script_bindings/str.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420
/* 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 https://mozilla.org/MPL/2.0/. */
//! The `ByteString` struct.
use std::borrow::{Borrow, Cow, ToOwned};
use std::default::Default;
use std::hash::{Hash, Hasher};
use std::marker::PhantomData;
use std::ops::{Deref, DerefMut};
use std::str::FromStr;
use std::sync::LazyLock;
use std::{fmt, ops, str};
use cssparser::CowRcStr;
use html5ever::{LocalName, Namespace};
use num_traits::Zero;
use regex::Regex;
use servo_atoms::Atom;
/// Encapsulates the IDL `ByteString` type.
#[derive(Clone, Debug, Default, Eq, JSTraceable, MallocSizeOf, PartialEq)]
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 the length.
pub fn len(&self) -> usize {
self.0.len()
}
/// Checks if the ByteString is empty.
pub fn is_empty(&self) -> bool {
self.0.is_empty()
}
/// Returns `self` with A–Z replaced by a–z.
pub fn to_lower(&self) -> ByteString {
ByteString::new(self.0.to_ascii_lowercase())
}
}
impl From<ByteString> for Vec<u8> {
fn from(byte_string: ByteString) -> Vec<u8> {
byte_string.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.
#[derive(Clone, Default, Eq, Hash, MallocSizeOf, Ord, PartialEq, PartialOrd)]
pub struct USVString(pub String);
impl Borrow<str> for USVString {
#[inline]
fn borrow(&self) -> &str {
&self.0
}
}
impl Deref for USVString {
type Target = str;
#[inline]
fn deref(&self) -> &str {
&self.0
}
}
impl DerefMut for USVString {
#[inline]
fn deref_mut(&mut self) -> &mut str {
&mut self.0
}
}
impl AsRef<str> for USVString {
fn as_ref(&self) -> &str {
&self.0
}
}
impl fmt::Display for USVString {
#[inline]
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
fmt::Display::fmt(&**self, f)
}
}
impl PartialEq<str> for USVString {
fn eq(&self, other: &str) -> bool {
&**self == other
}
}
impl<'a> PartialEq<&'a str> for USVString {
fn eq(&self, other: &&'a str) -> bool {
&**self == *other
}
}
impl From<String> for USVString {
fn from(contents: String) -> USVString {
USVString(contents)
}
}
/// 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,
}
})
}
/// A DOMString.
///
/// This type corresponds to the [`DOMString`] type in WebIDL.
///
/// [`DOMString`]: https://webidl.spec.whatwg.org/#idl-DOMString
///
/// Conceptually, a DOMString has the same value space as a JavaScript String,
/// i.e., an array of 16-bit *code units* representing UTF-16, potentially with
/// unpaired surrogates present (also sometimes called WTF-16).
///
/// Currently, this type stores a Rust `String`, in order to avoid issues when
/// integrating with the rest of the Rust ecosystem and even the rest of the
/// browser itself.
///
/// However, Rust `String`s are guaranteed to be valid UTF-8, and as such have
/// a *smaller value space* than WTF-16 (i.e., some JavaScript String values
/// can not be represented as a Rust `String`). This introduces the question of
/// what to do with values being passed from JavaScript to Rust that contain
/// unpaired surrogates.
///
/// The hypothesis is that it does not matter much how exactly those values are
/// transformed, because passing unpaired surrogates into the DOM is very rare.
/// Instead Servo withh replace the unpaired surrogate by a U+FFFD replacement
/// character.
///
/// Currently, the lack of crash reports about this issue provides some
/// evidence to support the hypothesis. This evidence will hopefully be used to
/// convince other browser vendors that it would be safe to replace unpaired
/// surrogates at the boundary between JavaScript and native code. (This would
/// unify the `DOMString` and `USVString` types, both in the WebIDL standard
/// and in Servo.)
///
/// This type is currently `!Send`, in order to help with an independent
/// experiment to store `JSString`s rather than Rust `String`s.
#[derive(Clone, Debug, Eq, Hash, MallocSizeOf, Ord, PartialEq, PartialOrd)]
pub struct DOMString(String, PhantomData<*const ()>);
impl DOMString {
/// Creates a new `DOMString`.
pub fn new() -> DOMString {
DOMString(String::new(), PhantomData)
}
/// Creates a new `DOMString` from a `String`.
pub fn from_string(s: String) -> DOMString {
DOMString(s, PhantomData)
}
/// Get the internal `&str` value of this [`DOMString`].
pub fn str(&self) -> &str {
&self.0
}
/// Appends a given string slice onto the end of this String.
pub fn push_str(&mut self, string: &str) {
self.0.push_str(string)
}
/// Clears this `DOMString`, removing all contents.
pub fn clear(&mut self) {
self.0.clear()
}
/// Shortens this String to the specified length.
pub fn truncate(&mut self, new_len: usize) {
self.0.truncate(new_len);
}
/// Removes newline characters according to <https://infra.spec.whatwg.org/#strip-newlines>.
pub fn strip_newlines(&mut self) {
self.0.retain(|c| c != '\r' && c != '\n');
}
/// Removes leading and trailing ASCII whitespaces according to
/// <https://infra.spec.whatwg.org/#strip-leading-and-trailing-ascii-whitespace>.
