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
//! Parallel iterator types for [strings][std::str]
//!
//! You will rarely need to interact with this module directly unless you need
//! to name one of the iterator types.
//!
//! Note: [`ParallelString::par_split()`] and [`par_split_terminator()`]
//! reference a `Pattern` trait which is not visible outside this crate.
//! This trait is intentionally kept private, for use only by Rayon itself.
//! It is implemented for `char` and any `F: Fn(char) -> bool + Sync + Send`.
//!
//! [`ParallelString::par_split()`]: trait.ParallelString.html#method.par_split
//! [`par_split_terminator()`]: trait.ParallelString.html#method.par_split_terminator
//!
//! [std::str]: https://doc.rust-lang.org/stable/std/str/
use crate::iter::plumbing::*;
use crate::iter::*;
use crate::split_producer::*;
/// Test if a byte is the start of a UTF-8 character.
/// (extracted from `str::is_char_boundary`)
#[inline]
fn is_char_boundary(b: u8) -> bool {
// This is bit magic equivalent to: b < 128 || b >= 192
(b as i8) >= -0x40
}
/// Find the index of a character boundary near the midpoint.
#[inline]
fn find_char_midpoint(chars: &str) -> usize {
let mid = chars.len() / 2;
// We want to split near the midpoint, but we need to find an actual
// character boundary. So we look at the raw bytes, first scanning
// forward from the midpoint for a boundary, then trying backward.
let (left, right) = chars.as_bytes().split_at(mid);
match right.iter().cloned().position(is_char_boundary) {
Some(i) => mid + i,
None => left
.iter()
.cloned()
.rposition(is_char_boundary)
.unwrap_or(0),
}
}
/// Try to split a string near the midpoint.
#[inline]
fn split(chars: &str) -> Option<(&str, &str)> {
let index = find_char_midpoint(chars);
if index > 0 {
Some(chars.split_at(index))
} else {
None
}
}
/// Parallel extensions for strings.
pub trait ParallelString {
/// Returns a plain string slice, which is used to implement the rest of
/// the parallel methods.
fn as_parallel_string(&self) -> &str;
/// Returns a parallel iterator over the characters of a string.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let max = "hello".par_chars().max_by_key(|c| *c as i32);
/// assert_eq!(Some('o'), max);
/// ```
fn par_chars(&self) -> Chars<'_> {
Chars {
chars: self.as_parallel_string(),
}
}
/// Returns a parallel iterator over the characters of a string, with their positions.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let min = "hello".par_char_indices().min_by_key(|&(_i, c)| c as i32);
/// assert_eq!(Some((1, 'e')), min);
/// ```
fn par_char_indices(&self) -> CharIndices<'_> {
CharIndices {
chars: self.as_parallel_string(),
}
}
/// Returns a parallel iterator over the bytes of a string.
///
/// Note that multi-byte sequences (for code points greater than `U+007F`)
/// are produced as separate items, but will not be split across threads.
/// If you would prefer an indexed iterator without that guarantee, consider
/// `string.as_bytes().par_iter().cloned()` instead.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let max = "hello".par_bytes().max();
/// assert_eq!(Some(b'o'), max);
/// ```
fn par_bytes(&self) -> Bytes<'_> {
Bytes {
chars: self.as_parallel_string(),
}
}
/// Returns a parallel iterator over a string encoded as UTF-16.
///
/// Note that surrogate pairs (for code points greater than `U+FFFF`) are
/// produced as separate items, but will not be split across threads.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
///
/// let max = "hello".par_encode_utf16().max();
/// assert_eq!(Some(b'o' as u16), max);
///
/// let text = "Zażółć gęślą jaźń";
/// let utf8_len = text.len();
/// let utf16_len = text.par_encode_utf16().count();
/// assert!(utf16_len <= utf8_len);
/// ```
fn par_encode_utf16(&self) -> EncodeUtf16<'_> {
EncodeUtf16 {
chars: self.as_parallel_string(),
}
}
/// Returns a parallel iterator over substrings separated by a
/// given character or predicate, similar to `str::split`.
///
/// Note: the `Pattern` trait is private, for use only by Rayon itself.
