-
Notifications
You must be signed in to change notification settings - Fork 31
/
diff_match_patch.js
2196 lines (2045 loc) · 74.8 KB
/
diff_match_patch.js
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 Match and Patch
*
* Copyright 2006 Google Inc.
* http://code.google.com/p/google-diff-match-patch/
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/**
* @fileoverview Computes the difference between two texts to create a patch.
* Applies the patch onto another text, allowing for errors.
* @author [email protected] (Neil Fraser)
*/
/**
* Class containing the diff, match and patch methods.
* @constructor
*/
function diff_match_patch() {
// Defaults.
// Redefine these in your program to override the defaults.
// Number of seconds to map a diff before giving up (0 for infinity).
this.Diff_Timeout = 1.0;
// Cost of an empty edit operation in terms of edit characters.
this.Diff_EditCost = 4;
// At what point is no match declared (0.0 = perfection, 1.0 = very loose).
this.Match_Threshold = 0.5;
// How far to search for a match (0 = exact location, 1000+ = broad match).
// A match this many characters away from the expected location will add
// 1.0 to the score (0.0 is a perfect match).
this.Match_Distance = 1000;
// When deleting a large block of text (over ~64 characters), how close do
// the contents have to be to match the expected contents. (0.0 = perfection,
// 1.0 = very loose). Note that Match_Threshold controls how closely the
// end points of a delete need to match.
this.Patch_DeleteThreshold = 0.5;
// Chunk size for context length.
this.Patch_Margin = 4;
// The number of bits in an int.
this.Match_MaxBits = 32;
}
// DIFF FUNCTIONS
/**
* The data structure representing a diff is an array of tuples:
* [[DIFF_DELETE, 'Hello'], [DIFF_INSERT, 'Goodbye'], [DIFF_EQUAL, ' world.']]
* which means: delete 'Hello', add 'Goodbye' and keep ' world.'
*/
var DIFF_DELETE = -1;
var DIFF_INSERT = 1;
var DIFF_EQUAL = 0;
/** @typedef {{0: number, 1: string}} */
diff_match_patch.Diff;
/**
* Find the differences between two texts. Simplifies the problem by stripping
* any common prefix or suffix off the texts before diffing.
* @param {string} text1 Old string to be diffed.
* @param {string} text2 New string to be diffed.
* @param {boolean=} opt_checklines Optional speedup flag. If present and false,
* then don't run a line-level diff first to identify the changed areas.
* Defaults to true, which does a faster, slightly less optimal diff.
* @param {number} opt_deadline Optional time when the diff should be complete
* by. Used internally for recursive calls. Users should set DiffTimeout
* instead.
* @return {!Array.<!diff_match_patch.Diff>} Array of diff tuples.
*/
diff_match_patch.prototype.diff_main = function(text1, text2, opt_checklines,
opt_deadline) {
// Set a deadline by which time the diff must be complete.
if (typeof opt_deadline == 'undefined') {
if (this.Diff_Timeout <= 0) {
opt_deadline = Number.MAX_VALUE;
} else {
opt_deadline = (new Date).getTime() + this.Diff_Timeout * 1000;
}
}
var deadline = opt_deadline;
// Check for null inputs.
if (text1 == null || text2 == null) {
throw new Error('Null input. (diff_main)');
}
// Check for equality (speedup).
if (text1 == text2) {
if (text1) {
return [[DIFF_EQUAL, text1]];
}
return [];
}
if (typeof opt_checklines == 'undefined') {
opt_checklines = true;
}
var checklines = opt_checklines;
// Trim off common prefix (speedup).
var commonlength = this.diff_commonPrefix(text1, text2);
var commonprefix = text1.substring(0, commonlength);
text1 = text1.substring(commonlength);
text2 = text2.substring(commonlength);
// Trim off common suffix (speedup).
commonlength = this.diff_commonSuffix(text1, text2);
var commonsuffix = text1.substring(text1.length - commonlength);
text1 = text1.substring(0, text1.length - commonlength);
text2 = text2.substring(0, text2.length - commonlength);
// Compute the diff on the middle block.
var diffs = this.diff_compute_(text1, text2, checklines, deadline);
// Restore the prefix and suffix.
if (commonprefix) {
diffs.unshift([DIFF_EQUAL, commonprefix]);
}
if (commonsuffix) {
diffs.push([DIFF_EQUAL, commonsuffix]);
}
this.diff_cleanupMerge(diffs);
return diffs;
};
/**
* Find the differences between two texts. Assumes that the texts do not
* have any common prefix or suffix.
