1 files changed, 646 insertions, 210 deletions

diff --git a/dir.c b/dir.c
index e05b850acf..2c02b312b7 100644
--- a/dir.c
+++ b/dir.c
@@ -18,59 +18,90 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, in
 	int check_only, const struct path_simplify *simplify);
 static int get_dtype(struct dirent *de, const char *path, int len);
 
-static int common_prefix(const char **pathspec)
+/* helper string functions with support for the ignore_case flag */
+int strcmp_icase(const char *a, const char *b)
 {
-	const char *path, *slash, *next;
-	int prefix;
+	return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
+}
 
-	if (!pathspec)
-		return 0;
+int strncmp_icase(const char *a, const char *b, size_t count)
+{
+	return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
+}
 
-	path = *pathspec;
-	slash = strrchr(path, '/');
-	if (!slash)
-		return 0;
+int fnmatch_icase(const char *pattern, const char *string, int flags)
+{
+	return fnmatch(pattern, string, flags | (ignore_case ? FNM_CASEFOLD : 0));
+}
 
-	prefix = slash - path + 1;
-	while ((next = *++pathspec) != NULL) {
-		int len = strlen(next);
-		if (len >= prefix && !memcmp(path, next, prefix))
-			continue;
-		len = prefix - 1;
-		for (;;) {
-			if (!len)
-				return 0;
-			if (next[--len] != '/')
-				continue;
-			if (memcmp(path, next, len+1))
-				continue;
-			prefix = len + 1;
-			break;
+static size_t common_prefix_len(const char **pathspec)
+{
+	const char *n, *first;
+	size_t max = 0;
+
+	if (!pathspec)
+		return max;
+
+	first = *pathspec;
+	while ((n = *pathspec++)) {
+		size_t i, len = 0;
+		for (i = 0; first == n || i < max; i++) {
+			char c = n[i];
+			if (!c || c != first[i] || is_glob_special(c))
+				break;
+			if (c == '/')
+				len = i + 1;
+		}
+		if (first == n || len < max) {
+			max = len;
+			if (!max)
+				break;
 		}
 	}
-	return prefix;
+	return max;
+}
+
+/*
+ * Returns a copy of the longest leading path common among all
+ * pathspecs.
+ */
+char *common_prefix(const char **pathspec)
+{
+	unsigned long len = common_prefix_len(pathspec);
+
+	return len ? xmemdupz(*pathspec, len) : NULL;
 }
 
 int fill_directory(struct dir_struct *dir, const char **pathspec)
 {
-	const char *path;
-	int len;
+	size_t len;
 
 	/*
 	 * Calculate common prefix for the pathspec, and
 	 * use that to optimize the directory walk
 	 */
-	len = common_prefix(pathspec);
-	path = "";
-
-	if (len)
-		path = xmemdupz(*pathspec, len);
+	len = common_prefix_len(pathspec);
 
 	/* Read the directory and prune it */
-	read_directory(dir, path, len, pathspec);
+	read_directory(dir, pathspec ? *pathspec : "", len, pathspec);
 	return len;
 }
 
+int within_depth(const char *name, int namelen,
+			int depth, int max_depth)
+{
+	const char *cp = name, *cpe = name + namelen;
+
+	while (cp < cpe) {
+		if (*cp++ != '/')
+			continue;
+		depth++;
+		if (depth > max_depth)
+			return 0;
+	}
+	return 1;
+}
+
 /*
  * Does 'match' match the given name?
  * A match is found if
@@ -91,16 +122,30 @@ static int match_one(const char *match, const char *name, int namelen)
 	if (!*match)
 		return MATCHED_RECURSIVELY;
 
