git_path(): be aware of file relocation in $GIT_DIR

We allow the user to relocate certain paths out of $GIT_DIR via
environment variables, e.g. GIT_OBJECT_DIRECTORY, GIT_INDEX_FILE and
GIT_GRAFT_FILE. Callers are not supposed to use git_path() or
git_pathdup() to get those paths. Instead they must use
get_object_directory(), get_index_file() and get_graft_file()
respectively. This is inconvenient and could be missed in review (for
example, there's git_path("objects/info/alternates") somewhere in
sha1_file.c).

This patch makes git_path() and git_pathdup() understand those
environment variables. So if you set GIT_OBJECT_DIRECTORY to /foo/bar,
git_path("objects/abc") should return /foo/bar/abc. The same is done
for the two remaining env variables.

"git rev-parse --git-path" is the wrapper for script use.

This patch kinda reverts a0279e1 (setup_git_env: use git_pathdup
instead of xmalloc + sprintf - 2014-06-19) because using git_pathdup
here would result in infinite recursion:

  setup_git_env() -> git_pathdup("objects") -> .. -> adjust_git_path()
  -> get_object_directory() -> oops, git_object_directory is NOT set
  yet -> setup_git_env()

I wanted to make git_pathdup_literal() that skips adjust_git_path().
But that won't work because later on when $GIT_COMMON_DIR is
introduced, git_pathdup_literal("objects") needs adjust_git_path() to
replace $GIT_DIR with $GIT_COMMON_DIR.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-rev-parse.txt

@@ -233,6 +233,13 @@ print a message to stderr and exit with nonzero status.
 	repository.  If <path> is a gitfile then the resolved path
 	to the real repository is printed.
 
+--git-path <path>::
+	Resolve "$GIT_DIR/<path>" and takes other path relocation
+	variables such as $GIT_OBJECT_DIRECTORY,
+	$GIT_INDEX_FILE... into account. For example, if
+	$GIT_OBJECT_DIRECTORY is set to /foo/bar then "git rev-parse
+	--git-path objects/abc" returns /foo/bar/abc.
+
 --show-cdup::
 	When the command is invoked from a subdirectory, show the
 	path of the top-level directory relative to the current

builtin/rev-parse.c

@@ -533,6 +533,13 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix)
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
 
+		if (!strcmp(arg, "--git-path")) {
+			if (!argv[i + 1])
+				die("--git-path requires an argument");
+			puts(git_path("%s", argv[i + 1]));
+			i++;
+			continue;
+		}
 		if (as_is) {
 			if (show_file(arg, output_prefix) && as_is < 2)
 				verify_filename(prefix, arg, 0);

cache.h

@@ -617,6 +617,7 @@ extern int fsync_object_files;
 extern int core_preload_index;
 extern int core_apply_sparse_checkout;
 extern int precomposed_unicode;
+extern int git_db_env, git_index_env, git_graft_env;
 
 /*
  * The character that begins a commented line in user-editable file

environment.c

@@ -83,6 +83,7 @@ static size_t namespace_len;
 
 static const char *git_dir;
 static char *git_object_dir, *git_index_file, *git_graft_file;
+int git_db_env, git_index_env, git_graft_env;
 
 /*
  * Repository-local GIT_* environment variables; see cache.h for details.
@@ -124,10 +125,18 @@ static char *expand_namespace(const char *raw_namespace)
 	return strbuf_detach(&buf, NULL);
 }
 
-static char *git_path_from_env(const char *envvar, const char *path)
+static char *git_path_from_env(const char *envvar, const char *path,
+			       int *fromenv)
 {
 	const char *value = getenv(envvar);
-	return value ? xstrdup(value) : git_pathdup("%s", path);
+	if (!value) {
+		char *buf = xmalloc(strlen(git_dir) + strlen(path) + 2);
+		sprintf(buf, "%s/%s", git_dir, path);
+		return buf;
+	}
+	if (fromenv)
+		*fromenv = 1;
+	return xstrdup(value);
 }
 
 static void setup_git_env(void)
@@ -140,9 +149,9 @@ static void setup_git_env(void)
 		git_dir = DEFAULT_GIT_DIR_ENVIRONMENT;
 	gitfile = read_gitfile(git_dir);
 	git_dir = xstrdup(gitfile ? gitfile : git_dir);
-	git_object_dir = git_path_from_env(DB_ENVIRONMENT, "objects");
+	git_object_dir = git_path_from_env(DB_ENVIRONMENT, "objects", &git_db_env);
-	git_index_file = git_path_from_env(INDEX_ENVIRONMENT, "index");
+	git_index_file = git_path_from_env(INDEX_ENVIRONMENT, "index", &git_index_env);
-	git_graft_file = git_path_from_env(GRAFT_ENVIRONMENT, "info/grafts");
+	git_graft_file = git_path_from_env(GRAFT_ENVIRONMENT, "info/grafts", &git_graft_env);
 	if (getenv(NO_REPLACE_OBJECTS_ENVIRONMENT))
 		check_replace_refs = 0;
 	namespace = expand_namespace(getenv(GIT_NAMESPACE_ENVIRONMENT));

path.c

@@ -60,13 +60,58 @@ char *mksnpath(char *buf, size_t n, const char *fmt, ...)
 	return cleanup_path(buf);
 }
 
+static int dir_prefix(const char *buf, const char *dir)
+{
+	int len = strlen(dir);
+	return !strncmp(buf, dir, len) &&
+		(is_dir_sep(buf[len]) || buf[len] == '\0');
+}
+
+/* $buf =~ m|$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);
+}
+
+static void replace_dir(struct strbuf *buf, int len, const char *newdir)
+{
+	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] = '/';
+}
+
+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());
+}
+
 static void do_git_path(struct strbuf *buf, const char *fmt, va_list args)
 {
-	const char *git_dir = get_git_dir();
+	int gitdir_len;
-	strbuf_addstr(buf, git_dir);
+	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);
 }
 

t/t0060-path-utils.sh

@@ -19,6 +19,14 @@ relative_path() {
 	"test \"\$(test-path-utils relative_path '$1' '$2')\" = '$expected'"
 }
 
+test_git_path() {
+	test_expect_success "git-path $1 $2 => $3" "
+		$1 git rev-parse --git-path $2 >actual &&
+		echo $3 >expect &&
+		test_cmp expect actual
+	"
+}
+
 # On Windows, we are using MSYS's bash, which mangles the paths.
 # Absolute paths are anchored at the MSYS installation directory,
 # which means that the path / accounts for this many characters:
@@ -244,4 +252,15 @@ relative_path "<null>"		"<empty>"	./
 relative_path "<null>"		"<null>"	./
 relative_path "<null>"		/foo/a/b	./
 
+test_git_path A=B                info/grafts .git/info/grafts
+test_git_path GIT_GRAFT_FILE=foo info/grafts foo
+test_git_path GIT_GRAFT_FILE=foo info/////grafts foo
+test_git_path GIT_INDEX_FILE=foo index foo
+test_git_path GIT_INDEX_FILE=foo index/foo .git/index/foo
+test_git_path GIT_INDEX_FILE=foo index2 .git/index2
+test_expect_success 'setup fake objects directory foo' 'mkdir foo'
+test_git_path GIT_OBJECT_DIRECTORY=foo objects foo
+test_git_path GIT_OBJECT_DIRECTORY=foo objects/foo foo/foo
+test_git_path GIT_OBJECT_DIRECTORY=foo objects2 .git/objects2
+
 test_done