[PATCH 0/4 v3] Introducing the .git file

[PATCH 0/4 v3] Introducing the .git file

[Lars Hjemli]

This is a resend of my previous series implementing the .git file,
rebased on top of todays master (e3c58f8b). The patches are identical
to the final suggestions in http://thread.gmane.org/gmane.comp.version-control.git/74258
except for the previous 1/5 which is dropped from the series (since it
already appears in master). There are also some minor touch-ups to the
commit messages.

Shortlog:
 Add platform-independent .git "symlink"
 Teach resolve_gitlink_ref() about the .git file
 Teach git-submodule.sh about the .git file
 Teach GIT-VERSION-GEN about the .git file

Diffstat:
 Documentation/repository-layout.txt |    5 ++-
 GIT-VERSION-GEN                     |    2 +-
 cache.h                             |    1 +
 environment.c                       |    2 +
 git-submodule.sh                    |    4 +-
 refs.c                              |   17 +++++-
 setup.c                             |   47 ++++++++++++++++
 t/t0002-gitfile.sh                  |  103 +++++++++++++++++++++++++++++++++++
 8 files changed, 174 insertions(+), 7 deletions(-)

[PATCH 1/4] Add platform-independent .git "symlink"

[Lars Hjemli]

This patch allows .git to be a regular textfile containing the path of
the real git directory (prefixed with "gitdir: "), which can be useful on
platforms lacking support for real symlinks.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>
---
 Documentation/repository-layout.txt |    5 ++-
 cache.h                             |    1 +
 environment.c                       |    2 +
 setup.c                             |   47 ++++++++++++++++
 t/t0002-gitfile.sh                  |  103 +++++++++++++++++++++++++++++++++++
 5 files changed, 157 insertions(+), 1 deletions(-)
 create mode 100755 t/t0002-gitfile.sh

diff --git a/Documentation/repository-layout.txt b/Documentation/repository-layout.txt
index 6939130..bbaed2e 100644
--- a/Documentation/repository-layout.txt
+++ b/Documentation/repository-layout.txt
@@ -3,7 +3,10 @@ git repository layout
 
 You may find these things in your git repository (`.git`
 directory for a repository associated with your working tree, or
-`'project'.git` directory for a public 'bare' repository).
+`'project'.git` directory for a public 'bare' repository. It is
+also possible to have a working tree where `.git` is a plain
+ascii file containing `gitdir: <path>`, i.e. the path to the
+real git repository).
 
 objects::
 	Object store associated with this repository.  Usually
diff --git a/cache.h b/cache.h
index e1000bc..1ad822a 100644
--- a/cache.h
+++ b/cache.h
@@ -277,6 +277,7 @@ extern char *get_index_file(void);
 extern char *get_graft_file(void);
 extern int set_git_dir(const char *path);
 extern const char *get_git_work_tree(void);
+extern const char *read_gitfile_gently(const char *path);
 
 #define ALTERNATE_DB_ENVIRONMENT "GIT_ALTERNATE_OBJECT_DIRECTORIES"
 
diff --git a/environment.c b/environment.c
index 3527f16..8058e7b 100644
--- a/environment.c
+++ b/environment.c
@@ -49,6 +49,8 @@ static void setup_git_env(void)
 {
 	git_dir = getenv(GIT_DIR_ENVIRONMENT);
 	if (!git_dir)
+		git_dir = read_gitfile_gently(DEFAULT_GIT_DIR_ENVIRONMENT);
+	if (!git_dir)
 		git_dir = DEFAULT_GIT_DIR_ENVIRONMENT;
 	git_object_dir = getenv(DB_ENVIRONMENT);
 	if (!git_object_dir) {
diff --git a/setup.c b/setup.c
index 4509598..20502be 100644
--- a/setup.c
+++ b/setup.c
@@ -239,6 +239,44 @@ static int check_repository_format_gently(int *nongit_ok)
 }
 
