1 | // Copyright 2012-2015 The Rust Project Developers. See the COPYRIGHT |
2 | // file at the top-level directory of this distribution and at |
3 | // http://rust-lang.org/COPYRIGHT. |
4 | // |
5 | // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or |
6 | // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license |
7 | // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your |
8 | // option. This file may not be copied, modified, or distributed |
9 | // except according to those terms. |
10 | |
11 | //! Unicode character composition and decomposition utilities |
12 | //! as described in |
13 | //! [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/). |
14 | //! |
15 | //! ```rust |
16 | //! extern crate unicode_normalization; |
17 | //! |
18 | //! use unicode_normalization::char::compose; |
19 | //! use unicode_normalization::UnicodeNormalization; |
20 | //! |
21 | //! fn main() { |
22 | //! assert_eq!(compose('A' ,' \u{30a}' ), Some('Å' )); |
23 | //! |
24 | //! let s = "ÅΩ" ; |
25 | //! let c = s.nfc().collect::<String>(); |
26 | //! assert_eq!(c, "ÅΩ" ); |
27 | //! } |
28 | //! ``` |
29 | //! |
30 | //! # crates.io |
31 | //! |
32 | //! You can use this package in your project by adding the following |
33 | //! to your `Cargo.toml`: |
34 | //! |
35 | //! ```toml |
36 | //! [dependencies] |
37 | //! unicode-normalization = "0.1.20" |
38 | //! ``` |
39 | |
40 | #![deny (missing_docs, unsafe_code)] |
41 | #![doc ( |
42 | html_logo_url = "https://unicode-rs.github.io/unicode-rs_sm.png" , |
43 | html_favicon_url = "https://unicode-rs.github.io/unicode-rs_sm.png" |
44 | )] |
45 | #![cfg_attr (not(feature = "std" ), no_std)] |
46 | |
47 | #[cfg (not(feature = "std" ))] |
48 | extern crate alloc; |
49 | |
50 | #[cfg (feature = "std" )] |
51 | extern crate core; |
52 | |
53 | extern crate tinyvec; |
54 | |
55 | pub use crate::decompose::Decompositions; |
56 | pub use crate::quick_check::{ |
57 | is_nfc, is_nfc_quick, is_nfc_stream_safe, is_nfc_stream_safe_quick, is_nfd, is_nfd_quick, |
58 | is_nfd_stream_safe, is_nfd_stream_safe_quick, is_nfkc, is_nfkc_quick, is_nfkd, is_nfkd_quick, |
59 | IsNormalized, |
60 | }; |
61 | pub use crate::recompose::Recompositions; |
62 | pub use crate::replace::Replacements; |
63 | pub use crate::stream_safe::StreamSafe; |
64 | pub use crate::tables::UNICODE_VERSION; |
65 | use core::{ |
66 | str::Chars, |
67 | option, |
68 | }; |
69 | |
70 | mod no_std_prelude; |
71 | |
72 | mod decompose; |
73 | mod lookups; |
74 | mod normalize; |
75 | mod perfect_hash; |
76 | mod quick_check; |
77 | mod recompose; |
78 | mod replace; |
79 | mod stream_safe; |
80 | |
81 | #[rustfmt::skip] |
82 | mod tables; |
83 | |
84 | #[doc (hidden)] |
85 | pub mod __test_api; |
86 | #[cfg (test)] |
87 | mod test; |
88 | |
89 | /// Methods for composing and decomposing characters. |
90 | pub mod char { |
91 | pub use crate::normalize::{ |
92 | compose, decompose_canonical, decompose_cjk_compat_variants, decompose_compatible, |
93 | }; |
94 | |
95 | pub use crate::lookups::{canonical_combining_class, is_combining_mark}; |
96 | |
97 | /// Return whether the given character is assigned (`General_Category` != `Unassigned`) |
98 | /// and not Private-Use (`General_Category` != `Private_Use`), in the supported version |
99 | /// of Unicode. |
100 | pub use crate::tables::is_public_assigned; |
101 | } |
102 | |
103 | /// Methods for iterating over strings while applying Unicode normalizations |
104 | /// as described in |
105 | /// [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/). |
106 | pub trait UnicodeNormalization<I: Iterator<Item = char>> { |
107 | /// Returns an iterator over the string in Unicode Normalization Form D |
108 | /// (canonical decomposition). |
109 | fn nfd(self) -> Decompositions<I>; |
110 | |
111 | /// Returns an iterator over the string in Unicode Normalization Form KD |
112 | /// (compatibility decomposition). |
113 | fn nfkd(self) -> Decompositions<I>; |
114 | |
115 | /// An Iterator over the string in Unicode Normalization Form C |
