Merge branch 'ua/os-version-capability' into jch

The value of "uname -s" is by default sent over the wire as a new
capability, with an opt-out for privacy-concious folks.

* ua/os-version-capability:
  connect: advertise OS version
  t5701: add setup test to remove side-effect dependency
  version: extend get_uname_info() to hide system details
  version: refactor get_uname_info()
  version: refactor redact_non_printables()
  version: replace manual ASCII checks with isprint() for clarity

Author: gitster

Documentation/config/transfer.adoc

@@ -125,3 +125,10 @@ transfer.bundleURI::
 transfer.advertiseObjectInfo::
 	When `true`, the `object-info` capability is advertised by
 	servers. Defaults to false.
+
+transfer.advertiseOSVersion::
+	When set to `true` on the server, the server will advertise its
+	`os-version` capability to the client. On the client side, if set
+	to `true`, it will advertise its `os-version` capability to the
+	server only if the server also advertises its `os-version` capability.
+	Defaults to true.

Documentation/gitprotocol-v2.adoc

@@ -190,6 +190,23 @@ printable ASCII characters except space (i.e., the byte range 32 < x <
 and debugging purposes, and MUST NOT be used to programmatically assume
 the presence or absence of particular features.
 
+os-version
+~~~~~~~~~~
+
+In the same way as the `agent` capability above, the server can
+advertise the `os-version` capability to notify the client the
+kind of operating system it is running on. The client may optionally
+send its own `os-version` capability, to notify the server the kind
+of operating system it is also running on in its request to the server
+(but it MUST NOT do so if the server did not advertise the os-version
+capability). The value of this capability may consist of ASCII printable
+characters(from 33 to 126 inclusive) and are typically made from the
+result of `uname -s`(OS name e.g Linux). The os-version capability can
+be disabled entirely by setting the `transfer.advertiseOSVersion` config
+option to `false`. The `os-version` strings are purely informative for
+statistics and debugging purposes, and MUST NOT be used to
+programmatically assume the presence or absence of particular features.
+
 ls-refs
 ~~~~~~~
 

builtin/bugreport.c

@@ -12,10 +12,10 @@
 #include "diagnose.h"
 #include "object-file.h"
 #include "setup.h"
+#include "version.h"
 
 static void get_system_info(struct strbuf *sys_info)
 {
-	struct utsname uname_info;
 	char *shell = NULL;
 
 	/* get git version from native cmd */
@@ -24,16 +24,7 @@ static void get_system_info(struct strbuf *sys_info)
 
 	/* system call for other version info */
 	strbuf_addstr(sys_info, "uname: ");
-	if (uname(&uname_info))
-		strbuf_addf(sys_info, _("uname() failed with error '%s' (%d)\n"),
-			    strerror(errno),
-			    errno);
-	else
-		strbuf_addf(sys_info, "%s %s %s %s\n",
-			    uname_info.sysname,
-			    uname_info.release,
-			    uname_info.version,
-			    uname_info.machine);
+	get_uname_info(sys_info, 1);
 
 	strbuf_addstr(sys_info, _("compiler info: "));
 	get_compiler_info(sys_info);

connect.c

@@ -491,6 +491,9 @@ static void send_capabilities(int fd_out, struct packet_reader *reader)
 	if (server_supports_v2("agent"))
 		packet_write_fmt(fd_out, "agent=%s", git_user_agent_sanitized());
 
+	if (server_supports_v2("os-version") && advertise_os_version(the_repository))