-	for (;;) {
-		unsigned char c1 = *match;
-		unsigned char c2 = *name;
-		if (c1 == '\0' || is_glob_special(c1))
-			break;
-		if (c1 != c2)
-			return 0;
-		match++;
-		name++;
-		namelen--;
+	if (ignore_case) {
+		for (;;) {
+			unsigned char c1 = tolower(*match);
+			unsigned char c2 = tolower(*name);
+			if (c1 == '\0' || is_glob_special(c1))
+				break;
+			if (c1 != c2)
+				return 0;
+			match++;
+			name++;
+			namelen--;
+		}
+	} else {
+		for (;;) {
+			unsigned char c1 = *match;
+			unsigned char c2 = *name;
+			if (c1 == '\0' || is_glob_special(c1))
+				break;
+			if (c1 != c2)
+				return 0;
+			match++;
+			name++;
+			namelen--;
+		}
 	}
 
 
@@ -109,8 +154,8 @@ static int match_one(const char *match, const char *name, int namelen)
 	 * we need to match by fnmatch
 	 */
 	matchlen = strlen(match);
-	if (strncmp(match, name, matchlen))
-		return !fnmatch(match, name, 0) ? MATCHED_FNMATCH : 0;
+	if (strncmp_icase(match, name, matchlen))
+		return !fnmatch_icase(match, name, 0) ? MATCHED_FNMATCH : 0;
 
 	if (namelen == matchlen)
 		return MATCHED_EXACTLY;
@@ -154,6 +199,95 @@ int match_pathspec(const char **pathspec, const char *name, int namelen,
 	return retval;
 }
 
+/*
+ * Does 'match' match the given name?
+ * A match is found if
+ *
+ * (1) the 'match' string is leading directory of 'name', or
+ * (2) the 'match' string is a wildcard and matches 'name', or
+ * (3) the 'match' string is exactly the same as 'name'.
+ *
+ * and the return value tells which case it was.
+ *
+ * It returns 0 when there is no match.
+ */
+static int match_pathspec_item(const struct pathspec_item *item, int prefix,
+			       const char *name, int namelen)
+{
+	/* name/namelen has prefix cut off by caller */
+	const char *match = item->match + prefix;
+	int matchlen = item->len - prefix;
+
+	/* If the match was just the prefix, we matched */
+	if (!*match)
+		return MATCHED_RECURSIVELY;
+
+	if (matchlen <= namelen && !strncmp(match, name, matchlen)) {
+		if (matchlen == namelen)
+			return MATCHED_EXACTLY;
+
+		if (match[matchlen-1] == '/' || name[matchlen] == '/')
+			return MATCHED_RECURSIVELY;
+	}
+
+	if (item->use_wildcard && !fnmatch(match, name, 0))
+		return MATCHED_FNMATCH;
+
+	return 0;
+}
+
+/*
+ * Given a name and a list of pathspecs, see if the name matches
+ * any of the pathspecs.  The caller is also interested in seeing
+ * all pathspec matches some names it calls this function with
+ * (otherwise the user could have mistyped the unmatched pathspec),
+ * and a mark is left in seen[] array for pathspec element that
+ * actually matched anything.
+ */
+int match_pathspec_depth(const struct pathspec *ps,
+			 const char *name, int namelen,
+			 int prefix, char *seen)
+{
+	int i, retval = 0;
+
+	if (!ps->nr) {
+		if (!ps->recursive || ps->max_depth == -1)
+			return MATCHED_RECURSIVELY;
+
+		if (within_depth(name, namelen, 0, ps->max_depth))
+			return MATCHED_EXACTLY;
+		else
+			return 0;
+	}
+
+	name += prefix;
+	namelen -= prefix;
+
+	for (i = ps->nr - 1; i >= 0; i--) {
+		int how;
+		if (seen && seen[i] == MATCHED_EXACTLY)
+			continue;
+		how = match_pathspec_item(ps->items+i, prefix, name, namelen);
+		if (ps->recursive && ps->max_depth != -1 &&
+		    how && how != MATCHED_FNMATCH) {
+			int len = ps->items[i].len;
+			if (name[len] == '/')
+				len++;
+			if (within_depth(name+len, namelen-len, 0, ps->max_depth))
+				how = MATCHED_EXACTLY;
+			else
+				how = 0;
+		}
+		if (how) {
+			if (retval < how)
+				retval = how;
+			if (seen && seen[i] < how)
+				seen[i] = how;
+		}
+	}
+	return retval;
+}
+
 static int no_wildcard(const char *string)
 {
 	return string[strcspn(string, "*?[{\\")] == '\0';
@@ -200,36 +334,87 @@ void add_exclude(const char *string, const char *base,
 	which->excludes[which->nr++] = x;
 }
 
