From d3f2be4bd8790da2af8ed2b85dcea77d95a5da3e Mon Sep 17 00:00:00 2001 From: Lukas Kalbertodt Date: Tue, 22 Aug 2017 19:45:36 +0200 Subject: [PATCH] Add all methods of AsciiExt to u8 directly This is the first step in order to deprecate AsciiExt. Since this is a WIP commit, there is still some code duplication (notably the static arrays) that will be removed later. --- src/libcore/num/mod.rs | 655 +++++++++++++++++++++++++++++++++++++++++ src/libstd/ascii.rs | 2 +- 2 files changed, 656 insertions(+), 1 deletion(-) diff --git a/src/libcore/num/mod.rs b/src/libcore/num/mod.rs index 5799d37c19c..b631691c731 100644 --- a/src/libcore/num/mod.rs +++ b/src/libcore/num/mod.rs @@ -2257,6 +2257,558 @@ impl u8 { intrinsics::add_with_overflow, intrinsics::sub_with_overflow, intrinsics::mul_with_overflow } + + + /// Checks if the value is within the ASCII range. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let ascii = 97u8; + /// let non_ascii = 150u8; + /// + /// assert!(ascii.is_ascii()); + /// assert!(!non_ascii.is_ascii()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii(&self) -> bool { + *self & 128 == 0 + } + + /// Makes a copy of the value in its ASCII upper case equivalent. + /// + /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', + /// but non-ASCII letters are unchanged. + /// + /// To uppercase the value in-place, use [`make_ascii_uppercase`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let lowercase_a = 97u8; + /// + /// assert_eq!(65, lowercase_a.to_ascii_uppercase()); + /// ``` + /// + /// [`make_ascii_uppercase`]: #method.make_ascii_uppercase + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn to_ascii_uppercase(&self) -> u8 { + ASCII_UPPERCASE_MAP[*self as usize] + } + + /// Makes a copy of the value in its ASCII lower case equivalent. + /// + /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', + /// but non-ASCII letters are unchanged. + /// + /// To lowercase the value in-place, use [`make_ascii_lowercase`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = 65u8; + /// + /// assert_eq!(97, uppercase_a.to_ascii_lowercase()); + /// ``` + /// + /// [`make_ascii_lowercase`]: #method.make_ascii_lowercase + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn to_ascii_lowercase(&self) -> u8 { + ASCII_LOWERCASE_MAP[*self as usize] + } + + /// Checks that two values are an ASCII case-insensitive match. + /// + /// Same as `to_ascii_lowercase(a) == to_ascii_lowercase(b)`, + /// but without allocating and copying temporaries. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let lowercase_a = 97u8; + /// let uppercase_a = 65u8; + /// + /// assert!(lowercase_a.eq_ignore_ascii_case(uppercase_a)); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn eq_ignore_ascii_case(&self, other: u8) -> bool { + self.to_ascii_lowercase() == other.to_ascii_lowercase() + } + + /// Converts this value to its ASCII upper case equivalent in-place. + /// + /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', + /// but non-ASCII letters are unchanged. + /// + /// To return a new uppercased value without modifying the existing one, use + /// [`to_ascii_uppercase`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let mut byte = b'a'; + /// + /// byte.make_ascii_uppercase(); + /// + /// assert_eq!(b'A', byte); + /// ``` + /// + /// [`to_ascii_uppercase`]: #method.to_ascii_uppercase + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn make_ascii_uppercase(&mut self) { + *self = self.to_ascii_uppercase(); + } + + /// Converts this value to its ASCII lower case equivalent in-place. + /// + /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', + /// but non-ASCII letters are unchanged. + /// + /// To return a new lowercased value without modifying the existing one, use + /// [`to_ascii_lowercase`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let mut byte = b'A'; + /// + /// byte.make_ascii_lowercase(); + /// + /// assert_eq!(b'a', byte); + /// ``` + /// + /// [`to_ascii_lowercase`]: #method.to_ascii_lowercase + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn make_ascii_lowercase(&mut self) { + *self = self.to_ascii_lowercase(); + } + + /// Checks if the value is an ASCII alphabetic character: + /// + /// - U+0041 'A' ... U+005A 'Z', or + /// - U+0061 'a' ... U+007A 'z'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(uppercase_a.is_ascii_alphabetic()); + /// assert!(uppercase_g.is_ascii_alphabetic()); + /// assert!(a.is_ascii_alphabetic()); + /// assert!(g.is_ascii_alphabetic()); + /// assert!(!zero.is_ascii_alphabetic()); + /// assert!