1 // Copyright 2012-2014 The Rust Project Developers. See the COPYRIGHT
2 // file at the top-level directory of this distribution and at
3 // http://rust-lang.org/COPYRIGHT.
5 // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
6 // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
7 // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
8 // option. This file may not be copied, modified, or distributed
9 // except according to those terms.
11 // ignore-lexer-test FIXME #15679
13 //! Unicode string manipulation (`str` type)
17 //! Rust's string type is one of the core primitive types of the language. While
18 //! represented by the name `str`, the name `str` is not actually a valid type in
19 //! Rust. Each string must also be decorated with a pointer. `String` is used
20 //! for an owned string, so there is only one commonly-used `str` type in Rust:
23 //! `&str` is the borrowed string type. This type of string can only be created
24 //! from other strings, unless it is a static string (see below). As the word
25 //! "borrowed" implies, this type of string is owned elsewhere, and this string
26 //! cannot be moved out of.
28 //! As an example, here's some code that uses a string.
32 //! let borrowed_string = "This string is borrowed with the 'static lifetime";
36 //! From the example above, you can guess that Rust's string literals have the
37 //! `'static` lifetime. This is akin to C's concept of a static string.
38 //! More precisely, string literals are immutable views with a 'static lifetime
39 //! (otherwise known as the lifetime of the entire program), and thus have the
40 //! type `&'static str`.
44 //! Rust's string type, `str`, is a sequence of Unicode scalar values encoded as a
45 //! stream of UTF-8 bytes. All [strings](../../reference.html#literals) are
46 //! guaranteed to be validly encoded UTF-8 sequences. Additionally, strings are
47 //! not null-terminated and can thus contain null bytes.
49 //! The actual representation of strings have direct mappings to slices: `&str`
50 //! is the same as `&[u8]`.
52 #![doc(primitive = "str")]
55 use self::RecompositionState::*;
56 use self::DecompositionType::*;
58 use core::borrow::{BorrowFrom, ToOwned};
60 use core::clone::Clone;
61 use core::iter::AdditiveIterator;
62 use core::iter::{range, Iterator, IteratorExt};
63 use core::kinds::Sized;
65 use core::option::Option::{self, Some, None};
66 use core::slice::AsSlice;
67 use core::str as core_str;
68 use unicode::str::{UnicodeStr, Utf16Encoder};
70 use ring_buf::RingBuf;
75 use slice::SliceConcatExt;
77 pub use core::str::{FromStr, Utf8Error, Str};
78 pub use core::str::{Lines, LinesAny, MatchIndices, SplitStr, CharRange};
79 pub use core::str::{Split, SplitTerminator};
80 pub use core::str::{SplitN, RSplitN};
81 pub use core::str::{from_utf8, CharEq, Chars, CharIndices, Bytes};
82 pub use core::str::{from_utf8_unchecked, from_c_str};
83 pub use unicode::str::{Words, Graphemes, GraphemeIndices};
86 Section: Creating a string
89 impl<S: Str> SliceConcatExt<str, String> for [S] {
90 fn concat(&self) -> String {
91 let s = self.as_slice();
97 // `len` calculation may overflow but push_str will check boundaries
98 let len = s.iter().map(|s| s.as_slice().len()).sum();
99 let mut result = String::with_capacity(len);
102 result.push_str(s.as_slice())
108 fn connect(&self, sep: &str) -> String {
109 let s = self.as_slice();
112 return String::new();
120 // this is wrong without the guarantee that `self` is non-empty
121 // `len` calculation may overflow but push_str but will check boundaries
122 let len = sep.len() * (s.len() - 1)
123 + s.iter().map(|s| s.as_slice().len()).sum();
124 let mut result = String::with_capacity(len);
125 let mut first = true;
131 result.push_str(sep);
133 result.push_str(s.as_slice());
143 // Helper functions used for Unicode normalization
144 fn canonical_sort(comb: &mut [(char, u8)]) {
145 let len = comb.len();
146 for i in range(0, len) {
147 let mut swapped = false;
148 for j in range(1, len-i) {
149 let class_a = comb[j-1].1;
150 let class_b = comb[j].1;
151 if class_a != 0 && class_b != 0 && class_a > class_b {
156 if !swapped { break; }
161 enum DecompositionType {
166 /// External iterator for a string's decomposition's characters.
167 /// Use with the `std::iter` module.
169 pub struct Decompositions<'a> {
170 kind: DecompositionType,
172 buffer: Vec<(char, u8)>,
176 impl<'a> Iterator for Decompositions<'a> {
180 fn next(&mut self) -> Option<char> {
181 match self.buffer.first() {
184 self.buffer.remove(0);
187 Some(&(c, _)) if self.sorted => {
188 self.buffer.remove(0);
191 _ => self.sorted = false
195 for ch in self.iter {
196 let buffer = &mut self.buffer;
197 let sorted = &mut self.sorted;
199 let callback = |&mut: d| {
201 unicode::char::canonical_combining_class(d);
202 if class == 0 && !*sorted {
203 canonical_sort(buffer.as_mut_slice());
206 buffer.push((d, class));
210 unicode::char::decompose_canonical(ch, callback)
213 unicode::char::decompose_compatible(ch, callback)
224 canonical_sort(self.buffer.as_mut_slice());
228 if self.buffer.is_empty() {
231 match self.buffer.remove(0) {
241 fn size_hint(&self) -> (uint, Option<uint>) {
242 let (lower, _) = self.iter.size_hint();
248 enum RecompositionState {
254 /// External iterator for a string's recomposition's characters.
255 /// Use with the `std::iter` module.
257 pub struct Recompositions<'a> {
258 iter: Decompositions<'a>,
259 state: RecompositionState,
260 buffer: RingBuf<char>,
261 composee: Option<char>,
265 impl<'a> Iterator for Recompositions<'a> {
269 fn next(&mut self) -> Option<char> {
273 for ch in self.iter {
274 let ch_class = unicode::char::canonical_combining_class(ch);
275 if self.composee.is_none() {
279 self.composee = Some(ch);
282 let k = self.composee.clone().unwrap();
284 match self.last_ccc {
286 match unicode::char::compose(k, ch) {
288 self.composee = Some(r);
293 self.composee = Some(ch);
296 self.buffer.push_back(ch);
297 self.last_ccc = Some(ch_class);
302 if l_class >= ch_class {
303 // `ch` is blocked from `composee`
305 self.composee = Some(ch);
306 self.last_ccc = None;
307 self.state = Purging;
310 self.buffer.push_back(ch);
311 self.last_ccc = Some(ch_class);
314 match unicode::char::compose(k, ch) {
316 self.composee = Some(r);
320 self.buffer.push_back(ch);
321 self.last_ccc = Some(ch_class);
327 self.state = Finished;
328 if self.composee.is_some() {
329 return self.composee.take();
333 match self.buffer.pop_front() {
334 None => self.state = Composing,
339 match self.buffer.pop_front() {
340 None => return self.composee.take(),
349 /// External iterator for a string's UTF16 codeunits.
350 /// Use with the `std::iter` module.
352 pub struct Utf16Units<'a> {
353 encoder: Utf16Encoder<Chars<'a>>
356 impl<'a> Iterator for Utf16Units<'a> {
360 fn next(&mut self) -> Option<u16> { self.encoder.next() }
363 fn size_hint(&self) -> (uint, Option<uint>) { self.encoder.size_hint() }
370 // Return the initial codepoint accumulator for the first byte.
371 // The first byte is special, only want bottom 5 bits for width 2, 4 bits
372 // for width 3, and 3 bits for width 4
373 macro_rules! utf8_first_byte {
374 ($byte:expr, $width:expr) => (($byte & (0x7F >> $width)) as u32)
377 // return the value of $ch updated with continuation byte $byte
378 macro_rules! utf8_acc_cont_byte {
379 ($ch:expr, $byte:expr) => (($ch << 6) | ($byte & 63u8) as u32)
382 #[unstable = "trait is unstable"]
383 impl BorrowFrom<String> for str {
384 fn borrow_from(owned: &String) -> &str { owned[] }
387 #[unstable = "trait is unstable"]
388 impl ToOwned<String> for str {
389 fn to_owned(&self) -> String {
391 String::from_utf8_unchecked(self.as_bytes().to_owned())
401 Section: Trait implementations
404 /// Any string that can be represented as a slice.
406 pub trait StrExt for Sized?: ops::Slice<uint, str> {
407 /// Escapes each char in `s` with `char::escape_default`.
408 #[unstable = "return type may change to be an iterator"]
409 fn escape_default(&self) -> String {
410 self.chars().flat_map(|c| c.escape_default()).collect()
413 /// Escapes each char in `s` with `char::escape_unicode`.
414 #[unstable = "return type may change to be an iterator"]
415 fn escape_unicode(&self) -> String {
416 self.chars().flat_map(|c| c.escape_unicode()).collect()
419 /// Replaces all occurrences of one string with another.
423 /// * `from` - The string to replace
424 /// * `to` - The replacement string
428 /// The original string with all occurrences of `from` replaced with `to`.
433 /// let s = "Do you know the muffin man,
434 /// The muffin man, the muffin man, ...".to_string();
436 /// assert_eq!(s.replace("muffin man", "little lamb"),
437 /// "Do you know the little lamb,
438 /// The little lamb, the little lamb, ...".to_string());
440 /// // not found, so no change.
441 /// assert_eq!(s.replace("cookie monster", "little lamb"), s);
444 fn replace(&self, from: &str, to: &str) -> String {
445 let mut result = String::new();
446 let mut last_end = 0;
447 for (start, end) in self.match_indices(from) {
448 result.push_str(unsafe { self.slice_unchecked(last_end, start) });
452 result.push_str(unsafe { self.slice_unchecked(last_end, self.len()) });
456 /// Returns an iterator over the string in Unicode Normalization Form D
457 /// (canonical decomposition).
459 #[unstable = "this functionality may be moved to libunicode"]
460 fn nfd_chars<'a>(&'a self) -> Decompositions<'a> {
462 iter: self[].chars(),
469 /// Returns an iterator over the string in Unicode Normalization Form KD
470 /// (compatibility decomposition).
472 #[unstable = "this functionality may be moved to libunicode"]
473 fn nfkd_chars<'a>(&'a self) -> Decompositions<'a> {
475 iter: self[].chars(),
482 /// An Iterator over the string in Unicode Normalization Form C
483 /// (canonical decomposition followed by canonical composition).
485 #[unstable = "this functionality may be moved to libunicode"]
486 fn nfc_chars<'a>(&'a self) -> Recompositions<'a> {
488 iter: self.nfd_chars(),
490 buffer: RingBuf::new(),
496 /// An Iterator over the string in Unicode Normalization Form KC
497 /// (compatibility decomposition followed by canonical composition).
499 #[unstable = "this functionality may be moved to libunicode"]
500 fn nfkc_chars<'a>(&'a self) -> Recompositions<'a> {
502 iter: self.nfkd_chars(),
504 buffer: RingBuf::new(),
510 /// Returns true if a string contains a string pattern.
514 /// - pat - The string pattern to look for
519 /// assert!("bananas".contains("nana"));
522 fn contains(&self, pat: &str) -> bool {
523 core_str::StrExt::contains(self[], pat)
526 /// Returns true if a string contains a char pattern.
530 /// - pat - The char pattern to look for
535 /// assert!("hello".contains_char('e'));
537 #[unstable = "might get removed in favour of a more generic contains()"]
538 fn contains_char<P: CharEq>(&self, pat: P) -> bool {
539 core_str::StrExt::contains_char(self[], pat)
542 /// An iterator over the characters of `self`. Note, this iterates
543 /// over Unicode code-points, not Unicode graphemes.
548 /// let v: Vec<char> = "abc åäö".chars().collect();
549 /// assert_eq!(v, vec!['a', 'b', 'c', ' ', 'å', 'ä', 'ö']);
552 fn chars(&self) -> Chars {
553 core_str::StrExt::chars(self[])
556 /// An iterator over the bytes of `self`
561 /// let v: Vec<u8> = "bors".bytes().collect();
562 /// assert_eq!(v, b"bors".to_vec());
565 fn bytes(&self) -> Bytes {
566 core_str::StrExt::bytes(self[])
569 /// An iterator over the characters of `self` and their byte offsets.
571 fn char_indices(&self) -> CharIndices {
572 core_str::StrExt::char_indices(self[])
575 /// An iterator over substrings of `self`, separated by characters
576 /// matched by the pattern `pat`.
581 /// let v: Vec<&str> = "Mary had a little lamb".split(' ').collect();
582 /// assert_eq!(v, vec!["Mary", "had", "a", "little", "lamb"]);
584 /// let v: Vec<&str> = "abc1def2ghi".split(|&: c: char| c.is_numeric()).collect();
585 /// assert_eq!(v, vec!["abc", "def", "ghi"]);
587 /// let v: Vec<&str> = "lionXXtigerXleopard".split('X').collect();
588 /// assert_eq!(v, vec!["lion", "", "tiger", "leopard"]);
590 /// let v: Vec<&str> = "".split('X').collect();
591 /// assert_eq!(v, vec![""]);
594 fn split<P: CharEq>(&self, pat: P) -> Split<P> {
595 core_str::StrExt::split(self[], pat)
598 /// An iterator over substrings of `self`, separated by characters
599 /// matched by the pattern `pat`, restricted to splitting at most `count`
605 /// let v: Vec<&str> = "Mary had a little lambda".splitn(2, ' ').collect();
606 /// assert_eq!(v, vec!["Mary", "had", "a little lambda"]);
608 /// let v: Vec<&str> = "abc1def2ghi".splitn(1, |&: c: char| c.is_numeric()).collect();
609 /// assert_eq!(v, vec!["abc", "def2ghi"]);
611 /// let v: Vec<&str> = "lionXXtigerXleopard".splitn(2, 'X').collect();
612 /// assert_eq!(v, vec!["lion", "", "tigerXleopard"]);
614 /// let v: Vec<&str> = "abcXdef".splitn(0, 'X').collect();
615 /// assert_eq!(v, vec!["abcXdef"]);
617 /// let v: Vec<&str> = "".splitn(1, 'X').collect();
618 /// assert_eq!(v, vec![""]);
621 fn splitn<P: CharEq>(&self, count: uint, pat: P) -> SplitN<P> {
622 core_str::StrExt::splitn(self[], count, pat)
625 /// An iterator over substrings of `self`, separated by characters
626 /// matched by the pattern `pat`.
628 /// Equivalent to `split`, except that the trailing substring
629 /// is skipped if empty (terminator semantics).
634 /// let v: Vec<&str> = "A.B.".split_terminator('.').collect();
635 /// assert_eq!(v, vec!["A", "B"]);
637 /// let v: Vec<&str> = "A..B..".split_terminator('.').collect();
638 /// assert_eq!(v, vec!["A", "", "B", ""]);
640 /// let v: Vec<&str> = "Mary had a little lamb".split(' ').rev().collect();
641 /// assert_eq!(v, vec!["lamb", "little", "a", "had", "Mary"]);
643 /// let v: Vec<&str> = "abc1def2ghi".split(|&: c: char| c.is_numeric()).rev().collect();
644 /// assert_eq!(v, vec!["ghi", "def", "abc"]);
646 /// let v: Vec<&str> = "lionXXtigerXleopard".split('X').rev().collect();
647 /// assert_eq!(v, vec!["leopard", "tiger", "", "lion"]);
649 #[unstable = "might get removed"]
650 fn split_terminator<P: CharEq>(&self, pat: P) -> SplitTerminator<P> {
651 core_str::StrExt::split_terminator(self[], pat)
654 /// An iterator over substrings of `self`, separated by characters
655 /// matched by the pattern `pat`, starting from the end of the string.
