1 files changed, 419 insertions, 120 deletions

diff --git a/path.c b/path.c
index f10c91a927..65beb2dca3 100644
--- a/path.c
+++ b/path.c
@@ -4,6 +4,7 @@
 #include "cache.h"
 #include "strbuf.h"
 #include "string-list.h"
+#include "dir.h"
 
 static int get_st_mode_bits(const char *path, int *mode)
 {
@@ -16,11 +17,15 @@ static int get_st_mode_bits(const char *path, int *mode)
 
 static char bad_path[] = "/bad-path/";
 
-static char *get_pathname(void)
+static struct strbuf *get_pathname(void)
 {
-	static char pathname_array[4][PATH_MAX];
+	static struct strbuf pathname_array[4] = {
+		STRBUF_INIT, STRBUF_INIT, STRBUF_INIT, STRBUF_INIT
+	};
 	static int index;
-	return pathname_array[3 & ++index];
+	struct strbuf *sb = &pathname_array[3 & ++index];
+	strbuf_reset(sb);
+	return sb;
 }
 
 static char *cleanup_path(char *path)
@@ -34,6 +39,13 @@ static char *cleanup_path(char *path)
 	return path;
 }
 
+static void strbuf_cleanup_path(struct strbuf *sb)
+{
+	char *path = cleanup_path(sb->buf);
+	if (path > sb->buf)
+		strbuf_remove(sb, 0, path - sb->buf);
+}
+
 char *mksnpath(char *buf, size_t n, const char *fmt, ...)
 {
 	va_list args;
@@ -49,150 +61,424 @@ char *mksnpath(char *buf, size_t n, const char *fmt, ...)
 	return cleanup_path(buf);
 }
 
-static char *vsnpath(char *buf, size_t n, const char *fmt, va_list args)
+static int dir_prefix(const char *buf, const char *dir)
 {
-	const char *git_dir = get_git_dir();
-	size_t len;
+	int len = strlen(dir);
+	return !strncmp(buf, dir, len) &&
+		(is_dir_sep(buf[len]) || buf[len] == '\0');
+}
 
-	len = strlen(git_dir);
-	if (n < len + 1)
-		goto bad;
-	memcpy(buf, git_dir, len);
-	if (len && !is_dir_sep(git_dir[len-1]))
-		buf[len++] = '/';
-	len += vsnprintf(buf + len, n - len, fmt, args);
-	if (len >= n)
-		goto bad;
-	return cleanup_path(buf);
-bad:
-	strlcpy(buf, bad_path, n);
-	return buf;
+/* $buf =~ m|$dir/+$file| but without regex */
+static int is_dir_file(const char *buf, const char *dir, const char *file)
+{
+	int len = strlen(dir);
+	if (strncmp(buf, dir, len) || !is_dir_sep(buf[len]))
+		return 0;
+	while (is_dir_sep(buf[len]))
+		len++;
+	return !strcmp(buf + len, file);
 }
 
-char *git_snpath(char *buf, size_t n, const char *fmt, ...)
+static void replace_dir(struct strbuf *buf, int len, const char *newdir)
 {
-	char *ret;
-	va_list args;
-	va_start(args, fmt);
-	ret = vsnpath(buf, n, fmt, args);
-	va_end(args);
-	return ret;
+	int newlen = strlen(newdir);
+	int need_sep = (buf->buf[len] && !is_dir_sep(buf->buf[len])) &&
+		!is_dir_sep(newdir[newlen - 1]);
+	if (need_sep)
+		len--;	 /* keep one char, to be replaced with '/'  */
+	strbuf_splice(buf, 0, len, newdir, newlen);
+	if (need_sep)
+		buf->buf[newlen] = '/';
 }
 
