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
|
/* 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 html5ever::{LocalName, Namespace};
use servo_atoms::Atom;
use std::ascii::AsciiExt;
use std::borrow::{Borrow, Cow, ToOwned};
use std::fmt;
use std::hash::{Hash, Hasher};
use std::ops;
use std::ops::{Deref, DerefMut};
use std::str;
use std::str::{Bytes, FromStr};
/// Encapsulates the IDL `ByteString` type.
#[derive(JSTraceable, Clone, Eq, PartialEq, HeapSizeOf, Debug)]
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()
}
/// Compare `self` to `other`, matching A–Z and a–z as equal.
pub fn eq_ignore_case(&self, other: &ByteString) -> bool {
self.0.eq_ignore_ascii_case(&other.0)
}
/// Returns `self` with A–Z replaced by a–z.
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.
#[derive(Clone, HeapSizeOf)]
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,
}
})
}
/// A DOMString.
///
/// This type corresponds to the [`DOMString`](idl) type in WebIDL.
///
/// [idl]: https://heycam.github.io/webidl/#idl-DOMString
///
/// Cenceptually, 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.
/// In order to test this hypothesis, Servo will panic when encountering any
/// unpaired surrogates on conversion to `DOMString` by default. (The command
/// line option `-Z replace-surrogates` instead causes Servo to 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, HeapSizeOf, Ord, PartialEq, PartialOrd)]
pub struct DOMString(String);
impl !Send for DOMString {}
impl DOMString {
/// Creates a new `DOMString`.
pub fn new() -> DOMString {
DOMString(String::new())
}
/// Creates a new `DOMString` from a `String`.
pub fn from_string(s: String) -> DOMString {
DOMString(s)
}
/// 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);
}
/// An iterator over the bytes of this `DOMString`.
pub fn bytes(&self) -> Bytes {
self.0.bytes()
}
}
impl Borrow<str> for DOMString {
#[inline]
fn borrow(&self) -> &str {
&self.0
}
}
impl Default for DOMString {
fn default() -> Self {
DOMString(String::new())
}
}
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)
}
}
impl<'a> From<&'a 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 Into<Vec<u8>> for DOMString {
fn into(self) -> Vec<u8> {
self.0.into()
}
}
impl<'a> Into<Cow<'a, str>> for DOMString {
fn into(self) -> Cow<'a, str> {
self.0.into()
}
}
impl Extend<char> for DOMString {
fn extend<I>(&mut self, iterable: I) where I: IntoIterator<Item=char> {
self.0.extend(iterable)
}
}
|