Auto merge of #146173 - Kmeakin:km/unicode-data/no-ascii, r=jhpratt

Don't include ASCII characters in Unicode tables

Split off from #145219

Author: bors

library/alloc/src/str.rs

@@ -418,9 +418,8 @@ impl str {
         }
 
         fn case_ignorable_then_cased<I: Iterator<Item = char>>(iter: I) -> bool {
-            use core::unicode::{Case_Ignorable, Cased};
-            match iter.skip_while(|&c| Case_Ignorable(c)).next() {
-                Some(c) => Cased(c),
+            match iter.skip_while(|&c| c.is_case_ignorable()).next() {
+                Some(c) => c.is_cased(),
                 None => false,
             }
         }

library/core/src/char/methods.rs

@@ -969,7 +969,43 @@ impl char {
     #[must_use]
     #[inline]
     pub(crate) fn is_grapheme_extended(self) -> bool {
-        unicode::Grapheme_Extend(self)
+        !self.is_ascii() && unicode::Grapheme_Extend(self)
+    }
+
+    /// Returns `true` if this `char` has the `Cased` property.
+    ///
+    /// `Cased` is described in Chapter 4 (Character Properties) of the [Unicode Standard] and
+    /// specified in the [Unicode Character Database][ucd] [`DerivedCoreProperties.txt`].
+    ///
+    /// [Unicode Standard]: https://www.unicode.org/versions/latest/
+    /// [ucd]: https://www.unicode.org/reports/tr44/
+    /// [`DerivedCoreProperties.txt`]: https://www.unicode.org/Public/UCD/latest/ucd/DerivedCoreProperties.txt
+    #[must_use]
+    #[inline]
+    #[doc(hidden)]
+    #[unstable(feature = "char_internals", reason = "exposed only for libstd", issue = "none")]
+    pub fn is_cased(self) -> bool {
+        if self.is_ascii() { self.is_ascii_alphabetic() } else { unicode::Cased(self) }
+    }
+
+    /// Returns `true` if this `char` has the `Case_Ignorable` property.
+    ///
+    /// `Case_Ignorable` is described in Chapter 4 (Character Properties) of the [Unicode Standard] and
+    /// specified in the [Unicode Character Database][ucd] [`DerivedCoreProperties.txt`].
+    ///
+    /// [Unicode Standard]: https://www.unicode.org/versions/latest/
+    /// [ucd]: https://www.unicode.org/reports/tr44/
+    /// [`DerivedCoreProperties.txt`]: https://www.unicode.org/Public/UCD/latest/ucd/DerivedCoreProperties.txt
+    #[must_use]
+    #[inline]
+    #[doc(hidden)]
+    #[unstable(feature = "char_internals", reason = "exposed only for libstd", issue = "none")]
+    pub fn is_case_ignorable(self) -> bool {
+        if self.is_ascii() {
+            matches!(self, '\'' | '.' | ':' | '^' | '`')
+        } else {
+            unicode::Case_Ignorable(self)
+        }
     }
 
     /// Returns `true` if this `char` has one of the general categories for numbers.

library/core/src/unicode/unicode_data.rs

@@ -64,6 +64,7 @@ impl RawEmitter {
 
         writeln!(&mut self.file, "#[inline]").unwrap();
         writeln!(&mut self.file, "pub const fn lookup(c: char) -> bool {{").unwrap();
+        writeln!(&mut self.file, "    debug_assert!(!c.is_ascii());").unwrap();
         writeln!(&mut self.file, "    match c as u32 >> 8 {{").unwrap();
         for arm in arms {
             writeln!(&mut self.file, "        {arm},").unwrap();

src/tools/unicode-table-generator/src/cascading_map.rs

@@ -195,6 +195,7 @@ fn load_data() -> UnicodeData {
                 .into_iter()
                 .flatten()
                 .flat_map(|cp| cp.scalar())
+                .filter(|c| !c.is_ascii())
                 .map(u32::from)
                 .collect::<Vec<_>>();
             (prop, ranges_from_set(&codepoints))

src/tools/unicode-table-generator/src/main.rs

@@ -98,6 +98,7 @@ impl RawEmitter {
         self.blank_line();
 
         writeln!(&mut self.file, "pub const fn lookup(c: char) -> bool {{").unwrap();
+        writeln!(&mut self.file, "    debug_assert!(!c.is_ascii());").unwrap();
         if first_code_point > 0x7f {
             writeln!(&mut self.file, "    (c as u32) >= {first_code_point:#04x} &&").unwrap();
         }

src/tools/unicode-table-generator/src/raw_emitter.rs

@@ -99,6 +99,7 @@ impl RawEmitter {
         if first_code_point > 0x7f {
             writeln!(&mut self.file, "#[inline]").unwrap();
             writeln!(&mut self.file, "pub fn lookup(c: char) -> bool {{").unwrap();
+            writeln!(&mut self.file, "    debug_assert!(!c.is_ascii());").unwrap();
             writeln!(&mut self.file, "    (c as u32) >= {first_code_point:#04x} && lookup_slow(c)")
                 .unwrap();
             writeln!(&mut self.file, "}}").unwrap();
@@ -107,6 +108,7 @@ impl RawEmitter {
             writeln!(&mut self.file, "fn lookup_slow(c: char) -> bool {{").unwrap();
         } else {
             writeln!(&mut self.file, "pub fn lookup(c: char) -> bool {{").unwrap();
+            writeln!(&mut self.file, "    debug_assert!(!c.is_ascii());").unwrap();
         }
         writeln!(&mut self.file, "    const {{").unwrap();
         writeln!(