2006-01-07 10:33:54 +01:00
|
|
|
#include "cache.h"
|
2005-05-19 01:14:22 +02:00
|
|
|
#include "tag.h"
|
2005-04-18 20:39:48 +02:00
|
|
|
#include "commit.h"
|
2006-10-30 20:09:06 +01:00
|
|
|
#include "pkt-line.h"
|
2006-12-25 20:48:35 +01:00
|
|
|
#include "utf8.h"
|
2007-02-23 01:35:03 +01:00
|
|
|
#include "interpolate.h"
|
2007-04-09 11:34:05 +02:00
|
|
|
#include "diff.h"
|
|
|
|
#include "revision.h"
|
2005-04-18 20:39:48 +02:00
|
|
|
|
[PATCH] Avoid wasting memory in git-rev-list
As pointed out on the list, git-rev-list can use a lot of memory.
One low-hanging fruit is to free the commit buffer for commits that we
parse. By default, parse_commit() will save away the buffer, since a lot
of cases do want it, and re-reading it continually would be unnecessary.
However, in many cases the buffer isn't actually necessary and saving it
just wastes memory.
We could just free the buffer ourselves, but especially in git-rev-list,
we actually end up using the helper functions that automatically add
parent commits to the commit lists, so we don't actually control the
commit parsing directly.
Instead, just make this behaviour of "parse_commit()" a global flag.
Maybe this is a bit tasteless, but it's very simple, and it makes a
noticable difference in memory usage.
Before the change:
[torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null
0.26user 0.02system 0:00.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+3714minor)pagefaults 0swaps
after the change:
[torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null
0.26user 0.00system 0:00.27elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+2433minor)pagefaults 0swaps
note how the minor faults have decreased from 3714 pages to 2433 pages.
That's all due to the fewer anonymous pages allocated to hold the comment
buffers and their metadata.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-09-15 23:43:17 +02:00
|
|
|
int save_commit_buffer = 1;
|
|
|
|
|
2005-07-06 18:39:34 +02:00
|
|
|
struct sort_node
|
|
|
|
{
|
|
|
|
/*
|
2006-08-17 20:44:16 +02:00
|
|
|
* the number of children of the associated commit
|
|
|
|
* that also occur in the list being sorted.
|
|
|
|
*/
|
2005-07-06 18:39:34 +02:00
|
|
|
unsigned int indegree;
|
|
|
|
|
|
|
|
/*
|
2006-08-17 20:44:16 +02:00
|
|
|
* reference to original list item that we will re-use
|
|
|
|
* on output.
|
|
|
|
*/
|
2005-07-06 18:39:34 +02:00
|
|
|
struct commit_list * list_item;
|
|
|
|
|
|
|
|
};
|
|
|
|
|
2005-04-18 20:39:48 +02:00
|
|
|
const char *commit_type = "commit";
|
|
|
|
|
2007-06-13 10:42:05 +02:00
|
|
|
static struct cmt_fmt_map {
|
2006-05-15 02:20:46 +02:00
|
|
|
const char *n;
|
|
|
|
size_t cmp_len;
|
|
|
|
enum cmit_fmt v;
|
|
|
|
} cmt_fmts[] = {
|
|
|
|
{ "raw", 1, CMIT_FMT_RAW },
|
|
|
|
{ "medium", 1, CMIT_FMT_MEDIUM },
|
|
|
|
{ "short", 1, CMIT_FMT_SHORT },
|
2006-05-21 10:34:54 +02:00
|
|
|
{ "email", 1, CMIT_FMT_EMAIL },
|
2006-05-15 02:20:46 +02:00
|
|
|
{ "full", 5, CMIT_FMT_FULL },
|
|
|
|
{ "fuller", 5, CMIT_FMT_FULLER },
|
|
|
|
{ "oneline", 1, CMIT_FMT_ONELINE },
|
2007-02-23 01:35:03 +01:00
|
|
|
{ "format:", 7, CMIT_FMT_USERFORMAT},
|
2006-05-15 02:20:46 +02:00
|
|
|
};
|
|
|
|
|
2007-02-23 01:35:03 +01:00
|
|
|
static char *user_format;
|
|
|
|
|
2005-06-27 02:50:46 +02:00
|
|
|
enum cmit_fmt get_commit_format(const char *arg)
|
|
|
|
{
|
2006-05-15 02:20:46 +02:00
|
|
|
int i;
|
|
|
|
|
|
|
|
if (!arg || !*arg)
|
2005-06-27 02:50:46 +02:00
|
|
|
return CMIT_FMT_DEFAULT;
|
2006-05-15 02:20:46 +02:00
|
|
|
if (*arg == '=')
|
|
|
|
arg++;
|
2007-02-23 01:35:03 +01:00
|
|
|
if (!prefixcmp(arg, "format:")) {
|
|
|
|
if (user_format)
|
|
|
|
free(user_format);
|
|
|
|
user_format = xstrdup(arg + 7);
|
|
|
|
return CMIT_FMT_USERFORMAT;
|
|
|
|
}
|
2006-05-15 02:20:46 +02:00
|
|
|
for (i = 0; i < ARRAY_SIZE(cmt_fmts); i++) {
|
2007-02-02 14:10:25 +01:00
|
|
|
if (!strncmp(arg, cmt_fmts[i].n, cmt_fmts[i].cmp_len) &&
|
|
|
|
!strncmp(arg, cmt_fmts[i].n, strlen(arg)))
|
2006-05-15 02:20:46 +02:00
|
|
|
return cmt_fmts[i].v;
|
|
|
|
}
|
|
|
|
|
|
|
|
die("invalid --pretty format: %s", arg);
|
2005-06-27 02:50:46 +02:00
|
|
|
}
|
|
|
|
|
2005-08-21 11:51:10 +02:00
|
|
|
static struct commit *check_commit(struct object *obj,
|
|
|
|
const unsigned char *sha1,
|
|
|
|
int quiet)
|
2005-05-19 01:14:22 +02:00
|
|
|
{
|
2006-07-12 05:45:31 +02:00
|
|
|
if (obj->type != OBJ_COMMIT) {
|
2005-08-21 11:51:10 +02:00
|
|
|
if (!quiet)
|
|
|
|
error("Object %s is a %s, not a commit",
|
Shrink "struct object" a bit
This shrinks "struct object" by a small amount, by getting rid of the
"struct type *" pointer and replacing it with a 3-bit bitfield instead.
In addition, we merge the bitfields and the "flags" field, which
incidentally should also remove a useless 4-byte padding from the object
when in 64-bit mode.
Now, our "struct object" is still too damn large, but it's now less
obviously bloated, and of the remaining fields, only the "util" (which is
not used by most things) is clearly something that should be eventually
discarded.
This shrinks the "git-rev-list --all" memory use by about 2.5% on the
kernel archive (and, perhaps more importantly, on the larger mozilla
archive). That may not sound like much, but I suspect it's more on a
64-bit platform.
There are other remaining inefficiencies (the parent lists, for example,
probably have horrible malloc overhead), but this was pretty obvious.
Most of the patch is just changing the comparison of the "type" pointer
from one of the constant string pointers to the appropriate new TYPE_xxx
small integer constant.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-15 01:45:13 +02:00
|
|
|
sha1_to_hex(sha1), typename(obj->type));
|
2005-05-19 01:14:22 +02:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
return (struct commit *) obj;
|
|
|
|
}
|
|
|
|
|
2005-08-21 11:51:10 +02:00
|
|
|
struct commit *lookup_commit_reference_gently(const unsigned char *sha1,
|
|
|
|
int quiet)
|
2005-05-19 01:14:22 +02:00
|
|
|
{
|
2005-11-03 00:19:13 +01:00
|
|
|
struct object *obj = deref_tag(parse_object(sha1), NULL, 0);
|
2005-05-19 01:14:22 +02:00
|
|
|
|
|
|
|
if (!obj)
|
|
|
|
return NULL;
|
2005-08-21 11:51:10 +02:00
|
|
|
return check_commit(obj, sha1, quiet);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct commit *lookup_commit_reference(const unsigned char *sha1)
|
|
|
|
{
|
|
|
|
return lookup_commit_reference_gently(sha1, 0);
|
2005-05-19 01:14:22 +02:00
|
|
|
}
|
|
|
|
|
2005-06-03 17:05:39 +02:00
|
|
|
struct commit *lookup_commit(const unsigned char *sha1)
|
2005-04-18 20:39:48 +02:00
|
|
|
{
|
|
|
|
struct object *obj = lookup_object(sha1);
|
2007-04-17 07:11:43 +02:00
|
|
|
if (!obj)
|
|
|
|
return create_object(sha1, OBJ_COMMIT, alloc_commit_node());
|
2005-05-20 22:59:17 +02:00
|
|
|
if (!obj->type)
|
2006-07-12 05:45:31 +02:00
|
|
|
obj->type = OBJ_COMMIT;
|
2005-08-21 11:51:10 +02:00
|
|
|
return check_commit(obj, sha1, 0);
|
2005-04-18 20:39:48 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned long parse_commit_date(const char *buf)
|
|
|
|
{
|
|
|
|
unsigned long date;
|
|
|
|
|
|
|
|
if (memcmp(buf, "author", 6))
|
|
|
|
return 0;
|
|
|
|
while (*buf++ != '\n')
|
|
|
|
/* nada */;
|
|
|
|
if (memcmp(buf, "committer", 9))
|
|
|
|
return 0;
|
|
|
|
while (*buf++ != '>')
|
|
|
|
/* nada */;
|
|
|
|
date = strtoul(buf, NULL, 10);
|
|
|
|
if (date == ULONG_MAX)
|
|
|
|
date = 0;
|
|
|
|
return date;
|
|
|
|
}
|
|
|
|
|
2006-04-07 08:58:51 +02:00
|
|
|
static struct commit_graft **commit_graft;
|
2005-07-30 09:58:28 +02:00
|
|
|
static int commit_graft_alloc, commit_graft_nr;
|
|
|
|
|
|
|
|
static int commit_graft_pos(const unsigned char *sha1)
|
|
|
|
{
|
|
|
|
int lo, hi;
|
|
|
|
lo = 0;
|
|
|
|
hi = commit_graft_nr;
|
|
|
|
while (lo < hi) {
|
|
|
|
int mi = (lo + hi) / 2;
|
|
|
|
struct commit_graft *graft = commit_graft[mi];
|
2006-08-17 20:54:57 +02:00
|
|
|
int cmp = hashcmp(sha1, graft->sha1);
|
2005-07-30 09:58:28 +02:00
|
|
|
if (!cmp)
|
|
|
|
return mi;
|
|
|
|
if (cmp < 0)
|
|
|
|
hi = mi;
|
|
|
|
else
|
|
|
|
lo = mi + 1;
|
|
|
|
}
|
|
|
|
return -lo - 1;
|
|
|
|
}
|
|
|
|
|
2006-04-07 08:58:51 +02:00
|
|
|
int register_commit_graft(struct commit_graft *graft, int ignore_dups)
|
|
|
|
{
|
|
|
|
int pos = commit_graft_pos(graft->sha1);
|
2007-06-07 09:04:01 +02:00
|
|
|
|
2006-04-07 08:58:51 +02:00
|
|
|
if (0 <= pos) {
|
|
|
|
if (ignore_dups)
|
|
|
|
