repository: introduce the repository object

Introduce the repository object 'struct repository' which can be used to
hold all state pertaining to a git repository.

Some of the benefits of object-ifying a repository are:

  1. Make the code base more readable and easier to reason about.

  2. Allow for working on multiple repositories, specifically
     submodules, within the same process.  Currently the process for
     working on a submodule involves setting up an argv_array of options
     for a particular command and then launching a child process to
     execute the command in the context of the submodule.  This is
     clunky and can require lots of little hacks in order to ensure
     correctness.  Ideally it would be nice to simply pass a repository
     and an options struct to a command.

  3. Eliminating reliance on global state will make it easier to
     enable the use of threading to improve performance.

Signed-off-by: Brandon Williams <bmwill@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 224 insertions, 0 deletions

diff --git a/Makefile b/Makefile
index f484801638..32e4efc710 100644
--- a/Makefile
+++ b/Makefile
@@ -839,6 +839,7 @@ LIB_OBJS += refs/ref-cache.o
 LIB_OBJS += ref-filter.o
 LIB_OBJS += remote.o
 LIB_OBJS += replace_object.o
+LIB_OBJS += repository.o
 LIB_OBJS += rerere.o
 LIB_OBJS += resolve-undo.o
 LIB_OBJS += revision.o
diff --git a/repository.c b/repository.c
new file mode 100644
index 0000000000..cf440405a8
--- /dev/null
+++ b/repository.c
@@ -0,0 +1,159 @@
+#include "cache.h"
+#include "repository.h"
+
+/* The main repository */
+static struct repository the_repo;
+struct repository *the_repository = &the_repo;
+
+static char *git_path_from_env(const char *envvar, const char *git_dir,
+			       const char *path, int fromenv)
+{
+	if (fromenv) {
+		const char *value = getenv(envvar);
+		if (value)
+			return xstrdup(value);
+	}
+
+	return xstrfmt("%s/%s", git_dir, path);
+}
+
+static int find_common_dir(struct strbuf *sb, const char *gitdir, int fromenv)
+{
+	if (fromenv) {
+		const char *value = getenv(GIT_COMMON_DIR_ENVIRONMENT);
+		if (value) {
+			strbuf_addstr(sb, value);
+			return 1;
+		}
+	}
+
+	return get_common_dir_noenv(sb, gitdir);
+}
+
+static void repo_setup_env(struct repository *repo)
+{
+	struct strbuf sb = STRBUF_INIT;
+
+	repo->different_commondir = find_common_dir(&sb, repo->gitdir,
+						    !repo->ignore_env);
+	repo->commondir = strbuf_detach(&sb, NULL);
+	repo->objectdir = git_path_from_env(DB_ENVIRONMENT, repo->commondir,
+					    "objects", !repo->ignore_env);
+	repo->graft_file = git_path_from_env(GRAFT_ENVIRONMENT, repo->commondir,
+					     "info/grafts", !repo->ignore_env);
+	repo->index_file = git_path_from_env(INDEX_ENVIRONMENT, repo->gitdir,
+					     "index", !repo->ignore_env);
+}
+
+void repo_set_gitdir(struct repository *repo, const char *path)
+{
+	const char *gitfile = read_gitfile(path);
+
+	/*
+	 * NEEDSWORK: Eventually we want to be able to free gitdir and the rest
+	 * of the environment before reinitializing it again, but we have some
+	 * crazy code paths where we try to set gitdir with the current gitdir
+	 * and we don't want to free gitdir before copying the passed in value.
+	 */
+	repo->gitdir = xstrdup(gitfile ? gitfile : path);
+
+	repo_setup_env(repo);
+}
+
+/*
+ * Attempt to resolve and set the provided 'gitdir' for repository 'repo'.
+ * Return 0 upon success and a non-zero value upon failure.
+ */
+static int repo_init_gitdir(struct repository *repo, const char *gitdir)
+{
+	int ret = 0;
+	int error = 0;
+	char *abspath = NULL;
+	const char *resolved_gitdir;
+