-static int add_excludes_from_file_1(const char *fname,
-				    const char *base,
-				    int baselen,
-				    char **buf_p,
-				    struct exclude_list *which)
+static void *read_skip_worktree_file_from_index(const char *path, size_t *size)
+{
+	int pos, len;
+	unsigned long sz;
+	enum object_type type;
+	void *data;
+	struct index_state *istate = &the_index;
+
+	len = strlen(path);
+	pos = index_name_pos(istate, path, len);
+	if (pos < 0)
+		return NULL;
+	if (!ce_skip_worktree(istate->cache[pos]))
+		return NULL;
+	data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz);
+	if (!data || type != OBJ_BLOB) {
+		free(data);
+		return NULL;
+	}
+	*size = xsize_t(sz);
+	return data;
+}
+
+void free_excludes(struct exclude_list *el)
+{
+	int i;
+
+	for (i = 0; i < el->nr; i++)
+		free(el->excludes[i]);
+	free(el->excludes);
+
+	el->nr = 0;
+	el->excludes = NULL;
+}
+
+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)
 {
 	struct stat st;
 	int fd, i;
-	size_t size;
+	size_t size = 0;
 	char *buf, *entry;
 
 	fd = open(fname, O_RDONLY);
-	if (fd < 0 || fstat(fd, &st) < 0)
-		goto err;
-	size = xsize_t(st.st_size);
-	if (size == 0) {
-		close(fd);
-		return 0;
+	if (fd < 0 || fstat(fd, &st) < 0) {
+		if (0 <= fd)
+			close(fd);
+		if (!check_index ||
+		    (buf = read_skip_worktree_file_from_index(fname, &size)) == NULL)
+			return -1;
+		if (size == 0) {
+			free(buf);
+			return 0;
+		}
+		if (buf[size-1] != '\n') {
+			buf = xrealloc(buf, size+1);
+			buf[size++] = '\n';
+		}
 	}
-	buf = xmalloc(size+1);
-	if (read_in_full(fd, buf, size) != size)
-	{
-		free(buf);
-		goto err;
+	else {
+		size = xsize_t(st.st_size);
+		if (size == 0) {
+			close(fd);
+			return 0;
+		}
+		buf = xmalloc(size+1);
+		if (read_in_full(fd, buf, size) != size) {
+			free(buf);
+			close(fd);
+			return -1;
+		}
+		buf[size++] = '\n';
+		close(fd);
 	}
-	close(fd);
 
 	if (buf_p)
 		*buf_p = buf;
-	buf[size++] = '\n';
 	entry = buf;
 	for (i = 0; i < size; i++) {
 		if (buf[i] == '\n') {
@@ -241,17 +426,12 @@ static int add_excludes_from_file_1(const char *fname,
 		}
 	}
 	return 0;
-
- err:
-	if (0 <= fd)
-		close(fd);
-	return -1;
 }
 
 void add_excludes_from_file(struct dir_struct *dir, const char *fname)
 {
-	if (add_excludes_from_file_1(fname, "", 0, NULL,
-				     &dir->exclude_list[EXC_FILE]) < 0)
+	if (add_excludes_from_file_to_list(fname, "", 0, NULL,
+					   &dir->exclude_list[EXC_FILE], 0) < 0)
 		die("cannot use %s as an exclude file", fname);
 }
 