656 /// Restricted to splitting at most `count` times.
661 /// let v: Vec<&str> = "Mary had a little lamb".rsplitn(2, ' ').collect();
662 /// assert_eq!(v, vec!["lamb", "little", "Mary had a"]);
664 /// let v: Vec<&str> = "abc1def2ghi".rsplitn(1, |&: c: char| c.is_numeric()).collect();
665 /// assert_eq!(v, vec!["ghi", "abc1def"]);
667 /// let v: Vec<&str> = "lionXXtigerXleopard".rsplitn(2, 'X').collect();
668 /// assert_eq!(v, vec!["leopard", "tiger", "lionX"]);
671 fn rsplitn<P: CharEq>(&self, count: uint, pat: P) -> RSplitN<P> {
672 core_str::StrExt::rsplitn(self[], count, pat)
675 /// An iterator over the start and end indices of the disjoint
676 /// matches of the pattern `pat` within `self`.
678 /// That is, each returned value `(start, end)` satisfies
679 /// `self.slice(start, end) == sep`. For matches of `sep` within
680 /// `self` that overlap, only the indices corresponding to the
681 /// first match are returned.
686 /// let v: Vec<(uint, uint)> = "abcXXXabcYYYabc".match_indices("abc").collect();
687 /// assert_eq!(v, vec![(0,3), (6,9), (12,15)]);
689 /// let v: Vec<(uint, uint)> = "1abcabc2".match_indices("abc").collect();
690 /// assert_eq!(v, vec![(1,4), (4,7)]);
692 /// let v: Vec<(uint, uint)> = "ababa".match_indices("aba").collect();
693 /// assert_eq!(v, vec![(0, 3)]); // only the first `aba`
695 #[unstable = "might have its iterator type changed"]
696 fn match_indices<'a>(&'a self, pat: &'a str) -> MatchIndices<'a> {
697 core_str::StrExt::match_indices(self[], pat)
700 /// An iterator over the substrings of `self` separated by the pattern `sep`.
705 /// let v: Vec<&str> = "abcXXXabcYYYabc".split_str("abc").collect();
706 /// assert_eq!(v, vec!["", "XXX", "YYY", ""]);
708 /// let v: Vec<&str> = "1abcabc2".split_str("abc").collect();
709 /// assert_eq!(v, vec!["1", "", "2"]);
711 #[unstable = "might get removed in the future in favor of a more generic split()"]
712 fn split_str<'a>(&'a self, pat: &'a str) -> SplitStr<'a> {
713 core_str::StrExt::split_str(self[], pat)
716 /// An iterator over the lines of a string (subsequences separated
717 /// by `\n`). This does not include the empty string after a
723 /// let four_lines = "foo\nbar\n\nbaz\n";
724 /// let v: Vec<&str> = four_lines.lines().collect();
725 /// assert_eq!(v, vec!["foo", "bar", "", "baz"]);
728 fn lines(&self) -> Lines {
729 core_str::StrExt::lines(self[])
732 /// An iterator over the lines of a string, separated by either
733 /// `\n` or `\r\n`. As with `.lines()`, this does not include an
734 /// empty trailing line.
739 /// let four_lines = "foo\r\nbar\n\r\nbaz\n";
740 /// let v: Vec<&str> = four_lines.lines_any().collect();
741 /// assert_eq!(v, vec!["foo", "bar", "", "baz"]);
744 fn lines_any(&self) -> LinesAny {
745 core_str::StrExt::lines_any(self[])
748 /// Returns a slice of the given string from the byte range
749 /// [`begin`..`end`).
751 /// This operation is `O(1)`.
753 /// Panics when `begin` and `end` do not point to valid characters
754 /// or point beyond the last character of the string.
756 /// See also `slice_to` and `slice_from` for slicing prefixes and
757 /// suffixes of strings, and `slice_chars` for slicing based on
758 /// code point counts.
763 /// let s = "Löwe 老虎 Léopard";
764 /// assert_eq!(s.slice(0, 1), "L");
766 /// assert_eq!(s.slice(1, 9), "öwe 老");
768 /// // these will panic:
769 /// // byte 2 lies within `ö`:
770 /// // s.slice(2, 3);
772 /// // byte 8 lies within `老`
773 /// // s.slice(1, 8);
775 /// // byte 100 is outside the string
776 /// // s.slice(3, 100);
778 #[unstable = "use slice notation [a..b] instead"]
779 fn slice(&self, begin: uint, end: uint) -> &str {
780 core_str::StrExt::slice(self[], begin, end)
783 /// Returns a slice of the string from `begin` to its end.
785 /// Equivalent to `self.slice(begin, self.len())`.
787 /// Panics when `begin` does not point to a valid character, or is
790 /// See also `slice`, `slice_to` and `slice_chars`.
791 #[unstable = "use slice notation [a..] instead"]
792 fn slice_from(&self, begin: uint) -> &str {
793 core_str::StrExt::slice_from(self[], begin)
796 /// Returns a slice of the string from the beginning to byte
799 /// Equivalent to `self.slice(0, end)`.
801 /// Panics when `end` does not point to a valid character, or is
804 /// See also `slice`, `slice_from` and `slice_chars`.
805 #[unstable = "use slice notation [0..a] instead"]
806 fn slice_to(&self, end: uint) -> &str {
807 core_str::StrExt::slice_to(self[], end)
810 /// Returns a slice of the string from the character range
811 /// [`begin`..`end`).
813 /// That is, start at the `begin`-th code point of the string and
814 /// continue to the `end`-th code point. This does not detect or
815 /// handle edge cases such as leaving a combining character as the
816 /// first code point of the string.
818 /// Due to the design of UTF-8, this operation is `O(end)`.
819 /// See `slice`, `slice_to` and `slice_from` for `O(1)`
820 /// variants that use byte indices rather than code point
823 /// Panics if `begin` > `end` or the either `begin` or `end` are
824 /// beyond the last character of the string.
829 /// let s = "Löwe 老虎 Léopard";
830 /// assert_eq!(s.slice_chars(0, 4), "Löwe");
831 /// assert_eq!(s.slice_chars(5, 7), "老虎");
833 #[unstable = "may have yet to prove its worth"]
834 fn slice_chars(&self, begin: uint, end: uint) -> &str {
835 core_str::StrExt::slice_chars(self[], begin, end)
838 /// Takes a bytewise (not UTF-8) slice from a string.
840 /// Returns the substring from [`begin`..`end`).
842 /// Caller must check both UTF-8 character boundaries and the boundaries of
843 /// the entire slice as well.
845 unsafe fn slice_unchecked(&self, begin: uint, end: uint) -> &str {
846 core_str::StrExt::slice_unchecked(self[], begin, end)
849 /// Returns true if the pattern `pat` is a prefix of the string.
854 /// assert!("banana".starts_with("ba"));
857 fn starts_with(&self, pat: &str) -> bool {
858 core_str::StrExt::starts_with(self[], pat)
861 /// Returns true if the pattern `pat` is a suffix of the string.
866 /// assert!("banana".ends_with("nana"));
869 fn ends_with(&self, pat: &str) -> bool {
870 core_str::StrExt::ends_with(self[], pat)
873 /// Returns a string with all pre- and suffixes that match
874 /// the pattern `pat` repeatedly removed.
878 /// * pat - a string pattern
883 /// assert_eq!("11foo1bar11".trim_matches('1'), "foo1bar");
884 /// let x: &[_] = &['1', '2'];
885 /// assert_eq!("12foo1bar12".trim_matches(x), "foo1bar");
886 /// assert_eq!("123foo1bar123".trim_matches(|&: c: char| c.is_numeric()), "foo1bar");
889 fn trim_matches<P: CharEq>(&self, pat: P) -> &str {
890 core_str::StrExt::trim_matches(self[], pat)
893 /// Returns a string with all prefixes that match
894 /// the pattern `pat` repeatedly removed.
898 /// * pat - a string pattern
903 /// assert_eq!("11foo1bar11".trim_left_matches('1'), "foo1bar11");
904 /// let x: &[_] = &['1', '2'];
905 /// assert_eq!("12foo1bar12".trim_left_matches(x), "foo1bar12");
906 /// assert_eq!("123foo1bar123".trim_left_matches(|&: c: char| c.is_numeric()), "foo1bar123");
909 fn trim_left_matches<P: CharEq>(&self, pat: P) -> &str {
910 core_str::StrExt::trim_left_matches(self[], pat)
913 /// Returns a string with all suffixes that match
914 /// the pattern `pat` repeatedly removed.
918 /// * pat - a string pattern
923 /// assert_eq!("11foo1bar11".trim_right_matches('1'), "11foo1bar");
924 /// let x: &[_] = &['1', '2'];
925 /// assert_eq!("12foo1bar12".trim_right_matches(x), "12foo1bar");
926 /// assert_eq!("123foo1bar123".trim_right_matches(|&: c: char| c.is_numeric()), "123foo1bar");
929 fn trim_right_matches<P: CharEq>(&self, pat: P) -> &str {
930 core_str::StrExt::trim_right_matches(self[], pat)
933 /// Check that `index`-th byte lies at the start and/or end of a
934 /// UTF-8 code point sequence.
936 /// The start and end of the string (when `index == self.len()`)
937 /// are considered to be boundaries.
939 /// Panics if `index` is greater than `self.len()`.
944 /// let s = "Löwe 老虎 Léopard";
945 /// assert!(s.is_char_boundary(0));
947 /// assert!(s.is_char_boundary(6));
948 /// assert!(s.is_char_boundary(s.len()));
950 /// // second byte of `ö`
951 /// assert!(!s.is_char_boundary(2));
953 /// // third byte of `老`
954 /// assert!(!s.is_char_boundary(8));
956 #[unstable = "naming is uncertain with container conventions"]
957 fn is_char_boundary(&self, index: uint) -> bool {
958 core_str::StrExt::is_char_boundary(self[], index)
961 /// Pluck a character out of a string and return the index of the next
964 /// This function can be used to iterate over the Unicode characters of a
969 /// This example manually iterates through the characters of a
970 /// string; this should normally be done by `.chars()` or
974 /// use std::str::CharRange;
976 /// let s = "中华Việt Nam";
978 /// while i < s.len() {
979 /// let CharRange {ch, next} = s.char_range_at(i);
980 /// println!("{}: {}", i, ch);
1002 /// * s - The string
1003 /// * i - The byte offset of the char to extract
1007 /// A record {ch: char, next: uint} containing the char value and the byte
1008 /// index of the next Unicode character.
1012 /// If `i` is greater than or equal to the length of the string.
1013 /// If `i` is not the index of the beginning of a valid UTF-8 character.
1014 #[unstable = "naming is uncertain with container conventions"]
1015 fn char_range_at(&self, start: uint) -> CharRange {
1016 core_str::StrExt::char_range_at(self[], start)
1019 /// Given a byte position and a str, return the previous char and its position.
1021 /// This function can be used to iterate over a Unicode string in reverse.
1023 /// Returns 0 for next index if called on start index 0.
1027 /// If `i` is greater than the length of the string.
1028 /// If `i` is not an index following a valid UTF-8 character.
1029 #[unstable = "naming is uncertain with container conventions"]
1030 fn char_range_at_reverse(&self, start: uint) -> CharRange {
1031 core_str::StrExt::char_range_at_reverse(self[], start)
1034 /// Plucks the character starting at the `i`th byte of a string.
1040 /// assert_eq!(s.char_at(1), 'b');
1041 /// assert_eq!(s.char_at(2), 'π');
1042 /// assert_eq!(s.char_at(4), 'c');
1047 /// If `i` is greater than or equal to the length of the string.
1048 /// If `i` is not the index of the beginning of a valid UTF-8 character.
1049 #[unstable = "naming is uncertain with container conventions"]
1050 fn char_at(&self, i: uint) -> char {
1051 core_str::StrExt::char_at(self[], i)
1054 /// Plucks the character ending at the `i`th byte of a string.
1058 /// If `i` is greater than the length of the string.
1059 /// If `i` is not an index following a valid UTF-8 character.
1060 #[unstable = "naming is uncertain with container conventions"]
1061 fn char_at_reverse(&self, i: uint) -> char {
1062 core_str::StrExt::char_at_reverse(self[], i)
1065 /// Work with the byte buffer of a string as a byte slice.
1070 /// assert_eq!("bors".as_bytes(), b"bors");
1073 fn as_bytes(&self) -> &[u8] {
1074 core_str::StrExt::as_bytes(self[])
1077 /// Returns the byte index of the first character of `self` that
1078 /// matches the pattern `pat`.
1082 /// `Some` containing the byte index of the last matching character
1083 /// or `None` if there is no match
1088 /// let s = "Löwe 老虎 Léopard";
1090 /// assert_eq!(s.find('L'), Some(0));
1091 /// assert_eq!(s.find('é'), Some(14));
1093 /// // the first space
1094 /// assert_eq!(s.find(|&: c: char| c.is_whitespace()), Some(5));
1096 /// // neither are found
1097 /// let x: &[_] = &['1', '2'];
1098 /// assert_eq!(s.find(x), None);
1101 fn find<P: CharEq>(&self, pat: P) -> Option<uint> {
1102 core_str::StrExt::find(self[], pat)
1105 /// Returns the byte index of the last character of `self` that
1106 /// matches the pattern `pat`.
1110 /// `Some` containing the byte index of the last matching character
1111 /// or `None` if there is no match.
1116 /// let s = "Löwe 老虎 Léopard";
1118 /// assert_eq!(s.rfind('L'), Some(13));
1119 /// assert_eq!(s.rfind('é'), Some(14));
1121 /// // the second space
1122 /// assert_eq!(s.rfind(|&: c: char| c.is_whitespace()), Some(12));
1124 /// // searches for an occurrence of either `1` or `2`, but neither are found
1125 /// let x: &[_] = &['1', '2'];
1126 /// assert_eq!(s.rfind(x), None);
1129 fn rfind<P: CharEq>(&self, pat: P) -> Option<uint> {
1130 core_str::StrExt::rfind(self[], pat)
1133 /// Returns the byte index of the first matching substring
1137 /// * `needle` - The string to search for
1141 /// `Some` containing the byte index of the first matching substring
1142 /// or `None` if there is no match.
1147 /// let s = "Löwe 老虎 Léopard";
1149 /// assert_eq!(s.find_str("老虎 L"), Some(6));
1150 /// assert_eq!(s.find_str("muffin man"), None);
1152 #[unstable = "might get removed in favor of a more generic find in the future"]
1153 fn find_str(&self, needle: &str) -> Option<uint> {
1154 core_str::StrExt::find_str(self[], needle)
1157 /// Retrieves the first character from a string slice and returns
1158 /// it. This does not allocate a new string; instead, it returns a
1159 /// slice that point one character beyond the character that was
1160 /// shifted. If the string does not contain any characters,
1161 /// None is returned instead.
1166 /// let s = "Löwe 老虎 Léopard";
1167 /// let (c, s1) = s.slice_shift_char().unwrap();
1168 /// assert_eq!(c, 'L');
1169 /// assert_eq!(s1, "öwe 老虎 Léopard");
1171 /// let (c, s2) = s1.slice_shift_char().unwrap();
1172 /// assert_eq!(c, 'ö');
1173 /// assert_eq!(s2, "we 老虎 Léopard");
1175 #[unstable = "awaiting conventions about shifting and slices"]
1176 fn slice_shift_char(&self) -> Option<(char, &str)> {
1177 core_str::StrExt::slice_shift_char(self[])
1180 /// Returns the byte offset of an inner slice relative to an enclosing outer slice.
1182 /// Panics if `inner` is not a direct slice contained within self.
