git-commit-vandalism/tree.c

229 lines
5.0 KiB
C
Raw Normal View History

#include "cache.h"
#include "tree.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree-walk.h"
const char *tree_type = "tree";
static int read_one_entry(const unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage)
{
int len;
unsigned int size;
struct cache_entry *ce;
if (S_ISDIR(mode))
return READ_TREE_RECURSIVE;
len = strlen(pathname);
size = cache_entry_size(baselen + len);
ce = xcalloc(1, size);
ce->ce_mode = create_ce_mode(mode);
ce->ce_flags = create_ce_flags(baselen + len, stage);
memcpy(ce->name, base, baselen);
memcpy(ce->name + baselen, pathname, len+1);
hashcpy(ce->sha1, sha1);
return add_cache_entry(ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK);
}
static int match_tree_entry(const char *base, int baselen, const char *path, unsigned int mode, const char **paths)
{
const char *match;
int pathlen;
if (!paths)
return 1;
pathlen = strlen(path);
while ((match = *paths++) != NULL) {
int matchlen = strlen(match);
if (baselen >= matchlen) {
/* If it doesn't match, move along... */
if (strncmp(base, match, matchlen))
continue;
/* The base is a subdirectory of a path which was specified. */
return 1;
}
/* Does the base match? */
if (strncmp(base, match, baselen))
continue;
match += baselen;
matchlen -= baselen;
if (pathlen > matchlen)
continue;
if (matchlen > pathlen) {
if (match[pathlen] != '/')
continue;
if (!S_ISDIR(mode))
continue;
}
if (strncmp(path, match, pathlen))
continue;
return 1;
}
return 0;
}
int read_tree_recursive(struct tree *tree,
const char *base, int baselen,
int stage, const char **match,
read_tree_fn_t fn)
{
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>
2006-05-30 18:45:45 +02:00
struct name_entry entry;
if (parse_tree(tree))
return -1;
desc.buf = tree->buffer;
desc.size = 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>
2006-05-30 18:45:45 +02:00
while (tree_entry(&desc, &entry)) {
if (!match_tree_entry(base, baselen, entry.path, entry.mode, match))
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>
2006-05-30 18:45:45 +02:00
switch (fn(entry.sha1, base, baselen, entry.path, entry.mode, stage)) {
case 0:
continue;
case READ_TREE_RECURSIVE:
break;;
default:
return -1;
}
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>
2006-05-30 18:45:45 +02:00
if (S_ISDIR(entry.mode)) {
int retval;
char *newbase;
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>
2006-05-30 18:45:45 +02:00
newbase = xmalloc(baselen + 1 + entry.pathlen);
memcpy(newbase, base, baselen);
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>
2006-05-30 18:45:45 +02:00
memcpy(newbase + baselen, entry.path, entry.pathlen);
newbase[baselen + entry.pathlen] = '/';
retval = read_tree_recursive(lookup_tree(entry.sha1),
newbase,
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>
2006-05-30 18:45:45 +02:00
baselen + entry.pathlen + 1,
stage, match, fn);
free(newbase);
if (retval)
return -1;
continue;
}
}
return 0;
}
int read_tree(struct tree *tree, int stage, const char **match)
{
return read_tree_recursive(tree, "", 0, stage, match, read_one_entry);
}
struct tree *lookup_tree(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
if (!obj) {
Add specialized object allocator This creates a simple specialized object allocator for basic objects. This avoids wasting space with malloc overhead (metadata and extra alignment), since the specialized allocator knows the alignment, and that objects, once allocated, are never freed. It also allows us to track some basic statistics about object allocations. For example, for the mozilla import, it shows object usage as follows: blobs: 627629 (14710 kB) trees: 1119035 (34969 kB) commits: 196423 (8440 kB) tags: 1336 (46 kB) and the simpler allocator shaves off about 2.5% off the memory footprint off a "git-rev-list --all --objects", and is a bit faster too. [ Side note: this concludes the series of "save memory in object storage". The thing is, there simply isn't much more to be saved on the objects. Doing "git-rev-list --all --objects" on the mozilla archive has a final total RSS of 131498 pages for me: that's about 513MB. Of that, the object overhead is now just 56MB, the rest is going somewhere else (put another way: the fact that this patch shaves off 2.5% of the total memory overhead, considering that objects are now not much more than 10% of the total shows how big the wasted space really was: this makes object allocations much more memory- and time-efficient). I haven't looked at where the rest is, but I suspect the bulk of it is just the pack-file loading. It may be that we should pack the tree objects separately from the blob objects: for git-rev-list --objects, we don't actually ever need to even look at the blobs, but since trees and blobs are interspersed in the pack-file, we end up not being dense in the tree accesses, so we end up looking at more pages than we strictly need to. So with a 535MB pack-file, it's entirely possible - even likely - that most of the remaining RSS is just the mmap of the pack-file itself. We don't need to map in _all_ of it, but we do end up mapping a fair amount. ] Signed-off-by: Linus Torvalds <torvalds@osdl.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2006-06-19 19:44:15 +02:00
struct tree *ret = alloc_tree_node();
created_object(sha1, &ret->object);
ret->object.type = OBJ_TREE;
return ret;
}
if (!obj->type)
obj->type = OBJ_TREE;
if (obj->type != OBJ_TREE) {
error("Object %s is a %s, not a tree",
sha1_to_hex(sha1), typename(obj->type));
return NULL;
}
return (struct tree *) obj;
}
static void track_tree_refs(struct tree *item)
{
int n_refs = 0, i;
struct object_refs *refs;
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>
2006-05-30 18:45:45 +02:00
struct name_entry entry;
/* Count how many entries there are.. */
desc.buf = item->buffer;
desc.size = item->size;
while (desc.size) {
n_refs++;
update_tree_entry(&desc);
}
/* Allocate object refs and walk it again.. */
i = 0;
refs = alloc_object_refs(n_refs);
desc.buf = item->buffer;
desc.size = item->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>
2006-05-30 18:45:45 +02:00
while (tree_entry(&desc, &entry)) {
struct object *obj;
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>
2006-05-30 18:45:45 +02:00
if (S_ISDIR(entry.mode))
obj = &lookup_tree(entry.sha1)->object;
else
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>
2006-05-30 18:45:45 +02:00
obj = &lookup_blob(entry.sha1)->object;
refs->ref[i++] = obj;
}
set_object_refs(&item->object, refs);
}
int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size)
{
if (item->object.parsed)
return 0;
item->object.parsed = 1;
item->buffer = buffer;
item->size = size;
if (track_object_refs)
track_tree_refs(item);
return 0;
}
int parse_tree(struct tree *item)
{
char type[20];
void *buffer;
unsigned long size;
if (item->object.parsed)
return 0;
buffer = read_sha1_file(item->object.sha1, type, &size);
if (!buffer)
return error("Could not read %s",
sha1_to_hex(item->object.sha1));
if (strcmp(type, tree_type)) {
free(buffer);
return error("Object %s not a tree",
sha1_to_hex(item->object.sha1));
}
return parse_tree_buffer(item, buffer, size);
}
struct tree *parse_tree_indirect(const unsigned char *sha1)
{
struct object *obj = parse_object(sha1);
do {
if (!obj)
return NULL;
if (obj->type == OBJ_TREE)
return (struct tree *) obj;
else if (obj->type == OBJ_COMMIT)
obj = &(((struct commit *) obj)->tree->object);
else if (obj->type == OBJ_TAG)
obj = ((struct tag *) obj)->tagged;
else
return NULL;
if (!obj->parsed)
parse_object(obj->sha1);
} while (1);
}