2005-05-20 21:00:23 +00:00
|
|
|
/*
|
|
|
|
* Deltafication of a GIT database.
|
|
|
|
*
|
|
|
|
* (C) 2005 Nicolas Pitre <nico@cam.org>
|
|
|
|
*
|
|
|
|
* This code is free software; you can redistribute it and/or modify
|
|
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
|
|
* published by the Free Software Foundation.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "cache.h"
|
|
|
|
#include "delta.h"
|
|
|
|
|
|
|
|
static int replace_object(char *buf, unsigned long size, unsigned char *sha1)
|
|
|
|
{
|
|
|
|
char tmpfile[PATH_MAX];
|
|
|
|
int fd;
|
|
|
|
|
|
|
|
snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", get_object_directory());
|
|
|
|
fd = mkstemp(tmpfile);
|
|
|
|
if (fd < 0)
|
|
|
|
return error("%s: %s\n", tmpfile, strerror(errno));
|
|
|
|
if (write(fd, buf, size) != size) {
|
|
|
|
perror("unable to write file");
|
|
|
|
close(fd);
|
|
|
|
unlink(tmpfile);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
fchmod(fd, 0444);
|
|
|
|
close(fd);
|
|
|
|
if (rename(tmpfile, sha1_file_name(sha1))) {
|
|
|
|
perror("unable to replace original object");
|
|
|
|
unlink(tmpfile);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-06-21 20:04:33 +00:00
|
|
|
static void *create_object(unsigned char *buf, unsigned long len,
|
|
|
|
char *hdr, int hdrlen, unsigned long *retsize)
|
2005-05-20 21:00:23 +00:00
|
|
|
{
|
2005-06-21 20:04:33 +00:00
|
|
|
unsigned char *compressed;
|
2005-05-20 21:00:23 +00:00
|
|
|
unsigned long size;
|
|
|
|
z_stream stream;
|
|
|
|
|
|
|
|
/* Set it up */
|
|
|
|
memset(&stream, 0, sizeof(stream));
|
|
|
|
deflateInit(&stream, Z_BEST_COMPRESSION);
|
|
|
|
size = deflateBound(&stream, len+hdrlen);
|
|
|
|
compressed = xmalloc(size);
|
|
|
|
|
|
|
|
/* Compress it */
|
|
|
|
stream.next_out = compressed;
|
|
|
|
stream.avail_out = size;
|
|
|
|
|
|
|
|
/* First header.. */
|
2005-06-21 20:04:33 +00:00
|
|
|
stream.next_in = (unsigned char *)hdr;
|
2005-05-20 21:00:23 +00:00
|
|
|
stream.avail_in = hdrlen;
|
|
|
|
while (deflate(&stream, 0) == Z_OK)
|
|
|
|
/* nothing */;
|
|
|
|
|
|
|
|
/* Then the data itself.. */
|
|
|
|
stream.next_in = buf;
|
|
|
|
stream.avail_in = len;
|
|
|
|
while (deflate(&stream, Z_FINISH) == Z_OK)
|
|
|
|
/* nothing */;
|
|
|
|
deflateEnd(&stream);
|
|
|
|
*retsize = stream.total_out;
|
|
|
|
return compressed;
|
|
|
|
}
|
|
|
|
|
2005-06-21 20:04:33 +00:00
|
|
|
static int restore_original_object(unsigned char *buf, unsigned long len,
|
2005-05-20 21:00:23 +00:00
|
|
|
char *type, unsigned char *sha1)
|
|
|
|
{
|
|
|
|
char hdr[50];
|
|
|
|
int hdrlen, ret;
|
|
|
|
void *compressed;
|
|
|
|
unsigned long size;
|
|
|
|
|
|
|
|
hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
|
|
|
|
compressed = create_object(buf, len, hdr, hdrlen, &size);
|
|
|
|
ret = replace_object(compressed, size, sha1);
|
|
|
|
free(compressed);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2005-06-21 20:04:33 +00:00
|
|
|
static void *create_delta_object(unsigned char *buf, unsigned long len,
|
2005-05-20 21:00:23 +00:00
|
|
|
unsigned char *sha1_ref, unsigned long *size)
|
|
|
|
{
|
|
|
|
char hdr[50];
|
|
|
|
int hdrlen;
|
|
|
|
|
|
|
|
/* Generate the header + sha1 of reference for delta */
|
|
|
|
hdrlen = sprintf(hdr, "delta %lu", len+20)+1;
|
|
|
|
memcpy(hdr + hdrlen, sha1_ref, 20);
|
|
|
|
hdrlen += 20;
|
|
|
|
|
|
|
|
return create_object(buf, len, hdr, hdrlen, size);
|
|
|
|
}
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
static void *get_buffer(unsigned char *sha1, char *type,
|
|
|
|
unsigned long *size, unsigned long *compsize)
|
2005-05-20 21:00:23 +00:00
|
|
|
{
|
|
|
|
unsigned long mapsize;
|
