patch, 4 partsSome pathspec wildcard optimization

builtin/ls-files.c, builtin/ls-tree.c, cache.h, dir.c, tree-walk.c

diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index b5434af..4a9ee69 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -337,7 +337,7 @@ void overlay_tree_on_cache(const char *tree_name, const char *prefix)
 		matchbuf[0] = prefix;
 		matchbuf[1] = NULL;
 		init_pathspec(&pathspec, matchbuf);
-		pathspec.items[0].use_wildcard = 0;
+		pathspec.items[0].nowildcard_len = pathspec.items[0].len;
 	} else
 		init_pathspec(&pathspec, NULL);
 	if (read_tree(tree, 1, &pathspec))
diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c
index 235c17c..fb76e38 100644
--- a/builtin/ls-tree.c
+++ b/builtin/ls-tree.c
@@ -168,7 +168,7 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 
 	init_pathspec(&pathspec, get_pathspec(prefix, argv + 1));
 	for (i = 0; i < pathspec.nr; i++)
-		pathspec.items[i].use_wildcard = 0;
+		pathspec.items[i].nowildcard_len = pathspec.items[i].len;
 	pathspec.has_wildcard = 0;
 	tree = parse_tree_indirect(sha1);
 	if (!tree)
diff --git a/cache.h b/cache.h
index dbd8018..bf031f1 100644
--- a/cache.h
+++ b/cache.h
@@ -482,7 +482,7 @@ struct pathspec {
 	struct pathspec_item {
 		const char *match;
 		int len;
-		unsigned int use_wildcard:1;
+		int nowildcard_len;
 	} *items;
 };
 
diff --git a/dir.c b/dir.c
index 5a83aa7..c391d46 100644
--- a/dir.c
+++ b/dir.c
@@ -230,7 +230,7 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
 			return MATCHED_RECURSIVELY;
 	}
 
-	if (item->use_wildcard && !fnmatch(match, name, 0))
+	if (item->nowildcard_len < item->len && !fnmatch(match, name, 0))
 		return MATCHED_FNMATCH;
 
 	return 0;
@@ -1429,8 +1429,8 @@ int init_pathspec(struct pathspec *pathspec, const char **paths)
 
 		item->match = path;
 		item->len = strlen(path);
-		item->use_wildcard = !no_wildcard(path);
-		if (item->use_wildcard)
+		item->nowildcard_len = simple_length(path);
+		if (item->nowildcard_len < item->len)
 			pathspec->has_wildcard = 1;
 	}
 
diff --git a/tree-walk.c b/tree-walk.c
index 3f54c02..af871c5 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -626,7 +626,7 @@ enum interesting tree_entry_interesting(const struct name_entry *entry,
 					&never_interesting))
 				return entry_interesting;
 
-			if (item->use_wildcard) {
+			if (item->nowildcard_len < item->len) {
 				if (!fnmatch(match + baselen, entry->path, 0))
 					return entry_interesting;
 
@@ -642,7 +642,7 @@ enum interesting tree_entry_interesting(const struct name_entry *entry,
 		}
 
 match_wildcards:
-		if (!item->use_wildcard)
+		if (item->nowildcard_len == item->len)
 			continue;
 
 		/*

dir.c, dir.h, tree-walk.c

diff --git a/dir.c b/dir.c
index c391d46..e4e6ca1 100644
--- a/dir.c
+++ b/dir.c
@@ -34,6 +34,21 @@ int fnmatch_icase(const char *pattern, const char *string, int flags)
 	return fnmatch(pattern, string, flags | (ignore_case ? FNM_CASEFOLD : 0));
 }
 
+inline int git_fnmatch(const char *pattern, const char *string,
+		       int flags, int prefix)
+{
+	int fnm_flags = 0;
+	if (flags & GF_PATHNAME)
+		fnm_flags |= FNM_PATHNAME;
+	if (prefix > 0) {
+		if (strncmp(pattern, string, prefix))
+			return FNM_NOMATCH;
+		pattern += prefix;
+		string += prefix;
+	}
+	return fnmatch(pattern, string, fnm_flags);
+}
+
 static size_t common_prefix_len(const char **pathspec)
 {
 	const char *n, *first;
@@ -230,7 +245,8 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
 			return MATCHED_RECURSIVELY;
 	}
 
