summaryrefslogtreecommitdiff
path: root/sha1-lookup.c
blob: c4dc55d1f5cd07adcf46865354f841cc587c51f6 (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
#include "cache.h"
#include "sha1-lookup.h"
 
static uint32_t take2(const unsigned char *sha1)
{
	return ((sha1[0] << 8) | sha1[1]);
}
 
/*
 * Conventional binary search loop looks like this:
 *
 *      do {
 *              int mi = (lo + hi) / 2;
 *              int cmp = "entry pointed at by mi" minus "target";
 *              if (!cmp)
 *                      return (mi is the wanted one)
 *              if (cmp > 0)
 *                      hi = mi; "mi is larger than target"
 *              else
 *                      lo = mi+1; "mi is smaller than target"
 *      } while (lo < hi);
 *
 * The invariants are:
 *
 * - When entering the loop, lo points at a slot that is never
 *   above the target (it could be at the target), hi points at a
 *   slot that is guaranteed to be above the target (it can never
 *   be at the target).
 *
 * - We find a point 'mi' between lo and hi (mi could be the same
 *   as lo, but never can be the same as hi), and check if it hits
 *   the target.  There are three cases:
 *
 *    - if it is a hit, we are happy.
 *
 *    - if it is strictly higher than the target, we update hi with
 *      it.
 *
 *    - if it is strictly lower than the target, we update lo to be
 *      one slot after it, because we allow lo to be at the target.
 *
 * When choosing 'mi', we do not have to take the "middle" but
 * anywhere in between lo and hi, as long as lo <= mi < hi is
 * satisfied.  When we somehow know that the distance between the
 * target and lo is much shorter than the target and hi, we could
 * pick mi that is much closer to lo than the midway.
 */
/*
 * The table should contain "nr" elements.
 * The sha1 of element i (between 0 and nr - 1) should be returned
 * by "fn(i, table)".
 */
int sha1_pos(const unsigned char *sha1, void *table, size_t nr,
	     sha1_access_fn fn)
{
	size_t hi = nr;
	size_t lo = 0;
	size_t mi = 0;
 
	if (!nr)
		return -1;
 
	if (nr != 1) {
		size_t lov, hiv, miv, ofs;
 
		for (ofs = 0; ofs < 18; ofs += 2) {
			lov = take2(fn(0, table) + ofs);
			hiv = take2(fn(nr - 1, table) + ofs);
			miv = take2(sha1 + ofs);
			if (miv < lov)
				return -1;
			if (hiv < miv)
				return -1 - nr;
			if (lov != hiv) {
				/*
				 * At this point miv could be equal
				 * to hiv (but sha1 could still be higher);
				 * the invariant of (mi < hi) should be
				 * kept.
				 */
				mi = (nr - 1) * (miv - lov) / (hiv - lov);
				if (lo <= mi && mi < hi)
					break;
				die("BUG: assertion failed in binary search");
			}
		}
		if (18 <= ofs)
			die("cannot happen -- lo and hi are identical");
	}
 
	do {
		int cmp;
		cmp = hashcmp(fn(mi, table), sha1);
		if (!cmp)
			return mi;
		if (cmp > 0)
			hi = mi;
		else
			lo = mi + 1;
		mi = (hi + lo) / 2;
	} while (lo < hi);
	return -lo-1;
}
 
