// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
-//
-// ignore-lexer-test FIXME #15679
//! Operations on ASCII strings and characters
-#![unstable = "unsure about placement and naming"]
+#![stable(feature = "rust1", since = "1.0.0")]
+
+use prelude::v1::*;
-use iter::IteratorExt;
-use ops::FnMut;
-use slice::SliceExt;
-use str::StrExt;
-use string::String;
-use vec::Vec;
+use ops::Range;
+use mem;
/// Extension methods for ASCII-subset only operations on owned strings
-#[unstable = "would prefer to do this in a more general way"]
+#[unstable(feature = "owned_ascii_ext",
+ reason = "would prefer to do this in a more general way")]
pub trait OwnedAsciiExt {
- /// Convert the string to ASCII upper case:
+ /// Converts the string to ASCII upper case:
/// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
/// but non-ASCII letters are unchanged.
fn into_ascii_uppercase(self) -> Self;
- /// Convert the string to ASCII lower case:
+ /// Converts the string to ASCII lower case:
/// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
/// but non-ASCII letters are unchanged.
fn into_ascii_lowercase(self) -> Self;
}
-/// Extension methods for ASCII-subset only operations on string slices
-#[unstable = "would prefer to do this in a more general way"]
-pub trait AsciiExt<T = Self> {
- /// Check if within the ASCII range.
+/// Extension methods for ASCII-subset only operations on string slices.
+#[stable(feature = "rust1", since = "1.0.0")]
+pub trait AsciiExt {
+ /// Container type for copied ASCII characters.
+ #[stable(feature = "rust1", since = "1.0.0")]
+ type Owned;
+
+ /// Checks if within the ASCII range.
+ ///
+ /// # Examples
+ ///
+ /// ```
+ /// use std::ascii::AsciiExt;
+ ///
+ /// let ascii = 'a';
+ /// let utf8 = '❤';
+ ///
+ /// assert_eq!(true, ascii.is_ascii());
+ /// assert_eq!(false, utf8.is_ascii())
+ /// ```
+ #[stable(feature = "rust1", since = "1.0.0")]
fn is_ascii(&self) -> bool;
- /// Makes a copy of the string in ASCII upper case:
+ /// Makes a copy of the string in ASCII upper case.
+ ///
/// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z',
/// but non-ASCII letters are unchanged.
- fn to_ascii_uppercase(&self) -> T;
-
- /// Makes a copy of the string in ASCII lower case:
+ ///
+ /// # Examples
+ ///
+ /// ```
+ /// use std::ascii::AsciiExt;
+ ///
+ /// let ascii = 'a';
+ /// let utf8 = '❤';
+ ///
+ /// assert_eq!('A', ascii.to_ascii_uppercase());
+ /// assert_eq!('❤', utf8.to_ascii_uppercase());
+ /// ```
+ #[stable(feature = "rust1", since = "1.0.0")]
+ fn to_ascii_uppercase(&self) -> Self::Owned;
+
+ /// Makes a copy of the string in ASCII lower case.
+ ///
/// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z',
/// but non-ASCII letters are unchanged.
- fn to_ascii_lowercase(&self) -> T;
-
- /// Check that two strings are an ASCII case-insensitive match.
+ ///
+ /// # Examples
+ ///
+ /// ```
+ /// use std::ascii::AsciiExt;
+ ///
+ /// let ascii = 'A';
+ /// let utf8 = '❤';
+ ///
+ /// assert_eq!('a', ascii.to_ascii_lowercase());
+ /// assert_eq!('❤', utf8.to_ascii_lowercase());
+ /// ```
+ #[stable(feature = "rust1", since = "1.0.0")]
+ fn to_ascii_lowercase(&self) -> Self::Owned;
+
+ /// Checks that two strings are an ASCII case-insensitive match.
+ ///
/// Same as `to_ascii_lowercase(a) == to_ascii_lowercase(b)`,
/// but without allocating and copying temporary strings.
+ ///
+ /// # Examples
+ ///
+ /// ```
+ /// use std::ascii::AsciiExt;
+ ///
+ /// let ascii1 = 'A';
+ /// let ascii2 = 'a';
+ /// let ascii3 = 'A';
+ /// let ascii4 = 'z';
+ ///
+ /// assert_eq!(true, ascii1.eq_ignore_ascii_case(&ascii2));
+ /// assert_eq!(true, ascii1.eq_ignore_ascii_case(&ascii3));
+ /// assert_eq!(false, ascii1.eq_ignore_ascii_case(&ascii4));
+ /// ```
+ #[stable(feature = "rust1", since = "1.0.0")]
fn eq_ignore_ascii_case(&self, other: &Self) -> bool;
+
+ /// Converts this type to its ASCII upper case equivalent in-place.