free(graft);
|
|
|
|
else {
|
|
|
|
free(commit_graft[pos]);
|
|
|
|
commit_graft[pos] = graft;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
pos = -pos - 1;
|
|
|
|
if (commit_graft_alloc <= ++commit_graft_nr) {
|
|
|
|
commit_graft_alloc = alloc_nr(commit_graft_alloc);
|
|
|
|
commit_graft = xrealloc(commit_graft,
|
|
|
|
sizeof(*commit_graft) *
|
|
|
|
commit_graft_alloc);
|
|
|
|
}
|
|
|
|
if (pos < commit_graft_nr)
|
|
|
|
memmove(commit_graft + pos + 1,
|
|
|
|
commit_graft + pos,
|
|
|
|
(commit_graft_nr - pos - 1) *
|
|
|
|
sizeof(*commit_graft));
|
|
|
|
commit_graft[pos] = graft;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct commit_graft *read_graft_line(char *buf, int len)
|
|
|
|
{
|
|
|
|
/* The format is just "Commit Parent1 Parent2 ...\n" */
|
|
|
|
int i;
|
|
|
|
struct commit_graft *graft = NULL;
|
|
|
|
|
|
|
|
if (buf[len-1] == '\n')
|
|
|
|
buf[--len] = 0;
|
2006-04-17 13:41:49 +02:00
|
|
|
if (buf[0] == '#' || buf[0] == '\0')
|
2006-04-16 23:24:56 +02:00
|
|
|
return NULL;
|
2006-04-07 08:58:51 +02:00
|
|
|
if ((len + 1) % 41) {
|
|
|
|
bad_graft_data:
|
|
|
|
error("bad graft data: %s", buf);
|
|
|
|
free(graft);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
i = (len + 1) / 41 - 1;
|
|
|
|
graft = xmalloc(sizeof(*graft) + 20 * i);
|
|
|
|
graft->nr_parent = i;
|
|
|
|
if (get_sha1_hex(buf, graft->sha1))
|
|
|
|
goto bad_graft_data;
|
|
|
|
for (i = 40; i < len; i += 41) {
|
|
|
|
if (buf[i] != ' ')
|
|
|
|
goto bad_graft_data;
|
|
|
|
if (get_sha1_hex(buf + i + 1, graft->parent[i/41]))
|
|
|
|
goto bad_graft_data;
|
|
|
|
}
|
|
|
|
return graft;
|
|
|
|
}
|
|
|
|
|
|
|
|
int read_graft_file(const char *graft_file)
|
2005-07-30 09:58:28 +02:00
|
|
|
{
|
|
|
|
FILE *fp = fopen(graft_file, "r");
|
|
|
|
char buf[1024];
|
2006-04-07 08:58:51 +02:00
|
|
|
if (!fp)
|
|
|
|
return -1;
|
2005-07-30 09:58:28 +02:00
|
|
|
while (fgets(buf, sizeof(buf), fp)) {
|
|
|
|
/* The format is just "Commit Parent1 Parent2 ...\n" */
|
|
|
|
int len = strlen(buf);
|
2006-04-07 08:58:51 +02:00
|
|
|
struct commit_graft *graft = read_graft_line(buf, len);
|
2006-04-16 23:24:56 +02:00
|
|
|
if (!graft)
|
|
|
|
continue;
|
2006-04-07 08:58:51 +02:00
|
|
|
if (register_commit_graft(graft, 1))
|
2005-07-30 09:58:28 +02:00
|
|
|
error("duplicate graft data: %s", buf);
|
|
|
|
}
|
|
|
|
fclose(fp);
|
2006-04-07 08:58:51 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void prepare_commit_graft(void)
|
|
|
|
{
|
|
|
|
static int commit_graft_prepared;
|
|
|
|
char *graft_file;
|
|
|
|
|
|
|
|
if (commit_graft_prepared)
|
|
|
|
return;
|
|
|
|
graft_file = get_graft_file();
|
|
|
|
read_graft_file(graft_file);
|
2006-10-30 20:09:06 +01:00
|
|
|
/* make sure shallows are read */
|
|
|
|
is_repository_shallow();
|
2006-04-07 08:58:51 +02:00
|
|
|
commit_graft_prepared = 1;
|
2005-07-30 09:58:28 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct commit_graft *lookup_commit_graft(const unsigned char *sha1)
|
|
|
|
{
|
|
|
|
int pos;
|
2006-04-07 08:58:51 +02:00
|
|
|
prepare_commit_graft();
|
2005-07-30 09:58:28 +02:00
|
|
|
pos = commit_graft_pos(sha1);
|
|
|
|
if (pos < 0)
|
|
|
|
return NULL;
|
|
|
|
return commit_graft[pos];
|
|
|
|
}
|
|
|
|
|
2006-10-30 20:09:06 +01:00
|
|
|
int write_shallow_commits(int fd, int use_pack_protocol)
|
|
|
|
{
|
|
|
|
int i, count = 0;
|
|
|
|
for (i = 0; i < commit_graft_nr; i++)
|
|
|
|
if (commit_graft[i]->nr_parent < 0) {
|
|
|
|
const char *hex =
|
|
|
|
sha1_to_hex(commit_graft[i]->sha1);
|
|
|
|
count++;
|
|
|
|
if (use_pack_protocol)
|
|
|
|
packet_write(fd, "shallow %s", hex);
|
|
|
|
else {
|
2007-01-08 16:58:23 +01:00
|
|
|
if (write_in_full(fd, hex, 40) != 40)
|
|
|
|
break;
|
|
|
|
if (write_in_full(fd, "\n", 1) != 1)
|
|
|
|
break;
|
2006-10-30 20:09:06 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-10-30 20:09:53 +01:00
|
|
|
int unregister_shallow(const unsigned char *sha1)
|
|
|
|
{
|
|
|
|
int pos = commit_graft_pos(sha1);
|
|
|
|
if (pos < 0)
|
|
|
|
return -1;
|
|
|
|
if (pos + 1 < commit_graft_nr)
|
|
|
|
memcpy(commit_graft + pos, commit_graft + pos + 1,
|
|
|
|
sizeof(struct commit_graft *)
|
|
|
|
* (commit_graft_nr - pos - 1));
|
|
|
|
commit_graft_nr--;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-05-06 19:48:34 +02:00
|
|
|
int parse_commit_buffer(struct commit *item, void *buffer, unsigned long size)
|
2005-04-18 20:39:48 +02:00
|
|
|
{
|
2006-06-28 12:51:00 +02:00
|
|
|
char *tail = buffer;
|
2005-07-28 00:12:48 +02:00
|
|
|
char *bufptr = buffer;
|
2005-04-18 20:39:48 +02:00
|
|
|
unsigned char parent[20];
|
2005-06-21 05:26:03 +02:00
|
|
|
struct commit_list **pptr;
|
2005-07-30 09:58:28 +02:00
|
|
|
struct commit_graft *graft;
|
2005-11-17 06:32:44 +01:00
|
|
|
unsigned n_refs = 0;
|
2005-05-06 19:48:34 +02:00
|
|
|
|
2005-04-18 20:39:48 +02:00
|
|
|
if (item->object.parsed)
|
|
|
|
return 0;
|
|
|
|
item->object.parsed = 1;
|
2006-06-28 12:51:00 +02:00
|
|
|
tail += size;
|
|
|
|
if (tail <= bufptr + 5 || memcmp(bufptr, "tree ", 5))
|
2005-07-28 00:12:48 +02:00
|
|
|
return error("bogus commit object %s", sha1_to_hex(item->object.sha1));
|
2006-06-28 12:51:00 +02:00
|
|
|
if (tail <= bufptr + 45 || get_sha1_hex(bufptr + 5, parent) < 0)
|
2006-02-23 02:47:10 +01:00
|
|
|
return error("bad tree pointer in commit %s",
|
|
|
|
sha1_to_hex(item->object.sha1));
|
2005-04-18 20:39:48 +02:00
|
|
|
item->tree = lookup_tree(parent);
|
2005-04-24 23:31:57 +02:00
|
|
|
if (item->tree)
|
2005-11-17 06:32:44 +01:00
|
|
|
n_refs++;
|
2005-04-18 20:39:48 +02:00
|
|
|
bufptr += 46; /* "tree " + "hex sha1" + "\n" */
|
2005-06-21 05:26:03 +02:00
|
|
|
pptr = &item->parents;
|
2005-07-30 09:58:28 +02:00
|
|
|
|
|
|
|
graft = lookup_commit_graft(item->object.sha1);
|
2006-06-28 12:51:00 +02:00
|
|
|
while (bufptr + 48 < tail && !memcmp(bufptr, "parent ", 7)) {
|
2005-07-28 00:12:48 +02:00
|
|
|
struct commit *new_parent;
|
|
|
|
|
2006-06-28 12:51:00 +02:00
|
|
|
if (tail <= bufptr + 48 ||
|
|
|
|
get_sha1_hex(bufptr + 7, parent) ||
|
|
|
|
bufptr[47] != '\n')
|
2005-07-28 00:12:48 +02:00
|
|
|
return error("bad parents in commit %s", sha1_to_hex(item->object.sha1));
|
2005-07-30 09:58:28 +02:00
|
|
|
bufptr += 48;
|
|
|
|
if (graft)
|
|
|
|
continue;
|
2005-07-28 00:12:48 +02:00
|
|
|
new_parent = lookup_commit(parent);
|
2005-04-24 23:31:57 +02:00
|
|
|
if (new_parent) {
|
2005-06-21 05:26:03 +02:00
|
|
|
pptr = &commit_list_insert(new_parent, pptr)->next;
|
2005-11-17 06:32:44 +01:00
|
|
|
n_refs++;
|
2005-04-24 23:31:57 +02:00
|
|
|
}
|
2005-07-30 09:58:28 +02:00
|
|
|
}
|
|
|
|
if (graft) {
|
|
|
|
int i;
|
|
|
|
struct commit *new_parent;
|
|
|
|
for (i = 0; i < graft->nr_parent; i++) {
|
|
|
|
new_parent = lookup_commit(graft->parent[i]);
|
|
|
|
if (!new_parent)
|
|
|
|
continue;
|
|
|
|
pptr = &commit_list_insert(new_parent, pptr)->next;
|
2005-11-17 06:32:44 +01:00
|
|
|
n_refs++;
|
2005-07-30 09:58:28 +02:00
|
|
|
}
|
2005-04-18 20:39:48 +02:00
|
|
|
}
|
|
|
|
item->date = parse_commit_date(bufptr);
|
2005-11-17 06:32:44 +01:00
|
|
|
|
|
|
|
if (track_object_refs) {
|
|
|
|
unsigned i = 0;
|
|
|
|
struct commit_list *p;
|
|
|
|
struct object_refs *refs = alloc_object_refs(n_refs);
|
|
|
|
if (item->tree)
|
|
|
|
refs->ref[i++] = &item->tree->object;
|
|
|
|
for (p = item->parents; p; p = p->next)
|
|
|
|
refs->ref[i++] = &p->item->object;
|
|
|
|
set_object_refs(&item->object, refs);
|
|
|
|
}
|
|
|
|
|
2005-04-18 20:39:48 +02:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2005-05-06 19:48:34 +02:00
|
|
|
int parse_commit(struct commit *item)
|
|
|
|
{
|
2007-02-26 20:55:59 +01:00
|
|
|
enum object_type type;
|
2005-05-06 19:48:34 +02:00
|
|
|
void *buffer;
|
|
|
|
unsigned long size;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (item->object.parsed)
|
|
|
|
return 0;
|
2007-02-26 20:55:59 +01:00
|
|
|
buffer = read_sha1_file(item->object.sha1, &type, &size);
|
2005-05-06 19:48:34 +02:00
|
|
|
if (!buffer)
|
|
|
|
return error("Could not read %s",
|
|
|
|
sha1_to_hex(item->object.sha1));
|
2007-02-26 20:55:59 +01:00
|
|
|
if (type != OBJ_COMMIT) {
|
2005-05-06 19:48:34 +02:00
|
|
|
free(buffer);
|
|
|
|
return error("Object %s not a commit",
|
|
|
|
sha1_to_hex(item->object.sha1));
|
|
|
|
}
|
|
|
|
ret = parse_commit_buffer(item, buffer, size);
|
[PATCH] Avoid wasting memory in git-rev-list
As pointed out on the list, git-rev-list can use a lot of memory.
