If we have never seen attr 'X' in any .gitattributes file we have
examined so far, we can be sure that 'X' is not defined. So no need to
go over all the attr stack to look for attr 'X'. This is the purpose
behind this new field maybe_real.
This optimization breaks down if macros are involved because we can't
know for sure what macro would expand to 'X' at attr parsing time. But
if we go the permisstic way and assume all macros are expanded, we hit
the builtin "binary" macro. At least the "diff" attr defined in this
macro will disable this optimization for git-grep. So we wait until
any attr lines _may_ reference to a macro before we turn this off.
In git.git, this reduces the number of fill_one() call for "git grep
abcdefghi" from ~5300 to 3000. The optimization stops when it reads
t/.gitattributes, which uses 'binary' macro.
"git grep" is actually a good example to justify this patch. The
command checks "diff" attribute on every file. People usually don't
define this attribute. But they pay the attr lookup penalty anyway
without this patch, proportional to the number of attr lines they have
in repo.
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@xxxxxxxxx>
---
attr.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 43 insertions(+), 1 deletion(-)
diff --git a/attr.c b/attr.c
index 4ec6186..ba41761 100644
--- a/attr.c
+++ b/attr.c
@@ -33,9 +33,11 @@ struct git_attr {
unsigned h;
int attr_nr;
int maybe_macro;
+ int maybe_real;
char name[FLEX_ARRAY];
};
static int git_attr_nr;
+static int cannot_trust_maybe_real;
static struct git_attr_check *check_all_attr;
static struct git_attr *(git_attr_hash[HASHSIZE]);
@@ -97,6 +99,7 @@ static struct git_attr *git_attr_internal(const char *name, int len)
a->next = git_attr_hash[pos];
a->attr_nr = git_attr_nr++;
a->maybe_macro = 0;
+ a->maybe_real = 0;
git_attr_hash[pos] = a;
REALLOC_ARRAY(check_all_attr, git_attr_nr);
@@ -269,6 +272,10 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
/* Second pass to fill the attr_states */
for (cp = states, i = 0; *cp; i++) {
cp = parse_attr(src, lineno, cp, &(res->state[i]));
+ if (!is_macro)
+ res->state[i].attr->maybe_real = 1;
+ if (res->state[i].attr->maybe_macro)
+ cannot_trust_maybe_real = 1;
}
return res;
@@ -752,11 +759,46 @@ static void collect_all_attrs(const char *path)
rem = fill(path, pathlen, basename_offset, stk, rem);
}
+static void collect_selected_attrs(const char *path, int num,
+ struct git_attr_check *check)
+{
+ struct attr_stack *stk;
+ int i, pathlen, rem, dirlen;
+ int basename_offset;
+
+ pathlen = split_path(path, &dirlen, &basename_offset);
+ prepare_attr_stack(path, dirlen);
+ if (cannot_trust_maybe_real) {
+ for (i = 0; i < git_attr_nr; i++)
+ check_all_attr[i].value = ATTR__UNKNOWN;
+ } else {
+ rem = num;
+ for (i = 0; i < num; i++) {
+ struct git_attr_check *c;
+ c = check_all_attr + check[i].attr->attr_nr;
+ if (check[i].attr->maybe_real)
+ c->value = ATTR__UNKNOWN;
+ else {
+ c->value = ATTR__UNSET;
+ rem--;
+ }
+ }
+ if (!rem)
+ return;
+ }
+ rem = git_attr_nr;
+ for (stk = attr_stack; 0 < rem && stk; stk = stk->prev)
+ rem = fill(path, pathlen, basename_offset, stk, rem);
+}
+
int git_check_attr(const char *path, int num, struct git_attr_check *check)
{
int i;
- collect_all_attrs(path);
+ if (cannot_trust_maybe_real)
+ collect_all_attrs(path);
+ else
+ collect_selected_attrs(path, num, check);
for (i = 0; i < num; i++) {
const char *value = check_all_attr[check[i].attr->attr_nr].value;
--
2.2.0.84.ge9c7a8a
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html