Merge branch 'bc/sha-256-part-1-of-4'

SHA-256 transition continues.

* bc/sha-256-part-1-of-4: (22 commits)
  fast-import: add options for rewriting submodules
  fast-import: add a generic function to iterate over marks
  fast-import: make find_marks work on any mark set
  fast-import: add helper function for inserting mark object entries
  fast-import: permit reading multiple marks files
  commit: use expected signature header for SHA-256
  worktree: allow repository version 1
  init-db: move writing repo version into a function
  builtin/init-db: add environment variable for new repo hash
  builtin/init-db: allow specifying hash algorithm on command line
  setup: allow check_repository_format to read repository format
  t/helper: make repository tests hash independent
  t/helper: initialize repository if necessary
  t/helper/test-dump-split-index: initialize git repository
  t6300: make hash algorithm independent
  t6300: abstract away SHA-1-specific constants
  t: use hash-specific lookup tables to define test constants
  repository: require a build flag to use SHA-256
  hex: add functions to parse hex object IDs in any algorithm
  hex: introduce parsing variants taking hash algorithms
  ...

1 files changed, 65 insertions, 10 deletions

diff --git a/builtin/init-db.c b/builtin/init-db.c
index 5bf61a7e05..0b7222e718 100644
--- a/builtin/init-db.c
+++ b/builtin/init-db.c
@@ -20,6 +20,8 @@
 #define TEST_FILEMODE 1
 #endif
 
+#define GIT_DEFAULT_HASH_ENVIRONMENT "GIT_DEFAULT_HASH"
+
 static int init_is_bare_repository = 0;
 static int init_shared_repository = -1;
 static const char *init_db_template_dir;
@@ -176,13 +178,36 @@ static int needs_work_tree_config(const char *git_dir, const char *work_tree)
 	return 1;
 }
 
+void initialize_repository_version(int hash_algo)
+{
+	char repo_version_string[10];
+	int repo_version = GIT_REPO_VERSION;
+
+#ifndef ENABLE_SHA256
+	if (hash_algo != GIT_HASH_SHA1)
+		die(_("The hash algorithm %s is not supported in this build."), hash_algos[hash_algo].name);
+#endif
+
+	if (hash_algo != GIT_HASH_SHA1)
+		repo_version = GIT_REPO_VERSION_READ;
+
+	/* This forces creation of new config file */
+	xsnprintf(repo_version_string, sizeof(repo_version_string),
+		  "%d", repo_version);
+	git_config_set("core.repositoryformatversion", repo_version_string);
+
+	if (hash_algo != GIT_HASH_SHA1)
+		git_config_set("extensions.objectformat",
+			       hash_algos[hash_algo].name);
+}
+
 static int create_default_files(const char *template_path,
-				const char *original_git_dir)
+				const char *original_git_dir,
+				const struct repository_format *fmt)
 {
 	struct stat st1;
 	struct strbuf buf = STRBUF_INIT;
 	char *path;
-	char repo_version_string[10];
 	char junk[2];
 	int reinit;
 	int filemode;
@@ -244,10 +269,7 @@ static int create_default_files(const char *template_path,
 			exit(1);
 	}
 
-	/* This forces creation of new config file */
-	xsnprintf(repo_version_string, sizeof(repo_version_string),
-		  "%d", GIT_REPO_VERSION);
-	git_config_set("core.repositoryformatversion", repo_version_string);
+	initialize_repository_version(fmt->hash_algo);
 
 	/* Check filemode trustability */
 	path = git_path_buf(&buf, "config");
@@ -340,12 +362,33 @@ static void separate_git_dir(const char *git_dir, const char *git_link)
 	write_file(git_link, "gitdir: %s", git_dir);
 }
 
+static void validate_hash_algorithm(struct repository_format *repo_fmt, int hash)
+{
+	const char *env = getenv(GIT_DEFAULT_HASH_ENVIRONMENT);
+	/*
+	 * If we already have an initialized repo, don't allow the user to
+	 * specify a different algorithm, as that could cause corruption.
+	 * Otherwise, if the user has specified one on the command line, use it.
+	 */
+	if (repo_fmt->version >= 0 && hash != GIT_HASH_UNKNOWN && hash != repo_fmt->hash_algo)
+		die(_("attempt to reinitialize repository with different hash"));
+	else if (hash != GIT_HASH_UNKNOWN)
+		repo_fmt->hash_algo = hash;
+	else if (env) {
+		int env_algo = hash_algo_by_name(env);
+		if (env_algo == GIT_HASH_UNKNOWN)
+			die(_("unknown hash algorithm '%s'"), env);
+		repo_fmt->hash_algo = env_algo;
+	}
+}
+
 int init_db(const char *git_dir, const char *real_git_dir,
-	    const char *template_dir, unsigned int flags)
+	    const char *template_dir, int hash, unsigned int flags)
 {
 	int reinit;
 	int exist_ok = flags & INIT_DB_EXIST_OK;
 	char *original_git_dir = real_pathdup(git_dir, 1);
+	struct repository_format repo_fmt = REPOSITORY_FORMAT_INIT;
 
 	if (real_git_dir) {
 		struct stat st;
@@ -378,9 +421,11 @@ int init_db(const char *git_dir, const char *real_git_dir,
 	 * config file, so this will not fail.  What we are catching
 	 * is an attempt to reinitialize new repository with an old tool.
 	 */
-	check_repository_format();
+	check_repository_format(&repo_fmt);
 
-	reinit = create_default_files(template_dir, original_git_dir);
+	validate_hash_algorithm(&repo_fmt, hash);
+
+	reinit = create_default_files(template_dir, original_git_dir, &repo_fmt);
 
 	create_object_directory();
 
@@ -482,6 +527,8 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 	const char *work_tree;
 	const char *template_dir = NULL;
 	unsigned int flags = 0;
+	const char *object_format = NULL;
+	int hash_algo = GIT_HASH_UNKNOWN;
 	const struct option init_db_options[] = {
 		OPT_STRING(0, "template", &template_dir, N_("template-directory"),
 				N_("directory from which templates will be used")),
@@ -494,6 +541,8 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 		OPT_BIT('q', "quiet", &flags, N_("be quiet"), INIT_DB_QUIET),
 		OPT_STRING(0, "separate-git-dir", &real_git_dir, N_("gitdir"),
 			   N_("separate git dir from working tree")),
+		OPT_STRING(0, "object-format", &object_format, N_("hash"),
+			   N_("specify the hash algorithm to use")),
 		OPT_END()
 	};
 
@@ -546,6 +595,12 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 		free(cwd);
 	}
 
+	if (object_format) {
+		hash_algo = hash_algo_by_name(object_format);
+		if (hash_algo == GIT_HASH_UNKNOWN)
+			die(_("unknown hash algorithm '%s'"), object_format);
+	}
+
 	if (init_shared_repository != -1)
 		set_shared_repository(init_shared_repository);
 
@@ -597,5 +652,5 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 	UNLEAK(work_tree);
 
 	flags |= INIT_DB_EXIST_OK;
-	return init_db(git_dir, real_git_dir, template_dir, flags);
+	return init_db(git_dir, real_git_dir, template_dir, hash_algo, flags);
 }