builtin/diagnose.c: create 'git diagnose' builtin

Create a 'git diagnose' builtin to generate a standalone zip archive of
repository diagnostics.

The "diagnose" functionality was originally implemented for Scalar in
aa5c79a (scalar: implement `scalar diagnose`, 2022-05-28). However, the
diagnostics gathered are not specific to Scalar-cloned repositories and
can be useful when diagnosing issues in any Git repository.

Helped-by: Ævar Arnfjörð Bjarmason <[email protected]>
Helped-by: Derrick Stolee <[email protected]>
Signed-off-by: Victoria Dye <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: vdye

.gitignore

@@ -53,6 +53,7 @@
 /git-cvsimport
 /git-cvsserver
 /git-daemon
+/git-diagnose
 /git-diff
 /git-diff-files
 /git-diff-index

Documentation/git-diagnose.txt

@@ -0,0 +1,50 @@
+git-diagnose(1)
+================
+
+NAME
+----
+git-diagnose - Generate a zip archive of diagnostic information
+
+SYNOPSIS
+--------
+[verse]
+'git diagnose' [(-o | --output-directory) <path>] [(-s | --suffix) <format>]
+
+DESCRIPTION
+-----------
+Collects detailed information about the user's machine, Git client, and
+repository state and packages that information into a zip archive. The
+generated archive can then, for example, be shared with the Git mailing list to
+help debug an issue or serve as a reference for independent debugging.
+
+The following information is captured in the archive:
+
+  * 'git version --build-options'
+  * The path to the repository root
+  * The available disk space on the filesystem
+  * The name and size of each packfile, including those in alternate object
+    stores
+  * The total count of loose objects, as well as counts broken down by
+    `.git/objects` subdirectory
+
+This tool differs from linkgit:git-bugreport[1] in that it collects much more
+detailed information with a greater focus on reporting the size and data shape
+of repository contents.
+
+OPTIONS
+-------
+-o <path>::
+--output-directory <path>::
+	Place the resulting diagnostics archive in `<path>` instead of the
+	current directory.
+
+-s <format>::
+--suffix <format>::
+	Specify an alternate suffix for the diagnostics archive name, to create
+	a file named 'git-diagnostics-<formatted suffix>'. This should take the
+	form of a strftime(3) format string; the current local time will be
+	used.
+
+GIT
+---
+Part of the linkgit:git[1] suite

Makefile

@@ -1154,6 +1154,7 @@ BUILTIN_OBJS += builtin/credential-cache.o
 BUILTIN_OBJS += builtin/credential-store.o
 BUILTIN_OBJS += builtin/credential.o
 BUILTIN_OBJS += builtin/describe.o
+BUILTIN_OBJS += builtin/diagnose.o
 BUILTIN_OBJS += builtin/diff-files.o
 BUILTIN_OBJS += builtin/diff-index.o
 BUILTIN_OBJS += builtin/diff-tree.o

builtin.h

@@ -144,6 +144,7 @@ int cmd_credential_cache(int argc, const char **argv, const char *prefix);
 int cmd_credential_cache_daemon(int argc, const char **argv, const char *prefix);
 int cmd_credential_store(int argc, const char **argv, const char *prefix);
 int cmd_describe(int argc, const char **argv, const char *prefix);
+int cmd_diagnose(int argc, const char **argv, const char *prefix);
 int cmd_diff_files(int argc, const char **argv, const char *prefix);
 int cmd_diff_index(int argc, const char **argv, const char *prefix);
 int cmd_diff(int argc, const char **argv, const char *prefix);

builtin/diagnose.c

@@ -0,0 +1,57 @@
+#include "builtin.h"
+#include "parse-options.h"
+#include "diagnose.h"
+
+static const char * const diagnose_usage[] = {
+	N_("git diagnose [-o|--output-directory <path>] [-s|--suffix <format>]"),
+	NULL
+};
+
+int cmd_diagnose(int argc, const char **argv, const char *prefix)
+{
+	struct strbuf zip_path = STRBUF_INIT;
+	time_t now = time(NULL);
+	struct tm tm;
+	char *option_output = NULL;
+	char *option_suffix = "%Y-%m-%d-%H%M";
+	char *prefixed_filename;
+
+	const struct option diagnose_options[] = {
+		OPT_STRING('o', "output-directory", &option_output, N_("path"),
+			   N_("specify a destination for the diagnostics archive")),
+		OPT_STRING('s', "suffix", &option_suffix, N_("format"),
+			   N_("specify a strftime format suffix for the filename")),
+		OPT_END()
+	};
+
+	argc = parse_options(argc, argv, prefix, diagnose_options,
+			     diagnose_usage, 0);
+
+	/* Prepare the path to put the result */
+	prefixed_filename = prefix_filename(prefix,
+					    option_output ? option_output : "");
+	strbuf_addstr(&zip_path, prefixed_filename);
+	strbuf_complete(&zip_path, '/');
+
+	strbuf_addstr(&zip_path, "git-diagnostics-");
+	strbuf_addftime(&zip_path, option_suffix, localtime_r(&now, &tm), 0, 0);
+	strbuf_addstr(&zip_path, ".zip");
+
+	switch (safe_create_leading_directories(zip_path.buf)) {
+	case SCLD_OK:
+	case SCLD_EXISTS:
+		break;
+	default:
+		die_errno(_("could not create leading directories for '%s'"),
+			  zip_path.buf);
+	}
+
+	/* Prepare diagnostics */
+	if (create_diagnostics_archive(&zip_path, DIAGNOSE_STATS))
+		die_errno(_("unable to create diagnostics archive %s"),
+			  zip_path.buf);
+
+	free(prefixed_filename);
+	strbuf_release(&zip_path);
+	return 0;
+}

git.c

@@ -522,6 +522,7 @@ static struct cmd_struct commands[] = {
 	{ "credential-cache--daemon", cmd_credential_cache_daemon },
 	{ "credential-store", cmd_credential_store },
 	{ "describe", cmd_describe, RUN_SETUP },
+	{ "diagnose", cmd_diagnose, RUN_SETUP_GENTLY },
 	{ "diff", cmd_diff, NO_PARSEOPT },
 	{ "diff-files", cmd_diff_files, RUN_SETUP | NEED_WORK_TREE | NO_PARSEOPT },
 	{ "diff-index", cmd_diff_index, RUN_SETUP | NO_PARSEOPT },

t/t0092-diagnose.sh

@@ -0,0 +1,32 @@
+#!/bin/sh
+
+test_description='git diagnose'
+
+TEST_PASSES_SANITIZE_LEAK=true
+. ./test-lib.sh
+
+test_expect_success UNZIP 'creates diagnostics zip archive' '
+	test_when_finished rm -rf report &&
+
+	git diagnose -o report -s test >out &&
+	grep "Available space" out &&
+
+	zip_path=report/git-diagnostics-test.zip &&
+	test_path_is_file "$zip_path" &&
+
+	# Check zipped archive content
+	"$GIT_UNZIP" -p "$zip_path" diagnostics.log >out &&
+	test_file_not_empty out &&
+
+	"$GIT_UNZIP" -p "$zip_path" packs-local.txt >out &&
+	grep ".git/objects" out &&
+
+	"$GIT_UNZIP" -p "$zip_path" objects-local.txt >out &&
+	grep "^Total: [0-9][0-9]*" out &&
+
+	# Should not include .git directory contents by default
+	! "$GIT_UNZIP" -l "$zip_path" | grep ".git/"
+	grep "^Total: [0-9][0-9]*" out
+'
+
+test_done