git/object.c

291 lines
6.1 KiB
C
Raw Normal View History

#include "cache.h"
#include "object.h"
#include "blob.h"
#include "tree.h"
#include "commit.h"
#include "tag.h"
static struct object **obj_hash;
static int nr_objs, obj_hash_size;
unsigned int get_max_object_index(void)
{
return obj_hash_size;
}
struct object *get_indexed_object(unsigned int idx)
{
return obj_hash[idx];
}
static const char *object_type_strings[] = {
NULL, /* OBJ_NONE = 0 */
"commit", /* OBJ_COMMIT = 1 */
"tree", /* OBJ_TREE = 2 */
"blob", /* OBJ_BLOB = 3 */
"tag", /* OBJ_TAG = 4 */
};
const char *typename(unsigned int type)
{
if (type >= ARRAY_SIZE(object_type_strings))
return NULL;
return object_type_strings[type];
}
int type_from_string(const char *str)
{
int i;
for (i = 1; i < ARRAY_SIZE(object_type_strings); i++)
if (!strcmp(str, object_type_strings[i]))
return i;
die("invalid object type \"%s\"", str);
}
static unsigned int hash_obj(struct object *obj, unsigned int n)
{
unsigned int hash;
memcpy(&hash, obj->sha1, sizeof(unsigned int));
return hash % n;
}
static void insert_obj_hash(struct object *obj, struct object **hash, unsigned int size)
{
int j = hash_obj(obj, size);
while (hash[j]) {
j++;
if (j >= size)
j = 0;
}
hash[j] = obj;
}
static int hashtable_index(const unsigned char *sha1)
{
unsigned int i;
memcpy(&i, sha1, sizeof(unsigned int));
return (int)(i % obj_hash_size);
}
struct object *lookup_object(const unsigned char *sha1)
{
int i;
struct object *obj;
if (!obj_hash)
return NULL;
i = hashtable_index(sha1);
while ((obj = obj_hash[i]) != NULL) {
if (!hashcmp(sha1, obj->sha1))
break;
i++;
if (i == obj_hash_size)
i = 0;
}
return obj;
}
static void grow_object_hash(void)
{
int i;
int new_hash_size = obj_hash_size < 32 ? 32 : 2 * obj_hash_size;
struct object **new_hash;
new_hash = xcalloc(new_hash_size, sizeof(struct object *));
for (i = 0; i < obj_hash_size; i++) {
struct object *obj = obj_hash[i];
if (!obj)
continue;
insert_obj_hash(obj, new_hash, new_hash_size);
}
free(obj_hash);
obj_hash = new_hash;
obj_hash_size = new_hash_size;
}
void *create_object(const unsigned char *sha1, int type, void *o)
{
struct object *obj = o;
obj->parsed = 0;
obj->used = 0;
obj->type = type;
obj->flags = 0;
hashcpy(obj->sha1, sha1);
if (obj_hash_size - 1 <= nr_objs * 2)
grow_object_hash();
insert_obj_hash(obj, obj_hash, obj_hash_size);
nr_objs++;
return obj;
}
struct object *lookup_unknown_object(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
if (!obj)
obj = create_object(sha1, OBJ_NONE, alloc_object_node());
return obj;
}
struct object *parse_object_buffer(const unsigned char *sha1, enum object_type type, unsigned long size, void *buffer, int *eaten_p)
{
struct object *obj;
int eaten = 0;
obj = NULL;
if (type == OBJ_BLOB) {
struct blob *blob = lookup_blob(sha1);
if (blob) {
if (parse_blob_buffer(blob, buffer, size))
return NULL;
obj = &blob->object;
}
} else if (type == OBJ_TREE) {
struct tree *tree = lookup_tree(sha1);
if (tree) {
obj = &tree->object;
if (!tree->object.parsed) {
if (parse_tree_buffer(tree, buffer, size))
return NULL;
eaten = 1;
}
}
} else if (type == OBJ_COMMIT) {
struct commit *commit = lookup_commit(sha1);
if (commit) {
if (parse_commit_buffer(commit, buffer, size))
return NULL;
if (!commit->buffer) {
commit->buffer = buffer;
eaten = 1;
}
obj = &commit->object;
}
} else if (type == OBJ_TAG) {
struct tag *tag = lookup_tag(sha1);
if (tag) {
if (parse_tag_buffer(tag, buffer, size))
return NULL;
obj = &tag->object;
}
} else {
warning("object %s has unknown type id %d\n", sha1_to_hex(sha1), type);
obj = NULL;
}
if (obj && obj->type == OBJ_NONE)
obj->type = type;
*eaten_p = eaten;
return obj;
}
struct object *parse_object(const unsigned char *sha1)
{
unsigned long size;
enum object_type type;
int eaten;
void *buffer = read_sha1_file(sha1, &type, &size);
if (buffer) {
struct object *obj;
if (check_sha1_signature(sha1, buffer, size, typename(type)) < 0) {
free(buffer);
error("sha1 mismatch %s\n", sha1_to_hex(sha1));
return NULL;
}
obj = parse_object_buffer(sha1, type, size, buffer, &eaten);
if (!eaten)
free(buffer);
return obj;
}
return NULL;
}
struct object_list *object_list_insert(struct object *item,
struct object_list **list_p)
{
struct object_list *new_list = xmalloc(sizeof(struct object_list));
new_list->item = item;
new_list->next = *list_p;
*list_p = new_list;
return new_list;
}
void object_list_append(struct object *item,
struct object_list **list_p)
{
while (*list_p) {
list_p = &((*list_p)->next);
}
*list_p = xmalloc(sizeof(struct object_list));
(*list_p)->next = NULL;
(*list_p)->item = item;
}
unsigned object_list_length(struct object_list *list)
{
unsigned ret = 0;
while (list) {
list = list->next;
ret++;
}
return ret;
}
int object_list_contains(struct object_list *list, struct object *obj)
{
while (list) {
if (list->item == obj)
return 1;
list = list->next;
}
return 0;
}
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
void add_object_array(struct object *obj, const char *name, struct object_array *array)
{
add_object_array_with_mode(obj, name, array, S_IFINVALID);
}
void add_object_array_with_mode(struct object *obj, const char *name, struct object_array *array, unsigned mode)
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
{
unsigned nr = array->nr;
unsigned alloc = array->alloc;
struct object_array_entry *objects = array->objects;
if (nr >= alloc) {
alloc = (alloc + 32) * 2;
objects = xrealloc(objects, alloc * sizeof(*objects));
array->alloc = alloc;
array->objects = objects;
}
objects[nr].item = obj;
objects[nr].name = name;
objects[nr].mode = mode;
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
array->nr = ++nr;
}
void object_array_remove_duplicates(struct object_array *array)
{
int ref, src, dst;
struct object_array_entry *objects = array->objects;
for (ref = 0; ref < array->nr - 1; ref++) {
for (src = ref + 1, dst = src;
src < array->nr;
src++) {
if (!strcmp(objects[ref].name, objects[src].name))
continue;
if (src != dst)
objects[dst] = objects[src];
dst++;
}
array->nr = dst;
}
}