-	if (item->nowildcard_len < item->len && !fnmatch(match, name, 0))
+	if (item->nowildcard_len < item->len &&
+	    !git_fnmatch(match, name, 0, item->nowildcard_len - prefix))
 		return MATCHED_FNMATCH;
 
 	return 0;
diff --git a/dir.h b/dir.h
index f5c89e3..4cd5074 100644
--- a/dir.h
+++ b/dir.h
@@ -139,4 +139,12 @@ extern int strcmp_icase(const char *a, const char *b);
 extern int strncmp_icase(const char *a, const char *b, size_t count);
 extern int fnmatch_icase(const char *pattern, const char *string, int flags);
 
+/*
+ * The prefix part of pattern must not contains wildcards.
+ */
+#define GF_PATHNAME 1
+
+extern int git_fnmatch(const char *pattern, const char *string,
+		       int flags, int prefix);
+
 #endif
diff --git a/tree-walk.c b/tree-walk.c
index af871c5..2fcf3c0 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -627,7 +627,8 @@ enum interesting tree_entry_interesting(const struct name_entry *entry,
 				return entry_interesting;
 
 			if (item->nowildcard_len < item->len) {
-				if (!fnmatch(match + baselen, entry->path, 0))
+				if (!git_fnmatch(match + baselen, entry->path,
+						 0, item->nowildcard_len - baselen))
 					return entry_interesting;
 
 				/*
@@ -652,7 +653,8 @@ match_wildcards:
 
 		strbuf_add(base, entry->path, pathlen);
 
-		if (!fnmatch(match, base->buf + base_offset, 0)) {
+		if (!git_fnmatch(match, base->buf + base_offset,
+				 0, item->nowildcard_len)) {
 			strbuf_setlen(base, base_offset + baselen);
 			return entry_interesting;
 		}

cache.h, dir.c, dir.h, tree-walk.c

diff --git a/cache.h b/cache.h
index bf031f1..d18f584 100644
--- a/cache.h
+++ b/cache.h
@@ -473,6 +473,8 @@ extern int index_name_is_other(const struct index_state *, const char *, int);
 extern int ie_match_stat(const struct index_state *, struct cache_entry *, struct stat *, unsigned int);
 extern int ie_modified(const struct index_state *, struct cache_entry *, struct stat *, unsigned int);
 
+#define PSF_ONESTAR 1
+
 struct pathspec {
 	const char **raw; /* get_pathspec() result, not freed by free_pathspec() */
 	int nr;
@@ -483,6 +485,7 @@ struct pathspec {
 		const char *match;
 		int len;
 		int nowildcard_len;
+		int flags;
 	} *items;
 };
 
diff --git a/dir.c b/dir.c
index e4e6ca1..d00f240 100644
--- a/dir.c
+++ b/dir.c
@@ -46,6 +46,12 @@ inline int git_fnmatch(const char *pattern, const char *string,
 		pattern += prefix;
 		string += prefix;
 	}
+	if (flags & GF_ONESTAR) {
+		int pattern_len = strlen(++pattern);
+		int string_len = strlen(string);
+		return strcmp(pattern,
+			      string + string_len - pattern_len);
+	}
 	return fnmatch(pattern, string, fnm_flags);
 }
 
@@ -246,7 +252,9 @@ static int match_pathspec_item(const struct pathspec_item *item, int prefix,
 	}
 
 	if (item->nowildcard_len < item->len &&
-	    !git_fnmatch(match, name, 0, item->nowildcard_len - prefix))
+	    !git_fnmatch(match, name,
+			 item->flags & PSF_ONESTAR ? GF_ONESTAR : 0,
+			 item->nowildcard_len - prefix))
 		return MATCHED_FNMATCH;
 
 	return 0;
@@ -1446,8 +1454,13 @@ int init_pathspec(struct pathspec *pathspec, const char **paths)
 		item->match = path;
 		item->len = strlen(path);
 		item->nowildcard_len = simple_length(path);
-		if (item->nowildcard_len < item->len)
+		item->flags = 0;
+		if (item->nowildcard_len < item->len) {
 			pathspec->has_wildcard = 1;
+			if (path[item->nowildcard_len] == '*' &&
+			    no_wildcard(path + item->nowildcard_len + 1))
+				item->flags |= PSF_ONESTAR;
+		}
 	}
 
 	qsort(pathspec->items, pathspec->nr,
diff --git a/dir.h b/dir.h
index 4cd5074..590532b 100644
--- a/dir.h
+++ b/dir.h
@@ -143,6 +143,7 @@ extern int fnmatch_icase(const char *pattern, const char *string, int flags);
  * The prefix part of pattern must not contains wildcards.
  */
 #define GF_PATHNAME 1
+#define GF_ONESTAR  2
 
