diff2 = diffLine.Content
case DiffLineDel:
compareDiffLine = diffSection.GetLine(DiffLineAdd, diffLine.LeftIdx)
if compareDiffLine == nil {
return DiffInlineWithHighlightCode(diffSection.FileName, language, diffLine.Content[1:])
}
diff1 = diffLine.Content
diff2 = compareDiffLine.Content
default:
if strings.IndexByte(" +-", diffLine.Content[0]) > -1 {
return DiffInlineWithHighlightCode(diffSection.FileName, language, diffLine.Content[1:])
}
return DiffInlineWithHighlightCode(diffSection.FileName, language, diffLine.Content)
}
diffRecord := diffMatchPatch.DiffMain(highlight.Code(diffSection.FileName, language, diff1[1:]), highlight.Code(diffSection.FileName, language, diff2[1:]), true)
diffRecord = diffMatchPatch.DiffCleanupEfficiency(diffRecord)
return diffToHTML(diffSection.FileName, diffRecord, diffLine.Type)
}
// DiffFile represents a file diff.
type DiffFile struct {
Name string
NameHash string
OldName string
Index int
Addition, Deletion int
Type DiffFileType
IsCreated bool
IsDeleted bool
IsBin bool
IsLFSFile bool
IsRenamed bool
IsAmbiguous bool
IsSubmodule bool
Sections []*DiffSection
IsIncomplete bool
IsIncompleteLineTooLong bool
IsProtected bool
IsGenerated bool
IsVendored bool
IsViewed bool // User specific
HasChangedSinceLastReview bool // User specific
Language string
}
// GetType returns type of diff file.
func (diffFile *DiffFile) GetType() int {
return int(diffFile.Type)
}
// GetTailSection creates a fake DiffLineSection if the last section is not the end of the file
func (diffFile *DiffFile) GetTailSection(gitRepo *git.Repository, leftCommitID, rightCommitID string) *DiffSection {
if len(diffFile.Sections) == 0 || diffFile.Type != DiffFileChange || diffFile.IsBin || diffFile.IsLFSFile {
return nil
}
leftCommit, err := gitRepo.GetCommit(leftCommitID)
if err != nil {
return nil
}
rightCommit, err := gitRepo.GetCommit(rightCommitID)
if err != nil {
return nil
}
lastSection := diffFile.Sections[len(diffFile.Sections)-1]
lastLine := lastSection.Lines[len(lastSection.Lines)-1]
leftLineCount := getCommitFileLineCount(leftCommit, diffFile.Name)
rightLineCount := getCommitFileLineCount(rightCommit, diffFile.Name)
if leftLineCount <= lastLine.LeftIdx || rightLineCount <= lastLine.RightIdx {
return nil
}
tailDiffLine := &DiffLine{
Type: DiffLineSection,
Content: " ",
SectionInfo: &DiffLineSectionInfo{
Path: diffFile.Name,
LastLeftIdx: lastLine.LeftIdx,
LastRightIdx: lastLine.RightIdx,
LeftIdx: leftLineCount,
RightIdx: rightLineCount,
},
}
tailSection := &DiffSection{FileName: diffFile.Name, Lines: []*DiffLine{tailDiffLine}}
return tailSection
}
// GetDiffFileName returns the name of the diff file, or its old name in case it was deleted
func (diffFile *DiffFile) GetDiffFileName() string {
if diffFile.Name == "" {
return diffFile.OldName
}
return diffFile.Name
}
func (diffFile *DiffFile) ShouldBeHidden() bool {
return diffFile.IsGenerated || diffFile.IsViewed
}
func getCommitFileLineCount(commit *git.Commit, filePath string) int {
blob, err := commit.GetBlobByPath(filePath)
if err != nil {
return 0
}
lineCount, err := blob.GetBlobLineCount()
if err != nil {
return 0
}
return lineCount
}
// Diff represents a difference between two git trees.
type Diff struct {
Start, End string
NumFiles int
TotalAddition, TotalDeletion int
Files []*DiffFile
IsIncomplete bool
NumViewedFiles int // user-specific
}
// LoadComments loads comments into each line
func (diff *Diff) LoadComments(ctx context.Context, issue *issues_model.Issue, currentUser *user_model.User) error {
allComments, err := issues_model.FetchCodeComments(ctx, issue, currentUser)
if err != nil {
return err
}
for _, file := range diff.Files {
if lineCommits, ok := allComments[file.Name]; ok {
for _, section := range file.Sections {
for _, line := range section.Lines {
if comments, ok := lineCommits[int64(line.LeftIdx*-1)]; ok {
line.Comments = append(line.Comments, comments...)
