annotate mercurial/bdiff.c @ 11364:0044193a1c45

bdiff.c: Added support for py3k. This patch adds support for py3k in bdiff.c. This is accomplished by including a header file responsible for abstracting the API differences between python 2 and python 3.
author Renato Cunha <renatoc@gmail.com>
date Tue, 15 Jun 2010 19:49:56 -0300
parents e96597c8d0ea
children faee0ffbc24b
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
2859
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>
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
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
3561
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
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
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
8858
16f6c13706df bdiff: fix compile with GCC -ansi (issue1690)
Matt Mackall <mpm@selenic.com>
parents: 7625
diff changeset
21 #ifdef __linux
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
22 #define inline __inline
8858
16f6c13706df bdiff: fix compile with GCC -ansi (issue1690)
Matt Mackall <mpm@selenic.com>
parents: 7625
diff changeset
23 #endif
16f6c13706df bdiff: fix compile with GCC -ansi (issue1690)
Matt Mackall <mpm@selenic.com>
parents: 7625
diff changeset
24
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
25 #ifdef _WIN32
551
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
26 #ifdef _MSC_VER
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
27 #define inline __inline
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
28 typedef unsigned long uint32_t;
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
29 #else
510
7f3fc8fd427e More fiddling with uint32_t includes for extensions
mpm@selenic.com
parents: 495
diff changeset
30 #include <stdint.h>
551
b460a2fd8bb7 [PATCH] bdiff/mpatch under MSVC
mpm@selenic.com
parents: 510
diff changeset
31 #endif
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
32 static uint32_t htonl(uint32_t x)
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
33 {
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
34 return ((x & 0x000000ffUL) << 24) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
35 ((x & 0x0000ff00UL) << 8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
36 ((x & 0x00ff0000UL) >> 8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
37 ((x & 0xff000000UL) >> 24);
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
38 }
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
39 #else
510
7f3fc8fd427e More fiddling with uint32_t includes for extensions
mpm@selenic.com
parents: 495
diff changeset
40 #include <sys/types.h>
7036
bfad9865b1dc allow Mercurial to compile on Haiku
Scott McCreary <scottmc2@gmail.com>
parents: 5620
diff changeset
41 #if defined __BEOS__ && !defined __HAIKU__
4073
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3561
diff changeset
42 #include <ByteOrder.h>
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3561
diff changeset
43 #else
597
e530637ea060 [PATCH] use <arpa/inet.h> instead of <netinet/in.h> for ntohl/htonl
mpm@selenic.com
parents: 553
diff changeset
44 #include <arpa/inet.h>
4073
95ffa36d1d2a BeOS compatibility support
Andrew Bachmann <andrewbachmann@gmail.com>
parents: 3561
diff changeset
45 #endif
2543
860e9c83fc59 Include inttypes.h instead of stdint.h (fixes issue299)
Thomas Arendsen Hein <thomas@intevation.de>
parents: 2483
diff changeset
46 #include <inttypes.h>
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
47 #endif
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
48
11364
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
49 #include "util.h"
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
50
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
51 struct line {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
52 int h, len, n, e;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
53 const char *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
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
56 struct pos {
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
57 int pos, len;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
58 };
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
59
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
60 struct hunk {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
61 int a1, a2, b1, b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
62 };
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
63
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
64 struct hunklist {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
65 struct hunk *base, *head;
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
68 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
69 {
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
70 int h, i;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
71 const char *p, *b = a;
5340
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5339
diff changeset
72 const char * const plast = a + len - 1;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
73 struct line *l;
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 /* count the lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
76 i = 1; /* extra line for sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
77 for (p = a; p < a + len; p++)
5340
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5339
diff changeset
78 if (*p == '\n' || p == plast)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
79 i++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
80
1978
10606ee61107 do proper typecasting on malloc() and calloc() calls
TK Soh <teekaysoh@yahoo.com>
parents: 1759
diff changeset
81 *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
82 if (!l)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
83 return -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 /* build the line array and calculate hashes */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
86 h = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
87 for (p = a; p < a + len; p++) {
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
88 /* Leonid Yuriev's hash */
7187
a79d3f535809 spaces->tabs in one line of a C extension for consistency
Thomas Arendsen Hein <thomas@intevation.de>
parents: 7036
diff changeset
89 h = (h * 1664525) + *p + 1013904223;
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
90
5340
5737845fd974 bdiff: simple splitlines optimization
Christoph Spiel <cspiel@freenet.de>
parents: 5339
diff changeset
91 if (*p == '\n' || p == plast) {
5342
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
92 l->h = h;
d0c48891dd4a bdiff: switch to lyhash
Matt Mackall <mpm@selenic.com>
parents: 5341
diff changeset
93 h = 0;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
94 l->len = p - b + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
95 l->l = b;
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
96 l->n = INT_MAX;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
97 l++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
98 b = p + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
99 }
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 /* set up a sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
103 l->h = l->len = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
104 l->l = a + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
105 return i - 1;
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
108 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
109 {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
110 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
111 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
112
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
