[−][src]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 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

ⓘImportant traits for Graphemes<'a>
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);

ⓘImportant traits for GraphemeIndices<'a>
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);

ⓘImportant traits for UnicodeWords<'a>
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);

ⓘImportant traits for UWordBounds<'a>
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);

ⓘImportant traits for UWordBoundIndices<'a>
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);

ⓘImportant traits for UnicodeSentences<'a>
fn unicode_sentences<'a>(&'a self) -> UnicodeSentences<'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.

ⓘImportant traits for USentenceBounds<'a>
fn split_sentence_bounds<'a>(&'a self) -> USentenceBounds<'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.

ⓘImportant traits for USentenceBoundIndices<'a>
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.

Loading content...

Implementors

impl UnicodeSegmentation for str[src]

Loading content...