One low-hanging fruit is to free the commit buffer for commits that we
parse. By default, parse_commit() will save away the buffer, since a lot
of cases do want it, and re-reading it continually would be unnecessary.
However, in many cases the buffer isn't actually necessary and saving it
just wastes memory.
We could just free the buffer ourselves, but especially in git-rev-list,
we actually end up using the helper functions that automatically add
parent commits to the commit lists, so we don't actually control the
commit parsing directly.
Instead, just make this behaviour of "parse_commit()" a global flag.
Maybe this is a bit tasteless, but it's very simple, and it makes a
noticable difference in memory usage.
Before the change:
[torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null
0.26user 0.02system 0:00.28elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+3714minor)pagefaults 0swaps
after the change:
[torvalds@g5 linux]$ /usr/bin/time git-rev-list v2.6.12..HEAD > /dev/null
0.26user 0.00system 0:00.27elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+0outputs (0major+2433minor)pagefaults 0swaps
note how the minor faults have decreased from 3714 pages to 2433 pages.
That's all due to the fewer anonymous pages allocated to hold the comment
buffers and their metadata.
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2005-09-15 23:43:17 +02:00
|
|
|
if (save_commit_buffer && !ret) {
|
2005-05-26 03:27:14 +02:00
|
|
|
item->buffer = buffer;
|
|
|
|
return 0;
|
|
|
|
}
|
2005-05-06 19:48:34 +02:00
|
|
|
free(buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2005-05-31 03:44:02 +02:00
|
|
|
struct commit_list *commit_list_insert(struct commit *item, struct commit_list **list_p)
|
2005-04-24 03:47:23 +02:00
|
|
|
{
|
2005-04-26 21:00:58 +02:00
|
|
|
struct commit_list *new_list = xmalloc(sizeof(struct commit_list));
|
2005-04-24 03:47:23 +02:00
|
|
|
new_list->item = item;
|
|
|
|
new_list->next = *list_p;
|
|
|
|
*list_p = new_list;
|
2005-05-31 03:44:02 +02:00
|
|
|
return new_list;
|
2005-04-24 03:47:23 +02:00
|
|
|
}
|
|
|
|
|
2005-04-18 20:39:48 +02:00
|
|
|
void free_commit_list(struct commit_list *list)
|
|
|
|
{
|
|
|
|
while (list) {
|
|
|
|
struct commit_list *temp = list;
|
|
|
|
list = temp->next;
|
|
|
|
free(temp);
|
|
|
|
}
|
|
|
|
}
|
2005-04-24 03:47:23 +02:00
|
|
|
|
2005-07-06 18:31:17 +02:00
|
|
|
struct commit_list * insert_by_date(struct commit *item, struct commit_list **list)
|
2005-04-24 03:47:23 +02:00
|
|
|
{
|
|
|
|
struct commit_list **pp = list;
|
|
|
|
struct commit_list *p;
|
|
|
|
while ((p = *pp) != NULL) {
|
|
|
|
if (p->item->date < item->date) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
pp = &p->next;
|
|
|
|
}
|
2005-07-06 18:31:17 +02:00
|
|
|
return commit_list_insert(item, pp);
|
2005-04-24 03:47:23 +02:00
|
|
|
}
|
|
|
|
|
2007-06-07 09:04:01 +02:00
|
|
|
|
2005-04-24 03:47:23 +02:00
|
|
|
void sort_by_date(struct commit_list **list)
|
|
|
|
{
|
|
|
|
struct commit_list *ret = NULL;
|
|
|
|
while (*list) {
|
2005-07-06 18:31:17 +02:00
|
|
|
insert_by_date((*list)->item, &ret);
|
2005-04-24 03:47:23 +02:00
|
|
|
*list = (*list)->next;
|
|
|
|
}
|
|
|
|
*list = ret;
|
|
|
|
}
|
|
|
|
|
2005-04-24 05:29:22 +02:00
|
|
|
struct commit *pop_most_recent_commit(struct commit_list **list,
|
|
|
|
unsigned int mark)
|
2005-04-24 03:47:23 +02:00
|
|
|
{
|
|
|
|
struct commit *ret = (*list)->item;
|
|
|
|
struct commit_list *parents = ret->parents;
|
|
|
|
struct commit_list *old = *list;
|
|
|
|
|
|
|
|
*list = (*list)->next;
|
|
|
|
free(old);
|
|
|
|
|
|
|
|
while (parents) {
|
2005-04-24 04:21:28 +02:00
|
|
|
struct commit *commit = parents->item;
|
2005-04-24 05:29:22 +02:00
|
|
|
parse_commit(commit);
|
|
|
|
if (!(commit->object.flags & mark)) {
|
|
|
|
commit->object.flags |= mark;
|
2005-07-06 18:31:17 +02:00
|
|
|
insert_by_date(commit, list);
|
2005-04-24 04:21:28 +02:00
|
|
|
}
|
2005-04-24 03:47:23 +02:00
|
|
|
parents = parents->next;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
2005-06-01 17:34:23 +02:00
|
|
|
|
2006-01-08 03:52:42 +01:00
|
|
|
void clear_commit_marks(struct commit *commit, unsigned int mark)
|
|
|
|
{
|
|
|
|
struct commit_list *parents;
|
|
|
|
|
|
|
|
commit->object.flags &= ~mark;
|
2006-07-05 02:45:22 +02:00
|
|
|
parents = commit->parents;
|
2006-01-08 03:52:42 +01:00
|
|
|
while (parents) {
|
2006-07-03 12:05:20 +02:00
|
|
|
struct commit *parent = parents->item;
|
2006-07-05 02:45:22 +02:00
|
|
|
|
|
|
|
/* Have we already cleared this? */
|
|
|
|
if (mark & parent->object.flags)
|
2006-07-03 12:05:20 +02:00
|
|
|
clear_commit_marks(parent, mark);
|
2006-01-08 03:52:42 +01:00
|
|
|
parents = parents->next;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-06-01 17:34:23 +02:00
|
|
|
/*
|
|
|
|
* Generic support for pretty-printing the header
|
|
|
|
*/
|
|
|
|
static int get_one_line(const char *msg, unsigned long len)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
while (len--) {
|
|
|
|
char c = *msg++;
|
2006-04-12 20:31:23 +02:00
|
|
|
if (!c)
|
|
|
|
break;
|
2005-06-01 17:34:23 +02:00
|
|
|
ret++;
|
|
|
|
if (c == '\n')
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2007-01-13 02:32:38 +01:00
|
|
|
/* High bit set, or ISO-2022-INT */
|
|
|
|
static int non_ascii(int ch)
|
|
|
|
{
|
|
|
|
ch = (ch & 0xff);
|
|
|
|
return ((ch & 0x80) || (ch == 0x1b));
|
|
|
|
}
|
|
|
|
|
2006-05-16 11:29:42 +02:00
|
|
|
static int is_rfc2047_special(char ch)
|
|
|
|
{
|
2007-01-13 02:32:38 +01:00
|
|
|
return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
|
2006-05-16 11:29:42 +02:00
|
|
|
}
|
|
|
|
|
2007-01-13 02:32:38 +01:00
|
|
|
static int add_rfc2047(char *buf, const char *line, int len,
|
|
|
|
const char *encoding)
|
2006-05-16 11:29:42 +02:00
|
|
|
{
|
|
|
|
char *bp = buf;
|
|
|
|
int i, needquote;
|
2007-01-13 02:32:38 +01:00
|
|
|
char q_encoding[128];
|
|
|
|
const char *q_encoding_fmt = "=?%s?q?";
|
2006-05-16 11:29:42 +02:00
|
|
|
|
|
|
|
for (i = needquote = 0; !needquote && i < len; i++) {
|
2007-01-13 02:32:38 +01:00
|
|
|
int ch = line[i];
|
|
|
|
if (non_ascii(ch))
|
2006-05-16 11:29:42 +02:00
|
|
|
needquote++;
|
|
|
|
if ((i + 1 < len) &&
|
|
|
|
(ch == '=' && line[i+1] == '?'))
|
|
|
|
needquote++;
|
|
|
|
}
|
|
|
|
if (!needquote)
|
|
|
|
return sprintf(buf, "%.*s", len, line);
|
|
|
|
|
2007-01-13 02:32:38 +01:00
|
|
|
i = snprintf(q_encoding, sizeof(q_encoding), q_encoding_fmt, encoding);
|
|
|
|
if (sizeof(q_encoding) < i)
|
|
|
|
die("Insanely long encoding name %s", encoding);
|
|
|
|
memcpy(bp, q_encoding, i);
|
|
|
|
bp += i;
|
2006-05-16 11:29:42 +02:00
|
|
|
for (i = 0; i < len; i++) {
|
2006-06-20 00:00:17 +02:00
|
|
|
unsigned ch = line[i] & 0xFF;
|
2007-06-01 23:08:12 +02:00
|
|
|
/*
|
|
|
|
* We encode ' ' using '=20' even though rfc2047
|
|
|
|
* allows using '_' for readability. Unfortunately,
|
|
|
|
* many programs do not understand this and just
|
|
|
|
* leave the underscore in place.