|
|
|
void *map = map_sha1_file(sha1, &mapsize);
|
|
|
|
if (map) {
|
|
|
|
void *buffer = unpack_sha1_file(map, mapsize, type, size);
|
|
|
|
munmap(map, mapsize);
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (compsize)
|
|
|
|
*compsize = mapsize;
|
2005-05-20 21:00:23 +00:00
|
|
|
if (buffer)
|
|
|
|
return buffer;
|
|
|
|
}
|
|
|
|
error("unable to get object %s", sha1_to_hex(sha1));
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
static void *expand_delta(void *delta, unsigned long *size, char *type,
|
|
|
|
unsigned int *depth, unsigned char **links)
|
2005-05-20 21:00:23 +00:00
|
|
|
{
|
|
|
|
void *buf = NULL;
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
unsigned int level = (*depth)++;
|
|
|
|
if (*size < 20) {
|
2005-05-20 21:00:23 +00:00
|
|
|
error("delta object is bad");
|
|
|
|
free(delta);
|
|
|
|
} else {
|
|
|
|
unsigned long ref_size;
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
void *ref = get_buffer(delta, type, &ref_size, NULL);
|
2005-05-20 21:00:23 +00:00
|
|
|
if (ref && !strcmp(type, "delta"))
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
ref = expand_delta(ref, &ref_size, type, depth, links);
|
|
|
|
else if (ref)
|
|
|
|
{
|
|
|
|
*links = xmalloc(*depth * 20);
|
|
|
|
}
|
|
|
|
if (ref) {
|
|
|
|
buf = patch_delta(ref, ref_size, delta+20, *size-20, size);
|
|
|
|
free(ref);
|
|
|
|
if (buf)
|
|
|
|
memcpy(*links + level*20, delta, 20);
|
|
|
|
else
|
|
|
|
free(*links);
|
|
|
|
}
|
2005-05-20 21:00:23 +00:00
|
|
|
free(delta);
|
|
|
|
}
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
|
|
|
static char *mkdelta_usage =
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
"mkdelta [--max-depth=N] [--max-behind=N] <reference_sha1> <target_sha1> [<next_sha1> ...]";
|
|
|
|
|
|
|
|
struct delta {
|
|
|
|
unsigned char sha1[20]; /* object sha1 */
|
|
|
|
unsigned long size; /* object size */
|
|
|
|
void *buf; /* object content */
|
|
|
|
unsigned char *links; /* delta reference links */
|
|
|
|
unsigned int depth; /* delta depth */
|
|
|
|
};
|
|
|
|
|
2005-05-20 21:00:23 +00:00
|
|
|
int main(int argc, char **argv)
|
|
|
|
{
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
struct delta *ref, trg;
|
|
|
|
char ref_type[20], trg_type[20], *skip_reason;
|
|
|
|
void *best_buf;
|
|
|
|
unsigned long best_size, orig_size, orig_compsize;
|
|
|
|
unsigned int r, orig_ref, best_ref, nb_refs, next_ref, max_refs = 0;
|
|
|
|
unsigned int i, duplicate, skip_lvl, verbose = 0, quiet = 0;
|
|
|
|
unsigned int max_depth = -1;
|
2005-05-20 21:00:23 +00:00
|
|
|
|
|
|
|
for (i = 1; i < argc; i++) {
|
|
|
|
if (!strcmp(argv[i], "-v")) {
|
|
|
|
verbose = 1;
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
quiet = 0;
|
|
|
|
} else if (!strcmp(argv[i], "-q")) {
|
|
|
|
quiet = 1;
|
|
|
|
verbose = 0;
|
2005-05-20 21:00:23 +00:00
|
|
|
} else if (!strcmp(argv[i], "-d") && i+1 < argc) {
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
max_depth = atoi(argv[++i]);
|
2005-05-20 21:00:23 +00:00
|
|
|
} else if (!strncmp(argv[i], "--max-depth=", 12)) {
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
max_depth = atoi(argv[i]+12);
|
|
|
|
} else if (!strcmp(argv[i], "-b") && i+1 < argc) {
|
|
|
|
max_refs = atoi(argv[++i]);
|
|
|
|
} else if (!strncmp(argv[i], "--max-behind=", 13)) {
|
|
|
|
max_refs = atoi(argv[i]+13);
|
2005-05-20 21:00:23 +00:00
|
|
|
} else
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (i + (max_depth != 0) >= argc)
|
2005-05-20 21:00:23 +00:00
|
|
|
usage(mkdelta_usage);
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (!max_refs || max_refs > argc - i)
|
|
|
|
max_refs = argc - i;
|
|
|
|
