mirror of
https://github.com/rust-lang/rust.git
synced 2025-05-14 02:49:40 +00:00
502 lines
16 KiB
Rust
502 lines
16 KiB
Rust
// Copyright 2013-2014 The Rust Project Developers. See the COPYRIGHT
|
||
// file at the top-level directory of this distribution and at
|
||
// http://rust-lang.org/COPYRIGHT.
|
||
//
|
||
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
|
||
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
|
||
// <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.
|
||
|
||
//! Operations on ASCII strings and characters.
|
||
//!
|
||
//! Most string operations in Rust act on UTF-8 strings. However, at times it
|
||
//! makes more sense to only consider the ASCII character set for a specific
|
||
//! operation.
|
||
//!
|
||
//! The [`escape_default`] function provides an iterator over the bytes of an
|
||
//! escaped version of the character given.
|
||
//!
|
||
//! [`escape_default`]: fn.escape_default.html
|
||
|
||
#![stable(feature = "rust1", since = "1.0.0")]
|
||
|
||
use fmt;
|
||
use ops::Range;
|
||
use iter::FusedIterator;
|
||
|
||
/// An iterator over the escaped version of a byte.
|
||
///
|
||
/// This `struct` is created by the [`escape_default`] function. See its
|
||
/// documentation for more.
|
||
///
|
||
/// [`escape_default`]: fn.escape_default.html
|
||
#[stable(feature = "core_ascii", since = "1.26.0")]
|
||
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
|
||
/// languages. The exact rules are:
|
||
///
|
||
/// * Tab is escaped as `\t`.
|
||
/// * Carriage return is escaped as `\r`.
|
||
/// * Line feed is escaped as `\n`.
|
||
/// * Single quote is escaped as `\'`.
|
||
/// * Double quote is escaped as `\"`.
|
||
/// * Backslash is escaped as `\\`.
|
||
/// * Any character in the 'printable ASCII' range `0x20` .. `0x7e`
|
||
/// inclusive is not escaped.
|
||
/// * Any other chars are given hex escapes of the form '\xNN'.
|
||
/// * Unicode escapes are never generated by this function.
|
||
///
|
||
/// # 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());
|
||
///
|
||
/// let mut escaped = ascii::escape_default(b'\r');
|
||
///
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
/// assert_eq!(b'r', escaped.next().unwrap());
|
||
///
|
||
/// let mut escaped = ascii::escape_default(b'\n');
|
||
///
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
/// assert_eq!(b'n', escaped.next().unwrap());
|
||
///
|
||
/// let mut escaped = ascii::escape_default(b'\'');
|
||
///
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
/// assert_eq!(b'\'', escaped.next().unwrap());
|
||
///
|
||
/// let mut escaped = ascii::escape_default(b'"');
|
||
///
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
/// assert_eq!(b'"', escaped.next().unwrap());
|
||
///
|
||
/// let mut escaped = ascii::escape_default(b'\\');
|
||
///
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
///
|
||
/// let mut escaped = ascii::escape_default(b'\x9d');
|
||
///
|
||
/// assert_eq!(b'\\', escaped.next().unwrap());
|
||
/// assert_eq!(b'x', escaped.next().unwrap());
|
||
/// assert_eq!(b'9', escaped.next().unwrap());
|
||
/// assert_eq!(b'd', escaped.next().unwrap());
|
||
/// ```
|
||
#[stable(feature = "core_ascii", since = "1.26.0")]
|
||
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 };
|
||
|
||
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 {}
|
||
#[unstable(feature = "fused", issue = "35602")]
|
||
impl FusedIterator for EscapeDefault {}
|
||
|
||
