Merge pull request atomvm#1708 from jgonet/jgonet/unicode-option

Add unicode alias for utf8 option

These changes are made under both the "Apache 2.0" and the "GNU Lesser General
Public License 2.1 or later" license terms (dual license).

SPDX-License-Identifier: Apache-2.0 OR LGPL-2.1-or-later

Author: bettio

libs/estdlib/src/unicode.erl

@@ -47,7 +47,7 @@
     char() | unicode_binary() | charlist(), unicode_binary() | []
 ).
 
--type encoding() :: utf8 | latin1.
+-type encoding() :: utf8 | unicode | latin1.
 
 -export_type([
     unicode_binary/0,

src/libAtomVM/nifs.c

@@ -5341,13 +5341,28 @@ static term nif_maps_next(Context *ctx, int argc, term argv[])
     return ret;
 }
 
+static bool encoding_from_atom(term encoding_atom, enum CharDataEncoding *encoding)
+{
+    switch (encoding_atom) {
+        case LATIN1_ATOM:
+            *encoding = Latin1Encoding;
+            return true;
+        case UTF8_ATOM:
+        case UNICODE_ATOM:
+            *encoding = UTF8Encoding;
+            return true;
+        default:
+            return false;
+    }
+}
+
 static term nif_unicode_characters_to_list(Context *ctx, int argc, term argv[])
 {
     enum CharDataEncoding in_encoding = UTF8Encoding;
-    if (argc == 2) {
-        if (argv[1] == LATIN1_ATOM) {
-            in_encoding = Latin1Encoding;
-        } else if (UNLIKELY((argv[1] != UTF8_ATOM))) {
+    bool has_in_encoding = argc == 2;
+    if (has_in_encoding) {
+        term in_encoding_atom = argv[1];
+        if (UNLIKELY(!encoding_from_atom(in_encoding_atom, &in_encoding))) {
             RAISE_ERROR(BADARG_ATOM);
         }
     }
@@ -5406,18 +5421,18 @@ static term nif_unicode_characters_to_binary(Context *ctx, int argc, term argv[]
 {
     enum CharDataEncoding in_encoding = UTF8Encoding;
     enum CharDataEncoding out_encoding = UTF8Encoding;
-    if (argc > 1) {
-        if (argv[1] == LATIN1_ATOM) {
-            in_encoding = Latin1Encoding;
-        } else if (UNLIKELY((argv[1] != UTF8_ATOM))) {
+    bool has_in_encoding = argc > 1;
+    bool has_out_encoding = argc == 3;
+    if (has_in_encoding) {
+        term in_encoding_atom = argv[1];
+        if (UNLIKELY(!encoding_from_atom(in_encoding_atom, &in_encoding))) {
             RAISE_ERROR(BADARG_ATOM);
         }
-        if (argc == 3) {
-            if (argv[2] == LATIN1_ATOM) {
-                out_encoding = Latin1Encoding;
-            } else if (UNLIKELY((argv[2] != UTF8_ATOM))) {
-                RAISE_ERROR(BADARG_ATOM);
-            }
+    }
+    if (has_out_encoding) {
+        term out_encoding_atom = argv[2];
+        if (UNLIKELY(!encoding_from_atom(out_encoding_atom, &out_encoding))) {
+            RAISE_ERROR(BADARG_ATOM);
         }
     }
     size_t len;

tests/erlang_tests/test_unicode.erl

@@ -52,12 +52,17 @@ test_to_list_latin1() ->
 test_to_list_utf8() ->
     "hello" = unicode:characters_to_list(<<"hello">>),
     "hello" = unicode:characters_to_list("hello", utf8),
+    "hello" = unicode:characters_to_list("hello", unicode),
     "hé" = unicode:characters_to_list(<<"hé"/utf8>>),
     "hé" = unicode:characters_to_list("hé"),
     "hé" = unicode:characters_to_list(<<"hé"/utf8>>, utf8),
+    "hé" = unicode:characters_to_list(<<"hé"/utf8>>, unicode),
     {error, "h", [-1]} = unicode:characters_to_list([$h, -1], utf8),
+    {error, "h", [-1]} = unicode:characters_to_list([$h, -1], unicode),
     [$h, 16#10ffff] = unicode:characters_to_list([$h, 16#10ffff], utf8),
+    [$h, 16#10ffff] = unicode:characters_to_list([$h, 16#10ffff], unicode),
     {error, "h", [16#110000]} = unicode:characters_to_list([$h, 16#110000], utf8),
+    {error, "h", [16#110000]} = unicode:characters_to_list([$h, 16#110000], unicode),
     {incomplete, "h", <<"é">>} = unicode:characters_to_list(<<"hé">>),
     {error, [], <<16#A0, 16#A1>>} = unicode:characters_to_list(<<16#A0, 16#A1>>),
     % Erlang/OTP documentation writes: "The last part is mostly for debugging"
@@ -131,10 +136,21 @@ test_to_binary_latin1() ->
 
 test_to_binary_utf8() ->
     <<"hello">> = unicode:characters_to_binary("hello", utf8, utf8),
+    <<"hello">> = unicode:characters_to_binary("hello", unicode, unicode),
+    <<"hello">> = unicode:characters_to_binary("hello", utf8, unicode),
+    <<"hello">> = unicode:characters_to_binary("hello", unicode, utf8),
     <<"hello">> = unicode:characters_to_binary(<<"hello">>, utf8, utf8),
+    <<"hello">> = unicode:characters_to_binary(<<"hello">>, unicode, unicode),
+    <<"hello">> = unicode:characters_to_binary(<<"hello">>, utf8, unicode),
+    <<"hello">> = unicode:characters_to_binary(<<"hello">>, unicode, utf8),
     <<"hé"/utf8>> = unicode:characters_to_binary("hé", latin1, utf8),
+    <<"hé"/utf8>> = unicode:characters_to_binary("hé", latin1, unicode),
     <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>, utf8, utf8),
+    <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>, unicode, unicode),
+    <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>, utf8, unicode),
+    <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>, unicode, utf8),
     <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>, utf8),
+    <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>, unicode),
     <<"hé"/utf8>> = unicode:characters_to_binary(<<"hé"/utf8>>),
     {error, <<"h">>, [-1]} = unicode:characters_to_binary([$h, -1]),
     <<"h", 244, 143, 191, 191>> = unicode:characters_to_binary([$h, 16#10FFFF]),