1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-10-31 14:27:54 +01:00
git/tree.c

254 lines
6.1 KiB
C
Raw Normal View History

#include "cache.h"
#include "cache-tree.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_opt(const unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage, int opt)
{
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, opt);
}
static int read_one_entry(const unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage, void *context)
{
return read_one_entry_opt(sha1, base, baselen, pathname, mode, stage,
ADD_CACHE_OK_TO_ADD|ADD_CACHE_SKIP_DFCHECK);
}
/*
* This is used when the caller knows there is no existing entries at
* the stage that will conflict with the entry being added.
*/
static int read_one_entry_quick(const unsigned char *sha1, const char *base, int baselen, const char *pathname, unsigned mode, int stage, void *context)
{
return read_one_entry_opt(sha1, base, baselen, pathname, mode, stage,
ADD_CACHE_JUST_APPEND);
}
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, void *context)
{
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;
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>
2006-05-30 18:45:45 +02:00
while (tree_entry(&desc, &entry)) {
if (!match_tree_entry(base, baselen, entry.path, entry.mode, match))
continue;
switch (fn(entry.sha1, base, baselen, entry.path, entry.mode, stage, context)) {
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;
unsigned int pathlen = tree_entry_len(entry.path, entry.sha1);
newbase = xmalloc(baselen + 1 + pathlen);
memcpy(newbase, base, baselen);
memcpy(newbase + baselen, entry.path, pathlen);
newbase[baselen + pathlen] = '/';
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
retval = read_tree_recursive(lookup_tree(entry.sha1),
newbase,
baselen + pathlen + 1,
stage, match, fn, context);
free(newbase);
if (retval)
return -1;
continue;
}
}
return 0;
}
static int cmp_cache_name_compare(const void *a_, const void *b_)
{
const struct cache_entry *ce1, *ce2;
ce1 = *((const struct cache_entry **)a_);
ce2 = *((const struct cache_entry **)b_);
return cache_name_compare(ce1->name, ce1->ce_flags,
ce2->name, ce2->ce_flags);
}
int read_tree(struct tree *tree, int stage, const char **match)
{
read_tree_fn_t fn = NULL;
int i, err;
/*
* Currently the only existing callers of this function all
* call it with stage=1 and after making sure there is nothing
* at that stage; we could always use read_one_entry_quick().
*
* But when we decide to straighten out git-read-tree not to
* use unpack_trees() in some cases, this will probably start
* to matter.
*/
/*
* See if we have cache entry at the stage. If so,
* do it the original slow way, otherwise, append and then
* sort at the end.
*/
for (i = 0; !fn && i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
if (ce_stage(ce) == stage)
fn = read_one_entry;
}
if (!fn)
fn = read_one_entry_quick;
err = read_tree_recursive(tree, "", 0, stage, match, fn, NULL);
if (fn == read_one_entry || err)
return err;
/*
* Sort the cache entry -- we need to nuke the cache tree, though.
*/
cache_tree_free(&active_cache_tree);
qsort(active_cache, active_nr, sizeof(active_cache[0]),
cmp_cache_name_compare);
return 0;
}
struct tree *lookup_tree(const unsigned char *sha1)
{
struct object *obj = lookup_object(sha1);
if (!obj)
return create_object(sha1, OBJ_TREE, alloc_tree_node());
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;
}
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;
return 0;
}
int parse_tree(struct tree *item)
{
enum object_type type;
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 (type != OBJ_TREE) {
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);
}