#[stable(feature = "std_debug", since = "1.16.0")]
|
||
impl fmt::Debug for EscapeDefault {
|
||
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
|
||
f.pad("EscapeDefault { .. }")
|
||
}
|
||
}
|
||
|
||
|
||
#[cfg(test)]
|
||
mod tests {
|
||
use char::from_u32;
|
||
|
||
#[test]
|
||
fn test_is_ascii() {
|
||
assert!(b"".is_ascii());
|
||
assert!(b"banana\0\x7F".is_ascii());
|
||
assert!(b"banana\0\x7F".iter().all(|b| b.is_ascii()));
|
||
assert!(!b"Vi\xe1\xbb\x87t Nam".is_ascii());
|
||
assert!(!b"Vi\xe1\xbb\x87t Nam".iter().all(|b| b.is_ascii()));
|
||
assert!(!b"\xe1\xbb\x87".iter().any(|b| b.is_ascii()));
|
||
|
||
assert!("".is_ascii());
|
||
assert!("banana\0\u{7F}".is_ascii());
|
||
assert!("banana\0\u{7F}".chars().all(|c| c.is_ascii()));
|
||
assert!(!"ประเทศไทย中华Việt Nam".chars().all(|c| c.is_ascii()));
|
||
assert!(!"ประเทศไทย中华ệ ".chars().any(|c| c.is_ascii()));
|
||
}
|
||
|
||
#[test]
|
||
fn test_to_ascii_uppercase() {
|
||
assert_eq!("url()URL()uRl()ürl".to_ascii_uppercase(), "URL()URL()URL()üRL");
|
||
assert_eq!("hıKß".to_ascii_uppercase(), "HıKß");
|
||
|
||
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());
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn test_to_ascii_lowercase() {
|
||
assert_eq!("url()URL()uRl()Ürl".to_ascii_lowercase(), "url()url()url()Ürl");
|
||
// Dotted capital I, Kelvin sign, Sharp S.
|
||
assert_eq!("HİKß".to_ascii_lowercase(), "hİKß");
|
||
|
||
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());
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn test_make_ascii_lower_case() {
|
||
macro_rules! test {
|
||
($from: expr, $to: expr) => {
|
||
{
|
||
let mut x = $from;
|
||
x.make_ascii_lowercase();
|
||
assert_eq!(x, $to);
|
||
}
|
||
}
|
||
}
|
||
test!(b'A', b'a');
|
||
test!(b'a', b'a');
|
||
test!(b'!', b'!');
|
||
test!('A', 'a');
|
||
test!('À', 'À');
|
||
test!('a', 'a');
|
||
test!('!', '!');
|
||
test!(b"H\xc3\x89".to_vec(), b"h\xc3\x89");
|
||
test!("HİKß".to_string(), "hİKß");
|
||
}
|
||
|
||
|
||
#[test]
|
||
fn test_make_ascii_upper_case() {
|
||
macro_rules! test {
|
||
($from: expr, $to: expr) => {
|
||
{
|
||
let mut x = $from;
|
||
x.make_ascii_uppercase();
|
||
assert_eq!(x, $to);
|
||
}
|
||
}
|
||
}
|
||
test!(b'a', b'A');
|
||
test!(b'A', b'A');
|
||
test!(b'!', b'!');
|
||
test!('a', 'A');
|
||
test!('à', 'à');
|
||
test!('A', 'A');
|
||
test!('!', '!');
|
||
test!(b"h\xc3\xa9".to_vec(), b"H\xc3\xa9");
|
||
test!("hıKß".to_string(), "HıKß");
|
||
|
||
let mut x = "Hello".to_string();
|
||
x[..3].make_ascii_uppercase(); // Test IndexMut on String.
|
||
assert_eq!(x, "HELlo")
|
||
}
|
||
|
||
#[test]
|
||
fn test_eq_ignore_ascii_case() {
|
||
assert!("url()URL()uRl()Ürl".eq_ignore_ascii_case("url()url()url()Ürl"));
|
||
assert!(!"Ürl".eq_ignore_ascii_case("ürl"));
|
||
// Dotted capital I, Kelvin sign, Sharp S.
|
||
assert!("HİKß".eq_ignore_ascii_case("hİKß"));
|
||
assert!(!"İ".eq_ignore_ascii_case("i"));
|
||
assert!(!"K".eq_ignore_ascii_case("k"));
|
||
assert!(!"ß".eq_ignore_ascii_case("s"));
|
||
|
||
for i in 0..501 {
|
||
let lower = if 'A' as u32 <= i && i <= 'Z' as u32 { i + 'a' as u32 - 'A' as u32 }
|
||
else { i };
|
||
assert!((from_u32(i).unwrap()).to_string().eq_ignore_ascii_case(
|
||
&from_u32(lower).unwrap().to_string()));
|
||
}
|
||
}
|
||
|
||
#[test]
|
||
fn inference_works() {
|
||
let x = "a".to_string();
|
||
x.eq_ignore_ascii_case("A");
|
||
}
|
||
|
||
// Shorthands used by the is_ascii_* tests.
