diff options
| author | Lukas Kalbertodt <lukas.kalbertodt@gmail.com> | 2017-09-28 18:25:16 +0200 |
|---|---|---|
| committer | Lukas Kalbertodt <lukas.kalbertodt@gmail.com> | 2017-11-03 21:27:40 +0100 |
| commit | 6f5556854ebe396d6e4550e5255de6696a924e1c (patch) | |
| tree | b0e0108cededb2d7ca96c21a67fd037d82f65a17 /src/libstd/ascii.rs | |
| parent | d425f8d2266f481bab447f30816fc9a1b4907868 (diff) | |
| download | rust-6f5556854ebe396d6e4550e5255de6696a924e1c.tar.gz rust-6f5556854ebe396d6e4550e5255de6696a924e1c.zip | |
Use direct implementation on u8/char to implement AsciiExt
The methods were copied to u8/char, so we can just use it in AsciiExt impls to avoid duplicate code.
Diffstat (limited to 'src/libstd/ascii.rs')
| -rw-r--r-- | src/libstd/ascii.rs | 321 |
1 files changed, 41 insertions, 280 deletions
diff --git a/src/libstd/ascii.rs b/src/libstd/ascii.rs index 327deb9b419..3dd8b2b08e6 100644 --- a/src/libstd/ascii.rs +++ b/src/libstd/ascii.rs @@ -753,202 +753,66 @@ impl AsciiExt for [u8] { } } -#[stable(feature = "rust1", since = "1.0.0")] -impl AsciiExt for u8 { - type Owned = u8; - #[inline] - fn is_ascii(&self) -> bool { *self & 128 == 0 } - #[inline] - fn to_ascii_uppercase(&self) -> u8 { ASCII_UPPERCASE_MAP[*self as usize] } - #[inline] - fn to_ascii_lowercase(&self) -> u8 { ASCII_LOWERCASE_MAP[*self as usize] } - #[inline] - fn eq_ignore_ascii_case(&self, other: &u8) -> bool { - self.to_ascii_lowercase() == other.to_ascii_lowercase() - } - #[inline] - fn make_ascii_uppercase(&mut self) { *self = self.to_ascii_uppercase(); } - #[inline] - fn make_ascii_lowercase(&mut self) { *self = self.to_ascii_lowercase(); } +macro_rules! impl_by_delegating { + ($ty:ty, $owned:ty) => { + #[stable(feature = "rust1", since = "1.0.0")] + impl AsciiExt for $ty { + type Owned = $owned; - #[inline] - fn is_ascii_alphabetic(&self) -> bool { - if *self >= 0x80 { return false; } - match ASCII_CHARACTER_CLASS[*self as usize] { - L|Lx|U|Ux => true, - _ => false - } - } + #[inline] + fn is_ascii(&self) -> bool { self.is_ascii() } - #[inline] - fn is_ascii_uppercase(&self) -> bool { - if *self >= 0x80 { return false } - match ASCII_CHARACTER_CLASS[*self as usize] { - U|Ux => true, - _ => false - } - } + #[inline] + fn to_ascii_uppercase(&self) -> Self::Owned { self.to_ascii_uppercase() } - #[inline] - fn is_ascii_lowercase(&self) -> bool { - if *self >= 0x80 { return false } - match ASCII_CHARACTER_CLASS[*self as usize] { - L|Lx => true, - _ => false - } - } + #[inline] + fn to_ascii_lowercase(&self) -> Self::Owned { self.to_ascii_lowercase() } - #[inline] - fn is_ascii_alphanumeric(&self) -> bool { - if *self >= 0x80 { return false } - match ASCII_CHARACTER_CLASS[*self as usize] { - D|L|Lx|U|Ux => true, - _ => false - } - } + #[inline] + fn eq_ignore_ascii_case(&self, o: &Self) -> bool { self.eq_ignore_ascii_case(o) } - #[inline] - fn is_ascii_digit(&self) -> bool { - if *self >= 0x80 { return false } - match ASCII_CHARACTER_CLASS[*self as usize] { - D => true, - _ => false - } - } + #[inline] + fn make_ascii_uppercase(&mut self) { self.make_ascii_uppercase(); } - #[inline] - fn is_ascii_hexdigit(&self) -> bool { - if *self >= 0x80 { return false } - match ASCII_CHARACTER_CLASS[*self as usize] { - D|Lx|Ux => true, - _ => false - } - } + #[inline] + fn make_ascii_lowercase(&mut self) { self.make_ascii_lowercase(); } - #[inline] - fn is_ascii_punctuation(&self) -> bool { - if *self >= 0x80 { return false } - match ASCII_CHARACTER_CLASS[*self as usize] { - P => true, - _ => false - } - } + #[inline] + fn is_ascii_alphabetic(&self) -> bool { self.is_ascii_alphabetic() } - #[inline] - fn is_ascii_graphic(&self) -> bool { - if *self >= 0x80 { return false; } - match ASCII_CHARACTER_CLASS[*self as usize] { - Ux|U|Lx|L|D|P => true, - _ => false - } - } + #[inline] + fn