1187 /// let string = "a\nb\nc";
1188 /// let lines: Vec<&str> = string.lines().collect();
1190 /// assert!(string.subslice_offset(lines[0]) == 0); // &"a"
1191 /// assert!(string.subslice_offset(lines[1]) == 2); // &"b"
1192 /// assert!(string.subslice_offset(lines[2]) == 4); // &"c"
1194 #[unstable = "awaiting convention about comparability of arbitrary slices"]
1195 fn subslice_offset(&self, inner: &str) -> uint {
1196 core_str::StrExt::subslice_offset(self[], inner)
1199 /// Return an unsafe pointer to the strings buffer.
1201 /// The caller must ensure that the string outlives this pointer,
1202 /// and that it is not reallocated (e.g. by pushing to the
1206 fn as_ptr(&self) -> *const u8 {
1207 core_str::StrExt::as_ptr(self[])
1210 /// Return an iterator of `u16` over the string encoded as UTF-16.
1211 #[unstable = "this functionality may only be provided by libunicode"]
1212 fn utf16_units(&self) -> Utf16Units {
1213 Utf16Units { encoder: Utf16Encoder::new(self[].chars()) }
1216 /// Return the number of bytes in this string
1221 /// assert_eq!("foo".len(), 3);
1222 /// assert_eq!("ƒoo".len(), 4);
1226 fn len(&self) -> uint {
1227 core_str::StrExt::len(self[])
1230 /// Returns true if this slice contains no bytes
1235 /// assert!("".is_empty());
1239 fn is_empty(&self) -> bool {
1240 core_str::StrExt::is_empty(self[])
1243 /// Parse this string into the specified type.
1248 /// assert_eq!("4".parse::<u32>(), Some(4));
1249 /// assert_eq!("j".parse::<u32>(), None);
1252 #[unstable = "this method was just created"]
1253 fn parse<F: FromStr>(&self) -> Option<F> {
1254 core_str::StrExt::parse(self[])
1257 /// Returns an iterator over the
1258 /// [grapheme clusters](http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries)
1261 /// If `is_extended` is true, the iterator is over the *extended grapheme clusters*;
1262 /// otherwise, the iterator is over the *legacy grapheme clusters*.
1263 /// [UAX#29](http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries)
1264 /// recommends extended grapheme cluster boundaries for general processing.
1269 /// let gr1 = "a\u{310}e\u{301}o\u{308}\u{332}".graphemes(true).collect::<Vec<&str>>();
1270 /// let b: &[_] = &["a\u{310}", "e\u{301}", "o\u{308}\u{332}"];
1271 /// assert_eq!(gr1.as_slice(), b);
1272 /// let gr2 = "a\r\nb🇷🇺🇸🇹".graphemes(true).collect::<Vec<&str>>();
1273 /// let b: &[_] = &["a", "\r\n", "b", "🇷🇺🇸🇹"];
1274 /// assert_eq!(gr2.as_slice(), b);
1276 #[unstable = "this functionality may only be provided by libunicode"]
1277 fn graphemes(&self, is_extended: bool) -> Graphemes {
1278 UnicodeStr::graphemes(self[], is_extended)
1281 /// Returns an iterator over the grapheme clusters of self and their byte offsets.
1282 /// See `graphemes()` method for more information.
1287 /// let gr_inds = "a̐éö̲\r\n".grapheme_indices(true).collect::<Vec<(uint, &str)>>();
1288 /// let b: &[_] = &[(0u, "a̐"), (3, "é"), (6, "ö̲"), (11, "\r\n")];
1289 /// assert_eq!(gr_inds.as_slice(), b);
1291 #[unstable = "this functionality may only be provided by libunicode"]
1292 fn grapheme_indices(&self, is_extended: bool) -> GraphemeIndices {
1293 UnicodeStr::grapheme_indices(self[], is_extended)
1296 /// An iterator over the words of a string (subsequences separated
1297 /// by any sequence of whitespace). Sequences of whitespace are
1298 /// collapsed, so empty "words" are not included.
1303 /// let some_words = " Mary had\ta little \n\t lamb";
1304 /// let v: Vec<&str> = some_words.words().collect();
1305 /// assert_eq!(v, vec!["Mary", "had", "a", "little", "lamb"]);
1308 fn words(&self) -> Words {
1309 UnicodeStr::words(self[])
1312 /// Returns a string's displayed width in columns, treating control
1313 /// characters as zero-width.
1315 /// `is_cjk` determines behavior for characters in the Ambiguous category:
1316 /// if `is_cjk` is `true`, these are 2 columns wide; otherwise, they are 1.
1317 /// In CJK locales, `is_cjk` should be `true`, else it should be `false`.
1318 /// [Unicode Standard Annex #11](http://www.unicode.org/reports/tr11/)
1319 /// recommends that these characters be treated as 1 column (i.e.,
1320 /// `is_cjk` = `false`) if the locale is unknown.
1321 #[unstable = "this functionality may only be provided by libunicode"]
1322 fn width(&self, is_cjk: bool) -> uint {
1323 UnicodeStr::width(self[], is_cjk)
1326 /// Returns a string with leading and trailing whitespace removed.
1328 fn trim(&self) -> &str {
1329 UnicodeStr::trim(self[])
1332 /// Returns a string with leading whitespace removed.
1334 fn trim_left(&self) -> &str {
1335 UnicodeStr::trim_left(self[])
1338 /// Returns a string with trailing whitespace removed.
1340 fn trim_right(&self) -> &str {
1341 UnicodeStr::trim_right(self[])
1346 impl StrExt for str {}
1352 use core::iter::AdditiveIterator;
1353 use super::from_utf8;
1354 use super::Utf8Error;
1359 assert!("" <= "foo");
1360 assert!("foo" <= "foo");
1361 assert!("foo" != "bar");
1366 assert_eq!("".len(), 0u);
1367 assert_eq!("hello world".len(), 11u);
1368 assert_eq!("\x63".len(), 1u);
1369 assert_eq!("\u{a2}".len(), 2u);
1370 assert_eq!("\u{3c0}".len(), 2u);
1371 assert_eq!("\u{2620}".len(), 3u);
1372 assert_eq!("\u{1d11e}".len(), 4u);
1374 assert_eq!("".chars().count(), 0u);
1375 assert_eq!("hello world".chars().count(), 11u);
1376 assert_eq!("\x63".chars().count(), 1u);
1377 assert_eq!("\u{a2}".chars().count(), 1u);
1378 assert_eq!("\u{3c0}".chars().count(), 1u);
1379 assert_eq!("\u{2620}".chars().count(), 1u);
1380 assert_eq!("\u{1d11e}".chars().count(), 1u);
1381 assert_eq!("ประเทศไทย中华Việt Nam".chars().count(), 19u);
1383 assert_eq!("hello".width(false), 10u);
1384 assert_eq!("hello".width(true), 10u);
1385 assert_eq!("\0\0\0\0\0".width(false), 0u);
1386 assert_eq!("\0\0\0\0\0".width(true), 0u);
1387 assert_eq!("".width(false), 0u);
1388 assert_eq!("".width(true), 0u);
1389 assert_eq!("\u{2081}\u{2082}\u{2083}\u{2084}".width(false), 4u);
1390 assert_eq!("\u{2081}\u{2082}\u{2083}\u{2084}".width(true), 8u);
1395 assert_eq!("hello".find('l'), Some(2u));
1396 assert_eq!("hello".find(|&: c:char| c == 'o'), Some(4u));
1397 assert!("hello".find('x').is_none());
1398 assert!("hello".find(|&: c:char| c == 'x').is_none());
1399 assert_eq!("ประเทศไทย中华Việt Nam".find('华'), Some(30u));
1400 assert_eq!("ประเทศไทย中华Việt Nam".find(|&: c: char| c == '华'), Some(30u));
1405 assert_eq!("hello".rfind('l'), Some(3u));
1406 assert_eq!("hello".rfind(|&: c:char| c == 'o'), Some(4u));
1407 assert!("hello".rfind('x').is_none());
1408 assert!("hello".rfind(|&: c:char| c == 'x').is_none());
1409 assert_eq!("ประเทศไทย中华Việt Nam".rfind('华'), Some(30u));
1410 assert_eq!("ประเทศไทย中华Việt Nam".rfind(|&: c: char| c == '华'), Some(30u));
1415 let empty = String::from_str("");
1416 let s: String = empty.chars().collect();
1417 assert_eq!(empty, s);
1418 let data = String::from_str("ประเทศไทย中");
1419 let s: String = data.chars().collect();
1420 assert_eq!(data, s);
1424 fn test_into_bytes() {
1425 let data = String::from_str("asdf");
1426 let buf = data.into_bytes();
1427 assert_eq!(b"asdf", buf);
1431 fn test_find_str() {
1433 assert_eq!("".find_str(""), Some(0u));
1434 assert!("banana".find_str("apple pie").is_none());
1436 let data = "abcabc";
1437 assert_eq!(data.slice(0u, 6u).find_str("ab"), Some(0u));
1438 assert_eq!(data.slice(2u, 6u).find_str("ab"), Some(3u - 2u));
1439 assert!(data.slice(2u, 4u).find_str("ab").is_none());
1441 let string = "ประเทศไทย中华Việt Nam";
1442 let mut data = String::from_str(string);
1443 data.push_str(string);
1444 assert!(data.find_str("ไท华").is_none());
1445 assert_eq!(data.slice(0u, 43u).find_str(""), Some(0u));
1446 assert_eq!(data.slice(6u, 43u).find_str(""), Some(6u - 6u));
1448 assert_eq!(data.slice(0u, 43u).find_str("ประ"), Some( 0u));
1449 assert_eq!(data.slice(0u, 43u).find_str("ทศไ"), Some(12u));
1450 assert_eq!(data.slice(0u, 43u).find_str("ย中"), Some(24u));
1451 assert_eq!(data.slice(0u, 43u).find_str("iệt"), Some(34u));
1452 assert_eq!(data.slice(0u, 43u).find_str("Nam"), Some(40u));
1454 assert_eq!(data.slice(43u, 86u).find_str("ประ"), Some(43u - 43u));
1455 assert_eq!(data.slice(43u, 86u).find_str("ทศไ"), Some(55u - 43u));
1456 assert_eq!(data.slice(43u, 86u).find_str("ย中"), Some(67u - 43u));
1457 assert_eq!(data.slice(43u, 86u).find_str("iệt"), Some(77u - 43u));
1458 assert_eq!(data.slice(43u, 86u).find_str("Nam"), Some(83u - 43u));
1462 fn test_slice_chars() {
1463 fn t(a: &str, b: &str, start: uint) {
1464 assert_eq!(a.slice_chars(start, start + b.chars().count()), b);
1467 t("hello", "llo", 2);
1468 t("hello", "el", 1);
1471 assert_eq!("ะเทศไท", "ประเทศไทย中华Việt Nam".slice_chars(2, 8));
1474 fn s(x: &str) -> String { x.to_string() }
1476 macro_rules! test_concat {
1477 ($expected: expr, $string: expr) => {
1479 let s: String = $string.concat();
1480 assert_eq!($expected, s);
1486 fn test_concat_for_different_types() {
1487 test_concat!("ab", vec![s("a"), s("b")]);
1488 test_concat!("ab", vec!["a", "b"]);
1489 test_concat!("ab", vec!["a", "b"].as_slice());
1490 test_concat!("ab", vec![s("a"), s("b")]);
1494 fn test_concat_for_different_lengths() {
1495 let empty: &[&str] = &[];
1496 test_concat!("", empty);
1497 test_concat!("a", ["a"]);
1498 test_concat!("ab", ["a", "b"]);
1499 test_concat!("abc", ["", "a", "bc"]);
1502 macro_rules! test_connect {
1503 ($expected: expr, $string: expr, $delim: expr) => {
1505 let s = $string.connect($delim);
1506 assert_eq!($expected, s);
1512 fn test_connect_for_different_types() {
1513 test_connect!("a-b", ["a", "b"], "-");
1514 let hyphen = "-".to_string();
1515 test_connect!("a-b", [s("a"), s("b")], hyphen.as_slice());
1516 test_connect!("a-b", vec!["a", "b"], hyphen.as_slice());
1517 test_connect!("a-b", vec!["a", "b"].as_slice(), "-");
1518 test_connect!("a-b", vec![s("a"), s("b")], "-");
1522 fn test_connect_for_different_lengths() {
1523 let empty: &[&str] = &[];
1524 test_connect!("", empty, "-");
1525 test_connect!("a", ["a"], "-");
1526 test_connect!("a-b", ["a", "b"], "-");
1527 test_connect!("-a-bc", ["", "a", "bc"], "-");
1531 fn test_unsafe_slice() {
1532 assert_eq!("ab", unsafe {"abc".slice_unchecked(0, 2)});
