Merge branch 'sverk/r16/utf8-atoms'

* sverk/r16/utf8-atoms:
  erl_interface: Fix bug when transcoding atoms from and to UTF8
  erl_interface: Changed erlang_char_encoding interface
  erts: Testcase doing unicode atom printout with ~w
  erl_interface: even more utf8 atom stuff
  erts: Fix bug in analyze_utf8 causing faulty latin1 detection
  Add UTF-8 node name support for epmd
  workaround...
  Fix merge conflict with hasse
  UTF-8 atom documentation
  test case
  erl_interface: utf8 atoms continued
  Add utf8 atom distribution test cases
  atom fixes for NIFs and atom_to_binary
  UTF-8 support for distribution
  Implement UTF-8 atom support for jinterface
  erl_interface: Enable decode of unicode atoms
  stdlib: Fix printing of unicode atoms
  erts: Change internal representation of atoms to utf8
  erts: Refactor rename DFLAG(S)_INTERNAL_TAGS for conformity

Conflicts:
	erts/emulator/beam/io.c

OTP-10753

1 files changed, 21 insertions, 11 deletions

diff --git a/erts/emulator/beam/erl_nif.c b/erts/emulator/beam/erl_nif.c
index 1bd2d933b2..fb295c9a8a 100644
--- a/erts/emulator/beam/erl_nif.c
+++ b/erts/emulator/beam/erl_nif.c
@@ -743,16 +743,23 @@ int enif_get_atom(ErlNifEnv* env, Eterm atom, char* buf, unsigned len,
 {
     Atom* ap;
     ASSERT(encoding == ERL_NIF_LATIN1);
-    if (is_not_atom(atom)) {
+    if (is_not_atom(atom) || len==0) {
 	return 0;
     }
     ap = atom_tab(atom_val(atom));
-    if (ap->len+1 > len) {
+
+    if (ap->latin1_chars < 0 || ap->latin1_chars >= len) {
 	return 0;
     }
-    sys_memcpy(buf, ap->name, ap->len);
-    buf[ap->len] = '\0';
-    return ap->len + 1;
+    if (ap->latin1_chars == ap->len) {
+	sys_memcpy(buf, ap->name, ap->len);
+    }
+    else {
+	int dlen = erts_utf8_to_latin1((byte*)buf, ap->name, ap->len);
+	ASSERT(dlen == ap->latin1_chars); (void)dlen;
+    }
+    buf[ap->latin1_chars] = '\0';
+    return ap->latin1_chars + 1;
 }
 
 int enif_get_int(ErlNifEnv* env, Eterm term, int* ip)
@@ -854,7 +861,10 @@ int enif_get_atom_length(ErlNifEnv* env, Eterm atom, unsigned* len,
     ASSERT(enc == ERL_NIF_LATIN1);
     if (is_not_atom(atom)) return 0;
     ap = atom_tab(atom_val(atom));
-    *len = ap->len;
+    if (ap->latin1_chars < 0) {
+	return 0;
+    }
+    *len = ap->latin1_chars;
     return 1;
 }
 
@@ -961,7 +971,7 @@ ERL_NIF_TERM enif_make_atom(ErlNifEnv* env, const char* name)
 
 ERL_NIF_TERM enif_make_atom_len(ErlNifEnv* env, const char* name, size_t len)
 {
-    return am_atom_put(name, len);
+    return erts_atom_put((byte*)name, len, ERTS_ATOM_ENC_LATIN1, 1);
 }
 
 int enif_make_existing_atom(ErlNifEnv* env, const char* name, ERL_NIF_TERM* atom,
@@ -974,7 +984,7 @@ int enif_make_existing_atom_len(ErlNifEnv* env, const char* name, size_t len,
 				ERL_NIF_TERM* atom, ErlNifCharEncoding encoding)
 {
     ASSERT(encoding == ERL_NIF_LATIN1);
-    return erts_atom_get(name, len, atom);
+    return erts_atom_get(name, len, atom, 1);
 }
 
 ERL_NIF_TERM enif_make_tuple(ErlNifEnv* env, unsigned cnt, ...)
@@ -1633,7 +1643,7 @@ BIF_RETTYPE load_nif_2(BIF_ALIST_2)
 			     "this vm variant (%s).",
 			     entry->vm_variant, ERL_NIF_VM_VARIANT);
     }
-    else if (!erts_is_atom_str((char*)entry->name, mod_atom)) {
+    else if (!erts_is_atom_str((char*)entry->name, mod_atom, 1)) {
 	ret = load_nif_error(BIF_P, bad_lib, "Library module name '%s' does not"
 			     " match calling module '%T'", entry->name, mod_atom);
     }
@@ -1643,7 +1653,7 @@ BIF_RETTYPE load_nif_2(BIF_ALIST_2)
 	for (i=0; i < entry->num_of_funcs && ret==am_ok; i++) {
 	    BeamInstr** code_pp;
 	    ErlNifFunc* f = &entry->funcs[i];
-	    if (!erts_atom_get(f->name, sys_strlen(f->name), &f_atom)
+	    if (!erts_atom_get(f->name, sys_strlen(f->name), &f_atom, 1)
 		|| (code_pp = get_func_pp(mod->curr.code, f_atom, f->arity))==NULL) {
 		ret = load_nif_error(BIF_P,bad_lib,"Function not found %T:%s/%u",
 				     mod_atom, f->name, f->arity);
@@ -1746,7 +1756,7 @@ BIF_RETTYPE load_nif_2(BIF_ALIST_2)
 	for (i=0; i < entry->num_of_funcs; i++)
 	{
 	    BeamInstr* code_ptr;
-	    erts_atom_get(entry->funcs[i].name, sys_strlen(entry->funcs[i].name), &f_atom); 
+	    erts_atom_get(entry->funcs[i].name, sys_strlen(entry->funcs[i].name), &f_atom, 1); 
 	    code_ptr = *get_func_pp(mod->curr.code, f_atom, entry->funcs[i].arity);
 	    
 	    if (code_ptr[1] == 0) {