ref = xmalloc(max_refs * sizeof(*ref));
|
|
|
|
for (r = 0; r < max_refs; r++)
|
|
|
|
ref[r].buf = ref[r].links = NULL;
|
|
|
|
next_ref = nb_refs = 0;
|
2005-05-20 21:00:23 +00:00
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
do {
|
|
|
|
if (get_sha1(argv[i], trg.sha1))
|
2005-05-20 21:00:23 +00:00
|
|
|
die("bad sha1 %s", argv[i]);
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
trg.buf = get_buffer(trg.sha1, trg_type, &trg.size, &orig_compsize);
|
|
|
|
if (trg.buf && !trg.size) {
|
2005-05-20 21:00:23 +00:00
|
|
|
if (verbose)
|
|
|
|
printf("skip %s (object is empty)\n", argv[i]);
|
|
|
|
continue;
|
|
|
|
}
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
orig_size = trg.size;
|
|
|
|
orig_ref = -1;
|
|
|
|
trg.depth = 0;
|
|
|
|
trg.links = NULL;
|
|
|
|
if (trg.buf && !strcmp(trg_type, "delta")) {
|
|
|
|
for (r = 0; r < nb_refs; r++)
|
|
|
|
if (!memcmp(trg.buf, ref[r].sha1, 20))
|
|
|
|
break;
|
|
|
|
if (r < nb_refs) {
|
|
|
|
/* no need to reload the reference object */
|
|
|
|
trg.depth = ref[r].depth + 1;
|
|
|
|
trg.links = xmalloc(trg.depth*20);
|
|
|
|
memcpy(trg.links, trg.buf, 20);
|
|
|
|
memcpy(trg.links+20, ref[r].links, ref[r].depth*20);
|
|
|
|
trg.buf = patch_delta(ref[r].buf, ref[r].size,
|
|
|
|
trg.buf+20, trg.size-20,
|
|
|
|
&trg.size);
|
|
|
|
strcpy(trg_type, ref_type);
|
|
|
|
orig_ref = r;
|
|
|
|
} else {
|
|
|
|
trg.buf = expand_delta(trg.buf, &trg.size, trg_type,
|
|
|
|
&trg.depth, &trg.links);
|
2005-05-20 21:00:23 +00:00
|
|
|
}
|
|
|
|
}
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (!trg.buf)
|
|
|
|
die("unable to read target object %s", argv[i]);
|
2005-05-20 21:00:23 +00:00
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (!nb_refs) {
|
|
|
|
strcpy(ref_type, trg_type);
|
|
|
|
} else if (max_depth && strcmp(ref_type, trg_type)) {
|
2005-05-20 21:00:23 +00:00
|
|
|
die("type mismatch for object %s", argv[i]);
|
|
|
|
}
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
duplicate = 0;
|
|
|
|
best_buf = NULL;
|
|
|
|
best_size = -1;
|
|
|
|
best_ref = -1;
|
|
|
|
skip_lvl = 0;
|
|
|
|
skip_reason = NULL;
|
|
|
|
for (r = 0; max_depth && r < nb_refs; r++) {
|
|
|
|
void *delta_buf, *comp_buf;
|
|
|
|
unsigned long delta_size, comp_size;
|
|
|
|
unsigned int l;
|
|
|
|
|
|
|
|
duplicate = !memcmp(trg.sha1, ref[r].sha1, 20);
|
|
|
|
if (duplicate) {
|
|
|
|
skip_reason = "already seen";
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (ref[r].depth >= max_depth) {
|
|
|
|
if (skip_lvl < 1) {
|
|
|
|
skip_reason = "exceeding max link depth";
|
|
|
|
skip_lvl = 1;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
for (l = 0; l < ref[r].depth; l++)
|
|
|
|
if (!memcmp(trg.sha1, ref[r].links + l*20, 20))
|
|
|
|
break;
|
|
|
|
if (l != ref[r].depth) {
|
|
|
|
if (skip_lvl < 2) {
|
|
|
|
skip_reason = "would create a loop";
|
|
|
|
skip_lvl = 2;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if (trg.depth < max_depth && r == orig_ref) {
|
|
|
|
if (skip_lvl < 3) {
|
|
|
|
skip_reason = "delta already in place";
|
|
|
|
skip_lvl = 3;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
delta_buf = diff_delta(ref[r].buf, ref[r].size,
|
|
|
|
trg.buf, trg.size, &delta_size);
|
|
|
|
if (!delta_buf)
|
|
|
|
die("out of memory");
|
|
|
|
if (trg.depth < max_depth &&
|
|
|
|
delta_size+20 >= orig_size) {
|
|
|
|
/* no need to even try to compress if original
|
|
|
|
object is smaller than this delta */
|
|
|
|
free(delta_buf);
|
|
|
|
if (skip_lvl < 4) {
|
|
|
|
skip_reason = "no size reduction";
|
|
|
|
skip_lvl = 4;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
comp_buf = create_delta_object(delta_buf, delta_size,