(!percent.is_ascii_alphabetic()); + /// assert!(!space.is_ascii_alphabetic()); + /// assert!(!lf.is_ascii_alphabetic()); + /// assert!(!esc.is_ascii_alphabetic()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_alphabetic(&self) -> bool { + if *self >= 0x80 { return false; } + match ASCII_CHARACTER_CLASS[*self as usize] { + L | Lx | U | Ux => true, + _ => false + } + } + + /// Checks if the value is an ASCII uppercase character: + /// U+0041 'A' ... U+005A 'Z'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(uppercase_a.is_ascii_uppercase()); + /// assert!(uppercase_g.is_ascii_uppercase()); + /// assert!(!a.is_ascii_uppercase()); + /// assert!(!g.is_ascii_uppercase()); + /// assert!(!zero.is_ascii_uppercase()); + /// assert!(!percent.is_ascii_uppercase()); + /// assert!(!space.is_ascii_uppercase()); + /// assert!(!lf.is_ascii_uppercase()); + /// assert!(!esc.is_ascii_uppercase()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_uppercase(&self) -> bool { + if *self >= 0x80 { return false } + match ASCII_CHARACTER_CLASS[*self as usize] { + U | Ux => true, + _ => false + } + } + + /// Checks if the value is an ASCII lowercase character: + /// U+0061 'a' ... U+007A 'z'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(!uppercase_a.is_ascii_lowercase()); + /// assert!(!uppercase_g.is_ascii_lowercase()); + /// assert!(a.is_ascii_lowercase()); + /// assert!(g.is_ascii_lowercase()); + /// assert!(!zero.is_ascii_lowercase()); + /// assert!(!percent.is_ascii_lowercase()); + /// assert!(!space.is_ascii_lowercase()); + /// assert!(!lf.is_ascii_lowercase()); + /// assert!(!esc.is_ascii_lowercase()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_lowercase(&self) -> bool { + if *self >= 0x80 { return false } + match ASCII_CHARACTER_CLASS[*self as usize] { + L | Lx => true, + _ => false + } + } + + /// Checks if the value is an ASCII alphanumeric character: + /// + /// - U+0041 'A' ... U+005A 'Z', U+0061 'a' ... U+007A 'z', or + /// - U+0030 '0' ... U+0039 '9'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(uppercase_a.is_ascii_alphanumeric()); + /// assert!(uppercase_g.is_ascii_alphanumeric()); + /// assert!(a.is_ascii_alphanumeric()); + /// assert!(g.is_ascii_alphanumeric()); + /// assert!(zero.is_ascii_alphanumeric()); + /// assert!(!percent.is_ascii_alphanumeric()); + /// assert!(!space.is_ascii_alphanumeric()); + /// assert!(!lf.is_ascii_alphanumeric()); + /// assert!(!esc.is_ascii_alphanumeric()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub 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 + } + } + + /// Checks if the value is an ASCII decimal digit: + /// U+0030 '0' ... U+0039 '9'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(!uppercase_a.is_ascii_digit()); + /// assert!(!uppercase_g.is_ascii_digit()); + /// assert!(!a.is_ascii_digit()); + /// assert!(!g.is_ascii_digit()); + /// assert!(zero.is_ascii_digit()); + /// assert!(!percent.is_ascii_digit()); + /// assert!(!space.is_ascii_digit()); + /// assert!(!lf.is_ascii_digit()); + /// assert!(!esc.is_ascii_digit()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_digit(&self) -> bool { + if *self >= 0x80 { return false } + match ASCII_CHARACTER_CLASS[*self as usize] { + D => true, + _ => false + } + } + + /// Checks if the value is an ASCII hexadecimal digit: + /// + /// - U+0030 '0' ... U+0039 '9', U+0041 'A' ... U+0046 'F', or + /// - U+0061 'a' ... U+0066 'f'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(uppercase_a.is_ascii_hexdigit()); + /// assert!(!uppercase_g.is_ascii_hexdigit()); + /// assert!(a.is_ascii_hexdigit()); + /// assert!(!g.is_ascii_hexdigit()); + /// assert!(zero.is_ascii_hexdigit()); + /// assert!(!percent.is_ascii_hexdigit()); + /// assert!(!space.is_ascii_hexdigit()); + /// assert!(!lf.is_ascii_hexdigit()); + /// assert!(!esc.is_ascii_hexdigit()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_hexdigit(&self) -> bool { + if *self >= 0x80 { return false } + match ASCII_CHARACTER_CLASS[*self as usize] { + D | Lx | Ux => true, + _ => false + } + } + + /// Checks if the value is an ASCII punctuation character: + /// + /// - U+0021 ... U+002F `! " # $ % & ' ( ) * + , - . /`, or + /// - U+003A ... U+0040 `: ; < = > ? @`, or + /// - U+005B ... U+0060 `[ \\ ] ^ _ \``, or + /// - U+007B ... U+007E `{ | } ~` + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(!uppercase_a.is_ascii_punctuation()); + /// assert!(!uppercase_g.is_ascii_punctuation()); + /// assert!(!a.is_ascii_punctuation()); + /// assert!(!g.is_ascii_punctuation()); + /// assert!(!zero.is_ascii_punctuation()); + /// assert!