-
Notifications
You must be signed in to change notification settings - Fork 12.7k
/
mod.rs
4625 lines (4359 loc) · 144 KB
/
mod.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
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// ignore-tidy-filelength
//! String manipulation.
//!
//! For more details, see the `std::str` module.
#![stable(feature = "rust1", since = "1.0.0")]
use self::pattern::Pattern;
use self::pattern::{DoubleEndedSearcher, ReverseSearcher, SearchStep, Searcher};
use crate::char;
use crate::fmt::{self, Write};
use crate::iter::{Chain, FlatMap, Flatten};
use crate::iter::{Cloned, Filter, FusedIterator, Map, TrustedLen, TrustedRandomAccess};
use crate::mem;
use crate::ops::Try;
use crate::option;
use crate::slice::{self, SliceIndex, Split as SliceSplit};
pub mod pattern;
#[unstable(feature = "str_internals", issue = "none")]
#[allow(missing_docs)]
pub mod lossy;
/// Parse a value from a string
///
/// `FromStr`'s [`from_str`] method is often used implicitly, through
/// [`str`]'s [`parse`] method. See [`parse`]'s documentation for examples.
///
/// [`from_str`]: #tymethod.from_str
/// [`str`]: ../../std/primitive.str.html
/// [`parse`]: ../../std/primitive.str.html#method.parse
///
/// `FromStr` does not have a lifetime parameter, and so you can only parse types
/// that do not contain a lifetime parameter themselves. In other words, you can
/// parse an `i32` with `FromStr`, but not a `&i32`. You can parse a struct that
/// contains an `i32`, but not one that contains an `&i32`.
///
/// # Examples
///
/// Basic implementation of `FromStr` on an example `Point` type:
///
/// ```
/// use std::str::FromStr;
/// use std::num::ParseIntError;
///
/// #[derive(Debug, PartialEq)]
/// struct Point {
/// x: i32,
/// y: i32
/// }
///
/// impl FromStr for Point {
/// type Err = ParseIntError;
///
/// fn from_str(s: &str) -> Result<Self, Self::Err> {
/// let coords: Vec<&str> = s.trim_matches(|p| p == '(' || p == ')' )
/// .split(',')
/// .collect();
///
/// let x_fromstr = coords[0].parse::<i32>()?;
/// let y_fromstr = coords[1].parse::<i32>()?;
///
/// Ok(Point { x: x_fromstr, y: y_fromstr })
/// }
/// }
///
/// let p = Point::from_str("(1,2)");
/// assert_eq!(p.unwrap(), Point{ x: 1, y: 2} )
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub trait FromStr: Sized {
/// The associated error which can be returned from parsing.
#[stable(feature = "rust1", since = "1.0.0")]
type Err;
/// Parses a string `s` to return a value of this type.
///
/// If parsing succeeds, return the value inside [`Ok`], otherwise
/// when the string is ill-formatted return an error specific to the
/// inside [`Err`]. The error type is specific to implementation of the trait.
///
/// [`Ok`]: ../../std/result/enum.Result.html#variant.Ok
/// [`Err`]: ../../std/result/enum.Result.html#variant.Err
///
/// # Examples
///
/// Basic usage with [`i32`][ithirtytwo], a type that implements `FromStr`:
///
/// [ithirtytwo]: ../../std/primitive.i32.html
///
/// ```
/// use std::str::FromStr;
///
/// let s = "5";
/// let x = i32::from_str(s).unwrap();
///
/// assert_eq!(5, x);
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
fn from_str(s: &str) -> Result<Self, Self::Err>;
}
#[stable(feature = "rust1", since = "1.0.0")]
impl FromStr for bool {
type Err = ParseBoolError;
/// Parse a `bool` from a string.
///
/// Yields a `Result<bool, ParseBoolError>`, because `s` may or may not
/// actually be parseable.
///
/// # Examples
///
/// ```
/// use std::str::FromStr;
///
/// assert_eq!(FromStr::from_str("true"), Ok(true));
/// assert_eq!(FromStr::from_str("false"), Ok(false));
/// assert!(<bool as FromStr>::from_str("not even a boolean").is_err());
/// ```
///
/// Note, in many cases, the `.parse()` method on `str` is more proper.