113 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
114 {
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
115 int i, j, buckets = 1, t, scale;
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
116 struct pos *h = NULL;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
117
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
118 /* 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
119 while (buckets < bn + 1)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
120 buckets *= 2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
121
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
122 /* try to allocate a large hash table to avoid collisions */
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
123 for (scale = 4; scale; scale /= 2) {
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
124 h = (struct pos *)malloc(scale * buckets * sizeof(struct pos));
5452
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
125 if (h)
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
126 break;
82b4ff3abbcd bdiff: tweaks for large files
Matt Mackall <mpm@selenic.com>
parents: 5342
diff changeset
127 }
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
128
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
129 if (!h)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
130 return 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
131
5339
058e93c3d07d I have spotted the biggest bottleneck in "bdiff.c". Actually it was
Christoph Spiel <cspiel@freenet.de>
parents: 4134
diff changeset
132 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
133
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
134 /* clear the hash table */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
135 for (i = 0; i <= buckets; i++) {
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
136 h[i].pos = INT_MAX;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
137 h[i].len = 0;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
138 }
400
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 /* add lines to the hash table chains */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
141 for (i = bn - 1; i >= 0; i--) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
142 /* find the equivalence class */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
143 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
144 j = (j + 1) & buckets)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
145 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
146 break;
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 /* add to the head of the equivalence class */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
149 b[i].n = h[j].pos;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
150 b[i].e = j;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
151 h[j].pos = i;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
152 h[j].len++; /* keep track of popularity */
400
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
155 /* compute popularity threshold */
9534
8e202431d620 bdiff: gradually enable the popularity hack
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 8858
diff changeset
156 t = (bn >= 31000) ? bn / 1000 : 1000000 / (bn + 1);
400
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 /* 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
159 for (i = 0; i < an; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
160 /* find the equivalence class */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
161 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
162 j = (j + 1) & buckets)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
163 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
164 break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
165
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
166 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
167 if (h[j].len <= t)
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
168 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
169 else
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
170 a[i].n = INT_MAX; /* too popular */
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
171 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
172
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
173 /* discard hash tables */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
174 free(h);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
175 return 1;
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
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
178 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
179 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
180 {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
181 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
182
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
183 for (i = a1; i < a2; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
184 /* skip things before the current block */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
185 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
186 ;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
187
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
188 /* loop through all lines match a[i] in b */
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
189 for (; j < b2; j = b[j].n) {
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
190 /* does this extend an earlier match? */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
191 if (i > a1 && j > b1 && pos[j - 1].pos == i - 1)
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
192 k = pos[j - 1].len + 1;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
193 else
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
194 k = 1;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
195 pos[j].pos = i;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
196 pos[j].len = k;
400
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 /* best match so far? */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
199 if (k > mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
200 mi = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
201 mj = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
202 mk = k;
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 }
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
207 if (mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
208 mi = mi - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
209 mj = mj - mk + 1;
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
212 /* expand match to include neighboring popular lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
213 while (mi - mb > a1 && mj - mb > b1 &&
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
214 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
215 mb++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
216 while (mi + mk < a2 && mj + mk < b2 &&
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
217 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
218 mk++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
219
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
220 *omi = mi - mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
221 *omj = mj - mb;
5341
458acf92b49e bdiff: use INT_MAX to avoid some inner loop comparisons
Matt Mackall <mpm@selenic.com>
parents: 5340
diff changeset
222
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
223 return mk + mb;
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
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
226 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
227 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
228 {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