1533 assert_eq!("bc", unsafe {"abc".slice_unchecked(1, 3)});
1534 assert_eq!("", unsafe {"abc".slice_unchecked(1, 1)});
1535 fn a_million_letter_a() -> String {
1537 let mut rs = String::new();
1539 rs.push_str("aaaaaaaaaa");
1544 fn half_a_million_letter_a() -> String {
1546 let mut rs = String::new();
1548 rs.push_str("aaaaa");
1553 let letters = a_million_letter_a();
1554 assert!(half_a_million_letter_a() ==
1555 unsafe {String::from_str(letters.slice_unchecked(
1561 fn test_starts_with() {
1562 assert!(("".starts_with("")));
1563 assert!(("abc".starts_with("")));
1564 assert!(("abc".starts_with("a")));
1565 assert!((!"a".starts_with("abc")));
1566 assert!((!"".starts_with("abc")));
1567 assert!((!"ödd".starts_with("-")));
1568 assert!(("ödd".starts_with("öd")));
1572 fn test_ends_with() {
1573 assert!(("".ends_with("")));
1574 assert!(("abc".ends_with("")));
1575 assert!(("abc".ends_with("c")));
1576 assert!((!"a".ends_with("abc")));
1577 assert!((!"".ends_with("abc")));
1578 assert!((!"ddö".ends_with("-")));
1579 assert!(("ddö".ends_with("dö")));
1583 fn test_is_empty() {
1584 assert!("".is_empty());
1585 assert!(!"a".is_empty());
1591 assert_eq!("".replace(a, "b"), String::from_str(""));
1592 assert_eq!("a".replace(a, "b"), String::from_str("b"));
1593 assert_eq!("ab".replace(a, "b"), String::from_str("bb"));
1595 assert!(" test test ".replace(test, "toast") ==
1596 String::from_str(" toast toast "));
1597 assert_eq!(" test test ".replace(test, ""), String::from_str(" "));
1601 fn test_replace_2a() {
1602 let data = "ประเทศไทย中华";
1603 let repl = "دولة الكويت";
1606 let a2 = "دولة الكويتทศไทย中华";
1607 assert_eq!(data.replace(a, repl), a2);
1611 fn test_replace_2b() {
1612 let data = "ประเทศไทย中华";
1613 let repl = "دولة الكويت";
1616 let b2 = "ปรدولة الكويتทศไทย中华";
1617 assert_eq!(data.replace(b, repl), b2);
1621 fn test_replace_2c() {
1622 let data = "ประเทศไทย中华";
1623 let repl = "دولة الكويت";
1626 let c2 = "ประเทศไทยدولة الكويت";
1627 assert_eq!(data.replace(c, repl), c2);
1631 fn test_replace_2d() {
1632 let data = "ประเทศไทย中华";
1633 let repl = "دولة الكويت";
1636 assert_eq!(data.replace(d, repl), data);
1641 assert_eq!("ab", "abc".slice(0, 2));
1642 assert_eq!("bc", "abc".slice(1, 3));
1643 assert_eq!("", "abc".slice(1, 1));
1644 assert_eq!("\u{65e5}", "\u{65e5}\u{672c}".slice(0, 3));
1646 let data = "ประเทศไทย中华";
1647 assert_eq!("ป", data.slice(0, 3));
1648 assert_eq!("ร", data.slice(3, 6));
1649 assert_eq!("", data.slice(3, 3));
1650 assert_eq!("华", data.slice(30, 33));
1652 fn a_million_letter_x() -> String {
1654 let mut rs = String::new();
1656 rs.push_str("华华华华华华华华华华");
1661 fn half_a_million_letter_x() -> String {
1663 let mut rs = String::new();
1665 rs.push_str("华华华华华");
1670 let letters = a_million_letter_x();
1671 assert!(half_a_million_letter_x() ==
1672 String::from_str(letters.slice(0u, 3u * 500000u)));
1677 let ss = "中华Việt Nam";
1679 assert_eq!("华", ss.slice(3u, 6u));
1680 assert_eq!("Việt Nam", ss.slice(6u, 16u));
1682 assert_eq!("ab", "abc".slice(0u, 2u));
1683 assert_eq!("bc", "abc".slice(1u, 3u));
1684 assert_eq!("", "abc".slice(1u, 1u));
1686 assert_eq!("中", ss.slice(0u, 3u));
1687 assert_eq!("华V", ss.slice(3u, 7u));
1688 assert_eq!("", ss.slice(3u, 3u));
1703 fn test_slice_fail() {
1704 "中华Việt Nam".slice(0u, 2u);
1708 fn test_slice_from() {
1709 assert_eq!("abcd".slice_from(0), "abcd");
1710 assert_eq!("abcd".slice_from(2), "cd");
1711 assert_eq!("abcd".slice_from(4), "");
1714 fn test_slice_to() {
1715 assert_eq!("abcd".slice_to(0), "");
1716 assert_eq!("abcd".slice_to(2), "ab");
1717 assert_eq!("abcd".slice_to(4), "abcd");
1721 fn test_trim_left_matches() {
1722 let v: &[char] = &[];
1723 assert_eq!(" *** foo *** ".trim_left_matches(v), " *** foo *** ");
1724 let chars: &[char] = &['*', ' '];
1725 assert_eq!(" *** foo *** ".trim_left_matches(chars), "foo *** ");
1726 assert_eq!(" *** *** ".trim_left_matches(chars), "");
1727 assert_eq!("foo *** ".trim_left_matches(chars), "foo *** ");
1729 assert_eq!("11foo1bar11".trim_left_matches('1'), "foo1bar11");
1730 let chars: &[char] = &['1', '2'];
1731 assert_eq!("12foo1bar12".trim_left_matches(chars), "foo1bar12");
1732 assert_eq!("123foo1bar123".trim_left_matches(|&: c: char| c.is_numeric()), "foo1bar123");
1736 fn test_trim_right_matches() {
1737 let v: &[char] = &[];
1738 assert_eq!(" *** foo *** ".trim_right_matches(v), " *** foo *** ");
1739 let chars: &[char] = &['*', ' '];
1740 assert_eq!(" *** foo *** ".trim_right_matches(chars), " *** foo");
1741 assert_eq!(" *** *** ".trim_right_matches(chars), "");
1742 assert_eq!(" *** foo".trim_right_matches(chars), " *** foo");
1744 assert_eq!("11foo1bar11".trim_right_matches('1'), "11foo1bar");
1745 let chars: &[char] = &['1', '2'];
1746 assert_eq!("12foo1bar12".trim_right_matches(chars), "12foo1bar");
1747 assert_eq!("123foo1bar123".trim_right_matches(|&: c: char| c.is_numeric()), "123foo1bar");
1751 fn test_trim_matches() {
1752 let v: &[char] = &[];
1753 assert_eq!(" *** foo *** ".trim_matches(v), " *** foo *** ");
1754 let chars: &[char] = &['*', ' '];
1755 assert_eq!(" *** foo *** ".trim_matches(chars), "foo");
1756 assert_eq!(" *** *** ".trim_matches(chars), "");
1757 assert_eq!("foo".trim_matches(chars), "foo");
1759 assert_eq!("11foo1bar11".trim_matches('1'), "foo1bar");
1760 let chars: &[char] = &['1', '2'];
1761 assert_eq!("12foo1bar12".trim_matches(chars), "foo1bar");
1762 assert_eq!("123foo1bar123".trim_matches(|&: c: char| c.is_numeric()), "foo1bar");
1766 fn test_trim_left() {
1767 assert_eq!("".trim_left(), "");
1768 assert_eq!("a".trim_left(), "a");
1769 assert_eq!(" ".trim_left(), "");
1770 assert_eq!(" blah".trim_left(), "blah");
1771 assert_eq!(" \u{3000} wut".trim_left(), "wut");
1772 assert_eq!("hey ".trim_left(), "hey ");
1776 fn test_trim_right() {
1777 assert_eq!("".trim_right(), "");
1778 assert_eq!("a".trim_right(), "a");
1779 assert_eq!(" ".trim_right(), "");
1780 assert_eq!("blah ".trim_right(), "blah");
1781 assert_eq!("wut \u{3000} ".trim_right(), "wut");
1782 assert_eq!(" hey".trim_right(), " hey");
1787 assert_eq!("".trim(), "");
1788 assert_eq!("a".trim(), "a");
1789 assert_eq!(" ".trim(), "");
1790 assert_eq!(" blah ".trim(), "blah");
1791 assert_eq!("\nwut \u{3000} ".trim(), "wut");
1792 assert_eq!(" hey dude ".trim(), "hey dude");
1796 fn test_is_whitespace() {
1797 assert!("".chars().all(|c| c.is_whitespace()));
1798 assert!(" ".chars().all(|c| c.is_whitespace()));
1799 assert!("\u{2009}".chars().all(|c| c.is_whitespace())); // Thin space
1800 assert!(" \n\t ".chars().all(|c| c.is_whitespace()));
1801 assert!(!" _ ".chars().all(|c| c.is_whitespace()));
1805 fn test_slice_shift_char() {
1806 let data = "ประเทศไทย中";
1807 assert_eq!(data.slice_shift_char(), Some(('ป', "ระเทศไทย中")));
1811 fn test_slice_shift_char_2() {
1813 assert_eq!(empty.slice_shift_char(), None);
1818 // deny overlong encodings
1819 assert!(from_utf8(&[0xc0, 0x80]).is_err());
1820 assert!(from_utf8(&[0xc0, 0xae]).is_err());
1821 assert!(from_utf8(&[0xe0, 0x80, 0x80]).is_err());
1822 assert!(from_utf8(&[0xe0, 0x80, 0xaf]).is_err());
1823 assert!(from_utf8(&[0xe0, 0x81, 0x81]).is_err());
1824 assert!(from_utf8(&[0xf0, 0x82, 0x82, 0xac]).is_err());
1825 assert!(from_utf8(&[0xf4, 0x90, 0x80, 0x80]).is_err());
1828 assert!(from_utf8(&[0xED, 0xA0, 0x80]).is_err());
1829 assert!(from_utf8(&[0xED, 0xBF, 0xBF]).is_err());
1831 assert!(from_utf8(&[0xC2, 0x80]).is_ok());
1832 assert!(from_utf8(&[0xDF, 0xBF]).is_ok());
1833 assert!(from_utf8(&[0xE0, 0xA0, 0x80]).is_ok());
1834 assert!(from_utf8(&[0xED, 0x9F, 0xBF]).is_ok());
1835 assert!(from_utf8(&[0xEE, 0x80, 0x80]).is_ok());
1836 assert!(from_utf8(&[0xEF, 0xBF, 0xBF]).is_ok());
1837 assert!(from_utf8(&[0xF0, 0x90, 0x80, 0x80]).is_ok());
1838 assert!(from_utf8(&[0xF4, 0x8F, 0xBF, 0xBF]).is_ok());
1842 fn test_is_utf16() {
1843 use unicode::str::is_utf16;
1844 macro_rules! pos ( ($($e:expr),*) => { { $(assert!(is_utf16($e));)* } });
1852 // surrogate pairs (randomly generated with Python 3's
1853 // .encode('utf-16be'))
1854 pos!(&[0xdb54, 0xdf16, 0xd880, 0xdee0, 0xdb6a, 0xdd45],
1855 &[0xd91f, 0xdeb1, 0xdb31, 0xdd84, 0xd8e2, 0xde14],
1856 &[0xdb9f, 0xdc26, 0xdb6f, 0xde58, 0xd850, 0xdfae]);
1858 // mixtures (also random)
1859 pos!(&[0xd921, 0xdcc2, 0x002d, 0x004d, 0xdb32, 0xdf65],
1860 &[0xdb45, 0xdd2d, 0x006a, 0xdacd, 0xddfe, 0x0006],
1861 &[0x0067, 0xd8ff, 0xddb7, 0x000f, 0xd900, 0xdc80]);
1864 macro_rules! neg ( ($($e:expr),*) => { { $(assert!(!is_utf16($e));)* } });
1867 // surrogate + regular unit
1869 // surrogate + lead surrogate
1871 // unterminated surrogate
1873 // trail surrogate without a lead
1876 // random byte sequences that Python 3's .decode('utf-16be')
1878 neg!(&[0x5b3d, 0x0141, 0xde9e, 0x8fdc, 0xc6e7],
1879 &[0xdf5a, 0x82a5, 0x62b9, 0xb447, 0x92f3],
1880 &[0xda4e, 0x42bc, 0x4462, 0xee98, 0xc2ca],
1881 &[0xbe00, 0xb04a, 0x6ecb, 0xdd89, 0xe278],
1882 &[0x0465, 0xab56, 0xdbb6, 0xa893, 0x665e],
1883 &[0x6b7f, 0x0a19, 0x40f4, 0xa657, 0xdcc5],
1884 &[0x9b50, 0xda5e, 0x24ec, 0x03ad, 0x6dee],
1885 &[0x8d17, 0xcaa7, 0xf4ae, 0xdf6e, 0xbed7],
1886 &[0xdaee, 0x2584, 0x7d30, 0xa626, 0x121a],
1887 &[0xd956, 0x4b43, 0x7570, 0xccd6, 0x4f4a],
1888 &[0x9dcf, 0x1b49, 0x4ba5, 0xfce9, 0xdffe],
1889 &[0x6572, 0xce53, 0xb05a, 0xf6af, 0xdacf],
1890 &[0x1b90, 0x728c, 0x9906, 0xdb68, 0xf46e],
1891 &[0x1606, 0xbeca, 0xbe76, 0x860f, 0xdfa5],
1892 &[0x8b4f, 0xde7a, 0xd220, 0x9fac, 0x2b6f],
1893 &[0xb8fe, 0xebbe, 0xda32, 0x1a5f, 0x8b8b],
1894 &[0x934b, 0x8956, 0xc434, 0x1881, 0xddf7],
1895 &[0x5a95, 0x13fc, 0xf116, 0xd89b, 0x93f9],
1896 &[0xd640, 0x71f1, 0xdd7d, 0x77eb, 0x1cd8],
1897 &[0x348b, 0xaef0, 0xdb2c, 0xebf1, 0x1282],
1898 &[0x50d7, 0xd824, 0x5010, 0xb369, 0x22ea]);
1902 fn test_as_bytes() {
1905 224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
1906 184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
1910 assert_eq!("".as_bytes(), b);
1911 assert_eq!("abc".as_bytes(), b"abc");
1912 assert_eq!("ศไทย中华Việt Nam".as_bytes(), v);
1917 fn test_as_bytes_fail() {
1918 // Don't double free. (I'm not sure if this exercises the
1919 // original problem code path anymore.)
