mercurial/bdiff.c
author mpm@selenic.com
Tue, 21 Jun 2005 18:54:44 -0800
changeset 411 9e9f7ab43ce2
parent 400 8b067bde6679
child 433 79c694462294
permissions -rw-r--r--
Add 'other OS' bits to bdiff.c / style cleanups -----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Add 'other OS' bits to bdiff.c / style cleanups manifest hash: 9a0ef60a59af0594f95a2b22de243fe8ef059762 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.0 (GNU/Linux) iD8DBQFCuNL0ywK+sNU5EO8RAg+yAKCe8dG411HdZZvsxB25AtfBBApQBQCgnb7O MGO0xvEBgAtt+3F+VJBkiU4= =F7r7 -----END PGP SIGNATURE-----
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     1
/*
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     2
 bdiff.c - efficient binary diff extension for Mercurial
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     3
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     4
 Copyright 2005 Matt Mackall <mpm@selenic.com>
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     5
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     6
 This software may be used and distributed according to the terms of
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     7
 the GNU General Public License, incorporated herein by reference.
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     8
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
     9
 Based roughly on Python difflib
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    10
*/
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    11
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    12
#include <Python.h>
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    13
#include <stdlib.h>
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    14
#include <string.h>
411
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    15
#ifdef _WIN32
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    16
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    17
typedef unsigned long uint32_t;
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    18
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    19
static uint32_t htonl(uint32_t x)
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    20
{
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    21
	return ((x & 0x000000ffUL) << 24) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    22
		((x & 0x0000ff00UL) <<  8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    23
		((x & 0x00ff0000UL) >>  8) |
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    24
		((x & 0xff000000UL) >> 24);
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    25
}
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    26
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    27
#else
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    28
  #include <netinet/in.h>
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    29
  #include <sys/types.h>
9e9f7ab43ce2 Add 'other OS' bits to bdiff.c / style cleanups
mpm@selenic.com
parents: 400
diff changeset
    30
#endif
400
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    31
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    32
struct line {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    33
	int h, len, n;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    34
	const char *l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    35
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    36
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    37
struct hunk {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    38
	int a1, a2, b1, b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    39
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    40
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    41
struct hunklist {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    42
	struct hunk *base, *head;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    43
};
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
static inline uint32_t rol32(uint32_t word, unsigned int shift)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    46
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    47
        return (word << shift) | (word >> (32 - shift));
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    50
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
    51
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    52
	int h, i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    53
	const char *p, *b = a;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    54
	struct line *l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    55
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    56
	/* count the lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    57
	i = 1; /* extra line for sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    58
	for (p = a; p < a + len; p++)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    59
		if (*p == '\n' || p == a + len - 1)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    60
			i++;
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
	*lr = l = malloc(sizeof(struct line) * i);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    63
	if (!l)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    64
		return -1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    65
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    66
	/* build the line array and calculate hashes */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    67
	h = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    68
	for (p = a; p < a + len; p++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    69
		h = *p + rol32(h, 7); /* a simple hash from GNU diff */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    70
		if (*p == '\n' || p == a + len - 1) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    71
			l->len = p - b + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    72
			l->h = h;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    73
			l->l = b;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    74
			l->n = -1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    75
			l++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    76
			b = p + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    77
			h = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    78
		}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    79
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    80
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    81
	/* set up a sentinel */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    82
	l->h = l->len = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    83
	l->l = a + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    84
	return i - 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    85
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    86
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    87
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
    88
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    89
	return a->len != b->len || memcmp(a->l, b->l, a->len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    90
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    91
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    92
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
    93
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    94
	int i, j, buckets = 1, t, *h, *l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    95
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    96
	/* build a hash table of the next highest power of 2 */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    97
	while (buckets < bn + 1)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    98
		buckets *= 2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
    99
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   100
	h = malloc(buckets * sizeof(int));
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   101
	l = calloc(buckets, sizeof(int));
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   102
	buckets = buckets - 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   103
	if (!h || !l) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   104
		free(h);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   105
		return 0;
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
	/* clear the hash table */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   109
	for (i = 0; i <= buckets; i++)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   110
		h[i] = -1;
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
	/* add lines to the hash table chains */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   113
	for (i = bn - 1; i >= 0; i--) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   114
		/* find the equivalence class */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   115
		for (j = b[i].h & buckets; h[j] != -1; j = (j + 1) & buckets)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   116
			if (!cmp(b + i, b + h[j]))
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   117
				break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   118
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   119
		/* add to the head of the equivalence class */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   120
		b[i].n = h[j];
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   121
		b[i].h = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   122
		h[j] = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   123
		l[j]++; /* keep track of popularity */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   124
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   125
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   126
	/* compute popularity threshold */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   127
	t = (bn >= 200) ? bn / 100 : bn + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   128
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   129
	/* match items in a to their equivalence class in b */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   130
	for (i = 0; i < an; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   131
		/* find the equivalence class */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   132
		for (j = a[i].h & buckets; h[j] != -1; j = (j + 1) & buckets)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   133
			if (!cmp(a + i, b + h[j]))
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   134
				break;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   135
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   136
		a[i].h = j; /* use equivalence class for quick compare */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   137
		if(l[j] <= t)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   138
			a[i].n = h[j]; /* point to head of match list */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   139
		else
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   140
			a[i].n = -1; /* too popular */
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   143
	/* discard hash tables */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   144
	free(h);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   145
	free(l);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   146
	return 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   147
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   148
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   149
static int longest_match(struct line *a, struct line *b, int *jpos, int *jlen,