229 int i, j, k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
230
10500
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
231 while (1) {
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
232 /* find the longest match in this chunk */
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
233 k = longest_match(a, b, pos, a1, a2, b1, b2, &i, &j);
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
234 if (!k)
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
235 return;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
236
10500
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
237 /* and recurse on the remaining chunks on either side */
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
238 recurse(a, b, pos, a1, i, b1, j, l);
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
239 l->head->a1 = i;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
240 l->head->a2 = i + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
241 l->head->b1 = j;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
242 l->head->b2 = j + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
243 l->head++;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
244 /* tail-recursion didn't happen, so doing equivalent iteration */
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
245 a1 = i + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
246 b1 = j + k;
e96597c8d0ea bdiff: do not use recursion / avoid stackoverflow (issue1940)
Alistair Bell <alistair@bellsonline.com>
parents: 10282
diff changeset
247 }
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
248 }
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 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
251 {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
252 struct hunklist l;
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
253 struct hunk *curr;
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
254 struct pos *pos;
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
255 int t;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
256
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
257 /* allocate and fill arrays */
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
258 t = equatelines(a, an, b, bn);
5571
f84bb2e1cc3a fix calloc(0, ...) issue
Jim Hague <jim.hague@acm.org>
parents: 5452
diff changeset
259 pos = (struct pos *)calloc(bn ? bn : 1, sizeof(struct pos));
827
a61728b58dc0 Fix array overflow bug in bdiff
"Wallace, Eric S" <eric.s.wallace@intel.com>
parents: 597
diff changeset
260 /* 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
261 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
262 ((an<bn ? an:bn) + 1));
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
263
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
264 if (pos && l.base && t) {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
265 /* generate the matching block list */
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
266 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: 3561
diff changeset
267 l.head->a1 = l.head->a2 = an;
1ca664c964e0 don't return uninitialized memory from bdiff.blocks()
Erling Ellingsen <erlingalf@gmail.com>
parents: 3561
diff changeset
268 l.head->b1 = l.head->b2 = bn;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
269 l.head++;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
270 }
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
271
474
b2ae8283d1a6 Minor speed improvements for bdiff
mpm@selenic.com
parents: 472
diff changeset
272 free(pos);
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
273
7625
930a2be7e875 bdiff: add comment about normalization
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7189
diff changeset
274 /* normalize the hunk list, try to push each hunk towards the end */
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
275 for (curr = l.base; curr != l.head; curr++) {
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
276 struct hunk *next = curr + 1;
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
277 int shift = 0;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
278
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
279 if (next == l.head)
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
280 break;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
281
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
282 if (curr->a2 == next->a1)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
283 while (curr->a2 + shift < an && curr->b2 + shift < bn
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
284 && !cmp(a + curr->a2 + shift,
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
285 b + curr->b2 + shift))
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
286 shift++;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
287 else if (curr->b2 == next->b1)
10282
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
288 while (curr->b2 + shift < bn && curr->a2 + shift < an
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
289 && !cmp(b + curr->b2 + shift,
08a0f04b56bd many, many trivial check-code fixups
Matt Mackall <mpm@selenic.com>
parents: 9534
diff changeset
290 a + curr->a2 + shift))
7104
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
291 shift++;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
292 if (!shift)
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
293 continue;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
294 curr->b2 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
295 next->b1 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
296 curr->a2 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
297 next->a1 += shift;
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
298 }
9514cbb6e4f6 bdiff: normalize the diff (issue1295)
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7036
diff changeset
299
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
300 return l;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
301 }
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
302
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
303 static PyObject *blocks(PyObject *self, PyObject *args)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
304 {
435
e731d25ddab2 Fix a compile warning for bdiff
mpm@selenic.com
parents: 433
diff changeset
305 PyObject *sa, *sb, *rl = NULL, *m;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
306 struct line *a, *b;
970
bf375e93073b Fix possible unitialized variable warnings
mpm@selenic.com
parents: 896
diff changeset
307 struct hunklist l = {NULL, NULL};
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
308 struct hunk *h;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
309 int an, bn, pos = 0;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
310
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
311 if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb))
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
312 return NULL;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
313
11364
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
314 an = splitlines(PyBytes_AsString(sa), PyBytes_Size(sa), &a);
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
315 bn = splitlines(PyBytes_AsString(sb), PyBytes_Size(sb), &b);
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
316
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
317 if (!a || !b)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
318 goto nomem;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
319
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
320 l = diff(a, an, b, bn);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
321 rl = PyList_New(l.head - l.base);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
