py/objstr: Always ensure mp_obj_str_from_vstr is unicode-safe.

Now that we have `mp_obj_new_str_type_from_vstr` (private helper used by
objstr.c) split from the public API (`mp_obj_new_str_from_vstr`), we can
enforce a unicode check at the public API without incurring a performance
cost on the various objstr.c methods (which are already working on known
unicode-safe strings).

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>

1 files changed, 5 insertions, 0 deletions

diff --git a/py/objstr.c b/py/objstr.c
index 69745a2f5..ab1229ad6 100644
--- a/py/objstr.c
+++ b/py/objstr.c
@@ -2248,6 +2248,11 @@ STATIC mp_obj_t mp_obj_new_str_type_from_vstr(const mp_obj_type_t *type, vstr_t
 }
 
 mp_obj_t mp_obj_new_str_from_vstr(vstr_t *vstr) {
+    #if MICROPY_PY_BUILTINS_STR_UNICODE && MICROPY_PY_BUILTINS_STR_UNICODE_CHECK
+    if (!utf8_check((byte *)vstr->buf, vstr->len)) {
+        mp_raise_msg(&mp_type_UnicodeError, NULL);
+    }
+    #endif // MICROPY_PY_BUILTINS_STR_UNICODE && MICROPY_PY_BUILTINS_STR_UNICODE_CHECK
     return mp_obj_new_str_type_from_vstr(&mp_type_str, vstr);
 }