environment: migrate encoding configs to struct repository

malon7782 · malon7782 · commit 196b272c881c · 2026-03-02T04:21:43.000+08:00
The global variables 'git_commit_encoding' and 'git_log_output_encoding'
prevent libification.

Migrate these variables into 'struct repository'. Note that these variables
are not migrated to 'repo_settings'. As user preferences, they must be parsed
eagerly to maintain immediate UX feedback.

While the core read and write APIs (updated in previous patches) now
utilize the 'struct repository' pointer, the config parsing step
('git_default_i18n_config') currently parses these values into
'the_repository', since safely plumbing a repository pointer through
the 'git_default_config' callback machinery is highly invasive due to
the diverse and custom structures currently passed via the 'void *cb'
parameter.

Signed-off-by: Tian Yuchen &lt;a3205153416@gmail.com&gt;
diff --git a/builtin/am.c b/builtin/am.c
@@ -1216,7 +1216,7 @@ static int parse_mail(struct am_state *state, const char *mail)
 	setup_mailinfo(the_repository, &mi);
 
 	if (state->utf8)
-		mi.metainfo_charset = get_commit_output_encoding();
+		mi.metainfo_charset = get_commit_output_encoding(the_repository);
 	else
 		mi.metainfo_charset = NULL;
 
@@ -1355,7 +1355,7 @@ static void get_commit_info(struct am_state *state, struct commit *commit)
 	struct ident_split id;
 
 	buffer = repo_logmsg_reencode(the_repository, commit, NULL,
-				      get_commit_output_encoding());
+				      get_commit_output_encoding(the_repository));
 
 	ident_line = find_commit_header(buffer, "author", &ident_len);
 	if (!ident_line)
diff --git a/builtin/blame.c b/builtin/blame.c
@@ -202,7 +202,7 @@ static void get_commit_info(struct commit *commit, struct commit_info *ret)
 	const char *subject, *encoding;
 	const char *message;
 
-	encoding = get_log_output_encoding();
+	encoding = get_log_output_encoding(the_repository);
 	message = repo_logmsg_reencode(the_repository, commit, NULL, encoding);
 	get_ac_line(message, "\nauthor ",
 		    &ret->author, &ret->author_mail,
diff --git a/builtin/commit.c b/builtin/commit.c
@@ -794,7 +794,7 @@ static int prepare_to_commit(const char *index_file, const char *prefix,
 			c = lookup_commit_reference_by_name(squash_message);
 			if (!c)
 				die(_("could not lookup commit '%s'"), squash_message);
-			ctx.output_encoding = get_commit_output_encoding();
+			ctx.output_encoding = get_commit_output_encoding(the_repository);
 			repo_format_commit_message(the_repository, c,
 						   "squash! %s\n\n", &sb,
 						   &ctx);
@@ -829,7 +829,7 @@ static int prepare_to_commit(const char *index_file, const char *prefix,
 		commit = lookup_commit_reference_by_name(fixup_commit);
 		if (!commit)
 			die(_("could not lookup commit '%s'"), fixup_commit);
-		ctx.output_encoding = get_commit_output_encoding();
+		ctx.output_encoding = get_commit_output_encoding(the_repository);
 		fmt = xstrfmt("%s! %%s\n\n", fixup_prefix);
 		repo_format_commit_message(the_repository, commit, fmt, &sb,
 					   &ctx);
@@ -1235,7 +1235,7 @@ static const char *read_commit_message(const char *name)
 	commit = lookup_commit_reference_by_name(name);
 	if (!commit)
 		die(_("could not lookup commit '%s'"), name);
-	out_enc = get_commit_output_encoding();
+	out_enc = get_commit_output_encoding(the_repository);
 	return repo_logmsg_reencode(the_repository, commit, NULL, out_enc);
 }
 
diff --git a/builtin/log.c b/builtin/log.c
@@ -568,7 +568,7 @@ static void show_tagger(const char *buf, struct rev_info *rev)
 