/// It is implemented for `char` and any `F: Fn(char) -> bool + Sync + Send`.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let total = "1, 2, buckle, 3, 4, door"
/// .par_split(',')
/// .filter_map(|s| s.trim().parse::<i32>().ok())
/// .sum();
/// assert_eq!(10, total);
/// ```
fn par_split<P: Pattern>(&self, separator: P) -> Split<'_, P> {
Split::new(self.as_parallel_string(), separator)
}
/// Returns a parallel iterator over substrings terminated by a
/// given character or predicate, similar to `str::split_terminator`.
/// It's equivalent to `par_split`, except it doesn't produce an empty
/// substring after a trailing terminator.
///
/// Note: the `Pattern` trait is private, for use only by Rayon itself.
/// It is implemented for `char` and any `F: Fn(char) -> bool + Sync + Send`.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let parts: Vec<_> = "((1 + 3) * 2)"
/// .par_split_terminator(|c| c == '(' || c == ')')
/// .collect();
/// assert_eq!(vec!["", "", "1 + 3", " * 2"], parts);
/// ```
fn par_split_terminator<P: Pattern>(&self, terminator: P) -> SplitTerminator<'_, P> {
SplitTerminator::new(self.as_parallel_string(), terminator)
}
/// Returns a parallel iterator over the lines of a string, ending with an
/// optional carriage return and with a newline (`\r\n` or just `\n`).
/// The final line ending is optional, and line endings are not included in
/// the output strings.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let lengths: Vec<_> = "hello world\nfizbuzz"
/// .par_lines()
/// .map(|l| l.len())
/// .collect();
/// assert_eq!(vec![11, 7], lengths);
/// ```
fn par_lines(&self) -> Lines<'_> {
Lines(self.as_parallel_string())
}
/// Returns a parallel iterator over the sub-slices of a string that are
/// separated by any amount of whitespace.
///
/// As with `str::split_whitespace`, 'whitespace' is defined according to
/// the terms of the Unicode Derived Core Property `White_Space`.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let longest = "which is the longest word?"
/// .par_split_whitespace()
/// .max_by_key(|word| word.len());
/// assert_eq!(Some("longest"), longest);
/// ```
fn par_split_whitespace(&self) -> SplitWhitespace<'_> {
SplitWhitespace(self.as_parallel_string())
}
/// Returns a parallel iterator over substrings that match a
/// given character or predicate, similar to `str::matches`.
///
/// Note: the `Pattern` trait is private, for use only by Rayon itself.
/// It is implemented for `char` and any `F: Fn(char) -> bool + Sync + Send`.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let total = "1, 2, buckle, 3, 4, door"
/// .par_matches(char::is_numeric)
/// .map(|s| s.parse::<i32>().expect("digit"))
/// .sum();
/// assert_eq!(10, total);
/// ```
fn par_matches<P: Pattern>(&self, pattern: P) -> Matches<'_, P> {
Matches {
chars: self.as_parallel_string(),
pattern,
}
}
/// Returns a parallel iterator over substrings that match a given character
/// or predicate, with their positions, similar to `str::match_indices`.
///
/// Note: the `Pattern` trait is private, for use only by Rayon itself.
/// It is implemented for `char` and any `F: Fn(char) -> bool + Sync + Send`.
///
/// # Examples
///
/// ```
/// use rayon::prelude::*;
/// let digits: Vec<_> = "1, 2, buckle, 3, 4, door"
/// .par_match_indices(char::is_numeric)
/// .collect();
/// assert_eq!(digits, vec![(0, "1"), (3, "2"), (14, "3"), (17, "4")]);
/// ```
fn par_match_indices<P: Pattern>(&self, pattern: P) -> MatchIndices<'_, P> {
MatchIndices {
chars: self.as_parallel_string(),
pattern,
}
}
}
impl ParallelString for str {
#[inline]
fn as_parallel_string(&self) -> &str {
self
}
}
// /////////////////////////////////////////////////////////////////////////
/// We hide the `Pattern` trait in a private module, as its API is not meant
/// for general consumption. If we could have privacy on trait items, then it
/// would be nicer to have its basic existence and implementors public while
/// keeping all of the methods private.
mod private {
use crate::iter::plumbing::Folder;
/// Pattern-matching trait for `ParallelString`, somewhat like a mix of
/// `std::str::pattern::{Pattern, Searcher}`.
