git/walker.c

335 lines
7.3 KiB
C
Raw Normal View History

#include "cache.h"
#include "walker.h"
#include "commit.h"
#include "tree.h"
#include "tree-walk.h"
#include "tag.h"
#include "blob.h"
#include "refs.h"
static unsigned char current_commit_sha1[20];
void walker_say(struct walker *walker, const char *fmt, ...)
{
if (walker->get_verbosely) {
va_list ap;
va_start(ap, fmt);
vfprintf(stderr, fmt, ap);
va_end(ap);
}
}
static void report_missing(const struct object *obj)
{
fprintf(stderr, "Cannot obtain needed %s %s\n",
obj->type ? typename(obj->type): "object",
oid_to_hex(&obj->oid));
if (!is_null_sha1(current_commit_sha1))
fprintf(stderr, "while processing commit %s.\n",
sha1_to_hex(current_commit_sha1));
}
static int process(struct walker *walker, struct object *obj);
static int process_tree(struct walker *walker, struct tree *tree)
{
struct tree_desc desc;
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-31 00:45:45 +08:00
struct name_entry entry;
if (parse_tree(tree))
return -1;
init_tree_desc(&desc, tree->buffer, tree->size);
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-31 00:45:45 +08:00
while (tree_entry(&desc, &entry)) {
struct object *obj = NULL;
/* submodule commits are not stored in the superproject */
if (S_ISGITLINK(entry.mode))
continue;
tree_entry(): new tree-walking helper function This adds a "tree_entry()" function that combines the common operation of doing a "tree_entry_extract()" + "update_tree_entry()". It also has a simplified calling convention, designed for simple loops that traverse over a whole tree: the arguments are pointers to the tree descriptor and a name_entry structure to fill in, and it returns a boolean "true" if there was an entry left to be gotten in the tree. This allows tree traversal with struct tree_desc desc; struct name_entry entry; desc.buf = tree->buffer; desc.size = tree->size; while (tree_entry(&desc, &entry) { ... use "entry.{path, sha1, mode, pathlen}" ... } which is not only shorter than writing it out in full, it's hopefully less error prone too. [ It's actually a tad faster too - we don't need to recalculate the entry pathlength in both extract and update, but need to do it only once. Also, some callers can avoid doing a "strlen()" on the result, since it's returned as part of the name_entry structure. However, by now we're talking just 1% speedup on "git-rev-list --objects --all", and we're definitely at the point where tree walking is no longer the issue any more. ] NOTE! Not everybody wants to use this new helper function, since some of the tree walkers very much on purpose do the descriptor update separately from the entry extraction. So the "extract + update" sequence still remains as the core sequence, this is just a simplified interface. We should probably add a silly two-line inline helper function for initializing the descriptor from the "struct tree" too, just to cut down on the noise from that common "desc" initializer. Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-05-31 00:45:45 +08:00
if (S_ISDIR(entry.mode)) {
struct tree *tree = lookup_tree(entry.oid);
if (tree)
obj = &tree->object;
}
else {
struct blob *blob = lookup_blob(entry.oid);
if (blob)
obj = &blob->object;
}
if (!obj || process(walker, obj))
return -1;
}
free_tree_buffer(tree);
return 0;
}
/* Remember to update object flag allocation in object.h */
#define COMPLETE (1U << 0)
#define SEEN (1U << 1)
#define TO_SCAN (1U << 2)
static struct commit_list *complete = NULL;
static int process_commit(struct walker *walker, struct commit *commit)
{
if (parse_commit(commit))
return -1;
while (complete && complete->item->date >= commit->date) {
pop_most_recent_commit(&complete, COMPLETE);
}
if (commit->object.flags & COMPLETE)
return 0;
hashcpy(current_commit_sha1, commit->object.oid.hash);
walker_say(walker, "walk %s\n", oid_to_hex(&commit->object.oid));
if (walker->get_tree) {
if (process(walker, &commit->tree->object))
return -1;
if (!walker->get_all)
walker->get_tree = 0;
}
if (walker->get_history) {
struct commit_list *parents = commit->parents;
for (; parents; parents = parents->next) {
if (process(walker, &parents->item->object))
return -1;
}
}
return 0;
}
static int process_tag(struct walker *walker, struct tag *tag)
{
if (parse_tag(tag))
return -1;
return process(walker, tag->tagged);
}
static struct object_list *process_queue = NULL;
static struct object_list **process_queue_end = &process_queue;
static int process_object(struct walker *walker, struct object *obj)
{
if (obj->type == OBJ_COMMIT) {
if (process_commit(walker, (struct commit *)obj))
return -1;
return 0;
}
if (obj->type == OBJ_TREE) {
if (process_tree(walker, (struct tree *)obj))
return -1;
return 0;
}
if (obj->type == OBJ_BLOB) {
return 0;
}
if (obj->type == OBJ_TAG) {
if (process_tag(walker, (struct tag *)obj))
return -1;
return 0;
}
return error("Unable to determine requirements "
"of type %s for %s",
typename(obj->type), oid_to_hex(&obj->oid));
}
static int process(struct walker *walker, struct object *obj)
{
if (obj->flags & SEEN)
return 0;
obj->flags |= SEEN;
if (has_object_file(&obj->oid)) {
/* We already have it, so we should scan it now. */
obj->flags |= TO_SCAN;
}
else {
if (obj->flags & COMPLETE)
return 0;
walker->prefetch(walker, obj->oid.hash);
}
object_list_insert(obj, process_queue_end);
process_queue_end = &(*process_queue_end)->next;
return 0;
}
static int loop(struct walker *walker)
{
struct object_list *elem;
while (process_queue) {
struct object *obj = process_queue->item;
elem = process_queue;
process_queue = elem->next;
free(elem);
if (!process_queue)
process_queue_end = &process_queue;
/* If we are not scanning this object, we placed it in
* the queue because we needed to fetch it first.
