include agent identifier in capability string

Instead of having the client advertise a particular version
number in the git protocol, we have managed extensions and
backwards compatibility by having clients and servers
advertise capabilities that they support. This is far more
robust than having each side consult a table of
known versions, and provides sufficient information for the
protocol interaction to complete.

However, it does not allow servers to keep statistics on
which client versions are being used. This information is
not necessary to complete the network request (the
capabilities provide enough information for that), but it
may be helpful to conduct a general survey of client
versions in use.

We already send the client version in the user-agent header
for http requests; adding it here allows us to gather
similar statistics for non-http requests.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

6 files changed, 38 insertions, 6 deletions

diff --git a/builtin/fetch-pack.c b/builtin/fetch-pack.c
index 149db8872..fe565966a 100644
--- a/builtin/fetch-pack.c
+++ b/builtin/fetch-pack.c
@@ -10,6 +10,7 @@
 #include "remote.h"
 #include "run-command.h"
 #include "transport.h"
+#include "version.h"
 
 static int transfer_unpack_limit = -1;
 static int fetch_unpack_limit = -1;
@@ -327,6 +328,7 @@ static int find_common(int fd[2], unsigned char *result_sha1,
 			if (args.no_progress)   strbuf_addstr(&c, " no-progress");
 			if (args.include_tag)   strbuf_addstr(&c, " include-tag");
 			if (prefer_ofs_delta)   strbuf_addstr(&c, " ofs-delta");
+			strbuf_addf(&c, " agent=%s", git_user_agent_sanitized());
 			packet_buf_write(&req_buf, "want %s%s\n", remote_hex, c.buf);
 			strbuf_release(&c);
 		} else
diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index 0afb8b289..fbfa1289c 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -12,6 +12,7 @@
 #include "string-list.h"
 #include "sha1-array.h"
 #include "connected.h"
+#include "version.h"
 
 static const char receive_pack_usage[] = "git receive-pack <git-dir>";
 
@@ -121,10 +122,11 @@ static void show_ref(const char *path, const unsigned char *sha1)
 	if (sent_capabilities)
 		packet_write(1, "%s %s\n", sha1_to_hex(sha1), path);
 	else
-		packet_write(1, "%s %s%c%s%s\n",
+		packet_write(1, "%s %s%c%s%s agent=%s\n",
 			     sha1_to_hex(sha1), path, 0,
 			     " report-status delete-refs side-band-64k quiet",
-			     prefer_ofs_delta ? " ofs-delta" : "");
+			     prefer_ofs_delta ? " ofs-delta" : "",
+			     git_user_agent_sanitized());
 	sent_capabilities = 1;
 }
 
diff --git a/builtin/send-pack.c b/builtin/send-pack.c
index d5d7105ba..c4d42113c 100644
--- a/builtin/send-pack.c
+++ b/builtin/send-pack.c
@@ -8,6 +8,7 @@
 #include "send-pack.h"
 #include "quote.h"
 #include "transport.h"
+#include "version.h"
 
 static const char send_pack_usage[] =
 "git send-pack [--all | --mirror] [--dry-run] [--force] [--receive-pack=<git-receive-pack>] [--verbose] [--thin] [<host>:]<directory> [<ref>...]\n"
@@ -306,11 +307,13 @@ int send_pack(struct send_pack_args *args,
 			int quiet = quiet_supported && (args->quiet || !args->progress);
 
 			if (!cmds_sent && (status_report || use_sideband || args->quiet)) {
-				packet_buf_write(&req_buf, "%s %s %s%c%s%s%s",
+				packet_buf_write(&req_buf,
+						 "%s %s %s%c%s%s%s agent=%s",
 						 old_hex, new_hex, ref->name, 0,
 						 status_report ? " report-status" : "",
 						 use_sideband ? " side-band-64k" : "",
-						 quiet ? " quiet" : "");
+						 quiet ? " quiet" : "",
+						 git_user_agent_sanitized());
 			}
 			else
 				packet_buf_write(&req_buf, "%s %s %s",
diff --git a/upload-pack.c b/upload-pack.c
index bb08e2eb0..2e90ccb74 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -11,6 +11,7 @@
 #include "list-objects.h"
 #include "run-command.h"
 #include "sigchain.h"
+#include "version.h"
 
 static const char upload_pack_usage[] = "git upload-pack [--strict] [--timeout=<n>] <dir>";
 
@@ -734,9 +735,11 @@ static int send_ref(const char *refname, const unsigned char *sha1, int flag, vo
 	}
 
 	if (capabilities)
-		packet_write(1, "%s %s%c%s%s\n", sha1_to_hex(sha1), refname_nons,
+		packet_write(1, "%s %s%c%s%s agent=%s\n",
+			     sha1_to_hex(sha1), refname_nons,
 			     0, capabilities,
-			     stateless_rpc ? " no-done" : "");
+			     stateless_rpc ? " no-done" : "",
+			     git_user_agent_sanitized());
 	else
 		packet_write(1, "%s %s\n", sha1_to_hex(sha1), refname_nons);
 	capabilities = NULL;
diff --git a/version.c b/version.c
index f98d5a654..6106a8098 100644
--- a/version.c
+++ b/version.c
@@ -1,5 +1,6 @@
 #include "git-compat-util.h"
 #include "version.h"
+#include "strbuf.h"
 
 const char git_version_string[] = GIT_VERSION;
 
@@ -15,3 +16,23 @@ const char *git_user_agent(void)
 
 	return agent;
 }
+
+const char *git_user_agent_sanitized(void)
+{
+	static const char *agent = NULL;
+
+	if (!agent) {
+		struct strbuf buf = STRBUF_INIT;
+		int i;
+
+		strbuf_addstr(&buf, git_user_agent());
+		strbuf_trim(&buf);
+		for (i = 0; i < buf.len; i++) {
+			if (buf.buf[i] <= 32 || buf.buf[i] >= 127)
+				buf.buf[i] = '.';
+		}
+		agent = buf.buf;
+	}
+
+	return agent;
+}
diff --git a/version.h b/version.h
index fd9cdd631..6911a4f15 100644
--- a/version.h
+++ b/version.h
@@ -4,5 +4,6 @@
 extern const char git_version_string[];
 
 const char *git_user_agent(void);
+const char *git_user_agent_sanitized(void);
 
 #endif /* VERSION_H */