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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598
// 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/main/LICENSE ).
use core::cmp::Ordering;
use core::str::FromStr;
#[allow(deprecated)]
use crate::ordering::SubtagOrderingResult;
use crate::parser::{
parse_language_identifier, parse_language_identifier_with_single_variant, ParserError,
ParserMode, SubtagIterator,
};
use crate::subtags;
use alloc::string::String;
use writeable::Writeable;
/// A core struct representing a [`Unicode BCP47 Language Identifier`].
///
/// # Examples
///
/// ```
/// use icu::locid::{
/// langid,
/// subtags::{language, region},
/// };
///
/// let li = langid!("en-US");
///
/// assert_eq!(li.language, language!("en"));
/// assert_eq!(li.script, None);
/// assert_eq!(li.region, Some(region!("US")));
/// assert_eq!(li.variants.len(), 0);
/// ```
///
/// # Parsing
///
/// Unicode recognizes three levels of standard conformance for any language identifier:
///
/// * *well-formed* - syntactically correct
/// * *valid* - well-formed and only uses registered language, region, script and variant subtags...
/// * *canonical* - valid and no deprecated codes or structure.
///
/// At the moment parsing normalizes a well-formed language identifier converting
/// `_` separators to `-` and adjusting casing to conform to the Unicode standard.
///
/// Any bogus subtags will cause the parsing to fail with an error.
/// No subtag validation is performed.
///
/// # Examples
///
/// ```
/// use icu::locid::{
/// langid,
/// subtags::{language, region, script, variant},
/// };
///
/// let li = langid!("eN_latn_Us-Valencia");
///
/// assert_eq!(li.language, language!("en"));
/// assert_eq!(li.script, Some(script!("Latn")));
/// assert_eq!(li.region, Some(region!("US")));
/// assert_eq!(li.variants.get(0), Some(&variant!("valencia")));
/// ```
///
/// [`Unicode BCP47 Language Identifier`]: https://unicode.org/reports/tr35/tr35.html#Unicode_language_identifier
#[derive(Default, PartialEq, Eq, Clone, Hash)]
#[allow(clippy::exhaustive_structs)] // This struct is stable (and invoked by a macro)
pub struct LanguageIdentifier {
/// Language subtag of the language identifier.
pub language: subtags::Language,
/// Script subtag of the language identifier.
pub script: Option<subtags::Script>,
/// Region subtag of the language identifier.
pub region: Option<subtags::Region>,
/// Variant subtags of the language identifier.
pub variants: subtags::Variants,
}
impl LanguageIdentifier {
/// A constructor which takes a utf8 slice, parses it and
/// produces a well-formed [`LanguageIdentifier`].
///
/// # Examples
///
/// ```
/// use icu::locid::LanguageIdentifier;
///
/// LanguageIdentifier::try_from_bytes(b"en-US").expect("Parsing failed");
/// ```
pub fn try_from_bytes(v: &[u8]) -> Result<Self, ParserError> {
parse_language_identifier(v, ParserMode::LanguageIdentifier)
}
#[doc(hidden)]
#[allow(clippy::type_complexity)]
// The return type should be `Result<Self, ParserError>` once the `const_precise_live_drops`
// is stabilized ([rust-lang#73255](https://github.com/rust-lang/rust/issues/73255)).
pub const fn try_from_bytes_with_single_variant(
v: &[u8],
) -> Result<
(
subtags::Language,
Option<subtags::Script>,
Option<subtags::Region>,
Option<subtags::Variant>,
),
ParserError,
> {
parse_language_identifier_with_single_variant(v, ParserMode::LanguageIdentifier)
}
/// A constructor which takes a utf8 slice which may contain extension keys,
/// parses it and produces a well-formed [`LanguageIdentifier`].
///
/// # Examples
///
/// ```
/// use icu::locid::{langid, LanguageIdentifier};
///
/// let li = LanguageIdentifier::try_from_locale_bytes(b"en-US-x-posix")
/// .expect("Parsing failed.");
///
/// assert_eq!(li, langid!("en-US"));
/// ```
///
/// This method should be used for input that may be a locale identifier.
/// All extensions will be lost.
pub fn try_from_locale_bytes(v: &[u8]) -> Result<Self, ParserError> {
parse_language_identifier(v, ParserMode::Locale)
}
/// The default undefined language "und". Same as [`default()`](Default::default()).
///
/// # Examples
///
/// ```
/// use icu::locid::LanguageIdentifier;
///
/// assert_eq!(LanguageIdentifier::default(), LanguageIdentifier::UND);
/// ```
pub const UND: Self = Self {
language: subtags::Language::UND,
script: None,
region: None,
variants: subtags::Variants::new(),
};
/// This is a best-effort operation that performs all available levels of canonicalization.