///
/// ```
/// assert_eq!("true".parse(), Ok(true));
/// assert_eq!("false".parse(), Ok(false));
/// assert!("not even a boolean".parse::<bool>().is_err());
/// ```
#[inline]
fn from_str(s: &str) -> Result<bool, ParseBoolError> {
match s {
"true" => Ok(true),
"false" => Ok(false),
_ => Err(ParseBoolError { _priv: () }),
}
}
}
/// An error returned when parsing a `bool` using [`from_str`] fails
///
/// [`from_str`]: ../../std/primitive.bool.html#method.from_str
#[derive(Debug, Clone, PartialEq, Eq)]
#[stable(feature = "rust1", since = "1.0.0")]
pub struct ParseBoolError {
_priv: (),
}
#[stable(feature = "rust1", since = "1.0.0")]
impl fmt::Display for ParseBoolError {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
"provided string was not `true` or `false`".fmt(f)
}
}
/*
Section: Creating a string
*/
/// Errors which can occur when attempting to interpret a sequence of [`u8`]
/// as a string.
///
/// [`u8`]: ../../std/primitive.u8.html
///
/// As such, the `from_utf8` family of functions and methods for both [`String`]s
/// and [`&str`]s make use of this error, for example.
///
/// [`String`]: ../../std/string/struct.String.html#method.from_utf8
/// [`&str`]: ../../std/str/fn.from_utf8.html
///
/// # Examples
///
/// This error type’s methods can be used to create functionality
/// similar to `String::from_utf8_lossy` without allocating heap memory:
///
/// ```
/// fn from_utf8_lossy<F>(mut input: &[u8], mut push: F) where F: FnMut(&str) {
/// loop {
/// match std::str::from_utf8(input) {
/// Ok(valid) => {
/// push(valid);
/// break
/// }
/// Err(error) => {
/// let (valid, after_valid) = input.split_at(error.valid_up_to());
/// unsafe {
/// push(std::str::from_utf8_unchecked(valid))
/// }
/// push("\u{FFFD}");
///
/// if let Some(invalid_sequence_length) = error.error_len() {
/// input = &after_valid[invalid_sequence_length..]
/// } else {
/// break
/// }
/// }
/// }
/// }
/// }
/// ```
#[derive(Copy, Eq, PartialEq, Clone, Debug)]
#[stable(feature = "rust1", since = "1.0.0")]
pub struct Utf8Error {
valid_up_to: usize,
error_len: Option<u8>,
}
impl Utf8Error {
/// Returns the index in the given string up to which valid UTF-8 was
/// verified.
///
/// It is the maximum index such that `from_utf8(&input[..index])`
/// would return `Ok(_)`.
///
/// # Examples
///
/// Basic usage:
///
/// ```
/// use std::str;
///
/// // some invalid bytes, in a vector
/// let sparkle_heart = vec![0, 159, 146, 150];
///
/// // std::str::from_utf8 returns a Utf8Error
/// let error = str::from_utf8(&sparkle_heart).unwrap_err();
///
/// // the second byte is invalid here
/// assert_eq!(1, error.valid_up_to());
/// ```
#[stable(feature = "utf8_error", since = "1.5.0")]
pub fn valid_up_to(&self) -> usize {
self.valid_up_to
}
/// Provides more information about the failure:
///
/// * `None`: the end of the input was reached unexpectedly.
/// `self.valid_up_to()` is 1 to 3 bytes from the end of the input.
/// If a byte stream (such as a file or a network socket) is being decoded incrementally,
/// this could be a valid `char` whose UTF-8 byte sequence is spanning multiple chunks.
///
/// * `Some(len)`: an unexpected byte was encountered.
/// The length provided is that of the invalid byte sequence
/// that starts at the index given by `valid_up_to()`.
/// Decoding should resume after that sequence
/// (after inserting a [`U+FFFD REPLACEMENT CHARACTER`][U+FFFD]) in case of
/// lossy decoding.
///
/// [U+FFFD]: ../../std/char/constant.REPLACEMENT_CHARACTER.html
#[stable(feature = "utf8_error_error_len", since = "1.20.0")]
pub fn error_len(&self) -> Option<usize> {
self.error_len.map(|len| len as usize)
}
}
/// Converts a slice of bytes to a string slice.
///
/// A string slice ([`&str`]) is made of bytes ([`u8`]), and a byte slice
/// ([`&[u8]`][byteslice]) is made of bytes, so this function converts between
/// the two. Not all byte slices are valid string slices, however: [`&str`] requires
/// that it is valid UTF-8. `from_utf8()` checks to ensure that the bytes are valid
/// UTF-8, and then does the conversion.
