forked from nodejs/node
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathdiff.js
More file actions
2106 lines (2011 loc) Β· 76.8 KB
/
diff.js
File metadata and controls
2106 lines (2011 loc) Β· 76.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*!
diff v7.0.0
BSD 3-Clause License
Copyright (c) 2009-2015, Kevin Decker <kpdecker@gmail.com>
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@license
*/
(function (global, factory) {
typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports) :
typeof define === 'function' && define.amd ? define(['exports'], factory) :
(global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global.Diff = {}));
})(this, (function (exports) { 'use strict';
function Diff() {}
Diff.prototype = {
diff: function diff(oldString, newString) {
var _options$timeout;
var options = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : {};
var callback = options.callback;
if (typeof options === 'function') {
callback = options;
options = {};
}
var self = this;
function done(value) {
value = self.postProcess(value, options);
if (callback) {
setTimeout(function () {
callback(value);
}, 0);
return true;
} else {
return value;
}
}
// Allow subclasses to massage the input prior to running
oldString = this.castInput(oldString, options);
newString = this.castInput(newString, options);
oldString = this.removeEmpty(this.tokenize(oldString, options));
newString = this.removeEmpty(this.tokenize(newString, options));
var newLen = newString.length,
oldLen = oldString.length;
var editLength = 1;
var maxEditLength = newLen + oldLen;
if (options.maxEditLength != null) {
maxEditLength = Math.min(maxEditLength, options.maxEditLength);
}
var maxExecutionTime = (_options$timeout = options.timeout) !== null && _options$timeout !== void 0 ? _options$timeout : Infinity;
var abortAfterTimestamp = Date.now() + maxExecutionTime;
var bestPath = [{
oldPos: -1,
lastComponent: undefined
}];
// Seed editLength = 0, i.e. the content starts with the same values
var newPos = this.extractCommon(bestPath[0], newString, oldString, 0, options);
if (bestPath[0].oldPos + 1 >= oldLen && newPos + 1 >= newLen) {
// Identity per the equality and tokenizer
return done(buildValues(self, bestPath[0].lastComponent, newString, oldString, self.useLongestToken));
}
// Once we hit the right edge of the edit graph on some diagonal k, we can
// definitely reach the end of the edit graph in no more than k edits, so
// there's no point in considering any moves to diagonal k+1 any more (from
// which we're guaranteed to need at least k+1 more edits).
// Similarly, once we've reached the bottom of the edit graph, there's no
// point considering moves to lower diagonals.
// We record this fact by setting minDiagonalToConsider and
// maxDiagonalToConsider to some finite value once we've hit the edge of
// the edit graph.
// This optimization is not faithful to the original algorithm presented in
// Myers's paper, which instead pointlessly extends D-paths off the end of
// the edit graph - see page 7 of Myers's paper which notes this point
// explicitly and illustrates it with a diagram. This has major performance
// implications for some common scenarios. For instance, to compute a diff
// where the new text simply appends d characters on the end of the
// original text of length n, the true Myers algorithm will take O(n+d^2)
// time while this optimization needs only O(n+d) time.
var minDiagonalToConsider = -Infinity,
maxDiagonalToConsider = Infinity;
// Main worker method. checks all permutations of a given edit length for acceptance.
function execEditLength() {
for (var diagonalPath = Math.max(minDiagonalToConsider, -editLength); diagonalPath <= Math.min(maxDiagonalToConsider, editLength); diagonalPath += 2) {
var basePath = void 0;
var removePath = bestPath[diagonalPath - 1],
addPath = bestPath[diagonalPath + 1];
if (removePath) {
// No one else is going to attempt to use this value, clear it
bestPath[diagonalPath - 1] = undefined;
}
var canAdd = false;
if (addPath) {
// what newPos will be after we do an insertion:
var addPathNewPos = addPath.oldPos - diagonalPath;
canAdd = addPath && 0 <= addPathNewPos && addPathNewPos < newLen;
}
var canRemove = removePath && removePath.oldPos + 1 < oldLen;
if (!canAdd && !canRemove) {
// If this path is a terminal then prune
bestPath[diagonalPath] = undefined;
continue;
}
// Select the diagonal that we want to branch from. We select the prior
// path whose position in the old string is the farthest from the origin
// and does not pass the bounds of the diff graph
if (!canRemove || canAdd && removePath.oldPos < addPath.oldPos) {
basePath = self.addToPath(addPath, true, false, 0, options);
} else {
basePath = self.addToPath(removePath, false, true, 1, options);
}
newPos = self.extractCommon(basePath, newString, oldString, diagonalPath, options);
if (basePath.oldPos + 1 >= oldLen && newPos + 1 >= newLen) {
// If we have hit the end of both strings, then we are done
return done(buildValues(self, basePath.lastComponent, newString, oldString, self.useLongestToken));
} else {
bestPath[diagonalPath] = basePath;
if (basePath.oldPos + 1 >= oldLen) {
maxDiagonalToConsider = Math.min(maxDiagonalToConsider, diagonalPath - 1);
}
if (newPos + 1 >= newLen) {
minDiagonalToConsider = Math.max(minDiagonalToConsider, diagonalPath + 1);
}
}
}
editLength++;
}
// Performs the length of edit iteration. Is a bit fugly as this has to support the
// sync and async mode which is never fun. Loops over execEditLength until a value
// is produced, or until the edit length exceeds options.maxEditLength (if given),
// in which case it will return undefined.