1920 let s = String::from_str("");
1921 let _bytes = s.as_bytes();
1927 let buf = "hello".as_ptr();
1929 assert_eq!(*buf.offset(0), b'h');
1930 assert_eq!(*buf.offset(1), b'e');
1931 assert_eq!(*buf.offset(2), b'l');
1932 assert_eq!(*buf.offset(3), b'l');
1933 assert_eq!(*buf.offset(4), b'o');
1938 fn test_subslice_offset() {
1939 let a = "kernelsprite";
1940 let b = a.slice(7, a.len());
1941 let c = a.slice(0, a.len() - 6);
1942 assert_eq!(a.subslice_offset(b), 7);
1943 assert_eq!(a.subslice_offset(c), 0);
1945 let string = "a\nb\nc";
1946 let lines: Vec<&str> = string.lines().collect();
1947 assert_eq!(string.subslice_offset(lines[0]), 0);
1948 assert_eq!(string.subslice_offset(lines[1]), 2);
1949 assert_eq!(string.subslice_offset(lines[2]), 4);
1954 fn test_subslice_offset_2() {
1955 let a = "alchemiter";
1956 let b = "cruxtruder";
1957 a.subslice_offset(b);
1961 fn vec_str_conversions() {
1962 let s1: String = String::from_str("All mimsy were the borogoves");
1964 let v: Vec<u8> = s1.as_bytes().to_vec();
1965 let s2: String = String::from_str(from_utf8(v.as_slice()).unwrap());
1966 let mut i: uint = 0u;
1967 let n1: uint = s1.len();
1968 let n2: uint = v.len();
1971 let a: u8 = s1.as_bytes()[i];
1972 let b: u8 = s2.as_bytes()[i];
1981 fn test_contains() {
1982 assert!("abcde".contains("bcd"));
1983 assert!("abcde".contains("abcd"));
1984 assert!("abcde".contains("bcde"));
1985 assert!("abcde".contains(""));
1986 assert!("".contains(""));
1987 assert!(!"abcde".contains("def"));
1988 assert!(!"".contains("a"));
1990 let data = "ประเทศไทย中华Việt Nam";
1991 assert!(data.contains("ประเ"));
1992 assert!(data.contains("ะเ"));
1993 assert!(data.contains("中华"));
1994 assert!(!data.contains("ไท华"));
1998 fn test_contains_char() {
1999 assert!("abc".contains_char('b'));
2000 assert!("a".contains_char('a'));
2001 assert!(!"abc".contains_char('d'));
2002 assert!(!"".contains_char('a'));
2007 let s = "ศไทย中华Việt Nam";
2008 let v = vec!['ศ','ไ','ท','ย','中','华','V','i','ệ','t',' ','N','a','m'];
2010 for ch in v.iter() {
2011 assert!(s.char_at(pos) == *ch);
2012 pos += ch.to_string().len();
2017 fn test_char_at_reverse() {
2018 let s = "ศไทย中华Việt Nam";
2019 let v = vec!['ศ','ไ','ท','ย','中','华','V','i','ệ','t',' ','N','a','m'];
2020 let mut pos = s.len();
2021 for ch in v.iter().rev() {
2022 assert!(s.char_at_reverse(pos) == *ch);
2023 pos -= ch.to_string().len();
2028 fn test_escape_unicode() {
2029 assert_eq!("abc".escape_unicode(),
2030 String::from_str("\\u{61}\\u{62}\\u{63}"));
2031 assert_eq!("a c".escape_unicode(),
2032 String::from_str("\\u{61}\\u{20}\\u{63}"));
2033 assert_eq!("\r\n\t".escape_unicode(),
2034 String::from_str("\\u{d}\\u{a}\\u{9}"));
2035 assert_eq!("'\"\\".escape_unicode(),
2036 String::from_str("\\u{27}\\u{22}\\u{5c}"));
2037 assert_eq!("\x00\x01\u{fe}\u{ff}".escape_unicode(),
2038 String::from_str("\\u{0}\\u{1}\\u{fe}\\u{ff}"));
2039 assert_eq!("\u{100}\u{ffff}".escape_unicode(),
2040 String::from_str("\\u{100}\\u{ffff}"));
2041 assert_eq!("\u{10000}\u{10ffff}".escape_unicode(),
2042 String::from_str("\\u{10000}\\u{10ffff}"));
2043 assert_eq!("ab\u{fb00}".escape_unicode(),
2044 String::from_str("\\u{61}\\u{62}\\u{fb00}"));
2045 assert_eq!("\u{1d4ea}\r".escape_unicode(),
2046 String::from_str("\\u{1d4ea}\\u{d}"));
2050 fn test_escape_default() {
2051 assert_eq!("abc".escape_default(), String::from_str("abc"));
2052 assert_eq!("a c".escape_default(), String::from_str("a c"));
2053 assert_eq!("\r\n\t".escape_default(), String::from_str("\\r\\n\\t"));
2054 assert_eq!("'\"\\".escape_default(), String::from_str("\\'\\\"\\\\"));
2055 assert_eq!("\u{100}\u{ffff}".escape_default(),
2056 String::from_str("\\u{100}\\u{ffff}"));
2057 assert_eq!("\u{10000}\u{10ffff}".escape_default(),
2058 String::from_str("\\u{10000}\\u{10ffff}"));
2059 assert_eq!("ab\u{fb00}".escape_default(),
2060 String::from_str("ab\\u{fb00}"));
2061 assert_eq!("\u{1d4ea}\r".escape_default(),
2062 String::from_str("\\u{1d4ea}\\r"));
2066 fn test_total_ord() {
2067 "1234".cmp("123") == Greater;
2068 "123".cmp("1234") == Less;
2069 "1234".cmp("1234") == Equal;
2070 "12345555".cmp("123456") == Less;
2071 "22".cmp("1234") == Greater;
2075 fn test_char_range_at() {
2076 let data = "b¢€𤭢𤭢€¢b";
2077 assert_eq!('b', data.char_range_at(0).ch);
2078 assert_eq!('¢', data.char_range_at(1).ch);
2079 assert_eq!('€', data.char_range_at(3).ch);
2080 assert_eq!('𤭢', data.char_range_at(6).ch);
2081 assert_eq!('𤭢', data.char_range_at(10).ch);
2082 assert_eq!('€', data.char_range_at(14).ch);
2083 assert_eq!('¢', data.char_range_at(17).ch);
2084 assert_eq!('b', data.char_range_at(19).ch);
2088 fn test_char_range_at_reverse_underflow() {
2089 assert_eq!("abc".char_range_at_reverse(0).next, 0);
2093 fn test_iterator() {
2094 let s = "ศไทย中华Việt Nam";
2095 let v = ['ศ','ไ','ท','ย','中','华','V','i','ệ','t',' ','N','a','m'];
2098 let mut it = s.chars();
2101 assert_eq!(c, v[pos]);
2104 assert_eq!(pos, v.len());
2108 fn test_rev_iterator() {
2109 let s = "ศไทย中华Việt Nam";
2110 let v = ['m', 'a', 'N', ' ', 't', 'ệ','i','V','华','中','ย','ท','ไ','ศ'];
2113 let mut it = s.chars().rev();
2116 assert_eq!(c, v[pos]);
2119 assert_eq!(pos, v.len());
2123 fn test_chars_decoding() {
2124 let mut bytes = [0u8; 4];
2125 for c in range(0u32, 0x110000).filter_map(|c| ::core::char::from_u32(c)) {
2126 let len = c.encode_utf8(&mut bytes).unwrap_or(0);
2127 let s = ::core::str::from_utf8(bytes[..len]).unwrap();
2128 if Some(c) != s.chars().next() {
2129 panic!("character {:x}={} does not decode correctly", c as u32, c);
2135 fn test_chars_rev_decoding() {
2136 let mut bytes = [0u8; 4];
2137 for c in range(0u32, 0x110000).filter_map(|c| ::core::char::from_u32(c)) {
2138 let len = c.encode_utf8(&mut bytes).unwrap_or(0);
2139 let s = ::core::str::from_utf8(bytes[..len]).unwrap();
2140 if Some(c) != s.chars().rev().next() {
2141 panic!("character {:x}={} does not decode correctly", c as u32, c);
2147 fn test_iterator_clone() {
2148 let s = "ศไทย中华Việt Nam";
2149 let mut it = s.chars();
2151 assert!(it.zip(it.clone()).all(|(x,y)| x == y));
2155 fn test_bytesator() {
2156 let s = "ศไทย中华Việt Nam";
2158 224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
2159 184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
2164 for b in s.bytes() {
2165 assert_eq!(b, v[pos]);
2171 fn test_bytes_revator() {
2172 let s = "ศไทย中华Việt Nam";
2174 224, 184, 168, 224, 185, 132, 224, 184, 151, 224, 184, 162, 228,
2175 184, 173, 229, 141, 142, 86, 105, 225, 187, 135, 116, 32, 78, 97,
2178 let mut pos = v.len();
2180 for b in s.bytes().rev() {
2182 assert_eq!(b, v[pos]);
2187 fn test_char_indicesator() {
2188 let s = "ศไทย中华Việt Nam";
2189 let p = [0, 3, 6, 9, 12, 15, 18, 19, 20, 23, 24, 25, 26, 27];
2190 let v = ['ศ','ไ','ท','ย','中','华','V','i','ệ','t',' ','N','a','m'];
2193 let mut it = s.char_indices();
2196 assert_eq!(c, (p[pos], v[pos]));
2199 assert_eq!(pos, v.len());
2200 assert_eq!(pos, p.len());
2204 fn test_char_indices_revator() {
2205 let s = "ศไทย中华Việt Nam";
2206 let p = [27, 26, 25, 24, 23, 20, 19, 18, 15, 12, 9, 6, 3, 0];
2207 let v = ['m', 'a', 'N', ' ', 't', 'ệ','i','V','华','中','ย','ท','ไ','ศ'];
2210 let mut it = s.char_indices().rev();
2213 assert_eq!(c, (p[pos], v[pos]));
2216 assert_eq!(pos, v.len());
2217 assert_eq!(pos, p.len());
2221 fn test_splitn_char_iterator() {
2222 let data = "\nMäry häd ä little lämb\nLittle lämb\n";
2224 let split: Vec<&str> = data.splitn(3, ' ').collect();
2225 assert_eq!(split, vec!["\nMäry", "häd", "ä", "little lämb\nLittle lämb\n"]);
2227 let split: Vec<&str> = data.splitn(3, |&: c: char| c == ' ').collect();
2228 assert_eq!(split, vec!["\nMäry", "häd", "ä", "little lämb\nLittle lämb\n"]);
2231 let split: Vec<&str> = data.splitn(3, 'ä').collect();
2232 assert_eq!(split, vec!["\nM", "ry h", "d ", " little lämb\nLittle lämb\n"]);
2234 let split: Vec<&str> = data.splitn(3, |&: c: char| c == 'ä').collect();
2235 assert_eq!(split, vec!["\nM", "ry h", "d ", " little lämb\nLittle lämb\n"]);
2239 fn test_split_char_iterator_no_trailing() {
2240 let data = "\nMäry häd ä little lämb\nLittle lämb\n";
2242 let split: Vec<&str> = data.split('\n').collect();
2243 assert_eq!(split, vec!["", "Märy häd ä little lämb", "Little lämb", ""]);
2245 let split: Vec<&str> = data.split_terminator('\n').collect();
2246 assert_eq!(split, vec!["", "Märy häd ä little lämb", "Little lämb"]);
2251 let data = "\n \tMäry häd\tä little lämb\nLittle lämb\n";
2252 let words: Vec<&str> = data.words().collect();
2253 assert_eq!(words, vec!["Märy", "häd", "ä", "little", "lämb", "Little", "lämb"])
2257 fn test_nfd_chars() {
2259 ($input: expr, $expected: expr) => {
2260 assert_eq!($input.nfd_chars().collect::<String>(), $expected);
2264 t!("\u{1e0b}\u{1c4}", "d\u{307}\u{1c4}");
2265 t!("\u{2026}", "\u{2026}");
2266 t!("\u{2126}", "\u{3a9}");
2267 t!("\u{1e0b}\u{323}", "d\u{323}\u{307}");
2268 t!("\u{1e0d}\u{307}", "d\u{323}\u{307}");
2269 t!("a\u{301}", "a\u{301}");
2270 t!("\u{301}a", "\u{301}a");
2271 t!("\u{d4db}", "\u{1111}\u{1171}\u{11b6}");
2272 t!("\u{ac1c}", "\u{1100}\u{1162}");
2276 fn test_nfkd_chars() {
2278 ($input: expr, $expected: expr) => {
2279 assert_eq!($input.nfkd_chars().collect::<String>(), $expected);
2283 t!("\u{1e0b}\u{1c4}", "d\u{307}DZ\u{30c}");
2284 t!("\u{2026}", "...");
2285 t!("\u{2126}", "\u{3a9}");
2286 t!("\u{1e0b}\u{323}", "d\u{323}\u{307}");
2287 t!("\u{1e0d}\u{307}", "d\u{323}\u{307}");
2288 t!("a\u{301}", "a\u{301}");
2289 t!("\u{301}a", "\u{301}a");
2290 t!("\u{d4db}", "\u{1111}\u{1171}\u{11b6}");
2291 t!("\u{ac1c}", "\u{1100}\u{1162}");
2295 fn test_nfc_chars() {
2297 ($input: expr, $expected: expr) => {
2298 assert_eq!($input.nfc_chars().collect::<String>(), $expected);
2302 t!("\u{1e0b}\u{1c4}", "\u{1e0b}\u{1c4}");
2303 t!("\u{2026}", "\u{2026}");
2304 t!("\u{2126}", "\u{3a9}");
2305 t!("\u{1e0b}\u{323}", "\u{1e0d}\u{307}");
2306 t!("\u{1e0d}\u{307}", "\u{1e0d}\u{307}");
2307 t!("a\u{301}", "\u{e1}");
2308 t!("\u{301}a", "\u{301}a");
2309 t!("\u{d4db}", "\u{d4db}");
2310 t!("\u{ac1c}", "\u{ac1c}");
2311 t!("a\u{300}\u{305}\u{315}\u{5ae}b", "\u{e0}\u{5ae}\u{305}\u{315}b");
2315 fn test_nfkc_chars() {
2317 ($input: expr, $expected: expr) => {
2318 assert_eq!($input.nfkc_chars().collect::<String>(), $expected);
2322 t!("\u{1e0b}\u{1c4}", "\u{1e0b}D\u{17d}");
2323 t!("\u{2026}", "...");
2324 t!("\u{2126}", "\u{3a9}");
2325 t!("\u{1e0b}\u{323}", "\u{1e0d}\u{307}");
2326 t!("\u{1e0d}\u{307}", "\u{1e0d}\u{307}");
2327 t!("a\u{301}", "\u{e1}");
2328 t!("\u{301}a", "\u{301}a");
