summaryrefslogtreecommitdiffstats
path: root/xdiff/xpatience.c
blob: a2d8955537f566458b6e912ff5fb8496fa7fe85a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
/*
 *  LibXDiff by Davide Libenzi ( File Differential Library )
 *  Copyright (C) 2003-2016 Davide Libenzi, Johannes E. Schindelin
 *
 *  This library is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU Lesser General Public
 *  License as published by the Free Software Foundation; either
 *  version 2.1 of the License, or (at your option) any later version.
 *
 *  This library is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  Lesser General Public License for more details.
 *
 *  You should have received a copy of the GNU Lesser General Public
 *  License along with this library; if not, see
 *  <http://www.gnu.org/licenses/>.
 *
 *  Davide Libenzi <davidel@xmailserver.org>
 *
 */
#include "xinclude.h"

/*
 * The basic idea of patience diff is to find lines that are unique in
 * both files.  These are intuitively the ones that we want to see as
 * common lines.
 *
 * The maximal ordered sequence of such line pairs (where ordered means
 * that the order in the sequence agrees with the order of the lines in
 * both files) naturally defines an initial set of common lines.
 *
 * Now, the algorithm tries to extend the set of common lines by growing
 * the line ranges where the files have identical lines.
 *
 * Between those common lines, the patience diff algorithm is applied
 * recursively, until no unique line pairs can be found; these line ranges
 * are handled by the well-known Myers algorithm.
 */

#define NON_UNIQUE ULONG_MAX

/*
 * This is a hash mapping from line hash to line numbers in the first and
 * second file.
 */
struct hashmap {
	int nr, alloc;
	struct entry {
		unsigned long hash;
		/*
		 * 0 = unused entry, 1 = first line, 2 = second, etc.
		 * line2 is NON_UNIQUE if the line is not unique
		 * in either the first or the second file.
		 */
		unsigned long line1, line2;
		/*
		 * "next" & "previous" are used for the longest common
		 * sequence;
		 * initially, "next" reflects only the order in file1.
		 */
		struct entry *next, *previous;

		/*
		 * If 1, this entry can serve as an anchor. See
		 * Documentation/diff-options.txt for more information.
		 */
		unsigned anchor : 1;
	} *entries, *first, *last;
	/* were common records found? */
	unsigned long has_matches;
	xdfenv_t *env;
	xpparam_t const *xpp;
};

static int is_anchor(xpparam_t const *xpp, const char *line)
{
	int i;
	for (i = 0; i < xpp->anchors_nr; i++) {
		if (!strncmp(line, xpp->anchors[i], strlen(xpp->anchors[i])))
			return 1;
	}
	return 0;
}

/* The argument "pass" is 1 for the first file, 2 for the second. */
static void insert_record(xpparam_t const *xpp, int line, struct hashmap *map,
			  int pass)
{
	xrecord_t **records = pass == 1 ?
		map->env->xdf1.recs : map->env->xdf2.recs;
	xrecord_t *record = records[line - 1];
	/*
	 * After xdl_prepare_env() (or more precisely, due to
	 * xdl_classify_record()), the "ha" member of the records (AKA lines)
	 * is _not_ the hash anymore, but a linearized version of it.  In
	 * other words, the "ha" member is guaranteed to start with 0 and
	 * the second record's ha can only be 0 or 1, etc.
	 *
	 * So we multiply ha by 2 in the hope that the hashing was
	 * "unique enough".
	 */
	int index = (int)((record->ha << 1) % map->alloc);

	while (map->entries[index].line1) {
		if (map->entries[index].hash != record->ha) {
			if (++index >= map->alloc)
				index = 0;
			continue;
		}
		if (pass == 2)
			map->has_matches = 1;
		if (pass == 1 || map->entries[index].line2)
			map->entries[index].line2 = NON_UNIQUE;
		else
			map->entries[index].line2 = line;
		return;
	}
	if (pass == 2)
		return;
	map->entries[index].line1 = line;
	map->entries[index].hash = record->ha;
	map->entries[index].anchor = is_anchor(xpp, map->env->xdf1.recs[line - 1]->ptr);
	if (!map->first)
		map->first = map->entries + index;
	if (map->last) {
		map->last->next = map->entries + index;
		map->entries[index].previous = map->last;
	}
	map->last = map->entries + index;
	map->nr++;
}

/*
 * This function has to be called for each recursion into the inter-hunk
 * parts, as previously non-unique lines can become unique when being
 * restricted to a smaller part of the files.
 *
 * It is assumed that env has been prepared using xdl_prepare().
 */
static int fill_hashmap(xpparam_t const *xpp, xdfenv_t *env,
		struct hashmap *result,
		int line1, int count1, int line2, int count2)
{
	result->xpp = xpp;
	result->env = env;

	/* We know exactly how large we want the hash map */
	result->alloc = count1 * 2;
	if (!XDL_CALLOC_ARRAY(result->entries, result->alloc))
		return -1;

	/* First, fill with entries from the first file */
	while (count1--)
		insert_record(xpp, line1++, result, 1);

	/* Then search for matches in the second file */
	while (count2--)
		insert_record(xpp, line2++, result, 2);

	return 0;
}

/*
 * Find the longest sequence with a smaller last element (meaning a smaller
 * line2, as we construct the sequence with entries ordered by line1).
 */
static int binary_search(struct entry **sequence, int longest,
		struct entry *entry)
{
	int left = -1, right = longest;

	while (left + 1 < right) {
		int middle = left + (right - left) / 2;
		/* by construction, no two entries can be equal */
		if (sequence[middle]->line2 > entry->line2)
			right = middle;
		else
			left = middle;
	}
	/* return the index in "sequence", _not_ the sequence length */
	return left;
}