 	pp.fmt = rev->commit_format;
 	pp.date_mode = rev->date_mode;
-	pp_user_info(&pp, "Tagger", &out, buf, get_log_output_encoding());
+	pp_user_info(&pp, "Tagger", &out, buf, get_log_output_encoding(the_repository));
 	fprintf(rev->diffopt.file, "%s", out.buf);
 	strbuf_release(&out);
 }
diff --git a/builtin/mailinfo.c b/builtin/mailinfo.c
@@ -52,7 +52,7 @@ static int parse_opt_quoted_cr(const struct option *opt, const char *arg, int un
 int cmd_mailinfo(int argc,
 		 const char **argv,
 		 const char *prefix,
-		 struct repository *repo UNUSED)
+		 struct repository *repo)
 {
 	struct metainfo_charset meta_charset;
 	struct mailinfo mi;
@@ -83,7 +83,7 @@ int cmd_mailinfo(int argc,
 		OPT_END()
 	};
 
-	setup_mailinfo(the_repository, &mi);
+	setup_mailinfo(repo, &mi);
 	meta_charset.policy = CHARSET_DEFAULT;
 
 	argc = parse_options(argc, argv, prefix, options, mailinfo_usage, 0);
@@ -93,7 +93,7 @@ int cmd_mailinfo(int argc,
 
 	switch (meta_charset.policy) {
 	case CHARSET_DEFAULT:
-		mi.metainfo_charset = get_commit_output_encoding();
+		mi.metainfo_charset = get_commit_output_encoding(repo);
 		break;
 	case CHARSET_NO_REENCODE:
 		mi.metainfo_charset = NULL;
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
@@ -304,7 +304,7 @@ static void show_commit(struct commit *commit, void *data)
 		ctx.date_mode = revs->date_mode;
 		ctx.date_mode_explicit = revs->date_mode_explicit;
 		ctx.fmt = revs->commit_format;
-		ctx.output_encoding = get_log_output_encoding();
+		ctx.output_encoding = get_log_output_encoding(the_repository);
 		ctx.color = revs->diffopt.use_color;
 		ctx.rev = revs;
 		pretty_print_commit(the_repository, &ctx, commit, &buf);
diff --git a/builtin/shortlog.c b/builtin/shortlog.c
@@ -248,7 +248,7 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 	ctx.fmt = CMIT_FMT_USERFORMAT;
 	ctx.abbrev = log->abbrev;
 	ctx.date_mode = log->date_mode;
-	ctx.output_encoding = get_log_output_encoding();
+	ctx.output_encoding = get_log_output_encoding(the_repository);
 
 	if (!log->summary) {
 		if (log->user_format)
diff --git a/bundle.c b/bundle.c
@@ -461,7 +461,7 @@ static void write_bundle_prerequisites(struct commit *commit, void *data)
 	write_or_die(bpi->fd, buf.buf, buf.len);
 
 	ctx.fmt = CMIT_FMT_ONELINE;
-	ctx.output_encoding = get_log_output_encoding();
+	ctx.output_encoding = get_log_output_encoding(the_repository);
 	strbuf_reset(&buf);
 	pretty_print_commit(the_repository, &ctx, commit, &buf);
 	strbuf_trim(&buf);
diff --git a/commit.c b/commit.c
@@ -1663,7 +1663,8 @@ N_("Warning: commit message did not conform to UTF-8.\n"
    "You may want to amend it after fixing the message, or set the config\n"
    "variable i18n.commitEncoding to the encoding your project uses.\n");
 
-static void write_commit_tree(struct strbuf *buffer, const char *msg, size_t msg_len,
+static void write_commit_tree(struct repository *r, struct strbuf *buffer,
+			      const char *msg, size_t msg_len,
 			      const struct object_id *tree,
 			      const struct object_id *parents, size_t parents_len,
 			      const char *author, const char *committer,
@@ -1673,7 +1674,7 @@ static void write_commit_tree(struct strbuf *buffer, const char *msg, size_t msg
 	size_t i;
 