///
/// [`&str`]: ../../std/primitive.str.html
/// [`u8`]: ../../std/primitive.u8.html
/// [byteslice]: ../../std/primitive.slice.html
///
/// If you are sure that the byte slice is valid UTF-8, and you don't want to
/// incur the overhead of the validity check, there is an unsafe version of
/// this function, [`from_utf8_unchecked`][fromutf8u], which has the same
/// behavior but skips the check.
///
/// [fromutf8u]: fn.from_utf8_unchecked.html
///
/// If you need a `String` instead of a `&str`, consider
/// [`String::from_utf8`][string].
///
/// [string]: ../../std/string/struct.String.html#method.from_utf8
///
/// Because you can stack-allocate a `[u8; N]`, and you can take a
/// [`&[u8]`][byteslice] of it, this function is one way to have a
/// stack-allocated string. There is an example of this in the
/// examples section below.
///
/// [byteslice]: ../../std/primitive.slice.html
///
/// # Errors
///
/// Returns `Err` if the slice is not UTF-8 with a description as to why the
/// provided slice is not UTF-8.
///
/// # Examples
///
/// Basic usage:
///
/// ```
/// use std::str;
///
/// // some bytes, in a vector
/// let sparkle_heart = vec![240, 159, 146, 150];
///
/// // We know these bytes are valid, so just use `unwrap()`.
/// let sparkle_heart = str::from_utf8(&sparkle_heart).unwrap();
///
/// assert_eq!("💖", sparkle_heart);
/// ```
///
/// Incorrect bytes:
///
/// ```
/// use std::str;
///
/// // some invalid bytes, in a vector
/// let sparkle_heart = vec![0, 159, 146, 150];
///
/// assert!(str::from_utf8(&sparkle_heart).is_err());
/// ```
///
/// See the docs for [`Utf8Error`][error] for more details on the kinds of
/// errors that can be returned.
///
/// [error]: struct.Utf8Error.html
///
/// A "stack allocated string":
///
/// ```
/// use std::str;
///
/// // some bytes, in a stack-allocated array
/// let sparkle_heart = [240, 159, 146, 150];
///
/// // We know these bytes are valid, so just use `unwrap()`.
/// let sparkle_heart = str::from_utf8(&sparkle_heart).unwrap();
///
/// assert_eq!("💖", sparkle_heart);
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub fn from_utf8(v: &[u8]) -> Result<&str, Utf8Error> {
run_utf8_validation(v)?;
// SAFETY: Just ran validation.
Ok(unsafe { from_utf8_unchecked(v) })
}
/// Converts a mutable slice of bytes to a mutable string slice.
///
/// # Examples
///
/// Basic usage:
///
/// ```
/// use std::str;
///
/// // "Hello, Rust!" as a mutable vector
/// let mut hellorust = vec![72, 101, 108, 108, 111, 44, 32, 82, 117, 115, 116, 33];
///
/// // As we know these bytes are valid, we can use `unwrap()`
/// let outstr = str::from_utf8_mut(&mut hellorust).unwrap();
///
/// assert_eq!("Hello, Rust!", outstr);
/// ```
///
/// Incorrect bytes:
///
/// ```
/// use std::str;
///
/// // Some invalid bytes in a mutable vector
/// let mut invalid = vec![128, 223];
///
/// assert!(str::from_utf8_mut(&mut invalid).is_err());
/// ```
/// See the docs for [`Utf8Error`][error] for more details on the kinds of
/// errors that can be returned.
///
/// [error]: struct.Utf8Error.html
#[stable(feature = "str_mut_extras", since = "1.20.0")]
pub fn from_utf8_mut(v: &mut [u8]) -> Result<&mut str, Utf8Error> {
run_utf8_validation(v)?;
// SAFETY: Just ran validation.
Ok(unsafe { from_utf8_unchecked_mut(v) })
}
/// Converts a slice of bytes to a string slice without checking
/// that the string contains valid UTF-8.
///
/// See the safe version, [`from_utf8`][fromutf8], for more information.
///
/// [fromutf8]: fn.from_utf8.html
///
/// # Safety
///
/// This function is unsafe because it does not check that the bytes passed to
/// it are valid UTF-8. If this constraint is violated, undefined behavior
/// results, as the rest of Rust assumes that [`&str`]s are valid UTF-8.