}
if comments, ok := lineCommits[int64(line.RightIdx)]; ok {
line.Comments = append(line.Comments, comments...)
}
sort.SliceStable(line.Comments, func(i, j int) bool {
return line.Comments[i].CreatedUnix < line.Comments[j].CreatedUnix
})
}
}
}
}
return nil
}
const cmdDiffHead = "diff --git "
// ParsePatch builds a Diff object from a io.Reader and some parameters.
func ParsePatch(maxLines, maxLineCharacters, maxFiles int, reader io.Reader, skipToFile string) (*Diff, error) {
log.Debug("ParsePatch(%d, %d, %d, ..., %s)", maxLines, maxLineCharacters, maxFiles, skipToFile)
var curFile *DiffFile
skipping := skipToFile != ""
diff := &Diff{Files: make([]*DiffFile, 0)}
sb := strings.Builder{}
// OK let's set a reasonable buffer size.
// This should be let's say at least the size of maxLineCharacters or 4096 whichever is larger.
readerSize := maxLineCharacters
if readerSize < 4096 {
readerSize = 4096
}
input := bufio.NewReaderSize(reader, readerSize)
line, err := input.ReadString('\n')
if err != nil {
if err == io.EOF {
return diff, nil
}
return diff, err
}
parsingLoop:
for {
// 1. A patch file always begins with `diff --git ` + `a/path b/path` (possibly quoted)
// if it does not we have bad input!
if !strings.HasPrefix(line, cmdDiffHead) {
return diff, fmt.Errorf("invalid first file line: %s", line)
}
if maxFiles > -1 && len(diff.Files) >= maxFiles {
lastFile := createDiffFile(diff, line)
diff.End = lastFile.Name
diff.IsIncomplete = true
_, err := io.Copy(io.Discard, reader)
if err != nil {
// By the definition of io.Copy this never returns io.EOF
return diff, fmt.Errorf("error during io.Copy: %w", err)
}
break parsingLoop
}
curFile = createDiffFile(diff, line)
if skipping {
if curFile.Name != skipToFile {
line, err = skipToNextDiffHead(input)
if err != nil {
if err == io.EOF {
return diff, nil
}
return diff, err
}
continue
}
skipping = false
}
diff.Files = append(diff.Files, curFile)
// 2. It is followed by one or more extended header lines:
//
// old mode <mode>
// new mode <mode>
// deleted file mode <mode>
// new file mode <mode>
// copy from <path>
// copy to <path>
// rename from <path>
// rename to <path>
// similarity index <number>
// dissimilarity index <number>
// index <hash>..<hash> <mode>
//
// * <mode> 6-digit octal numbers including the file type and file permission bits.
// * <path> does not include the a/ and b/ prefixes
// * <number> percentage of unchanged lines for similarity, percentage of changed
// lines dissimilarity as integer rounded down with terminal %. 100% => equal files.
// * The index line includes the blob object names before and after the change.
// The <mode> is included if the file mode does not change; otherwise, separate
// lines indicate the old and the new mode.
// 3. Following this header the "standard unified" diff format header may be encountered: (but not for every case...)
//
// --- a/<path>
// +++ b/<path>
//
// With multiple hunks
//
// @@ <hunk descriptor> @@
// +added line
// -removed line
// unchanged line
//
// 4. Binary files get:
//
// Binary files a/<path> and b/<path> differ
//
// but one of a/<path> and b/<path> could be /dev/null.
