[PATCH 04/10] attr: more matching optimizations from .gitignore

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

.gitattributes and .gitignore share the same pattern syntax but has
separate matching implementation. Over the years, ignore's
implementation accumulates more optimizations while attr's stays the
same.

This patch adds those optimizations to .gitattributes. Basically it
tries to avoid fnmatch/wildmatch in favor of strncmp as much as
possible.

There are two syntaxes that .gitignore supports but .gitattributes
does not: negative patterns and directory matching. They have never
worked and whether they will is up for future discussion. Meanwhile
make a note in the document and reject such patterns.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/gitattributes.txt |  2 ++
 attr.c                          | 68 ++++++++++++++++++++++++++++++++++-------
 dir.c                           |  8 ++---
 dir.h                           |  1 +
 4 files changed, 64 insertions(+), 15 deletions(-)

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index e16f3e1..702b8c1 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -56,6 +56,8 @@ When more than one pattern matches the path, a later line
 overrides an earlier line.  This overriding is done per
 attribute.  The rules how the pattern matches paths are the
 same as in `.gitignore` files; see linkgit:gitignore[5].
+Unlike `.gitignore`, negative patterns are not supported.
+Patterns that match directories are also not supported.
 
 When deciding what attributes are assigned to a path, git
 consults `$GIT_DIR/info/attributes` file (which has the highest
diff --git a/attr.c b/attr.c
index aeac564..1aa058e 100644
--- a/attr.c
+++ b/attr.c
@@ -115,6 +115,13 @@ struct attr_state {
 	const char *setto;
 };
 
+struct pattern {
+	const char *pattern;
+	int patternlen;
+	int nowildcardlen;
+	int flags;		/* EXC_FLAG_* */
+};
+
 /*
  * One rule, as from a .gitattributes file.
  *
@@ -131,7 +138,7 @@ struct attr_state {
  */
 struct match_attr {
 	union {
-		char *pattern;
+		struct pattern pat;
 		struct git_attr *attr;
 	} u;
 	char is_macro;
@@ -241,9 +248,18 @@ static struct match_attr *parse_attr_line(const char *line, const char *src,
 	if (is_macro)
 		res->u.attr = git_attr_internal(name, namelen);
 	else {
-		res->u.pattern = (char *)&(res->state[num_attr]);
-		memcpy(res->u.pattern, name, namelen);
-		res->u.pattern[namelen] = 0;
+		char *p = (char *)&(res->state[num_attr]);
+		memcpy(p, name, namelen);
+		p[namelen] = 0;
+		res->u.pat.pattern = p;
+		parse_exclude_pattern(&res->u.pat.pattern,
+				      &res->u.pat.patternlen,
+				      &res->u.pat.flags,
+				      &res->u.pat.nowildcardlen);
+		if (res->u.pat.flags & EXC_FLAG_NEGATIVE)
+			die(_("Negative patterns are not supported in git attributes"));
+		if (res->u.pat.flags & EXC_FLAG_MUSTBEDIR)
+			die(_("Directory patterns are not supported in git attributes"));
 	}
 	res->is_macro = is_macro;
 	res->num_attr = num_attr;
@@ -645,25 +661,55 @@ static void prepare_attr_stack(const char *path)
 
 static int path_matches(const char *pathname, int pathlen,
 			const char *basename,
-			const char *pattern,
+			const struct pattern *pat,
 			const char *base, int baselen)
 {
-	if (!strchr(pattern, '/')) {
+	const char *pattern = pat->pattern;
+	int prefix = pat->nowildcardlen;
+	const char *name;
+	int namelen;
+
+	if (pat->flags & EXC_FLAG_NODIR) {
+		if (prefix == pat->patternlen &&
+		    !strcmp_icase(pattern, basename))
+			return 1;
+
+		if (pat->flags & EXC_FLAG_ENDSWITH &&
+		    pat->patternlen - 1 <= pathlen &&
+		    !strcmp_icase(pattern + 1, pathname +
+				  pathlen - pat->patternlen + 1))
+			return 1;
+
 		return (fnmatch_icase(pattern, basename, 0) == 0);
 	}
 	/*
 	 * match with FNM_PATHNAME; the pattern has base implicitly
 	 * in front of it.
 	 */
-	if (*pattern == '/')
+	if (*pattern == '/') {
 		pattern++;
+		prefix--;
+	}
+
+	/*
+	 * note: unlike excluded_from_list, baselen here does not
+	 * contain the trailing slash
+	 */
+
 	if (pathlen < baselen ||
 	    (baselen && pathname[baselen] != '/') ||
 	    strncmp(pathname, base, baselen))
 		return 0;
-	if (baselen != 0)
-		baselen++;
-	return fnmatch_icase(pattern, pathname + baselen, FNM_PATHNAME) == 0;
+
+	namelen = baselen ? pathlen - baselen - 1 : pathlen;
+	name = pathname + pathlen - namelen;
+
+	/* if the non-wildcard part is longer than the remaining
+	   pathname, surely it cannot match */
+	if (!namelen || prefix > namelen)
+		return 0;
+
+	return fnmatch_icase(pattern, name, FNM_PATHNAME) == 0;
 }
 
 static int macroexpand_one(int attr_nr, int rem);
@@ -701,7 +747,7 @@ static int fill(const char *path, int pathlen, const char *basename,
 		if (a->is_macro)
 			continue;
 		if (path_matches(path, pathlen, basename,
-				 a->u.pattern, base, stk->originlen))
+				 &a->u.pat, base, stk->originlen))
 			rem = fill_one("fill", a, rem);
 	}
 	return rem;
diff --git a/dir.c b/dir.c
index cd13920..c6a0275 100644
--- a/dir.c
+++ b/dir.c
@@ -308,10 +308,10 @@ static int no_wildcard(const char *string)
 	return string[simple_length(string)] == '\0';
 }
 
-static void parse_exclude_pattern(const char **pattern,
-				  int *patternlen,
-				  int *flags,
-				  int *nowildcardlen)
+void parse_exclude_pattern(const char **pattern,
+			   int *patternlen,
+			   int *flags,
+			   int *nowildcardlen)
 {
 	const char *p = *pattern;
 	size_t i, len;
diff --git a/dir.h b/dir.h
index 41ea32d..fd5c2aa 100644
--- a/dir.h
+++ b/dir.h
@@ -97,6 +97,7 @@ extern int path_excluded(struct path_exclude_check *, const char *, int namelen,
 extern int add_excludes_from_file_to_list(const char *fname, const char *base, int baselen,
 					  char **buf_p, struct exclude_list *which, int check_index);
 extern void add_excludes_from_file(struct dir_struct *, const char *fname);
+extern void parse_exclude_pattern(const char **string, int *patternlen, int *flags, int *nowildcardlen);
 extern void add_exclude(const char *string, const char *base,
 			int baselen, struct exclude_list *which);
 extern void free_excludes(struct exclude_list *el);
-- 
1.7.12.1.405.gb727dc9