Mercurial > hg
annotate mercurial/bdiff.c @ 495:e94cebc60d96
Pull from TAH
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Pull from TAH
manifest hash: 08b55e07198b8a4272753895fe3727d9f52ebb75
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (GNU/Linux)
iD8DBQFCwO5YywK+sNU5EO8RArUtAJ9gsYYNbZH22COOz9B7ppwgCDxM8ACfYWcl
n9Dim3Z7qepGUXvRDEeFZ9c=
=JMQx
-----END PGP SIGNATURE-----
author | mpm@selenic.com |
---|---|
date | Mon, 27 Jun 2005 22:29:44 -0800 |
parents | 098d1f039c18 934279f3ca53 |
children | 7f3fc8fd427e |
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> |
411
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
15 #ifdef _WIN32 |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
16 static uint32_t htonl(uint32_t x) |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
17 { |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
18 return ((x & 0x000000ffUL) << 24) | |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
19 ((x & 0x0000ff00UL) << 8) | |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
20 ((x & 0x00ff0000UL) >> 8) | |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
21 ((x & 0xff000000UL) >> 24); |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
22 } |
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
23 #else |
472 | 24 #include <netinet/in.h> |
411
9e9f7ab43ce2
Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents:
400
diff
changeset
|
25 #endif |
400
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 line { |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
28 int h, len, n, e; |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
29 const char *l; |
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 |
474 | 32 struct pos { |
33 int pos, len; | |
34 }; | |
35 | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
36 struct hunk { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
37 int a1, a2, b1, b2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
38 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
39 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
40 struct hunklist { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
41 struct hunk *base, *head; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
42 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
43 |
439 | 44 static __inline uint32_t rol32(uint32_t word, unsigned int shift) |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
45 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
46 return (word << shift) | (word >> (32 - shift)); |
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 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
49 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
|
50 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
51 int h, i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
52 const char *p, *b = a; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
53 struct line *l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
54 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
55 /* count the lines */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
56 i = 1; /* extra line for sentinel */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
57 for (p = a; p < a + len; p++) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
58 if (*p == '\n' || p == a + len - 1) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
59 i++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
60 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
61 *lr = l = malloc(sizeof(struct line) * i); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
62 if (!l) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
63 return -1; |
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 /* build the line array and calculate hashes */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
66 h = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
67 for (p = a; p < a + len; p++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
68 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
|
69 if (*p == '\n' || p == a + len - 1) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
70 l->len = p - b + 1; |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
71 l->h = h * l->len; |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
72 l->l = b; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
73 l->n = -1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
74 l++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
75 b = p + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
76 h = 0; |
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 } |
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 /* set up a sentinel */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
81 l->h = l->len = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
82 l->l = a + len; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
83 return i - 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
84 } |
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 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
|
87 { |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
88 return a->h != b->h || a->len != b->len || memcmp(a->l, b->l, a->len); |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
89 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
90 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
91 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
|
92 { |
474 | 93 int i, j, buckets = 1, t; |
94 struct pos *h; | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
95 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
96 /* 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
|
97 while (buckets < bn + 1) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
98 buckets *= 2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
99 |
474 | 100 h = malloc(buckets * sizeof(struct pos)); |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
101 buckets = buckets - 1; |
474 | 102 if (!h) |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
103 return 0; |
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 /* clear the hash table */ |
474 | 106 for (i = 0; i <= buckets; i++) { |
107 h[i].pos = -1; | |
108 h[i].len = 0; | |
109 } | |
400
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 /* add lines to the hash table chains */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
112 for (i = bn - 1; i >= 0; i--) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
113 /* find the equivalence class */ |
474 | 114 for (j = b[i].h & buckets; h[j].pos != -1; |
115 j = (j + 1) & buckets) | |
116 if (!cmp(b + i, b + h[j].pos)) | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
117 break; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
118 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
119 /* add to the head of the equivalence class */ |
474 | 120 b[i].n = h[j].pos; |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
121 b[i].e = j; |
474 | 122 h[j].pos = i; |
123 h[j].len++; /* keep track of popularity */ | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
124 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
125 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
126 /* compute popularity threshold */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
127 t = (bn >= 200) ? bn / 100 : bn + 1; |
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 /* 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
|
130 for (i = 0; i < an; i++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
131 /* find the equivalence class */ |
474 | 132 for (j = a[i].h & buckets; h[j].pos != -1; |
133 j = (j + 1) & buckets) | |
134 if (!cmp(a + i, b + h[j].pos)) | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
135 break; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
136 |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
137 a[i].e = j; /* use equivalence class for quick compare */ |
474 | 138 if(h[j].len <= t) |
139 a[i].n = h[j].pos; /* point to head of match list */ | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
140 else |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
141 a[i].n = -1; /* too popular */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
142 } |
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 /* discard hash tables */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
145 free(h); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
146 return 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
147 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
148 |
474 | 149 static int longest_match(struct line *a, struct line *b, struct pos *pos, |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
150 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
|
151 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
152 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
|
153 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
154 for (i = a1; i < a2; i++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
155 /* skip things before the current block */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
156 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
|
157 ; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
158 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
159 /* 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
|
160 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
|
161 /* does this extend an earlier match? */ |
474 | 162 if (i > a1 && j > b1 && pos[j - 1].pos == i - 1) |
163 k = pos[j - 1].len + 1; | |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
164 else |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
165 k = 1; |
474 | 166 pos[j].pos = i; |
167 pos[j].len = k; | |
400
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 /* best match so far? */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
170 if (k > mk) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
171 mi = i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
172 mj = j; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
173 mk = k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
174 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
175 } |
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 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
178 if (mk) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
179 mi = mi - mk + 1; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
180 mj = mj - mk + 1; |
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 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
183 /* expand match to include neighboring popular lines */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
184 while (mi - mb > a1 && mj - mb > b1 && |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
185 a[mi - mb - 1].e == b[mj - mb - 1].e) |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
186 mb++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
187 while (mi + mk < a2 && mj + mk < b2 && |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
188 a[mi + mk].e == b[mj + mk].e) |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
189 mk++; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