@@ -300,9 +480,9 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 		memcpy(dir->basebuf + current, base + current,
 		       stk->baselen - current);
 		strcpy(dir->basebuf + stk->baselen, dir->exclude_per_dir);
-		add_excludes_from_file_1(dir->basebuf,
-					 dir->basebuf, stk->baselen,
-					 &stk->filebuf, el);
+		add_excludes_from_file_to_list(dir->basebuf,
+					       dir->basebuf, stk->baselen,
+					       &stk->filebuf, el, 1);
 		dir->exclude_stack = stk;
 		current = stk->baselen;
 	}
@@ -312,9 +492,9 @@ static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
 /* Scan the list and let the last match determine the fate.
  * Return 1 for exclude, 0 for include and -1 for undecided.
  */
-static int excluded_1(const char *pathname,
-		      int pathlen, const char *basename, int *dtype,
-		      struct exclude_list *el)
+int excluded_from_list(const char *pathname,
+		       int pathlen, const char *basename, int *dtype,
+		       struct exclude_list *el)
 {
 	int i;
 
@@ -334,14 +514,14 @@ static int excluded_1(const char *pathname,
 			if (x->flags & EXC_FLAG_NODIR) {
 				/* match basename */
 				if (x->flags & EXC_FLAG_NOWILDCARD) {
-					if (!strcmp(exclude, basename))
+					if (!strcmp_icase(exclude, basename))
 						return to_exclude;
 				} else if (x->flags & EXC_FLAG_ENDSWITH) {
 					if (x->patternlen - 1 <= pathlen &&
-					    !strcmp(exclude + 1, pathname + pathlen - x->patternlen + 1))
+					    !strcmp_icase(exclude + 1, pathname + pathlen - x->patternlen + 1))
 						return to_exclude;
 				} else {
-					if (fnmatch(exclude, basename, 0) == 0)
+					if (fnmatch_icase(exclude, basename, 0) == 0)
 						return to_exclude;
 				}
 			}
@@ -356,14 +536,14 @@ static int excluded_1(const char *pathname,
 
 				if (pathlen < baselen ||
 				    (baselen && pathname[baselen-1] != '/') ||
-				    strncmp(pathname, x->base, baselen))
+				    strncmp_icase(pathname, x->base, baselen))
 				    continue;
 
 				if (x->flags & EXC_FLAG_NOWILDCARD) {
-					if (!strcmp(exclude, pathname + baselen))
+					if (!strcmp_icase(exclude, pathname + baselen))
 						return to_exclude;
 				} else {
-					if (fnmatch(exclude, pathname+baselen,
+					if (fnmatch_icase(exclude, pathname+baselen,
 						    FNM_PATHNAME) == 0)
 					    return to_exclude;
 				}
@@ -373,7 +553,7 @@ static int excluded_1(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;
@@ -382,8 +562,8 @@ int excluded(struct dir_struct *dir, const char *pathname, int *dtype_p)
 
 	prep_exclude(dir, pathname, basename-pathname);
 	for (st = EXC_CMDL; st <= EXC_FILE; st++) {
-		switch (excluded_1(pathname, pathlen, basename,
-				   dtype_p, &dir->exclude_list[st])) {
+		switch (excluded_from_list(pathname, pathlen, basename,
+					   dtype_p, &dir->exclude_list[st])) {
 		case 0:
 			return 0;
 		case 1:
@@ -393,6 +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;
@@ -413,7 +651,7 @@ static struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathna
 	return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
 }
 
-static struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
+struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
 {
 	if (!cache_name_is_other(pathname, len))
 		return NULL;
@@ -425,10 +663,43 @@ static struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pat
 enum exist_status {
 	index_nonexistent = 0,
 	index_directory,
-	index_gitdir,
+	index_gitdir
 };
 