/*
 * Conventional binary search loop looks like this:
 *
 *	unsigned lo, hi;
 *      do {
 *              unsigned mi = (lo + hi) / 2;
 *              int cmp = "entry pointed at by mi" minus "target";
 *              if (!cmp)
 *                      return (mi is the wanted one)
 *              if (cmp > 0)
 *                      hi = mi; "mi is larger than target"
 *              else
 *                      lo = mi+1; "mi is smaller than target"
 *      } while (lo < hi);
 *
 * The invariants are:
 *
 * - When entering the loop, lo points at a slot that is never
 *   above the target (it could be at the target), hi points at a
 *   slot that is guaranteed to be above the target (it can never
 *   be at the target).
 *
 * - We find a point 'mi' between lo and hi (mi could be the same
 *   as lo, but never can be as same as hi), and check if it hits
 *   the target.  There are three cases:
 *
 *    - if it is a hit, we are happy.
 *
 *    - if it is strictly higher than the target, we set it to hi,
 *      and repeat the search.
 *
 *    - if it is strictly lower than the target, we update lo to
 *      one slot after it, because we allow lo to be at the target.
 *
 *   If the loop exits, there is no matching entry.
 *
 * When choosing 'mi', we do not have to take the "middle" but
 * anywhere in between lo and hi, as long as lo <= mi < hi is
 * satisfied.  When we somehow know that the distance between the
 * target and lo is much shorter than the target and hi, we could
 * pick mi that is much closer to lo than the midway.
 *
 * Now, we can take advantage of the fact that SHA-1 is a good hash
 * function, and as long as there are enough entries in the table, we
 * can expect uniform distribution.  An entry that begins with for
 * example "deadbeef..." is much likely to appear much later than in
 * the midway of the table.  It can reasonably be expected to be near
 * 87% (222/256) from the top of the table.
 *
 * However, we do not want to pick "mi" too precisely.  If the entry at
 * the 87% in the above example turns out to be higher than the target
 * we are looking for, we would end up narrowing the search space down
 * only by 13%, instead of 50% we would get if we did a simple binary
 * search.  So we would want to hedge our bets by being less aggressive.
 *
 * The table at "table" holds at least "nr" entries of "elem_size"
 * bytes each.  Each entry has the SHA-1 key at "key_offset".  The
 * table is sorted by the SHA-1 key of the entries.  The caller wants
 * to find the entry with "key", and knows that the entry at "lo" is
 * not higher than the entry it is looking for, and that the entry at
 * "hi" is higher than the entry it is looking for.
 */
int sha1_entry_pos(const void *table,
		   size_t elem_size,
		   size_t key_offset,
		   unsigned lo, unsigned hi, unsigned nr,
		   const unsigned char *key)
{
	const unsigned char *base = table;
	const unsigned char *hi_key, *lo_key;
	unsigned ofs_0;
	static int debug_lookup = -1;
 
	if (debug_lookup < 0)
		debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
 
	if (!nr || lo >= hi)
		return -1;
 
	if (nr == hi)
		hi_key = NULL;
	else
		hi_key = base + elem_size * hi + key_offset;
	lo_key = base + elem_size * lo + key_offset;
 
	ofs_0 = 0;
	do {
		int cmp;
		unsigned ofs, mi, range;
		unsigned lov, hiv, kyv;
		const unsigned char *mi_key;
 
		range = hi - lo;
		if (hi_key) {
			for (ofs = ofs_0; ofs < 20; ofs++)
				if (lo_key[ofs] != hi_key[ofs])
					break;
			ofs_0 = ofs;
			/*
			 * byte 0 thru (ofs-1) are the same between
			 * lo and hi; ofs is the first byte that is
			 * different.
			 */
			hiv = hi_key[ofs_0];
			if (ofs_0 < 19)
				hiv = (hiv << 8) | hi_key[ofs_0+1];
		} else {
			hiv = 256;
			if (ofs_0 < 19)
				hiv <<= 8;
		}
		lov = lo_key[ofs_0];
		kyv = key[ofs_0];
		if (ofs_0 < 19) {
			lov = (lov << 8) | lo_key[ofs_0+1];
			kyv = (kyv << 8) | key[ofs_0+1];
		}
		assert(lov < hiv);
 
		if (kyv < lov)
			return -1 - lo;
		if (hiv < kyv)
			return -1 - hi;
 
		/*
		 * Even if we know the target is much closer to 'hi'
		 * than 'lo', if we pick too precisely and overshoot
		 * (e.g. when we know 'mi' is closer to 'hi' than to
		 * 'lo', pick 'mi' that is higher than the target), we
		 * end up narrowing the search space by a smaller
		 * amount (i.e. the distance between 'mi' and 'hi')
		 * than what we would have (i.e. about half of 'lo'
		 * and 'hi').  Hedge our bets to pick 'mi' less
		 * aggressively, i.e. make 'mi' a bit closer to the
		 * middle than we would otherwise pick.
		 */
		kyv = (kyv * 6 + lov + hiv) / 8;
		if (lov < hiv - 1) {
			if (kyv == lov)
				kyv++;
			else if (kyv == hiv)
				kyv--;
		}
		mi = (range - 1) * (kyv - lov) / (hiv - lov) + lo;
 
		if (debug_lookup) {
			printf("lo %u hi %u rg %u mi %u ", lo, hi, range, mi);
			printf("ofs %u lov %x, hiv %x, kyv %x\n",
			       ofs_0, lov, hiv, kyv);
		}
		if (!(lo <= mi && mi < hi))
			die("assertion failure lo %u mi %u hi %u %s",
			    lo, mi, hi, sha1_to_hex(key));
 
		mi_key = base + elem_size * mi + key_offset;
		cmp = memcmp(mi_key + ofs_0, key + ofs_0, 20 - ofs_0);
		if (!cmp)
			return mi;
		if (cmp > 0) {
			hi = mi;
			hi_key = mi_key;
		} else {
			lo = mi + 1;
			lo_key = mi_key + elem_size;
		}
	} while (lo < hi);
	return -lo-1;
}