diff options
| -rw-r--r-- | library/core/src/char/convert.rs | 15 |
1 files changed, 14 insertions, 1 deletions
diff --git a/library/core/src/char/convert.rs b/library/core/src/char/convert.rs index 1774ddd7cbb..56dc2a594e1 100644 --- a/library/core/src/char/convert.rs +++ b/library/core/src/char/convert.rs @@ -271,7 +271,20 @@ impl FromStr for char { #[inline] const fn char_try_from_u32(i: u32) -> Result<char, CharTryFromError> { - if (i > MAX as u32) || (i >= 0xD800 && i <= 0xDFFF) { + // This is an optimized version of the check + // (i > MAX as u32) || (i >= 0xD800 && i <= 0xDFFF), + // which can also be written as + // i >= 0x110000 || (i >= 0xD800 && i < 0xE000). + // + // The XOR with 0xD800 permutes the ranges such that 0xD800..0xE000 is + // mapped to 0x0000..0x0800, while keeping all the high bits outside 0xFFFF the same. + // In particular, numbers >= 0x110000 stay in this range. + // + // Subtracting 0x800 causes 0x0000..0x0800 to wrap, meaning that a single + // unsigned comparison against 0x110000 - 0x800 will detect both the wrapped + // surrogate range as well as the numbers originally larger than 0x110000. + // + if (i ^ 0xD800).wrapping_sub(0x800) >= 0x110000 - 0x800 { Err(CharTryFromError(())) } else { // SAFETY: checked that it's a legal unicode value |