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   150
			 int a1, int a2, int b1, int b2, int *omi, int *omj)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   151
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   152
	int mi = a1, mj = b1, mk = 0, mb = 0, i, j, k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   153
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   154
	for (i = a1; i < a2; i++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   155
		/* skip things before the current block */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   156
		for (j = a[i].n; j != -1 && j < b1; j = b[j].n)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   157
			;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   158
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   159
		/* loop through all lines match a[i] in b */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   160
		for (; j != -1 && j < b2; j = b[j].n) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   161
			/* does this extend an earlier match? */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   162
			if (i > a1 && j > b1 && jpos[j - 1] == i)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   163
				k = jlen[j - 1] + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   164
			else
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   165
				k = 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   166
			jpos[j] = i + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   167
			jlen[j] = k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   168
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   169
			/* best match so far? */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   170
			if (k > mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   171
				mi = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   172
				mj = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   173
				mk = k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   174
			}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   175
		}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   176
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   177
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   178
	if (mk) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   179
		mi = mi - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   180
		mj = mj - mk + 1;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   181
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   182
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   183
	/* expand match to include neighboring popular lines */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   184
	while (mi - mb > a1 && mj - mb > b1 &&
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   185
	       a[mi - mb - 1].h == b[mj - mb - 1].h)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   186
		mb++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   187
	while (mi + mk < a2 && mj + mk < b2 &&
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   188
	       a[mi + mk].h == b[mj + mk].h)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   189
		mk++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   190
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   191
	*omi = mi - mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   192
	*omj = mj - mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   193
	return mk + mb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   194
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   195
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   196
static void recurse(struct line *a, struct line *b, int *jpos, int *jlen,
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   197
		    int a1, int a2, int b1, int b2, struct hunklist *l)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   198
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   199
	int i, j, k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   200
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   201
	/* find the longest match in this chunk */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   202
	k = longest_match(a, b, jpos, jlen, a1, a2, b1, b2, &i, &j);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   203
	if (!k)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   204
		return;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   205
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   206
	/* and recurse on the remaining chunks on either side */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   207
	recurse(a, b, jpos, jlen, a1, i, b1, j, l);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   208
	l->head->a1 = i;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   209
	l->head->a2 = i + k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   210
	l->head->b1 = j;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   211
	l->head->b2 = j + k;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   212
	l->head++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   213
	recurse(a, b, jpos, jlen, i + k, a2, j + k, b2, l);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   214
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   215
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   216
static PyObject *bdiff(PyObject *self, PyObject *args)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   217
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   218
	PyObject *sa, *sb, *result = NULL;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   219
	struct hunklist l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   220
	struct hunk *h;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   221
	struct line *al, *bl;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   222
	char encode[12], *rb;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   223
	int an, bn, len = 0, t, la = 0, lb = 0, *jpos, *jlen;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   224
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   225
	if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb))
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   226
		return NULL;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   227
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   228
	/* allocate and fill arrays */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   229
	an = splitlines(PyString_AsString(sa), PyString_Size(sa), &al);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   230
	bn = splitlines(PyString_AsString(sb), PyString_Size(sb), &bl);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   231
	t = equatelines(al, an, bl, bn);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   232
	jpos = calloc(bn, sizeof(int));
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   233
	jlen = calloc(bn, sizeof(int));
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   234
	l.head = l.base = malloc(sizeof(struct hunk) * ((an + bn) / 4 + 2));
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   235
	if (!al || !bl || !jpos || !jlen || !l.base || !t)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   236
		goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   237
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   238
	/* generate the matching block list */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   239
	recurse(al, bl, jpos, jlen, 0, an, 0, bn, &l);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   240
	l.head->a1 = an;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   241
	l.head->b1 = bn;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   242
	l.head++;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   243
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   244
	/* calculate length of output */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   245
	for(h = l.base; h != l.head; h++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   246
		if (h->a1 != la || h->b1 != lb)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   247
			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
   248
		la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   249
		lb = h->b2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   250
	}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   251
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   252
	result = PyString_FromStringAndSize(NULL, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   253
	if (!result)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   254
		goto nomem;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   255
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   256
	/* build binary patch */
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   257
	rb = PyString_AsString(result);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   258
	la = lb = 0;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   259
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   260
	for(h = l.base; h != l.head; h++) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   261
		if (h->a1 != la || h->b1 != lb) {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   262
			len = bl[h->b1].l - bl[lb].l;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   263
			*(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
   264
			*(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
   265
			*(uint32_t *)(encode + 8) = htonl(len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   266
			memcpy(rb, encode, 12);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   267
			memcpy(rb + 12, bl[lb].l, len);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   268
			rb += 12 + len;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   269
		}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   270
		la = h->a2;
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   271
		lb = h->b2;
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
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   274
nomem:
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   275
	free(al);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   276
	free(bl);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   277
	free(jpos);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   278
	free(jlen);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   279
	free(l.base);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   280
	return result ? result : PyErr_NoMemory();
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   281
}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   282
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   283
static char mdiff_doc[] = "Efficient binary diff.";
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   284
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   285
static PyMethodDef methods[] = {
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   286
	{"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"},
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   287
	{NULL, NULL}
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   288
};
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   289
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   290
PyMODINIT_FUNC initbdiff(void)
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   291
{
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   292
	Py_InitModule3("bdiff", methods, mdiff_doc);
8b067bde6679 Add a fast binary diff extension (not yet used)
mpm@selenic.com
parents:
diff changeset
   293
}