if (callback) {
(function exec() {
setTimeout(function () {
if (editLength > maxEditLength || Date.now() > abortAfterTimestamp) {
return callback();
}
if (!execEditLength()) {
exec();
}
}, 0);
})();
} else {
while (editLength <= maxEditLength && Date.now() <= abortAfterTimestamp) {
var ret = execEditLength();
if (ret) {
return ret;
}
}
}
},
addToPath: function addToPath(path, added, removed, oldPosInc, options) {
var last = path.lastComponent;
if (last && !options.oneChangePerToken && last.added === added && last.removed === removed) {
return {
oldPos: path.oldPos + oldPosInc,
lastComponent: {
count: last.count + 1,
added: added,
removed: removed,
previousComponent: last.previousComponent
}
};
} else {
return {
oldPos: path.oldPos + oldPosInc,
lastComponent: {
count: 1,
added: added,
removed: removed,
previousComponent: last
}
};
}
},
extractCommon: function extractCommon(basePath, newString, oldString, diagonalPath, options) {
var newLen = newString.length,
oldLen = oldString.length,
oldPos = basePath.oldPos,
newPos = oldPos - diagonalPath,
commonCount = 0;
while (newPos + 1 < newLen && oldPos + 1 < oldLen && this.equals(oldString[oldPos + 1], newString[newPos + 1], options)) {
newPos++;
oldPos++;
commonCount++;
if (options.oneChangePerToken) {
basePath.lastComponent = {
count: 1,
previousComponent: basePath.lastComponent,
added: false,
removed: false
};
}
}
if (commonCount && !options.oneChangePerToken) {
basePath.lastComponent = {
count: commonCount,
previousComponent: basePath.lastComponent,
added: false,
removed: false
};
}
basePath.oldPos = oldPos;
return newPos;
},
equals: function equals(left, right, options) {
if (options.comparator) {
return options.comparator(left, right);
} else {
return left === right || options.ignoreCase && left.toLowerCase() === right.toLowerCase();
}
},
removeEmpty: function removeEmpty(array) {
var ret = [];
for (var i = 0; i < array.length; i++) {
if (array[i]) {
ret.push(array[i]);
}
}
return ret;
},
castInput: function castInput(value) {
return value;
},
tokenize: function tokenize(value) {
return Array.from(value);
},
join: function join(chars) {
return chars.join('');
},
postProcess: function postProcess(changeObjects) {
return changeObjects;
}
};
function buildValues(diff, lastComponent, newString, oldString, useLongestToken) {
// First we convert our linked list of components in reverse order to an
// array in the right order:
var components = [];
var nextComponent;
while (lastComponent) {
components.push(lastComponent);
nextComponent = lastComponent.previousComponent;
delete lastComponent.previousComponent;
lastComponent = nextComponent;
}
components.reverse();
var componentPos = 0,
componentLen = components.length,
newPos = 0,
oldPos = 0;
for (; componentPos < componentLen; componentPos++) {
var component = components[componentPos];
if (!component.removed) {
if (!component.added && useLongestToken) {
var value = newString.slice(newPos, newPos + component.count);
value = value.map(function (value, i) {
var oldValue = oldString[oldPos + i];
return oldValue.length > value.length ? oldValue : value;
});
component.value = diff.join(value);
} else {
component.value = diff.join(newString.slice(newPos, newPos + component.count));
}
newPos += component.count;
// Common case
if (!component.added) {
oldPos += component.count;
}
} else {
component.value = diff.join(oldString.slice(oldPos, oldPos + component.count));
oldPos += component.count;
}
}
return components;
}
var characterDiff = new Diff();
function diffChars(oldStr, newStr, options) {
return characterDiff.diff(oldStr, newStr, options);
}
function longestCommonPrefix(str1, str2) {
var i;
for (i = 0; i < str1.length && i < str2.length; i++) {
if (str1[i] != str2[i]) {
return str1.slice(0, i);
}
}
return str1.slice(0, i);
}
function longestCommonSuffix(str1, str2) {
var i;
// Unlike longestCommonPrefix, we need a special case to handle all scenarios
// where we return the empty string since str1.slice(-0) will return the
// entire string.
