summaryrefslogtreecommitdiff
path: root/dir.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2007-03-30 20:39:30 -0700
committerJunio C Hamano <junkio@cox.net>2007-03-31 17:41:32 -0700
commit9fc42d609197ef331f1c5b2ce5ef6fc9f2ee634f (patch)
treeb59890e73a673167a4db90d85782851464c758f1 /dir.c
parentd8b6a1a10b93666246984a50d64a163e71163aeb (diff)
downloadgit-9fc42d609197ef331f1c5b2ce5ef6fc9f2ee634f.tar.gz
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the "read_directory()" function. If you pass NULL, it acts exactly like it used to do (read everything). If you pass a non-NULL pointer, it will simplify it into a "these are the prefixes without any special characters", and stop any readdir() early if the path in question doesn't match any of the prefixes. NOTE! This does *not* obviate the need for the caller to do the *exact* pathspec match later. It's a first-level filter on "read_directory()", but it does not do the full pathspec thing. Maybe it should. But in the meantime, builtin-add.c really does need to do first read_directory(dir, .., pathspec); if (pathspec) prune_directory(dir, pathspec, baselen); ie the "prune_directory()" part will do the *exact* pathspec pruning, while the "read_directory()" will use the pathspec just to do some quick high-level pruning of the directories it will recurse into. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
Diffstat (limited to 'dir.c')
-rw-r--r--dir.c96
1 files changed, 91 insertions, 5 deletions
diff --git a/dir.c b/dir.c
index b48e19dc09..7426fde330 100644
--- a/dir.c
+++ b/dir.c
@@ -8,6 +8,11 @@
#include "cache.h"
#include "dir.h"
+struct path_simplify {
+ int len;
+ const char *path;
+};
+
int common_prefix(const char **pathspec)
{
const char *path, *slash, *next;
@@ -293,6 +298,31 @@ static int dir_exists(const char *dirname, int len)
}
/*
+ * This is an inexact early pruning of any recursive directory
+ * reading - if the path cannot possibly be in the pathspec,
+ * return true, and we'll skip it early.
+ */
+static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
+{
+ if (simplify) {
+ for (;;) {
+ const char *match = simplify->path;
+ int len = simplify->len;
+
+ if (!match)
+ break;
+ if (len > pathlen)
+ len = pathlen;
+ if (!memcmp(path, match, len))
+ return 0;
+ simplify++;
+ }
+ return 1;
+ }
+ return 0;
+}
+
+/*
* Read a directory tree. We currently ignore anything but
* directories, regular files and symlinks. That's because git
* doesn't handle them at all yet. Maybe that will change some
@@ -301,7 +331,7 @@ static int dir_exists(const char *dirname, int len)
* Also, we ignore the name ".git" (even if it is not a directory).
* That likely will not change.
*/
-static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen, int check_only)
+static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen, int check_only, const struct path_simplify *simplify)
{
DIR *fdir = opendir(path);
int contents = 0;
@@ -324,6 +354,8 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
continue;
len = strlen(de->d_name);
memcpy(fullname + baselen, de->d_name, len+1);
+ if (simplify_away(fullname, baselen + len, simplify))
+ continue;
if (excluded(dir, fullname) != dir->show_ignored) {
if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
continue;
@@ -350,13 +382,13 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
if (dir->hide_empty_directories &&
!read_directory_recursive(dir,
fullname, fullname,
- baselen + len, 1))
+ baselen + len, 1, simplify))
continue;
break;
}
contents += read_directory_recursive(dir,
- fullname, fullname, baselen + len, 0);
+ fullname, fullname, baselen + len, 0, simplify);
continue;
case DT_REG:
case DT_LNK:
@@ -386,8 +418,61 @@ static int cmp_name(const void *p1, const void *p2)
e2->name, e2->len);
}
-int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen)
+/*
+ * Return the length of the "simple" part of a path match limiter.
+ */
+static int simple_length(const char *match)
{
+ const char special[256] = {
+ [0] = 1, ['?'] = 1,
+ ['\\'] = 1, ['*'] = 1,
+ ['['] = 1
+ };
+ int len = -1;
+
+ for (;;) {
+ unsigned char c = *match++;
+ len++;
+ if (special[c])
+ return len;
+ }
+}
+
+static struct path_simplify *create_simplify(const char **pathspec)
+{
+ int nr, alloc = 0;
+ struct path_simplify *simplify = NULL;
+
+ if (!pathspec)
+ return NULL;
+
+ for (nr = 0 ; ; nr++) {
+ const char *match;
+ if (nr >= alloc) {
+ alloc = alloc_nr(alloc);
+ simplify = xrealloc(simplify, alloc * sizeof(*simplify));
+ }
+ match = *pathspec++;
+ if (!match)
+ break;
+ simplify[nr].path = match;
+ simplify[nr].len = simple_length(match);
+ }
+ simplify[nr].path = NULL;
+ simplify[nr].len = 0;
+ return simplify;
+}
+
+static void free_simplify(struct path_simplify *simplify)
+{
+ if (simplify)
+ free(simplify);
+}
+
+int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen, const char **pathspec)
+{
+ struct path_simplify *simplify = create_simplify(pathspec);
+
/*
* Make sure to do the per-directory exclude for all the
* directories leading up to our base.
@@ -414,7 +499,8 @@ int read_directory(struct dir_struct *dir, const char *path, const char *base, i
}
}
- read_directory_recursive(dir, path, base, baselen, 0);
+ read_directory_recursive(dir, path, base, baselen, 0, simplify);
+ free_simplify(simplify);
qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
return dir->nr;
}