 	/* Not having i18n.commitencoding is the same as having utf-8 */
-	encoding_is_utf8 = is_encoding_utf8(git_commit_encoding);
+	encoding_is_utf8 = is_encoding_utf8(get_commit_output_encoding(r));
 
 	strbuf_grow(buffer, 8192); /* should avoid reallocs for the headers */
 	strbuf_addf(buffer, "tree %s\n", oid_to_hex(tree));
@@ -1694,7 +1695,7 @@ static void write_commit_tree(struct strbuf *buffer, const char *msg, size_t msg
 		committer = git_committer_info(IDENT_STRICT);
 	strbuf_addf(buffer, "committer %s\n", committer);
 	if (!encoding_is_utf8)
-		strbuf_addf(buffer, "encoding %s\n", git_commit_encoding);
+		strbuf_addf(buffer, "encoding %s\n", get_commit_output_encoding(r));
 
 	while (extra) {
 		add_extra_header(buffer, extra);
@@ -1722,7 +1723,7 @@ int commit_tree_extended(struct repository *r, const char *msg, size_t msg_len,
 	size_t i, nparents;
 
 	/* Not having i18n.commitencoding is the same as having utf-8 */
-	encoding_is_utf8 = is_encoding_utf8(git_commit_encoding);
+	encoding_is_utf8 = is_encoding_utf8(get_commit_output_encoding(r));
 
 	odb_assert_oid_type(the_repository->objects, tree, OBJ_TREE);
 
@@ -1735,7 +1736,7 @@ int commit_tree_extended(struct repository *r, const char *msg, size_t msg_len,
 	for (const struct commit_list *p = parents; p; p = p->next)
 		oidcpy(&parent_buf[i++], &p->item->object.oid);
 
-	write_commit_tree(&buffer, msg, msg_len, tree, parent_buf, nparents, author, committer, extra);
+	write_commit_tree(r, &buffer, msg, msg_len, tree, parent_buf, nparents, author, committer, extra);
 	if (sign_commit && sign_commit_to_strbuf(&sig, &buffer, sign_commit)) {
 		result = -1;
 		goto out;
@@ -1763,7 +1764,7 @@ int commit_tree_extended(struct repository *r, const char *msg, size_t msg_len,
 			free(mapped_parents);
 			goto out;
 		}
-		write_commit_tree(&compat_buffer, msg, msg_len, &mapped_tree,
+		write_commit_tree(r, &compat_buffer, msg, msg_len, &mapped_tree,
 				  mapped_parents, nparents, author, committer, compat_extra);
 		free_commit_extra_headers(compat_extra);
 		free(mapped_parents);
diff --git a/environment.c b/environment.c
@@ -197,15 +197,14 @@ const char *strip_namespace(const char *namespaced_ref)
 	return NULL;
 }
 
-const char *get_log_output_encoding(void)
+const char *get_log_output_encoding(struct repository *r)
 {
-	return git_log_output_encoding ? git_log_output_encoding
-		: get_commit_output_encoding();
+	return r->log_output_encoding ? r->log_output_encoding : get_commit_output_encoding(r);
 }
 
-const char *get_commit_output_encoding(void)
+const char *get_commit_output_encoding(struct repository *r)
 {
-	return git_commit_encoding ? git_commit_encoding : "UTF-8";
+	return r->commit_encoding ? r->commit_encoding : "UTF-8";
 }
 
 int use_optional_locks(void)
@@ -569,16 +568,14 @@ static int git_default_sparse_config(const char *var, const char *value)
 static int git_default_i18n_config(const char *var, const char *value)
 {
 	if (!strcmp(var, "i18n.commitencoding")) {
-		FREE_AND_NULL(git_commit_encoding);
-		return git_config_string(&git_commit_encoding, var, value);
+		FREE_AND_NULL(the_repository->commit_encoding);
+		return git_config_string(&the_repository->commit_encoding, var, value);
 	}
-
 	if (!strcmp(var, "i18n.logoutputencoding")) {
-		FREE_AND_NULL(git_log_output_encoding);
-		return git_config_string(&git_log_output_encoding, var, value);
+		FREE_AND_NULL(the_repository->log_output_encoding);
+		return git_config_string(&the_repository->log_output_encoding, var, value);
 	}
 
-	/* Add other config variables here and to Documentation/config.adoc. */
 	return 0;
 }
 
diff --git a/environment.h b/environment.h
@@ -193,11 +193,8 @@ extern enum object_creation_mode object_creation_mode;
 
 extern int grafts_keep_true_parents;
 
