summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNguyễn Thái Ngọc Duy <pclouds@gmail.com>2013-01-01 09:44:10 +0700
committerJunio C Hamano <gitster@pobox.com>2013-01-01 15:32:37 -0800
commit6f1a31f0aae6dbd5414b81fb6c0f4ff087146fc5 (patch)
treeb65e9ec331a8edc4c26b6742ca7b8023a36a0e88
parent46983441ae17b34abee2954b87efeeefbe0768b3 (diff)
downloadgit-6f1a31f0aae6dbd5414b81fb6c0f4ff087146fc5.tar.gz
wildmatch: advance faster in <asterisk> + <literal> patterns
Normally when we match "*X" on "abcX", we call dowild("X", "abcX"), dowild("X", "bcX"), dowild("X", "cX") and dowild("X", "X"). Only the last call may have a chance of matching. By skipping the text before "X", we can eliminate the first three useless calls. compat, '*/*/*' on linux-2.6.git file list 2000 times, before: wildmatch 7s 985049us fnmatch 2s 735541us or 34.26% faster and after: wildmatch 4s 492549us fnmatch 0s 888263us or 19.77% slower Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rwxr-xr-xt/t3070-wildmatch.sh8
-rw-r--r--wildmatch.c23
2 files changed, 31 insertions, 0 deletions
diff --git a/t/t3070-wildmatch.sh b/t/t3070-wildmatch.sh
index 97f1daff8e..4c37057ddf 100755
--- a/t/t3070-wildmatch.sh
+++ b/t/t3070-wildmatch.sh
@@ -207,6 +207,11 @@ match 0 x foo '*/*/*'
match 0 x foo/bar '*/*/*'
match 1 x foo/bba/arr '*/*/*'
match 0 x foo/bb/aa/rr '*/*/*'
+match 1 x foo/bb/aa/rr '**/**/**'
+match 1 x abcXdefXghi '*X*i'
+match 0 x ab/cXd/efXg/hi '*X*i'
+match 1 x ab/cXd/efXg/hi '*/*X*/*/*i'
+match 1 x ab/cXd/efXg/hi '**/*X*/**/*i'
pathmatch 1 foo foo
pathmatch 0 foo fo
@@ -226,5 +231,8 @@ pathmatch 0 foo '*/*/*'
pathmatch 0 foo/bar '*/*/*'
pathmatch 1 foo/bba/arr '*/*/*'
pathmatch 1 foo/bb/aa/rr '*/*/*'
+pathmatch 1 abcXdefXghi '*X*i'
+pathmatch 1 ab/cXd/efXg/hi '*/*X*/*/*i'
+pathmatch 1 ab/cXd/efXg/hi '*Xg*i'
test_done
diff --git a/wildmatch.c b/wildmatch.c
index bb425220b0..7192bdc1b8 100644
--- a/wildmatch.c
+++ b/wildmatch.c
@@ -133,6 +133,29 @@ static int dowild(const uchar *p, const uchar *text, unsigned int flags)
while (1) {
if (t_ch == '\0')
break;
+ /*
+ * Try to advance faster when an asterisk is
+ * followed by a literal. We know in this case
+ * that the the string before the literal
+ * must belong to "*".
+ * If match_slash is false, do not look past
+ * the first slash as it cannot belong to '*'.
+ */
+ if (!is_glob_special(*p)) {
+ p_ch = *p;
+ if ((flags & WM_CASEFOLD) && ISUPPER(p_ch))
+ p_ch = tolower(p_ch);
+ while ((t_ch = *text) != '\0' &&
+ (match_slash || t_ch != '/')) {
+ if ((flags & WM_CASEFOLD) && ISUPPER(t_ch))
+ t_ch = tolower(t_ch);
+ if (t_ch == p_ch)
+ break;
+ text++;
+ }
+ if (t_ch != p_ch)
+ return WM_NOMATCH;
+ }
if ((matched = dowild(p, text, flags)) != WM_NOMATCH) {
if (!match_slash || matched != WM_ABORT_TO_STARSTAR)
return matched;