 extern int git_fnmatch(const char *pattern, const char *string,
 		       int flags, int prefix);
diff --git a/tree-walk.c b/tree-walk.c
index 2fcf3c0..42fe610 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -628,7 +628,8 @@ enum interesting tree_entry_interesting(const struct name_entry *entry,
 
 			if (item->nowildcard_len < item->len) {
 				if (!git_fnmatch(match + baselen, entry->path,
-						 0, item->nowildcard_len - baselen))
+						 item->flags & PSF_ONESTAR ? GF_ONESTAR : 0,
+						 item->nowildcard_len - baselen))
 					return entry_interesting;
 
 				/*
@@ -654,7 +655,8 @@ match_wildcards:
 		strbuf_add(base, entry->path, pathlen);
 
 		if (!git_fnmatch(match, base->buf + base_offset,
-				 0, item->nowildcard_len)) {
+				 item->flags & PSF_ONESTAR ? GF_ONESTAR : 0,
+				 item->nowildcard_len)) {
 			strbuf_setlen(base, base_offset + baselen);
 			return entry_interesting;
 		}

diff --git a/tree-walk.c b/tree-walk.c
index 42fe610..dcc1015 100644
--- a/tree-walk.c
+++ b/tree-walk.c
@@ -573,6 +573,52 @@ static int match_dir_prefix(const char *base,
 }
 
 /*
+ * Perform matching on the leading non-wildcard part of
+ * pathspec. item->nowildcard_len must be greater than zero. Return
+ * non-zero if base is matched.
+ */
+static int match_wildcard_base(const struct pathspec_item *item,
+			       const char *base, int baselen,
+			       int *matched)
+{
+	const char *match = item->match;
+	/* the wildcard part is not considered in this function */
+	int matchlen = item->nowildcard_len;
+
+	if (baselen) {
+		int dirlen;
+		/*
+		 * Return early if base is longer than the
+		 * non-wildcard part but it does not match.
+		 */
+		if (baselen >= matchlen) {
+			*matched = matchlen;
+			return !strncmp(base, match, matchlen);
+		}
+
+		dirlen = matchlen;
+		while (dirlen && match[dirlen - 1] != '/')
+			dirlen--;
+
+		/* Return early if base is shorter than the
+		   non-wildcard part but it does not match. Note that
+		   base ends with '/' so we are sure it really matches
+		   directory */
+		if (strncmp(base, match, baselen))
+			return 0;
+		*matched = baselen;
+	} else
+		*matched = 0;
+	/*
+	 * we could have checked entry against the non-wildcard part
+	 * that is not in base and does similar never_interesting
+	 * optimization as in match_entry. For now just be happy with
+	 * base comparison.
+	 */
+	return entry_interesting;
+}
+
+/*
  * Is a tree entry interesting given the pathspec we have?
  *
  * Pre-condition: either baselen == base_offset (i.e. empty path)
@@ -602,7 +648,7 @@ enum interesting tree_entry_interesting(const struct name_entry *entry,
 		const struct pathspec_item *item = ps->items+i;
 		const char *match = item->match;
 		const char *base_str = base->buf + base_offset;
-		int matchlen = item->len;
+		int matchlen = item->len, matched = 0;
 
 		if (baselen >= matchlen) {
 			/* If it doesn't match, move along... */
@@ -647,9 +693,24 @@ match_wildcards:
 		if (item->nowildcard_len == item->len)
 			continue;
 
+		if (item->nowildcard_len &&
+		    !match_wildcard_base(item, base_str, baselen, &matched))
+			return entry_not_interesting;
+
 		/*
 		 * Concatenate base and entry->path into one and do
 		 * fnmatch() on it.
+		 *
+		 * While we could avoid concatenation in certain cases
+		 * [1], which saves a memcpy and potentially a
+		 * realloc, it turns out not worth it. Measurement on
+		 * linux-2.6 does not show any clear improvements,
+		 * partly because of the nowildcard_len optimization
+		 * in git_fnmatch(). Avoid micro-optimizations here.
+		 *
+		 * [1] if match_wildcard_base() says the base
+		 * directory is already matched, we only need to match
+		 * the rest, which is shorter so _in theory_ faster.
 		 */
 
 		strbuf_add(base, entry->path, pathlen);