116 | /// (canonical decomposition followed by canonical composition). |
117 | fn nfc(self) -> Recompositions<I>; |
118 | |
119 | /// An Iterator over the string in Unicode Normalization Form KC |
120 | /// (compatibility decomposition followed by canonical composition). |
121 | fn nfkc(self) -> Recompositions<I>; |
122 | |
123 | /// A transformation which replaces CJK Compatibility Ideograph codepoints |
124 | /// with normal forms using Standardized Variation Sequences. This is not |
125 | /// part of the canonical or compatibility decomposition algorithms, but |
126 | /// performing it before those algorithms produces normalized output which |
127 | /// better preserves the intent of the original text. |
128 | /// |
129 | /// Note that many systems today ignore variation selectors, so these |
130 | /// may not immediately help text display as intended, but they at |
131 | /// least preserve the information in a standardized form, giving |
132 | /// implementations the option to recognize them. |
133 | fn cjk_compat_variants(self) -> Replacements<I>; |
134 | |
135 | /// An Iterator over the string with Conjoining Grapheme Joiner characters |
136 | /// inserted according to the Stream-Safe Text Process (UAX15-D4) |
137 | fn stream_safe(self) -> StreamSafe<I>; |
138 | } |
139 | |
140 | impl<'a> UnicodeNormalization<Chars<'a>> for &'a str { |
141 | #[inline ] |
142 | fn nfd(self) -> Decompositions<Chars<'a>> { |
143 | decompose::new_canonical(self.chars()) |
144 | } |
145 | |
146 | #[inline ] |
147 | fn nfkd(self) -> Decompositions<Chars<'a>> { |
148 | decompose::new_compatible(self.chars()) |
149 | } |
150 | |
151 | #[inline ] |
152 | fn nfc(self) -> Recompositions<Chars<'a>> { |
153 | recompose::new_canonical(self.chars()) |
154 | } |
155 | |
156 | #[inline ] |
157 | fn nfkc(self) -> Recompositions<Chars<'a>> { |
158 | recompose::new_compatible(self.chars()) |
159 | } |
160 | |
161 | #[inline ] |
162 | fn cjk_compat_variants(self) -> Replacements<Chars<'a>> { |
163 | replace::new_cjk_compat_variants(self.chars()) |
164 | } |
165 | |
166 | #[inline ] |
167 | fn stream_safe(self) -> StreamSafe<Chars<'a>> { |
168 | StreamSafe::new(self.chars()) |
169 | } |
170 | } |
171 | |
172 | |
173 | impl UnicodeNormalization<option::IntoIter<char>> for char { |
174 | #[inline ] |
175 | fn nfd(self) -> Decompositions<option::IntoIter<char>> { |
176 | decompose::new_canonical(Some(self).into_iter()) |
177 | } |
178 | |
179 | #[inline ] |
180 | fn nfkd(self) -> Decompositions<option::IntoIter<char>> { |
181 | decompose::new_compatible(Some(self).into_iter()) |
182 | } |
183 | |
184 | #[inline ] |
185 | fn nfc(self) -> Recompositions<option::IntoIter<char>> { |
186 | recompose::new_canonical(Some(self).into_iter()) |
187 | } |
188 | |
189 | #[inline ] |
190 | fn nfkc(self) -> Recompositions<option::IntoIter<char>> { |
191 | recompose::new_compatible(Some(self).into_iter()) |
192 | } |
193 | |
194 | #[inline ] |
195 | fn cjk_compat_variants(self) -> Replacements<option::IntoIter<char>> { |
196 | replace::new_cjk_compat_variants(Some(self).into_iter()) |
197 | } |
198 | |
199 | #[inline ] |
200 | fn stream_safe(self) -> StreamSafe<option::IntoIter<char>> { |
201 | StreamSafe::new(Some(self).into_iter()) |
202 | } |
203 | } |
204 | |
205 | impl<I: Iterator<Item = char>> UnicodeNormalization<I> for I { |
206 | #[inline ] |
207 | fn nfd(self) -> Decompositions<I> { |
208 | decompose::new_canonical(self) |
209 | } |
210 | |
211 | #[inline ] |
212 | fn nfkd(self) -> Decompositions<I> { |
213 | decompose::new_compatible(self) |
214 | } |
215 | |
216 | #[inline ] |
217 | fn nfc(self) -> Recompositions<I> { |
218 | recompose::new_canonical(self) |
219 | } |
220 | |
221 | #[inline ] |
222 | fn nfkc(self) -> Recompositions<I> { |
223 | recompose::new_compatible(self) |
224 | } |
225 | |
226 | #[inline ] |
227 | fn cjk_compat_variants(self) -> Replacements<I> { |
228 | replace::new_cjk_compat_variants(self) |
229 | } |
230 | |
231 | #[inline ] |
232 | fn stream_safe(self) -> StreamSafe<I> { |
233 | StreamSafe::new(self) |
234 | } |
235 | } |
236 | |