*/
#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)
{
prefix = slash - path + 1;
while ((next = *++pathspec) != NULL) {
int len = strlen(next);
- if (len >= prefix && !memcmp(path, next, len))
+ if (len >= prefix && !memcmp(path, next, prefix))
continue;
+ len = prefix - 1;
for (;;) {
if (!len)
return 0;
return 0;
}
-struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
-{
+static struct dir_entry *dir_entry_new(const char *pathname, int len) {
struct dir_entry *ent;
- if (cache_name_pos(pathname, len) >= 0)
- return NULL;
-
- if (dir->nr == dir->alloc) {
- int alloc = alloc_nr(dir->alloc);
- dir->alloc = alloc;
- dir->entries = xrealloc(dir->entries, alloc*sizeof(ent));
- }
ent = xmalloc(sizeof(*ent) + len + 1);
- ent->ignored = ent->ignored_dir = 0;
ent->len = len;
memcpy(ent->name, pathname, len);
ent->name[len] = 0;
- dir->entries[dir->nr++] = ent;
return ent;
}
-static int dir_exists(const char *dirname, int len)
+struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
+{
+ if (cache_name_pos(pathname, len) >= 0)
+ return NULL;
+
+ ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
+ return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
+}
+
+struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
+{
+ if (cache_name_pos(pathname, len) >= 0)
+ return NULL;
+
+ ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
+ return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, 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_ISGITLINK(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_gitlinks' 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_gitlinks) {
+ 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;
+}
+
+static int in_pathspec(const char *path, int len, const struct path_simplify *simplify)
+{
+ if (simplify) {
+ for (; simplify->path; simplify++) {
+ if (len == simplify->len
+ && !memcmp(path, simplify->path, len))
+ return 1;
+ }
+ }
+ return 0;
+}
+
+static int get_dtype(struct dirent *de, const char *path)
+{
+ int dtype = DTYPE(de);
+ struct stat st;
+
+ if (dtype != DT_UNKNOWN)
+ return dtype;
+ if (lstat(path, &st))
+ return dtype;
+ if (S_ISREG(st.st_mode))
+ return DT_REG;
+ if (S_ISDIR(st.st_mode))
+ return DT_DIR;
+ if (S_ISLNK(st.st_mode))
+ return DT_LNK;
+ return dtype;
}
/*
* 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;
exclude_stk = push_exclude_per_directory(dir, base, baselen);
while ((de = readdir(fdir)) != NULL) {
- int len;
+ int len, dtype;
+ int exclude;
if ((de->d_name[0] == '.') &&
(de->d_name[1] == 0 ||
!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 (excluded(dir, fullname) != dir->show_ignored) {
- if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
+ if (simplify_away(fullname, baselen + len, simplify))
+ continue;
+
+ exclude = excluded(dir, fullname);
+ if (exclude && dir->collect_ignored
+ && in_pathspec(fullname, baselen + len, simplify))
+ dir_add_ignored(dir, fullname, baselen + len);
+
+ /*
+ * Excluded? If we don't explicitly want to show
+ * ignored files, ignore it
+ */
+ if (exclude && !dir->show_ignored)
+ continue;
+
+ dtype = get_dtype(de, fullname);
+
+ /*
+ * Do we want to see just the ignored files?
+ * We still need to recurse into directories,
+ * even if we don't ignore them, since the
+ * directory may contain files that we do..
+ */
+ if (!exclude && dir->show_ignored) {
+ if (dtype != DT_DIR)
continue;
- }
}
- switch (DTYPE(de)) {
- struct stat st;
+ switch (dtype) {
default:
continue;
- case DT_UNKNOWN:
- if (lstat(fullname, &st))
- continue;
- if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode))
- break;
- if (!S_ISDIR(st.st_mode))
- continue;
- /* fallthrough */
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))
+ switch (treat_directory(dir, fullname, baselen + len, simplify)) {
+ case show_directory:
+ if (exclude != dir->show_ignored)
continue;
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;
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.
}
}
- 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);
+ qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
return dir->nr;
}
struct stat sb;
return stat(f, &sb) == 0;
}
+
+/*
+ * get_relative_cwd() gets the prefix of the current working directory
+ * relative to 'dir'. If we are not inside 'dir', it returns NULL.
+ *
+ * As a convenience, it also returns NULL if 'dir' is already NULL. The
+ * reason for this behaviour is that it is natural for functions returning
+ * directory names to return NULL to say "this directory does not exist"
+ * or "this directory is invalid". These cases are usually handled the
+ * same as if the cwd is not inside 'dir' at all, so get_relative_cwd()
+ * returns NULL for both of them.
+ *
+ * Most notably, get_relative_cwd(buffer, size, get_git_work_tree())
+ * unifies the handling of "outside work tree" with "no work tree at all".
+ */
+char *get_relative_cwd(char *buffer, int size, const char *dir)
+{
+ char *cwd = buffer;
+
+ if (!dir)
+ return NULL;
+ if (!getcwd(buffer, size))
+ die("can't find the current directory: %s", strerror(errno));
+
+ if (!is_absolute_path(dir))
+ dir = make_absolute_path(dir);
+
+ while (*dir && *dir == *cwd) {
+ dir++;
+ cwd++;
+ }
+ if (*dir)
+ return NULL;
+ if (*cwd == '/')
+ return cwd + 1;
+ return cwd;
+}
+
+int is_inside_dir(const char *dir)
+{
+ char buffer[PATH_MAX];
+ return get_relative_cwd(buffer, sizeof(buffer), dir) != NULL;
+}