* @param {string} text1 Old string to be diffed.
* @param {string} text2 New string to be diffed.
* @param {boolean} checklines Speedup flag. If false, then don't run a
* line-level diff first to identify the changed areas.
* If true, then run a faster, slightly less optimal diff.
* @param {number} deadline Time when the diff should be complete by.
* @return {!Array.<!diff_match_patch.Diff>} Array of diff tuples.
* @private
*/
diff_match_patch.prototype.diff_compute_ = function(text1, text2, checklines,
deadline) {
var diffs;
if (!text1) {
// Just add some text (speedup).
return [[DIFF_INSERT, text2]];
}
if (!text2) {
// Just delete some text (speedup).
return [[DIFF_DELETE, text1]];
}
/** @type {?string} */
var longtext = text1.length > text2.length ? text1 : text2;
/** @type {?string} */
var shorttext = text1.length > text2.length ? text2 : text1;
var i = longtext.indexOf(shorttext);
if (i != -1) {
// Shorter text is inside the longer text (speedup).
diffs = [[DIFF_INSERT, longtext.substring(0, i)],
[DIFF_EQUAL, shorttext],
[DIFF_INSERT, longtext.substring(i + shorttext.length)]];
// Swap insertions for deletions if diff is reversed.
if (text1.length > text2.length) {
diffs[0][0] = diffs[2][0] = DIFF_DELETE;
}
return diffs;
}
if (shorttext.length == 1) {
// Single character string.
// After the previous speedup, the character can't be an equality.
return [[DIFF_DELETE, text1], [DIFF_INSERT, text2]];
}
longtext = shorttext = null; // Garbage collect.
// Check to see if the problem can be split in two.
var hm = this.diff_halfMatch_(text1, text2);
if (hm) {
// A half-match was found, sort out the return data.
var text1_a = hm[0];
var text1_b = hm[1];
var text2_a = hm[2];
var text2_b = hm[3];
var mid_common = hm[4];
// Send both pairs off for separate processing.
var diffs_a = this.diff_main(text1_a, text2_a, checklines, deadline);
var diffs_b = this.diff_main(text1_b, text2_b, checklines, deadline);
// Merge the results.
return diffs_a.concat([[DIFF_EQUAL, mid_common]], diffs_b);
}
if (checklines && text1.length > 100 && text2.length > 100) {
return this.diff_lineMode_(text1, text2, deadline);
}
return this.diff_bisect_(text1, text2, deadline);
};
/**
* Do a quick line-level diff on both strings, then rediff the parts for
* greater accuracy.
* This speedup can produce non-minimal diffs.
* @param {string} text1 Old string to be diffed.
* @param {string} text2 New string to be diffed.
* @param {number} deadline Time when the diff should be complete by.
* @return {!Array.<!diff_match_patch.Diff>} Array of diff tuples.
* @private
*/
diff_match_patch.prototype.diff_lineMode_ = function(text1, text2, deadline) {
// Scan the text on a line-by-line basis first.
var a = this.diff_linesToChars_(text1, text2);
text1 = a.chars1;
text2 = a.chars2;
var linearray = a.lineArray;
var diffs = this.diff_main(text1, text2, false, deadline);
// Convert the diff back to original text.
this.diff_charsToLines_(diffs, linearray);
// Eliminate freak matches (e.g. blank lines)
this.diff_cleanupSemantic(diffs);
// Rediff any replacement blocks, this time character-by-character.
// Add a dummy entry at the end.
diffs.push([DIFF_EQUAL, '']);
var pointer = 0;
var count_delete = 0;
var count_insert = 0;
var text_delete = '';
var text_insert = '';
while (pointer < diffs.length) {
switch (diffs[pointer][0]) {
case DIFF_INSERT:
count_insert++;
text_insert += diffs[pointer][1];
break;
case DIFF_DELETE:
count_delete++;
text_delete += diffs[pointer][1];
break;
case DIFF_EQUAL:
// Upon reaching an equality, check for prior redundancies.
if (count_delete >= 1 && count_insert >= 1) {
// Delete the offending records and add the merged ones.
diffs.splice(pointer - count_delete - count_insert,
count_delete + count_insert);
pointer = pointer - count_delete - count_insert;
var a = this.diff_main(text_delete, text_insert, false, deadline);
for (var j = a.length - 1; j >= 0; j--) {
diffs.splice(pointer, 0, a[j]);
}
pointer = pointer + a.length;
}
count_insert = 0;
count_delete = 0;
text_delete = '';
text_insert = '';
break;
}
pointer++;
}
diffs.pop(); // Remove the dummy entry at the end.
return diffs;
};
/**
* Find the 'middle snake' of a diff, split the problem in two
* and return the recursively constructed diff.