*/
if (! (obj->flags & TO_SCAN)) {
if (walker->fetch(walker, obj->oid.hash)) {
report_missing(obj);
return -1;
}
}
if (!obj->type)
parse_object(&obj->oid);
if (process_object(walker, obj))
return -1;
}
return 0;
}
static int interpret_target(struct walker *walker, char *target, unsigned char *sha1)
{
if (!get_sha1_hex(target, sha1))
return 0;
if (!check_refname_format(target, 0)) {
struct ref *ref = alloc_ref(target);
if (!walker->fetch_ref(walker, ref)) {
hashcpy(sha1, ref->old_oid.hash);
free(ref);
return 0;
}
free(ref);
}
return -1;
}
static int mark_complete(const char *path, const struct object_id *oid,
int flag, void *cb_data)
{
Convert lookup_commit* to struct object_id Convert lookup_commit, lookup_commit_or_die, lookup_commit_reference, and lookup_commit_reference_gently to take struct object_id arguments. Introduce a temporary in parse_object buffer in order to convert this function. This is required since in order to convert parse_object and parse_object_buffer, lookup_commit_reference_gently and lookup_commit_or_die would need to be converted. Not introducing a temporary would therefore require that lookup_commit_or_die take a struct object_id *, but lookup_commit would take unsigned char *, leaving a confusing and hard-to-use interface. parse_object_buffer will lose this temporary in a later patch. This commit was created with manual changes to commit.c, commit.h, and object.c, plus the following semantic patch: @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1.hash, E2) + lookup_commit_reference_gently(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_reference_gently(E1->hash, E2) + lookup_commit_reference_gently(E1, E2) @@ expression E1; @@ - lookup_commit_reference(E1.hash) + lookup_commit_reference(&E1) @@ expression E1; @@ - lookup_commit_reference(E1->hash) + lookup_commit_reference(E1) @@ expression E1; @@ - lookup_commit(E1.hash) + lookup_commit(&E1) @@ expression E1; @@ - lookup_commit(E1->hash) + lookup_commit(E1) @@ expression E1, E2; @@ - lookup_commit_or_die(E1.hash, E2) + lookup_commit_or_die(&E1, E2) @@ expression E1, E2; @@ - lookup_commit_or_die(E1->hash, E2) + lookup_commit_or_die(E1, E2) Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-05-07 06:10:10 +08:00
struct commit *commit = lookup_commit_reference_gently(oid, 1);
if (commit) {
commit->object.flags |= COMPLETE;
commit_list_insert(commit, &complete);
}
return 0;
}
int walker_targets_stdin(char ***target, const char ***write_ref)
{
int targets = 0, targets_alloc = 0;
struct strbuf buf = STRBUF_INIT;
*target = NULL; *write_ref = NULL;
while (1) {
char *rf_one = NULL;
char *tg_one;
if (strbuf_getline_lf(&buf, stdin) == EOF)
break;
tg_one = buf.buf;
rf_one = strchr(tg_one, '\t');
if (rf_one)
*rf_one++ = 0;
if (targets >= targets_alloc) {
targets_alloc = targets_alloc ? targets_alloc * 2 : 64;
REALLOC_ARRAY(*target, targets_alloc);
REALLOC_ARRAY(*write_ref, targets_alloc);
}
(*target)[targets] = xstrdup(tg_one);
(*write_ref)[targets] = xstrdup_or_null(rf_one);
targets++;
}
strbuf_release(&buf);
return targets;
}
void walker_targets_free(int targets, char **target, const char **write_ref)
{
while (targets--) {
free(target[targets]);
if (write_ref)
free((char *) write_ref[targets]);
}
}
int walker_fetch(struct walker *walker, int targets, char **target,
const char **write_ref, const char *write_ref_log_details)
{
struct strbuf refname = STRBUF_INIT;
struct strbuf err = STRBUF_INIT;
struct ref_transaction *transaction = NULL;
unsigned char *sha1 = xmalloc(targets * 20);
char *msg = NULL;
int i, ret = -1;
save_commit_buffer = 0;
if (write_ref) {
transaction = ref_transaction_begin(&err);
if (!transaction) {
error("%s", err.buf);
goto done;
}
}
if (!walker->get_recover) {
for_each_ref(mark_complete, NULL);
commit_list_sort_by_date(&complete);
}
for (i = 0; i < targets; i++) {
if (interpret_target(walker, target[i], &sha1[20 * i])) {
error("Could not interpret response from server '%s' as something to pull", target[i]);
goto done;
}
if (process(walker, lookup_unknown_object(&sha1[20 * i])))
goto done;
}
if (loop(walker))
goto done;
if (!write_ref) {
ret = 0;
goto done;
}
if (write_ref_log_details) {
msg = xstrfmt("fetch from %s", write_ref_log_details);
} else {
msg = NULL;
}
for (i = 0; i < targets; i++) {
if (!write_ref[i])
continue;
strbuf_reset(&refname);
strbuf_addf(&refname, "refs/%s", write_ref[i]);
if (ref_transaction_update(transaction, refname.buf,
&sha1[20 * i], NULL, 0,
msg ? msg : "fetch (unknown)",
&err)) {
error("%s", err.buf);
goto done;
}
}
if (ref_transaction_commit(transaction, &err)) {
error("%s", err.buf);
goto done;
}
ret = 0;
done:
ref_transaction_free(transaction);
free(msg);
free(sha1);
strbuf_release(&err);
strbuf_release(&refname);
return ret;
}
void walker_free(struct walker *walker)
{
walker->cleanup(walker);
free(walker);
}