 /*
+ * Do not use the alphabetically stored index to look up
+ * the directory name; instead, use the case insensitive
+ * name hash.
+ */
+static enum exist_status directory_exists_in_index_icase(const char *dirname, int len)
+{
+	struct cache_entry *ce = index_name_exists(&the_index, dirname, len + 1, ignore_case);
+	unsigned char endchar;
+
+	if (!ce)
+		return index_nonexistent;
+	endchar = ce->name[len];
+
+	/*
+	 * The cache_entry structure returned will contain this dirname
+	 * and possibly additional path components.
+	 */
+	if (endchar == '/')
+		return index_directory;
+
+	/*
+	 * If there are no additional path components, then this cache_entry
+	 * represents a submodule.  Submodules, despite being directories,
+	 * are stored in the cache without a closing slash.
+	 */
+	if (!endchar && S_ISGITLINK(ce->ce_mode))
+		return index_gitdir;
+
+	/* This should never be hit, but it exists just in case. */
+	return index_nonexistent;
+}
+
+/*
  * 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
@@ -437,7 +708,12 @@ enum exist_status {
  */
 static enum exist_status directory_exists_in_index(const char *dirname, int len)
 {
-	int pos = cache_name_pos(dirname, len);
+	int pos;
+
+	if (ignore_case)
+		return directory_exists_in_index_icase(dirname, len);
+
+	pos = cache_name_pos(dirname, len);
 	if (pos < 0)
 		pos = -pos-1;
 	while (pos < active_nr) {
@@ -493,7 +769,7 @@ static enum exist_status directory_exists_in_index(const char *dirname, int len)
 enum directory_treatment {
 	show_directory,
 	ignore_directory,
-	recurse_into_directory,
+	recurse_into_directory
 };
 
 static enum directory_treatment treat_directory(struct dir_struct *dir,
@@ -554,13 +830,29 @@ static int simplify_away(const char *path, int pathlen, const struct path_simpli
 	return 0;
 }
 
-static int in_pathspec(const char *path, int len, const struct path_simplify *simplify)
+/*
+ * This function tells us whether an excluded path matches a
+ * list of "interesting" pathspecs. That is, whether a path matched
+ * by any of the pathspecs could possibly be ignored by excluding
+ * the specified path. This can happen if:
+ *
+ *   1. the path is mentioned explicitly in the pathspec
+ *
+ *   2. the path is a directory prefix of some element in the
+ *      pathspec
+ */
+static int exclude_matches_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;
+			if (len < simplify->len
+			    && simplify->path[len] == '/'
+			    && !memcmp(path, simplify->path, len))
+				return 1;
 		}
 	}
 	return 0;
@@ -625,6 +917,86 @@ static int get_dtype(struct dirent *de, const char *path, int len)
 	return dtype;
 }
 
+enum path_treatment {
+	path_ignored,
+	path_handled,
+	path_recurse
+};
+
+static enum path_treatment treat_one_path(struct dir_struct *dir,
+					  struct strbuf *path,
+					  const struct path_simplify *simplify,
+					  int dtype, struct dirent *de)
+{
+	int exclude = excluded(dir, path->buf, &dtype);
+	if (exclude && (dir->flags & DIR_COLLECT_IGNORED)
+	    && exclude_matches_pathspec(path->buf, path->len, simplify))
+		dir_add_ignored(dir, path->buf, path->len);
+
+	/*
+	 * Excluded? If we don't explicitly want to show
+	 * ignored files, ignore it
+	 */
+	if (exclude && !(dir->flags & DIR_SHOW_IGNORED))
+		return path_ignored;
+
+	if (dtype == DT_UNKNOWN)
+		dtype = get_dtype(de, path->buf, path->len);
+
+	/*
+	 * 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->flags & DIR_SHOW_IGNORED)) {
+		if (dtype != DT_DIR)
+			return path_ignored;
+	}
+
+	switch (dtype) {
+	default:
+		return path_ignored;
+	case DT_DIR:
+		strbuf_addch(path, '/');
+		switch (treat_directory(dir, path->buf, path->len, simplify)) {
+		case show_directory:
+			if (exclude != !!(dir->flags
+					  & DIR_SHOW_IGNORED))
+				return path_ignored;
+			break;
+		case recurse_into_directory:
+			return path_recurse;
+		case ignore_directory:
+			return path_ignored;
+		}
+		break;
+	case DT_REG:
+	case DT_LNK:
+		break;
+	}
+	return path_handled;
+}
+
+static enum path_treatment treat_path(struct dir_struct *dir,
+				      struct dirent *de,
+				      struct strbuf *path,
+				      int baselen,
+				      const struct path_simplify *simplify)
+{
+	int dtype;
+
+	if (is_dot_or_dotdot(de->d_name) || !strcmp(de->d_name, ".git"))
+		return path_ignored;
+	strbuf_setlen(path, baselen);
+	strbuf_addstr(path, de->d_name);
+	if (simplify_away(path->buf, path->len, simplify))
+		return path_ignored;
+
+	dtype = DTYPE(de);
+	return treat_one_path(dir, path, simplify, dtype, de);
+}
+
 /*
  * Read a directory tree. We currently ignore anything but
  * directories, regular files and symlinks. That's because git
@@ -634,92 +1006,42 @@ static int get_dtype(struct dirent *de, const char *path, 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 *base, int baselen, int check_only, const struct path_simplify *simplify)
+static int read_directory_recursive(struct dir_struct *dir,
+				    const char *base, int baselen,
+				    int check_only,
+				    const struct path_simplify *simplify)
 {
-	DIR *fdir = opendir(*base ? base : ".");
+	DIR *fdir;
 	int contents = 0;
+	struct dirent *de;
+	struct strbuf path = STRBUF_INIT;
 