if (!str1 || !str2 || str1[str1.length - 1] != str2[str2.length - 1]) {
return '';
}
for (i = 0; i < str1.length && i < str2.length; i++) {
if (str1[str1.length - (i + 1)] != str2[str2.length - (i + 1)]) {
return str1.slice(-i);
}
}
return str1.slice(-i);
}
function replacePrefix(string, oldPrefix, newPrefix) {
if (string.slice(0, oldPrefix.length) != oldPrefix) {
throw Error("string ".concat(JSON.stringify(string), " doesn't start with prefix ").concat(JSON.stringify(oldPrefix), "; this is a bug"));
}
return newPrefix + string.slice(oldPrefix.length);
}
function replaceSuffix(string, oldSuffix, newSuffix) {
if (!oldSuffix) {
return string + newSuffix;
}
if (string.slice(-oldSuffix.length) != oldSuffix) {
throw Error("string ".concat(JSON.stringify(string), " doesn't end with suffix ").concat(JSON.stringify(oldSuffix), "; this is a bug"));
}
return string.slice(0, -oldSuffix.length) + newSuffix;
}
function removePrefix(string, oldPrefix) {
return replacePrefix(string, oldPrefix, '');
}
function removeSuffix(string, oldSuffix) {
return replaceSuffix(string, oldSuffix, '');
}
function maximumOverlap(string1, string2) {
return string2.slice(0, overlapCount(string1, string2));
}
// Nicked from https://stackoverflow.com/a/60422853/1709587
function overlapCount(a, b) {
// Deal with cases where the strings differ in length
var startA = 0;
if (a.length > b.length) {
startA = a.length - b.length;
}
var endB = b.length;
if (a.length < b.length) {
endB = a.length;
}
// Create a back-reference for each index
// that should be followed in case of a mismatch.
// We only need B to make these references:
var map = Array(endB);
var k = 0; // Index that lags behind j
map[0] = 0;
for (var j = 1; j < endB; j++) {
if (b[j] == b[k]) {
map[j] = map[k]; // skip over the same character (optional optimisation)
} else {
map[j] = k;
}
while (k > 0 && b[j] != b[k]) {
k = map[k];
}
if (b[j] == b[k]) {
k++;
}
}
// Phase 2: use these references while iterating over A
k = 0;
for (var i = startA; i < a.length; i++) {
while (k > 0 && a[i] != b[k]) {
k = map[k];
}
if (a[i] == b[k]) {
k++;
}
}
return k;
}
/**
* Returns true if the string consistently uses Windows line endings.
*/
function hasOnlyWinLineEndings(string) {
return string.includes('\r\n') && !string.startsWith('\n') && !string.match(/[^\r]\n/);
}
/**
* Returns true if the string consistently uses Unix line endings.
*/
function hasOnlyUnixLineEndings(string) {
return !string.includes('\r\n') && string.includes('\n');
}
// Based on https://en.wikipedia.org/wiki/Latin_script_in_Unicode
//
// Ranges and exceptions:
// Latin-1 Supplement, 0080β00FF
// - U+00D7 Γ Multiplication sign
// - U+00F7 Γ· Division sign
// Latin Extended-A, 0100β017F
// Latin Extended-B, 0180β024F
// IPA Extensions, 0250β02AF
// Spacing Modifier Letters, 02B0β02FF
// - U+02C7 Λ ˇ Caron
// - U+02D8 Λ ˘ Breve
// - U+02D9 Λ ˙ Dot Above
// - U+02DA Λ ˚ Ring Above
// - U+02DB Λ ˛ Ogonek
// - U+02DC Λ ˜ Small Tilde
// - U+02DD Λ ˝ Double Acute Accent
// Latin Extended Additional, 1E00β1EFF
var extendedWordChars = "a-zA-Z0-9_\\u{C0}-\\u{FF}\\u{D8}-\\u{F6}\\u{F8}-\\u{2C6}\\u{2C8}-\\u{2D7}\\u{2DE}-\\u{2FF}\\u{1E00}-\\u{1EFF}";
// Each token is one of the following:
// - A punctuation mark plus the surrounding whitespace
// - A word plus the surrounding whitespace
// - Pure whitespace (but only in the special case where this the entire text
// is just whitespace)
//
// We have to include surrounding whitespace in the tokens because the two
// alternative approaches produce horribly broken results:
// * If we just discard the whitespace, we can't fully reproduce the original
// text from the sequence of tokens and any attempt to render the diff will
// get the whitespace wrong.
