[4/7] for-each-repo: run subcommands on configured repos

Commit Message

Linus Arver via GitGitGadget Aug. 19, 2020, 5:16 p.m. UTC

From: Derrick Stolee <[e-mail]>

It can be helpful to store a list of repositories in global or system
config and then iterate Git commands on that list. Create a new builtin
that makes this process simple for experts. We will use this builtin to
run scheduled maintenance on all configured repositories in a future
change.

The test is very simple, but does highlight that the "--" argument is
optional.

Signed-off-by: Derrick Stolee <[e-mail]>
---
 .gitignore                          |  1 +
 Documentation/git-for-each-repo.txt | 45 ++++++++++++++++++++++
 Makefile                            |  1 +
 builtin.h                           |  1 +
 builtin/for-each-repo.c             | 58 +++++++++++++++++++++++++++++
 git.c                               |  1 +
 t/t0068-for-each-repo.sh            | 30 +++++++++++++++
 7 files changed, 137 insertions(+)
 create mode 100644 Documentation/git-for-each-repo.txt
 create mode 100644 builtin/for-each-repo.c
 create mode 100755 t/t0068-for-each-repo.sh

Comments

Đoàn Trần Công Danh Aug. 20, 2020, 3 p.m. UTC | #1

On 2020-08-19 17:16:45+0000, Derrick Stolee via GitGitGadget <[e-mail]> wrote:
> From: Derrick Stolee <[e-mail]>
> 
> It can be helpful to store a list of repositories in global or system
> config and then iterate Git commands on that list. Create a new builtin
> that makes this process simple for experts. We will use this builtin to
> run scheduled maintenance on all configured repositories in a future
> change.

Nice, I like this new command.

However, I'm not sure if we could declare this command as plumbing or
porcelain command.

I guess this command is meant more for scripting purpose, hence, it
should be plumbing, thus we need to define clear protocol for this
command, e.g, where it will redirect other command output, error to,
where for-each-repo write its own output/error.

Also, I think it would be nice to declare this is experimental for now.
Like we declared git-switch and git-restore.

