Merge branch 'jc/ls-files-i-dir'

"git ls-files --exclude=t -i" did not consider anything under t/
as excluded, as it did not pay attention to exclusion of leading
paths while walking the index.  Other two users of excluded() are
also updated.

* jc/ls-files-i-dir:
  dir.c: make excluded() file scope static
  unpack-trees.c: use path_excluded() in check_ok_to_remove()
  builtin/add.c: use path_excluded()
  path_excluded(): update API to less cache-entry centric
  ls-files -i: micro-optimize path_excluded()
  ls-files -i: pay attention to exclusion of leading paths

Author: gitster

builtin/add.c

@@ -443,21 +443,25 @@ int cmd_add(int argc, const char **argv, const char *prefix)
 
 	if (pathspec) {
 		int i;
+		struct path_exclude_check check;
+
+		path_exclude_check_init(&check, &dir);
 		if (!seen)
 			seen = find_used_pathspec(pathspec);
 		for (i = 0; pathspec[i]; i++) {
 			if (!seen[i] && pathspec[i][0]
 			    && !file_exists(pathspec[i])) {
 				if (ignore_missing) {
 					int dtype = DT_UNKNOWN;
-					if (excluded(&dir, pathspec[i], &dtype))
+					if (path_excluded(&check, pathspec[i], -1, &dtype))
 						dir_add_ignored(&dir, pathspec[i], strlen(pathspec[i]));
 				} else
 					die(_("pathspec '%s' did not match any files"),
 					    pathspec[i]);
 			}
 		}
 		free(seen);
+		path_exclude_check_clear(&check);
 	}
 
 	plug_bulk_checkin();

builtin/ls-files.c

@@ -200,9 +200,19 @@ static void show_ru_info(void)
 	}
 }
 
+static int ce_excluded(struct path_exclude_check *check, struct cache_entry *ce)
+{
+	int dtype = ce_to_dtype(ce);
+	return path_excluded(check, ce->name, ce_namelen(ce), &dtype);
+}
+
 static void show_files(struct dir_struct *dir)
 {
 	int i;
+	struct path_exclude_check check;
+
+	if ((dir->flags & DIR_SHOW_IGNORED))
+		path_exclude_check_init(&check, dir);
 
 	/* For cached/deleted files we don't need to even do the readdir */
 	if (show_others || show_killed) {
@@ -215,9 +225,8 @@ static void show_files(struct dir_struct *dir)
 	if (show_cached | show_stage) {
 		for (i = 0; i < active_nr; i++) {
 			struct cache_entry *ce = active_cache[i];
-			int dtype = ce_to_dtype(ce);
-			if (dir->flags & DIR_SHOW_IGNORED &&
-			    !excluded(dir, ce->name, &dtype))
+			if ((dir->flags & DIR_SHOW_IGNORED) &&
+			    !ce_excluded(&check, ce))
 				continue;
 			if (show_unmerged && !ce_stage(ce))
 				continue;
@@ -232,9 +241,8 @@ static void show_files(struct dir_struct *dir)
 			struct cache_entry *ce = active_cache[i];
 			struct stat st;
 			int err;
-			int dtype = ce_to_dtype(ce);
-			if (dir->flags & DIR_SHOW_IGNORED &&
-			    !excluded(dir, ce->name, &dtype))
+			if ((dir->flags & DIR_SHOW_IGNORED) &&
+			    !ce_excluded(&check, ce))
 				continue;
 			if (ce->ce_flags & CE_UPDATE)
 				continue;
@@ -247,6 +255,9 @@ static void show_files(struct dir_struct *dir)
 				show_ce_entry(tag_modified, ce);
 		}
 	}
+
+	if ((dir->flags & DIR_SHOW_IGNORED))
+		path_exclude_check_clear(&check);
 }
 
 /*

dir.c

@@ -553,7 +553,7 @@ int excluded_from_list(const char *pathname,
 	return -1; /* undecided */
 }
 
-int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
+static int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
 {
 	int pathlen = strlen(pathname);
 	int st;
@@ -573,6 +573,64 @@ int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
 	return 0;
 }
 