///
/// [`&str`]: ../../std/primitive.str.html
///
/// # Examples
///
/// Basic usage:
///
/// ```
/// use std::str;
///
/// // some bytes, in a vector
/// let sparkle_heart = vec![240, 159, 146, 150];
///
/// let sparkle_heart = unsafe {
/// str::from_utf8_unchecked(&sparkle_heart)
/// };
///
/// assert_eq!("💖", sparkle_heart);
/// ```
#[inline]
#[stable(feature = "rust1", since = "1.0.0")]
pub unsafe fn from_utf8_unchecked(v: &[u8]) -> &str {
&*(v as *const [u8] as *const str)
}
/// Converts a slice of bytes to a string slice without checking
/// that the string contains valid UTF-8; mutable version.
///
/// See the immutable version, [`from_utf8_unchecked()`][fromutf8], for more information.
///
/// [fromutf8]: fn.from_utf8_unchecked.html
///
/// # Examples
///
/// Basic usage:
///
/// ```
/// use std::str;
///
/// let mut heart = vec![240, 159, 146, 150];
/// let heart = unsafe { str::from_utf8_unchecked_mut(&mut heart) };
///
/// assert_eq!("💖", heart);
/// ```
#[inline]
#[stable(feature = "str_mut_extras", since = "1.20.0")]
pub unsafe fn from_utf8_unchecked_mut(v: &mut [u8]) -> &mut str {
&mut *(v as *mut [u8] as *mut str)
}
#[stable(feature = "rust1", since = "1.0.0")]
impl fmt::Display for Utf8Error {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
if let Some(error_len) = self.error_len {
write!(
f,
"invalid utf-8 sequence of {} bytes from index {}",
error_len, self.valid_up_to
)
} else {
write!(f, "incomplete utf-8 byte sequence from index {}", self.valid_up_to)
}
}
}
/*
Section: Iterators
*/
/// An iterator over the [`char`]s of a string slice.
///
/// [`char`]: ../../std/primitive.char.html
///
/// This struct is created by the [`chars`] method on [`str`].
/// See its documentation for more.
///
/// [`chars`]: ../../std/primitive.str.html#method.chars
/// [`str`]: ../../std/primitive.str.html
#[derive(Clone)]
#[stable(feature = "rust1", since = "1.0.0")]
pub struct Chars<'a> {
iter: slice::Iter<'a, u8>,
}
/// Returns the initial codepoint accumulator for the first byte.
/// The first byte is special, only want bottom 5 bits for width 2, 4 bits
/// for width 3, and 3 bits for width 4.
#[inline]
fn utf8_first_byte(byte: u8, width: u32) -> u32 {
(byte & (0x7F >> width)) as u32
}
/// Returns the value of `ch` updated with continuation byte `byte`.
#[inline]
fn utf8_acc_cont_byte(ch: u32, byte: u8) -> u32 {
(ch << 6) | (byte & CONT_MASK) as u32
}
/// Checks whether the byte is a UTF-8 continuation byte (i.e., starts with the
/// bits `10`).
#[inline]
fn utf8_is_cont_byte(byte: u8) -> bool {
(byte & !CONT_MASK) == TAG_CONT_U8
}
#[inline]
fn unwrap_or_0(opt: Option<&u8>) -> u8 {
match opt {
Some(&byte) => byte,
None => 0,
}
}
/// Reads the next code point out of a byte iterator (assuming a
/// UTF-8-like encoding).
#[unstable(feature = "str_internals", issue = "none")]
#[inline]
pub fn next_code_point<'a, I: Iterator<Item = &'a u8>>(bytes: &mut I) -> Option<u32> {
// Decode UTF-8
let x = *bytes.next()?;
if x < 128 {
return Some(x as u32);
}
// Multibyte case follows
// Decode from a byte combination out of: [[[x y] z] w]
// NOTE: Performance is sensitive to the exact formulation here
let init = utf8_first_byte(x, 2);
let y = unwrap_or_0(bytes.next());
let mut ch = utf8_acc_cont_byte(init, y);
if x >= 0xE0 {
// [[x y z] w] case
// 5th bit in 0xE0 .. 0xEF is always clear, so `init` is still valid
let z = unwrap_or_0(bytes.next());
let y_z = utf8_acc_cont_byte((y & CONT_MASK) as u32, z);
ch = init << 12 | y_z;
if x >= 0xF0 {
// [x y z w] case
// use only the lower 3 bits of `init`
let w = unwrap_or_0(bytes.next());
ch = (init & 7) << 18 | utf8_acc_cont_byte(y_z, w);
}
}
Some(ch)
}
/// Reads the last code point out of a byte iterator (assuming a
/// UTF-8-like encoding).
