Tidy shared unicode review feedback

Copilot · youknowone · web-flow · commit e968d838082a · 2026-04-05T07:44:23.000Z
Agent-Logs-Url: https://github.com/RustPython/RustPython/sessions/e4115dbc-b1a5-4a77-90a7-38cf9ac1cdf2 Co-authored-by: youknowone <69878+youknowone@users.noreply.github.com>
diff --git a/crates/sre_engine/src/string.rs b/crates/sre_engine/src/string.rs
@@ -345,13 +345,8 @@ pub(crate) fn is_digit(ch: u32) -> bool {
     rustpython_unicode::regex::is_digit(ch)
 }
 #[inline]
-pub(crate) fn is_loc_alnum(ch: u32) -> bool {
-    // FIXME: Ignore the locales
-    rustpython_unicode::regex::is_locale_alnum(ch)
-}
-#[inline]
 pub(crate) fn is_loc_word(ch: u32) -> bool {
-    ch == '_' as u32 || is_loc_alnum(ch)
+    rustpython_unicode::regex::is_locale_word(ch)
 }
 #[inline]
 pub(crate) const fn is_linebreak(ch: u32) -> bool {
@@ -384,12 +379,8 @@ pub(crate) const fn is_uni_linebreak(ch: u32) -> bool {
     rustpython_unicode::regex::is_unicode_linebreak(ch)
 }
 #[inline]
-pub(crate) fn is_uni_alnum(ch: u32) -> bool {
-    rustpython_unicode::regex::is_unicode_alnum(ch)
-}
-#[inline]
 pub(crate) fn is_uni_word(ch: u32) -> bool {
-    ch == '_' as u32 || is_uni_alnum(ch)
+    rustpython_unicode::regex::is_unicode_word(ch)
 }
 #[inline]
 pub fn lower_unicode(ch: u32) -> u32 {
diff --git a/crates/unicode/src/classify.rs b/crates/unicode/src/classify.rs
@@ -46,10 +46,12 @@ pub fn is_space(cp: u32) -> bool {
     })
 }
 
+/// Python's `str.isprintable()` semantics, which treat ASCII space as printable.
 pub fn is_printable(cp: u32) -> bool {
     cp == '\u{0020}' as u32 || is_repr_printable(cp)
 }
 
+/// Repr/escape printable semantics, which exclude all Unicode space separators.
 pub fn is_repr_printable(cp: u32) -> bool {
     !matches!(
         general_category(cp),

Original file line number	Diff line number	Diff line change
`@@ -46,10 +46,12 @@ pub fn is_space(cp: u32) -> bool {`
`46`	`46`	`})`
`47`	`47`	`}`
`48`	`48`
	`49`	+/// Python's `str.isprintable()` semantics, which treat ASCII space as printable.
`49`	`50`	`pub fn is_printable(cp: u32) -> bool {`
`50`	`51`	`cp == '\u{0020}' as u32 \|\| is_repr_printable(cp)`
`51`	`52`	`}`
`52`	`53`
	`54`	`+/// Repr/escape printable semantics, which exclude all Unicode space separators.`
`53`	`55`	`pub fn is_repr_printable(cp: u32) -> bool {`
`54`	`56`	`!matches!(`
`55`	`57`	`general_category(cp),`