+void path_exclude_check_init(struct path_exclude_check *check,
+			     struct dir_struct *dir)
+{
+	check->dir = dir;
+	strbuf_init(&check->path, 256);
+}
+
+void path_exclude_check_clear(struct path_exclude_check *check)
+{
+	strbuf_release(&check->path);
+}
+
+/*
+ * Is this name excluded?  This is for a caller like show_files() that
+ * do not honor directory hierarchy and iterate through paths that are
+ * possibly in an ignored directory.
+ *
+ * A path to a directory known to be excluded is left in check->path to
+ * optimize for repeated checks for files in the same excluded directory.
+ */
+int path_excluded(struct path_exclude_check *check,
+		  const char *name, int namelen, int *dtype)
+{
+	int i;
+	struct strbuf *path = &check->path;
+
+	/*
+	 * we allow the caller to pass namelen as an optimization; it
+	 * must match the length of the name, as we eventually call
+	 * excluded() on the whole name string.
+	 */
+	if (namelen < 0)
+		namelen = strlen(name);
+
+	if (path->len &&
+	    path->len <= namelen &&
+	    !memcmp(name, path->buf, path->len) &&
+	    (!name[path->len] || name[path->len] == '/'))
+		return 1;
+
+	strbuf_setlen(path, 0);
+	for (i = 0; name[i]; i++) {
+		int ch = name[i];
+
+		if (ch == '/') {
+			int dt = DT_DIR;
+			if (excluded(check->dir, path->buf, &dt))
+				return 1;
+		}
+		strbuf_addch(path, ch);
+	}
+
+	/* An entry in the index; cannot be a directory with subentries */
+	strbuf_setlen(path, 0);
+
+	return excluded(check->dir, name, dtype);
+}
+
 static struct dir_entry *dir_entry_new(const char *pathname, int len)
 {
 	struct dir_entry *ent;

dir.h

@@ -1,6 +1,8 @@
 #ifndef DIR_H
 #define DIR_H
 
+#include "strbuf.h"
+
 struct dir_entry {
 	unsigned int len;
 	char name[FLEX_ARRAY]; /* more */
@@ -76,8 +78,22 @@ extern int read_directory(struct dir_struct *, const char *path, int len, const
 
 extern int excluded_from_list(const char *pathname, int pathlen, const char *basename,
 			      int *dtype, struct exclude_list *el);
-extern int excluded(struct dir_struct *, const char *, int *);
 struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len);
+
+/*
+ * The excluded() API is meant for callers that check each level of leading
+ * directory hierarchies with excluded() to avoid recursing into excluded
+ * directories.  Callers that do not do so should use this API instead.
+ */
+struct path_exclude_check {
+	struct dir_struct *dir;
+	struct strbuf path;
+};
+extern void path_exclude_check_init(struct path_exclude_check *, struct dir_struct *);
+extern void path_exclude_check_clear(struct path_exclude_check *);
+extern int path_excluded(struct path_exclude_check *, const char *, int namelen, int *dtype);
+
+
 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);

unpack-trees.c

@@ -1023,6 +1023,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 			o->el = ⪙
 	}
 
+	if (o->dir) {
+		o->path_exclude_check = xmalloc(sizeof(struct path_exclude_check));
+		path_exclude_check_init(o->path_exclude_check, o->dir);
+	}
 	memset(&o->result, 0, sizeof(o->result));
 	o->result.initialized = 1;
 	o->result.timestamp.sec = o->src_index->timestamp.sec;
@@ -1148,6 +1152,10 @@ int unpack_trees(unsigned len, struct tree_desc *t, struct unpack_trees_options
 
 done:
 	free_excludes(&el);
+	if (o->path_exclude_check) {
+		path_exclude_check_clear(o->path_exclude_check);
+		free(o->path_exclude_check);
+	}
 	return ret;
 
 return_failed:
@@ -1363,7 +1371,8 @@ static int check_ok_to_remove(const char *name, int len, int dtype,
 	if (ignore_case && icase_exists(o, name, len, st))
 		return 0;
 
-	if (o->dir && excluded(o->dir, name, &dtype))
+	if (o->dir &&
+	    path_excluded(o->path_exclude_check, name, -1, &dtype))
 		/*
 		 * ce->name is explicitly excluded, so it is Ok to
 		 * overwrite it.

unpack-trees.h

@@ -52,6 +52,7 @@ struct unpack_trees_options {
 	const char *prefix;
 	int cache_bottom;
 	struct dir_struct *dir;
+	struct path_exclude_check *path_exclude_check;
 	struct pathspec *pathspec;
 	merge_fn_t fn;
 	const char *msgs[NB_UNPACK_TREES_ERROR_TYPES];