Patch

diff --git a/.gitignore b/.gitignore
index a5808fa30d..5eb2a2be71 100644
--- a/.gitignore
+++ b/.gitignore
@@ -67,6 +67,7 @@ 
 /git-filter-branch
 /git-fmt-merge-msg
 /git-for-each-ref
+/git-for-each-repo
 /git-format-patch
 /git-fsck
 /git-fsck-objects
diff --git a/Documentation/git-for-each-repo.txt b/Documentation/git-for-each-repo.txt
new file mode 100644
index 0000000000..83b06db410
--- /dev/null
+++ b/Documentation/git-for-each-repo.txt
@@ -0,0 +1,45 @@ 
+git-for-each-repo(1)
+====================
+
+NAME
+----
+git-for-each-repo - Run a Git command on a list of repositories
+
+
+SYNOPSIS
+--------
+[verse]
+'git for-each-repo' --config=<config> [--] <arguments>
+
+
+DESCRIPTION
+-----------
+Run a Git commands on a list of repositories. The arguments after the
+known options or `--` indicator are used as the arguments for the Git
+command.
+
+For example, we could run maintenance on each of a list of repositories
+stored in a `maintenance.repo` config variable using
+
+-------------
+git for-each-repo --config=maintenance.repo maintenance run
+-------------
+
+This will run `git -C <repo> maintenance run` for each value `<repo>`
+in the multi-valued config variable `maintenance.repo`.
+
+
+OPTIONS
+-------
+--config=<config>::
+	Use the given config variable as a multi-valued list storing
+	absolute path names. Iterate on that list of paths to run
+	the given arguments.
++
+These config values are loaded from system, global, and local Git config,
+as available. If `git for-each-repo` is run in a directory that is not a
+Git repository, then only the system and global config is used.
+
+GIT
+---
+Part of the linkgit:git[1] suite
diff --git a/Makefile b/Makefile
index 65f8cfb236..7c588ff036 100644
--- a/Makefile
+++ b/Makefile
@@ -1071,6 +1071,7 @@  BUILTIN_OBJS += builtin/fetch-pack.o
 BUILTIN_OBJS += builtin/fetch.o
 BUILTIN_OBJS += builtin/fmt-merge-msg.o
 BUILTIN_OBJS += builtin/for-each-ref.o
+BUILTIN_OBJS += builtin/for-each-repo.o
 BUILTIN_OBJS += builtin/fsck.o
 BUILTIN_OBJS += builtin/gc.o
 BUILTIN_OBJS += builtin/get-tar-commit-id.o
diff --git a/builtin.h b/builtin.h
index 17c1c0ce49..ff7c6e5aa9 100644
--- a/builtin.h
+++ b/builtin.h
@@ -150,6 +150,7 @@  int cmd_fetch(int argc, const char **argv, const char *prefix);
 int cmd_fetch_pack(int argc, const char **argv, const char *prefix);
 int cmd_fmt_merge_msg(int argc, const char **argv, const char *prefix);
 int cmd_for_each_ref(int argc, const char **argv, const char *prefix);
+int cmd_for_each_repo(int argc, const char **argv, const char *prefix);
 int cmd_format_patch(int argc, const char **argv, const char *prefix);
 int cmd_fsck(int argc, const char **argv, const char *prefix);
 int cmd_gc(int argc, const char **argv, const char *prefix);
diff --git a/builtin/for-each-repo.c b/builtin/for-each-repo.c
new file mode 100644
index 0000000000..5bba623ff1
--- /dev/null
+++ b/builtin/for-each-repo.c
@@ -0,0 +1,58 @@ 
+#include "cache.h"
+#include "config.h"
+#include "builtin.h"
+#include "parse-options.h"
+#include "run-command.h"
+#include "string-list.h"
+
+static const char * const for_each_repo_usage[] = {
+	N_("git for-each-repo --config=<config> <command-args>"),
+	NULL
+};
+
+static int run_command_on_repo(const char *path,
+			       void *cbdata)
+{
+	int i;
+	struct child_process child = CHILD_PROCESS_INIT;
+	struct strvec *args = (struct strvec *)cbdata;
+
+	child.git_cmd = 1;
+	strvec_pushl(&child.args, "-C", path, NULL);
+
+	for (i = 0; i < args->nr; i++)
+		strvec_push(&child.args, args->v[i]);
+
+	return run_command(&child);
+}
+
+int cmd_for_each_repo(int argc, const char **argv, const char *prefix)
+{
+	static const char *config_key = NULL;
+	int i, result = 0;
+	const struct string_list *values;
+	struct strvec args = STRVEC_INIT;
+
+	const struct option options[] = {
+		OPT_STRING(0, "config", &config_key, N_("config"),
+			   N_("config key storing a list of repository paths")),
+		OPT_END()
+	};
+
+	argc = parse_options(argc, argv, prefix, options, for_each_repo_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (!config_key)
+		die(_("missing --config=<config>"));
+
+	for (i = 0; i < argc; i++)
+		strvec_push(&args, argv[i]);
+
+	values = repo_config_get_value_multi(the_repository,
+					     config_key);
+
+	for (i = 0; !result && i < values->nr; i++)
+		result = run_command_on_repo(values->items[i].string, &args);
+
+	return result;
+}
diff --git a/git.c b/git.c
index 24f250d29a..1cab64b5d1 100644
--- a/git.c
+++ b/git.c
@@ -511,6 +511,7 @@  static struct cmd_struct commands[] = {
 	{ "fetch-pack", cmd_fetch_pack, RUN_SETUP | NO_PARSEOPT },
 	{ "fmt-merge-msg", cmd_fmt_merge_msg, RUN_SETUP },
 	{ "for-each-ref", cmd_for_each_ref, RUN_SETUP },
+	{ "for-each-repo", cmd_for_each_repo, RUN_SETUP_GENTLY },
 	{ "format-patch", cmd_format_patch, RUN_SETUP },
 	{ "fsck", cmd_fsck, RUN_SETUP },
 	{ "fsck-objects", cmd_fsck, RUN_SETUP },
diff --git a/t/t0068-for-each-repo.sh b/t/t0068-for-each-repo.sh
new file mode 100755
index 0000000000..136b4ec839
--- /dev/null
+++ b/t/t0068-for-each-repo.sh
@@ -0,0 +1,30 @@ 
+#!/bin/sh
+
+test_description='git for-each-repo builtin'
+
+. ./test-lib.sh
+
+test_expect_success 'run based on configured value' '
+	git init one &&
+	git init two &&
+	git init three &&
+	git -C two commit --allow-empty -m "DID NOT RUN" &&
+	git config run.key "$TRASH_DIRECTORY/one" &&
+	git config --add run.key "$TRASH_DIRECTORY/three" &&
+	git for-each-repo --config=run.key commit --allow-empty -m "ran" &&
+	git -C one log -1 --pretty=format:%s >message &&
+	grep ran message &&
+	git -C two log -1 --pretty=format:%s >message &&
+	! grep ran message &&
+	git -C three log -1 --pretty=format:%s >message &&
+	grep ran message &&
+	git for-each-repo --config=run.key -- commit --allow-empty -m "ran again" &&
+	git -C one log -1 --pretty=format:%s >message &&
+	grep again message &&
+	git -C two log -1 --pretty=format:%s >message &&
+	! grep again message &&
+	git -C three log -1 --pretty=format:%s >message &&
+	grep again message
+'
+
+test_done