-	if (fdir) {
-		struct dirent *de;
-		char path[PATH_MAX + 1];
-		memcpy(path, base, baselen);
-
-		while ((de = readdir(fdir)) != NULL) {
-			int len, dtype;
-			int exclude;
-
-			if (is_dot_or_dotdot(de->d_name) ||
-			     !strcmp(de->d_name, ".git"))
-				continue;
-			len = strlen(de->d_name);
-			/* Ignore overly long pathnames! */
-			if (len + baselen + 8 > sizeof(path))
-				continue;
-			memcpy(path + baselen, de->d_name, len+1);
-			len = baselen + len;
-			if (simplify_away(path, len, simplify))
-				continue;
-
-			dtype = DTYPE(de);
-			exclude = excluded(dir, path, &dtype);
-			if (exclude && (dir->flags & DIR_COLLECT_IGNORED)
-			    && in_pathspec(path, len, simplify))
-				dir_add_ignored(dir, path,len);
-
-			/*
-			 * Excluded? If we don't explicitly want to show
-			 * ignored files, ignore it
-			 */
-			if (exclude && !(dir->flags & DIR_SHOW_IGNORED))
-				continue;
-
-			if (dtype == DT_UNKNOWN)
-				dtype = get_dtype(de, path, len);
-
-			/*
-			 * 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->flags & DIR_SHOW_IGNORED)) {
-				if (dtype != DT_DIR)
-					continue;
-			}
+	strbuf_add(&path, base, baselen);
 
-			switch (dtype) {
-			default:
-				continue;
-			case DT_DIR:
-				memcpy(path + len, "/", 2);
-				len++;
-				switch (treat_directory(dir, path, len, simplify)) {
-				case show_directory:
-					if (exclude != !!(dir->flags
-							& DIR_SHOW_IGNORED))
-						continue;
-					break;
-				case recurse_into_directory:
-					contents += read_directory_recursive(dir,
-						path, len, 0, simplify);
-					continue;
-				case ignore_directory:
-					continue;
-				}
-				break;
-			case DT_REG:
-			case DT_LNK:
-				break;
-			}
-			contents++;
-			if (check_only)
-				goto exit_early;
-			else
-				dir_add_name(dir, path, len);
+	fdir = opendir(path.len ? path.buf : ".");
+	if (!fdir)
+		goto out;
+
+	while ((de = readdir(fdir)) != NULL) {
+		switch (treat_path(dir, de, &path, baselen, simplify)) {
+		case path_recurse:
+			contents += read_directory_recursive(dir, path.buf,
+							     path.len, 0,
+							     simplify);
+			continue;
+		case path_ignored:
+			continue;
+		case path_handled:
+			break;
 		}
-exit_early:
-		closedir(fdir);
+		contents++;
+		if (check_only)
+			break;
+		dir_add_name(dir, path.buf, path.len);
 	}
+	closedir(fdir);
+ out:
+	strbuf_release(&path);
 
 	return contents;
 }
@@ -778,6 +1100,44 @@ static void free_simplify(struct path_simplify *simplify)
 	free(simplify);
 }
 
