builtin/diagnose.c: add '--mode' option

Create '--mode=<mode>' option in 'git diagnose' to allow users to optionally
select non-default diagnostic information to include in the output archive.
Additionally, document the currently-available modes, emphasizing the
importance of not sharing a '--mode=all' archive publicly due to the
presence of sensitive information.

Note that the option parsing callback - 'option_parse_diagnose()' - is added
to 'diagnose.c' rather than 'builtin/diagnose.c' so that it may be reused in
future callers configuring a diagnostics archive.

Helped-by: Derrick Stolee <derrickstolee@github.com>
Signed-off-by: Victoria Dye <vdye@github.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 84 insertions, 4 deletions

diff --git a/Documentation/git-diagnose.txt b/Documentation/git-diagnose.txt
index ce07dd0725..3ec8cc7ad7 100644
--- a/Documentation/git-diagnose.txt
+++ b/Documentation/git-diagnose.txt
@@ -9,6 +9,7 @@ SYNOPSIS
 --------
 [verse]
 'git diagnose' [(-o | --output-directory) <path>] [(-s | --suffix) <format>]
+	       [--mode=<mode>]
 
 DESCRIPTION
 -----------
@@ -17,7 +18,7 @@ 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:
+By default, the following information is captured in the archive:
 
   * 'git version --build-options'
   * The path to the repository root
@@ -27,6 +28,9 @@ The following information is captured in the archive:
   * The total count of loose objects, as well as counts broken down by
     `.git/objects` subdirectory
 
+Additional information can be collected by selecting a different diagnostic mode
+using the `--mode` option.
+
 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.
@@ -45,6 +49,17 @@ OPTIONS
 	form of a strftime(3) format string; the current local time will be
 	used.
 
+--mode=(stats|all)::
+	Specify the type of diagnostics that should be collected. The default behavior
+	of 'git diagnose' is equivalent to `--mode=stats`.
++
+The `--mode=all` option collects everything included in `--mode=stats`, as well
+as copies of `.git`, `.git/hooks`, `.git/info`, `.git/logs`, and
+`.git/objects/info` directories. This additional information may be sensitive,
+as it can be used to reconstruct the full contents of the diagnosed repository.
+Users should exercise caution when sharing an archive generated with
+`--mode=all`.
+
 GIT
 ---
 Part of the linkgit:git[1] suite
diff --git a/builtin/diagnose.c b/builtin/diagnose.c
index 832493bba6..cd260c2015 100644
--- a/builtin/diagnose.c
+++ b/builtin/diagnose.c
@@ -3,7 +3,7 @@
 #include "diagnose.h"
 
 static const char * const diagnose_usage[] = {
-	N_("git diagnose [-o|--output-directory <path>] [-s|--suffix <format>]"),
+	N_("git diagnose [-o|--output-directory <path>] [-s|--suffix <format>] [--mode=<mode>]"),
 	NULL
 };
 
@@ -12,6 +12,7 @@ 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;
+	enum diagnose_mode mode = DIAGNOSE_STATS;
 	char *option_output = NULL;
 	char *option_suffix = "%Y-%m-%d-%H%M";
 	char *prefixed_filename;
@@ -21,6 +22,9 @@ int cmd_diagnose(int argc, const char **argv, const char *prefix)
 			   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_CALLBACK_F(0, "mode", &mode, N_("(stats|all)"),
+			       N_("specify the content of the diagnostic archive"),
+			       PARSE_OPT_NONEG, option_parse_diagnose),
 		OPT_END()
 	};
 
@@ -47,7 +51,7 @@ int cmd_diagnose(int argc, const char **argv, const char *prefix)
 	}
 
 	/* Prepare diagnostics */
-	if (create_diagnostics_archive(&zip_path, DIAGNOSE_STATS))
+	if (create_diagnostics_archive(&zip_path, mode))
 		die_errno(_("unable to create diagnostics archive %s"),
 			  zip_path.buf);
 
diff --git a/diagnose.c b/diagnose.c
index 9270056db2..beb0a8741b 100644
--- a/diagnose.c
+++ b/diagnose.c
@@ -13,6 +13,36 @@ struct archive_dir {
 	int recursive;
 };
 
+struct diagnose_option {
+	enum diagnose_mode mode;
+	const char *option_name;
+};
+
+static struct diagnose_option diagnose_options[] = {
+	{ DIAGNOSE_STATS, "stats" },
+	{ DIAGNOSE_ALL, "all" },
+};
+
+int option_parse_diagnose(const struct option *opt, const char *arg, int unset)
+{
+	int i;
+	enum diagnose_mode *diagnose = opt->value;
+
+	if (!arg) {
+		*diagnose = unset ? DIAGNOSE_NONE : DIAGNOSE_STATS;
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(diagnose_options); i++) {
+		if (!strcmp(arg, diagnose_options[i].option_name)) {
+			*diagnose = diagnose_options[i].mode;
+			return 0;
+		}
+	}
+
+	return error(_("invalid --%s value '%s'"), opt->long_name, arg);
+}
+
 static void dir_file_stats_objects(const char *full_path, size_t full_path_len,
 				   const char *file_name, void *data)
 {
diff --git a/diagnose.h b/diagnose.h
index 998775857a..7a4951a786 100644
--- a/diagnose.h
+++ b/diagnose.h
@@ -2,6 +2,7 @@
 #define DIAGNOSE_H
 
 #include "strbuf.h"
+#include "parse-options.h"
 
 enum diagnose_mode {
 	DIAGNOSE_NONE,
@@ -9,6 +10,8 @@ enum diagnose_mode {
 	DIAGNOSE_ALL
 };
 
+int option_parse_diagnose(const struct option *opt, const char *arg, int unset);
+
 int create_diagnostics_archive(struct strbuf *zip_path, enum diagnose_mode mode);
 
 #endif /* DIAGNOSE_H */
diff --git a/t/t0092-diagnose.sh b/t/t0092-diagnose.sh
index b6923726fd..fca9b58489 100755
--- a/t/t0092-diagnose.sh
+++ b/t/t0092-diagnose.sh
@@ -26,7 +26,35 @@ test_expect_success UNZIP 'creates diagnostics zip archive' '
 
 	# Should not include .git directory contents by default
 	! "$GIT_UNZIP" -l "$zip_path" | grep ".git/"
-	grep "^Total: [0-9][0-9]*" out
+'
+
+test_expect_success UNZIP '--mode=stats excludes .git dir contents' '
+	test_when_finished rm -rf report &&
+
+	git diagnose -o report -s test --mode=stats >out &&
+
+	# Includes pack quantity/size info
+	"$GIT_UNZIP" -p "$zip_path" packs-local.txt >out &&
+	grep ".git/objects" out &&
+
+	# Does not include .git directory contents
+	! "$GIT_UNZIP" -l "$zip_path" | grep ".git/"
+'
+
+test_expect_success UNZIP '--mode=all includes .git dir contents' '
+	test_when_finished rm -rf report &&
+
+	git diagnose -o report -s test --mode=all >out &&
+
+	# Includes pack quantity/size info
+	"$GIT_UNZIP" -p "$zip_path" packs-local.txt >out &&
+	grep ".git/objects" out &&
+
+	# Includes .git directory contents
+	"$GIT_UNZIP" -l "$zip_path" | grep ".git/" &&
+
+	"$GIT_UNZIP" -p "$zip_path" .git/HEAD >out &&
+	test_file_not_empty out
 '
 
 test_done