is_ascii_uppercase(&self) -> bool { self.is_ascii_uppercase() } - #[inline] - fn is_ascii_whitespace(&self) -> bool { - if *self >= 0x80 { return false; } - match ASCII_CHARACTER_CLASS[*self as usize] { - Cw|W => true, - _ => false - } - } + #[inline] + fn is_ascii_lowercase(&self) -> bool { self.is_ascii_lowercase() } - #[inline] - fn is_ascii_control(&self) -> bool { - if *self >= 0x80 { return false; } - match ASCII_CHARACTER_CLASS[*self as usize] { - C|Cw => true, - _ => false - } - } -} + #[inline] + fn is_ascii_alphanumeric(&self) -> bool { self.is_ascii_alphanumeric() } -#[stable(feature = "rust1", since = "1.0.0")] -impl AsciiExt for char { - type Owned = char; - #[inline] - fn is_ascii(&self) -> bool { - *self as u32 <= 0x7F - } + #[inline] + fn is_ascii_digit(&self) -> bool { self.is_ascii_digit() } - #[inline] - fn to_ascii_uppercase(&self) -> char { - if self.is_ascii() { - (*self as u8).to_ascii_uppercase() as char - } else { - *self - } - } - - #[inline] - fn to_ascii_lowercase(&self) -> char { - if self.is_ascii() { - (*self as u8).to_ascii_lowercase() as char - } else { - *self - } - } - - #[inline] - fn eq_ignore_ascii_case(&self, other: &char) -> bool { - self.to_ascii_lowercase() == other.to_ascii_lowercase() - } - - #[inline] - fn make_ascii_uppercase(&mut self) { *self = self.to_ascii_uppercase(); } - #[inline] - fn make_ascii_lowercase(&mut self) { *self = self.to_ascii_lowercase(); } - - #[inline] - fn is_ascii_alphabetic(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_alphabetic() - } - - #[inline] - fn is_ascii_uppercase(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_uppercase() - } - - #[inline] - fn is_ascii_lowercase(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_lowercase() - } - - #[inline] - fn is_ascii_alphanumeric(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_alphanumeric() - } - - #[inline] - fn is_ascii_digit(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_digit() - } + #[inline] + fn is_ascii_hexdigit(&self) -> bool { self.is_ascii_hexdigit() } - #[inline] - fn is_ascii_hexdigit(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_hexdigit() - } - - #[inline] - fn is_ascii_punctuation(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_punctuation() - } + #[inline] + fn is_ascii_punctuation(&self) -> bool { self.is_ascii_punctuation() } - #[inline] - fn is_ascii_graphic(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_graphic() - } + #[inline] + fn is_ascii_graphic(&self) -> bool { self.is_ascii_graphic() } - #[inline] - fn is_ascii_whitespace(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_whitespace() - } + #[inline] + fn is_ascii_whitespace(&self) -> bool { self.is_ascii_whitespace() } - #[inline] - fn is_ascii_control(&self) -> bool { - (*self as u32 <= 0x7f) && (*self as u8).is_ascii_control() + #[inline] + fn is_ascii_control(&self) -> bool { self.is_ascii_control() } + } } } +impl_by_delegating!(u8, u8); +impl_by_delegating!(char, char); + /// An iterator over the escaped version of a byte. /// /// This `struct` is created by the [`escape_default`] function. See its @@ -1066,109 +930,6 @@ impl fmt::Debug for EscapeDefault { } -static ASCII_LOWERCASE_MAP: [u8; 256] = [ - 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, - 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, - 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, - 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, - b' ', b'!', b'"', b'#', b'$', b'%', b'&', b'\'', - b'(', b')', b'*', b'+', b',', b'-', b'.', b'/', - b'0', b'1', b'2', b'3', b'4', b'5', b'6', b'7', - b'8', b'9', b':', b';', b'<', b'=', b'>', b'?', - b'@', - - b'a', b'b', b'c', b'd', b'e', b'f', b'g', - b'h', b'i', b'j', b'k', b'l', b'm', b'n', b'o', - b'p', b'q', b'r', b's', b't', b'u', b'v', b'w', - b'x', b'y', b'z', - - b'[', b'\\', b']', b'^', b'_', - b'`', b'a', b'b', b'c', b'd', b'e', b'f', b'g', - b'h', b'i', b'j', b'k', b'l', b'm', b'n', b'o', - b'p', b'q', b'r', b's', b't', b'u', b'v', b'w', - b'x', b'y', b'z', b'{', b'|', b'}', b'~', 