Add new AtU8 beam chunk

The new chunk stores atoms encoded in UTF-8.

beam_lib has also been modified to handle the new
'utf8_atoms' attribute while the 'atoms' attribute
may be a missing chunk from now on.

The binary_to_atom/2 BIF can now encode any utf8
binary with up to 255 characters.

The list_to_atom/1 BIF can now accept codepoints
higher than 255 with up to 255 characters (thanks
to Björn Gustavsson).

1 files changed, 7 insertions, 7 deletions

diff --git a/erts/emulator/beam/bif.c b/erts/emulator/beam/bif.c
index d886c2985e..95bf13c07c 100644
--- a/erts/emulator/beam/bif.c
+++ b/erts/emulator/beam/bif.c
@@ -3022,8 +3022,8 @@ BIF_RETTYPE atom_to_list_1(BIF_ALIST_1)
 BIF_RETTYPE list_to_atom_1(BIF_ALIST_1)
 {
     Eterm res;
-    char *buf = (char *) erts_alloc(ERTS_ALC_T_TMP, MAX_ATOM_CHARACTERS);
-    Sint i = intlist_to_buf(BIF_ARG_1, buf, MAX_ATOM_CHARACTERS);
+    byte *buf = (byte *) erts_alloc(ERTS_ALC_T_TMP, MAX_ATOM_SZ_LIMIT);
+    Sint i = erts_unicode_list_to_buf(BIF_ARG_1, buf, MAX_ATOM_CHARACTERS);
 
     if (i < 0) {
 	erts_free(ERTS_ALC_T_TMP, (void *) buf);
@@ -3033,7 +3033,7 @@ BIF_RETTYPE list_to_atom_1(BIF_ALIST_1)
 	}
 	BIF_ERROR(BIF_P, BADARG);
     }
-    res = erts_atom_put((byte *) buf, i, ERTS_ATOM_ENC_LATIN1, 1);
+    res = erts_atom_put(buf, i, ERTS_ATOM_ENC_UTF8, 1);
     ASSERT(is_atom(res));
     erts_free(ERTS_ALC_T_TMP, (void *) buf);
     BIF_RET(res);
@@ -3043,17 +3043,17 @@ BIF_RETTYPE list_to_atom_1(BIF_ALIST_1)
  
 BIF_RETTYPE list_to_existing_atom_1(BIF_ALIST_1)
 {
-    Sint i;
-    char *buf = (char *) erts_alloc(ERTS_ALC_T_TMP, MAX_ATOM_CHARACTERS);
+    byte *buf = (byte *) erts_alloc(ERTS_ALC_T_TMP, MAX_ATOM_SZ_LIMIT);
+    Sint i = erts_unicode_list_to_buf(BIF_ARG_1, buf, MAX_ATOM_CHARACTERS);
 
-    if ((i = intlist_to_buf(BIF_ARG_1, buf, MAX_ATOM_CHARACTERS)) < 0) {
+    if (i < 0) {
     error:
 	erts_free(ERTS_ALC_T_TMP, (void *) buf);
 	BIF_ERROR(BIF_P, BADARG);
     } else {
 	Eterm a;
 	
-	if (erts_atom_get(buf, i, &a, ERTS_ATOM_ENC_LATIN1)) {
+	if (erts_atom_get((char *) buf, i, &a, ERTS_ATOM_ENC_UTF8)) {
 	    erts_free(ERTS_ALC_T_TMP, (void *) buf);
 	    BIF_RET(a);
 	} else {