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::{option, str::Chars}; |
66 | |
67 | mod decompose; |
68 | mod lookups; |
69 | mod normalize; |
70 | mod perfect_hash; |
71 | mod quick_check; |
72 | mod recompose; |
73 | mod replace; |
74 | mod stream_safe; |
75 | mod tables; |
76 | |
77 | #[doc (hidden)] |
78 | pub mod __test_api; |
79 | #[cfg (test)] |
80 | mod test; |
81 | |
82 | /// Methods for composing and decomposing characters. |
83 | pub mod char { |
84 | pub use crate::normalize::{ |
85 | compose, decompose_canonical, decompose_cjk_compat_variants, decompose_compatible, |
86 | }; |
87 | |
88 | pub use crate::lookups::{canonical_combining_class, is_combining_mark}; |
89 | |
90 | /// Return whether the given character is assigned (`General_Category` != `Unassigned`) |
91 | /// and not Private-Use (`General_Category` != `Private_Use`), in the supported version |
92 | /// of Unicode. |
93 | pub use crate::tables::is_public_assigned; |
94 | } |
95 | |
96 | /// Methods for iterating over strings while applying Unicode normalizations |
97 | /// as described in |
98 | /// [Unicode Standard Annex #15](http://www.unicode.org/reports/tr15/). |
99 | pub trait UnicodeNormalization<I: Iterator<Item = char>> { |
100 | /// Returns an iterator over the string in Unicode Normalization Form D |
101 | /// (canonical decomposition). |
102 | fn nfd(self) -> Decompositions<I>; |
103 | |
104 | /// Returns an iterator over the string in Unicode Normalization Form KD |
105 | /// (compatibility decomposition). |
106 | fn nfkd(self) -> Decompositions<I>; |
107 | |
108 | /// An Iterator over the string in Unicode Normalization Form C |
109 | /// (canonical decomposition followed by canonical composition). |
110 | fn nfc(self) -> Recompositions<I>; |
111 | |
112 | /// An Iterator over the string in Unicode Normalization Form KC |
113 | /// (compatibility decomposition followed by canonical composition). |
114 | fn nfkc(self) -> Recompositions<I>; |
115 | |
116 | /// A transformation which replaces CJK Compatibility Ideograph codepoints |
117 | /// with normal forms using Standardized Variation Sequences. This is not |
118 | /// part of the canonical or compatibility decomposition algorithms, but |
119 | /// performing it before those algorithms produces normalized output which |
120 | /// better preserves the intent of the original text. |
121 | /// |
122 | /// Note that many systems today ignore variation selectors, so these |
123 | /// may not immediately help text display as intended, but they at |
124 | /// least preserve the information in a standardized form, giving |
125 | /// implementations the option to recognize them. |
126 | fn cjk_compat_variants(self) -> Replacements<I>; |
127 | |
128 | /// An Iterator over the string with Conjoining Grapheme Joiner characters |
129 | /// inserted according to the Stream-Safe Text Process (UAX15-D4) |
130 | fn stream_safe(self) -> StreamSafe<I>; |
131 | } |
132 | |
133 | impl<'a> UnicodeNormalization<Chars<'a>> for &'a str { |
134 | #[inline ] |
135 | fn nfd(self) -> Decompositions<Chars<'a>> { |
136 | Decompositions::new_canonical(self.chars()) |
137 | } |
138 | |
139 | #[inline ] |
140 | fn nfkd(self) -> Decompositions<Chars<'a>> { |
141 | Decompositions::new_compatible(self.chars()) |
142 | } |
143 | |
144 | #[inline ] |
145 | fn nfc(self) -> Recompositions<Chars<'a>> { |
146 | Recompositions::new_canonical(self.chars()) |
147 | } |
148 | |
149 | #[inline ] |
150 | fn nfkc(self) -> Recompositions<Chars<'a>> { |
151 | Recompositions::new_compatible(self.chars()) |
152 | } |
153 | |
154 | #[inline ] |
155 | fn cjk_compat_variants(self) -> Replacements<Chars<'a>> { |
156 | replace::new_cjk_compat_variants(self.chars()) |
157 | } |
158 | |
159 | #[inline ] |
160 | fn stream_safe(self) -> StreamSafe<Chars<'a>> { |
161 | StreamSafe::new(self.chars()) |
162 | } |
163 | } |
164 | |
165 | impl UnicodeNormalization<option::IntoIter<char>> for char { |
166 | #[inline ] |
167 | fn nfd(self) -> Decompositions<option::IntoIter<char>> { |
168 | Decompositions::new_canonical(Some(self).into_iter()) |
169 | } |
170 | |
171 | #[inline ] |
172 | fn nfkd(self) -> Decompositions<option::IntoIter<char>> { |
173 | Decompositions::new_compatible(Some(self).into_iter()) |
174 | } |
175 | |
176 | #[inline ] |
177 | fn nfc(self) -> Recompositions<option::IntoIter<char>> { |
178 | Recompositions::new_canonical(Some(self).into_iter()) |
179 | } |
180 | |
181 | #[inline ] |
182 | fn nfkc(self) -> Recompositions<option::IntoIter<char>> { |
183 | Recompositions::new_compatible(Some(self).into_iter()) |
184 | } |
185 | |
186 | #[inline ] |
187 | fn cjk_compat_variants(self) -> Replacements<option::IntoIter<char>> { |
188 | replace::new_cjk_compat_variants(Some(self).into_iter()) |
189 | } |
190 | |
191 | #[inline ] |
192 | fn stream_safe(self) -> StreamSafe<option::IntoIter<char>> { |
193 | StreamSafe::new(Some(self).into_iter()) |
194 | } |
195 | } |
196 | |
197 | impl<I: Iterator<Item = char>> UnicodeNormalization<I> for I { |
198 | #[inline ] |
199 | fn nfd(self) -> Decompositions<I> { |
200 | Decompositions::new_canonical(self) |
201 | } |
202 | |
203 | #[inline ] |
204 | fn nfkd(self) -> Decompositions<I> { |
205 | Decompositions::new_compatible(self) |
206 | } |
207 | |
208 | #[inline ] |
209 | fn nfc(self) -> Recompositions<I> { |
210 | Recompositions::new_canonical(self) |
211 | } |
212 | |
213 | #[inline ] |
214 | fn nfkc(self) -> Recompositions<I> { |
215 | Recompositions::new_compatible(self) |
216 | } |
217 | |
218 | #[inline ] |
219 | fn cjk_compat_variants(self) -> Replacements<I> { |
220 | replace::new_cjk_compat_variants(self) |
221 | } |
222 | |
223 | #[inline ] |
224 | fn stream_safe(self) -> StreamSafe<I> { |
225 | StreamSafe::new(self) |
226 | } |
227 | } |
228 | |