curFileLoop:
for {
line, err = input.ReadString('\n')
if err != nil {
if err != io.EOF {
return diff, err
}
break parsingLoop
}
switch {
case strings.HasPrefix(line, cmdDiffHead):
break curFileLoop
case strings.HasPrefix(line, "old mode ") ||
strings.HasPrefix(line, "new mode "):
if strings.HasSuffix(line, " 160000\n") {
curFile.IsSubmodule = true
}
case strings.HasPrefix(line, "rename from "):
curFile.IsRenamed = true
curFile.Type = DiffFileRename
if curFile.IsAmbiguous {
curFile.OldName = line[len("rename from ") : len(line)-1]
}
case strings.HasPrefix(line, "rename to "):
curFile.IsRenamed = true
curFile.Type = DiffFileRename
if curFile.IsAmbiguous {
curFile.Name = line[len("rename to ") : len(line)-1]
curFile.IsAmbiguous = false
}
case strings.HasPrefix(line, "copy from "):
curFile.IsRenamed = true
curFile.Type = DiffFileCopy
if curFile.IsAmbiguous {
curFile.OldName = line[len("copy from ") : len(line)-1]
}
case strings.HasPrefix(line, "copy to "):
curFile.IsRenamed = true
curFile.Type = DiffFileCopy
if curFile.IsAmbiguous {
curFile.Name = line[len("copy to ") : len(line)-1]
curFile.IsAmbiguous = false
}
case strings.HasPrefix(line, "new file"):
curFile.Type = DiffFileAdd
curFile.IsCreated = true
if strings.HasSuffix(line, " 160000\n") {
curFile.IsSubmodule = true
}
case strings.HasPrefix(line, "deleted"):
curFile.Type = DiffFileDel
curFile.IsDeleted = true
if strings.HasSuffix(line, " 160000\n") {
curFile.IsSubmodule = true
}
case strings.HasPrefix(line, "index"):
if strings.HasSuffix(line, " 160000\n") {
curFile.IsSubmodule = true
}
case strings.HasPrefix(line, "similarity index 100%"):
curFile.Type = DiffFileRename
case strings.HasPrefix(line, "Binary"):
curFile.IsBin = true
case strings.HasPrefix(line, "--- "):
// Handle ambiguous filenames
if curFile.IsAmbiguous {
// The shortest string that can end up here is:
// "--- a\t\n" without the quotes.
// This line has a len() of 7 but doesn't contain a oldName.
// So the amount that the line need is at least 8 or more.
// The code will otherwise panic for a out-of-bounds.
if len(line) > 7 && line[4] == 'a' {
curFile.OldName = line[6 : len(line)-1]
if line[len(line)-2] == '\t' {
curFile.OldName = curFile.OldName[:len(curFile.OldName)-1]
}
} else {
curFile.OldName = ""
}
}
// Otherwise do nothing with this line
case strings.HasPrefix(line, "+++ "):
// Handle ambiguous filenames
if curFile.IsAmbiguous {
if len(line) > 6 && line[4] == 'b' {
curFile.Name = line[6 : len(line)-1]
if line[len(line)-2] == '\t' {
curFile.Name = curFile.Name[:len(curFile.Name)-1]
}
if curFile.OldName == "" {
curFile.OldName = curFile.Name
}
} else {
curFile.Name = curFile.OldName
}
curFile.IsAmbiguous = false
}
// Otherwise do nothing with this line, but now switch to parsing hunks
lineBytes, isFragment, err := parseHunks(curFile, maxLines, maxLineCharacters, input)
diff.TotalAddition += curFile.Addition
diff.TotalDeletion += curFile.Deletion
if err != nil {
if err != io.EOF {
return diff, err
}
break parsingLoop
}
sb.Reset()
_, _ = sb.Write(lineBytes)
for isFragment {
lineBytes, isFragment, err = input.ReadLine()
if err != nil {
// Now by the definition of ReadLine this cannot be io.EOF
return diff, fmt.Errorf("unable to ReadLine: %w", err)
}
_, _ = sb.Write(lineBytes)
}
line = sb.String()
sb.Reset()
break curFileLoop
}
}
}
// TODO: There are numerous issues with this:
// - we might want to consider detecting encoding while parsing but...