///
/// Implementing this trait is not permitted outside of `rayon`.
pub trait Pattern: Sized + Sync + Send {
private_decl! {}
fn find_in(&self, haystack: &str) -> Option<usize>;
fn rfind_in(&self, haystack: &str) -> Option<usize>;
fn is_suffix_of(&self, haystack: &str) -> bool;
fn fold_splits<'ch, F>(&self, haystack: &'ch str, folder: F, skip_last: bool) -> F
where
F: Folder<&'ch str>;
fn fold_matches<'ch, F>(&self, haystack: &'ch str, folder: F) -> F
where
F: Folder<&'ch str>;
fn fold_match_indices<'ch, F>(&self, haystack: &'ch str, folder: F, base: usize) -> F
where
F: Folder<(usize, &'ch str)>;
}
}
use self::private::Pattern;
#[inline]
fn offset<T>(base: usize) -> impl Fn((usize, T)) -> (usize, T) {
move |(i, x)| (base + i, x)
}
impl Pattern for char {
private_impl! {}
#[inline]
fn find_in(&self, chars: &str) -> Option<usize> {
chars.find(*self)
}
#[inline]
fn rfind_in(&self, chars: &str) -> Option<usize> {
chars.rfind(*self)
}
#[inline]
fn is_suffix_of(&self, chars: &str) -> bool {
chars.ends_with(*self)
}
fn fold_splits<'ch, F>(&self, chars: &'ch str, folder: F, skip_last: bool) -> F
where
F: Folder<&'ch str>,
{
let mut split = chars.split(*self);
if skip_last {
split.next_back();
}
folder.consume_iter(split)
}
fn fold_matches<'ch, F>(&self, chars: &'ch str, folder: F) -> F
where
F: Folder<&'ch str>,
{
folder.consume_iter(chars.matches(*self))
}
fn fold_match_indices<'ch, F>(&self, chars: &'ch str, folder: F, base: usize) -> F
where
F: Folder<(usize, &'ch str)>,
{
folder.consume_iter(chars.match_indices(*self).map(offset(base)))
}
}
impl<FN: Sync + Send + Fn(char) -> bool> Pattern for FN {
private_impl! {}
fn find_in(&self, chars: &str) -> Option<usize> {
chars.find(self)
}
fn rfind_in(&self, chars: &str) -> Option<usize> {
chars.rfind(self)
}
fn is_suffix_of(&self, chars: &str) -> bool {
chars.ends_with(self)
}
fn fold_splits<'ch, F>(&self, chars: &'ch str, folder: F, skip_last: bool) -> F
where
F: Folder<&'ch str>,
{
let mut split = chars.split(self);
if skip_last {
split.next_back();
}
folder.consume_iter(split)
}
fn fold_matches<'ch, F>(&self, chars: &'ch str, folder: F) -> F
where
F: Folder<&'ch str>,
{
folder.consume_iter(chars.matches(self))
}
fn fold_match_indices<'ch, F>(&self, chars: &'ch str, folder: F, base: usize) -> F
where
F: Folder<(usize, &'ch str)>,
{
folder.consume_iter(chars.match_indices(self).map(offset(base)))
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over the characters of a string
#[derive(Debug, Clone)]
pub struct Chars<'ch> {
chars: &'ch str,
}
struct CharsProducer<'ch> {
chars: &'ch str,
}
impl<'ch> ParallelIterator for Chars<'ch> {
type Item = char;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
bridge_unindexed(CharsProducer { chars: self.chars }, consumer)
}
}
impl<'ch> UnindexedProducer for CharsProducer<'ch> {
type Item = char;
fn split(self) -> (Self, Option<Self>) {
match split(self.chars) {
Some((left, right)) => (
CharsProducer { chars: left },
Some(CharsProducer { chars: right }),
),
None => (self, None),
}
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
folder.consume_iter(self.chars.chars())
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over the characters of a string, with their positions
#[derive(Debug, Clone)]
pub struct CharIndices<'ch> {
chars: &'ch str,
}
struct CharIndicesProducer<'ch> {
index: usize,
chars: &'ch str,
}
impl<'ch> ParallelIterator for CharIndices<'ch> {
type Item = (usize, char);
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
let producer = CharIndicesProducer {
index: 0,
chars: self.chars,
};
bridge_unindexed(producer, consumer)
}
}
impl<'ch> UnindexedProducer for CharIndicesProducer<'ch> {
type Item = (usize, char);
fn split(self) -> (Self, Option<Self>) {
match split(self.chars) {
Some((left, right)) => (
CharIndicesProducer {
chars: left,
