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
// This file is part of ICU4X. For terms of use, please see the file // called LICENSE at the top level of the ICU4X source tree // (online at: https://github.com/unicode-org/icu4x/blob/master/LICENSE ). use super::script::SCRIPT_LENGTH; use crate::parser::errors::ParserError; use std::ops::RangeInclusive; use std::str::FromStr; use tinystr::TinyStr8; /// Language subtag (examples: `"en"`, `"csb"`, `"zh"`, `"und"`, etc.) /// /// `Language` represents a Unicode base language code conformat to the /// [`unicode_language_id`] field of the Language and Locale Identifier. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let language: Language = "en".parse() /// .expect("Failed to parse a language subtag."); /// ``` /// /// If the `Language` has no value assigned, it serializes to a string `"und"`, which /// can be then parsed back to an empty `Language` field. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// assert_eq!(Language::default().as_str(), "und"); /// ``` /// /// [`unicode_language_id`]: https://unicode.org/reports/tr35/#unicode_language_id #[derive(Default, Debug, PartialEq, Eq, Clone, Hash, PartialOrd, Ord, Copy)] pub struct Language(Option<TinyStr8>); const LANGUAGE_LENGTH: RangeInclusive<usize> = 2..=8; const UND_VALUE: TinyStr8 = unsafe { TinyStr8::new_unchecked(6_581_877_u64) }; // "und" impl Language { /// A constructor which takes a utf8 slice, parses it and /// produces a well-formed `Language`. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let lang = Language::from_bytes(b"en") /// .expect("Parsing failed."); /// /// assert_eq!(lang, "en"); /// ``` pub fn from_bytes(v: &[u8]) -> Result<Self, ParserError> { let slen = v.len(); let s = TinyStr8::from_bytes(v).map_err(|_| ParserError::InvalidLanguage)?; if !LANGUAGE_LENGTH.contains(&slen) || slen == SCRIPT_LENGTH || !s.is_ascii_alphabetic() { return Err(ParserError::InvalidLanguage); } let value = s.to_ascii_lowercase(); if value == UND_VALUE { Ok(Self(None)) } else { Ok(Self(Some(value))) } } /// Deconstructs the `Language` into raw format to be consumed /// by `from_raw_unchecked`. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let lang = Language::from_bytes(b"en") /// .expect("Parsing failed."); /// /// let raw = lang.into_raw(); /// let lang = unsafe { Language::from_raw_unchecked(raw) }; /// assert_eq!(lang, "en"); /// ``` pub fn into_raw(self) -> Option<u64> { self.0.map(Into::<u64>::into) } /// Constructor which takes a raw value returned by /// `into_raw`. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let lang = Language::from_bytes(b"en") /// .expect("Parsing failed."); /// /// let raw = lang.into_raw(); /// let lang = unsafe { Language::from_raw_unchecked(raw) }; /// assert_eq!(lang, "en"); /// ``` /// /// # Safety /// /// This function accepts a `u64` that is expected to be a valid `TinyStr8` /// representing a `Language` subtag in canonical syntax. pub const unsafe fn from_raw_unchecked(v: Option<u64>) -> Self { Self(match v { Some(v) => Some(TinyStr8::new_unchecked(v)), None => None, }) } /// A helper function for displaying /// a `Language` subtag as a `&str`. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let lang = Language::from_bytes(b"en") /// .expect("Parsing failed."); /// /// assert_eq!(lang.as_str(), "en"); /// ``` /// /// `Notice`: For many use cases, such as comparison, /// `Language` implements `PartialEq<&str>` which allows for direct comparisons. pub fn as_str(&self) -> &str { self.0.as_deref().unwrap_or("und") } /// Resets the `Language` subtag to an empty one. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let mut lang: Language = "csb".parse() /// .expect("Parsing failed."); /// /// assert_eq!(lang.as_str(), "csb"); /// /// lang.clear(); /// /// assert_eq!(lang.as_str(), "und"); /// ``` pub fn clear(&mut self) { self.0.take(); } /// Tests if the `Language` subtag is empty. /// /// # Examples /// /// ``` /// use icu_locid::subtags::Language; /// /// let mut lang: Language = "und".parse() /// .expect("Parsing failed."); /// /// assert_eq!(lang.is_empty(), true); /// /// lang.clear(); /// /// assert_eq!(lang.is_empty(), true); /// ``` pub fn is_empty(self) -> bool { self.0.is_none() } } impl FromStr for Language { type Err = ParserError; fn from_str(source: &str) -> Result<Self, Self::Err> { Self::from_bytes(source.as_bytes()) } } impl std::fmt::Display for Language { fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result { f.write_str(self.as_str()) } } impl PartialEq<&str> for Language { fn eq(&self, other: &&str) -> bool { self.as_str() == *other } } impl<'l> From<&'l Language> for &'l str { fn from(input: &'l Language) -> Self { input.as_str() } }