* See Myers 1986 paper: An O(ND) Difference Algorithm and Its Variations.
* @param {string} text1 Old string to be diffed.
* @param {string} text2 New string to be diffed.
* @param {number} deadline Time at which to bail if not yet complete.
* @return {!Array.<!diff_match_patch.Diff>} Array of diff tuples.
* @private
*/
diff_match_patch.prototype.diff_bisect_ = function(text1, text2, deadline) {
// Cache the text lengths to prevent multiple calls.
var text1_length = text1.length;
var text2_length = text2.length;
var max_d = Math.ceil((text1_length + text2_length) / 2);
var v_offset = max_d;
var v_length = 2 * max_d;
var v1 = new Array(v_length);
var v2 = new Array(v_length);
// Setting all elements to -1 is faster in Chrome & Firefox than mixing
// integers and undefined.
for (var x = 0; x < v_length; x++) {
v1[x] = -1;
v2[x] = -1;
}
v1[v_offset + 1] = 0;
v2[v_offset + 1] = 0;
var delta = text1_length - text2_length;
// If the total number of characters is odd, then the front path will collide
// with the reverse path.
var front = (delta % 2 != 0);
// Offsets for start and end of k loop.
// Prevents mapping of space beyond the grid.
var k1start = 0;
var k1end = 0;
var k2start = 0;
var k2end = 0;
for (var d = 0; d < max_d; d++) {
// Bail out if deadline is reached.
if ((new Date()).getTime() > deadline) {
break;
}
// Walk the front path one step.
for (var k1 = -d + k1start; k1 <= d - k1end; k1 += 2) {
var k1_offset = v_offset + k1;
var x1;
if (k1 == -d || (k1 != d && v1[k1_offset - 1] < v1[k1_offset + 1])) {
x1 = v1[k1_offset + 1];
} else {
x1 = v1[k1_offset - 1] + 1;
}
var y1 = x1 - k1;
while (x1 < text1_length && y1 < text2_length &&
text1.charAt(x1) == text2.charAt(y1)) {
x1++;
y1++;
}
v1[k1_offset] = x1;
if (x1 > text1_length) {
// Ran off the right of the graph.
k1end += 2;
} else if (y1 > text2_length) {
// Ran off the bottom of the graph.
k1start += 2;
} else if (front) {
var k2_offset = v_offset + delta - k1;
if (k2_offset >= 0 && k2_offset < v_length && v2[k2_offset] != -1) {
// Mirror x2 onto top-left coordinate system.
var x2 = text1_length - v2[k2_offset];
if (x1 >= x2) {
// Overlap detected.
return this.diff_bisectSplit_(text1, text2, x1, y1, deadline);
}
}
}
}
// Walk the reverse path one step.
for (var k2 = -d + k2start; k2 <= d - k2end; k2 += 2) {
var k2_offset = v_offset + k2;
var x2;
if (k2 == -d || (k2 != d && v2[k2_offset - 1] < v2[k2_offset + 1])) {
x2 = v2[k2_offset + 1];
} else {
x2 = v2[k2_offset - 1] + 1;
}
var y2 = x2 - k2;
while (x2 < text1_length && y2 < text2_length &&
text1.charAt(text1_length - x2 - 1) ==
text2.charAt(text2_length - y2 - 1)) {
x2++;
y2++;
}
v2[k2_offset] = x2;
if (x2 > text1_length) {
// Ran off the left of the graph.
k2end += 2;
} else if (y2 > text2_length) {
// Ran off the top of the graph.
k2start += 2;
} else if (!front) {
var k1_offset = v_offset + delta - k2;
if (k1_offset >= 0 && k1_offset < v_length && v1[k1_offset] != -1) {
var x1 = v1[k1_offset];
var y1 = v_offset + x1 - k1_offset;
// Mirror x2 onto top-left coordinate system.
x2 = text1_length - x2;
if (x1 >= x2) {
// Overlap detected.
return this.diff_bisectSplit_(text1, text2, x1, y1, deadline);
}
}
}
}
}
// Diff took too long and hit the deadline or
// number of diffs equals number of characters, no commonality at all.
return [[DIFF_DELETE, text1], [DIFF_INSERT, text2]];
};
/**
* Given the location of the 'middle snake', split the diff in two parts
* and recurse.