+static int treat_leading_path(struct dir_struct *dir,
+			      const char *path, int len,
+			      const struct path_simplify *simplify)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int baselen, rc = 0;
+	const char *cp;
+
+	while (len && path[len - 1] == '/')
+		len--;
+	if (!len)
+		return 1;
+	baselen = 0;
+	while (1) {
+		cp = path + baselen + !!baselen;
+		cp = memchr(cp, '/', path + len - cp);
+		if (!cp)
+			baselen = len;
+		else
+			baselen = cp - path;
+		strbuf_setlen(&sb, 0);
+		strbuf_add(&sb, path, baselen);
+		if (!is_directory(sb.buf))
+			break;
+		if (simplify_away(sb.buf, sb.len, simplify))
+			break;
+		if (treat_one_path(dir, &sb, simplify,
+				   DT_DIR, NULL) == path_ignored)
+			break; /* do not recurse into it */
+		if (len <= baselen) {
+			rc = 1;
+			break; /* finished checking */
+		}
+	}
+	strbuf_release(&sb);
+	return rc;
+}
+
 int read_directory(struct dir_struct *dir, const char *path, int len, const char **pathspec)
 {
 	struct path_simplify *simplify;
@@ -786,7 +1146,8 @@ int read_directory(struct dir_struct *dir, const char *path, int len, const char
 		return dir->nr;
 
 	simplify = create_simplify(pathspec);
-	read_directory_recursive(dir, path, len, 0, simplify);
+	if (!len || treat_leading_path(dir, path, len, simplify))
+		read_directory_recursive(dir, path, len, 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);
@@ -800,46 +1161,45 @@ int file_exists(const char *f)
 }
 
 /*
- * 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".
+ * Given two normalized paths (a trailing slash is ok), if subdir is
+ * outside dir, return -1.  Otherwise return the offset in subdir that
+ * can be used as relative path to dir.
  */
-char *get_relative_cwd(char *buffer, int size, const char *dir)
+int dir_inside_of(const char *subdir, const char *dir)
 {
-	char *cwd = buffer;
+	int offset = 0;
 
-	if (!dir)
-		return NULL;
-	if (!getcwd(buffer, size))
-		die_errno("can't find the current directory");
-
-	if (!is_absolute_path(dir))
-		dir = make_absolute_path(dir);
+	assert(dir && subdir && *dir && *subdir);
 
-	while (*dir && *dir == *cwd) {
+	while (*dir && *subdir && *dir == *subdir) {
 		dir++;
-		cwd++;
+		subdir++;
+		offset++;
 	}
-	if (*dir)
-		return NULL;
-	if (*cwd == '/')
-		return cwd + 1;
-	return cwd;
+
+	/* hel[p]/me vs hel[l]/yeah */
+	if (*dir && *subdir)
+		return -1;
+
+	if (!*subdir)
+		return !*dir ? offset : -1; /* same dir */
+
+	/* foo/[b]ar vs foo/[] */
+	if (is_dir_sep(dir[-1]))
+		return is_dir_sep(subdir[-1]) ? offset : -1;
+
+	/* foo[/]bar vs foo[] */
+	return is_dir_sep(*subdir) ? offset + 1 : -1;
 }
 
 int is_inside_dir(const char *dir)
 {
-	char buffer[PATH_MAX];
-	return get_relative_cwd(buffer, sizeof(buffer), dir) != NULL;
+	char cwd[PATH_MAX];
+	if (!dir)
+		return 0;
+	if (!getcwd(cwd, sizeof(cwd)))
+		die_errno("can't find the current directory");
+	return dir_inside_of(cwd, dir) >= 0;
 }
 
 int is_empty_dir(const char *path)
@@ -861,14 +1221,32 @@ int is_empty_dir(const char *path)
 	return ret;
 }
 
