git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 3/4] exclude: do strcmp as much as possible before fnmatch

From
Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date
Jun 7, 2012, 07:53 UTC
Message-ID
<1339055617-23028-3-git-send-email-pclouds@gmail.com>
In-Reply-To
<1339055617-23028-1-git-send-email-pclouds@gmail.com>

this also avoids calling fnmatch() if the non-wildcard prefix is longer than basename

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Fixed the global "wildcards" string thing by using simple_length().
 dir.c | 37 ++++++++++++++++++++++++-------------
 dir.h |  2 +-
 2 files changed, 25 insertions(+), 14 deletions(-)
diff --git a/dir.c b/dir.c
index bbf958c..94fe9f8 100644
--- a/dir.c
+++ b/dir.c
@@ -341,8 +341,7 @@ 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 = simple_length(string);
 	if (*string == '*' && no_wildcard(string+1))
 		x->flags |= EXC_FLAG_ENDSWITH;
 	ALLOC_GROW(which->excludes, which->nr + 1, which->alloc);
@@ -518,8 +517,9 @@ 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)
@@ -530,7 +530,7 @@ 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) {
@@ -544,26 +544,37 @@ 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;
-- 
1.7.11.rc1.185.g281ad67
Previous: Nguyễn Thái Ngọc DuyNext: Nguyễn Thái Ngọc Duy
Message 3 of 7 in “Unindent excluded_from_list()”
  1. 1/4 Unindent excluded_from_list()Nguyễn Thái Ngọc Duy, Jun 7, 2012
  2. 2/4 dir.c: get rid of the wildcard symbol set in no_wildcard()Nguyễn Thái Ngọc Duy, Jun 7, 2012
  3. 3/4 exclude: do strcmp as much as possible before fnmatchNguyễn Thái Ngọc Duy, Jun 7, 2012
  4. 4/4 exclude: reuse last basename comparisonNguyễn Thái Ngọc Duy, Jun 7, 2012
  5. Junio C HamanoJun 7, 2012
  6. Junio C HamanoJun 7, 2012
  7. Nguyen Thai Ngoc DuyJun 8, 2012

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.