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

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:
  agent: advertise OS name via agent capability
  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/gitprotocol-v2.adoc

@@ -184,9 +184,13 @@ form `agent=X`) to notify the client that the server is running version
 the `agent` capability with a value `Y` (in the form `agent=Y`) in its
 request to the server (but it MUST NOT do so if the server did not
 advertise the agent capability). The `X` and `Y` strings may contain any
-printable ASCII characters except space (i.e., the byte range 32 < x <
-127), and are typically of the form "package/version" (e.g.,
-"git/1.8.3.1"). The agent strings are purely informative for statistics
+printable ASCII characters except space (i.e., the byte range 33 <= x <=
+126), and are typically of the form "package/version-os" (e.g.,
+"git/1.8.3.1-Linux") where `os` is the operating system name (e.g.,
+"Linux"). `X` and `Y` can be configured using the GIT_USER_AGENT
+environment variable and it takes priority. The `os` is
+retrieved using the 'sysname' field of the `uname(2)` system call
+or its equivalent. The agent strings are purely informative for statistics
 and debugging purposes, and MUST NOT be used to programmatically assume
 the presence or absence of particular features.
 

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

@@ -624,7 +624,7 @@ const char *parse_feature_value(const char *feature_list, const char *feature, s
 					*offset = found + len - orig_start;
 				return value;
 			}
-			/* feature with a value (e.g., "agent=git/1.2.3") */
+			/* feature with a value (e.g., "agent=git/1.2.3-Linux") */
 			else if (*value == '=') {
 				size_t end;
 

t/t5701-git-serve.sh

@@ -7,24 +7,40 @@ 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" "$(git version | cut -d" " -f3)" >agent_capability &&
+
 	test_oid_cache <<-EOF &&
 	wrong_algo sha1:sha256
 	wrong_algo sha256:sha1
 	EOF
+
+	if test_have_prereq WINDOWS
+	then
+		printf "agent=FAKE\n" >agent_capability
+	else
+		printf -- "-%s\n" $(uname -s | test_redact_non_printables) >>agent_capability
+	fi &&
 	cat >expect.base <<-EOF &&
 	version 2
-	agent=git/$(git version | cut -d" " -f3)
+	$(cat agent_capability)
 	ls-refs=unborn
 	fetch=shallow wait-for-done
 	server-option
 	object-format=$(test_oid algo)
 	EOF
-	cat >expect.trailer <<-EOF &&
+	cat >expect.trailer <<-EOF
 	0000
 	EOF
+'
+
+test_expect_success 'test capability advertisement' '
 	cat expect.base expect.trailer >expect &&
 
+	if test_have_prereq WINDOWS
+	then
+		GIT_USER_AGENT=FAKE && export GIT_USER_AGENT
+	fi &&
 	GIT_TEST_SIDEBAND_ALL=0 test-tool serve-v2 \
 		--advertise-capabilities >out &&
 	test-tool pkt-line unpack <out >actual &&
@@ -355,6 +371,10 @@ test_expect_success 'test capability advertisement with uploadpack.advertiseBund
 	    expect.extra \
 	    expect.trailer >expect &&
 
+	if test_have_prereq WINDOWS
+	then
+		GIT_USER_AGENT=FAKE && export GIT_USER_AGENT
+	fi &&
 	GIT_TEST_SIDEBAND_ALL=0 test-tool serve-v2 \
 		--advertise-capabilities >out &&
 	test-tool pkt-line unpack <out >actual &&

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 @@
+#define USE_THE_REPOSITORY_VARIABLE
+
 #include "git-compat-util.h"
 #include "version.h"
 #include "strbuf.h"
+#include "gettext.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;
@@ -24,6 +40,27 @@ const char *git_user_agent(void)
 	return agent;
 }
 
+/*
+  Retrieve, sanitize and cache operating system info for subsequent
+  calls. Return a pointer to the sanitized operating system info
+  string.
+*/
+static const char *os_info(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;
+}
+
 const char *git_user_agent_sanitized(void)
 {
 	static const char *agent = NULL;
@@ -32,13 +69,35 @@ 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] = '.';
+
+		if (!getenv("GIT_USER_AGENT")) {
+			strbuf_addch(&buf, '-');
+			strbuf_addstr(&buf, os_info());
 		}
-		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;
+}

version.h

@@ -1,10 +1,20 @@
 #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);
+
+
 #endif /* VERSION_H */