|
|
|
|
*/
|
|
|
|
if (is_rfc2047_special(ch) || ch == ' ') {
|
2006-05-16 11:29:42 +02:00
|
|
|
sprintf(bp, "=%02X", ch);
|
|
|
|
bp += 3;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
*bp++ = ch;
|
|
|
|
}
|
|
|
|
memcpy(bp, "?=", 2);
|
|
|
|
bp += 2;
|
|
|
|
return bp - buf;
|
|
|
|
}
|
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
static unsigned long bound_rfc2047(unsigned long len, const char *encoding)
|
|
|
|
{
|
|
|
|
/* upper bound of q encoded string of length 'len' */
|
|
|
|
unsigned long elen = strlen(encoding);
|
|
|
|
|
|
|
|
return len * 3 + elen + 100;
|
|
|
|
}
|
|
|
|
|
2006-08-28 15:52:13 +02:00
|
|
|
static int add_user_info(const char *what, enum cmit_fmt fmt, char *buf,
|
2007-04-25 08:36:22 +02:00
|
|
|
const char *line, enum date_mode dmode,
|
2007-01-13 02:32:38 +01:00
|
|
|
const char *encoding)
|
2005-06-01 17:34:23 +02:00
|
|
|
{
|
|
|
|
char *date;
|
2005-08-30 06:17:21 +02:00
|
|
|
int namelen;
|
2005-06-01 17:34:23 +02:00
|
|
|
unsigned long time;
|
2005-06-05 18:02:03 +02:00
|
|
|
int tz, ret;
|
2005-11-10 07:15:27 +01:00
|
|
|
const char *filler = " ";
|
2005-06-01 17:34:23 +02:00
|
|
|
|
2005-08-09 07:15:40 +02:00
|
|
|
if (fmt == CMIT_FMT_ONELINE)
|
|
|
|
return 0;
|
2005-06-01 17:34:23 +02:00
|
|
|
date = strchr(line, '>');
|
|
|
|
if (!date)
|
|
|
|
return 0;
|
|
|
|
namelen = ++date - line;
|
|
|
|
time = strtoul(date, &date, 10);
|
|
|
|
tz = strtol(date, NULL, 10);
|
|
|
|
|
2006-04-19 01:45:27 +02:00
|
|
|
if (fmt == CMIT_FMT_EMAIL) {
|
2006-05-16 11:29:42 +02:00
|
|
|
char *name_tail = strchr(line, '<');
|
|
|
|
int display_name_length;
|
|
|
|
if (!name_tail)
|
|
|
|
return 0;
|
|
|
|
while (line < name_tail && isspace(name_tail[-1]))
|
|
|
|
name_tail--;
|
|
|
|
display_name_length = name_tail - line;
|
2006-04-19 01:45:27 +02:00
|
|
|
filler = "";
|
2006-05-16 11:29:42 +02:00
|
|
|
strcpy(buf, "From: ");
|
|
|
|
ret = strlen(buf);
|
2007-01-13 02:32:38 +01:00
|
|
|
ret += add_rfc2047(buf + ret, line, display_name_length,
|
|
|
|
encoding);
|
2006-05-16 11:29:42 +02:00
|
|
|
memcpy(buf + ret, name_tail, namelen - display_name_length);
|
|
|
|
ret += namelen - display_name_length;
|
|
|
|
buf[ret++] = '\n';
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
ret = sprintf(buf, "%s: %.*s%.*s\n", what,
|
|
|
|
(fmt == CMIT_FMT_FULLER) ? 4 : 0,
|
|
|
|
filler, namelen, line);
|
2006-04-19 01:45:27 +02:00
|
|
|
}
|
2005-11-10 07:15:27 +01:00
|
|
|
switch (fmt) {
|
|
|
|
case CMIT_FMT_MEDIUM:
|
2006-08-28 15:52:13 +02:00
|
|
|
ret += sprintf(buf + ret, "Date: %s\n",
|
2007-04-25 08:36:22 +02:00
|
|
|
show_date(time, tz, dmode));
|
2005-11-10 07:15:27 +01:00
|
|
|
break;
|
2006-04-19 01:45:27 +02:00
|
|
|
case CMIT_FMT_EMAIL:
|
2006-05-01 10:44:33 +02:00
|
|
|
ret += sprintf(buf + ret, "Date: %s\n",
|
|
|
|
show_rfc2822_date(time, tz));
|
2006-04-19 01:45:27 +02:00
|
|
|
break;
|
2005-11-10 07:15:27 +01:00
|
|
|
case CMIT_FMT_FULLER:
|
2006-08-28 15:52:13 +02:00
|
|
|
ret += sprintf(buf + ret, "%sDate: %s\n", what,
|
2007-04-25 08:36:22 +02:00
|
|
|
show_date(time, tz, dmode));
|
2005-11-10 07:15:27 +01:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
/* notin' */
|
|
|
|
break;
|
|
|
|
}
|
2005-06-05 18:02:03 +02:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2006-04-19 01:45:27 +02:00
|
|
|
static int is_empty_line(const char *line, int *len_p)
|
2005-06-05 18:02:03 +02:00
|
|
|
{
|
2006-04-19 01:45:27 +02:00
|
|
|
int len = *len_p;
|
2005-06-05 18:02:03 +02:00
|
|
|
while (len && isspace(line[len-1]))
|
|
|
|
len--;
|
2006-04-19 01:45:27 +02:00
|
|
|
*len_p = len;
|
2005-06-05 18:02:03 +02:00
|
|
|
return !len;
|
2005-06-01 17:34:23 +02:00
|
|
|
}
|
|
|
|
|
2006-01-27 11:17:19 +01:00
|
|
|
static int add_merge_info(enum cmit_fmt fmt, char *buf, const struct commit *commit, int abbrev)
|
2005-06-18 22:52:05 +02:00
|
|
|
{
|
2006-01-27 11:17:19 +01:00
|
|
|
struct commit_list *parent = commit->parents;
|
|
|
|
int offset;
|
2005-08-09 07:15:40 +02:00
|
|
|
|
2006-04-19 01:45:27 +02:00
|
|
|
if ((fmt == CMIT_FMT_ONELINE) || (fmt == CMIT_FMT_EMAIL) ||
|
|
|
|
!parent || !parent->next)
|
2006-01-27 11:17:19 +01:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
offset = sprintf(buf, "Merge:");
|
|
|
|
|
|
|
|
while (parent) {
|
|
|
|
struct commit *p = parent->item;
|
2006-10-12 01:16:02 +02:00
|
|
|
const char *hex = NULL;
|
|
|
|
const char *dots;
|
|
|
|
if (abbrev)
|
|
|
|
hex = find_unique_abbrev(p->object.sha1, abbrev);
|
|
|
|
if (!hex)
|
|
|
|
hex = sha1_to_hex(p->object.sha1);
|
|
|
|
dots = (abbrev && strlen(hex) != 40) ? "..." : "";
|
2006-01-27 11:17:19 +01:00
|
|
|
parent = parent->next;
|
|
|
|
|
2006-02-03 02:52:19 +01:00
|
|
|
offset += sprintf(buf + offset, " %s%s", hex, dots);
|
2005-06-18 22:52:05 +02:00
|
|
|
}
|
2006-01-27 11:17:19 +01:00
|
|
|
buf[offset++] = '\n';
|
2005-06-18 22:52:05 +02:00
|
|
|
return offset;
|
|
|
|
}
|
|
|
|
|
2006-12-25 20:48:35 +01:00
|
|
|
static char *get_header(const struct commit *commit, const char *key)
|
|
|
|
{
|
|
|
|
int key_len = strlen(key);
|
|
|
|
const char *line = commit->buffer;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
const char *eol = strchr(line, '\n'), *next;
|
|
|
|
|
|
|
|
if (line == eol)
|
|
|
|
return NULL;
|
|
|
|
if (!eol) {
|
|
|
|
eol = line + strlen(line);
|
|
|
|
next = NULL;
|
|
|
|
} else
|
|
|
|
next = eol + 1;
|
2007-05-04 23:51:32 +02:00
|
|
|
if (eol - line > key_len &&
|
|
|
|
!strncmp(line, key, key_len) &&
|
|
|
|
line[key_len] == ' ') {
|
2006-12-25 20:48:35 +01:00
|
|
|
int len = eol - line - key_len;
|
|
|
|
char *ret = xmalloc(len);
|
|
|
|
memcpy(ret, line + key_len + 1, len - 1);
|
|
|
|
ret[len - 1] = '\0';
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
line = next;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-03-07 02:44:17 +01:00
|
|
|
static char *replace_encoding_header(char *buf, const char *encoding)
|
2006-12-31 00:49:32 +01:00
|
|
|
{
|
|
|
|
char *encoding_header = strstr(buf, "\nencoding ");
|
2007-03-28 23:52:09 +02:00
|
|
|
char *header_end = strstr(buf, "\n\n");
|
2006-12-31 00:49:32 +01:00
|
|
|
char *end_of_encoding_header;
|
|
|
|
int encoding_header_pos;
|
|
|
|
int encoding_header_len;
|
|
|
|
int new_len;
|
|
|
|
int need_len;
|
|
|
|
int buflen = strlen(buf) + 1;
|
|
|
|
|
2007-03-28 23:52:09 +02:00
|
|
|
if (!header_end)
|
|
|
|
header_end = buf + buflen;
|
|
|
|
if (!encoding_header || encoding_header >= header_end)
|
|
|
|
return buf;
|
2006-12-31 00:49:32 +01:00
|
|
|
encoding_header++;
|
|
|
|
end_of_encoding_header = strchr(encoding_header, '\n');
|
|
|
|
if (!end_of_encoding_header)
|
|
|
|
return buf; /* should not happen but be defensive */
|
|
|
|
end_of_encoding_header++;
|
|
|
|
|
|
|
|
encoding_header_len = end_of_encoding_header - encoding_header;
|
|
|
|
encoding_header_pos = encoding_header - buf;
|
|
|
|
|
|
|
|
if (is_encoding_utf8(encoding)) {
|
|
|
|
/* we have re-coded to UTF-8; drop the header */
|
|
|
|
memmove(encoding_header, end_of_encoding_header,
|
|
|
|
buflen - (encoding_header_pos + encoding_header_len));
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
new_len = strlen(encoding);
|
|
|
|
need_len = new_len + strlen("encoding \n");
|
|
|
|
if (encoding_header_len < need_len) {
|
|
|
|
buf = xrealloc(buf, buflen + (need_len - encoding_header_len));
|
|
|
|
encoding_header = buf + encoding_header_pos;
|
|
|
|
end_of_encoding_header = encoding_header + encoding_header_len;
|
|
|
|
}
|
|
|
|
memmove(end_of_encoding_header + (need_len - encoding_header_len),
|
|
|
|
end_of_encoding_header,
|
|
|
|
buflen - (encoding_header_pos + encoding_header_len));
|
|
|
|
memcpy(encoding_header + 9, encoding, strlen(encoding));
|
|
|
|
encoding_header[9 + new_len] = '\n';
|
|
|
|
return buf;
|
|
|
|
}
|
|
|
|
|
2007-01-13 02:32:38 +01:00
|
|
|
static char *logmsg_reencode(const struct commit *commit,
|
2007-03-07 02:44:17 +01:00
|
|
|
const char *output_encoding)
|
2006-12-25 20:48:35 +01:00
|
|
|
{
|
2007-03-07 02:44:17 +01:00
|
|
|
static const char *utf8 = "utf-8";
|
|
|
|
const char *use_encoding;
|
2006-12-28 01:41:33 +01:00
|
|
|
char *encoding;
|
2006-12-25 20:48:35 +01:00
|
|
|
char *out;
|
|
|
|
|
2007-01-13 02:32:38 +01:00
|
|
|
if (!*output_encoding)
|
2006-12-25 20:48:35 +01:00
|
|
|
return NULL;
