aboutsummaryrefslogblamecommitdiffstats
path: root/vendor/gotest.tools/internal/difflib/difflib.go
blob: 5efa99c1d4615452067f034c81ab40686c6e76d5 (plain) (tree)
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



































































































































































































































































































































































































































                                                                                         
/* Package difflib is a partial port of Python difflib module.

Original source: https://github.com/pmezard/go-difflib

This file is trimmed to only the parts used by this repository.
*/
package difflib // import "gotest.tools/internal/difflib"

func min(a, b int) int {
	if a < b {
		return a
	}
	return b
}

func max(a, b int) int {
	if a > b {
		return a
	}
	return b
}

type Match struct {
	A    int
	B    int
	Size int
}

type OpCode struct {
	Tag byte
	I1  int
	I2  int
	J1  int
	J2  int
}

// SequenceMatcher compares sequence of strings. The basic
// algorithm predates, and is a little fancier than, an algorithm
// published in the late 1980's by Ratcliff and Obershelp under the
// hyperbolic name "gestalt pattern matching".  The basic idea is to find
// the longest contiguous matching subsequence that contains no "junk"
// elements (R-O doesn't address junk).  The same idea is then applied
// recursively to the pieces of the sequences to the left and to the right
// of the matching subsequence.  This does not yield minimal edit
// sequences, but does tend to yield matches that "look right" to people.
//
// SequenceMatcher tries to compute a "human-friendly diff" between two
// sequences.  Unlike e.g. UNIX(tm) diff, the fundamental notion is the
// longest *contiguous* & junk-free matching subsequence.  That's what
// catches peoples' eyes.  The Windows(tm) windiff has another interesting
// notion, pairing up elements that appear uniquely in each sequence.
// That, and the method here, appear to yield more intuitive difference
// reports than does diff.  This method appears to be the least vulnerable
// to synching up on blocks of "junk lines", though (like blank lines in
// ordinary text files, or maybe "<P>" lines in HTML files).  That may be
// because this is the only method of the 3 that has a *concept* of
// "junk" <wink>.
//
// Timing:  Basic R-O is cubic time worst case and quadratic time expected
// case.  SequenceMatcher is quadratic time for the worst case and has
// expected-case behavior dependent in a complicated way on how many
// elements the sequences have in common; best case time is linear.
type SequenceMatcher struct {
	a              []string
	b              []string
	b2j            map[string][]int
	IsJunk         func(string) bool
	autoJunk       bool
	bJunk          map[string]struct{}
	matchingBlocks []Match
	fullBCount     map[string]int
	bPopular       map[string]struct{}
	opCodes        []OpCode
}

func NewMatcher(a, b []string) *SequenceMatcher {
	m := SequenceMatcher{autoJunk: true}
	m.SetSeqs(a, b)
	return &m
}

// Set two sequences to be compared.
func (m *SequenceMatcher) SetSeqs(a, b []string) {
	m.SetSeq1(a)
	m.SetSeq2(b)
}

// Set the first sequence to be compared. The second sequence to be compared is
// not changed.
//
// SequenceMatcher computes and caches detailed information about the second
// sequence, so if you want to compare one sequence S against many sequences,
// use .SetSeq2(s) once and call .SetSeq1(x) repeatedly for each of the other
// sequences.
//
// See also SetSeqs() and SetSeq2().
func (m *SequenceMatcher) SetSeq1(a []string) {
	if &a == &m.a {
		return
	}
	m.a = a
	m.matchingBlocks = nil
	m.opCodes = nil
}

// Set the second sequence to be compared. The first sequence to be compared is
// not changed.
func (m *SequenceMatcher) SetSeq2(b []string) {
	if &b == &m.b {
		return
	}
	m.b = b
	m.matchingBlocks = nil
	m.opCodes = nil
	m.fullBCount = nil
	m.chainB()
}

func (m *SequenceMatcher) chainB() {
	// Populate line -> index mapping
	b2j := map[string][]int{}
	for i, s := range m.b {
		indices := b2j[s]
		indices = append(indices, i)
		b2j[s] = indices
	}

	// Purge junk elements
	m.bJunk = map[string]struct{}{}
	if m.IsJunk != nil {
		junk := m.bJunk
		for s, _ := range b2j {
			if m.IsJunk(s) {
				junk[s] = struct{}{}
			}
		}
		for s, _ := range junk {
			delete(b2j, s)
		}
	}

	// Purge remaining popular elements
	popular := map[string]struct{}{}
	n := len(m.b)
	if m.autoJunk && n >= 200 {
		ntest := n/100 + 1
		for s, indices := range b2j {
			if len(indices) > ntest {
				popular[s] = struct{}{}
			}
		}
		for s, _ := range popular {
			delete(b2j, s)
		}
	}
	m.bPopular = popular
	m.b2j = b2j
}

func (m *SequenceMatcher) isBJunk(s string) bool {
	_, ok := m.bJunk[s]
	return ok
}

