annotate mercurial/bdiff.c @ 5452:82b4ff3abbcd

bdiff: tweaks for large files - adjust the common line threshold to .1% this speeds up a delta of 7M lines of source from 10m to 40s - adjust the scaling of the hash array down a bit as it was raising the peak memory usage significantly
author Matt Mackall <mpm@selenic.com>
date Thu, 11 Oct 2007 00:46:56 -0500
parents d0c48891dd4a
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
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
2858
345bac2bc4ec update copyrights.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2600
diff changeset
4 Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>
400
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>
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
15 #include <limits.h>
867
0cd2ee61b10a Allow Mercurial to build on HP-UX 11
tksoh@users.sourceforge.net
parents: 839
diff changeset
16
3547
8c617d48564a add AIX to the list of compilers that don't have inline keyword
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 3369
diff changeset
17 #if defined __hpux || defined __SUNPRO_C || defined _AIX
1759
5afd459db177 Sunpro compiler patch
Fabian Otto <sigsegv@alchiba.ni.cs.tu-berlin.de>
parents: 1542
diff changeset
18 # define inline
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2577
diff changeset
19 #endif
1759
5afd459db177 Sunpro compiler patch
Fabian Otto <sigsegv@alchiba.ni.cs.tu-berlin.de>
parents: 1542
diff changeset
20
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
21 #ifdef _WIN32
551
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
22 #ifdef _MSC_VER
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
23 #define inline __inline
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
24 typedef unsigned long uint32_t;
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
25 #else
510
7f3fc8fd427e More fiddling with uint32_t includes for extensions
mpm@selenic.com
parents: 495
diff changeset
26 #include <stdint.h>
551
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
27 #endif
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
28 static uint32_t htonl(uint32_t x)
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
29 {
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
30 return ((x & 0x000000ffUL) << 24) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
31 ((x & 0x0000ff00UL) << 8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
32 ((x & 0x00ff0000UL) >> 8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
33 ((x & 0xff000000UL) >> 24);
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
34 }
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
35 #else
510
7f3fc8fd427e More fiddling with uint32_t includes for extensions
mpm@selenic.com
parents: 495
diff changeset
36 #include <sys/types.h>
4073
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3547
diff changeset
37 #ifdef __BEOS__
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3547
diff changeset
38 #include <ByteOrder.h>
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3547
diff changeset
39 #else
597
e530637ea060 [PATCH] use <arpa/inet.h> instead of <netinet/in.h> for ntohl/htonl
mpm@selenic.com
parents: 553
diff changeset
40 #include <arpa/inet.h>
4073
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3547
diff changeset
41 #endif
2543
860e9c83fc59 Include inttypes.h instead of stdint.h (fixes issue299)
Thomas Arendsen Hein <thomas@intevation.de>
parents: 2483
diff changeset
42 #include <inttypes.h>
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
43 #endif
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
44
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
45 struct line {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
46 int h, len, n, e;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
47 const char *l;
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
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
50 struct pos {
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
51 int pos, len;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
52 };
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
53
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
54 struct hunk {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
55 int a1, a2, b1, b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
56 };
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
57
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
58 struct hunklist {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
59 struct hunk *base, *head;
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
62 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
63 {
5366
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5365
diff changeset
64 int h, i;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
65 const char *p, *b = a;
5364
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5363
diff changeset
66 const char * const plast = a + len - 1;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
67 struct line *l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
68
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
69 /* count the lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
70 i = 1; /* extra line for sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
71 for (p = a; p < a + len; p++)
5364
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5363
diff changeset
72 if (*p == '\n' || p == plast)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
73 i++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
74
1978
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
75 *lr = l = (struct line *)malloc(sizeof(struct line) * i);
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
76 if (!l)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
77 return -1;
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 /* build the line array and calculate hashes */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
80 h = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
81 for (p = a; p < a + len; p++) {
5366
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5365
diff changeset
82 /* Leonid Yuriev's hash */
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5365
diff changeset
83 h = (h * 1664525) + *p + 1013904223;
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5365
diff changeset
84
5364
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5363
diff changeset
85 if (*p == '\n' || p == plast) {
5366
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5365
diff changeset
86 l->h = h;
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5365
diff changeset
87 h = 0;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
88 l->len = p - b + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
89 l->l = b;
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
90 l->n = INT_MAX;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
91 l++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
92 b = p + 1;
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 }
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 /* set up a sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
97 l->h = l->len = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
98 l->l = a + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
99 return i - 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
100 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
101
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
102 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
103 {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
104 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
105 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
106
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
107 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
108 {
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
109 int i, j, buckets = 1, t, scale;
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
110 struct pos *h = NULL;
400
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 /* 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
113 while (buckets < bn + 1)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
114 buckets *= 2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
115
5363
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
116 /* try to allocate a large hash table to avoid collisions */
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
117 for (scale = 4; scale; scale /= 2) {
5363
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
118 h = (struct pos *)malloc(scale * buckets * sizeof(struct pos));
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
119 if (h)
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
120 break;
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
121 }
5363
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
122
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
123 if (!h)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