// - we're likely to fail to get the correct encoding here anyway as we won't have enough information
diffLineTypeBuffers := make(map[DiffLineType]*bytes.Buffer, 3)
diffLineTypeDecoders := make(map[DiffLineType]*encoding.Decoder, 3)
diffLineTypeBuffers[DiffLinePlain] = new(bytes.Buffer)
diffLineTypeBuffers[DiffLineAdd] = new(bytes.Buffer)
diffLineTypeBuffers[DiffLineDel] = new(bytes.Buffer)
for _, f := range diff.Files {
f.NameHash = base.EncodeSha1(f.Name)
for _, buffer := range diffLineTypeBuffers {
buffer.Reset()
}
for _, sec := range f.Sections {
for _, l := range sec.Lines {
if l.Type == DiffLineSection {
continue
}
diffLineTypeBuffers[l.Type].WriteString(l.Content[1:])
diffLineTypeBuffers[l.Type].WriteString("\n")
}
}
for lineType, buffer := range diffLineTypeBuffers {
diffLineTypeDecoders[lineType] = nil
if buffer.Len() == 0 {
continue
}
charsetLabel, err := charset.DetectEncoding(buffer.Bytes())
if charsetLabel != "UTF-8" && err == nil {
encoding, _ := stdcharset.Lookup(charsetLabel)
if encoding != nil {
diffLineTypeDecoders[lineType] = encoding.NewDecoder()
}
}
}
for _, sec := range f.Sections {
for _, l := range sec.Lines {
decoder := diffLineTypeDecoders[l.Type]
if decoder != nil {
if c, _, err := transform.String(decoder, l.Content[1:]); err == nil {
l.Content = l.Content[0:1] + c
}
}
}
}
}
diff.NumFiles = len(diff.Files)
return diff, nil
}
func skipToNextDiffHead(input *bufio.Reader) (line string, err error) {
// need to skip until the next cmdDiffHead
var isFragment, wasFragment bool
var lineBytes []byte
for {
lineBytes, isFragment, err = input.ReadLine()
if err != nil {
return
}
if wasFragment {
wasFragment = isFragment
continue
}
if bytes.HasPrefix(lineBytes, []byte(cmdDiffHead)) {
break
}
wasFragment = isFragment
}
line = string(lineBytes)
if isFragment {
var tail string
tail, err = input.ReadString('\n')
if err != nil {
return
}
line += tail
}
return line, err
}
func parseHunks(curFile *DiffFile, maxLines, maxLineCharacters int, input *bufio.Reader) (lineBytes []byte, isFragment bool, err error) {
sb := strings.Builder{}
var (
curSection *DiffSection
curFileLinesCount int
curFileLFSPrefix bool
)
lastLeftIdx := -1
leftLine, rightLine := 1, 1
for {
for isFragment {
curFile.IsIncomplete = true
curFile.IsIncompleteLineTooLong = true
_, isFragment, err = input.ReadLine()
if err != nil {
// Now by the definition of ReadLine this cannot be io.EOF
err = fmt.Errorf("unable to ReadLine: %w", err)
return
}
}
sb.Reset()
lineBytes, isFragment, err = input.ReadLine()
if err != nil {
if err == io.EOF {
return
}
err = fmt.Errorf("unable to ReadLine: %w", err)
return
}
if lineBytes[0] == 'd' {
// End of hunks
return
}
switch lineBytes[0] {
case '@':
if maxLines > -1 && curFileLinesCount >= maxLines {
curFile.IsIncomplete = true
continue
}
_, _ = sb.Write(lineBytes)
for isFragment {
// This is very odd indeed - we're in a section header and the line is too long
// This really shouldn't happen...
lineBytes, isFragment, err = input.ReadLine()
if err != nil {
// Now by the definition of ReadLine this cannot be io.EOF
err = fmt.Errorf("unable to ReadLine: %w", err)
return
}
_, _ = sb.Write(lineBytes)
}
line := sb.String()
// Create a new section to represent this hunk
curSection = &DiffSection{file: curFile}
lastLeftIdx = -1
curFile.Sections = append(curFile.Sections, curSection)
lineSectionInfo := getDiffLineSectionInfo(curFile.Name, line, leftLine-1, rightLine-1)
diffLine := &DiffLine{
Type: DiffLineSection,
Content: line,
SectionInfo: lineSectionInfo,
}
curSection.Lines = append(curSection.Lines, diffLine)
curSection.FileName = curFile.Name
// update line number.
leftLine = lineSectionInfo.LeftIdx
rightLine = lineSectionInfo.RightIdx
continue
case '\\':
if maxLines > -1 && curFileLinesCount >= maxLines {
curFile.IsIncomplete = true
continue
}
// This is used only to indicate that the current file does not have a terminal newline
if !bytes.Equal(lineBytes, []byte("\\ No newline at end of file")) {
err = fmt.Errorf("unexpected line in hunk: %s", string(lineBytes))
return
}
// Technically this should be the end the file!