|
||
macro_rules! assert_all {
|
||
($what:ident, $($str:tt),+) => {{
|
||
$(
|
||
for b in $str.chars() {
|
||
if !b.$what() {
|
||
panic!("expected {}({}) but it isn't",
|
||
stringify!($what), b);
|
||
}
|
||
}
|
||
for b in $str.as_bytes().iter() {
|
||
if !b.$what() {
|
||
panic!("expected {}(0x{:02x})) but it isn't",
|
||
stringify!($what), b);
|
||
}
|
||
}
|
||
assert!($str.$what());
|
||
assert!($str.as_bytes().$what());
|
||
)+
|
||
}};
|
||
($what:ident, $($str:tt),+,) => (assert_all!($what,$($str),+))
|
||
}
|
||
macro_rules! assert_none {
|
||
($what:ident, $($str:tt),+) => {{
|
||
$(
|
||
for b in $str.chars() {
|
||
if b.$what() {
|
||
panic!("expected not-{}({}) but it is",
|
||
stringify!($what), b);
|
||
}
|
||
}
|
||
for b in $str.as_bytes().iter() {
|
||
if b.$what() {
|
||
panic!("expected not-{}(0x{:02x})) but it is",
|
||
stringify!($what), b);
|
||
}
|
||
}
|
||
)*
|
||
}};
|
||
($what:ident, $($str:tt),+,) => (assert_none!($what,$($str),+))
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_alphabetic() {
|
||
assert_all!(is_ascii_alphabetic,
|
||
"",
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
);
|
||
assert_none!(is_ascii_alphabetic,
|
||
"0123456789",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_uppercase() {
|
||
assert_all!(is_ascii_uppercase,
|
||
"",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
);
|
||
assert_none!(is_ascii_uppercase,
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"0123456789",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_lowercase() {
|
||
assert_all!(is_ascii_lowercase,
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
);
|
||
assert_none!(is_ascii_lowercase,
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"0123456789",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_alphanumeric() {
|
||
assert_all!(is_ascii_alphanumeric,
|
||
"",
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"0123456789",
|
||
);
|
||
assert_none!(is_ascii_alphanumeric,
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_digit() {
|
||
assert_all!(is_ascii_digit,
|
||
"",
|
||
"0123456789",
|
||
);
|
||
assert_none!(is_ascii_digit,
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_hexdigit() {
|
||
assert_all!(is_ascii_hexdigit,
|
||
"",
|
||
"0123456789",
|
||
"abcdefABCDEF",
|
||
);
|
||
assert_none!(is_ascii_hexdigit,
|
||
"ghijklmnopqrstuvwxyz",
|
||
"GHIJKLMNOQPRSTUVWXYZ",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_punctuation() {
|
||
assert_all!(is_ascii_punctuation,
|
||
"",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
);
|
||
assert_none!(is_ascii_punctuation,
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"0123456789",
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_graphic() {
|
||
assert_all!(is_ascii_graphic,
|
||
"",
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"0123456789",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
);
|
||
assert_none!(is_ascii_graphic,
|
||
" \t\n\x0c\r",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_whitespace() {
|
||
assert_all!(is_ascii_whitespace,
|
||
"",
|
||
" \t\n\x0c\r",
|
||
);
|
||
assert_none!(is_ascii_whitespace,
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"0123456789",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x0b\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
}
|
||
|
||
#[test]
|
||
fn test_is_ascii_control() {
|
||
assert_all!(is_ascii_control,
|
||
"",
|
||
"\x00\x01\x02\x03\x04\x05\x06\x07",
|
||
"\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
|
||
"\x10\x11\x12\x13\x14\x15\x16\x17",
|
||
"\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f",
|
||
"\x7f",
|
||
);
|
||
assert_none!(is_ascii_control,
|
||
"abcdefghijklmnopqrstuvwxyz",
|
||
"ABCDEFGHIJKLMNOQPRSTUVWXYZ",
|
||
"0123456789",
|
||
"!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~",
|
||
" ",
|
||
);
|
||
}
|
||
}
|