Trait unicode_segmentation::UnicodeSegmentation

pub trait UnicodeSegmentation {
    fn graphemes<'a>(&'a self, is_extended: bool) -> Graphemes<'a>;
    fn grapheme_indices<'a>(&'a self, is_extended: bool) -> GraphemeIndices<'a>;
    fn unicode_words<'a>(&'a self) -> UnicodeWords<'a>;
    fn unicode_word_indices<'a>(&'a self) -> UnicodeWordIndices<'a>;
    fn split_word_bounds<'a>(&'a self) -> UWordBounds<'a>;
    fn split_word_bound_indices<'a>(&'a self) -> UWordBoundIndices<'a>;
    fn unicode_sentences<'a>(&'a self) -> UnicodeSentences<'a>;
    fn split_sentence_bounds<'a>(&'a self) -> USentenceBounds<'a>;
    fn split_sentence_bound_indices<'a>(&'a self) -> USentenceBoundIndices<'a>;
}

Methods for segmenting strings according to Unicode Standard Annex #29.

Required methods

fn graphemes<'a>(&'a self, is_extended: bool) -> Graphemes<'a>

Returns an iterator over the grapheme clusters of self.

If is_extended is true, the iterator is over the extended grapheme clusters; otherwise, the iterator is over the legacy grapheme clusters. UAX#29 recommends extended grapheme cluster boundaries for general processing.

Examples

let gr1 = UnicodeSegmentation::graphemes("a\u{310}e\u{301}o\u{308}\u{332}", true)
          .collect::<Vec<&str>>();
let b: &[_] = &["a\u{310}", "e\u{301}", "o\u{308}\u{332}"];

assert_eq!(&gr1[..], b);

let gr2 = UnicodeSegmentation::graphemes("a\r\nb🇷🇺🇸🇹", true).collect::<Vec<&str>>();
let b: &[_] = &["a", "\r\n", "b", "🇷🇺", "🇸🇹"];

assert_eq!(&gr2[..], b);

fn grapheme_indices<'a>(&'a self, is_extended: bool) -> GraphemeIndices<'a>

Returns an iterator over the grapheme clusters of self and their byte offsets. See graphemes() for more information.

Examples

let gr_inds = UnicodeSegmentation::grapheme_indices("a̐éö̲\r\n", true)
              .collect::<Vec<(usize, &str)>>();
let b: &[_] = &[(0, "a̐"), (3, "é"), (6, "ö̲"), (11, "\r\n")];

assert_eq!(&gr_inds[..], b);

fn unicode_words<'a>(&'a self) -> UnicodeWords<'a>

Returns an iterator over the words of self, separated on UAX#29 word boundaries.

Here, “words” are just those substrings which, after splitting on UAX#29 word boundaries, contain any alphanumeric characters. That is, the substring must contain at least one character with the Alphabetic property, or with General_Category=Number.

Example

let uws = "The quick (\"brown\") fox can't jump 32.3 feet, right?";
let uw1 = uws.unicode_words().collect::<Vec<&str>>();
let b: &[_] = &["The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right"];

assert_eq!(&uw1[..], b);

fn unicode_word_indices<'a>(&'a self) -> UnicodeWordIndices<'a>

Returns an iterator over the words of self, separated on UAX#29 word boundaries, and their offsets.

Here, “words” are just those substrings which, after splitting on UAX#29 word boundaries, contain any alphanumeric characters. That is, the substring must contain at least one character with the Alphabetic property, or with General_Category=Number.

Example

let uwis = "The quick (\"brown\") fox can't jump 32.3 feet, right?";
let uwi1 = uwis.unicode_word_indices().collect::<Vec<(usize, &str)>>();
let b: &[_] = &[(0, "The"), (4, "quick"), (12, "brown"), (20, "fox"), (24, "can't"),
                (30, "jump"), (35, "32.3"), (40, "feet"), (46, "right")];

assert_eq!(&uwi1[..], b);

fn split_word_bounds<'a>(&'a self) -> UWordBounds<'a>

Returns an iterator over substrings of self separated on UAX#29 word boundaries.

The concatenation of the substrings returned by this function is just the original string.

Example

let swu1 = "The quick (\"brown\")  fox".split_word_bounds().collect::<Vec<&str>>();
let b: &[_] = &["The", " ", "quick", " ", "(", "\"", "brown", "\"", ")", "  ", "fox"];

assert_eq!(&swu1[..], b);

fn split_word_bound_indices<'a>(&'a self) -> UWordBoundIndices<'a>

Returns an iterator over substrings of self, split on UAX#29 word boundaries, and their offsets. See split_word_bounds() for more information.

Example

let swi1 = "Brr, it's 29.3°F!".split_word_bound_indices().collect::<Vec<(usize, &str)>>();
let b: &[_] = &[(0, "Brr"), (3, ","), (4, " "), (5, "it's"), (9, " "), (10, "29.3"),
                (14, "°"), (16, "F"), (17, "!")];

assert_eq!(&swi1[..], b);

fn unicode_sentences<'a>(&'a self) -> UnicodeSentences<'a>

Returns an iterator over substrings of self separated on UAX#29 sentence boundaries.

Here, “sentences” are just those substrings which, after splitting on UAX#29 sentence boundaries, contain any alphanumeric characters. That is, the substring must contain at least one character with the Alphabetic property, or with General_Category=Number.

Example

let uss = "Mr. Fox jumped. [...] The dog was too lazy.";
let us1 = uss.unicode_sentences().collect::<Vec<&str>>();
let b: &[_] = &["Mr. ", "Fox jumped. ", "The dog was too lazy."];

assert_eq!(&us1[..], b);

fn split_sentence_bounds<'a>(&'a self) -> USentenceBounds<'a>

Returns an iterator over substrings of self separated on UAX#29 sentence boundaries.

The concatenation of the substrings returned by this function is just the original string.

Example

let ssbs = "Mr. Fox jumped. [...] The dog was too lazy.";
let ssb1 = ssbs.split_sentence_bounds().collect::<Vec<&str>>();
let b: &[_] = &["Mr. ", "Fox jumped. ", "[...] ", "The dog was too lazy."];

assert_eq!(&ssb1[..], b);

fn split_sentence_bound_indices<'a>(&'a self) -> USentenceBoundIndices<'a>

Returns an iterator over substrings of self, split on UAX#29 sentence boundaries, and their offsets. See split_sentence_bounds() for more information.

Example

let ssis = "Mr. Fox jumped. [...] The dog was too lazy.";
let ssi1 = ssis.split_sentence_bound_indices().collect::<Vec<(usize, &str)>>();
let b: &[_] = &[(0, "Mr. "), (4, "Fox jumped. "), (16, "[...] "),
                (22, "The dog was too lazy.")];

assert_eq!(&ssi1[..], b);

Loading content...

Implementors

impl UnicodeSegmentation for str

fn graphemes(&self, is_extended: bool) -> Graphemes<'_>

fn grapheme_indices(&self, is_extended: bool) -> GraphemeIndices<'_>

fn unicode_words(&self) -> UnicodeWords<'_>

fn unicode_word_indices(&self) -> UnicodeWordIndices<'_>

fn split_word_bounds(&self) -> UWordBounds<'_>

fn split_word_bound_indices(&self) -> UWordBoundIndices<'_>

fn unicode_sentences(&self) -> UnicodeSentences<'_>

fn split_sentence_bounds(&self) -> USentenceBounds<'_>

fn split_sentence_bound_indices(&self) -> USentenceBoundIndices<'_>

Loading content...