#[inline]
fn next_code_point_reverse<'a, I>(bytes: &mut I) -> Option<u32>
where
I: DoubleEndedIterator<Item = &'a u8>,
{
// Decode UTF-8
let w = match *bytes.next_back()? {
next_byte if next_byte < 128 => return Some(next_byte as u32),
back_byte => back_byte,
};
// Multibyte case follows
// Decode from a byte combination out of: [x [y [z w]]]
let mut ch;
let z = unwrap_or_0(bytes.next_back());
ch = utf8_first_byte(z, 2);
if utf8_is_cont_byte(z) {
let y = unwrap_or_0(bytes.next_back());
ch = utf8_first_byte(y, 3);
if utf8_is_cont_byte(y) {
let x = unwrap_or_0(bytes.next_back());
ch = utf8_first_byte(x, 4);
ch = utf8_acc_cont_byte(ch, y);
}
ch = utf8_acc_cont_byte(ch, z);
}
ch = utf8_acc_cont_byte(ch, w);
Some(ch)
}
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> Iterator for Chars<'a> {
type Item = char;
#[inline]
fn next(&mut self) -> Option<char> {
next_code_point(&mut self.iter).map(|ch| {
// SAFETY: `str` invariant says `ch` is a valid Unicode Scalar Value.
unsafe { char::from_u32_unchecked(ch) }
})
}
#[inline]
fn count(self) -> usize {
// length in `char` is equal to the number of non-continuation bytes
let bytes_len = self.iter.len();
let mut cont_bytes = 0;
for &byte in self.iter {
cont_bytes += utf8_is_cont_byte(byte) as usize;
}
bytes_len - cont_bytes
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
let len = self.iter.len();
// `(len + 3)` can't overflow, because we know that the `slice::Iter`
// belongs to a slice in memory which has a maximum length of
// `isize::MAX` (that's well below `usize::MAX`).
((len + 3) / 4, Some(len))
}
#[inline]
fn last(mut self) -> Option<char> {
// No need to go through the entire string.
self.next_back()
}
}
#[stable(feature = "chars_debug_impl", since = "1.38.0")]
impl fmt::Debug for Chars<'_> {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
write!(f, "Chars(")?;
f.debug_list().entries(self.clone()).finish()?;
write!(f, ")")?;
Ok(())
}
}
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> DoubleEndedIterator for Chars<'a> {
#[inline]
fn next_back(&mut self) -> Option<char> {
next_code_point_reverse(&mut self.iter).map(|ch| {
// SAFETY: `str` invariant says `ch` is a valid Unicode Scalar Value.
unsafe { char::from_u32_unchecked(ch) }
})
}
}
#[stable(feature = "fused", since = "1.26.0")]
impl FusedIterator for Chars<'_> {}
impl<'a> Chars<'a> {
/// Views the underlying data as a subslice of the original data.
///
/// This has the same lifetime as the original slice, and so the
/// iterator can continue to be used while this exists.
///
/// # Examples
///
/// ```
/// let mut chars = "abc".chars();
///
/// assert_eq!(chars.as_str(), "abc");
/// chars.next();
/// assert_eq!(chars.as_str(), "bc");
/// chars.next();
/// chars.next();
/// assert_eq!(chars.as_str(), "");
/// ```
#[stable(feature = "iter_to_slice", since = "1.4.0")]
#[inline]
pub fn as_str(&self) -> &'a str {
// SAFETY: `Chars` is only made from a str, which guarantees the iter is valid UTF-8.
unsafe { from_utf8_unchecked(self.iter.as_slice()) }
}
}
/// An iterator over the [`char`]s of a string slice, and their positions.
///
/// [`char`]: ../../std/primitive.char.html
///
/// This struct is created by the [`char_indices`] method on [`str`].
/// See its documentation for more.