|
2006-12-28 01:41:33 +01:00
|
|
|
encoding = get_header(commit, "encoding");
|
2007-03-07 02:44:17 +01:00
|
|
|
use_encoding = encoding ? encoding : utf8;
|
|
|
|
if (!strcmp(use_encoding, output_encoding))
|
2007-03-19 22:42:40 +01:00
|
|
|
out = xstrdup(commit->buffer);
|
2007-01-01 03:18:23 +01:00
|
|
|
else
|
|
|
|
out = reencode_string(commit->buffer,
|
2007-03-07 02:44:17 +01:00
|
|
|
output_encoding, use_encoding);
|
2006-12-31 00:49:32 +01:00
|
|
|
if (out)
|
|
|
|
out = replace_encoding_header(out, output_encoding);
|
|
|
|
|
2007-03-07 02:44:17 +01:00
|
|
|
free(encoding);
|
2006-12-25 20:48:35 +01:00
|
|
|
return out;
|
|
|
|
}
|
|
|
|
|
2007-02-23 01:35:03 +01:00
|
|
|
static void fill_person(struct interp *table, const char *msg, int len)
|
|
|
|
{
|
|
|
|
int start, end, tz = 0;
|
|
|
|
unsigned long date;
|
|
|
|
char *ep;
|
|
|
|
|
|
|
|
/* parse name */
|
|
|
|
for (end = 0; end < len && msg[end] != '<'; end++)
|
|
|
|
; /* do nothing */
|
|
|
|
start = end + 1;
|
|
|
|
while (end > 0 && isspace(msg[end - 1]))
|
|
|
|
end--;
|
|
|
|
table[0].value = xstrndup(msg, end);
|
|
|
|
|
|
|
|
if (start >= len)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/* parse email */
|
|
|
|
for (end = start + 1; end < len && msg[end] != '>'; end++)
|
|
|
|
; /* do nothing */
|
|
|
|
|
|
|
|
if (end >= len)
|
|
|
|
return;
|
|
|
|
|
|
|
|
table[1].value = xstrndup(msg + start, end - start);
|
|
|
|
|
|
|
|
/* parse date */
|
|
|
|
for (start = end + 1; start < len && isspace(msg[start]); start++)
|
|
|
|
; /* do nothing */
|
|
|
|
if (start >= len)
|
|
|
|
return;
|
|
|
|
date = strtoul(msg + start, &ep, 10);
|
|
|
|
if (msg + start == ep)
|
|
|
|
return;
|
|
|
|
|
2007-03-28 01:26:28 +02:00
|
|
|
table[5].value = xstrndup(msg + start, ep - (msg + start));
|
2007-02-23 01:35:03 +01:00
|
|
|
|
|
|
|
/* parse tz */
|
|
|
|
for (start = ep - msg + 1; start < len && isspace(msg[start]); start++)
|
|
|
|
; /* do nothing */
|
|
|
|
if (start + 1 < len) {
|
|
|
|
tz = strtoul(msg + start + 1, NULL, 10);
|
|
|
|
if (msg[start] == '-')
|
|
|
|
tz = -tz;
|
|
|
|
}
|
|
|
|
|
|
|
|
interp_set_entry(table, 2, show_date(date, tz, 0));
|
|
|
|
interp_set_entry(table, 3, show_rfc2822_date(date, tz));
|
|
|
|
interp_set_entry(table, 4, show_date(date, tz, 1));
|
|
|
|
}
|
|
|
|
|
|
|
|
static long format_commit_message(const struct commit *commit,
|
2007-06-11 09:34:54 +02:00
|
|
|
const char *msg, char **buf_p, unsigned long *space_p)
|
2007-02-23 01:35:03 +01:00
|
|
|
{
|
|
|
|
struct interp table[] = {
|
|
|
|
{ "%H" }, /* commit hash */
|
|
|
|
{ "%h" }, /* abbreviated commit hash */
|
|
|
|
{ "%T" }, /* tree hash */
|
|
|
|
{ "%t" }, /* abbreviated tree hash */
|
|
|
|
{ "%P" }, /* parent hashes */
|
|
|
|
{ "%p" }, /* abbreviated parent hashes */
|
|
|
|
{ "%an" }, /* author name */
|
|
|
|
{ "%ae" }, /* author email */
|
|
|
|
{ "%ad" }, /* author date */
|
|
|
|
{ "%aD" }, /* author date, RFC2822 style */
|
|
|
|
{ "%ar" }, /* author date, relative */
|
|
|
|
{ "%at" }, /* author date, UNIX timestamp */
|
|
|
|
{ "%cn" }, /* committer name */
|
|
|
|
{ "%ce" }, /* committer email */
|
|
|
|
{ "%cd" }, /* committer date */
|
|
|
|
{ "%cD" }, /* committer date, RFC2822 style */
|
|
|
|
{ "%cr" }, /* committer date, relative */
|
|
|
|
{ "%ct" }, /* committer date, UNIX timestamp */
|
|
|
|
{ "%e" }, /* encoding */
|
|
|
|
{ "%s" }, /* subject */
|
|
|
|
{ "%b" }, /* body */
|
|
|
|
{ "%Cred" }, /* red */
|
|
|
|
{ "%Cgreen" }, /* green */
|
|
|
|
{ "%Cblue" }, /* blue */
|
|
|
|
{ "%Creset" }, /* reset color */
|
2007-04-09 11:34:05 +02:00
|
|
|
{ "%n" }, /* newline */
|
|
|
|
{ "%m" }, /* left/right/bottom */
|
2007-02-23 01:35:03 +01:00
|
|
|
};
|
|
|
|
enum interp_index {
|
|
|
|
IHASH = 0, IHASH_ABBREV,
|
|
|
|
ITREE, ITREE_ABBREV,
|
|
|
|
IPARENTS, IPARENTS_ABBREV,
|
|
|
|
IAUTHOR_NAME, IAUTHOR_EMAIL,
|
|
|
|
IAUTHOR_DATE, IAUTHOR_DATE_RFC2822, IAUTHOR_DATE_RELATIVE,
|
|
|
|
IAUTHOR_TIMESTAMP,
|
|
|
|
ICOMMITTER_NAME, ICOMMITTER_EMAIL,
|
|
|
|
ICOMMITTER_DATE, ICOMMITTER_DATE_RFC2822,
|
|
|
|
ICOMMITTER_DATE_RELATIVE, ICOMMITTER_TIMESTAMP,
|
|
|
|
IENCODING,
|
|
|
|
ISUBJECT,
|
|
|
|
IBODY,
|
|
|
|
IRED, IGREEN, IBLUE, IRESET_COLOR,
|
2007-04-09 11:34:05 +02:00
|
|
|
INEWLINE,
|
|
|
|
ILEFT_RIGHT,
|
2007-02-23 01:35:03 +01:00
|
|
|
};
|
|
|
|
struct commit_list *p;
|
|
|
|
char parents[1024];
|
|
|
|
int i;
|
|
|
|
enum { HEADER, SUBJECT, BODY } state;
|
|
|
|
|
2007-04-09 11:34:05 +02:00
|
|
|
if (ILEFT_RIGHT + 1 != ARRAY_SIZE(table))
|
2007-02-23 01:35:03 +01:00
|
|
|
die("invalid interp table!");
|
|
|
|
|
|
|
|
/* these are independent of the commit */
|
|
|
|
interp_set_entry(table, IRED, "\033[31m");
|
|
|
|
interp_set_entry(table, IGREEN, "\033[32m");
|
|
|
|
interp_set_entry(table, IBLUE, "\033[34m");
|
|
|
|
interp_set_entry(table, IRESET_COLOR, "\033[m");
|
|
|
|
interp_set_entry(table, INEWLINE, "\n");
|
|
|
|
|
|
|
|
/* these depend on the commit */
|
|
|
|
if (!commit->object.parsed)
|
|
|
|
parse_object(commit->object.sha1);
|
|
|
|
interp_set_entry(table, IHASH, sha1_to_hex(commit->object.sha1));
|
|
|
|
interp_set_entry(table, IHASH_ABBREV,
|
|
|
|
find_unique_abbrev(commit->object.sha1,
|
|
|
|
DEFAULT_ABBREV));
|
|
|
|
interp_set_entry(table, ITREE, sha1_to_hex(commit->tree->object.sha1));
|
|
|
|
interp_set_entry(table, ITREE_ABBREV,
|
|
|
|
find_unique_abbrev(commit->tree->object.sha1,
|
|
|
|
DEFAULT_ABBREV));
|
2007-04-09 11:34:05 +02:00
|
|
|
interp_set_entry(table, ILEFT_RIGHT,
|
|
|
|
(commit->object.flags & BOUNDARY)
|
|
|
|
? "-"
|
|
|
|
: (commit->object.flags & SYMMETRIC_LEFT)
|
|
|
|
? "<"
|
|
|
|
: ">");
|
2007-03-28 22:33:37 +02:00
|
|
|
|
|
|
|
parents[1] = 0;
|
2007-02-23 01:35:03 +01:00
|
|
|
for (i = 0, p = commit->parents;
|
|
|
|
p && i < sizeof(parents) - 1;
|
|
|
|
p = p->next)
|
2007-03-28 22:33:37 +02:00
|
|
|
i += snprintf(parents + i, sizeof(parents) - i - 1, " %s",
|
2007-02-23 01:35:03 +01:00
|
|
|
sha1_to_hex(p->item->object.sha1));
|
2007-03-28 22:33:37 +02:00
|
|
|
interp_set_entry(table, IPARENTS, parents + 1);
|
|
|
|
|
|
|
|
parents[1] = 0;
|
2007-02-23 01:35:03 +01:00
|
|
|
for (i = 0, p = commit->parents;
|
|
|
|
p && i < sizeof(parents) - 1;
|
|
|
|
p = p->next)
|
2007-03-28 22:33:37 +02:00
|
|
|
i += snprintf(parents + i, sizeof(parents) - i - 1, " %s",
|
2007-02-23 01:35:03 +01:00
|
|
|
find_unique_abbrev(p->item->object.sha1,
|
|
|
|
DEFAULT_ABBREV));
|
2007-03-28 22:33:37 +02:00
|
|
|
interp_set_entry(table, IPARENTS_ABBREV, parents + 1);
|
2007-02-23 01:35:03 +01:00
|
|
|
|
|
|
|
for (i = 0, state = HEADER; msg[i] && state < BODY; i++) {
|
|
|
|
int eol;
|
|
|
|
for (eol = i; msg[eol] && msg[eol] != '\n'; eol++)
|
|
|
|
; /* do nothing */
|
|
|
|
|
|
|
|
if (state == SUBJECT) {
|
|
|
|
table[ISUBJECT].value = xstrndup(msg + i, eol - i);
|
|
|
|
i = eol;
|
|
|
|
}
|
|
|
|
if (i == eol) {
|
|
|
|
state++;
|
|
|
|
/* strip empty lines */
|
|
|
|
while (msg[eol + 1] == '\n')
|
|
|
|
eol++;
|
|
|
|
} else if (!prefixcmp(msg + i, "author "))
|
|
|
|
fill_person(table + IAUTHOR_NAME,
|
|
|
|
msg + i + 7, eol - i - 7);
|
|
|
|
else if (!prefixcmp(msg + i, "committer "))
|
|
|
|
fill_person(table + ICOMMITTER_NAME,
|
|
|
|
msg + i + 10, eol - i - 10);
|
|
|
|
else if (!prefixcmp(msg + i, "encoding "))
|
2007-03-28 23:09:05 +02:00
|
|
|
table[IENCODING].value =
|
|
|
|
xstrndup(msg + i + 9, eol - i - 9);
|
2007-02-23 01:35:03 +01:00
|
|
|
i = eol;
|
|
|
|
}
|
|
|
|
if (msg[i])
|
|
|
|
table[IBODY].value = xstrdup(msg + i);
|
|
|
|
for (i = 0; i < ARRAY_SIZE(table); i++)
|
|
|
|
if (!table[i].value)
|
|
|
|
interp_set_entry(table, i, "<unknown>");
|
|
|
|
|
2007-06-11 09:34:54 +02:00
|
|
|
do {
|
|
|
|
char *buf = *buf_p;
|
|
|
|
unsigned long space = *space_p;
|
|
|
|
|
|
|
|
space = interpolate(buf, space, user_format,
|
|
|
|
table, ARRAY_SIZE(table));
|
|
|
|
if (!space)
|
|
|
|
break;
|
|
|
|
buf = xrealloc(buf, space);
|
|
|
|
*buf_p = buf;
|
|
|
|
*space_p = space;
|
|
|
|
} while (1);
|
2007-02-23 01:35:03 +01:00
|
|
|
interp_clear_table(table, ARRAY_SIZE(table));
|
|
|
|
|
2007-06-11 09:34:54 +02:00
|
|
|
return strlen(*buf_p);
|
2007-02-23 01:35:03 +01:00
|
|
|
}
|
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
static void pp_header(enum cmit_fmt fmt,
|
|
|
|
int abbrev,