/*
 * The idea is to start with the list of common unique lines sorted by
 * the order in file1.  For each of these pairs, the longest (partial)
 * sequence whose last element's line2 is smaller is determined.
 *
 * For efficiency, the sequences are kept in a list containing exactly one
 * item per sequence length: the sequence with the smallest last
 * element (in terms of line2).
 */
static int find_longest_common_sequence(struct hashmap *map, struct entry **res)
{
	struct entry **sequence;
	int longest = 0, i;
	struct entry *entry;

	/*
	 * If not -1, this entry in sequence must never be overridden.
	 * Therefore, overriding entries before this has no effect, so
	 * do not do that either.
	 */
	int anchor_i = -1;

	if (!XDL_ALLOC_ARRAY(sequence, map->nr))
		return -1;

	for (entry = map->first; entry; entry = entry->next) {
		if (!entry->line2 || entry->line2 == NON_UNIQUE)
			continue;
		i = binary_search(sequence, longest, entry);
		entry->previous = i < 0 ? NULL : sequence[i];
		++i;
		if (i <= anchor_i)
			continue;
		sequence[i] = entry;
		if (entry->anchor) {
			anchor_i = i;
			longest = anchor_i + 1;
		} else if (i == longest) {
			longest++;
		}
	}

	/* No common unique lines were found */
	if (!longest) {
		*res = NULL;
		xdl_free(sequence);
		return 0;
	}

	/* Iterate starting at the last element, adjusting the "next" members */
	entry = sequence[longest - 1];
	entry->next = NULL;
	while (entry->previous) {
		entry->previous->next = entry;
		entry = entry->previous;
	}
	*res = entry;
	xdl_free(sequence);
	return 0;
}

static int match(struct hashmap *map, int line1, int line2)
{
	xrecord_t *record1 = map->env->xdf1.recs[line1 - 1];
	xrecord_t *record2 = map->env->xdf2.recs[line2 - 1];
	return record1->ha == record2->ha;
}

static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
		int line1, int count1, int line2, int count2);

static int walk_common_sequence(struct hashmap *map, struct entry *first,
		int line1, int count1, int line2, int count2)
{
	int end1 = line1 + count1, end2 = line2 + count2;
	int next1, next2;

	for (;;) {
		/* Try to grow the line ranges of common lines */
		if (first) {
			next1 = first->line1;
			next2 = first->line2;
			while (next1 > line1 && next2 > line2 &&
					match(map, next1 - 1, next2 - 1)) {
				next1--;
				next2--;
			}
		} else {
			next1 = end1;
			next2 = end2;
		}
		while (line1 < next1 && line2 < next2 &&
				match(map, line1, line2)) {
			line1++;
			line2++;
		}

		/* Recurse */
		if (next1 > line1 || next2 > line2) {
			if (patience_diff(map->xpp, map->env,
					line1, next1 - line1,
					line2, next2 - line2))
				return -1;
		}

		if (!first)
			return 0;

		while (first->next &&
				first->next->line1 == first->line1 + 1 &&
				first->next->line2 == first->line2 + 1)
			first = first->next;

		line1 = first->line1 + 1;
		line2 = first->line2 + 1;

		first = first->next;
	}
}

static int fall_back_to_classic_diff(struct hashmap *map,
		int line1, int count1, int line2, int count2)
{
	xpparam_t xpp;

	memset(&xpp, 0, sizeof(xpp));
	xpp.flags = map->xpp->flags & ~XDF_DIFF_ALGORITHM_MASK;

	return xdl_fall_back_diff(map->env, &xpp,
				  line1, count1, line2, count2);
}

/*
 * Recursively find the longest common sequence of unique lines,
 * and if none was found, ask xdl_do_diff() to do the job.
 *
 * This function assumes that env was prepared with xdl_prepare_env().
 */
static int patience_diff(xpparam_t const *xpp, xdfenv_t *env,
		int line1, int count1, int line2, int count2)
{
	struct hashmap map;
	struct entry *first;
	int result = 0;

	/* trivial case: one side is empty */
	if (!count1) {
		while(count2--)
			env->xdf2.rchg[line2++ - 1] = 1;
		return 0;
	} else if (!count2) {
		while(count1--)
			env->xdf1.rchg[line1++ - 1] = 1;
		return 0;
	}

	memset(&map, 0, sizeof(map));
	if (fill_hashmap(xpp, env, &map,
			line1, count1, line2, count2))
		return -1;

	/* are there any matching lines at all? */
	if (!map.has_matches) {
		while(count1--)
			env->xdf1.rchg[line1++ - 1] = 1;
		while(count2--)
			env->xdf2.rchg[line2++ - 1] = 1;
		xdl_free(map.entries);
		return 0;
	}

	result = find_longest_common_sequence(&map, &first);
	if (result)
		goto out;
	if (first)
		result = walk_common_sequence(&map, first,
			line1, count1, line2, count2);
	else
		result = fall_back_to_classic_diff(&map,
			line1, count1, line2, count2);
 out:
	xdl_free(map.entries);
	return result;
}

int xdl_do_patience_diff(xpparam_t const *xpp, xdfenv_t *env)
{
	return patience_diff(xpp, env, 1, env->xdf1.nrec, 1, env->xdf2.nrec);
}