..self
},
Some(CharIndicesProducer {
chars: right,
index: self.index + left.len(),
}),
),
None => (self, None),
}
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
let base = self.index;
folder.consume_iter(self.chars.char_indices().map(offset(base)))
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over the bytes of a string
#[derive(Debug, Clone)]
pub struct Bytes<'ch> {
chars: &'ch str,
}
struct BytesProducer<'ch> {
chars: &'ch str,
}
impl<'ch> ParallelIterator for Bytes<'ch> {
type Item = u8;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
bridge_unindexed(BytesProducer { chars: self.chars }, consumer)
}
}
impl<'ch> UnindexedProducer for BytesProducer<'ch> {
type Item = u8;
fn split(self) -> (Self, Option<Self>) {
match split(self.chars) {
Some((left, right)) => (
BytesProducer { chars: left },
Some(BytesProducer { chars: right }),
),
None => (self, None),
}
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
folder.consume_iter(self.chars.bytes())
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over a string encoded as UTF-16
#[derive(Debug, Clone)]
pub struct EncodeUtf16<'ch> {
chars: &'ch str,
}
struct EncodeUtf16Producer<'ch> {
chars: &'ch str,
}
impl<'ch> ParallelIterator for EncodeUtf16<'ch> {
type Item = u16;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
bridge_unindexed(EncodeUtf16Producer { chars: self.chars }, consumer)
}
}
impl<'ch> UnindexedProducer for EncodeUtf16Producer<'ch> {
type Item = u16;
fn split(self) -> (Self, Option<Self>) {
match split(self.chars) {
Some((left, right)) => (
EncodeUtf16Producer { chars: left },
Some(EncodeUtf16Producer { chars: right }),
),
None => (self, None),
}
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
folder.consume_iter(self.chars.encode_utf16())
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over substrings separated by a pattern
#[derive(Debug, Clone)]
pub struct Split<'ch, P: Pattern> {
chars: &'ch str,
separator: P,
}
impl<'ch, P: Pattern> Split<'ch, P> {
fn new(chars: &'ch str, separator: P) -> Self {
Split { chars, separator }
}
}
impl<'ch, P: Pattern> ParallelIterator for Split<'ch, P> {
type Item = &'ch str;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
let producer = SplitProducer::new(self.chars, &self.separator);
bridge_unindexed(producer, consumer)
}
}
/// Implement support for `SplitProducer`.
impl<'ch, P: Pattern> Fissile<P> for &'ch str {
fn length(&self) -> usize {
self.len()
}
fn midpoint(&self, end: usize) -> usize {
// First find a suitable UTF-8 boundary.
find_char_midpoint(&self[..end])
}
fn find(&self, separator: &P, start: usize, end: usize) -> Option<usize> {
separator.find_in(&self[start..end])
}
fn rfind(&self, separator: &P, end: usize) -> Option<usize> {
separator.rfind_in(&self[..end])
}
fn split_once(self, index: usize) -> (Self, Self) {
let (left, right) = self.split_at(index);
let mut right_iter = right.chars();
right_iter.next(); // skip the separator
(left, right_iter.as_str())
}
fn fold_splits<F>(self, separator: &P, folder: F, skip_last: bool) -> F
where
F: Folder<Self>,
{
separator.fold_splits(self, folder, skip_last)
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over substrings separated by a terminator pattern
#[derive(Debug, Clone)]
pub struct SplitTerminator<'ch, P: Pattern> {
chars: &'ch str,
terminator: P,
}
struct SplitTerminatorProducer<'ch, 'sep, P: Pattern> {
splitter: SplitProducer<'sep, P, &'ch str>,
skip_last: bool,
}
impl<'ch, P: Pattern> SplitTerminator<'ch, P> {
fn new(chars: &'ch str, terminator: P) -> Self {
SplitTerminator { chars, terminator }
}
}
impl<'ch, 'sep, P: Pattern + 'sep> SplitTerminatorProducer<'ch, 'sep, P> {
fn new(chars: &'ch str, terminator: &'sep P) -> Self {
SplitTerminatorProducer {
splitter: SplitProducer::new(chars, terminator),
skip_last: chars.is_empty() || terminator.is_suffix_of(chars),