|
|
|
|
enum date_mode dmode,
|
|
|
|
const char *encoding,
|
|
|
|
const struct commit *commit,
|
|
|
|
const char **msg_p,
|
|
|
|
unsigned long *len_p,
|
|
|
|
unsigned long *ofs_p,
|
|
|
|
char **buf_p,
|
|
|
|
unsigned long *space_p)
|
|
|
|
{
|
|
|
|
int parents_shown = 0;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
const char *line = *msg_p;
|
|
|
|
char *dst;
|
|
|
|
int linelen = get_one_line(*msg_p, *len_p);
|
|
|
|
unsigned long len;
|
|
|
|
|
|
|
|
if (!linelen)
|
|
|
|
return;
|
|
|
|
*msg_p += linelen;
|
|
|
|
*len_p -= linelen;
|
|
|
|
|
|
|
|
if (linelen == 1)
|
|
|
|
/* End of header */
|
|
|
|
return;
|
|
|
|
|
|
|
|
ALLOC_GROW(*buf_p, linelen + *ofs_p + 20, *space_p);
|
|
|
|
dst = *buf_p + *ofs_p;
|
|
|
|
|
|
|
|
if (fmt == CMIT_FMT_RAW) {
|
|
|
|
memcpy(dst, line, linelen);
|
|
|
|
*ofs_p += linelen;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!memcmp(line, "parent ", 7)) {
|
|
|
|
if (linelen != 48)
|
|
|
|
die("bad parent line in commit");
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!parents_shown) {
|
|
|
|
struct commit_list *parent;
|
|
|
|
int num;
|
|
|
|
for (parent = commit->parents, num = 0;
|
|
|
|
parent;
|
|
|
|
parent = parent->next, num++)
|
|
|
|
;
|
|
|
|
/* with enough slop */
|
|
|
|
num = *ofs_p + num * 50 + 20;
|
|
|
|
ALLOC_GROW(*buf_p, num, *space_p);
|
|
|
|
dst = *buf_p + *ofs_p;
|
|
|
|
*ofs_p += add_merge_info(fmt, dst, commit, abbrev);
|
|
|
|
parents_shown = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* MEDIUM == DEFAULT shows only author with dates.
|
|
|
|
* FULL shows both authors but not dates.
|
|
|
|
* FULLER shows both authors and dates.
|
|
|
|
*/
|
|
|
|
if (!memcmp(line, "author ", 7)) {
|
|
|
|
len = linelen;
|
|
|
|
if (fmt == CMIT_FMT_EMAIL)
|
|
|
|
len = bound_rfc2047(linelen, encoding);
|
2007-06-15 14:19:07 +02:00
|
|
|
ALLOC_GROW(*buf_p, *ofs_p + len + 80, *space_p);
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
dst = *buf_p + *ofs_p;
|
|
|
|
*ofs_p += add_user_info("Author", fmt, dst,
|
|
|
|
line + 7, dmode, encoding);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!memcmp(line, "committer ", 10) &&
|
|
|
|
(fmt == CMIT_FMT_FULL || fmt == CMIT_FMT_FULLER)) {
|
|
|
|
len = linelen;
|
|
|
|
if (fmt == CMIT_FMT_EMAIL)
|
|
|
|
len = bound_rfc2047(linelen, encoding);
|
2007-06-15 14:19:07 +02:00
|
|
|
ALLOC_GROW(*buf_p, *ofs_p + len + 80, *space_p);
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
dst = *buf_p + *ofs_p;
|
|
|
|
*ofs_p += add_user_info("Commit", fmt, dst,
|
|
|
|
line + 10, dmode, encoding);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void pp_title_line(enum cmit_fmt fmt,
|
|
|
|
const char **msg_p,
|
|
|
|
unsigned long *len_p,
|
|
|
|
unsigned long *ofs_p,
|
|
|
|
char **buf_p,
|
|
|
|
unsigned long *space_p,
|
|
|
|
int indent,
|
|
|
|
const char *subject,
|
|
|
|
const char *after_subject,
|
|
|
|
const char *encoding,
|
|
|
|
int plain_non_ascii)
|
|
|
|
{
|
|
|
|
char *title;
|
|
|
|
unsigned long title_alloc, title_len;
|
|
|
|
unsigned long len;
|
|
|
|
|
|
|
|
title_len = 0;
|
|
|
|
title_alloc = 80;
|
|
|
|
title = xmalloc(title_alloc);
|
|
|
|
for (;;) {
|
|
|
|
const char *line = *msg_p;
|
|
|
|
int linelen = get_one_line(line, *len_p);
|
|
|
|
*msg_p += linelen;
|
|
|
|
*len_p -= linelen;
|
|
|
|
|
|
|
|
if (!linelen || is_empty_line(line, &linelen))
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (title_alloc <= title_len + linelen + 2) {
|
|
|
|
title_alloc = title_len + linelen + 80;
|
|
|
|
title = xrealloc(title, title_alloc);
|
|
|
|
}
|
|
|
|
len = 0;
|
|
|
|
if (title_len) {
|
|
|
|
if (fmt == CMIT_FMT_EMAIL) {
|
|
|
|
len++;
|
|
|
|
title[title_len++] = '\n';
|
|
|
|
}
|
|
|
|
len++;
|
|
|
|
title[title_len++] = ' ';
|
|
|
|
}
|
|
|
|
memcpy(title + title_len, line, linelen);
|
|
|
|
title_len += linelen;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Enough slop for the MIME header and rfc2047 */
|
|
|
|
len = bound_rfc2047(title_len, encoding)+ 1000;
|
|
|
|
if (subject)
|
|
|
|
len += strlen(subject);
|
|
|
|
if (after_subject)
|
|
|
|
len += strlen(after_subject);
|
|
|
|
if (encoding)
|
|
|
|
len += strlen(encoding);
|
|
|
|
ALLOC_GROW(*buf_p, title_len + *ofs_p + len, *space_p);
|
|
|
|
|
|
|
|
if (subject) {
|
|
|
|
len = strlen(subject);
|
|
|
|
memcpy(*buf_p + *ofs_p, subject, len);
|
|
|
|
*ofs_p += len;
|
|
|
|
*ofs_p += add_rfc2047(*buf_p + *ofs_p,
|
|
|
|
title, title_len, encoding);
|
|
|
|
} else {
|
|
|
|
memcpy(*buf_p + *ofs_p, title, title_len);
|
|
|
|
*ofs_p += title_len;
|
|
|
|
}
|
|
|
|
(*buf_p)[(*ofs_p)++] = '\n';
|
|
|
|
if (plain_non_ascii) {
|
|
|
|
const char *header_fmt =
|
|
|
|
"MIME-Version: 1.0\n"
|
|
|
|
"Content-Type: text/plain; charset=%s\n"
|
|
|
|
"Content-Transfer-Encoding: 8bit\n";
|
|
|
|
*ofs_p += snprintf(*buf_p + *ofs_p,
|
|
|
|
*space_p - *ofs_p,
|
|
|
|
header_fmt, encoding);
|
|
|
|
}
|
|
|
|
if (after_subject) {
|
|
|
|
len = strlen(after_subject);
|
|
|
|
memcpy(*buf_p + *ofs_p, after_subject, len);
|
|
|
|
*ofs_p += len;
|
|
|
|
}
|
|
|
|
free(title);
|
|
|
|
if (fmt == CMIT_FMT_EMAIL) {
|
|
|
|
ALLOC_GROW(*buf_p, *ofs_p + 20, *space_p);
|
|
|
|
(*buf_p)[(*ofs_p)++] = '\n';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void pp_remainder(enum cmit_fmt fmt,
|
|
|
|
const char **msg_p,
|
|
|
|
unsigned long *len_p,
|
|
|
|
unsigned long *ofs_p,
|
|
|
|
char **buf_p,
|
|
|
|
unsigned long *space_p,
|
|
|
|
int indent)
|
|
|
|
{
|
|
|
|
int first = 1;
|
|
|
|
for (;;) {
|
|
|
|
const char *line = *msg_p;
|
|
|
|
int linelen = get_one_line(line, *len_p);
|
|
|
|
*msg_p += linelen;
|
|
|
|
*len_p -= linelen;
|
|
|
|
|
|
|
|
if (!linelen)
|
|
|
|
break;
|
|
|
|
|
|
|
|
if (is_empty_line(line, &linelen)) {
|
|
|
|
if (first)
|
|
|
|
continue;
|
|
|
|
if (fmt == CMIT_FMT_SHORT)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
first = 0;
|
|
|
|
|
|
|
|
ALLOC_GROW(*buf_p, *ofs_p + linelen + indent + 20, *space_p);
|
|
|
|
if (indent) {
|
|
|
|
memset(*buf_p + *ofs_p, ' ', indent);
|
|
|
|
*ofs_p += indent;
|
|
|
|
}
|
|
|
|
memcpy(*buf_p + *ofs_p, line, linelen);
|
|
|
|
*ofs_p += linelen;
|
|
|
|
(*buf_p)[(*ofs_p)++] = '\n';
|
|
|
|
}
|
2007-02-23 01:35:03 +01:00
|
|
|
}
|
|
|
|
|
2006-12-25 20:48:35 +01:00
|
|
|
unsigned long pretty_print_commit(enum cmit_fmt fmt,
|
|
|
|
const struct commit *commit,
|
|
|
|
unsigned long len,
|
2007-06-11 09:34:54 +02:00
|
|
|
char **buf_p, unsigned long *space_p,
|
2006-08-28 15:52:13 +02:00
|
|
|
int abbrev, const char *subject,
|
2006-12-25 20:48:35 +01:00
|
|
|
const char *after_subject,
|
2007-04-25 08:36:22 +02:00
|
|
|
enum date_mode dmode)
|
2005-06-01 17:34:23 +02:00
|
|
|
{
|
|
|
|
unsigned long offset = 0;
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
unsigned long beginning_of_body;
|
2006-04-19 01:45:27 +02:00
|
|
|
int indent = 4;
|
2006-01-27 10:54:59 +01:00
|
|
|
const char *msg = commit->buffer;
|
2006-05-22 08:55:00 +02:00
|
|
|
int plain_non_ascii = 0;
|
2007-01-13 02:32:38 +01:00
|
|
|
char *reencoded;
|
2007-03-07 02:44:17 +01:00
|
|
|
const char *encoding;
|
2007-06-11 09:34:54 +02:00
|
|
|
char *buf;
|
2006-12-25 20:48:35 +01:00
|
|
|
|
2007-02-23 01:35:03 +01:00
|
|
|
if (fmt == CMIT_FMT_USERFORMAT)
|
2007-06-11 09:34:54 +02:00
|
|
|
return format_commit_message(commit, msg, buf_p, space_p);
|
2007-02-23 01:35:03 +01:00
|
|
|
|
2007-01-13 02:32:38 +01:00
|
|
|
encoding = (git_log_output_encoding
|
|
|
|
? git_log_output_encoding
|
|
|
|
: git_commit_encoding);
|
|
|
|
if (!encoding)
|
|
|
|
encoding = "utf-8";
|
|
|
|
reencoded = logmsg_reencode(commit, encoding);
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
if (reencoded) {
|
2006-12-28 01:41:33 +01:00
|
|
|
msg = reencoded;
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
len = strlen(reencoded);
|
|
|
|
}
|
2006-04-19 01:45:27 +02:00
|
|
|
|
|
|
|
if (fmt == CMIT_FMT_ONELINE || fmt == CMIT_FMT_EMAIL)
|
|
|
|
indent = 0;
|
2005-06-01 17:34:23 +02:00
|
|
|
|
2006-05-22 08:55:00 +02:00
|
|
|
/* After-subject is used to pass in Content-Type: multipart
|
|
|
|
* MIME header; in that case we do not have to do the
|
|
|
|
* plaintext content type even if the commit message has
|
|
|
|
* non 7-bit ASCII character. Otherwise, check if we need
|
|
|
|
* to say this is not a 7-bit ASCII.