+	abspath = real_pathdup(gitdir, 0);
+	if (!abspath) {
+		ret = -1;
+		goto out;
+	}
+
+	/* 'gitdir' must reference the gitdir directly */
+	resolved_gitdir = resolve_gitdir_gently(abspath, &error);
+	if (!resolved_gitdir) {
+		ret = -1;
+		goto out;
+	}
+
+	repo_set_gitdir(repo, resolved_gitdir);
+
+out:
+	free(abspath);
+	return ret;
+}
+
+void repo_set_worktree(struct repository *repo, const char *path)
+{
+	repo->worktree = real_pathdup(path, 1);
+}
+
+static int read_and_verify_repository_format(struct repository_format *format,
+					     const char *commondir)
+{
+	int ret = 0;
+	struct strbuf sb = STRBUF_INIT;
+
+	strbuf_addf(&sb, "%s/config", commondir);
+	read_repository_format(format, sb.buf);
+	strbuf_reset(&sb);
+
+	if (verify_repository_format(format, &sb) < 0) {
+		warning("%s", sb.buf);
+		ret = -1;
+	}
+
+	strbuf_release(&sb);
+	return ret;
+}
+
+/*
+ * Initialize 'repo' based on the provided 'gitdir'.
+ * Return 0 upon success and a non-zero value upon failure.
+ */
+int repo_init(struct repository *repo, const char *gitdir, const char *worktree)
+{
+	struct repository_format format;
+	memset(repo, 0, sizeof(*repo));
+
+	repo->ignore_env = 1;
+
+	if (repo_init_gitdir(repo, gitdir))
+		goto error;
+
+	if (read_and_verify_repository_format(&format, repo->commondir))
+		goto error;
+
+	if (worktree)
+		repo_set_worktree(repo, worktree);
+
+	return 0;
+
+error:
+	repo_clear(repo);
+	return -1;
+}
+
+void repo_clear(struct repository *repo)
+{
+	free(repo->gitdir);
+	repo->gitdir = NULL;
+	free(repo->commondir);
+	repo->commondir = NULL;
+	free(repo->objectdir);
+	repo->objectdir = NULL;
+	free(repo->graft_file);
+	repo->graft_file = NULL;
+	free(repo->index_file);
+	repo->index_file = NULL;
+	free(repo->worktree);
+	repo->worktree = NULL;
+}
diff --git a/repository.h b/repository.h
new file mode 100644
index 0000000000..0a1db9633f
--- /dev/null
+++ b/repository.h
@@ -0,0 +1,64 @@
+#ifndef REPOSITORY_H
+#define REPOSITORY_H
+
+struct repository {
+	/* Environment */
+	/*
+	 * Path to the git directory.
+	 * Cannot be NULL after initialization.
+	 */
+	char *gitdir;
+
+	/*
+	 * Path to the common git directory.
+	 * Cannot be NULL after initialization.
+	 */
+	char *commondir;
+
+	/*
+	 * Path to the repository's object store.
+	 * Cannot be NULL after initialization.
+	 */
+	char *objectdir;
+
+	/*
+	 * Path to the repository's graft file.
+	 * Cannot be NULL after initialization.
+	 */
+	char *graft_file;
+
+	/*
+	 * Path to the current worktree's index file.
+	 * Cannot be NULL after initialization.
+	 */
+	char *index_file;
+
+	/*
+	 * Path to the working directory.
+	 * A NULL value indicates that there is no working directory.
+	 */
+	char *worktree;
+
+	/* Configurations */
+	/*
+	 * Bit used during initialization to indicate if repository state (like
+	 * the location of the 'objectdir') should be read from the
+	 * environment.  By default this bit will be set at the begining of
+	 * 'repo_init()' so that all repositories will ignore the environment.
+	 * The exception to this is 'the_repository', which doesn't go through
+	 * the normal 'repo_init()' process.
+	 */
+	unsigned ignore_env:1;
+
+	/* Indicate if a repository has a different 'commondir' from 'gitdir' */
+	unsigned different_commondir:1;
+};
+
+extern struct repository *the_repository;
+
+extern void repo_set_gitdir(struct repository *repo, const char *path);
+extern void repo_set_worktree(struct repository *repo, const char *path);
+extern int repo_init(struct repository *repo, const char *gitdir, const char *worktree);
+extern void repo_clear(struct repository *repo);
+
+#endif /* REPOSITORY_H */