[PATCH 2/3] exclude: do strcmp as much as possible before fnmatch

From

Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

Date

May 26, 2012, 12:31 UTC

Message-ID

<1338035474-4346-3-git-send-email-pclouds@gmail.com>

In-Reply-To

<1338035474-4346-1-git-send-email-pclouds@gmail.com>

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 dir.c | 41 +++++++++++++++++++++++++++--------------
 dir.h |  2 +-
 2 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/dir.c b/dir.c
index 8535cf2..50d744f 100644
--- a/dir.c
+++ b/dir.c
@@ -295,9 +295,11 @@ int match_pathspec_depth(const struct pathspec *ps,
 	return retval;
 }
 
+const char *wildcards = "*?[{\\";
+
 static int no_wildcard(const char *string)
 {
-	return string[strcspn(string, "*?[{\\")] == '\0';
+	return string[strcspn(string, wildcards)] == '\0';
 }
 
 void add_exclude(const char *string, const char *base,
@@ -336,8 +338,7 @@ void add_exclude(const char *string, const char *base,
 	x->flags = flags;
 	if (!strchr(string, '/'))
 		x->flags |= EXC_FLAG_NODIR;
-	if (no_wildcard(string))
-		x->flags |= EXC_FLAG_NOWILDCARD;
+	x->nowildcardlen = strcspn(string, wildcards);
 	if (*string == '*' && no_wildcard(string+1))
 		x->flags |= EXC_FLAG_ENDSWITH;
 	ALLOC_GROW(which->excludes, which->nr + 1, which->alloc);
@@ -513,8 +514,9 @@ int excluded_from_list(const char *pathname,
 
 	for (i = el->nr - 1; 0 <= i; i--) {
 		struct exclude *x = el->excludes[i];
-		const char *exclude = x->pattern;
+		const char *name, *exclude = x->pattern;
 		int to_exclude = x->to_exclude;
+		int namelen, prefix = x->nowildcardlen;
 
 		if (x->flags & EXC_FLAG_MUSTBEDIR) {
 			if (*dtype == DT_UNKNOWN)
@@ -525,7 +527,7 @@ int excluded_from_list(const char *pathname,
 
 		if (x->flags & EXC_FLAG_NODIR) {
 			/* match basename */
-			if (x->flags & EXC_FLAG_NOWILDCARD) {
+			if (prefix == x->patternlen) {
 				if (!strcmp_icase(exclude, basename))
 					return to_exclude;
 			} else if (x->flags & EXC_FLAG_ENDSWITH) {
@@ -539,26 +541,37 @@ int excluded_from_list(const char *pathname,
 			continue;
 		}
 
-
 		/* match with FNM_PATHNAME:
 		 * exclude has base (baselen long) implicitly in front of it.
 		 */
-		if (*exclude == '/')
+		if (*exclude == '/') {
 			exclude++;
+			prefix--;
+		}
 
 		if (pathlen < x->baselen ||
 		    (x->baselen && pathname[x->baselen-1] != '/') ||
 		    strncmp_icase(pathname, x->base, x->baselen))
 			continue;
 
-		if (x->flags & EXC_FLAG_NOWILDCARD) {
-			if (!strcmp_icase(exclude, pathname + x->baselen))
-				return to_exclude;
-		} else {
-			if (fnmatch_icase(exclude, pathname+x->baselen,
-					  FNM_PATHNAME) == 0)
-				return to_exclude;
+		namelen = x->baselen ? pathlen - x->baselen : pathlen;
+		name = pathname + pathlen  - namelen;
+
+		/* if the non-wildcard part is longer than the
+		   remaining pathname, surely it cannot match */
+		if (prefix > namelen)
+			continue;
+
+		if (prefix) {
+			if (strncmp_icase(exclude, name, prefix))
+				continue;
+			exclude += prefix;
+			name    += prefix;
+			namelen -= prefix;
 		}
+
+		if (!namelen || !fnmatch_icase(exclude, name, FNM_PATHNAME))
+			return to_exclude;
 	}
 	return -1; /* undecided */
 }
diff --git a/dir.h b/dir.h
index 58b6fc7..39fc145 100644
--- a/dir.h
+++ b/dir.h
@@ -7,7 +7,6 @@ struct dir_entry {
 };
 
 #define EXC_FLAG_NODIR 1
-#define EXC_FLAG_NOWILDCARD 2
 #define EXC_FLAG_ENDSWITH 4
 #define EXC_FLAG_MUSTBEDIR 8
 
@@ -17,6 +16,7 @@ struct exclude_list {
 	struct exclude {
 		const char *pattern;
 		int patternlen;
+		int nowildcardlen;
 		const char *base;
 		int baselen;
 		int to_exclude;

-- 
1.7.10.2.549.g9354186