///
/// [`char_indices`]: ../../std/primitive.str.html#method.char_indices
/// [`str`]: ../../std/primitive.str.html
#[derive(Clone, Debug)]
#[stable(feature = "rust1", since = "1.0.0")]
pub struct CharIndices<'a> {
front_offset: usize,
iter: Chars<'a>,
}
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> Iterator for CharIndices<'a> {
type Item = (usize, char);
#[inline]
fn next(&mut self) -> Option<(usize, char)> {
let pre_len = self.iter.iter.len();
match self.iter.next() {
None => None,
Some(ch) => {
let index = self.front_offset;
let len = self.iter.iter.len();
self.front_offset += pre_len - len;
Some((index, ch))
}
}
}
#[inline]
fn count(self) -> usize {
self.iter.count()
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
self.iter.size_hint()
}
#[inline]
fn last(mut self) -> Option<(usize, char)> {
// No need to go through the entire string.
self.next_back()
}
}
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> DoubleEndedIterator for CharIndices<'a> {
#[inline]
fn next_back(&mut self) -> Option<(usize, char)> {
self.iter.next_back().map(|ch| {
let index = self.front_offset + self.iter.iter.len();
(index, ch)
})
}
}
#[stable(feature = "fused", since = "1.26.0")]
impl FusedIterator for CharIndices<'_> {}
impl<'a> CharIndices<'a> {
/// Views the underlying data as a subslice of the original data.
///
/// This has the same lifetime as the original slice, and so the
/// iterator can continue to be used while this exists.
#[stable(feature = "iter_to_slice", since = "1.4.0")]
#[inline]
pub fn as_str(&self) -> &'a str {
self.iter.as_str()
}
}
/// An iterator over the bytes of a string slice.
///
/// This struct is created by the [`bytes`] method on [`str`].
/// See its documentation for more.
///
/// [`bytes`]: ../../std/primitive.str.html#method.bytes
/// [`str`]: ../../std/primitive.str.html
#[stable(feature = "rust1", since = "1.0.0")]
#[derive(Clone, Debug)]
pub struct Bytes<'a>(Cloned<slice::Iter<'a, u8>>);
#[stable(feature = "rust1", since = "1.0.0")]
impl Iterator for Bytes<'_> {
type Item = u8;
#[inline]
fn next(&mut self) -> Option<u8> {
self.0.next()
}
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) {
self.0.size_hint()
}
#[inline]
fn count(self) -> usize {
self.0.count()
}
#[inline]
fn last(self) -> Option<Self::Item> {
self.0.last()
}
#[inline]
fn nth(&mut self, n: usize) -> Option<Self::Item> {
self.0.nth(n)
}
#[inline]
fn all<F>(&mut self, f: F) -> bool
where
F: FnMut(Self::Item) -> bool,
{
self.0.all(f)
}
#[inline]
fn any<F>(&mut self, f: F) -> bool
where
F: FnMut(Self::Item) -> bool,
{
self.0.any(f)
}
#[inline]
fn find<P>(&mut self, predicate: P) -> Option<Self::Item>
where
P: FnMut(&Self::Item) -> bool,
{
self.0.find(predicate)
}
#[inline]
fn position<P>(&mut self, predicate: P) -> Option<usize>
where
P: FnMut(Self::Item) -> bool,
{
self.0.position(predicate)
}
#[inline]
fn rposition<P>(&mut self, predicate: P) -> Option<usize>
where
P: FnMut(Self::Item) -> bool,
{
self.0.rposition(predicate)
}
}
#[stable(feature = "rust1", since = "1.0.0")]
impl DoubleEndedIterator for Bytes<'_> {
#[inline]
fn next_back(&mut self) -> Option<u8> {
self.0.next_back()
}
#[inline]
fn nth_back(&mut self, n: usize) -> Option<Self::Item> {
self.0.nth_back(n)
}
#[inline]
fn rfind<P>(&mut self, predicate: P) -> Option<Self::Item>
where
P: FnMut(&Self::Item) -> bool,
{
self.0.rfind(predicate)
}
}
#[stable(feature = "rust1", since = "1.0.0")]
impl ExactSizeIterator for Bytes<'_> {
#[inline]
fn len(&self) -> usize {
self.0.len()
}
#[inline]
fn is_empty(&self) -> bool {
self.0.is_empty()
}
}
#[stable(feature = "fused", since = "1.26.0")]
impl FusedIterator for Bytes<'_> {}
#[unstable(feature = "trusted_len", issue = "37572")]
unsafe impl TrustedLen for Bytes<'_> {}
#[doc(hidden)]
unsafe impl TrustedRandomAccess for Bytes<'_> {
unsafe fn get_unchecked(&mut self, i: usize) -> u8 {
self.0.get_unchecked(i)
}
fn may_have_side_effect() -> bool {
false
}
}
/// This macro generates a Clone impl for string pattern API
/// wrapper types of the form X<'a, P>
macro_rules! derive_pattern_clone {
(clone $t:ident with |$s:ident| $e:expr) => {
impl<'a, P> Clone for $t<'a, P>
where
P: Pattern<'a, Searcher: Clone>,
{
fn clone(&self) -> Self {
let $s = self;
$e
}
}
};
}
/// This macro generates two public iterator structs
/// wrapping a private internal one that makes use of the `Pattern` API.