+ ///
+ /// See `to_ascii_uppercase` for more information.
+ ///
+ /// # Examples
+ ///
+ /// ```
+ /// # #![feature(ascii)]
+ /// use std::ascii::AsciiExt;
+ ///
+ /// let mut ascii = 'a';
+ ///
+ /// ascii.make_ascii_uppercase();
+ ///
+ /// assert_eq!('A', ascii);
+ /// ```
+ #[unstable(feature = "ascii")]
+ fn make_ascii_uppercase(&mut self);
+
+ /// Converts this type to its ASCII lower case equivalent in-place.
+ ///
+ /// See `to_ascii_lowercase` for more information.
+ ///
+ /// # Examples
+ ///
+ /// ```
+ /// # #![feature(ascii)]
+ /// use std::ascii::AsciiExt;
+ ///
+ /// let mut ascii = 'A';
+ ///
+ /// ascii.make_ascii_lowercase();
+ ///
+ /// assert_eq!('a', ascii);
+ /// ```
+ #[unstable(feature = "ascii")]
+ fn make_ascii_lowercase(&mut self);
}
-#[unstable = "would prefer to do this in a more general way"]
-impl AsciiExt<String> for str {
+#[stable(feature = "rust1", since = "1.0.0")]
+impl AsciiExt for str {
+ type Owned = String;
+
#[inline]
fn is_ascii(&self) -> bool {
self.bytes().all(|b| b.is_ascii())
#[inline]
fn to_ascii_uppercase(&self) -> String {
- // Vec<u8>::to_ascii_uppercase() preserves the UTF-8 invariant.
- unsafe { String::from_utf8_unchecked(self.as_bytes().to_ascii_uppercase()) }
+ self.to_string().into_ascii_uppercase()
}
#[inline]
fn to_ascii_lowercase(&self) -> String {
- // Vec<u8>::to_ascii_lowercase() preserves the UTF-8 invariant.
- unsafe { String::from_utf8_unchecked(self.as_bytes().to_ascii_lowercase()) }
+ self.to_string().into_ascii_lowercase()
}
#[inline]
fn eq_ignore_ascii_case(&self, other: &str) -> bool {
self.as_bytes().eq_ignore_ascii_case(other.as_bytes())
}
+
+ fn make_ascii_uppercase(&mut self) {
+ let me: &mut [u8] = unsafe { mem::transmute(self) };
+ me.make_ascii_uppercase()
+ }
+
+ fn make_ascii_lowercase(&mut self) {
+ let me: &mut [u8] = unsafe { mem::transmute(self) };
+ me.make_ascii_lowercase()
+ }
}
-#[unstable = "would prefer to do this in a more general way"]
impl OwnedAsciiExt for String {
#[inline]
fn into_ascii_uppercase(self) -> String {
}
}
-#[unstable = "would prefer to do this in a more general way"]
-impl AsciiExt<Vec<u8>> for [u8] {
+#[stable(feature = "rust1", since = "1.0.0")]
+impl AsciiExt for [u8] {
+ type Owned = Vec<u8>;
#[inline]
fn is_ascii(&self) -> bool {
self.iter().all(|b| b.is_ascii())
#[inline]
fn to_ascii_uppercase(&self) -> Vec<u8> {
- self.iter().map(|b| b.to_ascii_uppercase()).collect()
+ self.to_vec().into_ascii_uppercase()
}
#[inline]
fn to_ascii_lowercase(&self) -> Vec<u8> {
- self.iter().map(|b| b.to_ascii_lowercase()).collect()
+ self.to_vec().into_ascii_lowercase()
}
#[inline]
fn eq_ignore_ascii_case(&self, other: &[u8]) -> bool {
self.len() == other.len() &&
- self.iter().zip(other.iter()).all(|(a, b)| {
+ self.iter().zip(other).all(|(a, b)| {
a.eq_ignore_ascii_case(b)
})
}
+
+ fn make_ascii_uppercase(&mut self) {
+ for byte in self {
+ byte.make_ascii_uppercase();
+ }
+ }
+
+ fn make_ascii_lowercase(&mut self) {
+ for byte in self {
+ byte.make_ascii_lowercase();
+ }
+ }
}
-#[unstable = "would prefer to do this in a more general way"]
impl OwnedAsciiExt for Vec<u8> {
#[inline]
fn into_ascii_uppercase(mut self) -> Vec<u8> {