2329 t!("\u{d4db}", "\u{d4db}");
2330 t!("\u{ac1c}", "\u{ac1c}");
2331 t!("a\u{300}\u{305}\u{315}\u{5ae}b", "\u{e0}\u{5ae}\u{305}\u{315}b");
2336 let data = "\nMäry häd ä little lämb\n\nLittle lämb\n";
2337 let lines: Vec<&str> = data.lines().collect();
2338 assert_eq!(lines, vec!["", "Märy häd ä little lämb", "", "Little lämb"]);
2340 let data = "\nMäry häd ä little lämb\n\nLittle lämb"; // no trailing \n
2341 let lines: Vec<&str> = data.lines().collect();
2342 assert_eq!(lines, vec!["", "Märy häd ä little lämb", "", "Little lämb"]);
2346 fn test_graphemes() {
2347 use core::iter::order;
2348 // official Unicode test data
2349 // from http://www.unicode.org/Public/UCD/latest/ucd/auxiliary/GraphemeBreakTest.txt
2350 let test_same: [(_, &[_]); 325] = [
2351 ("\u{20}\u{20}", &["\u{20}", "\u{20}"]),
2352 ("\u{20}\u{308}\u{20}", &["\u{20}\u{308}", "\u{20}"]),
2353 ("\u{20}\u{D}", &["\u{20}", "\u{D}"]),
2354 ("\u{20}\u{308}\u{D}", &["\u{20}\u{308}", "\u{D}"]),
2355 ("\u{20}\u{A}", &["\u{20}", "\u{A}"]),
2356 ("\u{20}\u{308}\u{A}", &["\u{20}\u{308}", "\u{A}"]),
2357 ("\u{20}\u{1}", &["\u{20}", "\u{1}"]),
2358 ("\u{20}\u{308}\u{1}", &["\u{20}\u{308}", "\u{1}"]),
2359 ("\u{20}\u{300}", &["\u{20}\u{300}"]),
2360 ("\u{20}\u{308}\u{300}", &["\u{20}\u{308}\u{300}"]),
2361 ("\u{20}\u{1100}", &["\u{20}", "\u{1100}"]),
2362 ("\u{20}\u{308}\u{1100}", &["\u{20}\u{308}", "\u{1100}"]),
2363 ("\u{20}\u{1160}", &["\u{20}", "\u{1160}"]),
2364 ("\u{20}\u{308}\u{1160}", &["\u{20}\u{308}", "\u{1160}"]),
2365 ("\u{20}\u{11A8}", &["\u{20}", "\u{11A8}"]),
2366 ("\u{20}\u{308}\u{11A8}", &["\u{20}\u{308}", "\u{11A8}"]),
2367 ("\u{20}\u{AC00}", &["\u{20}", "\u{AC00}"]),
2368 ("\u{20}\u{308}\u{AC00}", &["\u{20}\u{308}", "\u{AC00}"]),
2369 ("\u{20}\u{AC01}", &["\u{20}", "\u{AC01}"]),
2370 ("\u{20}\u{308}\u{AC01}", &["\u{20}\u{308}", "\u{AC01}"]),
2371 ("\u{20}\u{1F1E6}", &["\u{20}", "\u{1F1E6}"]),
2372 ("\u{20}\u{308}\u{1F1E6}", &["\u{20}\u{308}", "\u{1F1E6}"]),
2373 ("\u{20}\u{378}", &["\u{20}", "\u{378}"]),
2374 ("\u{20}\u{308}\u{378}", &["\u{20}\u{308}", "\u{378}"]),
2375 ("\u{D}\u{20}", &["\u{D}", "\u{20}"]),
2376 ("\u{D}\u{308}\u{20}", &["\u{D}", "\u{308}", "\u{20}"]),
2377 ("\u{D}\u{D}", &["\u{D}", "\u{D}"]),
2378 ("\u{D}\u{308}\u{D}", &["\u{D}", "\u{308}", "\u{D}"]),
2379 ("\u{D}\u{A}", &["\u{D}\u{A}"]),
2380 ("\u{D}\u{308}\u{A}", &["\u{D}", "\u{308}", "\u{A}"]),
2381 ("\u{D}\u{1}", &["\u{D}", "\u{1}"]),
2382 ("\u{D}\u{308}\u{1}", &["\u{D}", "\u{308}", "\u{1}"]),
2383 ("\u{D}\u{300}", &["\u{D}", "\u{300}"]),
2384 ("\u{D}\u{308}\u{300}", &["\u{D}", "\u{308}\u{300}"]),
2385 ("\u{D}\u{903}", &["\u{D}", "\u{903}"]),
2386 ("\u{D}\u{1100}", &["\u{D}", "\u{1100}"]),
2387 ("\u{D}\u{308}\u{1100}", &["\u{D}", "\u{308}", "\u{1100}"]),
2388 ("\u{D}\u{1160}", &["\u{D}", "\u{1160}"]),
2389 ("\u{D}\u{308}\u{1160}", &["\u{D}", "\u{308}", "\u{1160}"]),
2390 ("\u{D}\u{11A8}", &["\u{D}", "\u{11A8}"]),
2391 ("\u{D}\u{308}\u{11A8}", &["\u{D}", "\u{308}", "\u{11A8}"]),
2392 ("\u{D}\u{AC00}", &["\u{D}", "\u{AC00}"]),
2393 ("\u{D}\u{308}\u{AC00}", &["\u{D}", "\u{308}", "\u{AC00}"]),
2394 ("\u{D}\u{AC01}", &["\u{D}", "\u{AC01}"]),
2395 ("\u{D}\u{308}\u{AC01}", &["\u{D}", "\u{308}", "\u{AC01}"]),
2396 ("\u{D}\u{1F1E6}", &["\u{D}", "\u{1F1E6}"]),
2397 ("\u{D}\u{308}\u{1F1E6}", &["\u{D}", "\u{308}", "\u{1F1E6}"]),
2398 ("\u{D}\u{378}", &["\u{D}", "\u{378}"]),
2399 ("\u{D}\u{308}\u{378}", &["\u{D}", "\u{308}", "\u{378}"]),
2400 ("\u{A}\u{20}", &["\u{A}", "\u{20}"]),
2401 ("\u{A}\u{308}\u{20}", &["\u{A}", "\u{308}", "\u{20}"]),
2402 ("\u{A}\u{D}", &["\u{A}", "\u{D}"]),
2403 ("\u{A}\u{308}\u{D}", &["\u{A}", "\u{308}", "\u{D}"]),
2404 ("\u{A}\u{A}", &["\u{A}", "\u{A}"]),
2405 ("\u{A}\u{308}\u{A}", &["\u{A}", "\u{308}", "\u{A}"]),
2406 ("\u{A}\u{1}", &["\u{A}", "\u{1}"]),
2407 ("\u{A}\u{308}\u{1}", &["\u{A}", "\u{308}", "\u{1}"]),
2408 ("\u{A}\u{300}", &["\u{A}", "\u{300}"]),
2409 ("\u{A}\u{308}\u{300}", &["\u{A}", "\u{308}\u{300}"]),
2410 ("\u{A}\u{903}", &["\u{A}", "\u{903}"]),
2411 ("\u{A}\u{1100}", &["\u{A}", "\u{1100}"]),
2412 ("\u{A}\u{308}\u{1100}", &["\u{A}", "\u{308}", "\u{1100}"]),
2413 ("\u{A}\u{1160}", &["\u{A}", "\u{1160}"]),
2414 ("\u{A}\u{308}\u{1160}", &["\u{A}", "\u{308}", "\u{1160}"]),
2415 ("\u{A}\u{11A8}", &["\u{A}", "\u{11A8}"]),
2416 ("\u{A}\u{308}\u{11A8}", &["\u{A}", "\u{308}", "\u{11A8}"]),
2417 ("\u{A}\u{AC00}", &["\u{A}", "\u{AC00}"]),
2418 ("\u{A}\u{308}\u{AC00}", &["\u{A}", "\u{308}", "\u{AC00}"]),
2419 ("\u{A}\u{AC01}", &["\u{A}", "\u{AC01}"]),
2420 ("\u{A}\u{308}\u{AC01}", &["\u{A}", "\u{308}", "\u{AC01}"]),
2421 ("\u{A}\u{1F1E6}", &["\u{A}", "\u{1F1E6}"]),
2422 ("\u{A}\u{308}\u{1F1E6}", &["\u{A}", "\u{308}", "\u{1F1E6}"]),
2423 ("\u{A}\u{378}", &["\u{A}", "\u{378}"]),
2424 ("\u{A}\u{308}\u{378}", &["\u{A}", "\u{308}", "\u{378}"]),
2425 ("\u{1}\u{20}", &["\u{1}", "\u{20}"]),
2426 ("\u{1}\u{308}\u{20}", &["\u{1}", "\u{308}", "\u{20}"]),
2427 ("\u{1}\u{D}", &["\u{1}", "\u{D}"]),
2428 ("\u{1}\u{308}\u{D}", &["\u{1}", "\u{308}", "\u{D}"]),
2429 ("\u{1}\u{A}", &["\u{1}", "\u{A}"]),
2430 ("\u{1}\u{308}\u{A}", &["\u{1}", "\u{308}", "\u{A}"]),
2431 ("\u{1}\u{1}", &["\u{1}", "\u{1}"]),
2432 ("\u{1}\u{308}\u{1}", &["\u{1}", "\u{308}", "\u{1}"]),
2433 ("\u{1}\u{300}", &["\u{1}", "\u{300}"]),
2434 ("\u{1}\u{308}\u{300}", &["\u{1}", "\u{308}\u{300}"]),
2435 ("\u{1}\u{903}", &["\u{1}", "\u{903}"]),
2436 ("\u{1}\u{1100}", &["\u{1}", "\u{1100}"]),
2437 ("\u{1}\u{308}\u{1100}", &["\u{1}", "\u{308}", "\u{1100}"]),
2438 ("\u{1}\u{1160}", &["\u{1}", "\u{1160}"]),
2439 ("\u{1}\u{308}\u{1160}", &["\u{1}", "\u{308}", "\u{1160}"]),
2440 ("\u{1}\u{11A8}", &["\u{1}", "\u{11A8}"]),
2441 ("\u{1}\u{308}\u{11A8}", &["\u{1}", "\u{308}", "\u{11A8}"]),
2442 ("\u{1}\u{AC00}", &["\u{1}", "\u{AC00}"]),
2443 ("\u{1}\u{308}\u{AC00}", &["\u{1}", "\u{308}", "\u{AC00}"]),
2444 ("\u{1}\u{AC01}", &["\u{1}", "\u{AC01}"]),
2445 ("\u{1}\u{308}\u{AC01}", &["\u{1}", "\u{308}", "\u{AC01}"]),
2446 ("\u{1}\u{1F1E6}", &["\u{1}", "\u{1F1E6}"]),
2447 ("\u{1}\u{308}\u{1F1E6}", &["\u{1}", "\u{308}", "\u{1F1E6}"]),
2448 ("\u{1}\u{378}", &["\u{1}", "\u{378}"]),
2449 ("\u{1}\u{308}\u{378}", &["\u{1}", "\u{308}", "\u{378}"]),
2450 ("\u{300}\u{20}", &["\u{300}", "\u{20}"]),
2451 ("\u{300}\u{308}\u{20}", &["\u{300}\u{308}", "\u{20}"]),
2452 ("\u{300}\u{D}", &["\u{300}", "\u{D}"]),
2453 ("\u{300}\u{308}\u{D}", &["\u{300}\u{308}", "\u{D}"]),
2454 ("\u{300}\u{A}", &["\u{300}", "\u{A}"]),
2455 ("\u{300}\u{308}\u{A}", &["\u{300}\u{308}", "\u{A}"]),
2456 ("\u{300}\u{1}", &["\u{300}", "\u{1}"]),
2457 ("\u{300}\u{308}\u{1}", &["\u{300}\u{308}", "\u{1}"]),
2458 ("\u{300}\u{300}", &["\u{300}\u{300}"]),
2459 ("\u{300}\u{308}\u{300}", &["\u{300}\u{308}\u{300}"]),
2460 ("\u{300}\u{1100}", &["\u{300}", "\u{1100}"]),
2461 ("\u{300}\u{308}\u{1100}", &["\u{300}\u{308}", "\u{1100}"]),
2462 ("\u{300}\u{1160}", &["\u{300}", "\u{1160}"]),
2463 ("\u{300}\u{308}\u{1160}", &["\u{300}\u{308}", "\u{1160}"]),
2464 ("\u{300}\u{11A8}", &["\u{300}", "\u{11A8}"]),
2465 ("\u{300}\u{308}\u{11A8}", &["\u{300}\u{308}", "\u{11A8}"]),
2466 ("\u{300}\u{AC00}", &["\u{300}", "\u{AC00}"]),
2467 ("\u{300}\u{308}\u{AC00}", &["\u{300}\u{308}", "\u{AC00}"]),
2468 ("\u{300}\u{AC01}", &["\u{300}", "\u{AC01}"]),
2469 ("\u{300}\u{308}\u{AC01}", &["\u{300}\u{308}", "\u{AC01}"]),
2470 ("\u{300}\u{1F1E6}", &["\u{300}", "\u{1F1E6}"]),
2471 ("\u{300}\u{308}\u{1F1E6}", &["\u{300}\u{308}", "\u{1F1E6}"]),
2472 ("\u{300}\u{378}", &["\u{300}", "\u{378}"]),
2473 ("\u{300}\u{308}\u{378}", &["\u{300}\u{308}", "\u{378}"]),
2474 ("\u{903}\u{20}", &["\u{903}", "\u{20}"]),
2475 ("\u{903}\u{308}\u{20}", &["\u{903}\u{308}", "\u{20}"]),
2476 ("\u{903}\u{D}", &["\u{903}", "\u{D}"]),
2477 ("\u{903}\u{308}\u{D}", &["\u{903}\u{308}", "\u{D}"]),
2478 ("\u{903}\u{A}", &["\u{903}", "\u{A}"]),
2479 ("\u{903}\u{308}\u{A}", &["\u{903}\u{308}", "\u{A}"]),
2480 ("\u{903}\u{1}", &["\u{903}", "\u{1}"]),
2481 ("\u{903}\u{308}\u{1}", &["\u{903}\u{308}", "\u{1}"]),
2482 ("\u{903}\u{300}", &["\u{903}\u{300}"]),
2483 ("\u{903}\u{308}\u{300}", &["\u{903}\u{308}\u{300}"]),
2484 ("\u{903}\u{1100}", &["\u{903}", "\u{1100}"]),
2485 ("\u{903}\u{308}\u{1100}", &["\u{903}\u{308}", "\u{1100}"]),
2486 ("\u{903}\u{1160}", &["\u{903}", "\u{1160}"]),
2487 ("\u{903}\u{308}\u{1160}", &["\u{903}\u{308}", "\u{1160}"]),
2488 ("\u{903}\u{11A8}", &["\u{903}", "\u{11A8}"]),
2489 ("\u{903}\u{308}\u{11A8}", &["\u{903}\u{308}", "\u{11A8}"]),
2490 ("\u{903}\u{AC00}", &["\u{903}", "\u{AC00}"]),
2491 ("\u{903}\u{308}\u{AC00}", &["\u{903}\u{308}", "\u{AC00}"]),
2492 ("\u{903}\u{AC01}", &["\u{903}", "\u{AC01}"]),
2493 ("\u{903}\u{308}\u{AC01}", &["\u{903}\u{308}", "\u{AC01}"]),
2494 ("\u{903}\u{1F1E6}", &["\u{903}", "\u{1F1E6}"]),
2495 ("\u{903}\u{308}\u{1F1E6}", &["\u{903}\u{308}", "\u{1F1E6}"]),
2496 ("\u{903}\u{378}", &["\u{903}", "\u{378}"]),
2497 ("\u{903}\u{308}\u{378}", &["\u{903}\u{308}", "\u{378}"]),
2498 ("\u{1100}\u{20}", &["\u{1100}", "\u{20}"]),
2499 ("\u{1100}\u{308}\u{20}", &["\u{1100}\u{308}", "\u{20}"]),
2500 ("\u{1100}\u{D}", &["\u{1100}", "\u{D}"]),
2501 ("\u{1100}\u{308}\u{D}", &["\u{1100}\u{308}", "\u{D}"]),
2502 ("\u{1100}\u{A}", &["\u{1100}", "\u{A}"]),
2503 ("\u{1100}\u{308}\u{A}", &["\u{1100}\u{308}", "\u{A}"]),
2504 ("\u{1100}\u{1}", &["\u{1100}", "\u{1}"]),
2505 ("\u{1100}\u{308}\u{1}", &["\u{1100}\u{308}", "\u{1}"]),
2506 ("\u{1100}\u{300}", &["\u{1100}\u{300}"]),
2507 ("\u{1100}\u{308}\u{300}", &["\u{1100}\u{308}\u{300}"]),
2508 ("\u{1100}\u{1100}", &["\u{1100}\u{1100}"]),
2509 ("\u{1100}\u{308}\u{1100}", &["\u{1100}\u{308}", "\u{1100}"]),
2510 ("\u{1100}\u{1160}", &["\u{1100}\u{1160}"]),
2511 ("\u{1100}\u{308}\u{1160}", &["\u{1100}\u{308}", "\u{1160}"]),
2512 ("\u{1100}\u{11A8}", &["\u{1100}", "\u{11A8}"]),
2513 ("\u{1100}\u{308}\u{11A8}", &["\u{1100}\u{308}", "\u{11A8}"]),
2514 ("\u{1100}\u{AC00}", &["\u{1100}\u{AC00}"]),
2515 ("\u{1100}\u{308}\u{AC00}", &["\u{1100}\u{308}", "\u{AC00}"]),
2516 ("\u{1100}\u{AC01}", &["\u{1100}\u{AC01}"]),
2517 ("\u{1100}\u{308}\u{AC01}", &["\u{1100}\u{308}", "\u{AC01}"]),
2518 ("\u{1100}\u{1F1E6}", &["\u{1100}", "\u{1F1E6}"]),
2519 ("\u{1100}\u{308}\u{1F1E6}", &["\u{1100}\u{308}", "\u{1F1E6}"]),
2520 ("\u{1100}\u{378}", &["\u{1100}", "\u{378}"]),
2521 ("\u{1100}\u{308}\u{378}", &["\u{1100}\u{308}", "\u{378}"]),
2522 ("\u{1160}\u{20}", &["\u{1160}", "\u{20}"]),
2523 ("\u{1160}\u{308}\u{20}", &["\u{1160}\u{308}", "\u{20}"]),
2524 ("\u{1160}\u{D}", &["\u{1160}", "\u{D}"]),
2525 ("\u{1160}\u{308}\u{D}", &["\u{1160}\u{308}", "\u{D}"]),
2526 ("\u{1160}\u{A}", &["\u{1160}", "\u{A}"]),
