Add tests for unicode dot in both str and bytes

src/lib.rs

@@ -30,6 +30,9 @@ extern crate core as std;
 pub use logos_derive::Logos;
 use std::fmt::Debug;
 
+#[cfg(test)]
+mod tests;
+
 mod lexer;
 pub mod source;
 

src/tests.rs

@@ -0,0 +1,57 @@
+use crate::Logos;
+
+#[derive(Logos, Debug, PartialEq)]
+#[logos(crate = crate)]
+enum TestUnicodeDot {
+    #[regex(".")]
+    Dot,
+}
+
+#[test]
+fn test_unicode_dot_str_ascii() {
+    let mut lexer = TestUnicodeDot::lexer("a");
+    assert_eq!(lexer.next(), Some(Ok(TestUnicodeDot::Dot)));
+    assert_eq!(lexer.remainder(), "");
+    assert_eq!(lexer.next(), None);
+}
+
+#[test]
+fn test_unicode_dot_str_unicode() {
+    let mut lexer = TestUnicodeDot::lexer("");
+    assert_eq!(lexer.next(), Some(Ok(TestUnicodeDot::Dot)));
+    assert_eq!(lexer.remainder(), "");
+    assert_eq!(lexer.next(), None);
+}
+
+#[derive(Logos, Debug, PartialEq)]
+#[logos(crate = crate)]
+enum TestUnicodeDotBytes {
+    #[regex(".", priority = 100)]
+    Dot,
+    #[regex(b".", priority = 0)]
+    InvalidUtf8,
+}
+
+#[test]
+fn test_unicode_dot_bytes_ascii() {
+    let mut lexer = TestUnicodeDotBytes::lexer(b"a");
+    assert_eq!(lexer.next(), Some(Ok(TestUnicodeDotBytes::Dot)));
+    assert_eq!(lexer.remainder(), b"");
+    assert_eq!(lexer.next(), None);
+}
+
+#[test]
+fn test_unicode_dot_bytes_unicode() {
+    let mut lexer = TestUnicodeDotBytes::lexer("".as_bytes());
+    assert_eq!(lexer.next(), Some(Ok(TestUnicodeDotBytes::Dot)));
+    assert_eq!(lexer.remainder(), b"");
+    assert_eq!(lexer.next(), None);
+}
+
+#[test]
+fn test_unicode_dot_bytes_invalid_utf8() {
+    let mut lexer = TestUnicodeDotBytes::lexer(b"\xff");
+    assert_eq!(lexer.next(), Some(Ok(TestUnicodeDotBytes::InvalidUtf8)));
+    assert_eq!(lexer.remainder(), b"");
+    assert_eq!(lexer.next(), None);
+}