Auto merge of #145479 - Kmeakin:km/hardcode-char-is-control, r=joboet

Hard-code `char::is_control`

Split off from https://github.com/rust-lang/rust/pull/145219

According to
https://www.unicode.org/policies/stability_policy.html#Property_Value, the set of codepoints in `Cc` will never change. So we can hard-code the patterns to match against instead of using a table.

This doesn't change the generated assembly, since the lookup table is small enough that[ LLVM is able to inline the whole search](https://godbolt.org/z/bG8dM37YG). But this does reduce the chance of regressions if LLVM's heuristics change in the future, and means less generated Rust code checked in to `unicode-data.rs`.

library/core/src/char/methods.rs

@@ -950,7 +950,11 @@ pub fn is_alphanumeric(self) -> bool {
     #[stable(feature = "rust1", since = "1.0.0")]
     #[inline]
     pub fn is_control(self) -> bool {
-        unicode::Cc(self)
+        // According to
+        // https://www.unicode.org/policies/stability_policy.html#Property_Value,
+        // the set of codepoints in `Cc` will never change.
+        // So we can just hard-code the patterns to match against instead of using a table.
+        matches!(self, '\0'..='\x1f' | '\x7f'..='\u{9f}')
     }
 
     /// Returns `true` if this `char` has the `Grapheme_Extend` property.

library/core/src/unicode/mod.rs

@@ -10,7 +10,6 @@
 
 #[rustfmt::skip]
 pub(crate) use unicode_data::alphabetic::lookup as Alphabetic;
-pub(crate) use unicode_data::cc::lookup as Cc;
 pub(crate) use unicode_data::grapheme_extend::lookup as Grapheme_Extend;
 pub(crate) use unicode_data::lowercase::lookup as Lowercase;
 pub(crate) use unicode_data::n::lookup as N;

library/core/src/unicode/unicode_data.rs

@@ -358,31 +358,6 @@ pub fn lookup(c: char) -> bool {
     }
 }
 
-#[rustfmt::skip]
-pub mod cc {
-    use super::ShortOffsetRunHeader;
-
-    static SHORT_OFFSET_RUNS: [ShortOffsetRunHeader; 1] = [
-        ShortOffsetRunHeader::new(0, 1114272),
-    ];
-    static OFFSETS: [u8; 5] = [
-        0, 32, 95, 33, 0,
-    ];
-    pub fn lookup(c: char) -> bool {
-        const {
-            assert!(SHORT_OFFSET_RUNS.last().unwrap().0 > char::MAX as u32);
-            let mut i = 0;
-            while i < SHORT_OFFSET_RUNS.len() {
-                assert!(SHORT_OFFSET_RUNS[i].start_index() < OFFSETS.len());
-                i += 1;
-            }
-        }
-        // SAFETY: We just ensured the last element of `SHORT_OFFSET_RUNS` is greater than `std::char::MAX`
-        // and the start indices of all elements in `SHORT_OFFSET_RUNS` are smaller than `OFFSETS.len()`.
-        unsafe { super::skip_search(c, &SHORT_OFFSET_RUNS, &OFFSETS) }
-    }
-}
-
 #[rustfmt::skip]
 pub mod grapheme_extend {
     use super::ShortOffsetRunHeader;

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

@@ -92,7 +92,6 @@
     "Case_Ignorable",
     "Grapheme_Extend",
     "White_Space",
-    "Cc",
     "N",
 ];