-char *git_pathdup(const char *fmt, ...)
+struct common_dir {
+	/* Not considered garbage for report_linked_checkout_garbage */
+	unsigned ignore_garbage:1;
+	unsigned is_dir:1;
+	/* Not common even though its parent is */
+	unsigned exclude:1;
+	const char *dirname;
+};
+
+static struct common_dir common_list[] = {
+	{ 0, 1, 0, "branches" },
+	{ 0, 1, 0, "hooks" },
+	{ 0, 1, 0, "info" },
+	{ 0, 0, 1, "info/sparse-checkout" },
+	{ 1, 1, 0, "logs" },
+	{ 1, 1, 1, "logs/HEAD" },
+	{ 0, 1, 1, "logs/refs/bisect" },
+	{ 0, 1, 0, "lost-found" },
+	{ 0, 1, 0, "objects" },
+	{ 0, 1, 0, "refs" },
+	{ 0, 1, 1, "refs/bisect" },
+	{ 0, 1, 0, "remotes" },
+	{ 0, 1, 0, "worktrees" },
+	{ 0, 1, 0, "rr-cache" },
+	{ 0, 1, 0, "svn" },
+	{ 0, 0, 0, "config" },
+	{ 1, 0, 0, "gc.pid" },
+	{ 0, 0, 0, "packed-refs" },
+	{ 0, 0, 0, "shallow" },
+	{ 0, 0, 0, NULL }
+};
+
+/*
+ * A compressed trie.  A trie node consists of zero or more characters that
+ * are common to all elements with this prefix, optionally followed by some
+ * children.  If value is not NULL, the trie node is a terminal node.
+ *
+ * For example, consider the following set of strings:
+ * abc
+ * def
+ * definite
+ * definition
+ *
+ * The trie would look look like:
+ * root: len = 0, children a and d non-NULL, value = NULL.
+ *    a: len = 2, contents = bc, value = (data for "abc")
+ *    d: len = 2, contents = ef, children i non-NULL, value = (data for "def")
+ *       i: len = 3, contents = nit, children e and i non-NULL, value = NULL
+ *           e: len = 0, children all NULL, value = (data for "definite")
+ *           i: len = 2, contents = on, children all NULL,
+ *              value = (data for "definition")
+ */
+struct trie {
+	struct trie *children[256];
+	int len;
+	char *contents;
+	void *value;
+};
+
+static struct trie *make_trie_node(const char *key, void *value)
+{
+	struct trie *new_node = xcalloc(1, sizeof(*new_node));
+	new_node->len = strlen(key);
+	if (new_node->len) {
+		new_node->contents = xmalloc(new_node->len);
+		memcpy(new_node->contents, key, new_node->len);
+	}
+	new_node->value = value;
+	return new_node;
+}
+
+/*
+ * Add a key/value pair to a trie.  The key is assumed to be \0-terminated.
+ * If there was an existing value for this key, return it.
+ */
+static void *add_to_trie(struct trie *root, const char *key, void *value)
+{
+	struct trie *child;
+	void *old;
+	int i;
+
+	if (!*key) {
+		/* we have reached the end of the key */
+		old = root->value;
+		root->value = value;
+		return old;
+	}
+
+	for (i = 0; i < root->len; i++) {
+		if (root->contents[i] == key[i])
+			continue;
+
+		/*
+		 * Split this node: child will contain this node's
+		 * existing children.
+		 */
+		child = malloc(sizeof(*child));
+		memcpy(child->children, root->children, sizeof(root->children));
+
+		child->len = root->len - i - 1;
+		if (child->len) {
+			child->contents = xstrndup(root->contents + i + 1,
+						   child->len);
+		}
+		child->value = root->value;
+		root->value = NULL;
+		root->len = i;
+
+		memset(root->children, 0, sizeof(root->children));
+		root->children[(unsigned char)root->contents[i]] = child;
+
+		/* This is the newly-added child. */
+		root->children[(unsigned char)key[i]] =
+			make_trie_node(key + i + 1, value);
+		return NULL;
+	}
+
+	/* We have matched the entire compressed section */
+	if (key[i]) {
+		child = root->children[(unsigned char)key[root->len]];
+		if (child) {
+			return add_to_trie(child, key + root->len + 1, value);
+		} else {
+			child = make_trie_node(key + root->len + 1, value);
+			root->children[(unsigned char)key[root->len]] = child;
+			return NULL;
+		}
+	}
+
+	old = root->value;
+	root->value = value;
+	return old;
+}
+
+typedef int (*match_fn)(const char *unmatched, void *data, void *baton);
+
+/*
+ * Search a trie for some key.  Find the longest /-or-\0-terminated
+ * prefix of the key for which the trie contains a value.  Call fn
+ * with the unmatched portion of the key and the found value, and
+ * return its return value.  If there is no such prefix, return -1.
+ *
+ * The key is partially normalized: consecutive slashes are skipped.
+ *
+ * For example, consider the trie containing only [refs,
+ * refs/worktree] (both with values).
+ *
+ * | key             | unmatched  | val from node | return value |