|
|
|
|
*/
|
|
|
|
if (fmt == CMIT_FMT_EMAIL && !after_subject) {
|
2006-06-20 00:00:17 +02:00
|
|
|
int i, ch, in_body;
|
|
|
|
|
|
|
|
for (in_body = i = 0; (ch = msg[i]) && i < len; i++) {
|
|
|
|
if (!in_body) {
|
|
|
|
/* author could be non 7-bit ASCII but
|
2006-12-28 01:41:33 +01:00
|
|
|
* the log may be so; skip over the
|
2006-06-20 00:00:17 +02:00
|
|
|
* header part first.
|
|
|
|
*/
|
|
|
|
if (ch == '\n' &&
|
|
|
|
i + 1 < len && msg[i+1] == '\n')
|
|
|
|
in_body = 1;
|
|
|
|
}
|
2007-01-13 02:32:38 +01:00
|
|
|
else if (non_ascii(ch)) {
|
2006-05-22 08:55:00 +02:00
|
|
|
plain_non_ascii = 1;
|
2006-06-20 00:00:17 +02:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
2006-05-22 08:55:00 +02:00
|
|
|
}
|
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
pp_header(fmt, abbrev, dmode, encoding,
|
|
|
|
commit, &msg, &len,
|
|
|
|
&offset, buf_p, space_p);
|
|
|
|
if (fmt != CMIT_FMT_ONELINE && !subject) {
|
|
|
|
ALLOC_GROW(*buf_p, offset + 20, *space_p);
|
|
|
|
(*buf_p)[offset++] = '\n';
|
2007-06-11 09:34:54 +02:00
|
|
|
}
|
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
/* Skip excess blank lines at the beginning of body, if any... */
|
2005-06-01 17:34:23 +02:00
|
|
|
for (;;) {
|
|
|
|
int linelen = get_one_line(msg, len);
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
int ll = linelen;
|
2005-06-01 17:34:23 +02:00
|
|
|
if (!linelen)
|
|
|
|
break;
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
if (!is_empty_line(msg, &ll))
|
2005-06-01 17:34:23 +02:00
|
|
|
break;
|
|
|
|
msg += linelen;
|
|
|
|
len -= linelen;
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
}
|
2005-06-05 18:02:03 +02:00
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
/* These formats treat the title line specially. */
|
|
|
|
if (fmt == CMIT_FMT_ONELINE
|
|
|
|
|| fmt == CMIT_FMT_EMAIL)
|
|
|
|
pp_title_line(fmt, &msg, &len, &offset,
|
|
|
|
buf_p, space_p, indent,
|
|
|
|
subject, after_subject, encoding,
|
|
|
|
plain_non_ascii);
|
2006-07-14 00:17:22 +02:00
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
beginning_of_body = offset;
|
|
|
|
if (fmt != CMIT_FMT_ONELINE)
|
|
|
|
pp_remainder(fmt, &msg, &len, &offset,
|
|
|
|
buf_p, space_p, indent);
|
2005-08-09 07:15:40 +02:00
|
|
|
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
while (offset && isspace((*buf_p)[offset-1]))
|
2006-04-15 06:20:51 +02:00
|
|
|
offset--;
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
|
|
|
|
ALLOC_GROW(*buf_p, offset + 20, *space_p);
|
|
|
|
buf = *buf_p;
|
|
|
|
|
2006-04-15 06:20:51 +02:00
|
|
|
/* Make sure there is an EOLN for the non-oneline case */
|
|
|
|
if (fmt != CMIT_FMT_ONELINE)
|
|
|
|
buf[offset++] = '\n';
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
|
2006-07-14 00:17:22 +02:00
|
|
|
/*
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
* The caller may append additional body text in e-mail
|
|
|
|
* format. Make sure we did not strip the blank line
|
|
|
|
* between the header and the body.
|
2006-07-14 00:17:22 +02:00
|
|
|
*/
|
Extend --pretty=oneline to cover the first paragraph,
so that an ugly commit message like this can be
handled sanely.
Currently, --pretty=oneline and --pretty=email (hence
format-patch) take and use only the first line of the commit log
message. This changes them to:
- Take the first paragraph, where the definition of the first
paragraph is "skip all blank lines from the beginning, and
then grab everything up to the next empty line".
- Replace all line breaks with a whitespace.
This change would not affect a well-behaved commit message that
adheres to the convention of "single line summary, a blank line,
and then body of message", as its first paragraph always
consists of a single line. Commit messages from different
culture, such as the ones imported from CVS/SVN, can however get
chomped with the existing behaviour at the first linebreak in
the middle of sentence right now, which would become much easier
to see with this change.
The Subject: and --pretty=oneline output would become very long
and unsightly for non-conforming commits, but their messages are
already ugly anyway, and thischange at least avoids the loss of
information.
The Subject: line from a multi-line paragraph is folded using
RFC2822 line folding rules at the places where line breaks were
in the original.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 07:10:55 +02:00
|
|
|
if (fmt == CMIT_FMT_EMAIL && offset <= beginning_of_body)
|
2006-07-14 00:17:22 +02:00
|
|
|
buf[offset++] = '\n';
|
2005-06-01 17:34:23 +02:00
|
|
|
buf[offset] = '\0';
|
2006-12-25 20:48:35 +01:00
|
|
|
free(reencoded);
|
2005-06-01 17:34:23 +02:00
|
|
|
return offset;
|
|
|
|
}
|
2005-06-06 17:39:40 +02:00
|
|
|
|
|
|
|
struct commit *pop_commit(struct commit_list **stack)
|
|
|
|
{
|
|
|
|
struct commit_list *top = *stack;
|
|
|
|
struct commit *item = top ? top->item : NULL;
|
|
|
|
|
|
|
|
if (top) {
|
|
|
|
*stack = top->next;
|
|
|
|
free(top);
|
|
|
|
}
|
|
|
|
return item;
|
|
|
|
}
|
|
|
|
|
2006-03-10 10:21:37 +01:00
|
|
|
void topo_sort_default_setter(struct commit *c, void *data)
|
|
|
|
{
|
2006-06-18 03:26:18 +02:00
|
|
|
c->util = data;
|
2006-03-10 10:21:37 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
void *topo_sort_default_getter(struct commit *c)
|
|
|
|
{
|
2006-06-18 03:26:18 +02:00
|
|
|
return c->util;
|
2006-03-10 10:21:37 +01:00
|
|
|
}
|
|
|
|
|
2005-07-06 18:39:34 +02:00
|
|
|
/*
|
|
|
|
* Performs an in-place topological sort on the list supplied.
|
|
|
|
*/
|
2006-02-16 07:05:33 +01:00
|
|
|
void sort_in_topological_order(struct commit_list ** list, int lifo)
|
2006-03-10 10:21:37 +01:00
|
|
|
{
|
|
|
|
sort_in_topological_order_fn(list, lifo, topo_sort_default_setter,
|
|
|
|
topo_sort_default_getter);
|
|
|
|
}
|
|
|
|
|
|
|
|
void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
|
|
|
|
topo_sort_set_fn_t setter,
|
|
|
|
topo_sort_get_fn_t getter)
|
2005-07-06 18:39:34 +02:00
|
|
|
{
|
|
|
|
struct commit_list * next = *list;
|
2005-11-14 19:01:26 +01:00
|
|
|
struct commit_list * work = NULL, **insert;
|
2005-07-06 18:39:34 +02:00
|
|
|
struct commit_list ** pptr = list;
|
|
|
|
struct sort_node * nodes;
|
|
|
|
struct sort_node * next_nodes;
|
|
|
|
int count = 0;
|
|
|
|
|
|
|
|
/* determine the size of the list */
|
|
|
|
while (next) {
|
|
|
|
next = next->next;
|
|
|
|
count++;
|
|
|
|
}
|
2007-06-07 09:04:01 +02:00
|
|
|
|
2005-12-24 13:12:43 +01:00
|
|
|
if (!count)
|
|
|
|
return;
|
2005-07-06 18:39:34 +02:00
|
|
|
/* allocate an array to help sort the list */
|
|
|
|
nodes = xcalloc(count, sizeof(*nodes));
|
|
|
|
/* link the list to the array */
|
|
|
|
next_nodes = nodes;
|
|
|
|
next=*list;
|
|
|
|
while (next) {
|
|
|
|
next_nodes->list_item = next;
|
2006-03-10 10:21:37 +01:00
|
|
|
setter(next->item, next_nodes);
|
2005-07-06 18:39:34 +02:00
|
|
|
next_nodes++;
|
|
|
|
next = next->next;
|
|
|
|
}
|
|
|
|
/* update the indegree */
|
|
|
|
next=*list;
|
|
|
|
while (next) {
|
|
|
|
struct commit_list * parents = next->item->parents;
|
|
|
|
while (parents) {
|
|
|
|
struct commit * parent=parents->item;
|
2006-03-10 10:21:37 +01:00
|
|
|
struct sort_node * pn = (struct sort_node *) getter(parent);
|
|
|
|
|
2005-07-06 18:39:34 +02:00
|
|
|
if (pn)
|
|
|
|
pn->indegree++;
|
|
|
|
parents=parents->next;
|
|
|
|
}
|
|
|
|
next=next->next;
|
|
|
|
}
|
2007-06-07 09:04:01 +02:00
|
|
|
/*
|
2005-07-06 18:39:34 +02:00
|
|
|
* find the tips
|
|
|
|
*
|
2007-06-07 09:04:01 +02:00
|
|
|
* tips are nodes not reachable from any other node in the list
|
|
|
|
*
|
2005-07-06 18:39:34 +02:00
|
|
|
* the tips serve as a starting set for the work queue.
