shared: utf8 - support decoding the full utf16

We originally only supported the BMP (i.e., we treated UTF-16 as UCS-2).

Signed-off-by: Anthony G. Basile <blueness@gentoo.org>

1 files changed, 13 insertions, 0 deletions

diff --git a/test/test-utf8.c b/test/test-utf8.c
index bd8ca86834..2f0a95f1c0 100644
--- a/test/test-utf8.c
+++ b/test/test-utf8.c
@@ -44,10 +44,23 @@ static void test_utf8_encoded_valid_unichar(void) {
 
 }
 
+static void test_utf16_to_utf8(void) {
+        char *a = NULL;
+        const uint16_t utf16[] = { 'a', 0xd800, 'b', 0xdc00, 'c', 0xd801, 0xdc37 };
+        const char utf8[] = { 'a', 'b', 'c', 0xf0, 0x90, 0x90, 0xb7, 0 };
+
+        a = utf16_to_utf8(utf16, 14);
+        assert_se(a);
+        assert_se(streq(a, utf8));
+
+        free(a);
+}
+
 int main(int argc, char *argv[]) {
         test_utf8_is_printable();
         test_ascii_is_valid();
         test_utf8_encoded_valid_unichar();
+        test_utf16_to_utf8();
 
         return 0;
 }