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

SHA-256 transition continues.

Tentatively I dropped the bits about signed tag, as it depended on
a reverted change to the gpg interface API.

* 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
  ...

Author: gitster

Documentation/git-fast-import.txt

@@ -122,6 +122,26 @@ Locations of Marks Files
 Relative and non-relative marks may be combined by interweaving
 --(no-)-relative-marks with the --(import|export)-marks= options.
 
+Submodule Rewriting
+~~~~~~~~~~~~~~~~~~~
+
+--rewrite-submodules-from=<name>:<file>::
+--rewrite-submodules-to=<name>:<file>::
+  Rewrite the object IDs for the submodule specified by <name> from the values
+	used in the from <file> to those used in the to <file>. The from marks should
+	have been created by `git fast-export`, and the to marks should have been
+	created by `git fast-import` when importing that same submodule.
++
+<name> may be any arbitrary string not containing a colon character, but the
+same value must be used with both options when specifying corresponding marks.
+Multiple submodules may be specified with different values for <name>. It is an
+error not to use these options in corresponding pairs.
++
+These options are primarily useful when converting a repository from one hash
+algorithm to another; without them, fast-import will fail if it encounters a
+submodule because it has no way of writing the object ID into the new hash
+algorithm.
+
 Performance and Compression Tuning
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 

Documentation/git-init.txt

@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 'git init' [-q | --quiet] [--bare] [--template=<template_directory>]
-	  [--separate-git-dir <git dir>]
+	  [--separate-git-dir <git dir>] [--object-format=<format]
 	  [--shared[=<permissions>]] [directory]
 
 
@@ -48,6 +48,11 @@ Only print error and warning messages; all other output will be suppressed.
 Create a bare repository. If `GIT_DIR` environment is not set, it is set to the
 current working directory.
 
+--object-format=<format>::
+
+Specify the given object format (hash algorithm) for the repository.  The valid
+values are 'sha1' and (if enabled) 'sha256'.  'sha1' is the default.
+
 --template=<template_directory>::
 
 Specify the directory from which templates will be used.  (See the "TEMPLATE

Documentation/git.txt

@@ -493,6 +493,12 @@ double-quotes and respecting backslash escapes. E.g., the value
 	details. This variable has lower precedence than other path
 	variables such as GIT_INDEX_FILE, GIT_OBJECT_DIRECTORY...
 
