std: Stabilize the ascii module
This commit performs a stabilization pass over the `std::ascii` module taking the following actions: * the module name is now stable * `AsciiExt` is now stable after moving its type parameter to an `Owned` associated type * `AsciiExt::is_ascii` is now stable * `AsciiExt::to_ascii_uppercase` is now stable * `AsciiExt::to_ascii_lowercase` is now stable * `AsciiExt::eq_ignore_ascii_case` is now stable * `AsciiExt::make_ascii_uppercase` is added to possibly replace `OwnedAsciiExt::into_ascii_uppercase` (similarly for lowercase variants). * `escape_default` now returns an iterator and is stable * `EscapeDefault` is now stable Trait implementations are now also marked stable. Primarily it is still unstable to *implement* the `AsciiExt` trait due to it containing some unstable methods. [breaking-change]
This commit is contained in:
Alex Crichton
parent
0cf2d00f0e
commit
235f35b0b7
@ -12,15 +12,12 @@
|
||||
|
||||
//! Operations on ASCII strings and characters
|
||||
|
||||
#![unstable(feature = "std_misc",
|
||||
reason = "unsure about placement and naming")]
|
||||
#![stable(feature = "rust1", since = "1.0.0")]
|
||||
|
||||
use iter::IteratorExt;
|
||||
use ops::FnMut;
|
||||
use slice::SliceExt;
|
||||
use str::StrExt;
|
||||
use string::String;
|
||||
use vec::Vec;
|
||||
use prelude::v1::*;
|
||||
|
||||
use mem;
|
||||
use iter::Range;
|
||||
|
||||
/// Extension methods for ASCII-subset only operations on owned strings
|
||||
#[unstable(feature = "std_misc",
|
||||
@ -38,31 +35,50 @@ pub trait OwnedAsciiExt {
|
||||
}
|
||||
|
||||
/// Extension methods for ASCII-subset only operations on string slices
|
||||
#[unstable(feature = "std_misc",
|
||||
reason = "would prefer to do this in a more general way")]
|
||||
pub trait AsciiExt<T = Self> {
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
pub trait AsciiExt {
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
type Owned;
|
||||
|
||||
/// Check if within the ASCII range.
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
fn is_ascii(&self) -> bool;
|
||||
|
||||
/// 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;
|
||||
#[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;
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
fn to_ascii_lowercase(&self) -> Self::Owned;
|
||||
|
||||
/// Check 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.
|
||||
#[stable(feature = "rust1", since = "1.0.0")]
|
||||
fn eq_ignore_ascii_case(&self, other: &Self) -> bool;
|
||||
|
||||
/// Convert this type to its ASCII upper case equivalent in-place.
|
||||
///
|
||||
/// See `to_ascii_uppercase` for more information.
|
||||
#[unstable(feature = "ascii")]
|
||||
fn make_ascii_uppercase(&mut self);
|
||||
|
||||
/// Convert this type to its ASCII lower case equivalent in-place.
|
||||
///
|
||||
/// See `to_ascii_lowercase` for more information.
|
||||
#[unstable(feature = "ascii")]
|
||||
fn make_ascii_lowercase(&mut self);
|
||||
}
|
||||
|
||||
#[unstable(feature = "std_misc",
|
||||
reason = "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())
|
||||
@ -70,20 +86,28 @@ fn is_ascii(&self) -> bool {
|
||||
|
||||
#[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(feature = "std_misc",
|
||||
@ -102,9 +126,9 @@ fn into_ascii_lowercase(self) -> String {
|
||||
}
|
||||
}
|
||||
|
||||
#[unstable(feature = "std_misc",
|
||||
reason = "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())
|
||||
@ -112,12 +136,12 @@ fn is_ascii(&self) -> bool {
|
||||
|
||||
#[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]
|
||||
@ -127,6 +151,18 @@ fn eq_ignore_ascii_case(&self, other: &[u8]) -> bool {
|
||||
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(feature = "std_misc",
|
||||
@ -134,48 +170,39 @@ fn eq_ignore_ascii_case(&self, other: &[u8]) -> bool {
|
||||
