From 4e4b916cbb989886b276c4c4e908c2cb59c0b53c Mon Sep 17 00:00:00 2001
From: Micha Reiser <micha@reiser.io>
Date: Thu, 7 Sep 2023 11:18:26 +0200
Subject: [PATCH] Add Lexer emoji test case

---
 crates/ruff_python_parser/src/lexer.rs | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/crates/ruff_python_parser/src/lexer.rs b/crates/ruff_python_parser/src/lexer.rs
index 167250179dcec1..2f8db084978e2b 100644
--- a/crates/ruff_python_parser/src/lexer.rs
+++ b/crates/ruff_python_parser/src/lexer.rs
@@ -1716,4 +1716,22 @@ def f(arg=%timeit a = b):
         let source = "[1";
         let _ = lex(source, Mode::Module).collect::<Vec<_>>();
     }
+
+    /// Emoji identifiers are a non-standard python feature and are not supported by our lexer.
+    #[test]
+    fn test_emoji_identifier() {
+        let source = "\u{0000}";
+
+        let lexed: Vec<_> = lex(source, Mode::Module).collect();
+
+        match lexed.as_slice() {
+            [Err(error), Ok((Tok::Newline, _))] => {
+                assert_eq!(
+                    error.error,
+                    LexicalErrorType::UnrecognizedToken { tok: '\u{0000}' }
+                )
+            }
+            result => panic!("Expected an error token followed by a newline but found {result:?}"),
+        }
+    }
 }