///
/// At the moment the operation will normalize casing and the separator, but in the future
/// it may also validate and update from deprecated subtags to canonical ones.
///
/// # Examples
///
/// ```
/// use icu::locid::LanguageIdentifier;
///
/// assert_eq!(
/// LanguageIdentifier::canonicalize("pL_latn_pl").as_deref(),
/// Ok("pl-Latn-PL")
/// );
/// ```
pub fn canonicalize<S: AsRef<[u8]>>(input: S) -> Result<String, ParserError> {
let lang_id = Self::try_from_bytes(input.as_ref())?;
Ok(lang_id.write_to_string().into_owned())
}
/// Compare this [`LanguageIdentifier`] with BCP-47 bytes.
///
/// The return value is equivalent to what would happen if you first converted this
/// [`LanguageIdentifier`] to a BCP-47 string and then performed a byte comparison.
///
/// This function is case-sensitive and results in a *total order*, so it is appropriate for
/// binary search. The only argument producing [`Ordering::Equal`] is `self.to_string()`.
///
/// # Examples
///
/// ```
/// use icu::locid::LanguageIdentifier;
/// use std::cmp::Ordering;
///
/// let bcp47_strings: &[&str] = &[
/// "pl-Latn-PL",
/// "und",
/// "und-Adlm",
/// "und-GB",
/// "und-ZA",
/// "und-fonipa",
/// "zh",
/// ];
///
/// for ab in bcp47_strings.windows(2) {
/// let a = ab[0];
/// let b = ab[1];
/// assert!(a.cmp(b) == Ordering::Less);
/// let a_langid = a.parse::<LanguageIdentifier>().unwrap();
/// assert!(a_langid.strict_cmp(a.as_bytes()) == Ordering::Equal);
/// assert!(a_langid.strict_cmp(b.as_bytes()) == Ordering::Less);
/// }
/// ```
pub fn strict_cmp(&self, other: &[u8]) -> Ordering {
self.writeable_cmp_bytes(other)
}
pub(crate) fn as_tuple(
&self,
) -> (
subtags::Language,
Option<subtags::Script>,
Option<subtags::Region>,
&subtags::Variants,
) {
(self.language, self.script, self.region, &self.variants)
}
/// Compare this [`LanguageIdentifier`] with another [`LanguageIdentifier`] field-by-field.
/// The result is a total ordering sufficient for use in a [`BTreeMap`].
///
/// Unlike [`Self::strict_cmp`], this function's ordering may not equal string ordering.
///
/// [`BTreeMap`]: alloc::collections::BTreeMap
pub fn total_cmp(&self, other: &Self) -> Ordering {
self.as_tuple().cmp(&other.as_tuple())
}
/// Compare this [`LanguageIdentifier`] with an iterator of BCP-47 subtags.
///
/// This function has the same equality semantics as [`LanguageIdentifier::strict_cmp`]. It is intended as
/// a more modular version that allows multiple subtag iterators to be chained together.
///
/// For an additional example, see [`SubtagOrderingResult`].
///
/// # Examples
///
/// ```
/// use icu::locid::LanguageIdentifier;
/// use std::cmp::Ordering;
///
/// let subtags: &[&[u8]] = &[b"ca", b"ES", b"valencia"];
///
/// let loc = "ca-ES-valencia".parse::<LanguageIdentifier>().unwrap();
/// assert_eq!(
/// Ordering::Equal,
/// loc.strict_cmp_iter(subtags.iter().copied()).end()
/// );
///
/// let loc = "ca-ES".parse::<LanguageIdentifier>().unwrap();
/// assert_eq!(
/// Ordering::Less,
/// loc.strict_cmp_iter(subtags.iter().copied()).end()
/// );
///
/// let loc = "ca-ZA".parse::<LanguageIdentifier>().unwrap();
/// assert_eq!(
/// Ordering::Greater,
/// loc.strict_cmp_iter(subtags.iter().copied()).end()
/// );
/// ```
#[deprecated(since = "1.5.0", note = "if you need this, please file an issue")]
#[allow(deprecated)]
pub fn strict_cmp_iter<'l, I>(&self, mut subtags: I) -> SubtagOrderingResult<I>
where
I: Iterator<Item = &'l [u8]>,
{
let r = self.for_each_subtag_str(&mut |subtag| {
if let Some(other) = subtags.next() {
match subtag.as_bytes().cmp(other) {
Ordering::Equal => Ok(()),
not_equal => Err(not_equal),
}
} else {
Err(Ordering::Greater)
}
});
match r {
Ok(_) => SubtagOrderingResult::Subtags(subtags),
Err(o) => SubtagOrderingResult::Ordering(o),
}
}
/// Compare this `LanguageIdentifier` with a potentially unnormalized BCP-47 string.
