servo/components/script/dom/bindings/str.rs

116 lines
2.8 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

/* This Source Code Form is subject to the terms of the Mozilla Public
* License, v. 2.0. If a copy of the MPL was not distributed with this
* file, You can obtain one at http://mozilla.org/MPL/2.0/. */
//! The `ByteString` struct.
use std::ascii::AsciiExt;
use std::borrow::ToOwned;
use std::hash::{Hash, Hasher};
use std::mem;
use std::ops;
use std::str;
use std::str::FromStr;
/// Encapsulates the IDL `ByteString` type.
#[derive(JSTraceable, Clone, Eq, PartialEq, HeapSizeOf)]
pub struct ByteString(Vec<u8>);
impl ByteString {
/// Creates a new `ByteString`.
pub fn new(value: Vec<u8>) -> ByteString {
ByteString(value)
}
/// Returns `self` as a string, if it encodes valid UTF-8, and `None`
/// otherwise.
pub fn as_str(&self) -> Option<&str> {
str::from_utf8(&self.0).ok()
}
/// Returns ownership of the underlying Vec<u8> and copies an empty
/// vec in its place
pub fn bytes(&mut self) -> Vec<u8> {
mem::replace(&mut self.0, Vec::new())
}
/// Returns the length.
pub fn len(&self) -> usize {
self.0.len()
}
/// Compare `self` to `other`, matching AZ and az as equal.
pub fn eq_ignore_case(&self, other: &ByteString) -> bool {
self.0.eq_ignore_ascii_case(&other.0)
}
/// Returns `self` with AZ replaced by az.
pub fn to_lower(&self) -> ByteString {
ByteString::new(self.0.to_ascii_lowercase())
}
}
impl Into<Vec<u8>> for ByteString {
fn into(self) -> Vec<u8> {
self.0
}
}
impl Hash for ByteString {
fn hash<H: Hasher>(&self, state: &mut H) {
self.0.hash(state);
}
}
impl FromStr for ByteString {
type Err = ();
fn from_str(s: &str) -> Result<ByteString, ()> {
Ok(ByteString::new(s.to_owned().into_bytes()))
}
}
impl ops::Deref for ByteString {
type Target = [u8];
fn deref(&self) -> &[u8] {
&self.0
}
}
/// A string that is constructed from a UCS-2 buffer by replacing invalid code
/// points with the replacement character.
pub struct USVString(pub String);
/// Returns whether `s` is a `token`, as defined by
/// [RFC 2616](http://tools.ietf.org/html/rfc2616#page-17).
pub fn is_token(s: &[u8]) -> bool {
if s.is_empty() {
return false; // A token must be at least a single character
}
s.iter().all(|&x| {
// http://tools.ietf.org/html/rfc2616#section-2.2
match x {
0...31 | 127 => false, // CTLs
40 |
41 |
60 |
62 |
64 |
44 |
59 |
58 |
92 |
34 |
47 |
91 |
93 |
63 |
61 |
123 |
125 |
32 => false, // separators
x if x > 127 => false, // non-CHARs
_ => true,
}
})
}