124 return 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
125
5363
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
126 buckets = buckets * scale - 1;
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
127
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
128 /* clear the hash table */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
129 for (i = 0; i <= buckets; i++) {
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
130 h[i].pos = INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
131 h[i].len = 0;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
132 }
400
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 /* add lines to the hash table chains */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
135 for (i = bn - 1; i >= 0; i--) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
136 /* find the equivalence class */
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
137 for (j = b[i].h & buckets; h[j].pos != INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
138 j = (j + 1) & buckets)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
139 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
140 break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
141
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
142 /* add to the head of the equivalence class */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
143 b[i].n = h[j].pos;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
144 b[i].e = j;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
145 h[j].pos = i;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
146 h[j].len++; /* keep track of popularity */
400
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
149 /* compute popularity threshold */
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5366
diff changeset
150 t = (bn >= 4000) ? bn / 1000 : bn + 1;
400
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 /* 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
153 for (i = 0; i < an; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
154 /* find the equivalence class */
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
155 for (j = a[i].h & buckets; h[j].pos != INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
156 j = (j + 1) & buckets)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
157 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
158 break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
159
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
160 a[i].e = j; /* use equivalence class for quick compare */
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
161 if (h[j].len <= t)
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
162 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
163 else
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
164 a[i].n = INT_MAX; /* too popular */
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
165 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
166
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
167 /* discard hash tables */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
168 free(h);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
169 return 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
170 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
171
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
172 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
173 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
174 {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
175 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
176
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
177 for (i = a1; i < a2; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
178 /* skip things before the current block */
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
179 for (j = a[i].n; j < b1; j = b[j].n)
400
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 /* loop through all lines match a[i] in b */
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
183 for (; j < b2; j = b[j].n) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
184 /* does this extend an earlier match? */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
185 if (i > a1 && j > b1 && pos[j - 1].pos == i - 1)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
186 k = pos[j - 1].len + 1;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
187 else
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
188 k = 1;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
189 pos[j].pos = i;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
190 pos[j].len = k;
400
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 /* best match so far? */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
193 if (k > mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
194 mi = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
195 mj = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
196 mk = k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
197 }
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 }
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 if (mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
202 mi = mi - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
203 mj = mj - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
204 }
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 /* expand match to include neighboring popular lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
207 while (mi - mb > a1 && mj - mb > b1 &&
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
208 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
209 mb++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
210 while (mi + mk < a2 && mj + mk < b2 &&
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
211 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
212 mk++;
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 *omi = mi - mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
215 *omj = mj - mb;
5365
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5364
diff changeset
216
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
217 return mk + mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
218 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
219
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
220 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
221 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
222 {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
223 int i, j, k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
224
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
225 /* find the longest match in this chunk */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
226 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
227 if (!k)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
228 return;
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 /* and recurse on the remaining chunks on either side */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
231 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
232 l->head->a1 = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
233 l->head->a2 = i + k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
234 l->head->b1 = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
235 l->head->b2 = j + k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
236 l->head++;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
237 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
238 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
239
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
240 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
241 {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
242 struct hunklist l;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
243 struct pos *pos;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
244 int t;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
245
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
246 /* allocate and fill arrays */
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
247 t = equatelines(a, an, b, bn);
1978
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
248 pos = (struct pos *)calloc(bn, sizeof(struct pos));
827
a61728b58dc0 Fix array overflow bug in bdiff
"Wallace, Eric S" <eric.s.wallace@intel.com>
parents: 597
diff changeset
249 /* we can't have more matches than lines in the shorter file */
1978
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
250 l.head = l.base = (struct hunk *)malloc(sizeof(struct hunk) *
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
251 ((an<bn ? an:bn) + 1));
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
252
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
253 if (pos && l.base && t) {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
254 /* generate the matching block list */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