-int remove_dir_recursively(struct strbuf *path, int only_empty)
+static int remove_dir_recurse(struct strbuf *path, int flag, int *kept_up)
 {
-	DIR *dir = opendir(path->buf);
+	DIR *dir;
 	struct dirent *e;
-	int ret = 0, original_len = path->len, len;
+	int ret = 0, original_len = path->len, len, kept_down = 0;
+	int only_empty = (flag & REMOVE_DIR_EMPTY_ONLY);
+	int keep_toplevel = (flag & REMOVE_DIR_KEEP_TOPLEVEL);
+	unsigned char submodule_head[20];
+
+	if ((flag & REMOVE_DIR_KEEP_NESTED_GIT) &&
+	    !resolve_gitlink_ref(path->buf, "HEAD", submodule_head)) {
+		/* Do not descend and nuke a nested git work tree. */
+		if (kept_up)
+			*kept_up = 1;
+		return 0;
+	}
 
-	if (!dir)
-		return -1;
+	flag &= ~REMOVE_DIR_KEEP_TOPLEVEL;
+	dir = opendir(path->buf);
+	if (!dir) {
+		/* an empty dir could be removed even if it is unreadble */
+		if (!keep_toplevel)
+			return rmdir(path->buf);
+		else
+			return -1;
+	}
 	if (path->buf[original_len - 1] != '/')
 		strbuf_addch(path, '/');
 
@@ -883,7 +1261,7 @@ int remove_dir_recursively(struct strbuf *path, int only_empty)
 		if (lstat(path->buf, &st))
 			; /* fall thru */
 		else if (S_ISDIR(st.st_mode)) {
-			if (!remove_dir_recursively(path, only_empty))
+			if (!remove_dir_recurse(path, flag, &kept_down))
 				continue; /* happy */
 		} else if (!only_empty && !unlink(path->buf))
 			continue; /* happy, too */
@@ -895,11 +1273,22 @@ int remove_dir_recursively(struct strbuf *path, int only_empty)
 	closedir(dir);
 
 	strbuf_setlen(path, original_len);
-	if (!ret)
+	if (!ret && !keep_toplevel && !kept_down)
 		ret = rmdir(path->buf);
+	else if (kept_up)
+		/*
+		 * report the uplevel that it is not an error that we
+		 * did not rmdir() our directory.
+		 */
+		*kept_up = !ret;
 	return ret;
 }
 
+int remove_dir_recursively(struct strbuf *path, int flag)
+{
+	return remove_dir_recurse(path, flag, NULL);
+}
+
 void setup_standard_excludes(struct dir_struct *dir)
 {
 	const char *path;
@@ -925,9 +1314,56 @@ int remove_path(const char *name)
 		slash = dirs + (slash - name);
 		do {
 			*slash = '\0';
-		} while (rmdir(dirs) && (slash = strrchr(dirs, '/')));
+		} while (rmdir(dirs) == 0 && (slash = strrchr(dirs, '/')));
 		free(dirs);
 	}
 	return 0;
 }
 
+static int pathspec_item_cmp(const void *a_, const void *b_)
+{
+	struct pathspec_item *a, *b;
+
+	a = (struct pathspec_item *)a_;
+	b = (struct pathspec_item *)b_;
+	return strcmp(a->match, b->match);
+}
+
+int init_pathspec(struct pathspec *pathspec, const char **paths)
+{
+	const char **p = paths;
+	int i;
+
+	memset(pathspec, 0, sizeof(*pathspec));
+	if (!p)
+		return 0;
+	while (*p)
+		p++;
+	pathspec->raw = paths;
+	pathspec->nr = p - paths;
+	if (!pathspec->nr)
+		return 0;
+
+	pathspec->items = xmalloc(sizeof(struct pathspec_item)*pathspec->nr);
+	for (i = 0; i < pathspec->nr; i++) {
+		struct pathspec_item *item = pathspec->items+i;
+		const char *path = paths[i];
+
+		item->match = path;
+		item->len = strlen(path);
+		item->use_wildcard = !no_wildcard(path);
+		if (item->use_wildcard)
+			pathspec->has_wildcard = 1;
+	}
+
+	qsort(pathspec->items, pathspec->nr,
+	      sizeof(struct pathspec_item), pathspec_item_cmp);
+
+	return 0;
+}
+
+void free_pathspec(struct pathspec *pathspec)
+{
+	free(pathspec->items);
+	pathspec->items = NULL;
+}