summaryrefslogtreecommitdiffstats
path: root/third_party/rust/unicode-normalization/src/lib.rs
blob: 21c3bf1f954ba56e3c433fc10663b0888a3cf81f (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
// 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 = "0.1.20"
//! ```

#![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"
)]
#![cfg_attr(not(feature = "std"), no_std)]

#[cfg(not(feature = "std"))]
extern crate alloc;

#[cfg(feature = "std")]
extern crate core;

extern crate tinyvec;

pub use crate::decompose::Decompositions;
pub use crate::quick_check::{
    is_nfc, is_nfc_quick, is_nfc_stream_safe, is_nfc_stream_safe_quick, is_nfd, is_nfd_quick,
    is_nfd_stream_safe, is_nfd_stream_safe_quick, is_nfkc, is_nfkc_quick, is_nfkd, is_nfkd_quick,
    IsNormalized,
};
pub use crate::recompose::Recompositions;
pub use crate::replace::Replacements;
pub use crate::stream_safe::StreamSafe;
pub use crate::tables::UNICODE_VERSION;
use core::{
    str::Chars,
    option,
};

mod no_std_prelude;

mod decompose;
mod lookups;
mod normalize;
mod perfect_hash;
mod quick_check;
mod recompose;
mod replace;
mod stream_safe;

#[rustfmt::skip]
mod tables;

#[doc(hidden)]
pub mod __test_api;
#[cfg(test)]
mod test;

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

    pub use crate::lookups::{canonical_combining_class, is_combining_mark};

    /// Return whether the given character is assigned (`General_Category` != `Unassigned`)
    /// and not Private-Use (`General_Category` != `Private_Use`), in the supported version
    /// of Unicode.
    pub use crate::tables::is_public_assigned;
}

/// 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).
    fn nfd(self) -> Decompositions<I>;

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

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

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

    /// A transformation which replaces CJK Compatibility Ideograph codepoints
    /// with normal forms using Standardized Variation Sequences. This is not
    /// part of the canonical or compatibility decomposition algorithms, but
    /// performing it before those algorithms produces normalized output which
    /// better preserves the intent of the original text.
    ///
    /// Note that many systems today ignore variation selectors, so these
    /// may not immediately help text display as intended, but they at
    /// least preserve the information in a standardized form, giving
    /// implementations the option to recognize them.
    fn cjk_compat_variants(self) -> Replacements<I>;

    /// An Iterator over the string with Conjoining Grapheme Joiner characters
    /// inserted according to the Stream-Safe Text Process (UAX15-D4)
    fn stream_safe(self) -> StreamSafe<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())
    }

    #[inline]
    fn cjk_compat_variants(self) -> Replacements<Chars<'a>> {
        replace::new_cjk_compat_variants(self.chars())
    }

    #[inline]
    fn stream_safe(self) -> StreamSafe<Chars<'a>> {
        StreamSafe::new(self.chars())
    }
}


impl UnicodeNormalization<option::IntoIter<char>> for char {
    #[inline]
    fn nfd(self) -> Decompositions<option::IntoIter<char>> {
        decompose::new_canonical(Some(self).into_iter())
    }

    #[inline]
    fn nfkd(self) -> Decompositions<option::IntoIter<char>> {
        decompose::new_compatible(Some(self).into_iter())
    }

    #[inline]
    fn nfc(self) -> Recompositions<option::IntoIter<char>> {
        recompose::new_canonical(Some(self).into_iter())
    }

    #[inline]
    fn nfkc(self) -> Recompositions<option::IntoIter<char>> {
        recompose::new_compatible(Some(self).into_iter())
    }

    #[inline]
    fn cjk_compat_variants(self) -> Replacements<option::IntoIter<char>> {
        replace::new_cjk_compat_variants(Some(self).into_iter())
    }

    #[inline]
    fn stream_safe(self) -> StreamSafe<option::IntoIter<char>> {
        StreamSafe::new(Some(self).into_iter())
    }
}

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)
    }

    #[inline]
    fn cjk_compat_variants(self) -> Replacements<I> {
        replace::new_cjk_compat_variants(self)
    }

    #[inline]
    fn stream_safe(self) -> StreamSafe<I> {
        StreamSafe::new(self)
    }
}