fast-export, fast-import: add support for signed-commits

fast-export has a --signed-tags= option that controls how to handle tag
signatures.  However, there is no equivalent for commit signatures; it
just silently strips the signature out of the commit (analogously to
--signed-tags=strip).

While signatures are generally problematic for fast-export/fast-import
(because hashes are likely to change), if they're going to support tag
signatures, there's no reason to not also support commit signatures.

So, implement a --signed-commits= option that mirrors the --signed-tags=
option.

On the fast-export side, try to be as much like signed-tags as possible,
in both implementation and in user-interface.  This will change the
default behavior to '--signed-commits=abort' from what is now
'--signed-commits=strip'.  In order to provide an escape hatch for users
of third-party tools that call fast-export and do not yet know of the
--signed-commits= option, add an environment variable
'FAST_EXPORT_SIGNED_COMMITS_NOABORT=1' that changes the default to
'--signed-commits=warn-strip'.

Signed-off-by: Luke Shumaker <[email protected]>
Signed-off-by: Christian Couder <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: LukeShu

Documentation/git-fast-export.adoc

@@ -43,6 +43,17 @@ they will be exported, but you will see a warning.  'verbatim' and
 transformation affecting tags will be performed, or if you do not
 care that the resulting tag will have an invalid signature.
 
+--signed-commits=(verbatim|warn-verbatim|warn-strip|strip|abort)::
+	Specify how to handle signed commits.  Behaves exactly as
+	'--signed-tags', but for commits.
++
+Earlier versions this command that did not have '--signed-commits'
+behaved as if '--signed-commits=strip'.  As an escape hatch for users
+of tools that call 'git fast-export' but do not yet support
+'--signed-commits', you may set the environment variable
+'FAST_EXPORT_SIGNED_COMMITS_NOABORT=1' in order to change the default
+from 'abort' to 'warn-strip'.
+
 --tag-of-filtered-object=(abort|drop|rewrite)::
 	Specify how to handle tags whose tagged object is filtered out.
 	Since revisions and files to export can be limited by path,

Documentation/git-fast-import.adoc

@@ -431,12 +431,21 @@ and control the current import process.  More detailed discussion
 Create or update a branch with a new commit, recording one logical
 change to the project.
 
+////
+Yes, it's intentional that the 'gpgsig' line doesn't have a trailing
+`LF`; the definition of `data` has a byte-count prefix, so it
+doesn't need an `LF` to act as a terminator (and `data` also already
+includes an optional trailing `LF?` just in case you want to include
+one).
+////
+
 ....
 	'commit' SP <ref> LF
 	mark?
 	original-oid?
 	('author' (SP <name>)? SP LT <email> GT SP <when> LF)?
 	'committer' (SP <name>)? SP LT <email> GT SP <when> LF
+	('gpgsig' SP <alg> LF data)?
 	('encoding' SP <encoding> LF)?
 	data
 	('from' SP <commit-ish> LF)?
@@ -505,6 +514,15 @@ that was selected by the --date-format=<fmt> command-line option.
 See ``Date Formats'' above for the set of supported formats, and
 their syntax.
 
+`gpgsig`
+^^^^^^^^
+
+The optional `gpgsig` command is used to include a PGP/GPG signature
+that signs the commit data.
+
+Here <alg> specifies which hashing algorithm is used for this
+signature, either `sha1` or `sha256`.
+
 `encoding`
 ^^^^^^^^^^
 The optional `encoding` command indicates the encoding of the commit

builtin/fast-export.c

@@ -35,8 +35,11 @@ static const char *fast_export_usage[] = {
 	NULL
 };
 
+enum sign_mode { SIGN_ABORT, SIGN_VERBATIM, SIGN_STRIP, SIGN_WARN_VERBATIM, SIGN_WARN_STRIP };
+
 static int progress;
-static enum signed_tag_mode { SIGNED_TAG_ABORT, VERBATIM, WARN_VERBATIM, WARN_STRIP, STRIP } signed_tag_mode = SIGNED_TAG_ABORT;
+static enum sign_mode signed_tag_mode = SIGN_ABORT;
+static enum sign_mode signed_commit_mode = SIGN_ABORT;
 static enum tag_of_filtered_mode { TAG_FILTERING_ABORT, DROP, REWRITE } tag_of_filtered_mode = TAG_FILTERING_ABORT;
 static enum reencode_mode { REENCODE_ABORT, REENCODE_YES, REENCODE_NO } reencode_mode = REENCODE_ABORT;
 static int fake_missing_tagger;
@@ -53,23 +56,24 @@ static int anonymize;
 static struct hashmap anonymized_seeds;
 static struct revision_sources revision_sources;
 