-const char *get_log_output_encoding(void);
-const char *get_commit_output_encoding(void);
-
-extern char *git_commit_encoding;
-extern char *git_log_output_encoding;
+const char *get_log_output_encoding(struct repository *r);
+const char *get_commit_output_encoding(struct repository *r);
 
 extern char *editor_program;
 extern char *askpass_program;
diff --git a/log-tree.c b/log-tree.c
@@ -859,7 +859,7 @@ void show_log(struct rev_info *opt)
 
 		raw = (opt->commit_format == CMIT_FMT_USERFORMAT);
 		format_display_notes(&commit->object.oid, &notebuf,
-				     get_log_output_encoding(), raw);
+				     get_log_output_encoding(opt->repo), raw);
 		ctx.notes_message = strbuf_detach(&notebuf, NULL);
 	}
 
@@ -879,7 +879,7 @@ void show_log(struct rev_info *opt)
 	ctx.mailmap = opt->mailmap;
 	ctx.color = opt->diffopt.use_color;
 	ctx.expand_tabs_in_log = opt->expand_tabs_in_log;
-	ctx.output_encoding = get_log_output_encoding();
+	ctx.output_encoding = get_log_output_encoding(opt->repo);
 	ctx.rev = opt;
 	if (opt->from_ident.mail_begin && opt->from_ident.name_begin)
 		ctx.from_ident = &opt->from_ident;
diff --git a/pretty.c b/pretty.c
@@ -2298,7 +2298,7 @@ void pretty_print_commit(struct repository *r, struct pretty_print_context *pp,
 		return;
 	}
 
-	encoding = get_log_output_encoding();
+	encoding = get_log_output_encoding(r);
 	msg = reencoded = repo_logmsg_reencode(the_repository, commit, NULL,
 					       encoding);
 
diff --git a/remote-curl.c b/remote-curl.c
@@ -379,7 +379,7 @@ static int show_http_message(struct strbuf *type, struct strbuf *charset,
 	if (strcmp(type->buf, "text/plain"))
 		return -1;
 	if (charset->len)
-		strbuf_reencode(msg, charset->buf, get_log_output_encoding());
+		strbuf_reencode(msg, charset->buf, get_log_output_encoding(the_repository));
 
 	strbuf_trim(msg);
 	if (!msg->len)
diff --git a/replay.c b/replay.c
@@ -56,7 +56,7 @@ static struct commit *create_commit(struct repository *repo,
 	char *sign_commit = NULL; /* FIXME: cli users might want to sign again */
 	struct commit_extra_header *extra = NULL;
 	struct strbuf msg = STRBUF_INIT;
-	const char *out_enc = get_commit_output_encoding();
+	const char *out_enc = get_commit_output_encoding(repo);
 	const char *message = repo_logmsg_reencode(repo, based_on,
 						   NULL, out_enc);
 	const char *orig_message = NULL;
diff --git a/repository.c b/repository.c
@@ -370,6 +370,8 @@ void repo_clear(struct repository *repo)
 	FREE_AND_NULL(repo->index_file);
 	FREE_AND_NULL(repo->worktree);
 	FREE_AND_NULL(repo->submodule_prefix);
+	FREE_AND_NULL(repo->commit_encoding);
+	FREE_AND_NULL(repo->log_output_encoding);
 
 	odb_free(repo->objects);
 	repo->objects = NULL;
diff --git a/repository.h b/repository.h
@@ -172,6 +172,11 @@ struct repository {
 
 	/* Should repo_config() check for deprecated settings */
 	bool check_deprecated_config;
+
+	/* User's preferred encoding for commit messages and log output. */
+
+	char *commit_encoding;
+	char *log_output_encoding;
 };
 
 #ifdef USE_THE_REPOSITORY_VARIABLE
diff --git a/revision.c b/revision.c
@@ -2675,11 +2675,11 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 	} else if (!strcmp(arg, "--invert-grep")) {
 		revs->grep_filter.no_body_match = 1;
 	} else if ((argcount = parse_long_opt("encoding", argv, &optarg))) {
-		free(git_log_output_encoding);
+		free(revs->repo->log_output_encoding);
 		if (strcmp(optarg, "none"))
-			git_log_output_encoding = xstrdup(optarg);
+			revs->repo->log_output_encoding = xstrdup(optarg);
 		else
-			git_log_output_encoding = xstrdup("");
+			revs->repo->log_output_encoding = xstrdup("");
 		return argcount;
 	} else if (!strcmp(arg, "--reverse")) {
 		revs->reverse ^= 1;
@@ -3129,7 +3129,7 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s
 
 	diff_setup_done(&revs->diffopt);
 