- for byte in self.iter_mut() {
- *byte = byte.to_ascii_uppercase();
- }
+ self.make_ascii_uppercase();
self
}
#[inline]
fn into_ascii_lowercase(mut self) -> Vec<u8> {
- for byte in self.iter_mut() {
- *byte = byte.to_ascii_lowercase();
- }
+ self.make_ascii_lowercase();
self
}
}
-#[unstable = "would prefer to do this in a more general way"]
+#[stable(feature = "rust1", since = "1.0.0")]
impl AsciiExt for u8 {
+ type Owned = u8;
#[inline]
- fn is_ascii(&self) -> bool {
- *self & 128 == 0u8
- }
-
+ fn is_ascii(&self) -> bool { *self & 128 == 0 }
#[inline]
- fn to_ascii_uppercase(&self) -> u8 {
- ASCII_UPPERCASE_MAP[*self as uint]
- }
-
+ fn to_ascii_uppercase(&self) -> u8 { ASCII_UPPERCASE_MAP[*self as usize] }
#[inline]
- fn to_ascii_lowercase(&self) -> u8 {
- ASCII_LOWERCASE_MAP[*self as uint]
- }
-
+ 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(); }
}
-#[unstable = "would prefer to do this in a more general way"]
+#[stable(feature = "rust1", since = "1.0.0")]
impl AsciiExt for char {
+ type Owned = char;
#[inline]
fn is_ascii(&self) -> bool {
*self as u32 <= 0x7F
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(); }
}
-/// Returns a 'default' ASCII and C++11-like literal escape of a `u8`
+/// An iterator over the escaped version of a byte, constructed via
+/// `std::ascii::escape_default`.
+#[stable(feature = "rust1", since = "1.0.0")]
+pub struct EscapeDefault {
+ range: Range<usize>,
+ data: [u8; 4],
+}
+
+/// Returns an iterator that produces an escaped version of a `u8`.
///
/// The default is chosen with a bias toward producing literals that are
/// legal in a variety of languages, including C++11 and similar C-family
/// - Tab, CR and LF are escaped as '\t', '\r' and '\n' respectively.
/// - Single-quote, double-quote and backslash chars are backslash-escaped.
/// - Any other chars in the range [0x20,0x7e] are not escaped.
-/// - Any other chars are given hex escapes.
+/// - Any other chars are given hex escapes of the form '\xNN'.
/// - Unicode escapes are never generated by this function.
-#[unstable = "needs to be updated to use an iterator"]
-pub fn escape_default<F>(c: u8, mut f: F) where
- F: FnMut(u8),
-{
- match c {
- b'\t' => { f(b'\\'); f(b't'); }
- b'\r' => { f(b'\\'); f(b'r'); }
- b'\n' => { f(b'\\'); f(b'n'); }
- b'\\' => { f(b'\\'); f(b'\\'); }
- b'\'' => { f(b'\\'); f(b'\''); }
- b'"' => { f(b'\\'); f(b'"'); }
- b'\x20' ... b'\x7e' => { f(c); }
- _ => {
- f(b'\\');
- f(b'x');
- for &offset in [4u, 0u].iter() {
- match ((c as i32) >> offset) & 0xf {
- i @ 0 ... 9 => f(b'0' + (i as u8)),
- i => f(b'a' + (i as u8 - 10)),
- }
- }
+///
+/// # Examples
+///
+/// ```
+/// use std::ascii;
+///
+/// let escaped = ascii::escape_default(b'0').next().unwrap();
+/// assert_eq!(b'0', escaped);
+///
+/// let mut escaped = ascii::escape_default(b'\t');
+///
+/// assert_eq!(b'\\', escaped.next().unwrap());
+/// assert_eq!(b't', escaped.next().unwrap());
+/// ```
+#[stable(feature = "rust1", since = "1.0.0")]
+pub fn escape_default(c: u8) -> EscapeDefault {
+ let (data, len) = match c {
+ b'\t' => ([b'\\', b't', 0, 0], 2),
+ b'\r' => ([b'\\', b'r', 0, 0], 2),
+ b'\n' => ([b'\\', b'n', 0, 0], 2),
