git/tree-walk.c

213 lines
4.3 KiB
C
Raw Normal View History

#include "cache.h"
#include "tree-walk.h"
#include "tree.h"
void *fill_tree_descriptor(struct tree_desc *desc, const unsigned char *sha1)
{
unsigned long size = 0;
void *buf = NULL;
if (sha1) {
buf = read_object_with_reference(sha1, tree_type, &size, NULL);
if (!buf)
die("unable to read tree %s", sha1_to_hex(sha1));
}
desc->size = size;
desc->buf = buf;
return buf;
}
static int entry_compare(struct name_entry *a, struct name_entry *b)
{
return base_name_compare(
a->path, a->pathlen, a->mode,
b->path, b->pathlen, b->mode);
}
static void entry_clear(struct name_entry *a)
{
memset(a, 0, sizeof(*a));
}
static void entry_extract(struct tree_desc *t, struct name_entry *a)
{
a->sha1 = tree_entry_extract(t, &a->path, &a->mode);
a->pathlen = strlen(a->path);
}
void update_tree_entry(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 16:45:45 +00:00
const void *buf = desc->buf;
unsigned long size = desc->size;
int len = strlen(buf) + 1 + 20;
if (size < len)
die("corrupt tree file");
desc->buf = (char *) buf + len;
desc->size = size - len;
}
static const char *get_mode(const char *str, unsigned int *modep)
{
unsigned char c;
unsigned int mode = 0;
while ((c = *str++) != ' ') {
if (c < '0' || c > '7')
return NULL;
mode = (mode << 3) + (c - '0');
}
*modep = mode;
return str;
}
const unsigned char *tree_entry_extract(struct tree_desc *desc, const char **pathp, unsigned int *modep)
{
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 16:45:45 +00:00
const void *tree = desc->buf;
unsigned long size = desc->size;
int len = strlen(tree)+1;
const unsigned char *sha1 = (unsigned char *) tree + len;
const char *path;
unsigned int mode;
path = get_mode(tree, &mode);
if (!path || size < len + 20)
die("corrupt tree file");
*pathp = path;
*modep = canon_mode(mode);
return sha1;
}
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 16:45:45 +00:00
int tree_entry(struct tree_desc *desc, struct name_entry *entry)
{
const void *tree = desc->buf;
const char *path;
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 16:45:45 +00:00
unsigned long len, size = desc->size;
if (!size)
return 0;
path = get_mode(tree, &entry->mode);
if (!path)
die("corrupt tree file");
entry->path = path;
len = strlen(path);
entry->pathlen = len;
path += len + 1;
entry->sha1 = (const unsigned char *) path;
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 16:45:45 +00:00
path += 20;
len = path - (char *) tree;
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 16:45:45 +00:00
if (len > size)
die("corrupt tree file");
desc->buf = path;
desc->size = size - len;
return 1;
}
void traverse_trees(int n, struct tree_desc *t, const char *base, traverse_callback_t callback)
{
struct name_entry *entry = xmalloc(n*sizeof(*entry));
for (;;) {
struct name_entry entry[3];
unsigned long mask = 0;
int i, last;
last = -1;
for (i = 0; i < n; i++) {
if (!t[i].size)
continue;
entry_extract(t+i, entry+i);
if (last >= 0) {
int cmp = entry_compare(entry+i, entry+last);
/*
* Is the new name bigger than the old one?
* Ignore it
*/
if (cmp > 0)
continue;
/*
* Is the new name smaller than the old one?
* Ignore all old ones
*/
if (cmp < 0)
mask = 0;
}
mask |= 1ul << i;
last = i;
}
if (!mask)
break;
/*
* Update the tree entries we've walked, and clear
* all the unused name-entries.
*/
for (i = 0; i < n; i++) {
if (mask & (1ul << i)) {
update_tree_entry(t+i);
continue;
}
entry_clear(entry + i);
}
callback(n, mask, entry, base);
}
free(entry);
}
static int find_tree_entry(struct tree_desc *t, const char *name, unsigned char *result, unsigned *mode)
{
int namelen = strlen(name);
while (t->size) {
const char *entry;
const unsigned char *sha1;
int entrylen, cmp;
sha1 = tree_entry_extract(t, &entry, mode);
update_tree_entry(t);
entrylen = strlen(entry);
if (entrylen > namelen)
continue;
cmp = memcmp(name, entry, entrylen);
if (cmp > 0)
continue;
if (cmp < 0)
break;
if (entrylen == namelen) {
memcpy(result, sha1, 20);
return 0;
}
if (name[entrylen] != '/')
continue;
if (!S_ISDIR(*mode))
break;
if (++entrylen == namelen) {
memcpy(result, sha1, 20);
return 0;
}
return get_tree_entry(sha1, name + entrylen, result, mode);
}
return -1;
}
int get_tree_entry(const unsigned char *tree_sha1, const char *name, unsigned char *sha1, unsigned *mode)
{
int retval;
void *tree;
struct tree_desc t;
tree = read_object_with_reference(tree_sha1, tree_type, &t.size, NULL);
if (!tree)
return -1;
t.buf = tree;
retval = find_tree_entry(&t, name, sha1, mode);
free(tree);
return retval;
}