Properly deal with unicode chars in $

Closes #27.
elixir-makeup · May 9, 2024 · baa18c5 · baa18c5
1 parent 567c536
commit baa18c5
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 4 deletions.
diff --git a/lib/makeup/lexers/erlang_lexer.ex b/lib/makeup/lexers/erlang_lexer.ex
@@ -155,9 +155,8 @@ defmodule Makeup.Lexers.ErlangLexer do
   character =
     string("$")
     |> choice([
-      escape,
-      string("\\") |> ascii_char([?\s, ?%]),
-      ascii_char(not: ?\\)
+      string("\\") |> utf8_char([]),
+      utf8_char(not: ?\\)
     ])
     |> token(:string_char)
 
@@ -247,7 +246,7 @@ defmodule Makeup.Lexers.ErlangLexer do
     |> concat(token("/", :punctuation))
     |> concat(number_integer)
 
-  # Erlang prompt 
+  # Erlang prompt
   erl_prompt =
     string("\n")
     |> optional(string("(") |> concat(atom_name) |> string(")"))

diff --git a/test/makeup/erlang_lexer/erlang_lexer_tokenizer_test.exs b/test/makeup/erlang_lexer/erlang_lexer_tokenizer_test.exs
@@ -6,6 +6,12 @@ defmodule ErlangLexerTokenizer do
     assert lex("") == []
   end
 
+  test "character" do
+    assert lex("$a") == [{:string_char, %{}, "$a"}]
+    assert lex("$\\ ") == [{:string_char, %{}, "$\\ "}]
+    assert lex("$🫂") == [{:string_char, %{}, "$🫂"}]
+  end
+
   test "comment" do
     assert lex("%abc") == [{:comment_single, %{}, "%abc"}]
     assert lex("% abc") == [{:comment_single, %{}, "% abc"}]