(percent.is_ascii_punctuation()); + /// assert!(!space.is_ascii_punctuation()); + /// assert!(!lf.is_ascii_punctuation()); + /// assert!(!esc.is_ascii_punctuation()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_punctuation(&self) -> bool { + if *self >= 0x80 { return false } + match ASCII_CHARACTER_CLASS[*self as usize] { + P => true, + _ => false + } + } + + /// Checks if the value is an ASCII graphic character: + /// U+0021 '@' ... U+007E '~'. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(uppercase_a.is_ascii_graphic()); + /// assert!(uppercase_g.is_ascii_graphic()); + /// assert!(a.is_ascii_graphic()); + /// assert!(g.is_ascii_graphic()); + /// assert!(zero.is_ascii_graphic()); + /// assert!(percent.is_ascii_graphic()); + /// assert!(!space.is_ascii_graphic()); + /// assert!(!lf.is_ascii_graphic()); + /// assert!(!esc.is_ascii_graphic()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub 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 + } + } + + /// Checks if the value is an ASCII whitespace character: + /// U+0020 SPACE, U+0009 HORIZONTAL TAB, U+000A LINE FEED, + /// U+000C FORM FEED, or U+000D CARRIAGE RETURN. + /// + /// Rust uses the WhatWG Infra Standard's [definition of ASCII + /// whitespace][infra-aw]. There are several other definitions in + /// wide use. For instance, [the POSIX locale][pct] includes + /// U+000B VERTICAL TAB as well as all the above characters, + /// but—from the very same specification—[the default rule for + /// "field splitting" in the Bourne shell][bfs] considers *only* + /// SPACE, HORIZONTAL TAB, and LINE FEED as whitespace. + /// + /// If you are writing a program that will process an existing + /// file format, check what that format's definition of whitespace is + /// before using this function. + /// + /// [infra-aw]: https://infra.spec.whatwg.org/#ascii-whitespace + /// [pct]: http://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html#tag_07_03_01 + /// [bfs]: http://pubs.opengroup.org/onlinepubs/9699919799/utilities/V3_chap02.html#tag_18_06_05 + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(!uppercase_a.is_ascii_whitespace()); + /// assert!(!uppercase_g.is_ascii_whitespace()); + /// assert!(!a.is_ascii_whitespace()); + /// assert!(!g.is_ascii_whitespace()); + /// assert!(!zero.is_ascii_whitespace()); + /// assert!(!percent.is_ascii_whitespace()); + /// assert!(space.is_ascii_whitespace()); + /// assert!(lf.is_ascii_whitespace()); + /// assert!(!esc.is_ascii_whitespace()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_whitespace(&self) -> bool { + if *self >= 0x80 { return false; } + match ASCII_CHARACTER_CLASS[*self as usize] { + Cw|W => true, + _ => false + } + } + + /// Checks if the value is an ASCII control character: + /// U+0000 NUL ... U+001F UNIT SEPARATOR, or U+007F DELETE. + /// Note that most ASCII whitespace characters are control + /// characters, but SPACE is not. + /// + /// # Examples + /// + /// ``` + /// #![feature(ascii_methods_on_intrinsics)] + /// + /// let uppercase_a = b'A'; + /// let uppercase_g = b'G'; + /// let a = b'a'; + /// let g = b'g'; + /// let zero = b'0'; + /// let percent = b'%'; + /// let space = b' '; + /// let lf = b'\n'; + /// let esc = 0x1b_u8; + /// + /// assert!(!uppercase_a.is_ascii_control()); + /// assert!(!uppercase_g.is_ascii_control()); + /// assert!(!a.is_ascii_control()); + /// assert!(!g.is_ascii_control()); + /// assert!(!zero.is_ascii_control()); + /// assert!(!percent.is_ascii_control()); + /// assert!(!space.is_ascii_control()); + /// assert!(lf.is_ascii_control()); + /// assert!(esc.is_ascii_control()); + /// ``` + #[unstable(feature = "ascii_methods_on_intrinsics", issue = "0")] + #[inline] + pub fn is_ascii_control(&self) -> bool { + if *self >= 0x80 { return false; } + match ASCII_CHARACTER_CLASS[*self as usize] { + C|Cw => true, + _ => false + } + } } #[lang = "u16"] @@ -2926,3 +3478,106 @@ impl_from! { u32, f64, #[stable(feature = "lossless_float_conv", since = "1.6.0" // Float -> Float impl_from! { f32, f64, #[stable(feature = "lossless_float_conv", since = "1.6.0")] } + +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_ +]; diff --git a/src/libstd/ascii.rs b/src/libstd/ascii.rs index 327deb9b419..8ddc75868ac 100644 --- a/src/libstd/ascii.rs +++ b/src/libstd/ascii.rs @@ -685,7 +685,7 @@ impl AsciiExt for [u8] { #[inline] fn eq_ignore_ascii_case(&self, other: &[u8]) -> bool { self.len() == other.len() && - self.iter().zip(other).all(|(a, b)| { + self.iter().zip(other).all(|(a, &b)| { a.eq_ignore_ascii_case(b) }) }