+		packet_write_fmt(fd_out, "os-version=%s", os_version_sanitized());
+
 	if (server_feature_v2("object-format", &hash_name)) {
 		int hash_algo = hash_algo_by_name(hash_name);
 		if (hash_algo == GIT_HASH_UNKNOWN)

serve.c

@@ -29,6 +29,16 @@ static int agent_advertise(struct repository *r UNUSED,
 	return 1;
 }
 
+static int os_version_advertise(struct repository *r,
+			   struct strbuf *value)
+{
+	if (!advertise_os_version(r))
+		return 0;
+	if (value)
+		strbuf_addstr(value, os_version_sanitized());
+	return 1;
+}
+
 static int object_format_advertise(struct repository *r,
 				   struct strbuf *value)
 {
@@ -121,6 +131,10 @@ static struct protocol_capability capabilities[] = {
 		.name = "agent",
 		.advertise = agent_advertise,
 	},
+	{
+		.name = "os-version",
+		.advertise = os_version_advertise,
+	},
 	{
 		.name = "ls-refs",
 		.advertise = ls_refs_advertise,

t/t5555-http-smart-common.sh

@@ -123,9 +123,17 @@ test_expect_success 'git receive-pack --advertise-refs: v1' '
 '
 
 test_expect_success 'git upload-pack --advertise-refs: v2' '
+	printf "agent=FAKE\n" >agent_and_osversion &&
+	if test_have_prereq WINDOWS
+	then
+		git config transfer.advertiseOSVersion false
+	else
+		printf "os-version=%s\n" $(uname -s | test_redact_non_printables) >>agent_and_osversion
+	fi &&
+
 	cat >expect <<-EOF &&
 	version 2
-	agent=FAKE
+	$(cat agent_and_osversion)
 	ls-refs=unborn
 	fetch=shallow wait-for-done
 	server-option

t/t5701-git-serve.sh

@@ -7,14 +7,17 @@ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
 
 . ./test-lib.sh
 
-test_expect_success 'test capability advertisement' '
+test_expect_success 'setup to generate files with expected content' '
+	printf "agent=git/%s\n" "$(git version | cut -d" " -f3)" >agent_and_osversion &&
+
 	test_oid_cache <<-EOF &&
 	wrong_algo sha1:sha256
 	wrong_algo sha256:sha1
 	EOF
+
 	cat >expect.base <<-EOF &&
 	version 2
-	agent=git/$(git version | cut -d" " -f3)
+	$(cat agent_and_osversion)
 	ls-refs=unborn
 	fetch=shallow wait-for-done
 	server-option
@@ -23,7 +26,26 @@ test_expect_success 'test capability advertisement' '
 	cat >expect.trailer <<-EOF &&
 	0000
 	EOF
-	cat expect.base expect.trailer >expect &&
+
+	if test_have_prereq WINDOWS
+	then
+		git config transfer.advertiseOSVersion false
+	else
+		printf "os-version=%s\n" $(uname -s | test_redact_non_printables) >>agent_and_osversion
+	fi &&
+
+	cat >expect_osversion.base <<-EOF
+	version 2
+	$(cat agent_and_osversion)
+	ls-refs=unborn
+	fetch=shallow wait-for-done
+	server-option
+	object-format=$(test_oid algo)
+	EOF
+'
+
+test_expect_success 'test capability advertisement' '
+	cat expect_osversion.base expect.trailer >expect &&
 
 	GIT_TEST_SIDEBAND_ALL=0 test-tool serve-v2 \
 		--advertise-capabilities >out &&
@@ -351,7 +373,7 @@ test_expect_success 'test capability advertisement with uploadpack.advertiseBund
 	cat >expect.extra <<-EOF &&
 	bundle-uri
 	EOF
-	cat expect.base \
+	cat expect_osversion.base \
 	    expect.extra \
 	    expect.trailer >expect &&
 

t/test-lib-functions.sh

@@ -2043,3 +2043,11 @@ test_trailing_hash () {
 		test-tool hexdump |
 		sed "s/ //g"
 }
+
+# Trim and replace each character with ascii code below 32 or above
+# 127 (included) using a dot '.' character.
+# Octal intervals \001-\040 and \177-\377