// FIXME: we should be putting a marker at the end of the file if there is no terminal new line
continue
case '+':
curFileLinesCount++
curFile.Addition++
if maxLines > -1 && curFileLinesCount >= maxLines {
curFile.IsIncomplete = true
continue
}
diffLine := &DiffLine{Type: DiffLineAdd, RightIdx: rightLine, Match: -1}
rightLine++
if curSection == nil {
// Create a new section to represent this hunk
curSection = &DiffSection{file: curFile}
curFile.Sections = append(curFile.Sections, curSection)
lastLeftIdx = -1
}
if lastLeftIdx > -1 {
diffLine.Match = lastLeftIdx
curSection.Lines[lastLeftIdx].Match = len(curSection.Lines)
lastLeftIdx++
if lastLeftIdx >= len(curSection.Lines) || curSection.Lines[lastLeftIdx].Type != DiffLineDel {
lastLeftIdx = -1
}
}
curSection.Lines = append(curSection.Lines, diffLine)
case '-':
curFileLinesCount++
curFile.Deletion++
if maxLines > -1 && curFileLinesCount >= maxLines {
curFile.IsIncomplete = true
continue
}
diffLine := &DiffLine{Type: DiffLineDel, LeftIdx: leftLine, Match: -1}
if leftLine > 0 {
leftLine++
}
if curSection == nil {
// Create a new section to represent this hunk
curSection = &DiffSection{file: curFile}
curFile.Sections = append(curFile.Sections, curSection)
lastLeftIdx = -1
}
if len(curSection.Lines) == 0 || curSection.Lines[len(curSection.Lines)-1].Type != DiffLineDel {
lastLeftIdx = len(curSection.Lines)
}
curSection.Lines = append(curSection.Lines, diffLine)
case ' ':
curFileLinesCount++
if maxLines > -1 && curFileLinesCount >= maxLines {
curFile.IsIncomplete = true
continue
}
diffLine := &DiffLine{Type: DiffLinePlain, LeftIdx: leftLine, RightIdx: rightLine}
leftLine++
rightLine++
lastLeftIdx = -1
if curSection == nil {
// Create a new section to represent this hunk
curSection = &DiffSection{file: curFile}
curFile.Sections = append(curFile.Sections, curSection)
}
curSection.Lines = append(curSection.Lines, diffLine)
default:
// This is unexpected
err = fmt.Errorf("unexpected line in hunk: %s", string(lineBytes))
return
}
line := string(lineBytes)
if isFragment {
curFile.IsIncomplete = true
curFile.IsIncompleteLineTooLong = true
for isFragment {
lineBytes, isFragment, err = input.ReadLine()
if err != nil {
// Now by the definition of ReadLine this cannot be io.EOF
err = fmt.Errorf("unable to ReadLine: %w", err)
return
}
}
}
if len(line) > maxLineCharacters {
curFile.IsIncomplete = true
curFile.IsIncompleteLineTooLong = true
line = line[:maxLineCharacters]
}
curSection.Lines[len(curSection.Lines)-1].Content = line
// handle LFS
if line[1:] == lfs.MetaFileIdentifier {
curFileLFSPrefix = true
} else if curFileLFSPrefix && strings.HasPrefix(line[1:], lfs.MetaFileOidPrefix) {
oid := strings.TrimPrefix(line[1:], lfs.MetaFileOidPrefix)
if len(oid) == 64 {
m := &git_model.LFSMetaObject{Pointer: lfs.Pointer{Oid: oid}}
count, err := db.CountByBean(db.DefaultContext, m)
if err == nil && count > 0 {
curFile.IsBin = true
curFile.IsLFSFile = true
curSection.Lines = nil
lastLeftIdx = -1
}
}
}
}
}
func createDiffFile(diff *Diff, line string) *DiffFile {
// The a/ and b/ filenames are the same unless rename/copy is involved.
// Especially, even for a creation or a deletion, /dev/null is not used
// in place of the a/ or b/ filenames.
//
// When rename/copy is involved, file1 and file2 show the name of the
// source file of the rename/copy and the name of the file that rename/copy
// produces, respectively.
//
// Path names are quoted if necessary.
//
// This means that you should always be able to determine the file name even when there
// there is potential ambiguity...