255 recurse(a, b, pos, 0, an, 0, bn, &l);
4131
1ca664c964e0 don't return uninitialized memory from bdiff.blocks()
Erling Ellingsen <erlingalf@gmail.com>
parents: 3547
diff changeset
256 l.head->a1 = l.head->a2 = an;
1ca664c964e0 don't return uninitialized memory from bdiff.blocks()
Erling Ellingsen <erlingalf@gmail.com>
parents: 3547
diff changeset
257 l.head->b1 = l.head->b2 = bn;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
258 l.head++;
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
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
261 free(pos);
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
262 return l;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
263 }
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 static PyObject *blocks(PyObject *self, PyObject *args)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
266 {
435
e731d25ddab2 Fix a compile warning for bdiff
mpm@selenic.com
parents: 433
diff changeset
267 PyObject *sa, *sb, *rl = NULL, *m;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
268 struct line *a, *b;
970
bf375e93073b Fix possible unitialized variable warnings
mpm@selenic.com
parents: 896
diff changeset
269 struct hunklist l = {NULL, NULL};
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
270 struct hunk *h;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
271 int an, bn, pos = 0;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
272
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
273 if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb))
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
274 return NULL;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
275
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
276 an = splitlines(PyString_AsString(sa), PyString_Size(sa), &a);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
277 bn = splitlines(PyString_AsString(sb), PyString_Size(sb), &b);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
278 if (!a || !b)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
279 goto nomem;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
280
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
281 l = diff(a, an, b, bn);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
282 rl = PyList_New(l.head - l.base);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
283 if (!l.head || !rl)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
284 goto nomem;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
285
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
286 for (h = l.base; h != l.head; h++) {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
287 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
288 PyList_SetItem(rl, pos, m);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
289 pos++;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
290 }
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
291
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
292 nomem:
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
293 free(a);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
294 free(b);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
295 free(l.base);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
296 return rl ? rl : PyErr_NoMemory();
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
297 }
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
298
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
299 static PyObject *bdiff(PyObject *self, PyObject *args)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
300 {
3333
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2858
diff changeset
301 char *sa, *sb;
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2858
diff changeset
302 PyObject *result = NULL;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
303 struct line *al, *bl;
970
bf375e93073b Fix possible unitialized variable warnings
mpm@selenic.com
parents: 896
diff changeset
304 struct hunklist l = {NULL, NULL};
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
305 struct hunk *h;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
306 char encode[12], *rb;
3333
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2858
diff changeset
307 int an, bn, len = 0, la, lb;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
308
3369
4bad632913d8 python2.5 PyArg_ParseTuple fix
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 3333
diff changeset
309 if (!PyArg_ParseTuple(args, "s#s#:bdiff", &sa, &la, &sb, &lb))
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
310 return NULL;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
311
3333
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2858
diff changeset
312 an = splitlines(sa, la, &al);
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2858
diff changeset
313 bn = splitlines(sb, lb, &bl);
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
314 if (!al || !bl)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
315 goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
316
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
317 l = diff(al, an, bl, bn);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
318 if (!l.head)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
319 goto nomem;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
320
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
321 /* calculate length of output */
3333
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2858
diff changeset
322 la = lb = 0;
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
323 for (h = l.base; h != l.head; h++) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
324 if (h->a1 != la || h->b1 != lb)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
325 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
326 la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
327 lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
328 }
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 result = PyString_FromStringAndSize(NULL, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
331 if (!result)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
332 goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
333
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
334 /* build binary patch */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
335 rb = PyString_AsString(result);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
336 la = lb = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
337
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
338 for (h = l.base; h != l.head; h++) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
339 if (h->a1 != la || h->b1 != lb) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
340 len = bl[h->b1].l - bl[lb].l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
341 *(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
342 *(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
343 *(uint32_t *)(encode + 8) = htonl(len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
344 memcpy(rb, encode, 12);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
345 memcpy(rb + 12, bl[lb].l, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
346 rb += 12 + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
347 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
348 la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
349 lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
350 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
351
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
352 nomem:
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
353 free(al);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
354 free(bl);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
355 free(l.base);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
356 return result ? result : PyErr_NoMemory();
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
357 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
358
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
359 static char mdiff_doc[] = "Efficient binary diff.";
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
360
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
361 static PyMethodDef methods[] = {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
362 {"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"},
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
363 {"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
364 {NULL, NULL}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
365 };
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
366
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
367 PyMODINIT_FUNC initbdiff(void)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
368 {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
369 Py_InitModule3("bdiff", methods, mdiff_doc);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
370 }
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
371