* @param {string} text1 Old string to be diffed.
* @param {string} text2 New string to be diffed.
* @param {number} x Index of split point in text1.
* @param {number} y Index of split point in text2.
* @param {number} deadline Time at which to bail if not yet complete.
* @return {!Array.<!diff_match_patch.Diff>} Array of diff tuples.
* @private
*/
diff_match_patch.prototype.diff_bisectSplit_ = function(text1, text2, x, y,
deadline) {
var text1a = text1.substring(0, x);
var text2a = text2.substring(0, y);
var text1b = text1.substring(x);
var text2b = text2.substring(y);
// Compute both diffs serially.
var diffs = this.diff_main(text1a, text2a, false, deadline);
var diffsb = this.diff_main(text1b, text2b, false, deadline);
return diffs.concat(diffsb);
};
/**
* Split two texts into an array of strings. Reduce the texts to a string of
* hashes where each Unicode character represents one line.
* @param {string} text1 First string.
* @param {string} text2 Second string.
* @return {{chars1: string, chars2: string, lineArray: !Array.<string>}}
* An object containing the encoded text1, the encoded text2 and
* the array of unique strings.
* The zeroth element of the array of unique strings is intentionally blank.
* @private
*/
diff_match_patch.prototype.diff_linesToChars_ = function(text1, text2) {
var lineArray = []; // e.g. lineArray[4] == 'Hello\n'
var lineHash = {}; // e.g. lineHash['Hello\n'] == 4
// '\x00' is a valid character, but various debuggers don't like it.
// So we'll insert a junk entry to avoid generating a null character.
lineArray[0] = '';
/**
* Split a text into an array of strings. Reduce the texts to a string of
* hashes where each Unicode character represents one line.
* Modifies linearray and linehash through being a closure.
* @param {string} text String to encode.
* @return {string} Encoded string.
* @private
*/
function diff_linesToCharsMunge_(text) {
var chars = '';
// Walk the text, pulling out a substring for each line.
// text.split('\n') would would temporarily double our memory footprint.
// Modifying text would create many large strings to garbage collect.
var lineStart = 0;
var lineEnd = -1;
// Keeping our own length variable is faster than looking it up.
var lineArrayLength = lineArray.length;
while (lineEnd < text.length - 1) {
lineEnd = text.indexOf('\n', lineStart);
if (lineEnd == -1) {
lineEnd = text.length - 1;
}
var line = text.substring(lineStart, lineEnd + 1);
lineStart = lineEnd + 1;
if (lineHash.hasOwnProperty ? lineHash.hasOwnProperty(line) :
(lineHash[line] !== undefined)) {
chars += String.fromCharCode(lineHash[line]);
} else {
chars += String.fromCharCode(lineArrayLength);
lineHash[line] = lineArrayLength;
lineArray[lineArrayLength++] = line;
}
}
return chars;
}
var chars1 = diff_linesToCharsMunge_(text1);
var chars2 = diff_linesToCharsMunge_(text2);
return {chars1: chars1, chars2: chars2, lineArray: lineArray};
};
/**
* Rehydrate the text in a diff from a string of line hashes to real lines of
* text.
* @param {!Array.<!diff_match_patch.Diff>} diffs Array of diff tuples.
* @param {!Array.<string>} lineArray Array of unique strings.
* @private
*/
diff_match_patch.prototype.diff_charsToLines_ = function(diffs, lineArray) {
for (var x = 0; x < diffs.length; x++) {
var chars = diffs[x][1];
var text = [];
for (var y = 0; y < chars.length; y++) {
text[y] = lineArray[chars.charCodeAt(y)];
}
diffs[x][1] = text.join('');
}
};
/**
* Determine the common prefix of two strings.
* @param {string} text1 First string.
* @param {string} text2 Second string.
* @return {number} The number of characters common to the start of each
* string.