|
|
|
|
ref[r].sha1, &comp_size);
|
|
|
|
if (!comp_buf)
|
|
|
|
die("out of memory");
|
|
|
|
free(delta_buf);
|
|
|
|
if (trg.depth < max_depth &&
|
|
|
|
comp_size >= orig_compsize) {
|
|
|
|
free(comp_buf);
|
|
|
|
if (skip_lvl < 5) {
|
|
|
|
skip_reason = "no size reduction";
|
|
|
|
skip_lvl = 5;
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
if ((comp_size < best_size) ||
|
|
|
|
(comp_size == best_size &&
|
|
|
|
ref[r].depth < ref[best_ref].depth)) {
|
|
|
|
free(best_buf);
|
|
|
|
best_buf = comp_buf;
|
|
|
|
best_size = comp_size;
|
|
|
|
best_ref = r;
|
|
|
|
}
|
2005-05-20 21:00:23 +00:00
|
|
|
}
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (best_buf) {
|
|
|
|
if (replace_object(best_buf, best_size, trg.sha1))
|
2005-05-20 21:00:23 +00:00
|
|
|
die("unable to write delta for %s", argv[i]);
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
free(best_buf);
|
|
|
|
free(trg.links);
|
|
|
|
trg.depth = ref[best_ref].depth + 1;
|
|
|
|
trg.links = xmalloc(trg.depth*20);
|
|
|
|
memcpy(trg.links, ref[best_ref].sha1, 20);
|
|
|
|
memcpy(trg.links+20, ref[best_ref].links, ref[best_ref].depth*20);
|
|
|
|
if (!quiet)
|
|
|
|
printf("delta %s (size=%ld.%02ld%% depth=%d dist=%d)\n",
|
|
|
|
argv[i], best_size*100 / orig_compsize,
|
|
|
|
(best_size*10000 / orig_compsize)%100,
|
|
|
|
trg.depth,
|
|
|
|
(next_ref - best_ref + max_refs)
|
|
|
|
% (max_refs + 1) + 1);
|
|
|
|
} else if (trg.depth > max_depth) {
|
|
|
|
if (restore_original_object(trg.buf, trg.size, trg_type, trg.sha1))
|
|
|
|
die("unable to restore %s", argv[i]);
|
|
|
|
if (!quiet)
|
|
|
|
printf("undelta %s (depth was %d)\n",
|
|
|
|
argv[i], trg.depth);
|
|
|
|
trg.depth = 0;
|
|
|
|
free(trg.links);
|
|
|
|
trg.links = NULL;
|
|
|
|
} else if (skip_reason && verbose) {
|
|
|
|
printf("skip %s (%s)\n", argv[i], skip_reason);
|
2005-05-20 21:00:23 +00:00
|
|
|
}
|
|
|
|
|
[PATCH] mkdelta enhancements (take 2)
Although it was described as such, git-mkdelta didn't really attempt to
find the best delta against any previous object in the list, but was
only able to create a delta against the preceeding object. This patch
reworks the code to fix that limitation and hopefully makes it a bit
clearer than before, including fixing the delta loop detection which was
broken.
This means that
git-mkdelta sha1 sha2 sha3 sha4 sha5 sha6
will now create a sha2 delta against sha1, a sha3 delta against either
sha2 or sha1 and keep the best one, a sha4 delta against either sha3,
sha2 or sha1, etc. The --max-behind argument limits that search for the
best delta to the specified number of previous objects in the list. If
no limit is specified it is unlimited (note: it might run out of
memory with long object lists).
Also added a -q (quiet) switch so it is possible to have 3 levels of
output: -q for nothing, -v for verbose, and if none of -q nor -v is
specified then only actual changes on the object database are shown.
Finally the git-deltafy-script has been updated accordingly, and some
bugs fixed (thanks to Stephen C. Tweedie for spotting them).
This version has been toroughly tested and I think it is ready
for public consumption.
Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-30 01:52:19 +00:00
|
|
|
if (!duplicate) {
|
|
|
|
free(ref[next_ref].buf);
|
|
|
|
free(ref[next_ref].links);
|
|
|
|
ref[next_ref] = trg;
|
|
|
|
if (++next_ref > nb_refs)
|
|
|
|
nb_refs = next_ref;
|
|
|
|
if (next_ref == max_refs)
|
|
|
|
next_ref = 0;
|
|
|
|
} else {
|
|
|
|
free(trg.buf);
|
|
|
|
free(trg.links);
|
|
|
|
}
|
|
|
|
} while (++i < argc);
|
2005-05-20 21:00:23 +00:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|