+# correspond to decimal intervals 1-32 and 127-255
+test_redact_non_printables () {
+    tr -d "\n\r" | tr "[\001-\040][\177-\377]" "."
+}

version.c

@@ -1,6 +1,9 @@
 #include "git-compat-util.h"
 #include "version.h"
 #include "strbuf.h"
+#include "sane-ctype.h"
+#include "gettext.h"
+#include "config.h"
 
 #ifndef GIT_VERSION_H
 # include "version-def.h"
@@ -11,6 +14,19 @@
 const char git_version_string[] = GIT_VERSION;
 const char git_built_from_commit_string[] = GIT_BUILT_FROM_COMMIT;
 
+/*
+ * Trim and replace each character with ascii code below 32 or above
+ * 127 (included) using a dot '.' character.
+ */
+static void redact_non_printables(struct strbuf *buf)
+{
+	strbuf_trim(buf);
+	for (size_t i = 0; i < buf->len; i++) {
+		if (!isprint(buf->buf[i]) || buf->buf[i] == ' ')
+			buf->buf[i] = '.';
+	}
+}
+
 const char *git_user_agent(void)
 {
 	static const char *agent = NULL;
@@ -32,13 +48,58 @@ const char *git_user_agent_sanitized(void)
 		struct strbuf buf = STRBUF_INIT;
 
 		strbuf_addstr(&buf, git_user_agent());
-		strbuf_trim(&buf);
-		for (size_t i = 0; i < buf.len; i++) {
-			if (buf.buf[i] <= 32 || buf.buf[i] >= 127)
-				buf.buf[i] = '.';
-		}
-		agent = buf.buf;
+		redact_non_printables(&buf);
+		agent = strbuf_detach(&buf, NULL);
 	}
 
 	return agent;
 }
+
+int get_uname_info(struct strbuf *buf, unsigned int full)
+{
+	struct utsname uname_info;
+
+	if (uname(&uname_info)) {
+		strbuf_addf(buf, _("uname() failed with error '%s' (%d)\n"),
+			    strerror(errno),
+			    errno);
+		return -1;
+	}
+	if (full)
+		strbuf_addf(buf, "%s %s %s %s\n",
+			    uname_info.sysname,
+			    uname_info.release,
+			    uname_info.version,
+			    uname_info.machine);
+	else
+	     strbuf_addf(buf, "%s\n", uname_info.sysname);
+	return 0;
+}
+
+const char *os_version_sanitized(void)
+{
+	static const char *os = NULL;
+
+	if (!os) {
+		struct strbuf buf = STRBUF_INIT;
+
+		get_uname_info(&buf, 0);
+		/* Sanitize the os information immediately */
+		redact_non_printables(&buf);
+		os = strbuf_detach(&buf, NULL);
+	}
+
+	return os;
+}
+
+int advertise_os_version(struct repository *r)
+{
+	static int transfer_advertise_os_version = -1;
+
+	if (transfer_advertise_os_version == -1) {
+		repo_config_get_bool(r, "transfer.advertiseosversion", &transfer_advertise_os_version);
+		/* enabled by default */
+		transfer_advertise_os_version = !!transfer_advertise_os_version;
+	}
+	return transfer_advertise_os_version;
+}

version.h

@@ -1,10 +1,32 @@
 #ifndef VERSION_H
 #define VERSION_H
 
+struct repository;
+
 extern const char git_version_string[];
 extern const char git_built_from_commit_string[];
 
 const char *git_user_agent(void);
 const char *git_user_agent_sanitized(void);
 
+/*
+  Try to get information about the system using uname(2).
+  Return -1 and put an error message into 'buf' in case of uname()
+  error. Return 0 and put uname info into 'buf' otherwise.
+*/
+int get_uname_info(struct strbuf *buf, unsigned int full);
+
+/*
+  Retrieve, sanitize and cache system information for subsequent
+  calls. Return a pointer to the sanitized system information
+  string.
+*/
+const char *os_version_sanitized(void);
+
+/*
+  Retrieve and cache whether os-version capability is enabled.
+  Return 1 if enabled, 0 if disabled.
+*/
+int advertise_os_version(struct repository *r);
+
 #endif /* VERSION_H */