Auto merge of rust-lang#122013 - Swatinem:unicode-gen-fastpath, r=scottmcm

Add a lower bound check to `unicode-table-generator` output

This adds a dedicated check for the lower bound
(if it is outside of ASCII range) to the output of the `unicode-table-generator` tool.

This generalized the ASCII-only fast-path, but only for the `Grapheme_Extend` property for now, as that is the only one with a lower bound outside of ASCII.

Author: bors

core/src/char/methods.rs

@@ -927,7 +927,7 @@ impl char {
     #[must_use]
     #[inline]
     pub(crate) fn is_grapheme_extended(self) -> bool {
-        self > '\x7f' && unicode::Grapheme_Extend(self)
+        unicode::Grapheme_Extend(self)
     }
 
     /// Returns `true` if this `char` has one of the general categories for numbers.

core/src/unicode/unicode_data.rs

@@ -315,7 +315,11 @@ pub mod grapheme_extend {
         15, 0, 7, 1, 17, 2, 7, 1, 2, 1, 5, 100, 1, 160, 7, 0, 1, 61, 4, 0, 4, 0, 7, 109, 7, 0, 96,
         128, 240, 0,
     ];
+    #[inline]
     pub fn lookup(c: char) -> bool {
+        (c as u32) >= 0x300 && lookup_slow(c)
+    }
+    fn lookup_slow(c: char) -> bool {
         super::skip_search(
             c as u32,
             &SHORT_OFFSET_RUNS,