-	if (!is_encoding_utf8(get_log_output_encoding()))
+	if (!is_encoding_utf8(get_log_output_encoding(revs->repo)))
 		revs->grep_filter.ignore_locale = 1;
 	compile_grep_patterns(&revs->grep_filter);
 
@@ -4063,7 +4063,7 @@ static int commit_match(struct commit *commit, struct rev_info *opt)
 	 * so we will not end up with a buffer that has two different encodings
 	 * in it.
 	 */
-	encoding = get_log_output_encoding();
+	encoding = get_log_output_encoding(opt->repo);
 	message = repo_logmsg_reencode(the_repository, commit, NULL, encoding);
 
 	/* Copy the commit to temporary if we are using "fake" headers */
diff --git a/sequencer.c b/sequencer.c
diff --git a/submodule.c b/submodule.c

Original file line number	Diff line number	Diff line change
`@@ -568,7 +568,7 @@ static void show_tagger(const char buf, struct rev_info rev)`
`568`	`568`
`569`	`569`	`pp.fmt = rev->commit_format;`
`570`	`570`	`pp.date_mode = rev->date_mode;`
`571`		`- pp_user_info(&pp, "Tagger", &out, buf, get_log_output_encoding());`
	`571`	`+ pp_user_info(&pp, "Tagger", &out, buf, get_log_output_encoding(the_repository));`
`572`	`572`	`fprintf(rev->diffopt.file, "%s", out.buf);`
`573`	`573`	`strbuf_release(&out);`
`574`	`574`	`}`
Original file line number	Diff line number	Diff line change
`@@ -197,15 +197,14 @@ const char strip_namespace(const char namespaced_ref)`
`197`	`197`	`return NULL;`
`198`	`198`	`}`
`199`	`199`
`200`		`-const char *get_log_output_encoding(void)`
	`200`	`+const char get_log_output_encoding(struct repository r)`
`201`	`201`	`{`
`202`		`- return git_log_output_encoding ? git_log_output_encoding`
`203`		`- : get_commit_output_encoding();`
	`202`	`+ return r->log_output_encoding ? r->log_output_encoding : get_commit_output_encoding(r);`
`204`	`203`	`}`
`205`	`204`
`206`		`-const char *get_commit_output_encoding(void)`
	`205`	`+const char get_commit_output_encoding(struct repository r)`
`207`	`206`	`{`
`208`		`- return git_commit_encoding ? git_commit_encoding : "UTF-8";`
	`207`	`+ return r->commit_encoding ? r->commit_encoding : "UTF-8";`
`209`	`208`	`}`
`210`	`209`
`211`	`210`	`int use_optional_locks(void)`
`@@ -569,16 +568,14 @@ static int git_default_sparse_config(const char var, const char value)`
`569`	`568`	`static int git_default_i18n_config(const char var, const char value)`
`570`	`569`	`{`
`571`	`570`	`if (!strcmp(var, "i18n.commitencoding")) {`
`572`		`- FREE_AND_NULL(git_commit_encoding);`
`573`		`- return git_config_string(&git_commit_encoding, var, value);`
	`571`	`+ FREE_AND_NULL(the_repository->commit_encoding);`
	`572`	`+ return git_config_string(&the_repository->commit_encoding, var, value);`
`574`	`573`	`}`
`575`		`-`
`576`	`574`	`if (!strcmp(var, "i18n.logoutputencoding")) {`
`577`		`- FREE_AND_NULL(git_log_output_encoding);`
`578`		`- return git_config_string(&git_log_output_encoding, var, value);`
	`575`	`+ FREE_AND_NULL(the_repository->log_output_encoding);`
	`576`	`+ return git_config_string(&the_repository->log_output_encoding, var, value);`
`579`	`577`	`}`
`580`	`578`
`581`		`- /* Add other config variables here and to Documentation/config.adoc. */`
`582`	`579`	`return 0;`
`583`	`580`	`}`
`584`	`581`