// * If we have separate tokens for whitespace, then in a typical text every
// second token will be a single space character. But this often results in
// the optimal diff between two texts being a perverse one that preserves
// the spaces between words but deletes and reinserts actual common words.
// See https://github.com/kpdecker/jsdiff/issues/160#issuecomment-1866099640
// for an example.
//
// Keeping the surrounding whitespace of course has implications for .equals
// and .join, not just .tokenize.
// This regex does NOT fully implement the tokenization rules described above.
// Instead, it gives runs of whitespace their own "token". The tokenize method
// then handles stitching whitespace tokens onto adjacent word or punctuation
// tokens.
var tokenizeIncludingWhitespace = new RegExp("[".concat(extendedWordChars, "]+|\\s+|[^").concat(extendedWordChars, "]"), 'ug');
var wordDiff = new Diff();
wordDiff.equals = function (left, right, options) {
if (options.ignoreCase) {
left = left.toLowerCase();
right = right.toLowerCase();
}
return left.trim() === right.trim();
};
wordDiff.tokenize = function (value) {
var options = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : {};
var parts;
if (options.intlSegmenter) {
if (options.intlSegmenter.resolvedOptions().granularity != 'word') {
throw new Error('The segmenter passed must have a granularity of "word"');
}
parts = Array.from(options.intlSegmenter.segment(value), function (segment) {
return segment.segment;
});
} else {
parts = value.match(tokenizeIncludingWhitespace) || [];
}
var tokens = [];
var prevPart = null;
parts.forEach(function (part) {
if (/\s/.test(part)) {
if (prevPart == null) {
tokens.push(part);
} else {
tokens.push(tokens.pop() + part);
}
} else if (/\s/.test(prevPart)) {
if (tokens[tokens.length - 1] == prevPart) {
tokens.push(tokens.pop() + part);
} else {
tokens.push(prevPart + part);
}
} else {
tokens.push(part);
}
prevPart = part;
});
return tokens;
};
wordDiff.join = function (tokens) {
// Tokens being joined here will always have appeared consecutively in the
// same text, so we can simply strip off the leading whitespace from all the
// tokens except the first (and except any whitespace-only tokens - but such
// a token will always be the first and only token anyway) and then join them
// and the whitespace around words and punctuation will end up correct.
return tokens.map(function (token, i) {
if (i == 0) {
return token;
} else {
return token.replace(/^\s+/, '');
}
}).join('');
};
wordDiff.postProcess = function (changes, options) {
if (!changes || options.oneChangePerToken) {
return changes;
}
var lastKeep = null;
// Change objects representing any insertion or deletion since the last
// "keep" change object. There can be at most one of each.
var insertion = null;
var deletion = null;
changes.forEach(function (change) {
if (change.added) {
insertion = change;
} else if (change.removed) {
deletion = change;
} else {
if (insertion || deletion) {
// May be false at start of text
dedupeWhitespaceInChangeObjects(lastKeep, deletion, insertion, change);
}
lastKeep = change;
insertion = null;
deletion = null;
}
});
if (insertion || deletion) {
dedupeWhitespaceInChangeObjects(lastKeep, deletion, insertion, null);
}
return changes;
};
function diffWords(oldStr, newStr, options) {
// This option has never been documented and never will be (it's clearer to
// just call `diffWordsWithSpace` directly if you need that behavior), but
// has existed in jsdiff for a long time, so we retain support for it here
// for the sake of backwards compatibility.
if ((options === null || options === void 0 ? void 0 : options.ignoreWhitespace) != null && !options.ignoreWhitespace) {
return diffWordsWithSpace(oldStr, newStr, options);
}
return wordDiff.diff(oldStr, newStr, options);
}
function dedupeWhitespaceInChangeObjects(startKeep, deletion, insertion, endKeep) {
// Before returning, we tidy up the leading and trailing whitespace of the
// change objects to eliminate cases where trailing whitespace in one object
// is repeated as leading whitespace in the next.
// Below are examples of the outcomes we want here to explain the code.
// I=insert, K=keep, D=delete
// 1. diffing 'foo bar baz' vs 'foo baz'
// Prior to cleanup, we have K:'foo ' D:' bar ' K:' baz'
// After cleanup, we want: K:'foo ' D:'bar ' K:'baz'
//
// 2. Diffing 'foo bar baz' vs 'foo qux baz'
// Prior to cleanup, we have K:'foo ' D:' bar ' I:' qux ' K:' baz'
// After cleanup, we want K:'foo ' D:'bar' I:'qux' K:' baz'
//
// 3. Diffing 'foo\nbar baz' vs 'foo baz'
// Prior to cleanup, we have K:'foo ' D:'\nbar ' K:' baz'
// After cleanup, we want K'foo' D:'\nbar' K:' baz'
//
// 4. Diffing 'foo baz' vs 'foo\nbar baz'
// Prior to cleanup, we have K:'foo\n' I:'\nbar ' K:' baz'
// After cleanup, we ideally want K'foo' I:'\nbar' K:' baz'
// but don't actually manage this currently (the pre-cleanup change
// objects don't contain enough information to make it possible).
//
// 5. Diffing 'foo bar baz' vs 'foo baz'
// Prior to cleanup, we have K:'foo ' D:' bar ' K:' baz'
// After cleanup, we want K:'foo ' D:' bar ' K:'baz'
//
// Our handling is unavoidably imperfect in the case where there's a single
// indel between keeps and the whitespace has changed. For instance, consider
// diffing 'foo\tbar\nbaz' vs 'foo baz'. Unless we create an extra change
// object to represent the insertion of the space character (which isn't even
// a token), we have no way to avoid losing information about the texts'
// original whitespace in the result we return. Still, we do our best to
// output something that will look sensible if we e.g. print it with
// insertions in green and deletions in red.
// Between two "keep" change objects (or before the first or after the last
// change object), we can have either:
// * A "delete" followed by an "insert"
// * Just an "insert"
// * Just a "delete"
// We handle the three cases separately.
if (deletion && insertion) {
var oldWsPrefix = deletion.value.match(/^\s*/)[0];
var oldWsSuffix = deletion.value.match(/\s*$/)[0];
var newWsPrefix = insertion.value.match(/^\s*/)[0];
var newWsSuffix = insertion.value.match(/\s*$/)[0];
if (startKeep) {
var commonWsPrefix = longestCommonPrefix(oldWsPrefix, newWsPrefix);
startKeep.value = replaceSuffix(startKeep.value, newWsPrefix, commonWsPrefix);
deletion.value = removePrefix(deletion.value, commonWsPrefix);
insertion.value = removePrefix(insertion.value, commonWsPrefix);
}
if (endKeep) {
var commonWsSuffix = longestCommonSuffix(oldWsSuffix, newWsSuffix);
endKeep.value = replacePrefix(endKeep.value, newWsSuffix, commonWsSuffix);
deletion.value = removeSuffix(deletion.value, commonWsSuffix);
insertion.value = removeSuffix(insertion.value, commonWsSuffix);
}
} else if (insertion) {
// The whitespaces all reflect what was in the new text rather than
// the old, so we essentially have no information about whitespace
// insertion or deletion. We just want to dedupe the whitespace.
// We do that by having each change object keep its trailing
// whitespace and deleting duplicate leading whitespace where
// present.
if (startKeep) {
insertion.value = insertion.value.replace(/^\s*/, '');
}
if (endKeep) {
endKeep.value = endKeep.value.replace(/^\s*/, '');
}
// otherwise we've got a deletion and no insertion
} else if (startKeep && endKeep) {
var newWsFull = endKeep.value.match(/^\s*/)[0],
delWsStart = deletion.value.match(/^\s*/)[0],
delWsEnd = deletion.value.match(/\s*$/)[0];
// Any whitespace that comes straight after startKeep in both the old and
// new texts, assign to startKeep and remove from the deletion.
var newWsStart = longestCommonPrefix(newWsFull, delWsStart);
deletion.value = removePrefix(deletion.value, newWsStart);
// Any whitespace that comes straight before endKeep in both the old and
// new texts, and hasn't already been assigned to startKeep, assign to
// endKeep and remove from the deletion.