 /*
+ * Try to read the location of the git directory from the .git file,
+ * return path to git directory if found.
+ */
+const char *read_gitfile_gently(const char *path)
+{
+	char *buf;
+	struct stat st;
+	int fd;
+	size_t len;
+
+	if (stat(path, &st))
+		return NULL;
+	if (!S_ISREG(st.st_mode))
+		return NULL;
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		die("Error opening %s: %s", path, strerror(errno));
+	buf = xmalloc(st.st_size + 1);
+	len = read_in_full(fd, buf, st.st_size);
+	close(fd);
+	if (len != st.st_size)
+		die("Error reading %s", path);
+	buf[len] = '\0';
+	if (prefixcmp(buf, "gitdir: "))
+		die("Invalid gitfile format: %s", path);
+	while (buf[len - 1] == '\n' || buf[len - 1] == '\r')
+		len--;
+	if (len < 9)
+		die("No path in gitfile: %s", path);
+	buf[len] = '\0';
+	if (!is_git_directory(buf + 8))
+		die("Not a git repository: %s", buf + 8);
+	path = make_absolute_path(buf + 8);
+	free(buf);
+	return path;
+}
+
+/*
  * We cannot decide in this function whether we are in the work tree or
  * not, since the config can only be read _after_ this function was called.
  */
@@ -247,6 +285,7 @@ const char *setup_git_directory_gently(int *nongit_ok)
 	const char *work_tree_env = getenv(GIT_WORK_TREE_ENVIRONMENT);
 	static char cwd[PATH_MAX+1];
 	const char *gitdirenv;
+	const char *gitfile_dir;
 	int len, offset;
 
 	/*
@@ -293,8 +332,10 @@ const char *setup_git_directory_gently(int *nongit_ok)
 
 	/*
 	 * Test in the following order (relative to the cwd):
+	 * - .git (file containing "gitdir: <path>")
 	 * - .git/
 	 * - ./ (bare)
+	 * - ../.git
 	 * - ../.git/
 	 * - ../ (bare)
 	 * - ../../.git/
@@ -302,6 +343,12 @@ const char *setup_git_directory_gently(int *nongit_ok)
 	 */
 	offset = len = strlen(cwd);
 	for (;;) {
+		gitfile_dir = read_gitfile_gently(DEFAULT_GIT_DIR_ENVIRONMENT);
+		if (gitfile_dir) {
+			if (set_git_dir(gitfile_dir))
+				die("Repository setup failed");
+			break;
+		}
 		if (is_git_directory(DEFAULT_GIT_DIR_ENVIRONMENT))
 			break;
 		if (is_git_directory(".")) {
diff --git a/t/t0002-gitfile.sh b/t/t0002-gitfile.sh
new file mode 100755
index 0000000..c5dbc72
--- /dev/null
+++ b/t/t0002-gitfile.sh
@@ -0,0 +1,103 @@
+#!/bin/sh
+
+test_description='.git file
+
+Verify that plumbing commands work when .git is a file
+'
+. ./test-lib.sh
+
+objpath() {
+    echo "$1" | sed -e 's|\(..\)|\1/|'
+}
+
+objck() {
+	p=$(objpath "$1")
+	if test ! -f "$REAL/objects/$p"
+	then
+		echo "Object not found: $REAL/objects/$p"
+		false
+	fi
+}
+
+
+test_expect_success 'initial setup' '
+	REAL="$(pwd)/.real" &&
+	mv .git "$REAL"
+'
+
+test_expect_success 'bad setup: invalid .git file format' '
+	echo "gitdir $REAL" >.git &&
+	if git rev-parse 2>.err
+	then
+		echo "git rev-parse accepted an invalid .git file"
+		false
+	fi &&
+	if ! grep -qe "Invalid gitfile format" .err
+	then
+		echo "git rev-parse returned wrong error"
+		false
+	fi
+'
+
+test_expect_success 'bad setup: invalid .git file path' '
+	echo "gitdir: $REAL.not" >.git &&
+	if git rev-parse 2>.err
+	then
+		echo "git rev-parse accepted an invalid .git file path"
+		false
+	fi &&
+	if ! grep -qe "Not a git repository" .err
+	then
+		echo "git rev-parse returned wrong error"
+		false
+	fi
+'
+
+test_expect_success 'final setup + check rev-parse --git-dir' '
+	echo "gitdir: $REAL" >.git &&
+	test "$REAL" = "$(git rev-parse --git-dir)"
+'
+
+test_expect_success 'check hash-object' '
+	echo "foo" >bar &&
+	SHA=$(cat bar | git hash-object -w --stdin) &&
+	objck $SHA
+'
+
+test_expect_success 'check cat-file' '
+	git cat-file blob $SHA >actual &&
+	diff -u bar actual
+'
+
+test_expect_success 'check update-index' '
+	if test -f "$REAL/index"
+	then
+		echo "Hmm, $REAL/index exists?"
+		false
+	fi &&
+	rm -f "$REAL/objects/$(objpath $SHA)" &&
+	git update-index --add bar &&
+	if ! test -f "$REAL/index"
+	then
+		echo "$REAL/index not found"
+		false
+	fi &&
+	objck $SHA
+'
+
+test_expect_success 'check write-tree' '
+	SHA=$(git write-tree) &&
+	objck $SHA
+'
+
+test_expect_success 'check commit-tree' '
+	SHA=$(echo "commit bar" | git commit-tree $SHA) &&
+	objck $SHA
+'
+
+test_expect_success 'check rev-list' '
+	echo $SHA >"$REAL/HEAD" &&
+	test "$SHA" = "$(git rev-list HEAD)"
+'
+
+test_done
-- 
1.5.4.1.188.g3ea1f5

