Mercurial > hg
annotate mercurial/bdiff.c @ 400:8b067bde6679
Add a fast binary diff extension (not yet used)
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Add a fast binary diff extension (not yet used)
manifest hash: fbfdcab2b1f4856af45176fcf2423d602dfe88c4
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (GNU/Linux)
iD8DBQFCuL6eywK+sNU5EO8RAoT+AJ95z9gx2IrucBS30CnCQFkZT7lSbgCgnXh5
ScZcgwzJ/mEo9i5vuKNlCIs=
=Gr58
-----END PGP SIGNATURE-----
author | mpm@selenic.com |
---|---|
date | Tue, 21 Jun 2005 17:27:58 -0800 |
parents | |
children | 9e9f7ab43ce2 |
rev | line source |
---|---|
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
1 /* |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
2 bdiff.c - efficient binary diff extension for Mercurial |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
3 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
4 Copyright 2005 Matt Mackall <mpm@selenic.com> |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
5 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
6 This software may be used and distributed according to the terms of |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
7 the GNU General Public License, incorporated herein by reference. |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
8 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
9 Based roughly on Python difflib |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
10 */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
11 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
12 #include <Python.h> |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
13 #include <stdlib.h> |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
14 #include <string.h> |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
15 #include <netinet/in.h> |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
16 #include <sys/types.h> |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
17 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
18 struct line { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
19 int h, len, n; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
20 const char *l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
21 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
22 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
23 struct hunk { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
24 int a1, a2, b1, b2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
25 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
26 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
27 struct hunklist { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
28 struct hunk *base, *head; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
29 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
30 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
31 static inline uint32_t rol32(uint32_t word, unsigned int shift) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
32 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
33 return (word << shift) | (word >> (32 - shift)); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
34 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
35 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
36 int splitlines(const char *a, int len, struct line **lr) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
37 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
38 int h, i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
39 const char *p, *b = a; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
40 struct line *l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
41 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
42 /* count the lines */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
43 i = 1; /* extra line for sentinel */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
44 for (p = a; p < a + len; p++) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
45 if (*p == '\n' || p == a + len - 1) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
46 i++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
47 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
48 *lr = l = malloc(sizeof(struct line) * i); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
49 if (!l) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
50 return -1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
51 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
52 /* build the line array and calculate hashes */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
53 h = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
54 for (p = a; p < a + len; p++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
55 h = *p + rol32(h, 7); /* a simple hash from GNU diff */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
56 if (*p == '\n' || p == a + len - 1) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
57 l->len = p - b + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
58 l->h = h; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
59 l->l = b; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
60 l->n = -1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
61 l++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
62 b = p + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
63 h = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
64 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
65 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
66 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
67 /* set up a sentinel */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
68 l->h = l->len = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
69 l->l = a + len; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
70 return i - 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
71 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
72 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
73 int inline cmp(struct line *a, struct line *b) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
74 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
75 return a->len != b->len || memcmp(a->l, b->l, a->len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
76 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
77 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
78 static int equatelines(struct line *a, int an, struct line *b, int bn) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
79 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
80 int i, j, buckets = 1, t, *h, *l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
81 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
82 /* build a hash table of the next highest power of 2 */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
83 while (buckets < bn + 1) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
84 buckets *= 2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
85 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
86 h = malloc(buckets * sizeof(int)); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
87 l = calloc(buckets, sizeof(int)); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
88 buckets = buckets - 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
89 if (!h || !l) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
90 free(h); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
91 return 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
92 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
93 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
94 /* clear the hash table */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
95 for (i = 0; i <= buckets; i++) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
96 h[i] = -1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
97 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
98 /* add lines to the hash table chains */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
99 for (i = bn - 1; i >= 0; i--) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
100 /* find the equivalence class */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
101 for (j = b[i].h & buckets; h[j] != -1; j = (j + 1) & buckets) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
102 if (!cmp(b + i, b + h[j])) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
103 break; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
104 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
105 /* add to the head of the equivalence class */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
106 b[i].n = h[j]; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
107 b[i].h = j; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
108 h[j] = i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
109 l[j]++; /* keep track of popularity */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
110 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
111 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
112 /* compute popularity threshold */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
113 t = (bn >= 200) ? bn / 100 : bn + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
114 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
115 /* match items in a to their equivalence class in b */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
116 for (i = 0; i < an; i++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
117 /* find the equivalence class */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
118 for (j = a[i].h & buckets; h[j] != -1; j = (j + 1) & buckets) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
119 if (!cmp(a + i, b + h[j])) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
120 break; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
121 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
122 a[i].h = j; /* use equivalence class for quick compare */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
123 if(l[j] <= t) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
124 a[i].n = h[j]; /* point to head of match list */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
125 else |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
126 a[i].n = -1; /* too popular */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
127 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
128 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
129 /* discard hash tables */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
130 free(h); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
131 free(l); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
132 return 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
133 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
134 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
135 static int longest_match(struct line *a, struct line *b, int *jpos, int *jlen, |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
136 int a1, int a2, int b1, int b2, int *omi, int *omj) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
137 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