var newWsEnd = longestCommonSuffix(removePrefix(newWsFull, newWsStart), delWsEnd);
deletion.value = removeSuffix(deletion.value, newWsEnd);
endKeep.value = replacePrefix(endKeep.value, newWsFull, newWsEnd);
// If there's any whitespace from the new text that HASN'T already been
// assigned, assign it to the start:
startKeep.value = replaceSuffix(startKeep.value, newWsFull, newWsFull.slice(0, newWsFull.length - newWsEnd.length));
} else if (endKeep) {
// We are at the start of the text. Preserve all the whitespace on
// endKeep, and just remove whitespace from the end of deletion to the
// extent that it overlaps with the start of endKeep.
var endKeepWsPrefix = endKeep.value.match(/^\s*/)[0];
var deletionWsSuffix = deletion.value.match(/\s*$/)[0];
var overlap = maximumOverlap(deletionWsSuffix, endKeepWsPrefix);
deletion.value = removeSuffix(deletion.value, overlap);
} else if (startKeep) {
// We are at the END of the text. Preserve all the whitespace on
// startKeep, and just remove whitespace from the start of deletion to
// the extent that it overlaps with the end of startKeep.
var startKeepWsSuffix = startKeep.value.match(/\s*$/)[0];
var deletionWsPrefix = deletion.value.match(/^\s*/)[0];
var _overlap = maximumOverlap(startKeepWsSuffix, deletionWsPrefix);
deletion.value = removePrefix(deletion.value, _overlap);
}
}
var wordWithSpaceDiff = new Diff();
wordWithSpaceDiff.tokenize = function (value) {
// Slightly different to the tokenizeIncludingWhitespace regex used above in
// that this one treats each individual newline as a distinct tokens, rather
// than merging them into other surrounding whitespace. This was requested
// in https://github.com/kpdecker/jsdiff/issues/180 &
// https://github.com/kpdecker/jsdiff/issues/211
var regex = new RegExp("(\\r?\\n)|[".concat(extendedWordChars, "]+|[^\\S\\n\\r]+|[^").concat(extendedWordChars, "]"), 'ug');
return value.match(regex) || [];
};
function diffWordsWithSpace(oldStr, newStr, options) {
return wordWithSpaceDiff.diff(oldStr, newStr, options);
}
function generateOptions(options, defaults) {
if (typeof options === 'function') {
defaults.callback = options;
} else if (options) {
for (var name in options) {
/* istanbul ignore else */
if (options.hasOwnProperty(name)) {
defaults[name] = options[name];
}
}
}
return defaults;
}
var lineDiff = new Diff();
lineDiff.tokenize = function (value, options) {
if (options.stripTrailingCr) {
// remove one \r before \n to match GNU diff's --strip-trailing-cr behavior
value = value.replace(/\r\n/g, '\n');
}
var retLines = [],
linesAndNewlines = value.split(/(\n|\r\n)/);
// Ignore the final empty token that occurs if the string ends with a new line
if (!linesAndNewlines[linesAndNewlines.length - 1]) {
linesAndNewlines.pop();
}
// Merge the content and line separators into single tokens
for (var i = 0; i < linesAndNewlines.length; i++) {
var line = linesAndNewlines[i];
if (i % 2 && !options.newlineIsToken) {
retLines[retLines.length - 1] += line;
} else {
retLines.push(line);
}
}
return retLines;
};
lineDiff.equals = function (left, right, options) {
// If we're ignoring whitespace, we need to normalise lines by stripping
// whitespace before checking equality. (This has an annoying interaction
// with newlineIsToken that requires special handling: if newlines get their
// own token, then we DON'T want to trim the *newline* tokens down to empty
// strings, since this would cause us to treat whitespace-only line content
// as equal to a separator between lines, which would be weird and
// inconsistent with the documented behavior of the options.)
if (options.ignoreWhitespace) {
if (!options.newlineIsToken || !left.includes('\n')) {
left = left.trim();
}
if (!options.newlineIsToken || !right.includes('\n')) {
right = right.trim();
}
} else if (options.ignoreNewlineAtEof && !options.newlineIsToken) {
if (left.endsWith('\n')) {
left = left.slice(0, -1);
}
if (right.endsWith('\n')) {
right = right.slice(0, -1);
}
}
return Diff.prototype.equals.call(this, left, right, options);
};
function diffLines(oldStr, newStr, callback) {
return lineDiff.diff(oldStr, newStr, callback);
}
// Kept for backwards compatibility. This is a rather arbitrary wrapper method
// that just calls `diffLines` with `ignoreWhitespace: true`. It's confusing to
// have two ways to do exactly the same thing in the API, so we no longer
// document this one (library users should explicitly use `diffLines` with
// `ignoreWhitespace: true` instead) but we keep it around to maintain
// compatibility with code that used old versions.
