remote-curl: reencode http error messages

We currently recognize an error message with a content-type
"text/plain; charset=utf-16" as text, but we ignore the
charset parameter entirely. Let's encode it to
log_output_encoding, which is presumably something the
user's terminal can handle.

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

3 files changed, 19 insertions, 7 deletions

diff --git a/remote-curl.c b/remote-curl.c
index a5ab977306..4493b389de 100644
--- a/remote-curl.c
+++ b/remote-curl.c
@@ -194,19 +194,19 @@ static void free_discovery(struct discovery *d)
 	}
 }
 
-static int show_http_message(struct strbuf *type, struct strbuf *msg)
+static int show_http_message(struct strbuf *type, struct strbuf *charset,
+			     struct strbuf *msg)
 {
 	const char *p, *eol;
 
 	/*
 	 * We only show text/plain parts, as other types are likely
 	 * to be ugly to look at on the user's terminal.
-	 *
-	 * TODO should handle "; charset=XXX", and re-encode into
-	 * logoutputencoding
 	 */
 	if (strcmp(type->buf, "text/plain"))
 		return -1;
+	if (charset->len)
+		strbuf_reencode(msg, charset->buf, get_log_output_encoding());
 
 	strbuf_trim(msg);
 	if (!msg->len)
@@ -225,6 +225,7 @@ static struct discovery* discover_refs(const char *service, int for_push)
 {
 	struct strbuf exp = STRBUF_INIT;
 	struct strbuf type = STRBUF_INIT;
+	struct strbuf charset = STRBUF_INIT;
 	struct strbuf buffer = STRBUF_INIT;
 	struct strbuf refs_url = STRBUF_INIT;
 	struct strbuf effective_url = STRBUF_INIT;
@@ -249,6 +250,7 @@ static struct discovery* discover_refs(const char *service, int for_push)
 
 	memset(&options, 0, sizeof(options));
 	options.content_type = &type;
+	options.charset = &charset;
 	options.effective_url = &effective_url;
 	options.base_url = &url;
 	options.no_cache = 1;
@@ -259,13 +261,13 @@ static struct discovery* discover_refs(const char *service, int for_push)
 	case HTTP_OK:
 		break;
 	case HTTP_MISSING_TARGET:
-		show_http_message(&type, &buffer);
+		show_http_message(&type, &charset, &buffer);
 		die("repository '%s' not found", url.buf);
 	case HTTP_NOAUTH:
-		show_http_message(&type, &buffer);
+		show_http_message(&type, &charset, &buffer);
 		die("Authentication failed for '%s'", url.buf);
 	default:
-		show_http_message(&type, &buffer);
+		show_http_message(&type, &charset, &buffer);
 		die("unable to access '%s': %s", url.buf, curl_errorstr);
 	}
 
@@ -310,6 +312,7 @@ static struct discovery* discover_refs(const char *service, int for_push)
 	strbuf_release(&refs_url);
 	strbuf_release(&exp);
 	strbuf_release(&type);
+	strbuf_release(&charset);
 	strbuf_release(&effective_url);
 	strbuf_release(&buffer);
 	last_discovery = last;
diff --git a/t/lib-httpd/error.sh b/t/lib-httpd/error.sh
index 23cec97cc3..eafc9d2d90 100755
--- a/t/lib-httpd/error.sh
+++ b/t/lib-httpd/error.sh
@@ -15,6 +15,10 @@ case "$PATH_INFO" in
 	printf "text/plain; charset=utf-8"
 	charset=utf-8
 	;;
+*utf16*)
+	printf "text/plain; charset=utf-16"
+	charset=utf-16
+	;;
 esac
 printf "\n"
 
diff --git a/t/t5550-http-fetch-dumb.sh b/t/t5550-http-fetch-dumb.sh
index b35b2610e3..01b8aae2ed 100755
--- a/t/t5550-http-fetch-dumb.sh
+++ b/t/t5550-http-fetch-dumb.sh
@@ -186,5 +186,10 @@ test_expect_success 'git client shows text/plain with a charset' '
 	grep "this is the error message" stderr
 '
 
+test_expect_success 'http error messages are reencoded' '
+	test_must_fail git clone "$HTTPD_URL/error/utf16" 2>stderr &&
+	grep "this is the error message" stderr
+'
+
 stop_httpd
 test_done