//
// but we can be simpler with our heuristics by just forcing git to prefix things nicely
curFile := &DiffFile{
Index: len(diff.Files) + 1,
Type: DiffFileChange,
Sections: make([]*DiffSection, 0, 10),
}
rd := strings.NewReader(line[len(cmdDiffHead):] + " ")
curFile.Type = DiffFileChange
var oldNameAmbiguity, newNameAmbiguity bool
curFile.OldName, oldNameAmbiguity = readFileName(rd)
curFile.Name, newNameAmbiguity = readFileName(rd)
if oldNameAmbiguity && newNameAmbiguity {
curFile.IsAmbiguous = true
// OK we should bet that the oldName and the newName are the same if they can be made to be same
// So we need to start again ...
if (len(line)-len(cmdDiffHead)-1)%2 == 0 {
// diff --git a/b b/b b/b b/b b/b b/b
//
midpoint := (len(line) + len(cmdDiffHead) - 1) / 2
new, old := line[len(cmdDiffHead):midpoint], line[midpoint+1:]
if len(new) > 2 && len(old) > 2 && new[2:] == old[2:] {
curFile.OldName = old[2:]
curFile.Name = old[2:]
}
}
}
curFile.IsRenamed = curFile.Name != curFile.OldName
return curFile
}
func readFileName(rd *strings.Reader) (string, bool) {
ambiguity := false
var name string
char, _ := rd.ReadByte()
_ = rd.UnreadByte()
if char == '"' {
fmt.Fscanf(rd, "%q ", &name)
if len(name) == 0 {
log.Error("Reader has no file name: %v", rd)
return "", true
}
if name[0] == '\\' {
name = name[1:]
}
} else {
// This technique is potentially ambiguous it may not be possible to uniquely identify the filenames from the diff line alone
ambiguity = true
fmt.Fscanf(rd, "%s ", &name)
char, _ := rd.ReadByte()
_ = rd.UnreadByte()
for !(char == 0 || char == '"' || char == 'b') {
var suffix string
fmt.Fscanf(rd, "%s ", &suffix)
name += " " + suffix
char, _ = rd.ReadByte()
_ = rd.UnreadByte()
}
}
if len(name) < 2 {
log.Error("Unable to determine name from reader: %v", rd)
return "", true
}
return name[2:], ambiguity
}
// DiffOptions represents the options for a DiffRange
type DiffOptions struct {
BeforeCommitID string
AfterCommitID string
SkipTo string
MaxLines int
MaxLineCharacters int
MaxFiles int
WhitespaceBehavior string
DirectComparison bool
}
// GetDiff builds a Diff between two commits of a repository.
// Passing the empty string as beforeCommitID returns a diff from the parent commit.
// The whitespaceBehavior is either an empty string or a git flag
func GetDiff(gitRepo *git.Repository, opts *DiffOptions, files ...string) (*Diff, error) {
repoPath := gitRepo.Path
commit, err := gitRepo.GetCommit(opts.AfterCommitID)
if err != nil {
return nil, err
}
argsLength := 6
if len(opts.WhitespaceBehavior) > 0 {
argsLength++
}
if len(opts.SkipTo) > 0 {
argsLength++
}
if len(files) > 0 {
argsLength += len(files) + 1
}
diffArgs := make([]string, 0, argsLength)
if (len(opts.BeforeCommitID) == 0 || opts.BeforeCommitID == git.EmptySHA) && commit.ParentCount() == 0 {
diffArgs = append(diffArgs, "diff", "--src-prefix=\\a/", "--dst-prefix=\\b/", "-M")
if len(opts.WhitespaceBehavior) != 0 {
diffArgs = append(diffArgs, opts.WhitespaceBehavior)
}
// append empty tree ref
diffArgs = append(diffArgs, "4b825dc642cb6eb9a060e54bf8d69288fbee4904")
diffArgs = append(diffArgs, opts.AfterCommitID)
} else {
actualBeforeCommitID := opts.BeforeCommitID
if len(actualBeforeCommitID) == 0 {
parentCommit, _ := commit.Parent(0)
actualBeforeCommitID = parentCommit.ID.String()
}
diffArgs = append(diffArgs, "diff", "--src-prefix=\\a/", "--dst-prefix=\\b/", "-M")
if len(opts.WhitespaceBehavior) != 0 {
diffArgs = append(diffArgs, opts.WhitespaceBehavior)
}
diffArgs = append(diffArgs, actualBeforeCommitID)
diffArgs = append(diffArgs, opts.AfterCommitID)
opts.BeforeCommitID = actualBeforeCommitID
}
// In git 2.31, git diff learned --skip-to which we can use to shortcut skip to file
// so if we are using at least this version of git we don't have to tell ParsePatch to do
// the skipping for us
parsePatchSkipToFile := opts.SkipTo
if opts.SkipTo != "" && git.CheckGitVersionAtLeast("2.31") == nil {
diffArgs = append(diffArgs, "--skip-to="+opts.SkipTo)
parsePatchSkipToFile = ""
}
if len(files) > 0 {
diffArgs = append(diffArgs, "--")
diffArgs = append(diffArgs, files...)