2527 ("\u{1160}\u{308}\u{A}", &["\u{1160}\u{308}", "\u{A}"]),
2528 ("\u{1160}\u{1}", &["\u{1160}", "\u{1}"]),
2529 ("\u{1160}\u{308}\u{1}", &["\u{1160}\u{308}", "\u{1}"]),
2530 ("\u{1160}\u{300}", &["\u{1160}\u{300}"]),
2531 ("\u{1160}\u{308}\u{300}", &["\u{1160}\u{308}\u{300}"]),
2532 ("\u{1160}\u{1100}", &["\u{1160}", "\u{1100}"]),
2533 ("\u{1160}\u{308}\u{1100}", &["\u{1160}\u{308}", "\u{1100}"]),
2534 ("\u{1160}\u{1160}", &["\u{1160}\u{1160}"]),
2535 ("\u{1160}\u{308}\u{1160}", &["\u{1160}\u{308}", "\u{1160}"]),
2536 ("\u{1160}\u{11A8}", &["\u{1160}\u{11A8}"]),
2537 ("\u{1160}\u{308}\u{11A8}", &["\u{1160}\u{308}", "\u{11A8}"]),
2538 ("\u{1160}\u{AC00}", &["\u{1160}", "\u{AC00}"]),
2539 ("\u{1160}\u{308}\u{AC00}", &["\u{1160}\u{308}", "\u{AC00}"]),
2540 ("\u{1160}\u{AC01}", &["\u{1160}", "\u{AC01}"]),
2541 ("\u{1160}\u{308}\u{AC01}", &["\u{1160}\u{308}", "\u{AC01}"]),
2542 ("\u{1160}\u{1F1E6}", &["\u{1160}", "\u{1F1E6}"]),
2543 ("\u{1160}\u{308}\u{1F1E6}", &["\u{1160}\u{308}", "\u{1F1E6}"]),
2544 ("\u{1160}\u{378}", &["\u{1160}", "\u{378}"]),
2545 ("\u{1160}\u{308}\u{378}", &["\u{1160}\u{308}", "\u{378}"]),
2546 ("\u{11A8}\u{20}", &["\u{11A8}", "\u{20}"]),
2547 ("\u{11A8}\u{308}\u{20}", &["\u{11A8}\u{308}", "\u{20}"]),
2548 ("\u{11A8}\u{D}", &["\u{11A8}", "\u{D}"]),
2549 ("\u{11A8}\u{308}\u{D}", &["\u{11A8}\u{308}", "\u{D}"]),
2550 ("\u{11A8}\u{A}", &["\u{11A8}", "\u{A}"]),
2551 ("\u{11A8}\u{308}\u{A}", &["\u{11A8}\u{308}", "\u{A}"]),
2552 ("\u{11A8}\u{1}", &["\u{11A8}", "\u{1}"]),
2553 ("\u{11A8}\u{308}\u{1}", &["\u{11A8}\u{308}", "\u{1}"]),
2554 ("\u{11A8}\u{300}", &["\u{11A8}\u{300}"]),
2555 ("\u{11A8}\u{308}\u{300}", &["\u{11A8}\u{308}\u{300}"]),
2556 ("\u{11A8}\u{1100}", &["\u{11A8}", "\u{1100}"]),
2557 ("\u{11A8}\u{308}\u{1100}", &["\u{11A8}\u{308}", "\u{1100}"]),
2558 ("\u{11A8}\u{1160}", &["\u{11A8}", "\u{1160}"]),
2559 ("\u{11A8}\u{308}\u{1160}", &["\u{11A8}\u{308}", "\u{1160}"]),
2560 ("\u{11A8}\u{11A8}", &["\u{11A8}\u{11A8}"]),
2561 ("\u{11A8}\u{308}\u{11A8}", &["\u{11A8}\u{308}", "\u{11A8}"]),
2562 ("\u{11A8}\u{AC00}", &["\u{11A8}", "\u{AC00}"]),
2563 ("\u{11A8}\u{308}\u{AC00}", &["\u{11A8}\u{308}", "\u{AC00}"]),
2564 ("\u{11A8}\u{AC01}", &["\u{11A8}", "\u{AC01}"]),
2565 ("\u{11A8}\u{308}\u{AC01}", &["\u{11A8}\u{308}", "\u{AC01}"]),
2566 ("\u{11A8}\u{1F1E6}", &["\u{11A8}", "\u{1F1E6}"]),
2567 ("\u{11A8}\u{308}\u{1F1E6}", &["\u{11A8}\u{308}", "\u{1F1E6}"]),
2568 ("\u{11A8}\u{378}", &["\u{11A8}", "\u{378}"]),
2569 ("\u{11A8}\u{308}\u{378}", &["\u{11A8}\u{308}", "\u{378}"]),
2570 ("\u{AC00}\u{20}", &["\u{AC00}", "\u{20}"]),
2571 ("\u{AC00}\u{308}\u{20}", &["\u{AC00}\u{308}", "\u{20}"]),
2572 ("\u{AC00}\u{D}", &["\u{AC00}", "\u{D}"]),
2573 ("\u{AC00}\u{308}\u{D}", &["\u{AC00}\u{308}", "\u{D}"]),
2574 ("\u{AC00}\u{A}", &["\u{AC00}", "\u{A}"]),
2575 ("\u{AC00}\u{308}\u{A}", &["\u{AC00}\u{308}", "\u{A}"]),
2576 ("\u{AC00}\u{1}", &["\u{AC00}", "\u{1}"]),
2577 ("\u{AC00}\u{308}\u{1}", &["\u{AC00}\u{308}", "\u{1}"]),
2578 ("\u{AC00}\u{300}", &["\u{AC00}\u{300}"]),
2579 ("\u{AC00}\u{308}\u{300}", &["\u{AC00}\u{308}\u{300}"]),
2580 ("\u{AC00}\u{1100}", &["\u{AC00}", "\u{1100}"]),
2581 ("\u{AC00}\u{308}\u{1100}", &["\u{AC00}\u{308}", "\u{1100}"]),
2582 ("\u{AC00}\u{1160}", &["\u{AC00}\u{1160}"]),
2583 ("\u{AC00}\u{308}\u{1160}", &["\u{AC00}\u{308}", "\u{1160}"]),
2584 ("\u{AC00}\u{11A8}", &["\u{AC00}\u{11A8}"]),
2585 ("\u{AC00}\u{308}\u{11A8}", &["\u{AC00}\u{308}", "\u{11A8}"]),
2586 ("\u{AC00}\u{AC00}", &["\u{AC00}", "\u{AC00}"]),
2587 ("\u{AC00}\u{308}\u{AC00}", &["\u{AC00}\u{308}", "\u{AC00}"]),
2588 ("\u{AC00}\u{AC01}", &["\u{AC00}", "\u{AC01}"]),
2589 ("\u{AC00}\u{308}\u{AC01}", &["\u{AC00}\u{308}", "\u{AC01}"]),
2590 ("\u{AC00}\u{1F1E6}", &["\u{AC00}", "\u{1F1E6}"]),
2591 ("\u{AC00}\u{308}\u{1F1E6}", &["\u{AC00}\u{308}", "\u{1F1E6}"]),
2592 ("\u{AC00}\u{378}", &["\u{AC00}", "\u{378}"]),
2593 ("\u{AC00}\u{308}\u{378}", &["\u{AC00}\u{308}", "\u{378}"]),
2594 ("\u{AC01}\u{20}", &["\u{AC01}", "\u{20}"]),
2595 ("\u{AC01}\u{308}\u{20}", &["\u{AC01}\u{308}", "\u{20}"]),
2596 ("\u{AC01}\u{D}", &["\u{AC01}", "\u{D}"]),
2597 ("\u{AC01}\u{308}\u{D}", &["\u{AC01}\u{308}", "\u{D}"]),
2598 ("\u{AC01}\u{A}", &["\u{AC01}", "\u{A}"]),
2599 ("\u{AC01}\u{308}\u{A}", &["\u{AC01}\u{308}", "\u{A}"]),
2600 ("\u{AC01}\u{1}", &["\u{AC01}", "\u{1}"]),
2601 ("\u{AC01}\u{308}\u{1}", &["\u{AC01}\u{308}", "\u{1}"]),
2602 ("\u{AC01}\u{300}", &["\u{AC01}\u{300}"]),
2603 ("\u{AC01}\u{308}\u{300}", &["\u{AC01}\u{308}\u{300}"]),
2604 ("\u{AC01}\u{1100}", &["\u{AC01}", "\u{1100}"]),
2605 ("\u{AC01}\u{308}\u{1100}", &["\u{AC01}\u{308}", "\u{1100}"]),
2606 ("\u{AC01}\u{1160}", &["\u{AC01}", "\u{1160}"]),
2607 ("\u{AC01}\u{308}\u{1160}", &["\u{AC01}\u{308}", "\u{1160}"]),
2608 ("\u{AC01}\u{11A8}", &["\u{AC01}\u{11A8}"]),
2609 ("\u{AC01}\u{308}\u{11A8}", &["\u{AC01}\u{308}", "\u{11A8}"]),
2610 ("\u{AC01}\u{AC00}", &["\u{AC01}", "\u{AC00}"]),
2611 ("\u{AC01}\u{308}\u{AC00}", &["\u{AC01}\u{308}", "\u{AC00}"]),
2612 ("\u{AC01}\u{AC01}", &["\u{AC01}", "\u{AC01}"]),
2613 ("\u{AC01}\u{308}\u{AC01}", &["\u{AC01}\u{308}", "\u{AC01}"]),
2614 ("\u{AC01}\u{1F1E6}", &["\u{AC01}", "\u{1F1E6}"]),
2615 ("\u{AC01}\u{308}\u{1F1E6}", &["\u{AC01}\u{308}", "\u{1F1E6}"]),
2616 ("\u{AC01}\u{378}", &["\u{AC01}", "\u{378}"]),
2617 ("\u{AC01}\u{308}\u{378}", &["\u{AC01}\u{308}", "\u{378}"]),
2618 ("\u{1F1E6}\u{20}", &["\u{1F1E6}", "\u{20}"]),
2619 ("\u{1F1E6}\u{308}\u{20}", &["\u{1F1E6}\u{308}", "\u{20}"]),
2620 ("\u{1F1E6}\u{D}", &["\u{1F1E6}", "\u{D}"]),
2621 ("\u{1F1E6}\u{308}\u{D}", &["\u{1F1E6}\u{308}", "\u{D}"]),
2622 ("\u{1F1E6}\u{A}", &["\u{1F1E6}", "\u{A}"]),
2623 ("\u{1F1E6}\u{308}\u{A}", &["\u{1F1E6}\u{308}", "\u{A}"]),
2624 ("\u{1F1E6}\u{1}", &["\u{1F1E6}", "\u{1}"]),
2625 ("\u{1F1E6}\u{308}\u{1}", &["\u{1F1E6}\u{308}", "\u{1}"]),
2626 ("\u{1F1E6}\u{300}", &["\u{1F1E6}\u{300}"]),
2627 ("\u{1F1E6}\u{308}\u{300}", &["\u{1F1E6}\u{308}\u{300}"]),
2628 ("\u{1F1E6}\u{1100}", &["\u{1F1E6}", "\u{1100}"]),
2629 ("\u{1F1E6}\u{308}\u{1100}", &["\u{1F1E6}\u{308}", "\u{1100}"]),
2630 ("\u{1F1E6}\u{1160}", &["\u{1F1E6}", "\u{1160}"]),
2631 ("\u{1F1E6}\u{308}\u{1160}", &["\u{1F1E6}\u{308}", "\u{1160}"]),
2632 ("\u{1F1E6}\u{11A8}", &["\u{1F1E6}", "\u{11A8}"]),
2633 ("\u{1F1E6}\u{308}\u{11A8}", &["\u{1F1E6}\u{308}", "\u{11A8}"]),
2634 ("\u{1F1E6}\u{AC00}", &["\u{1F1E6}", "\u{AC00}"]),
2635 ("\u{1F1E6}\u{308}\u{AC00}", &["\u{1F1E6}\u{308}", "\u{AC00}"]),
2636 ("\u{1F1E6}\u{AC01}", &["\u{1F1E6}", "\u{AC01}"]),
2637 ("\u{1F1E6}\u{308}\u{AC01}", &["\u{1F1E6}\u{308}", "\u{AC01}"]),
2638 ("\u{1F1E6}\u{1F1E6}", &["\u{1F1E6}\u{1F1E6}"]),
2639 ("\u{1F1E6}\u{308}\u{1F1E6}", &["\u{1F1E6}\u{308}", "\u{1F1E6}"]),
2640 ("\u{1F1E6}\u{378}", &["\u{1F1E6}", "\u{378}"]),
2641 ("\u{1F1E6}\u{308}\u{378}", &["\u{1F1E6}\u{308}", "\u{378}"]),
2642 ("\u{378}\u{20}", &["\u{378}", "\u{20}"]),
2643 ("\u{378}\u{308}\u{20}", &["\u{378}\u{308}", "\u{20}"]),
2644 ("\u{378}\u{D}", &["\u{378}", "\u{D}"]),
2645 ("\u{378}\u{308}\u{D}", &["\u{378}\u{308}", "\u{D}"]),
2646 ("\u{378}\u{A}", &["\u{378}", "\u{A}"]),
2647 ("\u{378}\u{308}\u{A}", &["\u{378}\u{308}", "\u{A}"]),
2648 ("\u{378}\u{1}", &["\u{378}", "\u{1}"]),
2649 ("\u{378}\u{308}\u{1}", &["\u{378}\u{308}", "\u{1}"]),
2650 ("\u{378}\u{300}", &["\u{378}\u{300}"]),
2651 ("\u{378}\u{308}\u{300}", &["\u{378}\u{308}\u{300}"]),
2652 ("\u{378}\u{1100}", &["\u{378}", "\u{1100}"]),
2653 ("\u{378}\u{308}\u{1100}", &["\u{378}\u{308}", "\u{1100}"]),
2654 ("\u{378}\u{1160}", &["\u{378}", "\u{1160}"]),
2655 ("\u{378}\u{308}\u{1160}", &["\u{378}\u{308}", "\u{1160}"]),
2656 ("\u{378}\u{11A8}", &["\u{378}", "\u{11A8}"]),
2657 ("\u{378}\u{308}\u{11A8}", &["\u{378}\u{308}", "\u{11A8}"]),
2658 ("\u{378}\u{AC00}", &["\u{378}", "\u{AC00}"]),
2659 ("\u{378}\u{308}\u{AC00}", &["\u{378}\u{308}", "\u{AC00}"]),
2660 ("\u{378}\u{AC01}", &["\u{378}", "\u{AC01}"]),
2661 ("\u{378}\u{308}\u{AC01}", &["\u{378}\u{308}", "\u{AC01}"]),
2662 ("\u{378}\u{1F1E6}", &["\u{378}", "\u{1F1E6}"]),
2663 ("\u{378}\u{308}\u{1F1E6}", &["\u{378}\u{308}", "\u{1F1E6}"]),
2664 ("\u{378}\u{378}", &["\u{378}", "\u{378}"]),
2665 ("\u{378}\u{308}\u{378}", &["\u{378}\u{308}", "\u{378}"]),
2666 ("\u{61}\u{1F1E6}\u{62}", &["\u{61}", "\u{1F1E6}", "\u{62}"]),
2667 ("\u{1F1F7}\u{1F1FA}", &["\u{1F1F7}\u{1F1FA}"]),
2668 ("\u{1F1F7}\u{1F1FA}\u{1F1F8}", &["\u{1F1F7}\u{1F1FA}\u{1F1F8}"]),
2669 ("\u{1F1F7}\u{1F1FA}\u{1F1F8}\u{1F1EA}",
2670 &["\u{1F1F7}\u{1F1FA}\u{1F1F8}\u{1F1EA}"]),
2671 ("\u{1F1F7}\u{1F1FA}\u{200B}\u{1F1F8}\u{1F1EA}",
2672 &["\u{1F1F7}\u{1F1FA}", "\u{200B}", "\u{1F1F8}\u{1F1EA}"]),
2673 ("\u{1F1E6}\u{1F1E7}\u{1F1E8}", &["\u{1F1E6}\u{1F1E7}\u{1F1E8}"]),
2674 ("\u{1F1E6}\u{200D}\u{1F1E7}\u{1F1E8}", &["\u{1F1E6}\u{200D}",
2675 "\u{1F1E7}\u{1F1E8}"]),
2676 ("\u{1F1E6}\u{1F1E7}\u{200D}\u{1F1E8}",
2677 &["\u{1F1E6}\u{1F1E7}\u{200D}", "\u{1F1E8}"]),
2678 ("\u{20}\u{200D}\u{646}", &["\u{20}\u{200D}", "\u{646}"]),
2679 ("\u{646}\u{200D}\u{20}", &["\u{646}\u{200D}", "\u{20}"]),
2682 let test_diff: [(_, &[_], &[_]); 23] = [
2683 ("\u{20}\u{903}", &["\u{20}\u{903}"], &["\u{20}", "\u{903}"]), ("\u{20}\u{308}\u{903}",
2684 &["\u{20}\u{308}\u{903}"], &["\u{20}\u{308}", "\u{903}"]), ("\u{D}\u{308}\u{903}",
2685 &["\u{D}", "\u{308}\u{903}"], &["\u{D}", "\u{308}", "\u{903}"]), ("\u{A}\u{308}\u{903}",
2686 &["\u{A}", "\u{308}\u{903}"], &["\u{A}", "\u{308}", "\u{903}"]), ("\u{1}\u{308}\u{903}",
2687 &["\u{1}", "\u{308}\u{903}"], &["\u{1}", "\u{308}", "\u{903}"]), ("\u{300}\u{903}",
2688 &["\u{300}\u{903}"], &["\u{300}", "\u{903}"]), ("\u{300}\u{308}\u{903}",
2689 &["\u{300}\u{308}\u{903}"], &["\u{300}\u{308}", "\u{903}"]), ("\u{903}\u{903}",
2690 &["\u{903}\u{903}"], &["\u{903}", "\u{903}"]), ("\u{903}\u{308}\u{903}",
2691 &["\u{903}\u{308}\u{903}"], &["\u{903}\u{308}", "\u{903}"]), ("\u{1100}\u{903}",
2692 &["\u{1100}\u{903}"], &["\u{1100}", "\u{903}"]), ("\u{1100}\u{308}\u{903}",
2693 &["\u{1100}\u{308}\u{903}"], &["\u{1100}\u{308}", "\u{903}"]), ("\u{1160}\u{903}",
2694 &["\u{1160}\u{903}"], &["\u{1160}", "\u{903}"]), ("\u{1160}\u{308}\u{903}",
2695 &["\u{1160}\u{308}\u{903}"], &["\u{1160}\u{308}", "\u{903}"]), ("\u{11A8}\u{903}",
2696 &["\u{11A8}\u{903}"], &["\u{11A8}", "\u{903}"]), ("\u{11A8}\u{308}\u{903}",
2697 &["\u{11A8}\u{308}\u{903}"], &["\u{11A8}\u{308}", "\u{903}"]), ("\u{AC00}\u{903}",
2698 &["\u{AC00}\u{903}"], &["\u{AC00}", "\u{903}"]), ("\u{AC00}\u{308}\u{903}",
2699 &["\u{AC00}\u{308}\u{903}"], &["\u{AC00}\u{308}", "\u{903}"]), ("\u{AC01}\u{903}",
2700 &["\u{AC01}\u{903}"], &["\u{AC01}", "\u{903}"]), ("\u{AC01}\u{308}\u{903}",