}
}
}
impl<'ch, P: Pattern> ParallelIterator for SplitTerminator<'ch, P> {
type Item = &'ch str;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
let producer = SplitTerminatorProducer::new(self.chars, &self.terminator);
bridge_unindexed(producer, consumer)
}
}
impl<'ch, 'sep, P: Pattern + 'sep> UnindexedProducer for SplitTerminatorProducer<'ch, 'sep, P> {
type Item = &'ch str;
fn split(mut self) -> (Self, Option<Self>) {
let (left, right) = self.splitter.split();
self.splitter = left;
let right = right.map(|right| {
let skip_last = self.skip_last;
self.skip_last = false;
SplitTerminatorProducer {
splitter: right,
skip_last,
}
});
(self, right)
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
self.splitter.fold_with(folder, self.skip_last)
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over lines in a string
#[derive(Debug, Clone)]
pub struct Lines<'ch>(&'ch str);
#[inline]
fn no_carriage_return(line: &str) -> &str {
if line.ends_with('\r') {
&line[..line.len() - 1]
} else {
line
}
}
impl<'ch> ParallelIterator for Lines<'ch> {
type Item = &'ch str;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
self.0
.par_split_terminator('\n')
.map(no_carriage_return)
.drive_unindexed(consumer)
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over substrings separated by whitespace
#[derive(Debug, Clone)]
pub struct SplitWhitespace<'ch>(&'ch str);
#[inline]
fn not_empty(s: &&str) -> bool {
!s.is_empty()
}
impl<'ch> ParallelIterator for SplitWhitespace<'ch> {
type Item = &'ch str;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
self.0
.par_split(char::is_whitespace)
.filter(not_empty)
.drive_unindexed(consumer)
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over substrings that match a pattern
#[derive(Debug, Clone)]
pub struct Matches<'ch, P: Pattern> {
chars: &'ch str,
pattern: P,
}
struct MatchesProducer<'ch, 'pat, P: Pattern> {
chars: &'ch str,
pattern: &'pat P,
}
impl<'ch, P: Pattern> ParallelIterator for Matches<'ch, P> {
type Item = &'ch str;
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
let producer = MatchesProducer {
chars: self.chars,
pattern: &self.pattern,
};
bridge_unindexed(producer, consumer)
}
}
impl<'ch, 'pat, P: Pattern> UnindexedProducer for MatchesProducer<'ch, 'pat, P> {
type Item = &'ch str;
fn split(self) -> (Self, Option<Self>) {
match split(self.chars) {
Some((left, right)) => (
MatchesProducer {
chars: left,
..self
},
Some(MatchesProducer {
chars: right,
..self
}),
),
None => (self, None),
}
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
self.pattern.fold_matches(self.chars, folder)
}
}
// /////////////////////////////////////////////////////////////////////////
/// Parallel iterator over substrings that match a pattern, with their positions
#[derive(Debug, Clone)]
pub struct MatchIndices<'ch, P: Pattern> {
chars: &'ch str,
pattern: P,
}
struct MatchIndicesProducer<'ch, 'pat, P: Pattern> {
index: usize,
chars: &'ch str,
pattern: &'pat P,
}
impl<'ch, P: Pattern> ParallelIterator for MatchIndices<'ch, P> {
type Item = (usize, &'ch str);
fn drive_unindexed<C>(self, consumer: C) -> C::Result
where
C: UnindexedConsumer<Self::Item>,
{
let producer = MatchIndicesProducer {
index: 0,
chars: self.chars,
pattern: &self.pattern,
};
bridge_unindexed(producer, consumer)
}
}
impl<'ch, 'pat, P: Pattern> UnindexedProducer for MatchIndicesProducer<'ch, 'pat, P> {
type Item = (usize, &'ch str);
fn split(self) -> (Self, Option<Self>) {
match split(self.chars) {
Some((left, right)) => (
MatchIndicesProducer {
chars: left,
..self
},
Some(MatchIndicesProducer {
chars: right,
index: self.index + left.len(),
..self
}),
),
None => (self, None),
}
}
fn fold_with<F>(self, folder: F) -> F
where
F: Folder<Self::Item>,
{
self.pattern
.fold_match_indices(self.chars, folder, self.index)
}
}