unic/lib.rs
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
// Copyright 2017 The UNIC Project Developers.
//
// See the COPYRIGHT file at the top-level directory of this distribution.
//
// 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.
#![warn(
bad_style,
missing_debug_implementations,
missing_docs,
unconditional_recursion
)]
#![forbid(unsafe_code)]
//! # UNIC: Unicode and Internationalization Crates for Rust
//!
//! The `unic` super-crate (this) is a collection of all UNIC components, providing
//! an easy way of access to all functionalities, when all or many are needed,
//! instead of importing components one-by-one, and ensuring all components
//! imported are compatible in algorithms and consistent data-wise.
//!
//! ## Major Components
//!
//! - [`char`](/unic-char): Unicode Character utilities.
//!
//! - [`ucd`](/unic-ucd): Unicode Character Database. (UAX\#44).
//!
//! - [`bidi`](/unic-bidi): Unicode Bidirectional Algorithm (UAX\#9).
//!
//! - [`normal`](/unic-normal): Unicode Normalization Forms (UAX\#15).
//!
//! - [`segment`](/unic-segment): Unicode Text Segmentation (UAX\#29).
//!
//! - [`idna`](/unic-idna): Unicode IDNA Compatibility Processing (UTS\#46).
//!
//!
//! ## A Basic Example
//!
//! ```rust
//! use unic::ucd::common::is_alphanumeric;
//! use unic::bidi::BidiInfo;
//! use unic::normal::StrNormalForm;
//! use unic::segment::{GraphemeIndices, Graphemes, WordBoundIndices, WordBounds, Words};
//! use unic::ucd::normal::compose;
//! use unic::ucd::{is_cased, Age, BidiClass, CharAge, CharBidiClass, StrBidiClass, UnicodeVersion};
//!
//! #[cfg_attr(rustfmt, rustfmt_skip)]
//! #[test]
//! fn test_sample() {
//!
//! // Age
//!
//! assert_eq!(Age::of('A').unwrap().actual(), UnicodeVersion { major: 1, minor: 1, micro: 0 });
//! assert_eq!(Age::of('\u{A0000}'), None);
//! assert_eq!(
//! Age::of('\u{10FFFF}').unwrap().actual(),
//! UnicodeVersion { major: 2, minor: 0, micro: 0 }
//! );
//!
//! if let Some(age) = '🦊'.age() {
//! assert_eq!(age.actual().major, 9);
//! assert_eq!(age.actual().minor, 0);
//! assert_eq!(age.actual().micro, 0);
//! }
//!
//! // Bidi
//!
//! let text = concat![
//! "א",
//! "ב",
//! "ג",
//! "a",
//! "b",
//! "c",
//! ];
//!
//! assert!(!text.has_bidi_explicit());
//! assert!(text.has_rtl());
//! assert!(text.has_ltr());
//!
//! assert_eq!(text.chars().nth(0).unwrap().bidi_class(), BidiClass::RightToLeft);
//! assert!(!text.chars().nth(0).unwrap().is_ltr());
//! assert!(text.chars().nth(0).unwrap().is_rtl());
//!
//! assert_eq!(text.chars().nth(3).unwrap().bidi_class(), BidiClass::LeftToRight);
//! assert!(text.chars().nth(3).unwrap().is_ltr());
//! assert!(!text.chars().nth(3).unwrap().is_rtl());
//!
//! let bidi_info = BidiInfo::new(text, None);
//! assert_eq!(bidi_info.paragraphs.len(), 1);
//!
//! let para = &bidi_info.paragraphs[0];
//! assert_eq!(para.level.number(), 1);
//! assert_eq!(para.level.is_rtl(), true);
//!
//! let line = para.range.clone();
//! let display = bidi_info.reorder_line(para, line);
//! assert_eq!(
//! display,
//! concat![
//! "a",
//! "b",
//! "c",
//! "ג",
//! "ב",
//! "א",
//! ]
//! );
//!
//! // Case
//!
//! assert_eq!(is_cased('A'), true);
//! assert_eq!(is_cased('א'), false);
//!
//! // Normalization
//!
//! assert_eq!(compose('A', '\u{030A}'), Some('Å'));
//!
//! let s = "ÅΩ";
//! let c = s.nfc().collect::<String>();
//! assert_eq!(c, "ÅΩ");
//!
//! // Segmentation
//!
//! assert_eq!(
//! Graphemes::new("a\u{310}e\u{301}o\u{308}\u{332}").collect::<Vec<&str>>(),
//! &["a\u{310}", "e\u{301}", "o\u{308}\u{332}"]
//! );
//!
//! assert_eq!(
//! Graphemes::new("a\r\nb🇺🇳🇮🇨").collect::<Vec<&str>>(),
//! &["a", "\r\n", "b", "🇺🇳", "🇮🇨"]
//! );
//!
//! assert_eq!(
//! GraphemeIndices::new("a̐éö̲\r\n").collect::<Vec<(usize, &str)>>(),
//! &[(0, "a̐"), (3, "é"), (6, "ö̲"), (11, "\r\n")]
//! );
//!
//! assert_eq!(
//! Words::new(
//! "The quick (\"brown\") fox can't jump 32.3 feet, right?",
//! |s: &&str| s.chars().any(is_alphanumeric),
//! ).collect::<Vec<&str>>(),
//! &["The", "quick", "brown", "fox", "can't", "jump", "32.3", "feet", "right"]
//! );
//!
//! assert_eq!(
//! WordBounds::new("The quick (\"brown\") fox").collect::<Vec<&str>>(),
//! &["The", " ", "quick", " ", "(", "\"", "brown", "\"", ")", " ", " ", "fox"]
//! );
//!
//! assert_eq!(
//! WordBoundIndices::new("Brr, it's 29.3°F!").collect::<Vec<(usize, &str)>>(),
//! &[
//! (0, "Brr"),
//! (3, ","),
//! (4, " "),
//! (5, "it's"),
//! (9, " "),
//! (10, "29.3"),
//! (14, "°"),
//! (16, "F"),
//! (17, "!")
//! ]
//! );
//! }
//! ```
pub use unic_bidi as bidi;
pub use unic_char as char;
pub use unic_emoji as emoji;
pub use unic_idna as idna;
pub use unic_normal as normal;
pub use unic_segment as segment;
pub use unic_ucd as ucd;
/// The [Unicode version](https://www.unicode.org/versions/) of data
pub use crate::ucd::UNICODE_VERSION;
mod pkg_info;
pub use crate::pkg_info::{PKG_DESCRIPTION, PKG_NAME, PKG_VERSION};