summaryrefslogtreecommitdiff
path: root/dir.c
diff options
context:
space:
mode:
Diffstat (limited to 'dir.c')
-rw-r--r--dir.c228
1 files changed, 208 insertions, 20 deletions
diff --git a/dir.c b/dir.c
index 602282b..d306352 100644
--- a/dir.c
+++ b/dir.c
@@ -7,6 +7,16 @@
*/
#include "cache.h"
#include "dir.h"
+#include "refs.h"
+
+struct path_simplify {
+ int len;
+ const char *path;
+};
+
+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);
int common_prefix(const char **pathspec)
{
@@ -282,15 +292,136 @@ struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int
return ent;
}
-static int dir_exists(const char *dirname, int len)
+enum exist_status {
+ index_nonexistent = 0,
+ index_directory,
+ index_gitdir,
+};
+
+/*
+ * The index sorts alphabetically by entry name, which
+ * means that a gitlink sorts as '\0' at the end, while
+ * a directory (which is defined not as an entry, but as
+ * the files it contains) will sort with the '/' at the
+ * end.
+ */
+static enum exist_status directory_exists_in_index(const char *dirname, int len)
{
int pos = cache_name_pos(dirname, len);
- if (pos >= 0)
+ if (pos < 0)
+ pos = -pos-1;
+ while (pos < active_nr) {
+ struct cache_entry *ce = active_cache[pos++];
+ unsigned char endchar;
+
+ if (strncmp(ce->name, dirname, len))
+ break;
+ endchar = ce->name[len];
+ if (endchar > '/')
+ break;
+ if (endchar == '/')
+ return index_directory;
+ if (!endchar && S_ISDIRLNK(ntohl(ce->ce_mode)))
+ return index_gitdir;
+ }
+ return index_nonexistent;
+}
+
+/*
+ * When we find a directory when traversing the filesystem, we
+ * have three distinct cases:
+ *
+ * - ignore it
+ * - see it as a directory
+ * - recurse into it
+ *
+ * and which one we choose depends on a combination of existing
+ * git index contents and the flags passed into the directory
+ * traversal routine.
+ *
+ * Case 1: If we *already* have entries in the index under that
+ * directory name, we always recurse into the directory to see
+ * all the files.
+ *
+ * Case 2: If we *already* have that directory name as a gitlink,
+ * we always continue to see it as a gitlink, regardless of whether
+ * there is an actual git directory there or not (it might not
+ * be checked out as a subproject!)
+ *
+ * Case 3: if we didn't have it in the index previously, we
+ * have a few sub-cases:
+ *
+ * (a) if "show_other_directories" is true, we show it as
+ * just a directory, unless "hide_empty_directories" is
+ * also true and the directory is empty, in which case
+ * we just ignore it entirely.
+ * (b) if it looks like a git directory, and we don't have
+ * 'no_dirlinks' set we treat it as a gitlink, and show it
+ * as a directory.
+ * (c) otherwise, we recurse into it.
+ */
+enum directory_treatment {
+ show_directory,
+ ignore_directory,
+ recurse_into_directory,
+};
+
+static enum directory_treatment treat_directory(struct dir_struct *dir,
+ const char *dirname, int len,
+ const struct path_simplify *simplify)
+{
+ /* The "len-1" is to strip the final '/' */
+ switch (directory_exists_in_index(dirname, len-1)) {
+ case index_directory:
+ return recurse_into_directory;
+
+ case index_gitdir:
+ if (dir->show_other_directories)
+ return ignore_directory;
+ return show_directory;
+
+ case index_nonexistent:
+ if (dir->show_other_directories)
+ break;
+ if (!dir->no_dirlinks) {
+ unsigned char sha1[20];
+ if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
+ return show_directory;
+ }
+ return recurse_into_directory;
+ }
+
+ /* This is the "show_other_directories" case */
+ if (!dir->hide_empty_directories)
+ return show_directory;
+ if (!read_directory_recursive(dir, dirname, dirname, len, 1, simplify))
+ return ignore_directory;
+ return show_directory;
+}
+
+/*
+ * 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;
- pos = -pos-1;
- if (pos >= active_nr) /* can't */
- return 0;
- return !strncmp(active_cache[pos]->name, dirname, len);
+ }
+ return 0;
}
/*
@@ -302,7 +433,7 @@ 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;
@@ -324,7 +455,12 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
!strcmp(de->d_name + 1, "git")))
continue;
len = strlen(de->d_name);
+ /* Ignore overly long pathnames! */
+ if (len + baselen + 8 > sizeof(fullname))
+ continue;
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;
@@ -346,19 +482,17 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
case DT_DIR:
memcpy(fullname + baselen + len, "/", 2);
len++;
- if (dir->show_other_directories &&
- !dir_exists(fullname, baselen + len)) {
- if (dir->hide_empty_directories &&
- !read_directory_recursive(dir,
- fullname, fullname,
- baselen + len, 1))
- continue;
+ switch (treat_directory(dir, fullname, baselen + len, simplify)) {
+ case show_directory:
break;
+ case recurse_into_directory:
+ contents += read_directory_recursive(dir,
+ fullname, fullname, baselen + len, 0, simplify);
+ continue;
+ case ignore_directory:
+ continue;
}
-
- contents += read_directory_recursive(dir,
- fullname, fullname, baselen + len, 0);
- continue;
+ break;
case DT_REG:
case DT_LNK:
break;
@@ -387,8 +521,61 @@ 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.
@@ -415,7 +602,8 @@ 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;
}