From fa7a2a51c40ed1ae2539271e0e1f3e2d863f6fa6 Mon Sep 17 00:00:00 2001
From: Tom Schuster <evilpies@gmail.com>
Date: Fri, 14 Feb 2025 22:28:57 +0100
Subject: [PATCH] Switch identifier crate from unic-ucd-ident to
 unicode-id-start

---
 Cargo.toml       |  2 +-
 src/lib.rs       | 13 +++++++++++++
 src/tokenizer.rs |  4 ++--
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/Cargo.toml b/Cargo.toml
index 8295022..9e1d87f 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -11,7 +11,7 @@ license = "MIT"
 url = "2.4.1"
 regex = "1.10.5"
 serde = { version = "1.0.127", features = ["derive"] }
-unic-ucd-ident = { version = "0.9.0", features = ["id"] }
+unicode-id-start = "1.0"
 
 [dev-dependencies]
 serde_json = "1.0.66"
diff --git a/src/lib.rs b/src/lib.rs
index 7a73226..18f76c6 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -1047,4 +1047,17 @@ mod tests {
     .unwrap();
     assert!(pattern.has_regexp_groups());
   }
+
+  #[test]
+  fn unicode_middle_dot() {
+    let pattern = <UrlPattern>::parse(
+      UrlPatternInit {
+        pathname: Some("/:a\u{30FB}b.".to_owned()),
+        ..Default::default()
+      },
+      Default::default(),
+    )
+    .unwrap();
+    assert_eq!(pattern.pathname.group_name_list, vec!["a\u{30FB}b"]);
+  }
 }
diff --git a/src/tokenizer.rs b/src/tokenizer.rs
index dd25cfb..c15c22e 100644
--- a/src/tokenizer.rs
+++ b/src/tokenizer.rs
@@ -319,9 +319,9 @@ pub fn tokenize(
 #[inline]
 pub(crate) fn is_valid_name_codepoint(code_point: char, first: bool) -> bool {
   if first {
-    unic_ucd_ident::is_id_start(code_point) || matches!(code_point, '$' | '_')
+    unicode_id_start::is_id_start(code_point) || matches!(code_point, '$' | '_')
   } else {
-    unic_ucd_ident::is_id_continue(code_point)
+    unicode_id_start::is_id_continue(code_point)
       || matches!(code_point, '$' | '\u{200C}' | '\u{200D}')
   }
 }