2701 &["\u{AC01}\u{308}\u{903}"], &["\u{AC01}\u{308}", "\u{903}"]), ("\u{1F1E6}\u{903}",
2702 &["\u{1F1E6}\u{903}"], &["\u{1F1E6}", "\u{903}"]), ("\u{1F1E6}\u{308}\u{903}",
2703 &["\u{1F1E6}\u{308}\u{903}"], &["\u{1F1E6}\u{308}", "\u{903}"]), ("\u{378}\u{903}",
2704 &["\u{378}\u{903}"], &["\u{378}", "\u{903}"]), ("\u{378}\u{308}\u{903}",
2705 &["\u{378}\u{308}\u{903}"], &["\u{378}\u{308}", "\u{903}"]),
2708 for &(s, g) in test_same.iter() {
2709 // test forward iterator
2710 assert!(order::equals(s.graphemes(true), g.iter().map(|&x| x)));
2711 assert!(order::equals(s.graphemes(false), g.iter().map(|&x| x)));
2713 // test reverse iterator
2714 assert!(order::equals(s.graphemes(true).rev(), g.iter().rev().map(|&x| x)));
2715 assert!(order::equals(s.graphemes(false).rev(), g.iter().rev().map(|&x| x)));
2718 for &(s, gt, gf) in test_diff.iter() {
2719 // test forward iterator
2720 assert!(order::equals(s.graphemes(true), gt.iter().map(|&x| x)));
2721 assert!(order::equals(s.graphemes(false), gf.iter().map(|&x| x)));
2723 // test reverse iterator
2724 assert!(order::equals(s.graphemes(true).rev(), gt.iter().rev().map(|&x| x)));
2725 assert!(order::equals(s.graphemes(false).rev(), gf.iter().rev().map(|&x| x)));
2728 // test the indices iterators
2729 let s = "a̐éö̲\r\n";
2730 let gr_inds = s.grapheme_indices(true).collect::<Vec<(uint, &str)>>();
2731 let b: &[_] = &[(0u, "a̐"), (3, "é"), (6, "ö̲"), (11, "\r\n")];
2732 assert_eq!(gr_inds, b);
2733 let gr_inds = s.grapheme_indices(true).rev().collect::<Vec<(uint, &str)>>();
2734 let b: &[_] = &[(11, "\r\n"), (6, "ö̲"), (3, "é"), (0u, "a̐")];
2735 assert_eq!(gr_inds, b);
2736 let mut gr_inds_iter = s.grapheme_indices(true);
2738 let gr_inds = gr_inds_iter.by_ref();
2739 let e1 = gr_inds.size_hint();
2740 assert_eq!(e1, (1, Some(13)));
2741 let c = gr_inds.count();
2744 let e2 = gr_inds_iter.size_hint();
2745 assert_eq!(e2, (0, Some(0)));
2747 // make sure the reverse iterator does the right thing with "\n" at beginning of string
2749 let gr = s.graphemes(true).rev().collect::<Vec<&str>>();
2750 let b: &[_] = &["\r", "\r\n", "\n"];
2755 fn test_split_strator() {
2756 fn t(s: &str, sep: &str, u: &[&str]) {
2757 let v: Vec<&str> = s.split_str(sep).collect();
2760 t("--1233345--", "12345", &["--1233345--"]);
2761 t("abc::hello::there", "::", &["abc", "hello", "there"]);
2762 t("::hello::there", "::", &["", "hello", "there"]);
2763 t("hello::there::", "::", &["hello", "there", ""]);
2764 t("::hello::there::", "::", &["", "hello", "there", ""]);
2765 t("ประเทศไทย中华Việt Nam", "中华", &["ประเทศไทย", "Việt Nam"]);
2766 t("zzXXXzzYYYzz", "zz", &["", "XXX", "YYY", ""]);
2767 t("zzXXXzYYYz", "XXX", &["zz", "zYYYz"]);
2768 t(".XXX.YYY.", ".", &["", "XXX", "YYY", ""]);
2770 t("zz", "zz", &["",""]);
2771 t("ok", "z", &["ok"]);
2772 t("zzz", "zz", &["","z"]);
2773 t("zzzzz", "zz", &["","","z"]);
2777 fn test_str_default() {
2778 use core::default::Default;
2779 fn t<S: Default + Str>() {
2780 let s: S = Default::default();
2781 assert_eq!(s.as_slice(), "");
2789 fn test_str_container() {
2790 fn sum_len(v: &[&str]) -> uint {
2791 v.iter().map(|x| x.len()).sum()
2794 let s = String::from_str("01234");
2795 assert_eq!(5, sum_len(&["012", "", "34"]));
2796 assert_eq!(5, sum_len(&[String::from_str("01").as_slice(),
2797 String::from_str("2").as_slice(),
2798 String::from_str("34").as_slice(),
2799 String::from_str("").as_slice()]));
2800 assert_eq!(5, sum_len(&[s.as_slice()]));
2804 fn test_str_from_utf8() {
2806 assert_eq!(from_utf8(xs), Ok("hello"));
2808 let xs = "ศไทย中华Việt Nam".as_bytes();
2809 assert_eq!(from_utf8(xs), Ok("ศไทย中华Việt Nam"));
2811 let xs = b"hello\xFF";
2812 assert_eq!(from_utf8(xs), Err(Utf8Error::TooShort));
2819 use prelude::{SliceExt, IteratorExt, SliceConcatExt};
2821 use test::black_box;
2824 fn char_iterator(b: &mut Bencher) {
2825 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2827 b.iter(|| s.chars().count());
2831 fn char_iterator_for(b: &mut Bencher) {
2832 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2835 for ch in s.chars() { black_box(ch) }
2840 fn char_iterator_ascii(b: &mut Bencher) {
2841 let s = "Mary had a little lamb, Little lamb
2842 Mary had a little lamb, Little lamb
2843 Mary had a little lamb, Little lamb
2844 Mary had a little lamb, Little lamb
2845 Mary had a little lamb, Little lamb
2846 Mary had a little lamb, Little lamb";
2848 b.iter(|| s.chars().count());
2852 fn char_iterator_rev(b: &mut Bencher) {
2853 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2855 b.iter(|| s.chars().rev().count());
2859 fn char_iterator_rev_for(b: &mut Bencher) {
2860 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2863 for ch in s.chars().rev() { black_box(ch) }
2868 fn char_indicesator(b: &mut Bencher) {
2869 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2870 let len = s.chars().count();
2872 b.iter(|| assert_eq!(s.char_indices().count(), len));
2876 fn char_indicesator_rev(b: &mut Bencher) {
2877 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2878 let len = s.chars().count();
2880 b.iter(|| assert_eq!(s.char_indices().rev().count(), len));
2884 fn split_unicode_ascii(b: &mut Bencher) {
2885 let s = "ประเทศไทย中华Việt Namประเทศไทย中华Việt Nam";
2887 b.iter(|| assert_eq!(s.split('V').count(), 3));
2891 fn split_unicode_not_ascii(b: &mut Bencher) {
2892 struct NotAscii(char);
2893 impl CharEq for NotAscii {
2894 fn matches(&mut self, c: char) -> bool {
2895 let NotAscii(cc) = *self;
2898 fn only_ascii(&self) -> bool { false }
2900 let s = "ประเทศไทย中华Việt Namประเทศไทย中华Việt Nam";
2902 b.iter(|| assert_eq!(s.split(NotAscii('V')).count(), 3));
2907 fn split_ascii(b: &mut Bencher) {
2908 let s = "Mary had a little lamb, Little lamb, little-lamb.";
2909 let len = s.split(' ').count();
2911 b.iter(|| assert_eq!(s.split(' ').count(), len));
2915 fn split_not_ascii(b: &mut Bencher) {
2916 struct NotAscii(char);
2917 impl CharEq for NotAscii {
2919 fn matches(&mut self, c: char) -> bool {
2920 let NotAscii(cc) = *self;
2923 fn only_ascii(&self) -> bool { false }
2925 let s = "Mary had a little lamb, Little lamb, little-lamb.";
2926 let len = s.split(' ').count();
2928 b.iter(|| assert_eq!(s.split(NotAscii(' ')).count(), len));
2932 fn split_extern_fn(b: &mut Bencher) {
2933 let s = "Mary had a little lamb, Little lamb, little-lamb.";
2934 let len = s.split(' ').count();
2935 fn pred(c: char) -> bool { c == ' ' }
2937 b.iter(|| assert_eq!(s.split(pred).count(), len));
2941 fn split_closure(b: &mut Bencher) {
2942 let s = "Mary had a little lamb, Little lamb, little-lamb.";
2943 let len = s.split(' ').count();
2945 b.iter(|| assert_eq!(s.split(|&: c: char| c == ' ').count(), len));
2949 fn split_slice(b: &mut Bencher) {
2950 let s = "Mary had a little lamb, Little lamb, little-lamb.";
2951 let len = s.split(' ').count();
2953 let c: &[char] = &[' '];
2954 b.iter(|| assert_eq!(s.split(c).count(), len));
2958 fn bench_connect(b: &mut Bencher) {
2959 let s = "ศไทย中华Việt Nam; Mary had a little lamb, Little lamb";
2961 let v = vec![s, s, s, s, s, s, s, s, s, s];
2963 assert_eq!(v.connect(sep).len(), s.len() * 10 + sep.len() * 9);
2968 fn bench_contains_short_short(b: &mut Bencher) {
2969 let haystack = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
2973 assert!(haystack.contains(needle));
2978 fn bench_contains_short_long(b: &mut Bencher) {
2980 Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse quis lorem sit amet dolor \
2981 ultricies condimentum. Praesent iaculis purus elit, ac malesuada quam malesuada in. Duis sed orci \
2982 eros. Suspendisse sit amet magna mollis, mollis nunc luctus, imperdiet mi. Integer fringilla non \
2983 sem ut lacinia. Fusce varius tortor a risus porttitor hendrerit. Morbi mauris dui, ultricies nec \
2984 tempus vel, gravida nec quam.
2986 In est dui, tincidunt sed tempus interdum, adipiscing laoreet ante. Etiam tempor, tellus quis \
2987 sagittis interdum, nulla purus mattis sem, quis auctor erat odio ac tellus. In nec nunc sit amet \
2988 diam volutpat molestie at sed ipsum. Vestibulum laoreet consequat vulputate. Integer accumsan \
2989 lorem ac dignissim placerat. Suspendisse convallis faucibus lorem. Aliquam erat volutpat. In vel \
2990 eleifend felis. Sed suscipit nulla lorem, sed mollis est sollicitudin et. Nam fermentum egestas \
2991 interdum. Curabitur ut nisi justo.
2993 Sed sollicitudin ipsum tellus, ut condimentum leo eleifend nec. Cras ut velit ante. Phasellus nec \
2994 mollis odio. Mauris molestie erat in arcu mattis, at aliquet dolor vehicula. Quisque malesuada \
2995 lectus sit amet nisi pretium, a condimentum ipsum porta. Morbi at dapibus diam. Praesent egestas \
2996 est sed risus elementum, eu rutrum metus ultrices. Etiam fermentum consectetur magna, id rutrum \
2997 felis accumsan a. Aliquam ut pellentesque libero. Sed mi nulla, lobortis eu tortor id, suscipit \
2998 ultricies neque. Morbi iaculis sit amet risus at iaculis. Praesent eget ligula quis turpis \
2999 feugiat suscipit vel non arcu. Interdum et malesuada fames ac ante ipsum primis in faucibus. \
3000 Aliquam sit amet placerat lorem.
3002 Cras a lacus vel ante posuere elementum. Nunc est leo, bibendum ut facilisis vel, bibendum at \
3003 mauris. Nullam adipiscing diam vel odio ornare, luctus adipiscing mi luctus. Nulla facilisi. \
3004 Mauris adipiscing bibendum neque, quis adipiscing lectus tempus et. Sed feugiat erat et nisl \
3005 lobortis pharetra. Donec vitae erat enim. Nullam sit amet felis et quam lacinia tincidunt. Aliquam \
3006 suscipit dapibus urna. Sed volutpat urna in magna pulvinar volutpat. Phasellus nec tellus ac diam \
3009 Nam lectus enim, dapibus non nisi tempor, consectetur convallis massa. Maecenas eleifend dictum \
3010 feugiat. Etiam quis mauris vel risus luctus mattis a a nunc. Nullam orci quam, imperdiet id \
3011 vehicula in, porttitor ut nibh. Duis sagittis adipiscing nisl vitae congue. Donec mollis risus eu \
3012 leo suscipit, varius porttitor nulla porta. Pellentesque ut sem nec nisi euismod vehicula. Nulla \
3013 malesuada sollicitudin quam eu fermentum.";
3014 let needle = "english";
3017 assert!(!haystack.contains(needle));
3022 fn bench_contains_bad_naive(b: &mut Bencher) {
3023 let haystack = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
3024 let needle = "aaaaaaaab";
3027 assert!(!haystack.contains(needle));
3032 fn bench_contains_equal(b: &mut Bencher) {
3033 let haystack = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
3034 let needle = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
3037 assert!(haystack.contains(needle));