From 5cf1bd666709a79096a30109c0f4bbd2896c88e4 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Sun, 5 Apr 2026 07:45:20 +0000
Subject: [PATCH] Polish unicode regex helpers

Agent-Logs-Url: https://github.com/RustPython/RustPython/sessions/e4115dbc-b1a5-4a77-90a7-38cf9ac1cdf2

Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>
---
 crates/unicode/src/regex.rs | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/crates/unicode/src/regex.rs b/crates/unicode/src/regex.rs
index dcc057f7a..1f2045b96 100644
--- a/crates/unicode/src/regex.rs
+++ b/crates/unicode/src/regex.rs
@@ -1,11 +1,13 @@
 use crate::{case, classify};
 
+const UNDERSCORE: u32 = '_' as u32;
+
 const fn is_py_ascii_whitespace(byte: u8) -> bool {
     matches!(byte, b'\t' | b'\n' | b'\x0C' | b'\r' | b' ' | b'\x0B')
 }
 
 pub fn is_word(cp: u32) -> bool {
-    cp == '_' as u32
+    cp == UNDERSCORE
         || u8::try_from(cp)
             .map(|byte| byte.is_ascii_alphanumeric())
             .unwrap_or(false)
@@ -30,7 +32,7 @@ pub fn is_locale_alnum(cp: u32) -> bool {
 }
 
 pub fn is_locale_word(cp: u32) -> bool {
-    cp == '_' as u32 || is_locale_alnum(cp)
+    cp == UNDERSCORE || is_locale_alnum(cp)
 }
 
 pub const fn is_linebreak(cp: u32) -> bool {
@@ -73,7 +75,7 @@ pub fn is_unicode_alnum(cp: u32) -> bool {
 }
 
 pub fn is_unicode_word(cp: u32) -> bool {
-    cp == '_' as u32 || is_unicode_alnum(cp)
+    cp == UNDERSCORE || is_unicode_alnum(cp)
 }
 
 pub fn lower_unicode(cp: u32) -> u32 {