///
/// The return value is equivalent to what would happen if you first parsed the
/// BCP-47 string to a `LanguageIdentifier` and then performed a structural comparison.
///
/// # Examples
///
/// ```
/// use icu::locid::LanguageIdentifier;
///
/// let bcp47_strings: &[&str] = &[
/// "pl-LaTn-pL",
/// "uNd",
/// "UnD-adlm",
/// "uNd-GB",
/// "UND-FONIPA",
/// "ZH",
/// ];
///
/// for a in bcp47_strings {
/// assert!(a.parse::<LanguageIdentifier>().unwrap().normalizing_eq(a));
/// }
/// ```
pub fn normalizing_eq(&self, other: &str) -> bool {
macro_rules! subtag_matches {
($T:ty, $iter:ident, $expected:expr) => {
$iter
.next()
.map(|b| <$T>::try_from_bytes(b) == Ok($expected))
.unwrap_or(false)
};
}
let mut iter = SubtagIterator::new(other.as_bytes());
if !subtag_matches!(subtags::Language, iter, self.language) {
return false;
}
if let Some(ref script) = self.script {
if !subtag_matches!(subtags::Script, iter, *script) {
return false;
}
}
if let Some(ref region) = self.region {
if !subtag_matches!(subtags::Region, iter, *region) {
return false;
}
}
for variant in self.variants.iter() {
if !subtag_matches!(subtags::Variant, iter, *variant) {
return false;
}
}
iter.next().is_none()
}
pub(crate) fn for_each_subtag_str<E, F>(&self, f: &mut F) -> Result<(), E>
where
F: FnMut(&str) -> Result<(), E>,
{
f(self.language.as_str())?;
if let Some(ref script) = self.script {
f(script.as_str())?;
}
if let Some(ref region) = self.region {
f(region.as_str())?;
}
for variant in self.variants.iter() {
f(variant.as_str())?;
}
Ok(())
}
/// Executes `f` on each subtag string of this `LanguageIdentifier`, with every string in
/// lowercase ascii form.
///
/// The default canonicalization of language identifiers uses titlecase scripts and uppercase
/// regions. However, this differs from [RFC6497 (BCP 47 Extension T)], which specifies:
///
/// > _The canonical form for all subtags in the extension is lowercase, with the fields
/// ordered by the separators, alphabetically._
///
/// Hence, this method is used inside [`Transform Extensions`] to be able to get the correct
/// canonicalization of the language identifier.
///
/// As an example, the canonical form of locale **EN-LATN-CA-T-EN-LATN-CA** is
/// **en-Latn-CA-t-en-latn-ca**, with the script and region parts lowercased inside T extensions,
/// but titlecased and uppercased outside T extensions respectively.
///
/// [RFC6497 (BCP 47 Extension T)]: https://www.ietf.org/rfc/rfc6497.txt
/// [`Transform extensions`]: crate::extensions::transform
pub(crate) fn for_each_subtag_str_lowercased<E, F>(&self, f: &mut F) -> Result<(), E>
where
F: FnMut(&str) -> Result<(), E>,
{
f(self.language.as_str())?;
if let Some(ref script) = self.script {
f(script.into_tinystr().to_ascii_lowercase().as_str())?;
}
if let Some(ref region) = self.region {
f(region.into_tinystr().to_ascii_lowercase().as_str())?;
}
for variant in self.variants.iter() {
f(variant.as_str())?;
}
Ok(())
}
/// Writes this `LanguageIdentifier` to a sink, replacing uppercase ascii chars with
/// lowercase ascii chars.
///
/// The default canonicalization of language identifiers uses titlecase scripts and uppercase
/// regions. However, this differs from [RFC6497 (BCP 47 Extension T)], which specifies:
///
/// > _The canonical form for all subtags in the extension is lowercase, with the fields
/// ordered by the separators, alphabetically._
///
/// Hence, this method is used inside [`Transform Extensions`] to be able to get the correct
/// canonicalization of the language identifier.
///
/// As an example, the canonical form of locale **EN-LATN-CA-T-EN-LATN-CA** is
/// **en-Latn-CA-t-en-latn-ca**, with the script and region parts lowercased inside T extensions,
/// but titlecased and uppercased outside T extensions respectively.