}
reader, writer := io.Pipe()
defer func() {
_ = reader.Close()
_ = writer.Close()
}()
go func(ctx context.Context, diffArgs []string, repoPath string, writer *io.PipeWriter) {
cmd := git.NewCommand(ctx, diffArgs...)
cmd.SetDescription(fmt.Sprintf("GetDiffRange [repo_path: %s]", repoPath))
if err := cmd.Run(&git.RunOpts{
Timeout: time.Duration(setting.Git.Timeout.Default) * time.Second,
Dir: repoPath,
Stderr: os.Stderr,
Stdout: writer,
}); err != nil {
log.Error("error during RunWithContext: %w", err)
}
_ = writer.Close()
}(gitRepo.Ctx, diffArgs, repoPath, writer)
diff, err := ParsePatch(opts.MaxLines, opts.MaxLineCharacters, opts.MaxFiles, reader, parsePatchSkipToFile)
if err != nil {
return nil, fmt.Errorf("unable to ParsePatch: %w", err)
}
diff.Start = opts.SkipTo
checker, deferable := gitRepo.CheckAttributeReader(opts.AfterCommitID)
defer deferable()
for _, diffFile := range diff.Files {
gotVendor := false
gotGenerated := false
if checker != nil {
attrs, err := checker.CheckPath(diffFile.Name)
if err == nil {
if vendored, has := attrs["linguist-vendored"]; has {
if vendored == "set" || vendored == "true" {
diffFile.IsVendored = true
gotVendor = true
} else {
gotVendor = vendored == "false"
}
}
if generated, has := attrs["linguist-generated"]; has {
if generated == "set" || generated == "true" {
diffFile.IsGenerated = true
gotGenerated = true
} else {
gotGenerated = generated == "false"
}
}
if language, has := attrs["linguist-language"]; has && language != "unspecified" && language != "" {
diffFile.Language = language
} else if language, has := attrs["gitlab-language"]; has && language != "unspecified" && language != "" {
diffFile.Language = language
}
} else {
log.Error("Unexpected error: %v", err)
}
}
if !gotVendor {
diffFile.IsVendored = analyze.IsVendor(diffFile.Name)
}
if !gotGenerated {
diffFile.IsGenerated = analyze.IsGenerated(diffFile.Name)
}
tailSection := diffFile.GetTailSection(gitRepo, opts.BeforeCommitID, opts.AfterCommitID)
if tailSection != nil {
diffFile.Sections = append(diffFile.Sections, tailSection)
}
}
separator := "..."
if opts.DirectComparison {
separator = ".."
}
shortstatArgs := []string{opts.BeforeCommitID + separator + opts.AfterCommitID}
if len(opts.BeforeCommitID) == 0 || opts.BeforeCommitID == git.EmptySHA {
shortstatArgs = []string{git.EmptyTreeSHA, opts.AfterCommitID}
}
diff.NumFiles, diff.TotalAddition, diff.TotalDeletion, err = git.GetDiffShortStat(gitRepo.Ctx, repoPath, shortstatArgs...)
if err != nil && strings.Contains(err.Error(), "no merge base") {
// git >= 2.28 now returns an error if base and head have become unrelated.
// previously it would return the results of git diff --shortstat base head so let's try that...
shortstatArgs = []string{opts.BeforeCommitID, opts.AfterCommitID}
diff.NumFiles, diff.TotalAddition, diff.TotalDeletion, err = git.GetDiffShortStat(gitRepo.Ctx, repoPath, shortstatArgs...)