function diffTrimmedLines(oldStr, newStr, callback) {
var options = generateOptions(callback, {
ignoreWhitespace: true
});
return lineDiff.diff(oldStr, newStr, options);
}
var sentenceDiff = new Diff();
sentenceDiff.tokenize = function (value) {
return value.split(/(\S.+?[.!?])(?=\s+|$)/);
};
function diffSentences(oldStr, newStr, callback) {
return sentenceDiff.diff(oldStr, newStr, callback);
}
var cssDiff = new Diff();
cssDiff.tokenize = function (value) {
return value.split(/([{}:;,]|\s+)/);
};
function diffCss(oldStr, newStr, callback) {
return cssDiff.diff(oldStr, newStr, callback);
}
function ownKeys(e, r) {
var t = Object.keys(e);
if (Object.getOwnPropertySymbols) {
var o = Object.getOwnPropertySymbols(e);
r && (o = o.filter(function (r) {
return Object.getOwnPropertyDescriptor(e, r).enumerable;
})), t.push.apply(t, o);
}
return t;
}
function _objectSpread2(e) {
for (var r = 1; r < arguments.length; r++) {
var t = null != arguments[r] ? arguments[r] : {};
r % 2 ? ownKeys(Object(t), !0).forEach(function (r) {
_defineProperty(e, r, t[r]);
}) : Object.getOwnPropertyDescriptors ? Object.defineProperties(e, Object.getOwnPropertyDescriptors(t)) : ownKeys(Object(t)).forEach(function (r) {
Object.defineProperty(e, r, Object.getOwnPropertyDescriptor(t, r));
});
}
return e;
}
function _toPrimitive(t, r) {
if ("object" != typeof t || !t) return t;
var e = t[Symbol.toPrimitive];
if (void 0 !== e) {
var i = e.call(t, r || "default");
if ("object" != typeof i) return i;
throw new TypeError("@@toPrimitive must return a primitive value.");
}
return ("string" === r ? String : Number)(t);
}
function _toPropertyKey(t) {
var i = _toPrimitive(t, "string");
return "symbol" == typeof i ? i : i + "";
}
function _typeof(o) {
"@babel/helpers - typeof";
return _typeof = "function" == typeof Symbol && "symbol" == typeof Symbol.iterator ? function (o) {
return typeof o;
} : function (o) {
return o && "function" == typeof Symbol && o.constructor === Symbol && o !== Symbol.prototype ? "symbol" : typeof o;
}, _typeof(o);
}
function _defineProperty(obj, key, value) {
key = _toPropertyKey(key);
if (key in obj) {
Object.defineProperty(obj, key, {
value: value,
enumerable: true,
configurable: true,
writable: true
});
} else {
obj[key] = value;
}
return obj;
}
function _toConsumableArray(arr) {
return _arrayWithoutHoles(arr) || _iterableToArray(arr) || _unsupportedIterableToArray(arr) || _nonIterableSpread();
}
function _arrayWithoutHoles(arr) {
if (Array.isArray(arr)) return _arrayLikeToArray(arr);
}
function _iterableToArray(iter) {
if (typeof Symbol !== "undefined" && iter[Symbol.iterator] != null || iter["@@iterator"] != null) return Array.from(iter);
}
function _unsupportedIterableToArray(o, minLen) {
if (!o) return;
if (typeof o === "string") return _arrayLikeToArray(o, minLen);
var n = Object.prototype.toString.call(o).slice(8, -1);
if (n === "Object" && o.constructor) n = o.constructor.name;
if (n === "Map" || n === "Set") return Array.from(o);
if (n === "Arguments" || /^(?:Ui|I)nt(?:8|16|32)(?:Clamped)?Array$/.test(n)) return _arrayLikeToArray(o, minLen);
}
function _arrayLikeToArray(arr, len) {
if (len == null || len > arr.length) len = arr.length;
for (var i = 0, arr2 = new Array(len); i < len; i++) arr2[i] = arr[i];
return arr2;
}
function _nonIterableSpread() {
throw new TypeError("Invalid attempt to spread non-iterable instance.\nIn order to be iterable, non-array objects must have a [Symbol.iterator]() method.");
}
var jsonDiff = new Diff();
// Discriminate between two lines of pretty-printed, serialized JSON where one of them has a
// dangling comma and the other doesn't. Turns out including the dangling comma yields the nicest output:
jsonDiff.useLongestToken = true;
