diff mbox series

[4/5] setup: make object format configurable via config

Message ID e1cdaf0f0edec578d1cb9358fd4c6f6b39aaad3a.1723708417.git.ps@pks.im (mailing list archive)
State Superseded
Headers show
Series Introduce configs for default repo format | expand

Commit Message

Patrick Steinhardt Aug. 15, 2024, 8 a.m. UTC
The object format for repositories can either be configured explicitly
by passing the `--object-format=` option to git-init(1) or git-clone(1),
or globally by setting the `GIT_DEFAULT_HASH` environment variable.
While the former makes sense, setting random environment variables is
not really a good user experience in case someone decides to only use
SHA256 repositories.

It is only natural to expect for a user that things like this can also
be configured via their config. As such, introduce a new config
"init.defaultObjectFormat", similar to "init.defaultBranch", that allows
the user to configure the default object format when creating new repos.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 Documentation/config/init.txt |  5 ++++
 setup.c                       | 40 ++++++++++++++++++++++++++++
 t/t0001-init.sh               | 50 +++++++++++++++++++++++++++++++++++
 3 files changed, 95 insertions(+)

Comments

Justin Tobler Aug. 15, 2024, 10:17 p.m. UTC | #1
On 24/08/15 10:00AM, Patrick Steinhardt wrote:
> The object format for repositories can either be configured explicitly
> by passing the `--object-format=` option to git-init(1) or git-clone(1),
> or globally by setting the `GIT_DEFAULT_HASH` environment variable.
> While the former makes sense, setting random environment variables is
> not really a good user experience in case someone decides to only use
> SHA256 repositories.
> 
> It is only natural to expect for a user that things like this can also
> be configured via their config. As such, introduce a new config
> "init.defaultObjectFormat", similar to "init.defaultBranch", that allows
> the user to configure the default object format when creating new repos.

Adding an option to the Git config to allow the default hash algorithm
and reference format to be configured makes sense. In my opinion it is
much more ergonomic.

> 
> Signed-off-by: Patrick Steinhardt <ps@pks.im>
> ---
>  Documentation/config/init.txt |  5 ++++
>  setup.c                       | 40 ++++++++++++++++++++++++++++
>  t/t0001-init.sh               | 50 +++++++++++++++++++++++++++++++++++
>  3 files changed, 95 insertions(+)
> 
> diff --git a/Documentation/config/init.txt b/Documentation/config/init.txt
> index af03acdbcb..d6f8b6e61b 100644
> --- a/Documentation/config/init.txt
> +++ b/Documentation/config/init.txt
> @@ -8,3 +8,8 @@ endif::[]
>  `init.defaultBranch`::
>  	Allows overriding the default branch name e.g. when initializing
>  	a new repository.
> +`init.defaultObjectFormat`::
> +	Allows overriding the default object format for new repositories. See
> +	`--object-format=` in linkgit:git-init[1]. Both the command line option
> +	and the `GIT_DEFAULT_HASH` environment variable take precedence over
> +	this config.
> diff --git a/setup.c b/setup.c
> index 5dfcdc99dd..770ad1393f 100644
> --- a/setup.c
> +++ b/setup.c
> @@ -2284,11 +2284,49 @@ static void separate_git_dir(const char *git_dir, const char *git_link)
>  	write_file(git_link, "gitdir: %s", git_dir);
>  }
>  
> +struct default_format_config {
> +	int hash;
> +};
> +
> +static int read_default_format_config(const char *key, const char *value,
> +				      const struct config_context *ctx UNUSED,
> +				      void *payload)
> +{
> +	struct default_format_config *cfg = payload;
> +	char *str = NULL;
> +	int ret;
> +
> +	if (!strcmp(key, "init.defaultobjectformat")) {
> +		ret = git_config_string(&str, key, value);
> +		if (ret)
> +			goto out;
> +		cfg->hash = hash_algo_by_name(str);
> +		if (cfg->hash == GIT_HASH_UNKNOWN)
> +			warning(_("unknown hash algorithm '%s'"), str);
> +		goto out;
> +	}
> +
> +	ret = 0;
> +out:
> +	free(str);
> +	return ret;
> +}
> +
>  static void repository_format_configure(struct repository_format *repo_fmt,
>  					int hash, enum ref_storage_format ref_format)
>  {
> +	struct default_format_config cfg = {
> +		.hash = GIT_HASH_UNKNOWN,
> +	};
> +	struct config_options opts = {
> +		.respect_includes = 1,
> +		.ignore_repo = 1,
> +		.ignore_worktree = 1,
> +	};

As these format configurations only make sense to be included in the
global config, the search radius is limited accordingly. 

>  	const char *env;
>  
> +	config_with_options(read_default_format_config, &cfg, NULL, NULL, &opts);
> +
>  	/*
>  	 * If we already have an initialized repo, don't allow the user to
>  	 * specify a different algorithm, as that could cause corruption.
> @@ -2304,6 +2342,8 @@ static void repository_format_configure(struct repository_format *repo_fmt,
>  		if (env_algo == GIT_HASH_UNKNOWN)
>  			die(_("unknown hash algorithm '%s'"), env);
>  		repo_fmt->hash_algo = env_algo;
> +	} else if (cfg.hash != GIT_HASH_UNKNOWN) {
> +		repo_fmt->hash_algo = cfg.hash;

The environment variable takes higher precedence than the Git config.
Makes sense to allow the env to override Git cofiguration.