-static int parse_opt_signed_tag_mode(const struct option *opt,
+static int parse_opt_sign_mode(const struct option *opt,
 				     const char *arg, int unset)
 {
-	enum signed_tag_mode *val = opt->value;
-
-	if (unset || !strcmp(arg, "abort"))
-		*val = SIGNED_TAG_ABORT;
+	enum sign_mode *val = opt->value;
+	if (unset)
+		return 0;
+	else if (!strcmp(arg, "abort"))
+		*val = SIGN_ABORT;
 	else if (!strcmp(arg, "verbatim") || !strcmp(arg, "ignore"))
-		*val = VERBATIM;
+		*val = SIGN_VERBATIM;
 	else if (!strcmp(arg, "warn-verbatim") || !strcmp(arg, "warn"))
-		*val = WARN_VERBATIM;
+		*val = SIGN_WARN_VERBATIM;
 	else if (!strcmp(arg, "warn-strip"))
-		*val = WARN_STRIP;
+		*val = SIGN_WARN_STRIP;
 	else if (!strcmp(arg, "strip"))
-		*val = STRIP;
+		*val = SIGN_STRIP;
 	else
-		return error("Unknown signed-tags mode: %s", arg);
+		return error("Unknown %s mode: %s", opt->long_name, arg);
 	return 0;
 }
 
@@ -611,6 +615,44 @@ static void anonymize_ident_line(const char **beg, const char **end)
 	*end = out->buf + out->len;
 }
 
+/*
+ * find_commit_multiline_header is similar to find_commit_header,
+ * except that it handles multi-line headers, rathar than simply
+ * returning the first line of the header.
+ *
+ * The returned string has had the ' ' line continuation markers
+ * removed, and points to statically allocated memory (not to memory
+ * within 'msg'), so it is only valid until the next call to
+ * find_commit_multiline_header.
+ *
+ * If the header is found, then *end is set to point at the '\n' in
+ * msg that immediately follows the header value.
+ */
+static const char *find_commit_multiline_header(const char *msg,
+						const char *key,
+						const char **end)
+{
+	struct strbuf val = STRBUF_INIT;
+	const char *bol, *eol;
+	size_t len;
+
+	bol = find_commit_header(msg, key, &len);
+	if (!bol)
+		return NULL;
+	eol = bol + len;
+	strbuf_add(&val, bol, len);
+
+	while (eol[0] == '\n' && eol[1] == ' ') {
+		bol = eol + 2;
+		eol = strchrnul(bol, '\n');
+		strbuf_addch(&val, '\n');
+		strbuf_add(&val, bol, eol - bol);
+	}
+
+	*end = eol;
+	return strbuf_detach(&val, NULL);
+}
+
 static void handle_commit(struct commit *commit, struct rev_info *rev,
 			  struct string_list *paths_of_changed_objects)
 {
@@ -619,6 +661,7 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	const char *author, *author_end, *committer, *committer_end;
 	const char *encoding = NULL;
 	size_t encoding_len;
+	const char *signature_alg = NULL, *signature = NULL;
 	const char *message;
 	char *reencoded = NULL;
 	struct commit_list *p;
@@ -645,17 +688,25 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	commit_buffer_cursor = committer_end = strchrnul(committer, '\n');
 
 	/*
-	 * find_commit_header() gets a `+ 1` because
-	 * commit_buffer_cursor points at the trailing "\n" at the end
-	 * of the previous line, but find_commit_header() wants a
+	 * find_commit_header() and find_commit_multiline_header() get
+	 * a `+ 1` because commit_buffer_cursor points at the trailing
+	 * "\n" at the end of the previous line, but they want a
 	 * pointer to the beginning of the next line.
 	 */
+
 	if (*commit_buffer_cursor == '\n') {
 		encoding = find_commit_header(commit_buffer_cursor + 1, "encoding", &encoding_len);
 		if (encoding)
 			commit_buffer_cursor = encoding + encoding_len;
 	}
 