+ * |-----------------|------------|---------------|--------------|
+ * | a               | not called | n/a           | -1           |
+ * | refs            | \0         | refs          | as per fn    |
+ * | refs/           | /          | refs          | as per fn    |
+ * | refs/w          | /w         | refs          | as per fn    |
+ * | refs/worktree   | \0         | refs/worktree | as per fn    |
+ * | refs/worktree/  | /          | refs/worktree | as per fn    |
+ * | refs/worktree/a | /a         | refs/worktree | as per fn    |
+ * |-----------------|------------|---------------|--------------|
+ *
+ */
+static int trie_find(struct trie *root, const char *key, match_fn fn,
+		     void *baton)
+{
+	int i;
+	int result;
+	struct trie *child;
+
+	if (!*key) {
+		/* we have reached the end of the key */
+		if (root->value && !root->len)
+			return fn(key, root->value, baton);
+		else
+			return -1;
+	}
+
+	for (i = 0; i < root->len; i++) {
+		/* Partial path normalization: skip consecutive slashes. */
+		if (key[i] == '/' && key[i+1] == '/') {
+			key++;
+			continue;
+		}
+		if (root->contents[i] != key[i])
+			return -1;
+	}
+
+	/* Matched the entire compressed section */
+	key += i;
+	if (!*key)
+		/* End of key */
+		return fn(key, root->value, baton);
+
+	/* Partial path normalization: skip consecutive slashes */
+	while (key[0] == '/' && key[1] == '/')
+		key++;
+
+	child = root->children[(unsigned char)*key];
+	if (child)
+		result = trie_find(child, key + 1, fn, baton);
+	else
+		result = -1;
+
+	if (result >= 0 || (*key != '/' && *key != 0))
+		return result;
+	if (root->value)
+		return fn(key, root->value, baton);
+	else
+		return -1;
+}
+
+static struct trie common_trie;
+static int common_trie_done_setup;
+
+static void init_common_trie(void)
+{
+	struct common_dir *p;
+
+	if (common_trie_done_setup)
+		return;
+
+	for (p = common_list; p->dirname; p++)
+		add_to_trie(&common_trie, p->dirname, p);
+
+	common_trie_done_setup = 1;
+}
+
+/*
+ * Helper function for update_common_dir: returns 1 if the dir
+ * prefix is common.
+ */
+static int check_common(const char *unmatched, void *value, void *baton)
+{
+	struct common_dir *dir = value;
+
+	if (!dir)
+		return 0;
+
+	if (dir->is_dir && (unmatched[0] == 0 || unmatched[0] == '/'))
+		return !dir->exclude;
+
+	if (!dir->is_dir && unmatched[0] == 0)
+		return !dir->exclude;
+
+	return 0;
+}
+
+static void update_common_dir(struct strbuf *buf, int git_dir_len)
+{
+	char *base = buf->buf + git_dir_len;
+	init_common_trie();
+	if (trie_find(&common_trie, base, check_common, NULL) > 0)
+		replace_dir(buf, git_dir_len, get_git_common_dir());
+}
+
+void report_linked_checkout_garbage(void)
+{
+	struct strbuf sb = STRBUF_INIT;
+	const struct common_dir *p;
+	int len;
+
+	if (!git_common_dir_env)
+		return;
+	strbuf_addf(&sb, "%s/", get_git_dir());
+	len = sb.len;
+	for (p = common_list; p->dirname; p++) {
+		const char *path = p->dirname;
+		if (p->ignore_garbage)
+			continue;
+		strbuf_setlen(&sb, len);
+		strbuf_addstr(&sb, path);
+		if (file_exists(sb.buf))
+			report_garbage("unused in linked checkout", sb.buf);
+	}
+	strbuf_release(&sb);
+}
+
+static void adjust_git_path(struct strbuf *buf, int git_dir_len)
+{
+	const char *base = buf->buf + git_dir_len;
+	if (git_graft_env && is_dir_file(base, "info", "grafts"))
+		strbuf_splice(buf, 0, buf->len,
+			      get_graft_file(), strlen(get_graft_file()));
+	else if (git_index_env && !strcmp(base, "index"))
+		strbuf_splice(buf, 0, buf->len,
+			      get_index_file(), strlen(get_index_file()));
+	else if (git_db_env && dir_prefix(base, "objects"))
+		replace_dir(buf, git_dir_len + 7, get_object_directory());
+	else if (git_common_dir_env)
+		update_common_dir(buf, git_dir_len);
+}
+
+static void do_git_path(struct strbuf *buf, const char *fmt, va_list args)
+{
+	int gitdir_len;
+	strbuf_addstr(buf, get_git_dir());
+	if (buf->len && !is_dir_sep(buf->buf[buf->len - 1]))
+		strbuf_addch(buf, '/');
+	gitdir_len = buf->len;
+	strbuf_vaddf(buf, fmt, args);
+	adjust_git_path(buf, gitdir_len);
+	strbuf_cleanup_path(buf);
+}
+
+void strbuf_git_path(struct strbuf *sb, const char *fmt, ...)
 {
-	char path[PATH_MAX], *ret;
 	va_list args;
 	va_start(args, fmt);
-	ret = vsnpath(path, sizeof(path), fmt, args);
+	do_git_path(sb, fmt, args);
 	va_end(args);
-	return xstrdup(ret);
 }
 
-char *mkpathdup(const char *fmt, ...)
+const char *git_path(const char *fmt, ...)
 {
-	char *path;
-	struct strbuf sb = STRBUF_INIT;
+	struct strbuf *pathname = get_pathname();
 	va_list args;
-
 	va_start(args, fmt);
-	strbuf_vaddf(&sb, fmt, args);
+	do_git_path(pathname, fmt, args);
 	va_end(args);
-	path = xstrdup(cleanup_path(sb.buf));
-
-	strbuf_release(&sb);
-	return path;
+	return pathname->buf;
 }
 
-char *mkpath(const char *fmt, ...)
+char *git_pathdup(const char *fmt, ...)
 {
+	struct strbuf path = STRBUF_INIT;
 	va_list args;
-	unsigned len;
-	char *pathname = get_pathname();
-
 	va_start(args, fmt);
-	len = vsnprintf(pathname, PATH_MAX, fmt, args);
+	do_git_path(&path, fmt, args);
 	va_end(args);
-	if (len >= PATH_MAX)
-		return bad_path;
-	return cleanup_path(pathname);
+	return strbuf_detach(&path, NULL);
 }
 
-char *git_path(const char *fmt, ...)
+char *mkpathdup(const char *fmt, ...)
 {
-	char *pathname = get_pathname();
+	struct strbuf sb = STRBUF_INIT;
 	va_list args;
-	char *ret;
-
 	va_start(args, fmt);
-	ret = vsnpath(pathname, PATH_MAX, fmt, args);
+	strbuf_vaddf(&sb, fmt, args);
 	va_end(args);
-	return ret;
+	strbuf_cleanup_path(&sb);
+	return strbuf_detach(&sb, NULL);
 }
 
-void home_config_paths(char **global, char **xdg, char *file)
+const char *mkpath(const char *fmt, ...)
 {
-	char *xdg_home = getenv("XDG_CONFIG_HOME");
-	char *home = getenv("HOME");
-	char *to_free = NULL;
-
-	if (!home) {
-		if (global)
-			*global = NULL;
-	} else {
-		if (!xdg_home) {
-			to_free = mkpathdup("%s/.config", home);
-			xdg_home = to_free;
-		}
-		if (global)
-			*global = mkpathdup("%s/.gitconfig", home);
-	}
-
-	if (!xdg_home)
-		*xdg = NULL;
-	else
-		*xdg = mkpathdup("%s/git/%s", xdg_home, file);
-
-	free(to_free);
+	va_list args;
+	struct strbuf *pathname = get_pathname();
+	va_start(args, fmt);
+	strbuf_vaddf(pathname, fmt, args);
+	va_end(args);
+	return cleanup_path(pathname->buf);
 }
 
-char *git_path_submodule(const char *path, const char *fmt, ...)
+static void do_submodule_path(struct strbuf *buf, const char *path,
+			      const char *fmt, va_list args)
 {
-	char *pathname = get_pathname();
-	struct strbuf buf = STRBUF_INIT;
 	const char *git_dir;
-	va_list args;
-	unsigned len;
-
-	len = strlen(path);
-	if (len > PATH_MAX-100)
-		return bad_path;
 
-	strbuf_addstr(&buf, path);
-	if (len && path[len-1] != '/')
-		strbuf_addch(&buf, '/');
-	strbuf_addstr(&buf, ".git");
+	strbuf_addstr(buf, path);
+	if (buf->len && buf->buf[buf->len - 1] != '/')
+		strbuf_addch(buf, '/');
+	strbuf_addstr(buf, ".git");
 
-	git_dir = read_gitfile(buf.buf);
+	git_dir = read_gitfile(buf->buf);
 	if (git_dir) {
-		strbuf_reset(&buf);
-		strbuf_addstr(&buf, git_dir);
+		strbuf_reset(buf);
+		strbuf_addstr(buf, git_dir);
 	}
-	strbuf_addch(&buf, '/');
+	strbuf_addch(buf, '/');
 
-	if (buf.len >= PATH_MAX)
-		return bad_path;
-	memcpy(pathname, buf.buf, buf.len + 1);
+	strbuf_vaddf(buf, fmt, args);
+	strbuf_cleanup_path(buf);
+}
 
-	strbuf_release(&buf);
-	len = strlen(pathname);
+char *git_pathdup_submodule(const char *path, const char *fmt, ...)
+{
+	va_list args;
+	struct strbuf buf = STRBUF_INIT;
+	va_start(args, fmt);
+	do_submodule_path(&buf, path, fmt, args);
+	va_end(args);
+	return strbuf_detach(&buf, NULL);
+}
 
+void strbuf_git_path_submodule(struct strbuf *buf, const char *path,
+			       const char *fmt, ...)
+{
+	va_list args;
 	va_start(args, fmt);
-	len += vsnprintf(pathname + len, PATH_MAX - len, fmt, args);
+	do_submodule_path(buf, path, fmt, args);
 	va_end(args);
-	if (len >= PATH_MAX)
-		return bad_path;
-	return cleanup_path(pathname);
 }
 
 int validate_headref(const char *path)
@@ -275,16 +561,16 @@ char *expand_user_path(const char *path)
 			const char *home = getenv("HOME");
 			if (!home)
 				goto return_null;
-			strbuf_add(&user_path, home, strlen(home));
+			strbuf_addstr(&user_path, home);
 		} else {
 			struct passwd *pw = getpw_str(username, username_len);
 			if (!pw)
 				goto return_null;
-			strbuf_add(&user_path, pw->pw_dir, strlen(pw->pw_dir));
+			strbuf_addstr(&user_path, pw->pw_dir);
 		}
 		to_copy = first_slash;
 	}
-	strbuf_add(&user_path, to_copy, strlen(to_copy));
+	strbuf_addstr(&user_path, to_copy);
 	return strbuf_detach(&user_path, NULL);
 return_null:
 	strbuf_release(&user_path);
@@ -301,14 +587,9 @@ return_null:
  * (3) "relative/path" to mean cwd relative directory; or
  * (4) "/absolute/path" to mean absolute directory.
  *
- * Unless "strict" is given, we try access() for existence of "%s.git/.git",
- * "%s/.git", "%s.git", "%s" in this order.  The first one that exists is
- * what we try.
- *
- * Second, we try chdir() to that.  Upon failure, we return NULL.
- *
- * Then, we try if the current directory is a valid git repository.
- * Upon failure, we return NULL.
+ * Unless "strict" is given, we check "%s/.git", "%s", "%s.git/.git", "%s.git"
+ * in this order. We select the first one that is a valid git repository, and
+ * chdir() to it. If none match, or we fail to chdir, we return NULL.
  *
  * If all goes well, we return the directory we used to chdir() (but
  * before ~user is expanded), avoiding getcwd() resolving symbolic
@@ -822,13 +1103,6 @@ int daemon_avoid_alias(const char *p)
 	}
 }
 
-int offset_1st_component(const char *path)
-{
-	if (has_dos_drive_prefix(path))
-		return 2 + is_dir_sep(path[2]);
-	return is_dir_sep(path[0]);
-}
-
 static int only_spaces_and_periods(const char *path, size_t len, size_t skip)
 {
 	if (len < skip)
@@ -861,3 +1135,28 @@ int is_ntfs_dotgit(const char *name)
 			len = -1;
 		}
 }
+
+char *xdg_config_home(const char *filename)
+{
+	const char *home, *config_home;
+
+	assert(filename);
+	config_home = getenv("XDG_CONFIG_HOME");
+	if (config_home && *config_home)
+		return mkpathdup("%s/git/%s", config_home, filename);
+
+	home = getenv("HOME");
+	if (home)
+		return mkpathdup("%s/.config/git/%s", home, filename);
+	return NULL;
+}
+
+GIT_PATH_FUNC(git_path_cherry_pick_head, "CHERRY_PICK_HEAD")
+GIT_PATH_FUNC(git_path_revert_head, "REVERT_HEAD")
+GIT_PATH_FUNC(git_path_squash_msg, "SQUASH_MSG")
+GIT_PATH_FUNC(git_path_merge_msg, "MERGE_MSG")
+GIT_PATH_FUNC(git_path_merge_rr, "MERGE_RR")
+GIT_PATH_FUNC(git_path_merge_mode, "MERGE_MODE")
+GIT_PATH_FUNC(git_path_merge_head, "MERGE_HEAD")
+GIT_PATH_FUNC(git_path_fetch_head, "FETCH_HEAD")
+GIT_PATH_FUNC(git_path_shallow, "shallow")