// Find longest matching block in a[alo:ahi] and b[blo:bhi].
//
// If IsJunk is not defined:
//
// Return (i,j,k) such that a[i:i+k] is equal to b[j:j+k], where
//     alo <= i <= i+k <= ahi
//     blo <= j <= j+k <= bhi
// and for all (i',j',k') meeting those conditions,
//     k >= k'
//     i <= i'
//     and if i == i', j <= j'
//
// In other words, of all maximal matching blocks, return one that
// starts earliest in a, and of all those maximal matching blocks that
// start earliest in a, return the one that starts earliest in b.
//
// If IsJunk is defined, first the longest matching block is
// determined as above, but with the additional restriction that no
// junk element appears in the block.  Then that block is extended as
// far as possible by matching (only) junk elements on both sides.  So
// the resulting block never matches on junk except as identical junk
// happens to be adjacent to an "interesting" match.
//
// If no blocks match, return (alo, blo, 0).
func (m *SequenceMatcher) findLongestMatch(alo, ahi, blo, bhi int) Match {
	// CAUTION:  stripping common prefix or suffix would be incorrect.
	// E.g.,
	//    ab
	//    acab
	// Longest matching block is "ab", but if common prefix is
	// stripped, it's "a" (tied with "b").  UNIX(tm) diff does so
	// strip, so ends up claiming that ab is changed to acab by
	// inserting "ca" in the middle.  That's minimal but unintuitive:
	// "it's obvious" that someone inserted "ac" at the front.
	// Windiff ends up at the same place as diff, but by pairing up
	// the unique 'b's and then matching the first two 'a's.
	besti, bestj, bestsize := alo, blo, 0

	// find longest junk-free match
	// during an iteration of the loop, j2len[j] = length of longest
	// junk-free match ending with a[i-1] and b[j]
	j2len := map[int]int{}
	for i := alo; i != ahi; i++ {
		// look at all instances of a[i] in b; note that because
		// b2j has no junk keys, the loop is skipped if a[i] is junk
		newj2len := map[int]int{}
		for _, j := range m.b2j[m.a[i]] {
			// a[i] matches b[j]
			if j < blo {
				continue
			}
			if j >= bhi {
				break
			}
			k := j2len[j-1] + 1
			newj2len[j] = k
			if k > bestsize {
				besti, bestj, bestsize = i-k+1, j-k+1, k
			}
		}
		j2len = newj2len
	}

	// Extend the best by non-junk elements on each end.  In particular,
	// "popular" non-junk elements aren't in b2j, which greatly speeds
	// the inner loop above, but also means "the best" match so far
	// doesn't contain any junk *or* popular non-junk elements.
	for besti > alo && bestj > blo && !m.isBJunk(m.b[bestj-1]) &&
		m.a[besti-1] == m.b[bestj-1] {
		besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
	}
	for besti+bestsize < ahi && bestj+bestsize < bhi &&
		!m.isBJunk(m.b[bestj+bestsize]) &&
		m.a[besti+bestsize] == m.b[bestj+bestsize] {
		bestsize += 1
	}

	// Now that we have a wholly interesting match (albeit possibly
	// empty!), we may as well suck up the matching junk on each
	// side of it too.  Can't think of a good reason not to, and it
	// saves post-processing the (possibly considerable) expense of
	// figuring out what to do with it.  In the case of an empty
	// interesting match, this is clearly the right thing to do,
	// because no other kind of match is possible in the regions.
	for besti > alo && bestj > blo && m.isBJunk(m.b[bestj-1]) &&
		m.a[besti-1] == m.b[bestj-1] {
		besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
	}
	for besti+bestsize < ahi && bestj+bestsize < bhi &&
		m.isBJunk(m.b[bestj+bestsize]) &&
		m.a[besti+bestsize] == m.b[bestj+bestsize] {
		bestsize += 1
	}

	return Match{A: besti, B: bestj, Size: bestsize}
}

// Return list of triples describing matching subsequences.
//
// Each triple is of the form (i, j, n), and means that
// a[i:i+n] == b[j:j+n].  The triples are monotonically increasing in
// i and in j. It's also guaranteed that if (i, j, n) and (i', j', n') are
// adjacent triples in the list, and the second is not the last triple in the
// list, then i+n != i' or j+n != j'. IOW, adjacent triples never describe
// adjacent equal blocks.
//
// The last triple is a dummy, (len(a), len(b), 0), and is the only
// triple with n==0.
func (m *SequenceMatcher) GetMatchingBlocks() []Match {
	if m.matchingBlocks != nil {
		return m.matchingBlocks
	}

	var matchBlocks func(alo, ahi, blo, bhi int, matched []Match) []Match
	matchBlocks = func(alo, ahi, blo, bhi int, matched []Match) []Match {
		match := m.findLongestMatch(alo, ahi, blo, bhi)
		i, j, k := match.A, match.B, match.Size
		if match.Size > 0 {
			if alo < i && blo < j {
				matched = matchBlocks(alo, i, blo, j, matched)
			}
			matched = append(matched, match)
			if i+k < ahi && j+k < bhi {
				matched = matchBlocks(i+k, ahi, j+k, bhi, matched)
			}
		}
		return matched
	}
	matched := matchBlocks(0, len(m.a), 0, len(m.b), nil)