///
/// [RFC6497 (BCP 47 Extension T)]: https://www.ietf.org/rfc/rfc6497.txt
/// [`Transform extensions`]: crate::extensions::transform
pub(crate) fn write_lowercased_to<W: core::fmt::Write + ?Sized>(
&self,
sink: &mut W,
) -> core::fmt::Result {
let mut initial = true;
self.for_each_subtag_str_lowercased(&mut |subtag| {
if initial {
initial = false;
} else {
sink.write_char('-')?;
}
sink.write_str(subtag)
})
}
}
impl AsRef<LanguageIdentifier> for LanguageIdentifier {
#[inline(always)]
fn as_ref(&self) -> &Self {
self
}
}
impl AsMut<LanguageIdentifier> for LanguageIdentifier {
fn as_mut(&mut self) -> &mut Self {
self
}
}
impl core::fmt::Debug for LanguageIdentifier {
fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result {
core::fmt::Display::fmt(&self, f)
}
}
impl FromStr for LanguageIdentifier {
type Err = ParserError;
fn from_str(source: &str) -> Result<Self, Self::Err> {
Self::try_from_bytes(source.as_bytes())
}
}
impl_writeable_for_each_subtag_str_no_test!(LanguageIdentifier, selff, selff.script.is_none() && selff.region.is_none() && selff.variants.is_empty() => selff.language.write_to_string());
#[test]
fn test_writeable() {
use writeable::assert_writeable_eq;
assert_writeable_eq!(LanguageIdentifier::UND, "und");
assert_writeable_eq!("und-001".parse::<LanguageIdentifier>().unwrap(), "und-001");
assert_writeable_eq!(
"und-Mymr".parse::<LanguageIdentifier>().unwrap(),
"und-Mymr",
);
assert_writeable_eq!(
"my-Mymr-MM".parse::<LanguageIdentifier>().unwrap(),
"my-Mymr-MM",
);
assert_writeable_eq!(
"my-Mymr-MM-posix".parse::<LanguageIdentifier>().unwrap(),
"my-Mymr-MM-posix",
);
assert_writeable_eq!(
"zh-macos-posix".parse::<LanguageIdentifier>().unwrap(),
"zh-macos-posix",
);
}
/// # Examples
///
/// ```
/// use icu::locid::{langid, subtags::language, LanguageIdentifier};
///
/// assert_eq!(LanguageIdentifier::from(language!("en")), langid!("en"));
/// ```
impl From<subtags::Language> for LanguageIdentifier {
fn from(language: subtags::Language) -> Self {
Self {
language,
..Default::default()
}
}
}
/// # Examples
///
/// ```
/// use icu::locid::{langid, subtags::script, LanguageIdentifier};
///
/// assert_eq!(
/// LanguageIdentifier::from(Some(script!("latn"))),
/// langid!("und-Latn")
/// );
/// ```
impl From<Option<subtags::Script>> for LanguageIdentifier {
fn from(script: Option<subtags::Script>) -> Self {
Self {
script,
..Default::default()
}
}
}
/// # Examples
///
/// ```
/// use icu::locid::{langid, subtags::region, LanguageIdentifier};
///
/// assert_eq!(
/// LanguageIdentifier::from(Some(region!("US"))),
/// langid!("und-US")
/// );
/// ```
impl From<Option<subtags::Region>> for LanguageIdentifier {
fn from(region: Option<subtags::Region>) -> Self {
Self {
region,
..Default::default()
}
}
}
/// Convert from an LSR tuple to a [`LanguageIdentifier`].
///
/// # Examples
///
/// ```
/// use icu::locid::{
/// langid,
/// subtags::{language, region, script},
/// LanguageIdentifier,
/// };
///
/// let lang = language!("en");
/// let script = script!("Latn");
/// let region = region!("US");
/// assert_eq!(
/// LanguageIdentifier::from((lang, Some(script), Some(region))),
/// langid!("en-Latn-US")
/// );
/// ```
impl
From<(
subtags::Language,
Option<subtags::Script>,
Option<subtags::Region>,
)> for LanguageIdentifier
{
fn from(
lsr: (
subtags::Language,
Option<subtags::Script>,
Option<subtags::Region>,
),
) -> Self {
Self {
language: lsr.0,
script: lsr.1,
region: lsr.2,
..Default::default()
}
}
}
/// Convert from a [`LanguageIdentifier`] to an LSR tuple.
///
/// # Examples
///
/// ```
/// use icu::locid::{
/// langid,
/// subtags::{language, region, script},
/// };
///
/// let lid = langid!("en-Latn-US");
/// let (lang, script, region) = (&lid).into();
///
/// assert_eq!(lang, language!("en"));
/// assert_eq!(script, Some(script!("Latn")));
/// assert_eq!(region, Some(region!("US")));
/// ```
impl From<&LanguageIdentifier>
for (
subtags::Language,
Option<subtags::Script>,
Option<subtags::Region>,
)
{
fn from(langid: &LanguageIdentifier) -> Self {
(langid.language, langid.script, langid.region)
}
}