322 if (!l.head || !rl)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
323 goto nomem;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
324
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
325 for (h = l.base; h != l.head; h++) {
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
326 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
327 PyList_SetItem(rl, pos, m);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
328 pos++;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
329 }
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
330
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
331 nomem:
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
332 free(a);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
333 free(b);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
334 free(l.base);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
335 return rl ? rl : PyErr_NoMemory();
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
336 }
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
337
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
338 static PyObject *bdiff(PyObject *self, PyObject *args)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
339 {
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
340 char *sa, *sb;
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
341 PyObject *result = NULL;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
342 struct line *al, *bl;
970
bf375e93073b Fix possible unitialized variable warnings
mpm@selenic.com
parents: 896
diff changeset
343 struct hunklist l = {NULL, NULL};
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
344 struct hunk *h;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
345 char encode[12], *rb;
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
346 int an, bn, len = 0, la, lb;
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
347
3369
4bad632913d8 python2.5 PyArg_ParseTuple fix
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 3335
diff changeset
348 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
349 return NULL;
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
350
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
351 an = splitlines(sa, la, &al);
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
352 bn = splitlines(sb, lb, &bl);
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
353 if (!al || !bl)
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
354 goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
355
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
356 l = diff(al, an, bl, bn);
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
357 if (!l.head)
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
358 goto nomem;
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
359
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
360 /* calculate length of output */
3335
9061613c1593 Teach bdiff to support buffer objects
Brendan Cully <brendan@kublai.com>
parents: 2859
diff changeset
361 la = lb = 0;
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
362 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
363 if (h->a1 != la || h->b1 != lb)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
364 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
365 la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
366 lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
367 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
368
11364
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
369 result = PyBytes_FromStringAndSize(NULL, len);
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
370
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
371 if (!result)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
372 goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
373
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
374 /* build binary patch */
11364
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
375 rb = PyBytes_AsString(result);
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
376 la = lb = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
377
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
378 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
379 if (h->a1 != la || h->b1 != lb) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
380 len = bl[h->b1].l - bl[lb].l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
381 *(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
382 *(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
383 *(uint32_t *)(encode + 8) = htonl(len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
384 memcpy(rb, encode, 12);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
385 memcpy(rb + 12, bl[lb].l, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
386 rb += 12 + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
387 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
388 la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
389 lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
390 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
391
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
392 nomem:
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
393 free(al);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
394 free(bl);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
395 free(l.base);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
396 return result ? result : PyErr_NoMemory();
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
397 }
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
398
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
399 static char mdiff_doc[] = "Efficient binary diff.";
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
401 static PyMethodDef methods[] = {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
402 {"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"},
433
79c694462294 Add bdiff.blocks / minor performance tweaks
mpm@selenic.com
parents: 411
diff changeset
403 {"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
404 {NULL, NULL}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
405 };
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
406
11364
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
407 #ifdef IS_PY3K
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
408 static struct PyModuleDef bdiff_module = {
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
409 PyModuleDef_HEAD_INIT,
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
410 "bdiff",
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
411 mdiff_doc,
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
412 -1,
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
413 methods
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
414 };
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
415
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
416 PyMODINIT_FUNC PyInit_bdiff(void)
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
417 {
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
418 return PyModule_Create(&bdiff_module);
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
419 }
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
420 #else
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
421 PyMODINIT_FUNC initbdiff(void)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
422 {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
423 Py_InitModule3("bdiff", methods, mdiff_doc);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
424 }
11364
0044193a1c45 bdiff.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10500
diff changeset
425 #endif
1542
8e80eefb3de6 made C src formatting more consistent
twaldmann@thinkmo.de
parents: 1397
diff changeset
426