git/builtin-name-rev.c

280 lines
6.3 KiB
C
Raw Normal View History

#include "builtin.h"
#include "cache.h"
#include "commit.h"
#include "tag.h"
#include "refs.h"
#include "parse-options.h"
#define CUTOFF_DATE_SLOP 86400 /* one day */
typedef struct rev_name {
const char *tip_name;
int generation;
int distance;
} rev_name;
static long cutoff = LONG_MAX;
/* How many generations are maximally preferred over _one_ merge traversal? */
#define MERGE_TRAVERSAL_WEIGHT 65535
static void name_rev(struct commit *commit,
const char *tip_name, int generation, int distance,
int deref)
{
struct rev_name *name = (struct rev_name *)commit->util;
struct commit_list *parents;
int parent_number = 1;
if (!commit->object.parsed)
parse_commit(commit);
if (commit->date < cutoff)
return;
if (deref) {
char *new_name = xmalloc(strlen(tip_name)+3);
strcpy(new_name, tip_name);
strcat(new_name, "^0");
tip_name = new_name;
if (generation)
die("generation: %d, but deref?", generation);
}
if (name == NULL) {
name = xmalloc(sizeof(rev_name));
commit->util = name;
goto copy_data;
} else if (name->distance > distance) {
copy_data:
name->tip_name = tip_name;
name->generation = generation;
name->distance = distance;
} else
return;
for (parents = commit->parents;
parents;
parents = parents->next, parent_number++) {
if (parent_number > 1) {
int len = strlen(tip_name);
char *new_name = xmalloc(len +
1 + decimal_length(generation) + /* ~<n> */
1 + 2 + /* ^NN */
1);
if (len > 2 && !strcmp(tip_name + len - 2, "^0"))
len -= 2;
if (generation > 0)
sprintf(new_name, "%.*s~%d^%d", len, tip_name,
generation, parent_number);
else
sprintf(new_name, "%.*s^%d", len, tip_name,
parent_number);
name_rev(parents->item, new_name, 0,
distance + MERGE_TRAVERSAL_WEIGHT, 0);
} else {
name_rev(parents->item, tip_name, generation + 1,
distance + 1, 0);
}
}
}
struct name_ref_data {
int tags_only;
int name_only;
const char *ref_filter;
};
static int name_ref(const char *path, const unsigned char *sha1, int flags, void *cb_data)
{
struct object *o = parse_object(sha1);
struct name_ref_data *data = cb_data;
int deref = 0;
if (data->tags_only && prefixcmp(path, "refs/tags/"))
return 0;
if (data->ref_filter && fnmatch(data->ref_filter, path, 0))
return 0;
while (o && o->type == OBJ_TAG) {
struct tag *t = (struct tag *) o;
if (!t->tagged)
break; /* broken repository */
o = parse_object(t->tagged->sha1);
deref = 1;
}
if (o && o->type == OBJ_COMMIT) {
struct commit *commit = (struct commit *)o;
if (!prefixcmp(path, "refs/heads/"))
path = path + 11;
else if (data->tags_only
&& data->name_only
&& !prefixcmp(path, "refs/tags/"))
path = path + 10;
else if (!prefixcmp(path, "refs/"))
path = path + 5;
name_rev(commit, xstrdup(path), 0, 0, deref);
}
return 0;
}
/* returns a static buffer */
static const char* get_rev_name(struct object *o)
{
static char buffer[1024];
struct rev_name *n;
struct commit *c;
if (o->type != OBJ_COMMIT)
return "undefined";
c = (struct commit *) o;
n = c->util;
if (!n)
return "undefined";
if (!n->generation)
return n->tip_name;
else {
int len = strlen(n->tip_name);
if (len > 2 && !strcmp(n->tip_name + len - 2, "^0"))
len -= 2;
snprintf(buffer, sizeof(buffer), "%.*s~%d", len, n->tip_name,
n->generation);
return buffer;
}
}
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 08:42:35 +08:00
static char const * const name_rev_usage[] = {
"git-name-rev [options] ( --all | --stdin | <commit>... )",
NULL
};
int cmd_name_rev(int argc, const char **argv, const char *prefix)
{
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 08:42:35 +08:00
struct object_array revs = { 0, 0, NULL };
int all = 0, transform_stdin = 0;
struct name_ref_data data = { 0, 0, NULL };
struct option opts[] = {
OPT_BOOLEAN(0, "name-only", &data.name_only, "print only names (no SHA-1)"),
OPT_BOOLEAN(0, "tags", &data.tags_only, "only use tags to name the commits"),
OPT_STRING(0, "refs", &data.ref_filter, "pattern",
"only use refs matching <pattern>"),
OPT_GROUP(""),
OPT_BOOLEAN(0, "all", &all, "list all commits reachable from all refs"),