|
|
|
|
*/
|
|
|
|
next=*list;
|
2005-11-14 19:01:26 +01:00
|
|
|
insert = &work;
|
2005-07-06 18:39:34 +02:00
|
|
|
while (next) {
|
2006-03-10 10:21:37 +01:00
|
|
|
struct sort_node * node = (struct sort_node *) getter(next->item);
|
2005-07-06 18:39:34 +02:00
|
|
|
|
|
|
|
if (node->indegree == 0) {
|
2005-11-14 19:01:26 +01:00
|
|
|
insert = &commit_list_insert(next->item, insert)->next;
|
2005-07-06 18:39:34 +02:00
|
|
|
}
|
|
|
|
next=next->next;
|
|
|
|
}
|
2006-02-16 07:05:33 +01:00
|
|
|
|
2005-07-06 18:39:34 +02:00
|
|
|
/* process the list in topological order */
|
2006-02-16 07:05:33 +01:00
|
|
|
if (!lifo)
|
|
|
|
sort_by_date(&work);
|
2005-07-06 18:39:34 +02:00
|
|
|
while (work) {
|
|
|
|
struct commit * work_item = pop_commit(&work);
|
2006-03-10 10:21:37 +01:00
|
|
|
struct sort_node * work_node = (struct sort_node *) getter(work_item);
|
2005-07-06 18:39:34 +02:00
|
|
|
struct commit_list * parents = work_item->parents;
|
|
|
|
|
|
|
|
while (parents) {
|
|
|
|
struct commit * parent=parents->item;
|
2006-03-10 10:21:37 +01:00
|
|
|
struct sort_node * pn = (struct sort_node *) getter(parent);
|
|
|
|
|
2005-07-06 18:39:34 +02:00
|
|
|
if (pn) {
|
2006-03-10 10:21:37 +01:00
|
|
|
/*
|
2007-06-07 09:04:01 +02:00
|
|
|
* parents are only enqueued for emission
|
2005-07-06 18:39:34 +02:00
|
|
|
* when all their children have been emitted thereby
|
|
|
|
* guaranteeing topological order.
|
|
|
|
*/
|
|
|
|
pn->indegree--;
|
2006-02-16 07:05:33 +01:00
|
|
|
if (!pn->indegree) {
|
|
|
|
if (!lifo)
|
|
|
|
insert_by_date(parent, &work);
|
|
|
|
else
|
|
|
|
commit_list_insert(parent, &work);
|
|
|
|
}
|
2005-07-06 18:39:34 +02:00
|
|
|
}
|
|
|
|
parents=parents->next;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* work_item is a commit all of whose children
|
|
|
|
* have already been emitted. we can emit it now.
|
|
|
|
*/
|
|
|
|
*pptr = work_node->list_item;
|
|
|
|
pptr = &(*pptr)->next;
|
|
|
|
*pptr = NULL;
|
2006-03-10 10:21:37 +01:00
|
|
|
setter(work_item, NULL);
|
2005-07-06 18:39:34 +02:00
|
|
|
}
|
|
|
|
free(nodes);
|
|
|
|
}
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2007-01-09 08:10:49 +01:00
|
|
|
/* merge-base stuff */
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-10-23 02:32:47 +02:00
|
|
|
/* bits #0..15 in revision.h */
|
|
|
|
#define PARENT1 (1u<<16)
|
|
|
|
#define PARENT2 (1u<<17)
|
|
|
|
#define STALE (1u<<18)
|
|
|
|
#define RESULT (1u<<19)
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2007-01-09 08:10:49 +01:00
|
|
|
static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT);
|
|
|
|
|
2006-06-29 15:17:32 +02:00
|
|
|
static struct commit *interesting(struct commit_list *list)
|
|
|
|
{
|
|
|
|
while (list) {
|
|
|
|
struct commit *commit = list->item;
|
|
|
|
list = list->next;
|
2006-07-02 20:34:17 +02:00
|
|
|
if (commit->object.flags & STALE)
|
2006-06-29 15:17:32 +02:00
|
|
|
continue;
|
|
|
|
return commit;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
static struct commit_list *merge_bases(struct commit *one, struct commit *two)
|
2006-06-29 15:17:32 +02:00
|
|
|
{
|
|
|
|
struct commit_list *list = NULL;
|
|
|
|
struct commit_list *result = NULL;
|
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
if (one == two)
|
|
|
|
/* We do not mark this even with RESULT so we do not
|
|
|
|
* have to clean it up.
|
|
|
|
*/
|
|
|
|
return commit_list_insert(one, &result);
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
parse_commit(one);
|
|
|
|
parse_commit(two);
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
one->object.flags |= PARENT1;
|
|
|
|
two->object.flags |= PARENT2;
|
|
|
|
insert_by_date(one, &list);
|
|
|
|
insert_by_date(two, &list);
|
2006-06-29 15:17:32 +02:00
|
|
|
|
|
|
|
while (interesting(list)) {
|
2006-07-05 03:46:42 +02:00
|
|
|
struct commit *commit;
|
2006-06-29 15:17:32 +02:00
|
|
|
struct commit_list *parents;
|
2006-07-05 03:46:42 +02:00
|
|
|
struct commit_list *n;
|
|
|
|
int flags;
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
commit = list->item;
|
|
|
|
n = list->next;
|
|
|
|
free(list);
|
|
|
|
list = n;
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
flags = commit->object.flags & (PARENT1 | PARENT2 | STALE);
|
|
|
|
if (flags == (PARENT1 | PARENT2)) {
|
|
|
|
if (!(commit->object.flags & RESULT)) {
|
|
|
|
commit->object.flags |= RESULT;
|
|
|
|
insert_by_date(commit, &result);
|
|
|
|
}
|
2006-07-02 20:34:17 +02:00
|
|
|
/* Mark parents of a found merge stale */
|
|
|
|
flags |= STALE;
|
2006-06-29 15:17:32 +02:00
|
|
|
}
|
|
|
|
parents = commit->parents;
|
|
|
|
while (parents) {
|
|
|
|
struct commit *p = parents->item;
|
|
|
|
parents = parents->next;
|
|
|
|
if ((p->object.flags & flags) == flags)
|
|
|
|
continue;
|
|
|
|
parse_commit(p);
|
|
|
|
p->object.flags |= flags;
|
|
|
|
insert_by_date(p, &list);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
/* Clean up the result to remove stale ones */
|
2007-01-09 08:10:49 +01:00
|
|
|
free_commit_list(list);
|
2006-07-05 03:46:42 +02:00
|
|
|
list = result; result = NULL;
|
|
|
|
while (list) {
|
|
|
|
struct commit_list *n = list->next;
|
|
|
|
if (!(list->item->object.flags & STALE))
|
|
|
|
insert_by_date(list->item, &result);
|
|
|
|
free(list);
|
|
|
|
list = n;
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
struct commit_list *get_merge_bases(struct commit *one,
|
|
|
|
struct commit *two,
|
|
|
|
int cleanup)
|
|
|
|
{
|
|
|
|
struct commit_list *list;
|
|
|
|
struct commit **rslt;
|
|
|
|
struct commit_list *result;
|
|
|
|
int cnt, i, j;
|
|
|
|
|
|
|
|
result = merge_bases(one, two);
|
|
|
|
if (one == two)
|
|
|
|
return result;
|
|
|
|
if (!result || !result->next) {
|
|
|
|
if (cleanup) {
|
|
|
|
clear_commit_marks(one, all_flags);
|
|
|
|
clear_commit_marks(two, all_flags);
|
2006-06-29 15:17:32 +02:00
|
|
|
}
|
2006-07-05 03:46:42 +02:00
|
|
|
return result;
|
2006-06-29 15:17:32 +02:00
|
|
|
}
|
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
/* There are more than one */
|
|
|
|
cnt = 0;
|
|
|
|
list = result;
|
|
|
|
while (list) {
|
|
|
|
list = list->next;
|
|
|
|
cnt++;
|
|
|
|
}
|
|
|
|
rslt = xcalloc(cnt, sizeof(*rslt));
|
|
|
|
for (list = result, i = 0; list; list = list->next)
|
|
|
|
rslt[i++] = list->item;
|
|
|
|
free_commit_list(result);
|
|
|
|
|
|
|
|
clear_commit_marks(one, all_flags);
|
|
|
|
clear_commit_marks(two, all_flags);
|
|
|
|
for (i = 0; i < cnt - 1; i++) {
|
|
|
|
for (j = i+1; j < cnt; j++) {
|
|
|
|
if (!rslt[i] || !rslt[j])
|
|
|
|
continue;
|
|
|
|
result = merge_bases(rslt[i], rslt[j]);
|
|
|
|
clear_commit_marks(rslt[i], all_flags);
|
|
|
|
clear_commit_marks(rslt[j], all_flags);
|
|
|
|
for (list = result; list; list = list->next) {
|
|
|
|
if (rslt[i] == list->item)
|
|
|
|
rslt[i] = NULL;
|
|
|
|
if (rslt[j] == list->item)
|
|
|
|
rslt[j] = NULL;
|
|
|
|
}
|
|
|
|
}
|
2006-07-05 02:45:22 +02:00
|
|
|
}
|
2006-06-29 15:17:32 +02:00
|
|
|
|
2006-07-05 03:46:42 +02:00
|
|
|
/* Surviving ones in rslt[] are the independent results */
|
|
|
|
result = NULL;
|
|
|
|
for (i = 0; i < cnt; i++) {
|
|
|
|
if (rslt[i])
|
|
|
|
insert_by_date(rslt[i], &result);
|
|
|
|
}
|
|
|
|
free(rslt);
|
2006-06-29 15:17:32 +02:00
|
|
|
return result;
|
|
|
|
}
|
2006-12-19 09:14:04 +01:00
|
|
|
|
2007-01-09 08:22:31 +01:00
|
|
|
int in_merge_bases(struct commit *commit, struct commit **reference, int num)
|
2006-12-19 09:14:04 +01:00
|
|
|
{
|
|
|
|
struct commit_list *bases, *b;
|
|
|
|
int ret = 0;
|
|
|
|
|
2007-01-09 08:22:31 +01:00
|
|
|
if (num == 1)
|
|
|
|
bases = get_merge_bases(commit, *reference, 1);
|
|
|
|
else
|
|
|
|
die("not yet");
|
2006-12-19 09:14:04 +01:00
|
|
|
for (b = bases; b; b = b->next) {
|
2007-01-09 08:22:31 +01:00
|
|
|
if (!hashcmp(commit->object.sha1, b->item->object.sha1)) {
|
2006-12-19 09:14:04 +01:00
|
|
|
ret = 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
free_commit_list(bases);
|
|
|
|
return ret;
|
|
|
|
}
|