git-commit-vandalism/tree.c

254 lines
6.2 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(stage);
ce->ce_namelen = baselen + len;
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, struct strbuf *base,
const char *pathname, unsigned mode, int stage,
void *context)
{
return read_one_entry_opt(sha1, base->buf, base->len, 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, struct strbuf *base,
const char *pathname, unsigned mode, int stage,
void *context)
{
return read_one_entry_opt(sha1, base->buf, base->len, pathname,
mode, stage,
ADD_CACHE_JUST_APPEND);
}
static int read_tree_1(struct tree *tree, struct strbuf *base,
int stage, const struct pathspec *pathspec,
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;
unsigned char sha1[20];
int len, oldlen = base->len;
enum interesting retval = entry_not_interesting;
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 (retval != all_entries_interesting) {
retval = tree_entry_interesting(&entry, base, 0, pathspec);
if (retval == all_entries_not_interesting)
break;
if (retval == entry_not_interesting)
continue;
}
switch (fn(entry.oid->hash, base,
entry.path, entry.mode, stage, context)) {
case 0:
continue;
case READ_TREE_RECURSIVE:
break;
default:
return -1;
}
if (S_ISDIR(entry.mode))
hashcpy(sha1, entry.oid->hash);
else if (S_ISGITLINK(entry.mode)) {
struct commit *commit;
commit = lookup_commit(entry.oid->hash);
if (!commit)
die("Commit %s in submodule path %s%s not found",
oid_to_hex(entry.oid),
base->buf, entry.path);
if (parse_commit(commit))
die("Invalid commit %s in submodule path %s%s",
oid_to_hex(entry.oid),
base->buf, entry.path);
hashcpy(sha1, commit->tree->object.oid.hash);
}
else
continue;
len = tree_entry_len(&entry);
strbuf_add(base, entry.path, len);
strbuf_addch(base, '/');
retval = read_tree_1(lookup_tree(sha1),
base, stage, pathspec,
fn, context);
strbuf_setlen(base, oldlen);
if (retval)
return -1;
}
return 0;
}
int read_tree_recursive(struct tree *tree,
const char *base, int baselen,
int stage, const struct pathspec *pathspec,
read_tree_fn_t fn, void *context)
{
struct strbuf sb = STRBUF_INIT;
int ret;
strbuf_add(&sb, base, baselen);
ret = read_tree_1(tree, &sb, stage, pathspec, fn, context);
strbuf_release(&sb);
return ret;
}
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_stage_compare(ce1->name, ce1->ce_namelen, ce_stage(ce1),
ce2->name, ce2->ce_namelen, ce_stage(ce2));
}
int read_tree(struct tree *tree, int stage, struct pathspec *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++) {
Convert "struct cache_entry *" to "const ..." wherever possible I attempted to make index_state->cache[] a "const struct cache_entry **" to find out how existing entries in index are modified and where. The question I have is what do we do if we really need to keep track of on-disk changes in the index. The result is - diff-lib.c: setting CE_UPTODATE - name-hash.c: setting CE_HASHED - preload-index.c, read-cache.c, unpack-trees.c and builtin/update-index: obvious - entry.c: write_entry() may refresh the checked out entry via fill_stat_cache_info(). This causes "non-const struct cache_entry *" in builtin/apply.c, builtin/checkout-index.c and builtin/checkout.c - builtin/ls-files.c: --with-tree changes stagemask and may set CE_UPDATE Of these, write_entry() and its call sites are probably most interesting because it modifies on-disk info. But this is stat info and can be retrieved via refresh, at least for porcelain commands. Other just uses ce_flags for local purposes. So, keeping track of "dirty" entries is just a matter of setting a flag in index modification functions exposed by read-cache.c. Except unpack-trees, the rest of the code base does not do anything funny behind read-cache's back. The actual patch is less valueable than the summary above. But if anyone wants to re-identify the above sites. Applying this patch, then this: diff --git a/cache.h b/cache.h index 430d021..1692891 100644 --- a/cache.h +++ b/cache.h @@ -267,7 +267,7 @@ static inline unsigned int canon_mode(unsigned int mode) #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1) struct index_state { - struct cache_entry **cache; + const struct cache_entry **cache; unsigned int version; unsigned int cache_nr, cache_alloc, cache_changed; struct string_list *resolve_undo; will help quickly identify them without bogus warnings. Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2013-07-09 17:29:00 +02:00
const 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, alloc_tree_node());
add object_as_type helper for casting objects When we call lookup_commit, lookup_tree, etc, the logic goes something like: 1. Look for an existing object struct. If we don't have one, allocate and return a new one. 2. Double check that any object we have is the expected type (and complain and return NULL otherwise). 3. Convert an object with type OBJ_NONE (from a prior call to lookup_unknown_object) to the expected type. We can encapsulate steps 2 and 3 in a helper function which checks whether we have the expected object type, converts OBJ_NONE as appropriate, and returns the object. Not only does this shorten the code, but it also provides one central location for converting OBJ_NONE objects into objects of other types. Future patches will use that to enforce type-specific invariants. Since this is a refactoring, we would want it to behave exactly as the current code. It takes a little reasoning to see that this is the case: - for lookup_{commit,tree,etc} functions, we are just pulling steps 2 and 3 into a function that does the same thing. - for the call in peel_object, we currently only do step 3 (but we want to consolidate it with the others, as mentioned above). However, step 2 is a noop here, as the surrounding conditional makes sure we have OBJ_NONE (which we want to keep to avoid an extraneous call to sha1_object_info). - for the call in lookup_commit_reference_gently, we are currently doing step 2 but not step 3. However, step 3 is a noop here. The object we got will have just come from deref_tag, which must have figured out the type for each object in order to know when to stop peeling. Therefore the type will never be OBJ_NONE. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2014-07-13 08:42:03 +02:00
return object_as_type(obj, OBJ_TREE, 0);
}
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_gently(struct tree *item, int quiet_on_missing)
{
enum object_type type;
void *buffer;
unsigned long size;
if (item->object.parsed)
return 0;
buffer = read_sha1_file(item->object.oid.hash, &type, &size);
if (!buffer)
return quiet_on_missing ? -1 :
error("Could not read %s",
oid_to_hex(&item->object.oid));
if (type != OBJ_TREE) {
free(buffer);
return error("Object %s not a tree",
oid_to_hex(&item->object.oid));
}
return parse_tree_buffer(item, buffer, size);
}
void free_tree_buffer(struct tree *tree)
{
free(tree->buffer);
tree->buffer = NULL;
tree->size = 0;
tree->object.parsed = 0;
}
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->oid.hash);
} while (1);
}