OPT_BOOLEAN(0, "stdin", &transform_stdin, "read from stdin"),
OPT_END(),
};
git_config(git_default_config);
argc = parse_options(argc, argv, opts, name_rev_usage, 0);
if (!!all + !!transform_stdin + !!argc > 1) {
error("Specify either a list, or --all, not both!");
usage_with_options(name_rev_usage, opts);
}
if (all || transform_stdin)
cutoff = 0;
for (; argc; argc--, argv++) {
unsigned char sha1[20];
struct object *o;
struct commit *commit;
if (get_sha1(*argv, sha1)) {
fprintf(stderr, "Could not get sha1 for %s. Skipping.\n",
*argv);
continue;
}
o = deref_tag(parse_object(sha1), *argv, 0);
if (!o || o->type != OBJ_COMMIT) {
fprintf(stderr, "Could not get commit for %s. Skipping.\n",
*argv);
continue;
}
commit = (struct commit *)o;
if (cutoff > commit->date)
cutoff = commit->date;
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 08:42:35 +08:00
add_object_array((struct object *)commit, *argv, &revs);
}
if (cutoff)
cutoff = cutoff - CUTOFF_DATE_SLOP;
for_each_ref(name_ref, &data);
if (transform_stdin) {
char buffer[2048];
char *p, *p_start;
while (!feof(stdin)) {
int forty = 0;
p = fgets(buffer, sizeof(buffer), stdin);
if (!p)
break;
for (p_start = p; *p; p++) {
#define ishex(x) (isdigit((x)) || ((x) >= 'a' && (x) <= 'f'))
if (!ishex(*p))
forty = 0;
else if (++forty == 40 &&
!ishex(*(p+1))) {
unsigned char sha1[40];
const char *name = "undefined";
char c = *(p+1);
forty = 0;
*(p+1) = 0;
if (!get_sha1(p - 39, sha1)) {
struct object *o =
lookup_object(sha1);
if (o)
name = get_rev_name(o);
}
*(p+1) = c;
if (!strcmp(name, "undefined"))
continue;
fwrite(p_start, p - p_start + 1, 1,
stdout);
printf(" (%s)", name);
p_start = p + 1;
}
}
/* flush */
if (p_start != p)
fwrite(p_start, p - p_start, 1, stdout);
}
} else if (all) {
int i, max;
max = get_max_object_index();
for (i = 0; i < max; i++) {
struct object * obj = get_indexed_object(i);
if (!obj)
continue;
if (!data.name_only)
printf("%s ", sha1_to_hex(obj->sha1));
printf("%s\n", get_rev_name(obj));
}
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 08:42:35 +08:00
} else {
int i;
for (i = 0; i < revs.nr; i++) {
if (!data.name_only)
printf("%s ", revs.objects[i].name);
printf("%s\n", get_rev_name(revs.objects[i].item));
}
Add "named object array" concept We've had this notion of a "object_list" for a long time, which eventually grew a "name" member because some users (notably git-rev-list) wanted to name each object as it is generated. That object_list is great for some things, but it isn't all that wonderful for others, and the "name" member is generally not used by everybody. This patch splits the users of the object_list array up into two: the traditional list users, who want the list-like format, and who don't actually use or want the name. And another class of users that really used the list as an extensible array, and generally wanted to name the objects. The patch is fairly straightforward, but it's also biggish. Most of it really just cleans things up: switching the revision parsing and listing over to the array makes things like the builtin-diff usage much simpler (we now see exactly how many members the array has, and we don't get the objects reversed from the order they were on the command line). One of the main reasons for doing this at all is that the malloc overhead of the simple object list was actually pretty high, and the array is just a lot denser. So this patch brings down memory usage by git-rev-list by just under 3% (on top of all the other memory use optimizations) on the mozilla archive. It does add more lines than it removes, and more importantly, it adds a whole new infrastructure for maintaining lists of objects, but on the other hand, the new dynamic array code is pretty obvious. The change to builtin-diff-tree.c shows a fairly good example of why an array interface is sometimes more natural, and just much simpler for everybody. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-20 08:42:35 +08:00
}
return 0;
}