0x7f, - 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, - 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, - 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, - 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, - 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, - 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, - 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, - 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, - 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, - 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, - 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, - 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, - 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, - 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, - 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, - 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, -]; - -static ASCII_UPPERCASE_MAP: [u8; 256] = [ - 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, - 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, - 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, - 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, - b' ', b'!', b'"', b'#', b'$', b'%', b'&', b'\'', - b'(', b')', b'*', b'+', b',', b'-', b'.', b'/', - b'0', b'1', b'2', b'3', b'4', b'5', b'6', b'7', - b'8', b'9', b':', b';', b'<', b'=', b'>', b'?', - b'@', b'A', b'B', b'C', b'D', b'E', b'F', b'G', - b'H', b'I', b'J', b'K', b'L', b'M', b'N', b'O', - b'P', b'Q', b'R', b'S', b'T', b'U', b'V', b'W', - b'X', b'Y', b'Z', b'[', b'\\', b']', b'^', b'_', - b'`', - - b'A', b'B', b'C', b'D', b'E', b'F', b'G', - b'H', b'I', b'J', b'K', b'L', b'M', b'N', b'O', - b'P', b'Q', b'R', b'S', b'T', b'U', b'V', b'W', - b'X', b'Y', b'Z', - - b'{', b'|', b'}', b'~', 0x7f, - 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, - 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, - 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, - 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, - 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, - 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf, - 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, - 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf, - 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, - 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, - 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, - 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, - 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, - 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, - 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, - 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, -]; - -enum AsciiCharacterClass { - C, // control - Cw, // control whitespace - W, // whitespace - D, // digit - L, // lowercase - Lx, // lowercase hex digit - U, // uppercase - Ux, // uppercase hex digit - P, // punctuation -} -use self::AsciiCharacterClass::*; - -static ASCII_CHARACTER_CLASS: [AsciiCharacterClass; 128] = [ -// _0 _1 _2 _3 _4 _5 _6 _7 _8 _9 _a _b _c _d _e _f - C, C, C, C, C, C, C, C, C, Cw,Cw,C, Cw,Cw,C, C, // 0_ - C, C, C, C, C, C, C, C, C, C, C, C, C, C, C, C, // 1_ - W, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, // 2_ - D, D, D, D, D, D, D, D, D, D, P, P, P, P, P, P, // 3_ - P, Ux,Ux,Ux,Ux,Ux,Ux,U, U, U, U, U, U, U, U, U, // 4_ - U, U, U, U, U, U, U, U, U, U, U, P, P, P, P, P, // 5_ - P, Lx,Lx,Lx,Lx,Lx,Lx,L, L, L, L, L, L, L, L, L, // 6_ - L, L, L, L, L, L, L, L, L, L, L, P, P, P, P, C, // 7_ -]; - #[cfg(test)] mod tests { use super::*; |