impl OwnedAsciiExt for Vec<u8> {
|
||||
#[inline]
|
||||
fn into_ascii_uppercase(mut self) -> Vec<u8> {
|
||||
for byte in &mut self {
|
||||
*byte = byte.to_ascii_uppercase();
|
||||
}
|
||||
self.make_ascii_uppercase();
|
||||
self
|
||||
}
|
||||
|
||||
#[inline]
|
||||
fn into_ascii_lowercase(mut self) -> Vec<u8> {
|
||||
for byte in &mut self {
|
||||
*byte = byte.to_ascii_lowercase();
|
||||
}
|
||||
self.make_ascii_lowercase();
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
#[unstable(feature = "std_misc",
|
||||
reason = "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 == 0u8 }
|
||||
#[inline]
|
||||
fn to_ascii_uppercase(&self) -> u8 {
|
||||
ASCII_UPPERCASE_MAP[*self as usize]
|
||||
}
|
||||
|
||||
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]
|
||||
}
|
||||
|
||||
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(feature = "std_misc",
|
||||
reason = "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
|
||||
@ -203,6 +230,19 @@ fn to_ascii_lowercase(&self) -> char {
|
||||
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(); }
|
||||
}
|
||||
|
||||
/// 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 a 'default' ASCII and C++11-like literal escape of a `u8`
|
||||
@ -214,34 +254,46 @@ fn eq_ignore_ascii_case(&self, other: &char) -> bool {
|
||||
/// - 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(feature = "std_misc",
|
||||
reason = "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] {
|
||||
match ((c as i32) >> offset) & 0xf {
|
||||
i @ 0 ... 9 => f(b'0' + (i as u8)),
|
||||
i => f(b'a' + (i as u8 - 10)),
|
||||
}
|
||||
}
|
||||
#[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: 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,
|
||||
|
||||
@ -817,7 +817,9 @@ fn hash(&self, state: &mut S) {
|
||||
}
|
||||
}
|
||||
|
||||
impl AsciiExt<Wtf8Buf> for Wtf8 {
|
||||
impl AsciiExt for Wtf8 {
|
||||
type Owned = Wtf8Buf;
|
||||
|
||||
fn is_ascii(&self) -> bool {
|
||||
self.bytes.is_ascii()
|
||||
}
|
||||
@ -830,6 +832,9 @@ fn to_ascii_lowercase(&self) -> Wtf8Buf {
|
||||
fn eq_ignore_ascii_case(&self, other: &Wtf8) -> bool {
|
||||
self.bytes.eq_ignore_ascii_case(&other.bytes)
|
||||
}
|
||||
|
||||
fn make_ascii_uppercase(&mut self) { self.bytes.make_ascii_uppercase() }
|
||||
fn make_ascii_lowercase(&mut self) { self.bytes.make_ascii_lowercase() }
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
|
||||
@ -2761,15 +2761,13 @@ pub fn print_literal(&mut self, lit: &ast::Lit) -> IoResult<()> {
|
||||
ast::LitStr(ref st, style) => self.print_string(&st, style),
|
||||
ast::LitByte(byte) => {
|
||||
let mut res = String::from_str("b'");
|
||||
ascii::escape_default(byte, |c| res.push(c as char));
|
||||
res.extend(ascii::escape_default(byte).map(|c| c as char));
|
||||
res.push('\'');
|
||||
word(&mut self.s, &res[])
|
||||
}
|
||||
ast::LitChar(ch) => {
|
||||
let mut res = String::from_str("'");
|
||||
for c in ch.escape_default() {
|
||||
res.push(c);
|
||||
}
|
||||
res.extend(ch.escape_default());
|
||||
res.push('\'');
|
||||
word(&mut self.s, &res[])
|
||||
}
|
||||
@ -2809,8 +2807,8 @@ pub fn print_literal(&mut self, lit: &ast::Lit) -> IoResult<()> {
|
||||
ast::LitBinary(ref v) => {
|
||||
let mut escaped: String = String::new();
|
||||
for &ch in &**v {
|
||||
ascii::escape_default(ch as u8,
|
||||
|ch| escaped.push(ch as char));
|
||||
escaped.extend(ascii::escape_default(ch as u8)
|
||||
.map(|c| c as char));
|
||||
}
|
||||
word(&mut self.s, &format!("b\"{}\"", escaped)[])
|
||||
}
|
||||
|
||||
@ -58,7 +58,6 @@
|
||||
#![feature(path)]
|
||||
#![feature(rustc_private)]
|
||||
#![feature(staged_api)]
|
||||
#![feature(std_misc)]
|
||||
#![feature(unicode)]
|
||||
#![feature(env)]
|
||||
#![cfg_attr(windows, feature(libc))]
|
||||
|
||||
Loading…
Reference in New Issue
Block a user