190 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
191 *omi = mi - mb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
192 *omj = mj - mb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
193 return mk + mb; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
194 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
195 |
474 | 196 static void recurse(struct line *a, struct line *b, struct pos *pos, |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
197 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
|
198 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
199 int i, j, k; |
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 /* find the longest match in this chunk */ |
474 | 202 k = longest_match(a, b, pos, a1, a2, b1, b2, &i, &j); |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
203 if (!k) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
204 return; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
205 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
206 /* and recurse on the remaining chunks on either side */ |
474 | 207 recurse(a, b, pos, a1, i, b1, j, l); |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
208 l->head->a1 = i; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
209 l->head->a2 = i + k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
210 l->head->b1 = j; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
211 l->head->b2 = j + k; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
212 l->head++; |
474 | 213 recurse(a, b, pos, i + k, a2, j + k, b2, l); |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
214 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
215 |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
216 static struct hunklist diff(struct line *a, int an, struct line *b, int bn) |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
217 { |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
218 struct hunklist l; |
474 | 219 struct pos *pos; |
220 int t; | |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
221 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
222 /* allocate and fill arrays */ |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
223 t = equatelines(a, an, b, bn); |
474 | 224 pos = calloc(bn, sizeof(struct pos)); |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
225 l.head = l.base = malloc(sizeof(struct hunk) * ((an + bn) / 4 + 2)); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
226 |
474 | 227 if (pos && l.base && t) { |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
228 /* generate the matching block list */ |
474 | 229 recurse(a, b, pos, 0, an, 0, bn, &l); |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
230 l.head->a1 = an; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
231 l.head->b1 = bn; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
232 l.head++; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
233 } |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
234 |
474 | 235 free(pos); |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
236 return l; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
237 } |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
238 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
239 static PyObject *blocks(PyObject *self, PyObject *args) |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
240 { |
435 | 241 PyObject *sa, *sb, *rl = NULL, *m; |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
242 struct line *a, *b; |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
243 struct hunklist l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
244 struct hunk *h; |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
245 int an, bn, pos = 0; |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
246 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
247 if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb)) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
248 return NULL; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
249 |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
250 an = splitlines(PyString_AsString(sa), PyString_Size(sa), &a); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
251 bn = splitlines(PyString_AsString(sb), PyString_Size(sb), &b); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
252 if (!a || !b) |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
253 goto nomem; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
254 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
255 l = diff(a, an, b, bn); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
256 rl = PyList_New(l.head - l.base); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
257 if (!l.head || !rl) |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
258 goto nomem; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
259 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
260 for(h = l.base; h != l.head; h++) { |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
261 m = Py_BuildValue("iiii", h->a1, h->a2, h->b1, h->b2); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
262 PyList_SetItem(rl, pos, m); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
263 pos++; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
264 } |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
265 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
266 nomem: |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
267 free(a); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
268 free(b); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
269 free(l.base); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
270 return rl ? rl : PyErr_NoMemory(); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
271 } |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
272 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
273 static PyObject *bdiff(PyObject *self, PyObject *args) |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
274 { |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
275 PyObject *sa, *sb, *result = NULL; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
276 struct line *al, *bl; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
277 struct hunklist l; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
278 struct hunk *h; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
279 char encode[12], *rb; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
280 int an, bn, len = 0, la = 0, lb = 0; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
281 |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
282 if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb)) |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
283 return NULL; |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
284 |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
285 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
|
286 bn = splitlines(PyString_AsString(sb), PyString_Size(sb), &bl); |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
287 if (!al || !bl) |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
288 goto nomem; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
289 |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
290 l = diff(al, an, bl, bn); |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
291 if (!l.head) |
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
292 goto nomem; |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
293 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
294 /* calculate length of output */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
295 for(h = l.base; h != l.head; h++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
296 if (h->a1 != la || h->b1 != lb) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
297 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
|
298 la = h->a2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
299 lb = h->b2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
300 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
301 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
302 result = PyString_FromStringAndSize(NULL, len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
303 if (!result) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
304 goto nomem; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
305 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
306 /* build binary patch */ |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
307 rb = PyString_AsString(result); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
308 la = lb = 0; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
309 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
310 for(h = l.base; h != l.head; h++) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
311 if (h->a1 != la || h->b1 != lb) { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
312 len = bl[h->b1].l - bl[lb].l; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
313 *(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
|
314 *(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
|
315 *(uint32_t *)(encode + 8) = htonl(len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
316 memcpy(rb, encode, 12); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
317 memcpy(rb + 12, bl[lb].l, len); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
318 rb += 12 + len; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
319 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
320 la = h->a2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
321 lb = h->b2; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
322 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
323 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
324 nomem: |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
325 free(al); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
326 free(bl); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
327 free(l.base); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
328 return result ? result : PyErr_NoMemory(); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
329 } |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
330 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
331 static char mdiff_doc[] = "Efficient binary diff."; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
332 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
333 static PyMethodDef methods[] = { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
334 {"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"}, |
433
79c694462294
Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents:
411
diff
changeset
|
335 {"blocks", blocks, METH_VARARGS, "find a list of matching lines\n"}, |
400
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
336 {NULL, NULL} |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
337 }; |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
338 |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
339 PyMODINIT_FUNC initbdiff(void) |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
340 { |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
341 Py_InitModule3("bdiff", methods, mdiff_doc); |
8b067bde6679
Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff
changeset
|
342 } |