+ b'\\' => ([b'\\', b'\\', 0, 0], 2),
+ b'\'' => ([b'\\', b'\'', 0, 0], 2),
+ b'"' => ([b'\\', b'"', 0, 0], 2),
+ b'\x20' ... b'\x7e' => ([c, 0, 0, 0], 1),
+ _ => ([b'\\', b'x', hexify(c >> 4), hexify(c & 0xf)], 4),
+ };
+
+ return EscapeDefault { range: (0.. len), data: data };
+
+ fn hexify(b: u8) -> u8 {
+ match b {
+ 0 ... 9 => b'0' + b,
+ _ => b'a' + b - 10,
}
}
}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl Iterator for EscapeDefault {
+ type Item = u8;
+ fn next(&mut self) -> Option<u8> { self.range.next().map(|i| self.data[i]) }
+ fn size_hint(&self) -> (usize, Option<usize>) { self.range.size_hint() }
+}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl DoubleEndedIterator for EscapeDefault {
+ fn next_back(&mut self) -> Option<u8> {
+ self.range.next_back().map(|i| self.data[i])
+ }
+}
+#[stable(feature = "rust1", since = "1.0.0")]
+impl ExactSizeIterator for EscapeDefault {}
+
static ASCII_LOWERCASE_MAP: [u8; 256] = [
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
assert!("".is_ascii());
assert!("a".is_ascii());
assert!(!"\u{2009}".is_ascii());
-
}
#[test]
assert_eq!("url()URL()uRl()ürl".to_ascii_uppercase(), "URL()URL()URL()üRL");
assert_eq!("hıKß".to_ascii_uppercase(), "HıKß");
- let mut i = 0;
- while i <= 500 {
+ for i in 0..501 {
let upper = if 'a' as u32 <= i && i <= 'z' as u32 { i + 'A' as u32 - 'a' as u32 }
else { i };
assert_eq!((from_u32(i).unwrap()).to_string().to_ascii_uppercase(),
(from_u32(upper).unwrap()).to_string());
- i += 1;
}
}
// Dotted capital I, Kelvin sign, Sharp S.
assert_eq!("HİKß".to_ascii_lowercase(), "hİKß");
- let mut i = 0;
- while i <= 500 {
+ for i in 0..501 {
let lower = if 'A' as u32 <= i && i <= 'Z' as u32 { i + 'a' as u32 - 'A' as u32 }
else { i };
assert_eq!((from_u32(i).unwrap()).to_string().to_ascii_lowercase(),
(from_u32(lower).unwrap()).to_string());
- i += 1;
}
}
"URL()URL()URL()üRL".to_string());
assert_eq!(("hıKß".to_string()).into_ascii_uppercase(), "HıKß");
- let mut i = 0;
- while i <= 500 {
+ for i in 0..501 {
let upper = if 'a' as u32 <= i && i <= 'z' as u32 { i + 'A' as u32 - 'a' as u32 }
else { i };
assert_eq!((from_u32(i).unwrap()).to_string().into_ascii_uppercase(),
(from_u32(upper).unwrap()).to_string());
- i += 1;
}
}
// Dotted capital I, Kelvin sign, Sharp S.
assert_eq!(("HİKß".to_string()).into_ascii_lowercase(), "hİKß");
- let mut i = 0;
- while i <= 500 {
+ for i in 0..501 {
let lower = if 'A' as u32 <= i && i <= 'Z' as u32 { i + 'a' as u32 - 'A' as u32 }
else { i };
assert_eq!((from_u32(i).unwrap()).to_string().into_ascii_lowercase(),
(from_u32(lower).unwrap()).to_string());
- i += 1;
}
}
assert!(!"K".eq_ignore_ascii_case("k"));
assert!(!"ß".eq_ignore_ascii_case("s"));
- let mut i = 0;
- while i <= 500 {
- let c = i;
- let lower = if 'A' as u32 <= c && c <= 'Z' as u32 { c + 'a' as u32 - 'A' as u32 }
- else { c };
+ for i in 0..501 {
+ let lower = if 'A' as u32 <= i && i <= 'Z' as u32 { i + 'a' as u32 - 'A' as u32 }
+ else { i };
assert!((from_u32(i).unwrap()).to_string().eq_ignore_ascii_case(
- (from_u32(lower).unwrap()).to_string().as_slice()));
- i += 1;
+ &from_u32(lower).unwrap().to_string()));
}
}
}