pub fn strip_leading_and_trailing_ascii_whitespace(&mut self) {
if self.0.is_empty() {
return;
}
let trailing_whitespace_len = self
.0
.trim_end_matches(|ref c| char::is_ascii_whitespace(c))
.len();
self.0.truncate(trailing_whitespace_len);
if self.0.is_empty() {
return;
}
let first_non_whitespace = self.0.find(|ref c| !char::is_ascii_whitespace(c)).unwrap();
self.0.replace_range(0..first_non_whitespace, "");
}
/// <https://html.spec.whatwg.org/multipage/#valid-floating-point-number>
pub fn is_valid_floating_point_number_string(&self) -> bool {
static RE: LazyLock<Regex> = LazyLock::new(|| {
Regex::new(r"^-?(?:\d+\.\d+|\d+|\.\d+)(?:(e|E)(\+|\-)?\d+)?$").unwrap()
});
RE.is_match(&self.0) && self.parse_floating_point_number().is_some()
}
/// <https://html.spec.whatwg.org/multipage/#rules-for-parsing-floating-point-number-values>
pub fn parse_floating_point_number(&self) -> Option<f64> {
// Steps 15-16 are telling us things about IEEE rounding modes
// for floating-point significands; this code assumes the Rust
// compiler already matches them in any cases where
// that actually matters. They are not
// related to f64::round(), which is for rounding to integers.
let input = &self.0;
if let Ok(val) = input.trim().parse::<f64>() {
if !(
// A valid number is the same as what rust considers to be valid,
// except for +1., NaN, and Infinity.
val.is_infinite() || val.is_nan() || input.ends_with('.') || input.starts_with('+')
) {
return Some(val);
}
}
None
}
/// Applies the same processing as `parse_floating_point_number` with some additional handling
/// according to ECMA's string conversion steps.
///
/// Used for specific elements when handling floating point values, namely the `number` and
/// `range` inputs, as well as `meter` and `progress` elements.
///
/// <https://html.spec.whatwg.org/multipage/#best-representation-of-the-number-as-a-floating-point-number>
/// <https://tc39.es/ecma262/#sec-numeric-types-number-tostring>
pub fn set_best_representation_of_the_floating_point_number(&mut self) {
if let Some(val) = self.parse_floating_point_number() {
// [tc39] Step 2: If x is either +0 or -0, return "0".
let parsed_value = if val.is_zero() { 0.0_f64 } else { val };
self.0 = parsed_value.to_string()
}
}
}
impl Borrow<str> for DOMString {
#[inline]
fn borrow(&self) -> &str {
&self.0
}
}
impl Default for DOMString {
fn default() -> Self {
DOMString(String::new(), PhantomData)
}
}
impl Deref for DOMString {
type Target = str;
#[inline]
fn deref(&self) -> &str {
&self.0
}
}
impl DerefMut for DOMString {
#[inline]
fn deref_mut(&mut self) -> &mut str {
&mut self.0
}
}
impl AsRef<str> for DOMString {
fn as_ref(&self) -> &str {
&self.0
}
}
impl fmt::Display for DOMString {
#[inline]
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
fmt::Display::fmt(&**self, f)
}
}
impl PartialEq<str> for DOMString {
fn eq(&self, other: &str) -> bool {
&**self == other
}
}
impl<'a> PartialEq<&'a str> for DOMString {
fn eq(&self, other: &&'a str) -> bool {
&**self == *other
}
}
impl From<String> for DOMString {
fn from(contents: String) -> DOMString {
DOMString(contents, PhantomData)
}
}
impl From<&str> for DOMString {
fn from(contents: &str) -> DOMString {
DOMString::from(String::from(contents))
}
}
impl<'a> From<Cow<'a, str>> for DOMString {
fn from(contents: Cow<'a, str>) -> DOMString {
match contents {
Cow::Owned(s) => DOMString::from(s),
Cow::Borrowed(s) => DOMString::from(s),
}
}
}
impl From<DOMString> for LocalName {
fn from(contents: DOMString) -> LocalName {
LocalName::from(contents.0)
}
}
impl From<DOMString> for Namespace {
fn from(contents: DOMString) -> Namespace {
Namespace::from(contents.0)
}
}
impl From<DOMString> for Atom {
fn from(contents: DOMString) -> Atom {
Atom::from(contents.0)
}
}
impl From<DOMString> for String {
fn from(contents: DOMString) -> String {
contents.0
}
}
impl From<DOMString> for Vec<u8> {
fn from(contents: DOMString) -> Vec<u8> {
contents.0.into()
}
}
impl<'a> From<DOMString> for Cow<'a, str> {
fn from(contents: DOMString) -> Cow<'a, str> {
contents.0.into()
}
}
impl<'a> From<DOMString> for CowRcStr<'a> {
fn from(contents: DOMString) -> CowRcStr<'a> {
contents.0.into()
}
}
impl Extend<char> for DOMString {
fn extend<I>(&mut self, iterable: I)
where
I: IntoIterator<Item = char>,
{
self.0.extend(iterable)
}
}