*/
diff_match_patch.prototype.diff_commonPrefix = function(text1, text2) {
// Quick check for common null cases.
if (!text1 || !text2 || text1.charAt(0) != text2.charAt(0)) {
return 0;
}
// Binary search.
// Performance analysis: http://neil.fraser.name/news/2007/10/09/
var pointermin = 0;
var pointermax = Math.min(text1.length, text2.length);
var pointermid = pointermax;
var pointerstart = 0;
while (pointermin < pointermid) {
if (text1.substring(pointerstart, pointermid) ==
text2.substring(pointerstart, pointermid)) {
pointermin = pointermid;
pointerstart = pointermin;
} else {
pointermax = pointermid;
}
pointermid = Math.floor((pointermax - pointermin) / 2 + pointermin);
}
return pointermid;
};
/**
* Determine the common suffix of two strings.
* @param {string} text1 First string.
* @param {string} text2 Second string.
* @return {number} The number of characters common to the end of each string.
*/
diff_match_patch.prototype.diff_commonSuffix = function(text1, text2) {
// Quick check for common null cases.
if (!text1 || !text2 ||
text1.charAt(text1.length - 1) != text2.charAt(text2.length - 1)) {
return 0;
}
// Binary search.
// Performance analysis: http://neil.fraser.name/news/2007/10/09/
var pointermin = 0;
var pointermax = Math.min(text1.length, text2.length);
var pointermid = pointermax;
var pointerend = 0;
while (pointermin < pointermid) {
if (text1.substring(text1.length - pointermid, text1.length - pointerend) ==
text2.substring(text2.length - pointermid, text2.length - pointerend)) {
pointermin = pointermid;
pointerend = pointermin;
} else {
pointermax = pointermid;
}
pointermid = Math.floor((pointermax - pointermin) / 2 + pointermin);
}
return pointermid;
};
/**
* Determine if the suffix of one string is the prefix of another.
* @param {string} text1 First string.
* @param {string} text2 Second string.
* @return {number} The number of characters common to the end of the first
* string and the start of the second string.
* @private
*/
diff_match_patch.prototype.diff_commonOverlap_ = function(text1, text2) {
// Cache the text lengths to prevent multiple calls.
var text1_length = text1.length;
var text2_length = text2.length;
// Eliminate the null case.
if (text1_length == 0 || text2_length == 0) {
return 0;
}
// Truncate the longer string.
if (text1_length > text2_length) {
text1 = text1.substring(text1_length - text2_length);
} else if (text1_length < text2_length) {
text2 = text2.substring(0, text1_length);
}
var text_length = Math.min(text1_length, text2_length);
// Quick check for the worst case.
if (text1 == text2) {
return text_length;
}
// Start by looking for a single character match
// and increase length until no match is found.
// Performance analysis: http://neil.fraser.name/news/2010/11/04/
var best = 0;
var length = 1;
while (true) {
var pattern = text1.substring(text_length - length);
var found = text2.indexOf(pattern);
if (found == -1) {
return best;
}
length += found;
if (found == 0 || text1.substring(text_length - length) ==
text2.substring(0, length)) {
best = length;
length++;
}
}
};
/**
* Do the two texts share a substring which is at least half the length of the
* longer text?
* This speedup can produce non-minimal diffs.
* @param {string} text1 First string.
* @param {string} text2 Second string.
* @return {Array.<string>} Five element Array, containing the prefix of
* text1, the suffix of text1, the prefix of text2, the suffix of
* text2 and the common middle. Or null if there was no match.
* @private
*/
diff_match_patch.prototype.diff_halfMatch_ = function(text1, text2) {
if (this.Diff_Timeout <= 0) {
// Don't risk returning a non-optimal diff if we have unlimited time.
return null;
}
var longtext = text1.length > text2.length ? text1 : text2;
var shorttext = text1.length > text2.length ? text2 : text1;
if (longtext.length < 4 || shorttext.length * 2 < longtext.length) {
return null; // Pointless.
}
var dmp = this; // 'this' becomes 'window' in a closure.
/**
* Does a substring of shorttext exist within longtext such that the substring
* is at least half the length of longtext?
* Closure, but does not reference any external variables.
* @param {string} longtext Longer string.
* @param {string} shorttext Shorter string.
* @param {number} i Start index of quarter length substring within longtext.
* @return {Array.<string>} Five element Array, containing the prefix of
* longtext, the suffix of longtext, the prefix of shorttext, the suffix
* of shorttext and the common middle. Or null if there was no match.