[PATCH 2/4] Teach resolve_gitlink_ref() about the .git file

[Lars Hjemli]

When .git in a submodule is a file, resolve_gitlink_ref() needs to pick up
the real GIT_DIR of the submodule from that file.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>
---
 refs.c |   17 ++++++++++++++---
 1 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/refs.c b/refs.c
index 67d2a50..56de5cf 100644
--- a/refs.c
+++ b/refs.c
@@ -351,6 +351,7 @@ int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *re
 {
 	int len = strlen(path), retval;
 	char *gitdir;
+	const char *tmp;
 
 	while (len && path[len-1] == '/')
 		len--;
@@ -358,9 +359,19 @@ int resolve_gitlink_ref(const char *path, const char *refname, unsigned char *re
 		return -1;
 	gitdir = xmalloc(len + MAXREFLEN + 8);
 	memcpy(gitdir, path, len);
-	memcpy(gitdir + len, "/.git/", 7);
-
-	retval = resolve_gitlink_ref_recursive(gitdir, len+6, refname, result, 0);
+	memcpy(gitdir + len, "/.git", 6);
+	len += 5;
+
+	tmp = read_gitfile_gently(gitdir);
+	if (tmp) {
+		free(gitdir);
+		len = strlen(tmp);
+		gitdir = xmalloc(len + MAXREFLEN + 3);
+		memcpy(gitdir, tmp, len);
+	}
+	gitdir[len] = '/';
+	gitdir[++len] = '\0';
+	retval = resolve_gitlink_ref_recursive(gitdir, len, refname, result, 0);
 	free(gitdir);
 	return retval;
 }
-- 
1.5.4.1.188.g3ea1f5

[PATCH 3/4] Teach git-submodule.sh about the .git file

[Lars Hjemli]

When git-submodule tries to detect 'active' submodules, it checks for the
existence of a directory named '.git'. This isn't good enough now that .git
can be a file pointing to the real $GIT_DIR so the tests are changed to
reflect this.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>
---
 git-submodule.sh |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/git-submodule.sh b/git-submodule.sh
index a6aaf40..e7c08b5 100755
--- a/git-submodule.sh
+++ b/git-submodule.sh
@@ -288,7 +288,7 @@ cmd_update()
 			continue
 		fi
 
-		if ! test -d "$path"/.git
+		if ! test -d "$path"/.git -o -f "$path"/.git
 		then
 			module_clone "$path" "$url" || exit
 			subsha1=
@@ -362,7 +362,7 @@ cmd_status()
 	do
 		name=$(module_name "$path") || exit
 		url=$(git config submodule."$name".url)
-		if test -z "url" || ! test -d "$path"/.git
+		if test -z "url" || ! test -d "$path"/.git -o -f "$path"/.git
 		then
 			say "-$sha1 $path"
 			continue;
-- 
1.5.4.1.188.g3ea1f5

[PATCH 4/4] Teach GIT-VERSION-GEN about the .git file

[Lars Hjemli]

The presence of a .git directory used to be good enough evidence that
GIT-VERSION-GEN could use 'git describe' to get a version number. But
now .git might as well be a file so the test must be extended to cater for
such setups.

Signed-off-by: Lars Hjemli <hjemli@gmail.com>
---
 GIT-VERSION-GEN |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/GIT-VERSION-GEN b/GIT-VERSION-GEN
index 1ad324e..10fe488 100755
--- a/GIT-VERSION-GEN
+++ b/GIT-VERSION-GEN
@@ -11,7 +11,7 @@ LF='
 if test -f version
 then
 	VN=$(cat version) || VN="$DEF_VER"
-elif test -d .git &&
+elif test -d .git -o -f .git &&
 	VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
 	case "$VN" in
 	*$LF*) (exit 1) ;;
-- 
1.5.4.1.188.g3ea1f5