138 int mi = a1, mj = b1, mk = 0, mb = 0, i, j, k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
139 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
140 for (i = a1; i < a2; i++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
141 /* skip things before the current block */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
142 for (j = a[i].n; j != -1 && j < b1; j = b[j].n) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
143 ; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
144 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
145 /* loop through all lines match a[i] in b */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
146 for (; j != -1 && j < b2; j = b[j].n) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
147 /* does this extend an earlier match? */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
148 if (i > a1 && j > b1 && jpos[j - 1] == i) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
149 k = jlen[j - 1] + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
150 else |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
151 k = 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
152 jpos[j] = i + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
153 jlen[j] = k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
154 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
155 /* best match so far? */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
156 if (k > mk) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
157 mi = i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
158 mj = j; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
159 mk = k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
160 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
161 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
162 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
163 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
164 if (mk) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
165 mi = mi - mk + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
166 mj = mj - mk + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
167 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
168 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
169 /* expand match to include neighboring popular lines */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
170 while (mi - mb > a1 && mj - mb > b1 && |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
171 a[mi - mb - 1].h == b[mj - mb - 1].h) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
172 mb++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
173 while (mi + mk < a2 && mj + mk < b2 && |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
174 a[mi + mk].h == b[mj + mk].h) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
175 mk++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
176 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
177 *omi = mi - mb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
178 *omj = mj - mb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
179 return mk + mb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
180 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
181 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
182 static void recurse(struct line *a, struct line *b, int *jpos, int *jlen, |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
183 int a1, int a2, int b1, int b2, struct hunklist *l) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
184 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
185 int i, j, k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
186 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
187 /* find the longest match in this chunk */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
188 k = longest_match(a, b, jpos, jlen, a1, a2, b1, b2, &i, &j); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
189 if (!k) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
190 return; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
191 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
192 /* and recurse on the remaining chunks on either side */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
193 recurse(a, b, jpos, jlen, a1, i, b1, j, l); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
194 l->head->a1 = i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
195 l->head->a2 = i + k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
196 l->head->b1 = j; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
197 l->head->b2 = j + k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
198 l->head++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
199 recurse(a, b, jpos, jlen, i + k, a2, j + k, b2, l); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
200 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
201 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
202 static PyObject *bdiff(PyObject *self, PyObject *args) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
203 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
204 PyObject *sa, *sb, *result = NULL; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
205 struct hunklist l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
206 struct hunk *h; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
207 struct line *al, *bl; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
208 char encode[12], *rb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
209 int an, bn, len = 0, t, la = 0, lb = 0, *jpos, *jlen; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
210 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
211 if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb)) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
212 return NULL; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
213 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
214 /* allocate and fill arrays */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
215 an = splitlines(PyString_AsString(sa), PyString_Size(sa), &al); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
216 bn = splitlines(PyString_AsString(sb), PyString_Size(sb), &bl); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
217 t = equatelines(al, an, bl, bn); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
218 jpos = calloc(bn, sizeof(int)); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
219 jlen = calloc(bn, sizeof(int)); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
220 l.head = l.base = malloc(sizeof(struct hunk) * ((an + bn) / 4 + 2)); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
221 if (!al || !bl || !jpos || !jlen || !l.base || !t) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
222 goto nomem; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
223 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
224 /* generate the matching block list */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
225 recurse(al, bl, jpos, jlen, 0, an, 0, bn, &l); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
226 l.head->a1 = an; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
227 l.head->b1 = bn; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
228 l.head++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
229 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
230 /* calculate length of output */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
231 for(h = l.base; h != l.head; h++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
232 if (h->a1 != la || h->b1 != lb) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
233 len += 12 + bl[h->b1].l - bl[lb].l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
234 la = h->a2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
235 lb = h->b2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
236 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
237 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
238 result = PyString_FromStringAndSize(NULL, len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
239 if (!result) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
240 goto nomem; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
241 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
242 /* build binary patch */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
243 rb = PyString_AsString(result); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
244 la = lb = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
245 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
246 for(h = l.base; h != l.head; h++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
247 if (h->a1 != la || h->b1 != lb) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
248 len = bl[h->b1].l - bl[lb].l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
249 *(uint32_t *)(encode) = htonl(al[la].l - al->l); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
250 *(uint32_t *)(encode + 4) = htonl(al[h->a1].l - al->l); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
251 *(uint32_t *)(encode + 8) = htonl(len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
252 memcpy(rb, encode, 12); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
253 memcpy(rb + 12, bl[lb].l, len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
254 rb += 12 + len; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
255 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
256 la = h->a2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
257 lb = h->b2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
258 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
259 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
260 nomem: |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
261 free(al); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
262 free(bl); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
263 free(jpos); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
264 free(jlen); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
265 free(l.base); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
266 return result ? result : PyErr_NoMemory(); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
267 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
268 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
269 static char mdiff_doc[] = "Efficient binary diff."; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
270 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
271 static PyMethodDef methods[] = { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
272 {"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"}, |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
273 {NULL, NULL} |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
274 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
275 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
276 PyMODINIT_FUNC initbdiff(void) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
277 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
278 Py_InitModule3("bdiff", methods, mdiff_doc); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
279 } |