pub struct Locale {
pub id: LanguageIdentifier,
pub extensions: Extensions,
}
Expand description
A core struct representing a Unicode Locale Identifier
.
A locale is made of two parts:
- Unicode Language Identifier
- A set of Unicode Extensions
Locale
exposes all of the same fields and methods as LanguageIdentifier
, and
on top of that is able to parse, manipulate and serialize unicode extension fields.
Examples
use icu_locid::{
extensions_unicode_key as key, extensions_unicode_value as value,
locale, subtags_language as language, subtags_region as region,
};
let loc = locale!("en-US-u-ca-buddhist");
assert_eq!(loc.id.language, language!("en"));
assert_eq!(loc.id.script, None);
assert_eq!(loc.id.region, Some(region!("US")));
assert_eq!(loc.id.variants.len(), 0);
assert_eq!(
loc.extensions.unicode.keywords.get(&key!("ca")),
Some(&value!("buddhist"))
);
Parsing
Unicode recognizes three levels of standard conformance for a locale:
- well-formed - syntactically correct
- valid - well-formed and only uses registered language subtags, extensions, keywords, types…
- canonical - valid and no deprecated codes or structure.
At the moment parsing normalizes a well-formed locale 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 or canonicalization is performed.
Examples
use icu::locid::{subtags::*, Locale};
let loc: Locale = "eN_latn_Us-Valencia_u-hC-H12"
.parse()
.expect("Failed to parse.");
assert_eq!(loc.id.language, "en".parse::<Language>().unwrap());
assert_eq!(loc.id.script, "Latn".parse::<Script>().ok());
assert_eq!(loc.id.region, "US".parse::<Region>().ok());
assert_eq!(
loc.id.variants.get(0),
"valencia".parse::<Variant>().ok().as_ref()
);
Fields§
§id: LanguageIdentifier
The basic language/script/region components in the locale identifier along with any variants.
extensions: Extensions
Any extensions present in the locale identifier.
Implementations§
source§impl Locale
impl Locale
sourcepub fn try_from_bytes(v: &[u8]) -> Result<Locale, ParserError>
pub fn try_from_bytes(v: &[u8]) -> Result<Locale, ParserError>
sourcepub const UND: Locale = Self{
id: LanguageIdentifier::UND,
extensions: extensions::Extensions::new(),}
pub const UND: Locale = Self{ id: LanguageIdentifier::UND, extensions: extensions::Extensions::new(),}
sourcepub fn canonicalize<S>(input: S) -> Result<String, ParserError>where
S: AsRef<[u8]>,
pub fn canonicalize<S>(input: S) -> Result<String, ParserError>where S: AsRef<[u8]>,
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::Locale;
assert_eq!(
Locale::canonicalize("pL_latn_pl-U-HC-H12").as_deref(),
Ok("pl-Latn-PL-u-hc-h12")
);
sourcepub fn strict_cmp(&self, other: &[u8]) -> Ordering
pub fn strict_cmp(&self, other: &[u8]) -> Ordering
Compare this Locale
with BCP-47 bytes.
The return value is equivalent to what would happen if you first converted this
Locale
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::Locale;
use std::cmp::Ordering;
let bcp47_strings: &[&str] = &[
"pl-Latn-PL",
"und",
"und-fonipa",
"und-t-m0-true",
"und-u-ca-hebrew",
"und-u-ca-japanese",
"zh",
];
for ab in bcp47_strings.windows(2) {
let a = ab[0];
let b = ab[1];
assert!(a.cmp(b) == Ordering::Less);
let a_loc = a.parse::<Locale>().unwrap();
assert!(a_loc.strict_cmp(a.as_bytes()) == Ordering::Equal);
assert!(a_loc.strict_cmp(b.as_bytes()) == Ordering::Less);
}
sourcepub fn strict_cmp_iter<'l, I>(&self, subtags: I) -> SubtagOrderingResult<I>where
I: Iterator<Item = &'l [u8]>,
pub fn strict_cmp_iter<'l, I>(&self, subtags: I) -> SubtagOrderingResult<I>where I: Iterator<Item = &'l [u8]>,
Compare this Locale
with an iterator of BCP-47 subtags.
