aboutsummaryrefslogtreecommitdiff
path: root/unicode-segmentation/src/lib.rs
blob: fce3c52efe3dfd3ec6fe6cbab975a90433c24e81 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
// Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

//! Iterators which split strings on Grapheme Cluster, Word or Sentence boundaries, according
//! to the [Unicode Standard Annex #29](http://www.unicode.org/reports/tr29/) rules.
//!
//! ```rust
//! extern crate unicode_segmentation;
//!
//! use unicode_segmentation::UnicodeSegmentation;
//!
//! fn main() {
//!     let s = "a̐éö̲\r\n";
//!     let g = UnicodeSegmentation::graphemes(s, true).collect::<Vec<&str>>();
//!     let b: &[_] = &["a̐", "é", "ö̲", "\r\n"];
//!     assert_eq!(g, b);
//!
//!     let s = "The quick (\"brown\") fox can't jump 32.3 feet, right?";
//!     let w = s.unicode_words().collect::<Vec<&str>>();
//!     let b: &[_] = &["The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right"];
//!     assert_eq!(w, b);
//!
//!     let s = "The quick (\"brown\")  fox";
//!     let w = s.split_word_bounds().collect::<Vec<&str>>();
//!     let b: &[_] = &["The", " ", "quick", " ", "(", "\"", "brown", "\"", ")", "  ", "fox"];
//!     assert_eq!(w, b);
//! }
//! ```
//!
//! # no_std
//!
//! unicode-segmentation does not depend on libstd, so it can be used in crates
//! with the `#![no_std]` attribute.
//!
//! # crates.io
//!
//! You can use this package in your project by adding the following
//! to your `Cargo.toml`:
//!
//! ```toml
//! [dependencies]
//! unicode-segmentation = "1.3.0"
//! ```

#![deny(missing_docs, unsafe_code)]
#![doc(html_logo_url = "https://unicode-rs.github.io/unicode-rs_sm.png",
       html_favicon_url = "https://unicode-rs.github.io/unicode-rs_sm.png")]

#![no_std]

#[cfg(test)]
#[macro_use]
extern crate std;

#[cfg(test)]
#[macro_use]
extern crate quickcheck;

pub use grapheme::{Graphemes, GraphemeIndices};
pub use grapheme::{GraphemeCursor, GraphemeIncomplete};
pub use tables::UNICODE_VERSION;
pub use word::{UWordBounds, UWordBoundIndices, UnicodeWords};
pub use sentence::{USentenceBounds, USentenceBoundIndices, UnicodeSentences};

mod grapheme;
mod tables;
mod word;
mod sentence;

#[cfg(test)]
mod test;
#[cfg(test)]
mod testdata;

/// Methods for segmenting strings according to
/// [Unicode Standard Annex #29](http://www.unicode.org/reports/tr29/).
pub trait UnicodeSegmentation {
    /// Returns an iterator over the [grapheme clusters][graphemes] of `self`.
    ///
    /// [graphemes]: http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries
    ///
    /// If `is_extended` is true, the iterator is over the
    /// *extended grapheme clusters*;
    /// otherwise, the iterator is over the *legacy grapheme clusters*.
    /// [UAX#29](http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries)
    /// recommends extended grapheme cluster boundaries for general processing.
    ///
    /// # Examples
    ///
    /// ```
    /// # use self::unicode_segmentation::UnicodeSegmentation;
    /// 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 graphemes<'a>(&'a self, is_extended: bool) -> Graphemes<'a>;

    /// Returns an iterator over the grapheme clusters of `self` and their
    /// byte offsets. See `graphemes()` for more information.
    ///
    /// # Examples
    ///
    /// ```
    /// # use self::unicode_segmentation::UnicodeSegmentation;
    /// 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 grapheme_indices<'a>(&'a self, is_extended: bool) -> GraphemeIndices<'a>;

    /// Returns an iterator over the words of `self`, separated on
    /// [UAX#29 word boundaries](http://www.unicode.org/reports/tr29/#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](http://unicode.org/reports/tr44/#Alphabetic)
    /// property, or with
    /// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).
    ///
    /// # Example
    ///
    /// ```
    /// # use self::unicode_segmentation::UnicodeSegmentation;
    /// 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_words<'a>(&'a self) -> UnicodeWords<'a>;

    /// Returns an iterator over substrings of `self` separated on
    /// [UAX#29 word boundaries](http://www.unicode.org/reports/tr29/#Word_Boundaries).
    ///
    /// The concatenation of the substrings returned by this function is just the original string.
    ///
    /// # Example
    ///
    /// ```
    /// # use self::unicode_segmentation::UnicodeSegmentation;
    /// 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_bounds<'a>(&'a self) -> UWordBounds<'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
    ///
    /// ```
    /// # use self::unicode_segmentation::UnicodeSegmentation;
    /// 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 split_word_bound_indices<'a>(&'a self) -> UWordBoundIndices<'a>;

    /// Returns an iterator over substrings of `self` separated on
    /// [UAX#29 sentence boundaries](http://www.unicode.org/reports/tr29/#Sentence_Boundaries).
    ///
    /// The concatenation of the substrings returned by this function is just the original string.
    fn unicode_sentences<'a>(&'a self) -> UnicodeSentences<'a>;

    /// Returns an iterator over substrings of `self` separated on
    /// [UAX#29 sentence boundaries](http://www.unicode.org/reports/tr29/#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](http://unicode.org/reports/tr44/#Alphabetic)
    /// property, or with
    /// [General_Category=Number](http://unicode.org/reports/tr44/#General_Category_Values).
    fn split_sentence_bounds<'a>(&'a self) -> USentenceBounds<'a>;

    /// Returns an iterator over substrings of `self`, split on UAX#29 sentence boundaries,
    /// and their offsets. See `split_sentence_bounds()` for more information.
    fn split_sentence_bound_indices<'a>(&'a self) -> USentenceBoundIndices<'a>;
}

impl UnicodeSegmentation for str {
    #[inline]
    fn graphemes(&self, is_extended: bool) -> Graphemes {
        grapheme::new_graphemes(self, is_extended)
    }

    #[inline]
    fn grapheme_indices(&self, is_extended: bool) -> GraphemeIndices {
        grapheme::new_grapheme_indices(self, is_extended)
    }

    #[inline]
    fn unicode_words(&self) -> UnicodeWords {
        word::new_unicode_words(self)
    }

    #[inline]
    fn split_word_bounds(&self) -> UWordBounds {
        word::new_word_bounds(self)
    }

    #[inline]
    fn split_word_bound_indices(&self) -> UWordBoundIndices {
        word::new_word_bound_indices(self)
    }

    #[inline]
    fn unicode_sentences(&self) -> UnicodeSentences {
        sentence::new_unicode_sentences(self)
    }

    #[inline]
    fn split_sentence_bounds(&self) -> USentenceBounds {
        sentence::new_sentence_bounds(self)
    }

    #[inline]
    fn split_sentence_bound_indices(&self) -> USentenceBoundIndices {
        sentence::new_sentence_bound_indices(self)
    }
}