jsonDiff.tokenize = lineDiff.tokenize;
jsonDiff.castInput = function (value, options) {
var undefinedReplacement = options.undefinedReplacement,
_options$stringifyRep = options.stringifyReplacer,
stringifyReplacer = _options$stringifyRep === void 0 ? function (k, v) {
return typeof v === 'undefined' ? undefinedReplacement : v;
} : _options$stringifyRep;
return typeof value === 'string' ? value : JSON.stringify(canonicalize(value, null, null, stringifyReplacer), stringifyReplacer, ' ');
};
jsonDiff.equals = function (left, right, options) {
return Diff.prototype.equals.call(jsonDiff, left.replace(/,([\r\n])/g, '$1'), right.replace(/,([\r\n])/g, '$1'), options);
};
function diffJson(oldObj, newObj, options) {
return jsonDiff.diff(oldObj, newObj, options);
}
// This function handles the presence of circular references by bailing out when encountering an
// object that is already on the "stack" of items being processed. Accepts an optional replacer
function canonicalize(obj, stack, replacementStack, replacer, key) {
stack = stack || [];
replacementStack = replacementStack || [];
if (replacer) {
obj = replacer(key, obj);
}
var i;
for (i = 0; i < stack.length; i += 1) {
if (stack[i] === obj) {
return replacementStack[i];
}
}
var canonicalizedObj;
if ('[object Array]' === Object.prototype.toString.call(obj)) {
stack.push(obj);
canonicalizedObj = new Array(obj.length);
replacementStack.push(canonicalizedObj);
for (i = 0; i < obj.length; i += 1) {
canonicalizedObj[i] = canonicalize(obj[i], stack, replacementStack, replacer, key);
}
stack.pop();
replacementStack.pop();
return canonicalizedObj;
}
if (obj && obj.toJSON) {
obj = obj.toJSON();
}
if (_typeof(obj) === 'object' && obj !== null) {
stack.push(obj);
canonicalizedObj = {};
replacementStack.push(canonicalizedObj);
var sortedKeys = [],
_key;
for (_key in obj) {
/* istanbul ignore else */
if (Object.prototype.hasOwnProperty.call(obj, _key)) {
sortedKeys.push(_key);
}
}
sortedKeys.sort();
for (i = 0; i < sortedKeys.length; i += 1) {
_key = sortedKeys[i];
canonicalizedObj[_key] = canonicalize(obj[_key], stack, replacementStack, replacer, _key);
}
stack.pop();
replacementStack.pop();
} else {
canonicalizedObj = obj;
}
return canonicalizedObj;
}
var arrayDiff = new Diff();
arrayDiff.tokenize = function (value) {
return value.slice();
};
arrayDiff.join = arrayDiff.removeEmpty = function (value) {
return value;
};
function diffArrays(oldArr, newArr, callback) {
return arrayDiff.diff(oldArr, newArr, callback);
}
function unixToWin(patch) {
if (Array.isArray(patch)) {
return patch.map(unixToWin);
}
return _objectSpread2(_objectSpread2({}, patch), {}, {
hunks: patch.hunks.map(function (hunk) {
return _objectSpread2(_objectSpread2({}, hunk), {}, {
lines: hunk.lines.map(function (line, i) {
var _hunk$lines;
return line.startsWith('\\') || line.endsWith('\r') || (_hunk$lines = hunk.lines[i + 1]) !== null && _hunk$lines !== void 0 && _hunk$lines.startsWith('\\') ? line : line + '\r';
})
});
})
});
}
function winToUnix(patch) {
if (Array.isArray(patch)) {
return patch.map(winToUnix);
}
return _objectSpread2(_objectSpread2({}, patch), {}, {
hunks: patch.hunks.map(function (hunk) {
return _objectSpread2(_objectSpread2({}, hunk), {}, {
lines: hunk.lines.map(function (line) {
return line.endsWith('\r') ? line.substring(0, line.length - 1) : line;
})
});
})
});
}
/**
* Returns true if the patch consistently uses Unix line endings (or only involves one line and has
* no line endings).
*/
function isUnix(patch) {
if (!Array.isArray(patch)) {
patch = [patch];
}
return !patch.some(function (index) {
return index.hunks.some(function (hunk) {
return hunk.lines.some(function (line) {
return !line.startsWith('\\') && line.endsWith('\r');
});
});
});