This function has the same equality semantics as Locale::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::locale;
use std::cmp::Ordering;
let subtags: &[&[u8]] =
&[b"ca", b"ES", b"valencia", b"u", b"ca", b"hebrew"];
let loc = locale!("ca-ES-valencia-u-ca-hebrew");
assert_eq!(
Ordering::Equal,
loc.strict_cmp_iter(subtags.iter().copied()).end()
);
let loc = locale!("ca-ES-valencia");
assert_eq!(
Ordering::Less,
loc.strict_cmp_iter(subtags.iter().copied()).end()
);
let loc = locale!("ca-ES-valencia-u-nu-arab");
assert_eq!(
Ordering::Greater,
loc.strict_cmp_iter(subtags.iter().copied()).end()
);
sourcepub fn normalizing_eq(&self, other: &str) -> bool
pub fn normalizing_eq(&self, other: &str) -> bool
Compare this Locale
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 Locale
and then performed a structucal comparison.
Examples
use icu::locid::Locale;
use std::cmp::Ordering;
let bcp47_strings: &[&str] = &[
"pl-LaTn-pL",
"uNd",
"UND-FONIPA",
"UnD-t-m0-TrUe",
"uNd-u-CA-Japanese",
"ZH",
];
for a in bcp47_strings {
assert!(a.parse::<Locale>().unwrap().normalizing_eq(a));
}
Trait Implementations§
source§impl AsMut<LanguageIdentifier> for Locale
impl AsMut<LanguageIdentifier> for Locale
source§fn as_mut(&mut self) -> &mut LanguageIdentifier
fn as_mut(&mut self) -> &mut LanguageIdentifier
source§impl AsRef<LanguageIdentifier> for Locale
impl AsRef<LanguageIdentifier> for Locale
source§fn as_ref(&self) -> &LanguageIdentifier
fn as_ref(&self) -> &LanguageIdentifier
source§impl Display for Locale
impl Display for Locale
This trait is implemented for compatibility with fmt!
.
To create a string, [Writeable::write_to_string
] is usually more efficient.
source§impl From<(Language, Option<Script>, Option<Region>)> for Locale
impl From<(Language, Option<Script>, Option<Region>)> for Locale
Examples
use icu::locid::Locale;
use icu::locid::{
locale, subtags_language as language, subtags_region as region,
subtags_script as script,
};
assert_eq!(
Locale::from((
language!("en"),
Some(script!("Latn")),
Some(region!("US"))
)),
locale!("en-Latn-US")
);
source§impl From<Language> for Locale
impl From<Language> for Locale
Examples
use icu::locid::Locale;
use icu::locid::{locale, subtags_language as language};
assert_eq!(Locale::from(language!("en")), locale!("en"));
source§impl From<LanguageIdentifier> for Locale
impl From<LanguageIdentifier> for Locale
source§fn from(id: LanguageIdentifier) -> Locale
fn from(id: LanguageIdentifier) -> Locale
source§impl From<Locale> for LanguageIdentifier
impl From<Locale> for LanguageIdentifier
source§fn from(loc: Locale) -> LanguageIdentifier
fn from(loc: Locale) -> LanguageIdentifier
source§impl From<Option<Region>> for Locale
impl From<Option<Region>> for Locale
Examples
use icu::locid::Locale;
use icu::locid::{locale, subtags_region as region};
assert_eq!(Locale::from(Some(region!("US"))), locale!("und-US"));
source§impl From<Option<Script>> for Locale
impl From<Option<Script>> for Locale
Examples
use icu::locid::Locale;
use icu::locid::{locale, subtags_script as script};
assert_eq!(Locale::from(Some(script!("latn"))), locale!("und-Latn"));
source§impl PartialEq<Locale> for Locale
impl PartialEq<Locale> for Locale
source§impl Writeable for Locale
impl Writeable for Locale
source§fn write_to<W>(&self, sink: &mut W) -> Result<(), Error>where
W: Write + ?Sized,
fn write_to<W>(&self, sink: &mut W) -> Result<(), Error>where W: Write + ?Sized,
write_to_parts
, and discards any
Part
annotations.