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

// This file is part of ICU4X. For terms of use, please see the file
// called LICENSE at the top level of the ICU4X source tree
// (online at: https://github.com/unicode-org/icu4x/blob/main/LICENSE ).

//! Segment strings by lines, graphemes, words, and sentences.
//!
//! This module is published as its own crate ([`icu_segmenter`](https://docs.rs/icu_segmenter/latest/icu_segmenter/))
//! and as part of the [`icu`](https://docs.rs/icu/latest/icu/) crate. See the latter for more details on the ICU4X project.
//!
//! This module contains segmenter implementation for the following rules.
//!
//! - Line segmenter that is compatible with [Unicode Standard Annex #14][UAX14], _Unicode Line
//!   Breaking Algorithm_, with options to tailor line-breaking behavior for CSS [`line-break`] and
//!   [`word-break`] properties.
//! - Grapheme cluster segmenter, word segmenter, and sentence segmenter that are compatible with
//!   [Unicode Standard Annex #29][UAX29], _Unicode Text Segmentation_.
//!
//! [UAX14]: https://www.unicode.org/reports/tr14/
//! [UAX29]: https://www.unicode.org/reports/tr29/
//! [`line-break`]: https://drafts.csswg.org/css-text-3/#line-break-property
//! [`word-break`]: https://drafts.csswg.org/css-text-3/#word-break-property
//!
//! # Examples
//!
//! ## Line Break
//!
//! Find line break opportunities:
//!
//!```rust
//! use icu::segmenter::LineSegmenter;
//!
//! let segmenter = LineSegmenter::new_auto();
//!
//! let breakpoints: Vec<usize> = segmenter
//!     .segment_str("Hello World. Xin chào thế giới!")
//!     .collect();
//! assert_eq!(&breakpoints, &[0, 6, 13, 17, 23, 29, 36]);
//! ```
//!
//! See [`LineSegmenter`] for more examples.
//!
//! ## Grapheme Cluster Break
//!
//! Find all grapheme cluster boundaries:
//!
//!```rust
//! use icu::segmenter::GraphemeClusterSegmenter;
//!
//! let segmenter = GraphemeClusterSegmenter::new();
//!
//! let breakpoints: Vec<usize> = segmenter
//!     .segment_str("Hello World. Xin chào thế giới!")
//!     .collect();
//! assert_eq!(
//!     &breakpoints,
//!     &[
//!         0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18,
//!         19, 21, 22, 23, 24, 25, 28, 29, 30, 31, 34, 35, 36
//!     ]
//! );
//! ```
//!
//! See [`GraphemeClusterSegmenter`] for more examples.
//!
//! ## Word Break
//!
//! Find all word boundaries:
//!
//!```rust
//! use icu::segmenter::WordSegmenter;
//!
//! let segmenter = WordSegmenter::new_auto();
//!
//! let breakpoints: Vec<usize> = segmenter
//!     .segment_str("Hello World. Xin chào thế giới!")
//!     .collect();
//! assert_eq!(
//!     &breakpoints,
//!     &[0, 5, 6, 11, 12, 13, 16, 17, 22, 23, 28, 29, 35, 36]
//! );
//! ```
//!
//! See [`WordSegmenter`] for more examples.
//!
//! ## Sentence Break
//!
//! Segment the string into sentences:
//!
//!```rust
//! use icu::segmenter::SentenceSegmenter;
//!
//! let segmenter = SentenceSegmenter::new();
//!
//! let breakpoints: Vec<usize> = segmenter
//!     .segment_str("Hello World. Xin chào thế giới!")
//!     .collect();
//! assert_eq!(&breakpoints, &[0, 13, 36]);
//! ```
//!
//! See [`SentenceSegmenter`] for more examples.

// https://github.com/unicode-org/icu4x/blob/main/docs/process/boilerplate.md#library-annotations
#![cfg_attr(not(any(test, feature = "std")), no_std)]
#![cfg_attr(
    not(test),
    deny(
        clippy::indexing_slicing,
        clippy::unwrap_used,
        clippy::expect_used,
        clippy::panic,
        clippy::exhaustive_structs,
        clippy::exhaustive_enums,
        missing_debug_implementations,
    )
)]
#![warn(missing_docs)]

extern crate alloc;

mod complex;
mod error;
mod indices;
mod iterator_helpers;
mod rule_segmenter;

mod grapheme;
mod line;
mod sentence;
mod word;

pub mod provider;

// icu_datagen uses symbols, but we don't want to expose this implementation detail to the users.
#[doc(hidden)]
pub mod symbols;

// Main Segmenter and BreakIterator public types
pub use crate::grapheme::GraphemeClusterBreakIterator;
pub use crate::grapheme::GraphemeClusterSegmenter;
pub use crate::line::LineBreakIterator;
pub use crate::line::LineSegmenter;
pub use crate::sentence::SentenceBreakIterator;
pub use crate::sentence::SentenceSegmenter;
pub use crate::word::WordBreakIterator;
pub use crate::word::WordSegmenter;

// Options structs and enums
pub use crate::line::LineBreakOptions;
pub use crate::line::LineBreakStrictness;
pub use crate::line::LineBreakWordOption;
pub use crate::word::WordType;

// Typedefs
pub use crate::grapheme::GraphemeClusterBreakIteratorLatin1;
pub use crate::grapheme::GraphemeClusterBreakIteratorPotentiallyIllFormedUtf8;
pub use crate::grapheme::GraphemeClusterBreakIteratorUtf16;
pub use crate::grapheme::GraphemeClusterBreakIteratorUtf8;
pub use crate::line::LineBreakIteratorLatin1;
pub use crate::line::LineBreakIteratorPotentiallyIllFormedUtf8;
pub use crate::line::LineBreakIteratorUtf16;
pub use crate::line::LineBreakIteratorUtf8;
pub use crate::sentence::SentenceBreakIteratorLatin1;
pub use crate::sentence::SentenceBreakIteratorPotentiallyIllFormedUtf8;
pub use crate::sentence::SentenceBreakIteratorUtf16;
pub use crate::sentence::SentenceBreakIteratorUtf8;
pub use crate::word::WordBreakIteratorLatin1;
pub use crate::word::WordBreakIteratorPotentiallyIllFormedUtf8;
pub use crate::word::WordBreakIteratorUtf16;
pub use crate::word::WordBreakIteratorUtf8;

pub use error::SegmenterError;

#[doc(no_inline)]
pub use SegmenterError as Error;