}
if err != nil {
return nil, err
}
return diff, nil
}
// SyncAndGetUserSpecificDiff is like GetDiff, except that user specific data such as which files the given user has already viewed on the given PR will also be set
// Additionally, the database asynchronously is updated if files have changed since the last review
func SyncAndGetUserSpecificDiff(ctx context.Context, userID int64, pull *issues_model.PullRequest, gitRepo *git.Repository, opts *DiffOptions, files ...string) (*Diff, error) {
diff, err := GetDiff(gitRepo, opts, files...)
if err != nil {
return nil, err
}
review, err := pull_model.GetNewestReviewState(ctx, userID, pull.ID)
if err != nil || review == nil || review.UpdatedFiles == nil {
return diff, err
}
latestCommit := opts.AfterCommitID
if latestCommit == "" {
latestCommit = pull.HeadBranch // opts.AfterCommitID is preferred because it handles PRs from forks correctly and the branch name doesn't
}
changedFiles, err := gitRepo.GetFilesChangedBetween(review.CommitSHA, latestCommit)
if err != nil {
return diff, err
}
filesChangedSinceLastDiff := make(map[string]pull_model.ViewedState)
outer:
for _, diffFile := range diff.Files {
fileViewedState := review.UpdatedFiles[diffFile.GetDiffFileName()]
// Check whether it was previously detected that the file has changed since the last review
if fileViewedState == pull_model.HasChanged {
diffFile.HasChangedSinceLastReview = true
continue
}
filename := diffFile.GetDiffFileName()
// Check explicitly whether the file has changed since the last review
for _, changedFile := range changedFiles {
diffFile.HasChangedSinceLastReview = filename == changedFile
if diffFile.HasChangedSinceLastReview {
filesChangedSinceLastDiff[filename] = pull_model.HasChanged
continue outer // We don't want to check if the file is viewed here as that would fold the file, which is in this case unwanted
}
}
// Check whether the file has already been viewed
if fileViewedState == pull_model.Viewed {
diffFile.IsViewed = true
diff.NumViewedFiles++
}
}
// Explicitly store files that have changed in the database, if any is present at all.
// This has the benefit that the "Has Changed" attribute will be present as long as the user does not explicitly mark this file as viewed, so it will even survive a page reload after marking another file as viewed.
// On the other hand, this means that even if a commit reverting an unseen change is committed, the file will still be seen as changed.
if len(filesChangedSinceLastDiff) > 0 {
err := pull_model.UpdateReviewState(ctx, review.UserID, review.PullID, review.CommitSHA, filesChangedSinceLastDiff)
if err != nil {
log.Warn("Could not update review for user %d, pull %d, commit %s and the changed files %v: %v", review.UserID, review.PullID, review.CommitSHA, filesChangedSinceLastDiff, err)
return nil, err
}
}
return diff, err
}
// CommentAsDiff returns c.Patch as *Diff
func CommentAsDiff(c *issues_model.Comment) (*Diff, error) {
diff, err := ParsePatch(setting.Git.MaxGitDiffLines,
setting.Git.MaxGitDiffLineCharacters, setting.Git.MaxGitDiffFiles, strings.NewReader(c.Patch), "")
if err != nil {
log.Error("Unable to parse patch: %v", err)
return nil, err
}
if len(diff.Files) == 0 {
return nil, fmt.Errorf("no file found for comment ID: %d", c.ID)
}
secs := diff.Files[0].Sections
if len(secs) == 0 {
return nil, fmt.Errorf("no sections found for comment ID: %d", c.ID)
}
return diff, nil
}
// CommentMustAsDiff executes AsDiff and logs the error instead of returning
func CommentMustAsDiff(c *issues_model.Comment) *Diff {
if c == nil {
return nil
}
defer func() {
if err := recover(); err != nil {
log.Error("PANIC whilst retrieving diff for comment[%d] Error: %v\nStack: %s", c.ID, err, log.Stack(2))
}
}()
diff, err := CommentAsDiff(c)
if err != nil {
log.Warn("CommentMustAsDiff: %v", err)
}
return diff
}
// GetWhitespaceFlag returns git diff flag for treating whitespaces
func GetWhitespaceFlag(whitespaceBehavior string) string {
whitespaceFlags := map[string]string{
"ignore-all": "-w",
"ignore-change": "-b",
"ignore-eol": "--ignore-space-at-eol",
"show-all": "",
}
if flag, ok := whitespaceFlags[whitespaceBehavior]; ok {
return flag
}
log.Warn("unknown whitespace behavior: %q, default to 'show-all'", whitespaceBehavior)
return ""
}