///
/// For all patterns `P: Pattern<'a>` the following items will be
/// generated (generics omitted):
///
/// struct $forward_iterator($internal_iterator);
/// struct $reverse_iterator($internal_iterator);
///
/// impl Iterator for $forward_iterator
/// { /* internal ends up calling Searcher::next_match() */ }
///
/// impl DoubleEndedIterator for $forward_iterator
/// where P::Searcher: DoubleEndedSearcher
/// { /* internal ends up calling Searcher::next_match_back() */ }
///
/// impl Iterator for $reverse_iterator
/// where P::Searcher: ReverseSearcher
/// { /* internal ends up calling Searcher::next_match_back() */ }
///
/// impl DoubleEndedIterator for $reverse_iterator
/// where P::Searcher: DoubleEndedSearcher
/// { /* internal ends up calling Searcher::next_match() */ }
///
/// The internal one is defined outside the macro, and has almost the same
/// semantic as a DoubleEndedIterator by delegating to `pattern::Searcher` and
/// `pattern::ReverseSearcher` for both forward and reverse iteration.
///
/// "Almost", because a `Searcher` and a `ReverseSearcher` for a given
/// `Pattern` might not return the same elements, so actually implementing
/// `DoubleEndedIterator` for it would be incorrect.
/// (See the docs in `str::pattern` for more details)
///
/// However, the internal struct still represents a single ended iterator from
/// either end, and depending on pattern is also a valid double ended iterator,
/// so the two wrapper structs implement `Iterator`
/// and `DoubleEndedIterator` depending on the concrete pattern type, leading
/// to the complex impls seen above.
macro_rules! generate_pattern_iterators {
{
// Forward iterator
forward:
$(#[$forward_iterator_attribute:meta])*
struct $forward_iterator:ident;
// Reverse iterator
reverse:
$(#[$reverse_iterator_attribute:meta])*
struct $reverse_iterator:ident;
// Stability of all generated items
stability:
$(#[$common_stability_attribute:meta])*
// Internal almost-iterator that is being delegated to
internal:
$internal_iterator:ident yielding ($iterty:ty);
// Kind of delegation - either single ended or double ended
delegate $($t:tt)*
} => {
$(#[$forward_iterator_attribute])*
$(#[$common_stability_attribute])*
pub struct $forward_iterator<'a, P: Pattern<'a>>($internal_iterator<'a, P>);
$(#[$common_stability_attribute])*
impl<'a, P> fmt::Debug for $forward_iterator<'a, P>
where
P: Pattern<'a, Searcher: fmt::Debug>,
{
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.debug_tuple(stringify!($forward_iterator))
.field(&self.0)
.finish()
}
}
$(#[$common_stability_attribute])*
impl<'a, P: Pattern<'a>> Iterator for $forward_iterator<'a, P> {
type Item = $iterty;
#[inline]
fn next(&mut self) -> Option<$iterty> {
self.0.next()
}
}
$(#[$common_stability_attribute])*
impl<'a, P> Clone for $forward_iterator<'a, P>
where
P: Pattern<'a, Searcher: Clone>,
{
fn clone(&self) -> Self {
$forward_iterator(self.0.clone())
}
}
$(#[$reverse_iterator_attribute])*
$(#[$common_stability_attribute])*
pub struct $reverse_iterator<'a, P: Pattern<'a>>($internal_iterator<'a, P>);
$(#[$common_stability_attribute])*
impl<'a, P> fmt::Debug for $reverse_iterator<'a, P>
where
P: Pattern<'a, Searcher: fmt::Debug>,
{
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.debug_tuple(stringify!($reverse_iterator))
.field(&self.0)
.finish()