+	if (*commit_buffer_cursor == '\n') {
+		if ((signature = find_commit_multiline_header(commit_buffer_cursor + 1, "gpgsig", &commit_buffer_cursor)))
+			signature_alg = "sha1";
+		else if ((signature = find_commit_multiline_header(commit_buffer_cursor + 1, "gpgsig-sha256", &commit_buffer_cursor)))
+			signature_alg = "sha256";
+	}
+
 	message = strstr(commit_buffer_cursor, "\n\n");
 	if (message)
 		message += 2;
@@ -719,6 +770,31 @@ static void handle_commit(struct commit *commit, struct rev_info *rev,
 	printf("%.*s\n%.*s\n",
 	       (int)(author_end - author), author,
 	       (int)(committer_end - committer), committer);
+	if (signature) {
+		switch (signed_commit_mode) {
+		case SIGN_ABORT:
+			die("encountered signed commit %s; use "
+			    "--signed-commits=<mode> to handle it",
+			    oid_to_hex(&commit->object.oid));
+		case SIGN_WARN_VERBATIM:
+			warning("exporting signed commit %s",
+				oid_to_hex(&commit->object.oid));
+			/* fallthru */
+		case SIGN_VERBATIM:
+			printf("gpgsig %s\ndata %u\n%s",
+			       signature_alg,
+			       (unsigned)strlen(signature),
+			       signature);
+			break;
+		case SIGN_WARN_STRIP:
+			warning("stripping signature from commit %s",
+				oid_to_hex(&commit->object.oid));
+			/* fallthru */
+		case SIGN_STRIP:
+			break;
+		}
+		free((char *)signature);
+	}
 	if (!reencoded && encoding)
 		printf("encoding %.*s\n", (int)encoding_len, encoding);
 	printf("data %u\n%s",
@@ -834,21 +910,21 @@ static void handle_tag(const char *name, struct tag *tag)
 					       "\n-----BEGIN PGP SIGNATURE-----\n");
 		if (signature)
 			switch (signed_tag_mode) {
-			case SIGNED_TAG_ABORT:
+			case SIGN_ABORT:
 				die("encountered signed tag %s; use "
 				    "--signed-tags=<mode> to handle it",
 				    oid_to_hex(&tag->object.oid));
-			case WARN_VERBATIM:
+			case SIGN_WARN_VERBATIM:
 				warning("exporting signed tag %s",
 					oid_to_hex(&tag->object.oid));
 				/* fallthru */
-			case VERBATIM:
+			case SIGN_VERBATIM:
 				break;
-			case WARN_STRIP:
+			case SIGN_WARN_STRIP:
 				warning("stripping signature from tag %s",
 					oid_to_hex(&tag->object.oid));
 				/* fallthru */
-			case STRIP:
+			case SIGN_STRIP:
 				message_size = signature + 1 - message;
 				break;
 			}
@@ -1194,6 +1270,7 @@ int cmd_fast_export(int argc,
 		    const char *prefix,
 		    struct repository *repo UNUSED)
 {
+	const char *env_signed_commits_noabort;
 	struct rev_info revs;
 	struct commit *commit;
 	char *export_filename = NULL,
@@ -1207,7 +1284,10 @@ int cmd_fast_export(int argc,
 			    N_("show progress after <n> objects")),
 		OPT_CALLBACK(0, "signed-tags", &signed_tag_mode, N_("mode"),
 			     N_("select handling of signed tags"),
-			     parse_opt_signed_tag_mode),
+			     parse_opt_sign_mode),
+		OPT_CALLBACK(0, "signed-commits", &signed_commit_mode, N_("mode"),
+			     N_("select handling of signed commits"),
+			     parse_opt_sign_mode),
 		OPT_CALLBACK(0, "tag-of-filtered-object", &tag_of_filtered_mode, N_("mode"),
 			     N_("select handling of tags that tag filtered objects"),
 			     parse_opt_tag_of_filtered_mode),
@@ -1248,6 +1328,10 @@ int cmd_fast_export(int argc,
 	if (argc == 1)
 		usage_with_options (fast_export_usage, options);
 
+	env_signed_commits_noabort = getenv("FAST_EXPORT_SIGNED_COMMITS_NOABORT");
+	if (env_signed_commits_noabort && *env_signed_commits_noabort)
+		signed_commit_mode = SIGN_WARN_STRIP;
+
 	/* we handle encodings */
 	git_config(git_default_config, NULL);
 

builtin/fast-import.c

@@ -2719,10 +2719,13 @@ static struct hash_list *parse_merge(unsigned int *count)
 
 static void parse_new_commit(const char *arg)
 {
+	static struct strbuf sig = STRBUF_INIT;
 	static struct strbuf msg = STRBUF_INIT;
+	struct string_list siglines = STRING_LIST_INIT_NODUP;
 	struct branch *b;
 	char *author = NULL;
 	char *committer = NULL;
+	char *sig_alg = NULL;
 	char *encoding = NULL;
 	struct hash_list *merge_list = NULL;
 	unsigned int merge_count;
@@ -2746,6 +2749,13 @@ static void parse_new_commit(const char *arg)
 	}
 	if (!committer)
 		die("Expected committer but didn't get one");
+	if (skip_prefix(command_buf.buf, "gpgsig ", &v)) {
+		sig_alg = xstrdup(v);
+		read_next_command();
+		parse_data(&sig, 0, NULL);
+		read_next_command();
+	} else
+		strbuf_setlen(&sig, 0);
 	if (skip_prefix(command_buf.buf, "encoding ", &v)) {
 		encoding = xstrdup(v);
 		read_next_command();
@@ -2819,10 +2829,23 @@ static void parse_new_commit(const char *arg)
 		strbuf_addf(&new_data,
 			"encoding %s\n",
 			encoding);
+	if (sig_alg) {
+		if (!strcmp(sig_alg, "sha1"))
+			strbuf_addstr(&new_data, "gpgsig ");
+		else if (!strcmp(sig_alg, "sha256"))
+			strbuf_addstr(&new_data, "gpgsig-sha256 ");
+		else
+			die("Expected gpgsig algorithm sha1 or sha256, got %s", sig_alg);
+		string_list_split_in_place(&siglines, sig.buf, "\n", -1);
+		strbuf_add_separated_string_list(&new_data, "\n ", &siglines);
+		strbuf_addch(&new_data, '\n');
+	}
 	strbuf_addch(&new_data, '\n');
 	strbuf_addbuf(&new_data, &msg);
+	string_list_clear(&siglines, 1);
 	free(author);
 	free(committer);
+	free(sig_alg);
 	free(encoding);
 
 	if (!store_object(OBJ_COMMIT, &new_data, NULL, &b->oid, next_mark))