* @private
*/
function diff_halfMatchI_(longtext, shorttext, i) {
// Start with a 1/4 length substring at position i as a seed.
var seed = longtext.substring(i, i + Math.floor(longtext.length / 4));
var j = -1;
var best_common = '';
var best_longtext_a, best_longtext_b, best_shorttext_a, best_shorttext_b;
while ((j = shorttext.indexOf(seed, j + 1)) != -1) {
var prefixLength = dmp.diff_commonPrefix(longtext.substring(i),
shorttext.substring(j));
var suffixLength = dmp.diff_commonSuffix(longtext.substring(0, i),
shorttext.substring(0, j));
if (best_common.length < suffixLength + prefixLength) {
best_common = shorttext.substring(j - suffixLength, j) +
shorttext.substring(j, j + prefixLength);
best_longtext_a = longtext.substring(0, i - suffixLength);
best_longtext_b = longtext.substring(i + prefixLength);
best_shorttext_a = shorttext.substring(0, j - suffixLength);
best_shorttext_b = shorttext.substring(j + prefixLength);
}
}
if (best_common.length * 2 >= longtext.length) {
return [best_longtext_a, best_longtext_b,
best_shorttext_a, best_shorttext_b, best_common];
} else {
return null;
}
}
// First check if the second quarter is the seed for a half-match.
var hm1 = diff_halfMatchI_(longtext, shorttext,
Math.ceil(longtext.length / 4));
// Check again based on the third quarter.
var hm2 = diff_halfMatchI_(longtext, shorttext,
Math.ceil(longtext.length / 2));
var hm;
if (!hm1 && !hm2) {
return null;
} else if (!hm2) {
hm = hm1;
} else if (!hm1) {
hm = hm2;
} else {
// Both matched. Select the longest.
hm = hm1[4].length > hm2[4].length ? hm1 : hm2;
}
// A half-match was found, sort out the return data.
var text1_a, text1_b, text2_a, text2_b;
if (text1.length > text2.length) {
text1_a = hm[0];
text1_b = hm[1];
text2_a = hm[2];
text2_b = hm[3];
} else {
text2_a = hm[0];
text2_b = hm[1];
text1_a = hm[2];
text1_b = hm[3];
}
var mid_common = hm[4];
return [text1_a, text1_b, text2_a, text2_b, mid_common];
};
/**
* Reduce the number of edits by eliminating semantically trivial equalities.
* @param {!Array.<!diff_match_patch.Diff>} diffs Array of diff tuples.
*/
diff_match_patch.prototype.diff_cleanupSemantic = function(diffs) {
var changes = false;
var equalities = []; // Stack of indices where equalities are found.
var equalitiesLength = 0; // Keeping our own length var is faster in JS.
/** @type {?string} */
var lastequality = null;
// Always equal to diffs[equalities[equalitiesLength - 1]][1]
var pointer = 0; // Index of current position.
// Number of characters that changed prior to the equality.
var length_insertions1 = 0;
var length_deletions1 = 0;
// Number of characters that changed after the equality.
var length_insertions2 = 0;
var length_deletions2 = 0;
while (pointer < diffs.length) {
if (diffs[pointer][0] == DIFF_EQUAL) { // Equality found.
equalities[equalitiesLength++] = pointer;
length_insertions1 = length_insertions2;
length_deletions1 = length_deletions2;
length_insertions2 = 0;
length_deletions2 = 0;
lastequality = diffs[pointer][1];
} else { // An insertion or deletion.
if (diffs[pointer][0] == DIFF_INSERT) {
length_insertions2 += diffs[pointer][1].length;
} else {
length_deletions2 += diffs[pointer][1].length;
}
// Eliminate an equality that is smaller or equal to the edits on both
// sides of it.
if (lastequality && (lastequality.length <=
Math.max(length_insertions1, length_deletions1)) &&
(lastequality.length <= Math.max(length_insertions2,
length_deletions2))) {
// Duplicate record.
diffs.splice(equalities[equalitiesLength - 1], 0,
[DIFF_DELETE, lastequality]);
// Change second copy to insert.
diffs[equalities[equalitiesLength - 1] + 1][0] = DIFF_INSERT;
// Throw away the equality we just deleted.
equalitiesLength--;
// Throw away the previous equality (it needs to be reevaluated).
equalitiesLength--;
pointer = equalitiesLength > 0 ? equalities[equalitiesLength - 1] : -1;
length_insertions1 = 0; // Reset the counters.
length_deletions1 = 0;
length_insertions2 = 0;
length_deletions2 = 0;
lastequality = null;
changes = true;
}
}
pointer++;
}
// Normalize the diff.
if (changes) {
this.diff_cleanupMerge(diffs);
}
this.diff_cleanupSemanticLossless(diffs);
// Find any overlaps between deletions and insertions.
// e.g: <del>abcxxx</del><ins>xxxdef</ins>
// -> <del>abc</del>xxx<ins>def</ins>
// e.g: <del>xxxabc</del><ins>defxxx</ins>
// -> <ins>def</ins>xxx<del>abc</del>
// Only extract an overlap if it is as big as the edit ahead or behind it.
pointer = 1;
while (pointer < diffs.length) {
if (diffs[pointer - 1][0] == DIFF_DELETE &&
diffs[pointer][0] == DIFF_INSERT) {
var deletion = diffs[pointer - 1][1];
var insertion = diffs[pointer][1];
var overlap_length1 = this.diff_commonOverlap_(deletion, insertion);
var overlap_length2 = this.diff_commonOverlap_(insertion, deletion);
if (overlap_length1 >= overlap_length2) {
if (overlap_length1 >= deletion.length / 2 ||
overlap_length1 >= insertion.length / 2) {
// Overlap found. Insert an equality and trim the surrounding edits.
diffs.splice(pointer, 0,
[DIFF_EQUAL, insertion.substring(0, overlap_length1)]);
diffs[pointer - 1][1] =
deletion.substring(0, deletion.length - overlap_length1);
diffs[pointer + 1][1] = insertion.substring(overlap_length1);
pointer++;
}
} else {
if (overlap_length2 >= deletion.length / 2 ||
overlap_length2 >= insertion.length / 2) {
// Reverse overlap found.
// Insert an equality and swap and trim the surrounding edits.
diffs.splice(pointer, 0,
[DIFF_EQUAL, deletion.substring(0, overlap_length2)]);
diffs[pointer - 1][0] = DIFF_INSERT;
diffs[pointer - 1][1] =
insertion.substring(0, insertion.length - overlap_length2);
diffs[pointer + 1][0] = DIFF_DELETE;
diffs[pointer + 1][1] =
deletion.substring(overlap_length2);
pointer++;
}
}
pointer++;
}
pointer++;
}
};
/**
* Look for single edits surrounded on both sides by equalities
* which can be shifted sideways to align the edit to a word boundary.
* e.g: The c<ins>at c</ins>ame. -> The <ins>cat </ins>came.
* @param {!Array.<!diff_match_patch.Diff>} diffs Array of diff tuples.
*/
diff_match_patch.prototype.diff_cleanupSemanticLossless = function(diffs) {
/**
* Given two strings, compute a score representing whether the internal
* boundary falls on logical boundaries.
* Scores range from 6 (best) to 0 (worst).
* Closure, but does not reference any external variables.
* @param {string} one First string.
* @param {string} two Second string.
* @return {number} The score.
* @private
*/
function diff_cleanupSemanticScore_(one, two) {
if (!one || !two) {
// Edges are the best.
return 6;
}
// Each port of this function behaves slightly differently due to
// subtle differences in each language's definition of things like
// 'whitespace'. Since this function's purpose is largely cosmetic,
// the choice has been made to use each language's native features
// rather than force total conformity.
var char1 = one.charAt(one.length - 1);
var char2 = two.charAt(0);
var nonAlphaNumeric1 = char1.match(diff_match_patch.nonAlphaNumericRegex_);
var nonAlphaNumeric2 = char2.match(diff_match_patch.nonAlphaNumericRegex_);
var whitespace1 = nonAlphaNumeric1 &&
char1.match(diff_match_patch.whitespaceRegex_);
var whitespace2 = nonAlphaNumeric2 &&
char2.match(diff_match_patch.whitespaceRegex_);
var lineBreak1 = whitespace1 &&
char1.match(diff_match_patch.linebreakRegex_);
var lineBreak2 = whitespace2 &&
char2.match(diff_match_patch.linebreakRegex_);
var blankLine1 = lineBreak1 &&
one.match(diff_match_patch.blanklineEndRegex_);
var blankLine2 = lineBreak2 &&
two.match(diff_match_patch.blanklineStartRegex_);
if (blankLine1 || blankLine2) {
// Five points for blank lines.
return 5;
} else if (lineBreak1 || lineBreak2) {
// Four points for line breaks.
return 4;
} else if (nonAlphaNumeric1 && !whitespace1 && whitespace2) {
// Three points for end of sentences.
return 3;
} else if (whitespace1 || whitespace2) {
// Two points for whitespace.
return 2;
} else if (nonAlphaNumeric1 || nonAlphaNumeric2) {
// One point for non-alphanumeric.
return 1;
}
return 0;
}
var pointer = 1;
// Intentionally ignore the first and last element (don't need checking).
while (pointer < diffs.length - 1) {
if (diffs[pointer - 1][0] == DIFF_EQUAL &&
diffs[pointer + 1][0] == DIFF_EQUAL) {
// This is a single edit surrounded by equalities.
var equality1 = diffs[pointer - 1][1];
var edit = diffs[pointer][1];
var equality2 = diffs[pointer + 1][1];
// First, shift the edit as far left as possible.
var commonOffset = this.diff_commonSuffix(equality1, edit);
if (commonOffset) {
var commonString = edit.substring(edit.length - commonOffset);
equality1 = equality1.substring(0, equality1.length - commonOffset);
edit = commonString + edit.substring(0, edit.length - commonOffset);
equality2 = commonString + equality2;
}
// Second, step character by character right, looking for the best fit.
var bestEquality1 = equality1;
var bestEdit = edit;
var bestEquality2 = equality2;
var bestScore = diff_cleanupSemanticScore_(equality1, edit) +
diff_cleanupSemanticScore_(edit, equality2);
while (edit.charAt(0) === equality2.charAt(0)) {
equality1 += edit.charAt(0);
edit = edit.substring(1) + equality2.charAt(0);
equality2 = equality2.substring(1);
var score = diff_cleanupSemanticScore_(equality1, edit) +
diff_cleanupSemanticScore_(edit, equality2);
// The >= encourages trailing rather than leading whitespace on edits.
if (score >= bestScore) {
bestScore = score;
bestEquality1 = equality1;
bestEdit = edit;
bestEquality2 = equality2;
}
}
if (diffs[pointer - 1][1] != bestEquality1) {
// We have an improvement, save it back to the diff.
if (bestEquality1) {
diffs[pointer - 1][1] = bestEquality1;
} else {
diffs.splice(pointer - 1, 1);
pointer--;
}
diffs[pointer][1] = bestEdit;
if (bestEquality2) {
diffs[pointer + 1][1] = bestEquality2;
} else {
diffs.splice(pointer + 1, 1);
pointer--;
}
}
}
pointer++;
}
};
// Define some regex patterns for matching boundaries.
diff_match_patch.nonAlphaNumericRegex_ = /[^a-zA-Z0-9]/;
diff_match_patch.whitespaceRegex_ = /\s/;
diff_match_patch.linebreakRegex_ = /[\r\n]/;
diff_match_patch.blanklineEndRegex_ = /\n\r?\n$/;
diff_match_patch.blanklineStartRegex_ = /^\r?\n\r?\n/;
/**
* Reduce the number of edits by eliminating operationally trivial equalities.
* @param {!Array.<!diff_match_patch.Diff>} diffs Array of diff tuples.
*/
diff_match_patch.prototype.diff_cleanupEfficiency = function(diffs) {
var changes = false;
var equalities = []; // Stack of indices where equalities are found.
var equalitiesLength = 0; // Keeping our own length var is faster in JS.
/** @type {?string} */
var lastequality = null;
// Always equal to diffs[equalities[equalitiesLength - 1]][1]
var pointer = 0; // Index of current position.
// Is there an insertion operation before the last equality.
var pre_ins = false;
// Is there a deletion operation before the last equality.
var pre_del = false;
// Is there an insertion operation after the last equality.
var post_ins = false;
// Is there a deletion operation after the last equality.
var post_del = false;
while (pointer < diffs.length) {
if (diffs[pointer][0] == DIFF_EQUAL) { // Equality found.
if (diffs[pointer][1].length < this.Diff_EditCost &&
(post_ins || post_del)) {
// Candidate found.
equalities[equalitiesLength++] = pointer;
pre_ins = post_ins;
pre_del = post_del;