The way this patch is setup should make it easy to extend for a default
reference format config. Very nice.

-Justin
diff mbox series

Patch

diff --git a/Documentation/config/init.txt b/Documentation/config/init.txt
index af03acdbcb..d6f8b6e61b 100644
--- a/Documentation/config/init.txt
+++ b/Documentation/config/init.txt
@@ -8,3 +8,8 @@  endif::[]
 `init.defaultBranch`::
 	Allows overriding the default branch name e.g. when initializing
 	a new repository.
+`init.defaultObjectFormat`::
+	Allows overriding the default object format for new repositories. See
+	`--object-format=` in linkgit:git-init[1]. Both the command line option
+	and the `GIT_DEFAULT_HASH` environment variable take precedence over
+	this config.
diff --git a/setup.c b/setup.c
index 5dfcdc99dd..770ad1393f 100644
--- a/setup.c
+++ b/setup.c
@@ -2284,11 +2284,49 @@  static void separate_git_dir(const char *git_dir, const char *git_link)
 	write_file(git_link, "gitdir: %s", git_dir);
 }
 
+struct default_format_config {
+	int hash;
+};
+
+static int read_default_format_config(const char *key, const char *value,
+				      const struct config_context *ctx UNUSED,
+				      void *payload)
+{
+	struct default_format_config *cfg = payload;
+	char *str = NULL;
+	int ret;
+
+	if (!strcmp(key, "init.defaultobjectformat")) {
+		ret = git_config_string(&str, key, value);
+		if (ret)
+			goto out;
+		cfg->hash = hash_algo_by_name(str);
+		if (cfg->hash == GIT_HASH_UNKNOWN)
+			warning(_("unknown hash algorithm '%s'"), str);
+		goto out;
+	}
+
+	ret = 0;
+out:
+	free(str);
+	return ret;
+}
+
 static void repository_format_configure(struct repository_format *repo_fmt,
 					int hash, enum ref_storage_format ref_format)
 {
+	struct default_format_config cfg = {
+		.hash = GIT_HASH_UNKNOWN,
+	};
+	struct config_options opts = {
+		.respect_includes = 1,
+		.ignore_repo = 1,
+		.ignore_worktree = 1,
+	};
 	const char *env;
 
+	config_with_options(read_default_format_config, &cfg, NULL, NULL, &opts);
+
 	/*
 	 * If we already have an initialized repo, don't allow the user to
 	 * specify a different algorithm, as that could cause corruption.
@@ -2304,6 +2342,8 @@  static void repository_format_configure(struct repository_format *repo_fmt,
 		if (env_algo == GIT_HASH_UNKNOWN)
 			die(_("unknown hash algorithm '%s'"), env);
 		repo_fmt->hash_algo = env_algo;
+	} else if (cfg.hash != GIT_HASH_UNKNOWN) {
+		repo_fmt->hash_algo = cfg.hash;
 	}
 	repo_set_hash_algo(the_repository, repo_fmt->hash_algo);
 
diff --git a/t/t0001-init.sh b/t/t0001-init.sh
index 795408e16c..cd34710f32 100755
--- a/t/t0001-init.sh
+++ b/t/t0001-init.sh
@@ -523,6 +523,56 @@  test_expect_success 'init honors --object-format' '
 	test_cmp expected actual
 '
 
+test_expect_success 'init honors init.defaultObjectFormat' '
+	test_when_finished "rm -rf sha1 sha256" &&
+
+	test_config_global init.defaultObjectFormat sha1 &&
+	(
+		sane_unset GIT_DEFAULT_HASH &&
+		git init sha1 &&
+		git -C sha1 rev-parse --show-object-format >actual &&
+		echo sha1 >expected &&
+		test_cmp expected actual
+	) &&
+
+	test_config_global init.defaultObjectFormat sha256 &&
+	(
+		sane_unset GIT_DEFAULT_HASH &&
+		git init sha256 &&
+		git -C sha256 rev-parse --show-object-format >actual &&
+		echo sha256 >expected &&
+		test_cmp expected actual
+	)
+'
+
+test_expect_success 'init warns about invalid init.defaultObjectFormat' '
+	test_when_finished "rm -rf repo" &&
+	test_config_global init.defaultObjectFormat garbage &&
+
+	echo "warning: unknown hash algorithm ${SQ}garbage${SQ}" >expect &&
+	git init repo 2>err &&
+	test_cmp expect err &&
+
+	git -C repo rev-parse --show-object-format >actual &&
+	echo $GIT_DEFAULT_HASH >expected &&
+	test_cmp expected actual
+'
+
+test_expect_success '--object-format overrides GIT_DEFAULT_HASH' '
+	test_when_finished "rm -rf repo" &&
+	GIT_DEFAULT_HASH=sha1 git init --object-format=sha256 repo &&
+	git -C repo rev-parse --show-object-format >actual &&
+	echo sha256 >expected
+'
+
+test_expect_success 'GIT_DEFAULT_HASH overrides init.defaultObjectFormat' '
+	test_when_finished "rm -rf repo" &&
+	test_config_global init.defaultObjectFormat sha1 &&
+	GIT_DEFAULT_HASH=sha256 git init repo &&
+	git -C repo rev-parse --show-object-format >actual &&
+	echo sha256 >expected
+'
+
 test_expect_success 'extensions.objectFormat is not allowed with repo version 0' '
 	test_when_finished "rm -rf explicit-v0" &&
 	git init --object-format=sha256 explicit-v0 &&