+`GIT_DEFAULT_HASH_ALGORITHM`::
+	If this variable is set, the default hash algorithm for new
+	repositories will be set to this value. This value is currently
+	ignored when cloning; the setting of the remote repository
+	is used instead. The default is "sha1".
+
 Git Commits
 ~~~~~~~~~~~
 `GIT_AUTHOR_NAME`::

builtin/clone.c

@@ -1110,7 +1110,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	init_db(git_dir, real_git_dir, option_template, INIT_DB_QUIET);
+	init_db(git_dir, real_git_dir, option_template, GIT_HASH_UNKNOWN, INIT_DB_QUIET);
 
 	if (real_git_dir)
 		git_dir = real_git_dir;

builtin/commit.c

@@ -1667,7 +1667,7 @@ int cmd_commit(int argc, const char **argv, const char *prefix)
 	}
 
 	if (amend) {
-		const char *exclude_gpgsig[2] = { "gpgsig", NULL };
+		const char *exclude_gpgsig[3] = { "gpgsig", "gpgsig-sha256", NULL };
 		extra = read_commit_extra_headers(current_head, exclude_gpgsig);
 	} else {
 		struct commit_extra_header **tail = &extra;

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);
 }

builtin/pack-objects.c

@@ -880,7 +880,7 @@ static void write_reused_pack_one(size_t pos, struct hashfile *out,
 			len = encode_in_pack_object_header(header, sizeof(header),
 							   OBJ_REF_DELTA, size);
 			hashwrite(out, header, len);
-			hashwrite(out, base_oid.hash, 20);
+			hashwrite(out, base_oid.hash, the_hash_algo->rawsz);
 			copy_pack_data(out, reuse_packfile, w_curs, cur, next - cur);
 			return;
 		}

cache.h

@@ -627,7 +627,9 @@ int path_inside_repo(const char *prefix, const char *path);
 #define INIT_DB_EXIST_OK 0x0002
 
 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_algo,
+	    unsigned int flags);
+void initialize_repository_version(int hash_algo);
 
 void sanitize_stdfds(void);
 int daemonize(void);
@@ -1086,8 +1088,10 @@ int verify_repository_format(const struct repository_format *format,
  * and die if it is a version we don't understand. Generally one would
  * set_git_dir() before calling this, and use it only for "are we in a valid
  * repo?".
+ *
+ * If successful and fmt is not NULL, fill fmt with data.
  */
-void check_repository_format(void);
+void check_repository_format(struct repository_format *fmt);
 
 #define MTIME_CHANGED	0x0001
 #define CTIME_CHANGED	0x0002
@@ -1479,6 +1483,9 @@ int set_disambiguate_hint_config(const char *var, const char *value);
 int get_sha1_hex(const char *hex, unsigned char *sha1);
 int get_oid_hex(const char *hex, struct object_id *sha1);
 
+/* Like get_oid_hex, but for an arbitrary hash algorithm. */
+int get_oid_hex_algop(const char *hex, struct object_id *oid, const struct git_hash_algo *algop);
+
 /*
  * Read `len` pairs of hexadecimal digits from `hex` and write the
  * values to `binary` as `len` bytes. Return 0 on success, or -1 if
@@ -1514,6 +1521,20 @@ char *oid_to_hex(const struct object_id *oid);						/* same static buffer */
  */
 int parse_oid_hex(const char *hex, struct object_id *oid, const char **end);
 
+/* Like parse_oid_hex, but for an arbitrary hash algorithm. */
+int parse_oid_hex_algop(const char *hex, struct object_id *oid, const char **end,
+			const struct git_hash_algo *algo);
+
+
+/*
+ * These functions work like get_oid_hex and parse_oid_hex, but they will parse
+ * a hex value for any algorithm. The algorithm is detected based on the length
+ * and the algorithm in use is returned. If this is not a hex object ID in any
+ * algorithm, returns GIT_HASH_UNKNOWN.
+ */
+int get_oid_hex_any(const char *hex, struct object_id *oid);
+int parse_oid_hex_any(const char *hex, struct object_id *oid, const char **end);
+
 /*
  * This reads short-hand syntax that not only evaluates to a commit
  * object name, but also can act as if the end user spelled the name

commit.c

@@ -972,14 +972,22 @@ struct commit *get_fork_point(const char *refname, struct commit *commit)
 	return ret;
 }
 
-static const char gpg_sig_header[] = "gpgsig";
-static const int gpg_sig_header_len = sizeof(gpg_sig_header) - 1;
+/*
+ * Indexed by hash algorithm identifier.
+ */
+static const char *gpg_sig_headers[] = {
+	NULL,
+	"gpgsig",
+	"gpgsig-sha256",
+};
 
 static int do_sign_commit(struct strbuf *buf, const char *keyid)
 {
 	struct strbuf sig = STRBUF_INIT;
 	int inspos, copypos;
 	const char *eoh;
+	const char *gpg_sig_header = gpg_sig_headers[hash_algo_by_ptr(the_hash_algo)];
+	int gpg_sig_header_len = strlen(gpg_sig_header);
 
 	/* find the end of the header */
 	eoh = strstr(buf->buf, "\n\n");
@@ -1021,6 +1029,8 @@ int parse_signed_commit(const struct commit *commit,
 	const char *buffer = get_commit_buffer(commit, &size);
 	int in_signature, saw_signature = -1;
 	const char *line, *tail;
+	const char *gpg_sig_header = gpg_sig_headers[hash_algo_by_ptr(the_hash_algo)];
+	int gpg_sig_header_len = strlen(gpg_sig_header);
 
 	line = buffer;
 	tail = buffer + size;
@@ -1067,11 +1077,17 @@ int remove_signature(struct strbuf *buf)
 
 		if (in_signature && line[0] == ' ')
 			sig_end = next;
-		else if (starts_with(line, gpg_sig_header) &&
-			 line[gpg_sig_header_len] == ' ') {
-			sig_start = line;
-			sig_end = next;
-			in_signature = 1;
+		else if (starts_with(line, "gpgsig")) {
+			int i;
+			for (i = 1; i < GIT_HASH_NALGOS; i++) {
+				const char *p;
+				if (skip_prefix(line, gpg_sig_headers[i], &p) &&
+				    *p == ' ') {
+					sig_start = line;
+					sig_end = next;
+					in_signature = 1;
+				}
+			}
 		} else {
 			if (*line == '\n')
 				/* dump the whole remainder of the buffer */

config.mak.dev

@@ -16,6 +16,8 @@ DEVELOPER_CFLAGS += -Wstrict-prototypes
 DEVELOPER_CFLAGS += -Wunused
 DEVELOPER_CFLAGS += -Wvla
 
+DEVELOPER_CFLAGS += -DENABLE_SHA256
+
 ifndef COMPILER_FEATURES
 COMPILER_FEATURES := $(shell ./detect-compiler $(CC))
 endif

csum-file.c

@@ -157,7 +157,7 @@ void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpo
 {
 	hashflush(f);
 	checkpoint->offset = f->total;
-	checkpoint->ctx = f->ctx;
+	the_hash_algo->clone_fn(&checkpoint->ctx, &f->ctx);
 }
 
 int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint)