-
Notifications
You must be signed in to change notification settings - Fork 12.1k
/
str.rs
1918 lines (1821 loc) · 62.3 KB
/
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
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
// Copyright 2012-2014 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.
//! Unicode string manipulation (the `str` type).
//!
//! Rust's `str` type is one of the core primitive types of the language. `&str`
//! is the borrowed string type. This type of string can only be created from
//! other strings, unless it is a `&'static str` (see below). It is not possible
//! to move out of borrowed strings because they are owned elsewhere.
//!
//! # Examples
//!
//! Here's some code that uses a `&str`:
//!
//! ```
//! let s = "Hello, world.";
//! ```
//!
//! This `&str` is a `&'static str`, which is the type of string literals.
//! They're `'static` because literals are available for the entire lifetime of
//! the program.
//!
//! You can get a non-`'static` `&str` by taking a slice of a `String`:
//!
//! ```
//! let some_string = "Hello, world.".to_string();
//! let s = &some_string;
//! ```
//!
//! # Representation
//!
//! Rust's string type, `str`, is a sequence of Unicode scalar values encoded as
//! a stream of UTF-8 bytes. All [strings](../../reference.html#literals) are
//! guaranteed to be validly encoded UTF-8 sequences. Additionally, strings are
//! not null-terminated and can thus contain null bytes.
//!
//! The actual representation of `str`s have direct mappings to slices: `&str`
//! is the same as `&[u8]`.
#![doc(primitive = "str")]
#![stable(feature = "rust1", since = "1.0.0")]
// Many of the usings in this module are only used in the test configuration.
// It's cleaner to just turn off the unused_imports warning than to fix them.
#![allow(unused_imports)]
use self::RecompositionState::*;
use self::DecompositionType::*;
use core::clone::Clone;
use core::iter::{Iterator, Extend};
use core::option::Option::{self, Some, None};
use core::result::Result;
use core::str as core_str;
use core::str::pattern::Pattern;
use core::str::pattern::{Searcher, ReverseSearcher, DoubleEndedSearcher};
use core::mem;
use rustc_unicode::str::{UnicodeStr, Utf16Encoder};
use vec_deque::VecDeque;
use borrow::{Borrow, ToOwned};
use string::String;
use rustc_unicode;
use vec::Vec;
use slice::SliceConcatExt;
use boxed::Box;
pub use core::str::{FromStr, Utf8Error};
pub use core::str::{Lines, LinesAny, CharRange};
pub use core::str::{Split, RSplit};
pub use core::str::{SplitN, RSplitN};
pub use core::str::{SplitTerminator, RSplitTerminator};
pub use core::str::{Matches, RMatches};
pub use core::str::{MatchIndices, RMatchIndices};
pub use core::str::{from_utf8, Chars, CharIndices, Bytes};
pub use core::str::{from_utf8_unchecked, ParseBoolError};
pub use rustc_unicode::str::{SplitWhitespace, Words, Graphemes, GraphemeIndices};
pub use core::str::pattern;
impl<S: Borrow<str>> SliceConcatExt<str> for [S] {
type Output = String;
fn concat(&self) -> String {
if self.is_empty() {
return String::new();
}
// `len` calculation may overflow but push_str will check boundaries
let len = self.iter().map(|s| s.borrow().len()).sum();
let mut result = String::with_capacity(len);
for s in self {
result.push_str(s.borrow())
}
result
}
fn connect(&self, sep: &str) -> String {
if self.is_empty() {
return String::new();
}
// concat is faster
if sep.is_empty() {
return self.concat();
}
// this is wrong without the guarantee that `self` is non-empty
// `len` calculation may overflow but push_str but will check boundaries
let len = sep.len() * (self.len() - 1)
+ self.iter().map(|s| s.borrow().len()).sum::<usize>();
let mut result = String::with_capacity(len);
let mut first = true;
for s in self {
if first {
first = false;
} else {
result.push_str(sep);
}
result.push_str(s.borrow());
}
result
}
}
// Helper functions used for Unicode normalization
fn canonical_sort(comb: &mut [(char, u8)]) {
let len = comb.len();
for i in 0..len {
let mut swapped = false;
for j in 1..len-i {
let class_a = comb[j-1].1;
let class_b = comb[j].1;
if class_a != 0 && class_b != 0 && class_a > class_b {
comb.swap(j-1, j);
swapped = true;
}
}
if !swapped { break; }
}
}
#[derive(Clone)]
enum DecompositionType {
Canonical,
Compatible
}
/// External iterator for a string decomposition's characters.
///
/// For use with the `std::iter` module.
#[allow(deprecated)]
#[deprecated(reason = "use the crates.io `unicode-normalization` library instead",
since = "1.0.0")]
#[derive(Clone)]
#[unstable(feature = "unicode",
reason = "this functionality may be replaced with a more generic \
unicode crate on crates.io")]
pub struct Decompositions<'a> {
kind: DecompositionType,
iter: Chars<'a>,
buffer: Vec<(char, u8)>,
sorted: bool
}
#[allow(deprecated)]
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> Iterator for Decompositions<'a> {
type Item = char;
#[inline]
fn next(&mut self) -> Option<char> {
match self.buffer.first() {
Some(&(c, 0)) => {
self.sorted = false;
self.buffer.remove(0);
return Some(c);
}
Some(&(c, _)) if self.sorted => {
self.buffer.remove(0);
return Some(c);
}
_ => self.sorted = false
}
if !self.sorted {
for ch in self.iter.by_ref() {
let buffer = &mut self.buffer;
let sorted = &mut self.sorted;
{
let callback = |d| {
let class =
rustc_unicode::char::canonical_combining_class(d);
if class == 0 && !*sorted {
canonical_sort(buffer);
*sorted = true;
}
buffer.push((d, class));
};
match self.kind {
Canonical => {
rustc_unicode::char::decompose_canonical(ch, callback)
}
Compatible => {
rustc_unicode::char::decompose_compatible(ch, callback)
}
}
}
if *sorted {
break
}
}
}
if !self.sorted {
canonical_sort(&mut self.buffer);
self.sorted = true;
}
if self.buffer.is_empty() {
None
} else {
match self.buffer.remove(0) {
(c, 0) => {
self.sorted = false;
Some(c)
}
(c, _) => Some(c),
}
}
}
fn size_hint(&self) -> (usize, Option<usize>) {
let (lower, _) = self.iter.size_hint();
(lower, None)
}
}
#[derive(Clone)]
enum RecompositionState {
Composing,
Purging,
Finished
}
/// External iterator for a string recomposition's characters.
///
/// For use with the `std::iter` module.
#[allow(deprecated)]
#[deprecated(reason = "use the crates.io `unicode-normalization` library instead",
since = "1.0.0")]
#[derive(Clone)]
#[unstable(feature = "unicode",
reason = "this functionality may be replaced with a more generic \
unicode crate on crates.io")]
pub struct Recompositions<'a> {
iter: Decompositions<'a>,
state: RecompositionState,
buffer: VecDeque<char>,
composee: Option<char>,
last_ccc: Option<u8>
}
#[allow(deprecated)]
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> Iterator for Recompositions<'a> {
type Item = char;
#[inline]
fn next(&mut self) -> Option<char> {
loop {
match self.state {
Composing => {
for ch in self.iter.by_ref() {
let ch_class = rustc_unicode::char::canonical_combining_class(ch);
if self.composee.is_none() {
if ch_class != 0 {
return Some(ch);
}
self.composee = Some(ch);
continue;
}
let k = self.composee.clone().unwrap();
match self.last_ccc {
None => {
match rustc_unicode::char::compose(k, ch) {
Some(r) => {
self.composee = Some(r);
continue;
}
None => {
if ch_class == 0 {
self.composee = Some(ch);
return Some(k);
}
self.buffer.push_back(ch);
self.last_ccc = Some(ch_class);
}
}
}
Some(l_class) => {
if l_class >= ch_class {
// `ch` is blocked from `composee`
if ch_class == 0 {
self.composee = Some(ch);
self.last_ccc = None;
self.state = Purging;
return Some(k);
}
self.buffer.push_back(ch);
self.last_ccc = Some(ch_class);
continue;
}
match rustc_unicode::char::compose(k, ch) {
Some(r) => {
self.composee = Some(r);
continue;
}
None => {
self.buffer.push_back(ch);
self.last_ccc = Some(ch_class);
}
}
}
}
}
self.state = Finished;
if self.composee.is_some() {
return self.composee.take();
}
}
Purging => {
match self.buffer.pop_front() {
None => self.state = Composing,
s => return s
}
}
Finished => {
match self.buffer.pop_front() {
None => return self.composee.take(),
s => return s
}
}
}
}
}
}
/// External iterator for a string's UTF16 codeunits.
///
/// For use with the `std::iter` module.
#[derive(Clone)]
#[unstable(feature = "str_utf16")]
pub struct Utf16Units<'a> {
encoder: Utf16Encoder<Chars<'a>>
}
#[stable(feature = "rust1", since = "1.0.0")]
impl<'a> Iterator for Utf16Units<'a> {
type Item = u16;
#[inline]
fn next(&mut self) -> Option<u16> { self.encoder.next() }
#[inline]
fn size_hint(&self) -> (usize, Option<usize>) { self.encoder.size_hint() }
}
// Return 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
macro_rules! utf8_first_byte {
($byte:expr, $width:expr) => (($byte & (0x7F >> $width)) as u32)
}
// return the value of $ch updated with continuation byte $byte
macro_rules! utf8_acc_cont_byte {
($ch:expr, $byte:expr) => (($ch << 6) | ($byte & 63) as u32)
}
#[stable(feature = "rust1", since = "1.0.0")]
impl Borrow<str> for String {
#[inline]
fn borrow(&self) -> &str { &self[..] }
}
#[stable(feature = "rust1", since = "1.0.0")]
impl ToOwned for str {
type Owned = String;
fn to_owned(&self) -> String {
unsafe {
String::from_utf8_unchecked(self.as_bytes().to_owned())
}
}
}
/// Any string that can be represented as a slice.
#[lang = "str"]
#[cfg(not(test))]
#[stable(feature = "rust1", since = "1.0.0")]
impl str {
/// Returns the length of `self` in bytes.
///
/// # Examples
///
/// ```
/// assert_eq!("foo".len(), 3);
/// assert_eq!("ƒoo".len(), 4); // fancy f!
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
#[inline]
pub fn len(&self) -> usize {
core_str::StrExt::len(self)
}
/// Returns true if this slice has a length of zero bytes.
///
/// # Examples
///
/// ```
/// assert!("".is_empty());
/// ```
#[inline]
#[stable(feature = "rust1", since = "1.0.0")]
pub fn is_empty(&self) -> bool {
core_str::StrExt::is_empty(self)
}
/// Returns a string's displayed width in columns.
///
/// Control characters have zero width.
///
/// `is_cjk` determines behavior for characters in the Ambiguous category:
/// if `is_cjk` is
/// `true`, these are 2 columns wide; otherwise, they are 1.
/// In CJK locales, `is_cjk` should be
/// `true`, else it should be `false`.
/// [Unicode Standard Annex #11](http://www.unicode.org/reports/tr11/)
/// recommends that these
/// characters be treated as 1 column (i.e., `is_cjk = false`) if the
/// locale is unknown.
#[deprecated(reason = "use the crates.io `unicode-width` library instead",
since = "1.0.0")]
#[unstable(feature = "unicode",
reason = "this functionality may only be provided by libunicode")]
pub fn width(&self, is_cjk: bool) -> usize {
UnicodeStr::width(self, is_cjk)
}
/// Checks that `index`-th byte lies at the start and/or end of a
/// UTF-8 code point sequence.
///
/// The start and end of the string (when `index == self.len()`) are
/// considered to be
/// boundaries.
///
/// Returns `false` if `index` is greater than `self.len()`.
///
/// # Examples
///
/// ```
/// # #![feature(str_char)]
/// let s = "Löwe 老虎 Léopard";
/// assert!(s.is_char_boundary(0));
/// // start of `老`
/// assert!(s.is_char_boundary(6));
/// assert!(s.is_char_boundary(s.len()));
///
/// // second byte of `ö`
/// assert!(!s.is_char_boundary(2));
///
/// // third byte of `老`
/// assert!(!s.is_char_boundary(8));
/// ```
#[unstable(feature = "str_char",
reason = "it is unclear whether this method pulls its weight \
with the existence of the char_indices iterator or \
this method may want to be replaced with checked \
slicing")]
pub fn is_char_boundary(&self, index: usize) -> bool {
core_str::StrExt::is_char_boundary(self, index)
}
/// Converts `self` to a byte slice.
///
/// # Examples
///
/// ```
/// assert_eq!("bors".as_bytes(), b"bors");
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
#[inline(always)]
pub fn as_bytes(&self) -> &[u8] {
core_str::StrExt::as_bytes(self)
}
/// Returns a raw pointer to the `&str`'s buffer.
///
/// The caller must ensure that the string outlives this pointer, and
/// that it is not
/// reallocated (e.g. by pushing to the string).
///
/// # Examples
///
/// ```
/// let s = "Hello";
/// let p = s.as_ptr();
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
#[inline]
pub fn as_ptr(&self) -> *const u8 {
core_str::StrExt::as_ptr(self)
}
/// Takes a bytewise slice from a string.
///
/// Returns the substring from [`begin`..`end`).
///
/// # Unsafety
///
/// Caller must check both UTF-8 character boundaries and the boundaries
/// of the entire slice as
/// well.
///
/// # Examples
///
/// ```
/// let s = "Löwe 老虎 Léopard";
///
/// unsafe {
/// assert_eq!(s.slice_unchecked(0, 21), "Löwe 老虎 Léopard");
/// }
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub unsafe fn slice_unchecked(&self, begin: usize, end: usize) -> &str {
core_str::StrExt::slice_unchecked(self, begin, end)
}
/// Returns a slice of the string from the character range [`begin`..`end`).
///
/// That is, start at the `begin`-th code point of the string and continue
/// to the `end`-th code point. This does not detect or handle edge cases
/// such as leaving a combining character as the first code point of the
/// string.
///
/// Due to the design of UTF-8, this operation is `O(end)`. Use slicing
/// syntax if you want to use byte indices rather than codepoint indices.
///
/// # Panics
///
/// Panics if `begin` > `end` or the either `begin` or `end` are beyond the
/// last character of the string.
///
/// # Examples
///
/// ```
/// # #![feature(slice_chars)]
/// let s = "Löwe 老虎 Léopard";
///
/// assert_eq!(s.slice_chars(0, 4), "Löwe");
/// assert_eq!(s.slice_chars(5, 7), "老虎");
/// ```
#[unstable(feature = "slice_chars",
reason = "may have yet to prove its worth")]
pub fn slice_chars(&self, begin: usize, end: usize) -> &str {
core_str::StrExt::slice_chars(self, begin, end)
}
/// Given a byte position, return the next char and its index.
///
/// This can be used to iterate over the Unicode characters of a string.
///
/// # Panics
///
/// If `i` is greater than or equal to the length of the string.
/// If `i` is not the index of the beginning of a valid UTF-8 character.
///
/// # Examples
///
/// This example manually iterates through the characters of a string;
/// this should normally be
/// done by `.chars()` or `.char_indices()`.
///
/// ```
/// # #![feature(str_char, core)]
/// use std::str::CharRange;
///
/// let s = "中华Việt Nam";
/// let mut i = 0;
/// while i < s.len() {
/// let CharRange {ch, next} = s.char_range_at(i);
/// println!("{}: {}", i, ch);
/// i = next;
/// }
/// ```
///
/// This outputs:
///
/// ```text
/// 0: 中
/// 3: 华
/// 6: V
/// 7: i
/// 8: ệ
/// 11: t
/// 12:
/// 13: N
/// 14: a
/// 15: m
/// ```
#[unstable(feature = "str_char",
reason = "often replaced by char_indices, this method may \
be removed in favor of just char_at() or eventually \
removed altogether")]
pub fn char_range_at(&self, start: usize) -> CharRange {
core_str::StrExt::char_range_at(self, start)
}
/// Given a byte position, return the previous `char` and its position.
///
/// This function can be used to iterate over a Unicode string in reverse.
///
/// Returns 0 for next index if called on start index 0.
///
/// # Panics
///
/// If `i` is greater than the length of the string.
/// If `i` is not an index following a valid UTF-8 character.
///
/// # Examples
///
/// This example manually iterates through the characters of a string;
/// this should normally be
/// done by `.chars().rev()` or `.char_indices()`.
///
/// ```
/// # #![feature(str_char, core)]
/// use std::str::CharRange;
///
/// let s = "中华Việt Nam";
/// let mut i = s.len();
/// while i > 0 {
/// let CharRange {ch, next} = s.char_range_at_reverse(i);
/// println!("{}: {}", i, ch);
/// i = next;
/// }
/// ```
///
/// This outputs:
///
/// ```text
/// 16: m
/// 15: a
/// 14: N
/// 13:
/// 12: t
/// 11: ệ
/// 8: i
/// 7: V
/// 6: 华
/// 3: 中
/// ```
#[unstable(feature = "str_char",
reason = "often replaced by char_indices, this method may \
be removed in favor of just char_at_reverse() or \
eventually removed altogether")]
pub fn char_range_at_reverse(&self, start: usize) -> CharRange {
core_str::StrExt::char_range_at_reverse(self, start)
}
/// Given a byte position, return the `char` at that position.
///
/// # Panics
///
/// If `i` is greater than or equal to the length of the string.
/// If `i` is not the index of the beginning of a valid UTF-8 character.
///
/// # Examples
///
/// ```
/// # #![feature(str_char)]
/// let s = "abπc";
/// assert_eq!(s.char_at(1), 'b');
/// assert_eq!(s.char_at(2), 'π');
/// ```
#[unstable(feature = "str_char",
reason = "frequently replaced by the chars() iterator, this \
method may be removed or possibly renamed in the \
future; it is normally replaced by chars/char_indices \
iterators or by getting the first char from a \
subslice")]
pub fn char_at(&self, i: usize) -> char {
core_str::StrExt::char_at(self, i)
}
/// Given a byte position, return the `char` at that position, counting
/// from the end.
///
/// # Panics
///
/// If `i` is greater than the length of the string.
/// If `i` is not an index following a valid UTF-8 character.
///
/// # Examples
///
/// ```
/// # #![feature(str_char)]
/// let s = "abπc";
/// assert_eq!(s.char_at_reverse(1), 'a');
/// assert_eq!(s.char_at_reverse(2), 'b');
/// ```
#[unstable(feature = "str_char",
reason = "see char_at for more details, but reverse semantics \
are also somewhat unclear, especially with which \
cases generate panics")]
pub fn char_at_reverse(&self, i: usize) -> char {
core_str::StrExt::char_at_reverse(self, i)
}
/// Retrieves the first character from a `&str` and returns it.
///
/// This does not allocate a new string; instead, it returns a slice that
/// points one character
/// beyond the character that was shifted.
///
/// If the slice does not contain any characters, None is returned instead.
///
/// # Examples
///
/// ```
/// # #![feature(str_char)]
/// let s = "Löwe 老虎 Léopard";
/// let (c, s1) = s.slice_shift_char().unwrap();
///
/// assert_eq!(c, 'L');
/// assert_eq!(s1, "öwe 老虎 Léopard");
///
/// let (c, s2) = s1.slice_shift_char().unwrap();
///
/// assert_eq!(c, 'ö');
/// assert_eq!(s2, "we 老虎 Léopard");
/// ```
#[unstable(feature = "str_char",
reason = "awaiting conventions about shifting and slices and \
may not be warranted with the existence of the chars \
and/or char_indices iterators")]
pub fn slice_shift_char(&self) -> Option<(char, &str)> {
core_str::StrExt::slice_shift_char(self)
}
/// Divide one string slice into two at an index.
///
/// The index `mid` is a byte offset from the start of the string
/// that must be on a character boundary.
///
/// Return slices `&self[..mid]` and `&self[mid..]`.
///
/// # Panics
///
/// Panics if `mid` is beyond the last character of the string,
/// or if it is not on a character boundary.
///
/// # Examples
/// ```
/// # #![feature(collections)]
/// let s = "Löwe 老虎 Léopard";
/// let first_space = s.find(' ').unwrap_or(s.len());
/// let (a, b) = s.split_at(first_space);
///
/// assert_eq!(a, "Löwe");
/// assert_eq!(b, " 老虎 Léopard");
/// ```
#[inline]
pub fn split_at(&self, mid: usize) -> (&str, &str) {
core_str::StrExt::split_at(self, mid)
}
/// An iterator over the codepoints of `self`.
///
/// # Examples
///
/// ```
/// let v: Vec<char> = "abc åäö".chars().collect();
///
/// assert_eq!(v, ['a', 'b', 'c', ' ', 'å', 'ä', 'ö']);
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub fn chars(&self) -> Chars {
core_str::StrExt::chars(self)
}
/// An iterator over the characters of `self` and their byte offsets.
///
/// # Examples
///
/// ```
/// let v: Vec<(usize, char)> = "abc".char_indices().collect();
/// let b = vec![(0, 'a'), (1, 'b'), (2, 'c')];
///
/// assert_eq!(v, b);
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub fn char_indices(&self) -> CharIndices {
core_str::StrExt::char_indices(self)
}
/// An iterator over the bytes of `self`.
///
/// # Examples
///
/// ```
/// let v: Vec<u8> = "bors".bytes().collect();
///
/// assert_eq!(v, b"bors".to_vec());
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub fn bytes(&self) -> Bytes {
core_str::StrExt::bytes(self)
}
/// An iterator over the non-empty substrings of `self` which contain no whitespace,
/// and which are separated by any amount of whitespace.
///
/// # Examples
///
/// ```
/// let some_words = " Mary had\ta little \n\t lamb";
/// let v: Vec<&str> = some_words.split_whitespace().collect();
///
/// assert_eq!(v, ["Mary", "had", "a", "little", "lamb"]);
/// ```
#[stable(feature = "split_whitespace", since = "1.1.0")]
pub fn split_whitespace(&self) -> SplitWhitespace {
UnicodeStr::split_whitespace(self)
}
/// An iterator over the non-empty substrings of `self` which contain no whitespace,
/// and which are separated by any amount of whitespace.
///
/// # Examples
///
/// ```
/// # #![feature(str_words)]
/// # #![allow(deprecated)]
/// let some_words = " Mary had\ta little \n\t lamb";
/// let v: Vec<&str> = some_words.words().collect();
///
/// assert_eq!(v, ["Mary", "had", "a", "little", "lamb"]);
/// ```
#[deprecated(reason = "words() will be removed. Use split_whitespace() instead",
since = "1.1.0")]
#[unstable(feature = "str_words",
reason = "the precise algorithm to use is unclear")]
#[allow(deprecated)]
pub fn words(&self) -> Words {
UnicodeStr::words(self)
}
/// An iterator over the lines of a string, separated by `\n`.
///
/// This does not include the empty string after a trailing `\n`.
///
/// # Examples
///
/// ```
/// let four_lines = "foo\nbar\n\nbaz";
/// let v: Vec<&str> = four_lines.lines().collect();
///
/// assert_eq!(v, ["foo", "bar", "", "baz"]);
/// ```
///
/// Leaving off the trailing character:
///
/// ```
/// let four_lines = "foo\nbar\n\nbaz\n";
/// let v: Vec<&str> = four_lines.lines().collect();
///
/// assert_eq!(v, ["foo", "bar", "", "baz"]);
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub fn lines(&self) -> Lines {
core_str::StrExt::lines(self)
}
/// An iterator over the lines of a string, separated by either
/// `\n` or `\r\n`.
///
/// As with `.lines()`, this does not include an empty trailing line.
///
/// # Examples
///
/// ```
/// let four_lines = "foo\r\nbar\n\r\nbaz";
/// let v: Vec<&str> = four_lines.lines_any().collect();
///
/// assert_eq!(v, ["foo", "bar", "", "baz"]);
/// ```
///
/// Leaving off the trailing character:
///
/// ```
/// let four_lines = "foo\r\nbar\n\r\nbaz\n";
/// let v: Vec<&str> = four_lines.lines_any().collect();
///
/// assert_eq!(v, ["foo", "bar", "", "baz"]);
/// ```
#[stable(feature = "rust1", since = "1.0.0")]
pub fn lines_any(&self) -> LinesAny {
core_str::StrExt::lines_any(self)
}
/// Returns an iterator over the string in Unicode Normalization Form D
/// (canonical decomposition).
#[allow(deprecated)]
#[deprecated(reason = "use the crates.io `unicode-normalization` library instead",
since = "1.0.0")]
#[inline]
#[unstable(feature = "unicode",
reason = "this functionality may be replaced with a more generic \
unicode crate on crates.io")]
pub fn nfd_chars(&self) -> Decompositions {
Decompositions {
iter: self[..].chars(),
buffer: Vec::new(),
sorted: false,
kind: Canonical
}
}
/// Returns an iterator over the string in Unicode Normalization Form KD
/// (compatibility decomposition).
#[allow(deprecated)]
#[deprecated(reason = "use the crates.io `unicode-normalization` library instead",
since = "1.0.0")]
#[inline]
#[unstable(feature = "unicode",
reason = "this functionality may be replaced with a more generic \
unicode crate on crates.io")]
pub fn nfkd_chars(&self) -> Decompositions {
Decompositions {
iter: self[..].chars(),
buffer: Vec::new(),
sorted: false,
kind: Compatible
}
}
/// An Iterator over the string in Unicode Normalization Form C
/// (canonical decomposition followed by canonical composition).
#[allow(deprecated)]
#[deprecated(reason = "use the crates.io `unicode-normalization` library instead",
since = "1.0.0")]
#[inline]
#[unstable(feature = "unicode",
reason = "this functionality may be replaced with a more generic \
unicode crate on crates.io")]
pub fn nfc_chars(&self) -> Recompositions {
Recompositions {
iter: self.nfd_chars(),
state: Composing,
buffer: VecDeque::new(),
composee: None,
last_ccc: None
}
}
/// An Iterator over the string in Unicode Normalization Form KC
/// (compatibility decomposition followed by canonical composition).
#[allow(deprecated)]
#[deprecated(reason = "use the crates.io `unicode-normalization` library instead",
since = "1.0.0")]
#[inline]
#[unstable(feature = "unicode",
reason = "this functionality may be replaced with a more generic \
unicode crate on crates.io")]
pub fn nfkc_chars(&self) -> Recompositions {
Recompositions {
iter: self.nfkd_chars(),
state: Composing,
buffer: VecDeque::new(),
composee: None,
last_ccc: None
}
}
/// Returns an iterator over the [grapheme clusters][graphemes] of `self`.
///
/// [graphemes]: http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries
///
/// If `is_extended` is true, the iterator is over the