summaryrefslogtreecommitdiffstats
path: root/third_party/rust/unicode-normalization/src/lib.rs
blob: 59259980506e508b2ada2a29efda29429195c634 (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
// 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.

//! Unicode character composition and decomposition utilities
//! as described in
//! [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/).
//!
//! ```rust
//! extern crate unicode_normalization;
//!
//! use unicode_normalization::char::compose;
//! use unicode_normalization::UnicodeNormalization;
//!
//! fn main() {
//!     assert_eq!(compose('A','\u{30a}'), Some('Å'));
//!
//!     let s = "ÅΩ";
//!     let c = s.nfc().collect::<String>();
//!     assert_eq!(c, "ÅΩ");
//! }
//! ```
//!
//! # crates.io
//!
//! You can use this package in your project by adding the following
//! to your `Cargo.toml`:
//!
//! ```toml
//! [dependencies]
//! unicode-normalization = "0.1.0"
//! ```

#![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")]

pub use tables::UNICODE_VERSION;
pub use decompose::Decompositions;
pub use recompose::Recompositions;
use std::str::Chars;

mod decompose;
mod normalize;
mod recompose;
mod tables;

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

/// Methods for composing and decomposing characters.
pub mod char {
    pub use normalize::{decompose_canonical, decompose_compatible, compose};

    /// Look up the canonical combining class of a character.
    pub use tables::normalization::canonical_combining_class;

    /// Return whether the given character is a combining mark (`General_Category=Mark`)
    pub use tables::normalization::is_combining_mark;
}


/// Methods for iterating over strings while applying Unicode normalizations
/// as described in
/// [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/).
pub trait UnicodeNormalization<I: Iterator<Item=char>> {
    /// Returns an iterator over the string in Unicode Normalization Form D
    /// (canonical decomposition).
    #[inline]
    fn nfd(self) -> Decompositions<I>;

    /// Returns an iterator over the string in Unicode Normalization Form KD
    /// (compatibility decomposition).
    #[inline]
    fn nfkd(self) -> Decompositions<I>;

    /// An Iterator over the string in Unicode Normalization Form C
    /// (canonical decomposition followed by canonical composition).
    #[inline]
    fn nfc(self) -> Recompositions<I>;

    /// An Iterator over the string in Unicode Normalization Form KC
    /// (compatibility decomposition followed by canonical composition).
    #[inline]
    fn nfkc(self) -> Recompositions<I>;
}

impl<'a> UnicodeNormalization<Chars<'a>> for &'a str {
    #[inline]
    fn nfd(self) -> Decompositions<Chars<'a>> {
        decompose::new_canonical(self.chars())
    }

    #[inline]
    fn nfkd(self) -> Decompositions<Chars<'a>> {
        decompose::new_compatible(self.chars())
    }

    #[inline]
    fn nfc(self) -> Recompositions<Chars<'a>> {
        recompose::new_canonical(self.chars())
    }

    #[inline]
    fn nfkc(self) -> Recompositions<Chars<'a>> {
        recompose::new_compatible(self.chars())
    }
}

impl<I: Iterator<Item=char>> UnicodeNormalization<I> for I {
    #[inline]
    fn nfd(self) -> Decompositions<I> {
        decompose::new_canonical(self)
    }

    #[inline]
    fn nfkd(self) -> Decompositions<I> {
        decompose::new_compatible(self)
    }

    #[inline]
    fn nfc(self) -> Recompositions<I> {
        recompose::new_canonical(self)
    }

    #[inline]
    fn nfkc(self) -> Recompositions<I> {
        recompose::new_compatible(self)
    }
}