	// It's possible that we have adjacent equal blocks in the
	// matching_blocks list now.
	nonAdjacent := []Match{}
	i1, j1, k1 := 0, 0, 0
	for _, b := range matched {
		// Is this block adjacent to i1, j1, k1?
		i2, j2, k2 := b.A, b.B, b.Size
		if i1+k1 == i2 && j1+k1 == j2 {
			// Yes, so collapse them -- this just increases the length of
			// the first block by the length of the second, and the first
			// block so lengthened remains the block to compare against.
			k1 += k2
		} else {
			// Not adjacent.  Remember the first block (k1==0 means it's
			// the dummy we started with), and make the second block the
			// new block to compare against.
			if k1 > 0 {
				nonAdjacent = append(nonAdjacent, Match{i1, j1, k1})
			}
			i1, j1, k1 = i2, j2, k2
		}
	}
	if k1 > 0 {
		nonAdjacent = append(nonAdjacent, Match{i1, j1, k1})
	}

	nonAdjacent = append(nonAdjacent, Match{len(m.a), len(m.b), 0})
	m.matchingBlocks = nonAdjacent
	return m.matchingBlocks
}

// Return list of 5-tuples describing how to turn a into b.
//
// Each tuple is of the form (tag, i1, i2, j1, j2).  The first tuple
// has i1 == j1 == 0, and remaining tuples have i1 == the i2 from the
// tuple preceding it, and likewise for j1 == the previous j2.
//
// The tags are characters, with these meanings:
//
// 'r' (replace):  a[i1:i2] should be replaced by b[j1:j2]
//
// 'd' (delete):   a[i1:i2] should be deleted, j1==j2 in this case.
//
// 'i' (insert):   b[j1:j2] should be inserted at a[i1:i1], i1==i2 in this case.
//
// 'e' (equal):    a[i1:i2] == b[j1:j2]
func (m *SequenceMatcher) GetOpCodes() []OpCode {
	if m.opCodes != nil {
		return m.opCodes
	}
	i, j := 0, 0
	matching := m.GetMatchingBlocks()
	opCodes := make([]OpCode, 0, len(matching))
	for _, m := range matching {
		//  invariant:  we've pumped out correct diffs to change
		//  a[:i] into b[:j], and the next matching block is
		//  a[ai:ai+size] == b[bj:bj+size]. So we need to pump
		//  out a diff to change a[i:ai] into b[j:bj], pump out
		//  the matching block, and move (i,j) beyond the match
		ai, bj, size := m.A, m.B, m.Size
		tag := byte(0)
		if i < ai && j < bj {
			tag = 'r'
		} else if i < ai {
			tag = 'd'
		} else if j < bj {
			tag = 'i'
		}
		if tag > 0 {
			opCodes = append(opCodes, OpCode{tag, i, ai, j, bj})
		}
		i, j = ai+size, bj+size
		// the list of matching blocks is terminated by a
		// sentinel with size 0
		if size > 0 {
			opCodes = append(opCodes, OpCode{'e', ai, i, bj, j})
		}
	}
	m.opCodes = opCodes
	return m.opCodes
}

// Isolate change clusters by eliminating ranges with no changes.
//
// Return a generator of groups with up to n lines of context.
// Each group is in the same format as returned by GetOpCodes().
func (m *SequenceMatcher) GetGroupedOpCodes(n int) [][]OpCode {
	if n < 0 {
		n = 3
	}
	codes := m.GetOpCodes()
	if len(codes) == 0 {
		codes = []OpCode{OpCode{'e', 0, 1, 0, 1}}
	}
	// Fixup leading and trailing groups if they show no changes.
	if codes[0].Tag == 'e' {
		c := codes[0]
		i1, i2, j1, j2 := c.I1, c.I2, c.J1, c.J2
		codes[0] = OpCode{c.Tag, max(i1, i2-n), i2, max(j1, j2-n), j2}
	}
	if codes[len(codes)-1].Tag == 'e' {
		c := codes[len(codes)-1]
		i1, i2, j1, j2 := c.I1, c.I2, c.J1, c.J2
		codes[len(codes)-1] = OpCode{c.Tag, i1, min(i2, i1+n), j1, min(j2, j1+n)}
	}
	nn := n + n
	groups := [][]OpCode{}
	group := []OpCode{}
	for _, c := range codes {
		i1, i2, j1, j2 := c.I1, c.I2, c.J1, c.J2
		// End the current group and start a new one whenever
		// there is a large range with no changes.
		if c.Tag == 'e' && i2-i1 > nn {
			group = append(group, OpCode{c.Tag, i1, min(i2, i1+n),
				j1, min(j2, j1+n)})
			groups = append(groups, group)
			group = []OpCode{}
			i1, j1 = max(i1, i2-n), max(j1, j2-n)
		}
		group = append(group, OpCode{c.Tag, i1, i2, j1, j2})
	}
	if len(group) > 0 && !(len(group) == 1 && group[0].Tag == 'e') {
		groups = append(groups, group)
	}
	return groups
}