Struct icu_provider::DataLocale

pub struct DataLocale {
    pub language: Language,
    pub script: Option<Script>,
    pub region: Option<Region>,
    pub variant: Option<Variant>,
    pub subdivision: Option<Subtag>,
    /* private fields */
}

A locale type optimized for use in fallbacking and the ICU4X data pipeline.

DataLocale contains less functionality than [Locale] but more than [LanguageIdentifier] for better size and performance while still meeting the needs of the ICU4X data pipeline.

You can create a DataLocale from a borrowed [Locale], which is more efficient than cloning the [Locale], but less efficient than converting an owned [Locale]:

use icu_locale_core::locale;
use icu_provider::DataLocale;

let locale1 = locale!("en-u-ca-buddhist");
let data_locale = DataLocale::from(&locale1);

DataLocale only supports -u-sd keywords, to reflect the current state of CLDR data lookup and fallback. This may change in the future.

use icu_locale_core::{locale, Locale};
use icu_provider::DataLocale;

let locale = "hi-IN-t-en-h0-hybrid-u-attr-ca-buddhist-sd-inas"
    .parse::<Locale>()
    .unwrap();

assert_eq!(
    DataLocale::from(locale),
    DataLocale::from(locale!("hi-IN-u-sd-inas"))
);

Fields

language: Language

Language subtag

script: Option<Script>

Script subtag

region: Option<Region>

Region subtag

variant: Option<Variant>

Variant subtag

subdivision: Option<Subtag>

Subivision (-u-sd-) subtag

Implementations

impl DataLocale

pub const fn from_preferences_locale<M: DataMarker>( locale: LocalePreferences, ) -> Self

Returns a DataLocale usable for the marker M.

impl DataLocale

pub const fn default() -> Self

const version of Default::default

impl DataLocale

pub fn to_string(&self) -> String

Converts the given value to a String.

Under the hood, this uses an efficient [Writeable] implementation. However, in order to avoid allocating a string, it is more efficient to use [Writeable] directly.

impl DataLocale

pub fn try_from_str(s: &str) -> Result<Self, ParseError>

Parses a DataLocale.

pub fn try_from_utf8(code_units: &[u8]) -> Result<Self, ParseError>

Parses a DataLocale from a UTF-8 byte slice.

pub fn strict_cmp(&self, other: &[u8]) -> Ordering

Compare this DataLocale with BCP-47 bytes.

The return value is equivalent to what would happen if you first converted this DataLocale 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_provider::DataLocale;
use std::cmp::Ordering;

let bcp47_strings: &[&str] = &[
    "ca",
    "ca-ES",
    "ca-ES-u-sd-esct",
    "ca-ES-valencia",
    "cat",
    "pl-Latn-PL",
    "und",
    "und-fonipa",
    "zh",
];

for ab in bcp47_strings.windows(2) {
    let a = ab[0];
    let b = ab[1];
    assert_eq!(a.cmp(b), Ordering::Less, "strings: {} < {}", a, b);
    let a_loc: DataLocale = a.parse().unwrap();
    assert_eq!(
        a_loc.strict_cmp(a.as_bytes()),
        Ordering::Equal,
        "strict_cmp: {} == {}",
        a_loc,
        a
    );
    assert_eq!(
        a_loc.strict_cmp(b.as_bytes()),
        Ordering::Less,
        "strict_cmp: {} < {}",
        a_loc,
        b
    );
    let b_loc: DataLocale = b.parse().unwrap();
    assert_eq!(
        b_loc.strict_cmp(b.as_bytes()),
        Ordering::Equal,
        "strict_cmp: {} == {}",
        b_loc,
        b
    );
    assert_eq!(
        b_loc.strict_cmp(a.as_bytes()),
        Ordering::Greater,
        "strict_cmp: {} > {}",
        b_loc,
        a
    );
}

Comparison against invalid strings:

use icu_provider::DataLocale;

let invalid_strings: &[&str] = &[
    // Less than "ca-ES"
    "CA",
    "ar-x-gbp-FOO",
    // Greater than "ca-AR"
    "ca_ES",
    "ca-ES-x-gbp-FOO",
];

let data_locale = "ca-ES".parse::<DataLocale>().unwrap();

for s in invalid_strings.iter() {
    let expected_ordering = "ca-AR".cmp(s);
    let actual_ordering = data_locale.strict_cmp(s.as_bytes());
    assert_eq!(expected_ordering, actual_ordering, "{}", s);
}

pub fn is_default(&self) -> bool

Returns whether this DataLocale is und in the locale and extensions portion.

Examples

use icu_provider::DataLocale;

assert!("und".parse::<DataLocale>().unwrap().is_default());
assert!(!"de-u-sd-denw".parse::<DataLocale>().unwrap().is_default());
assert!(!"und-ES".parse::<DataLocale>().unwrap().is_default());

pub fn into_locale(self) -> Locale

Converts this DataLocale into a [Locale].

pub fn get_unicode_ext(&self, key: &Key) -> Option<Value>

Gets the value of the specified Unicode extension keyword for this DataLocale.

pub fn get_single_unicode_ext(&self, key: &str) -> Option<&str>

Like get_unicode_ext but untyped, easier to use during attributes migration.

Trait Implementations

impl Clone for DataLocale

fn clone(&self) -> DataLocale

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for DataLocale

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for &DataLocale

fn default() -> Self

Returns the “default value” for a type.

impl Default for DataLocale

fn default() -> DataLocale

Returns the “default value” for a type.

impl Display for DataLocale

This trait is implemented for compatibility with fmt!. To create a string, [Writeable::write_to_string] is usually more efficient.

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl From<&LanguageIdentifier> for DataLocale

fn from(langid: &LanguageIdentifier) -> Self

Converts to this type from the input type.

impl From<&Locale> for DataLocale

fn from(locale: &Locale) -> Self

Converts to this type from the input type.

impl From<LanguageIdentifier> for DataLocale

fn from(langid: LanguageIdentifier) -> Self

Converts to this type from the input type.

impl From<Locale> for DataLocale

fn from(locale: Locale) -> Self

Converts to this type from the input type.

impl FromStr for DataLocale

type Err = ParseError

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<Self, Self::Err>

Parses a string s to return a value of this type.

impl Hash for DataLocale

fn hash<H: Hasher>(&self, state: &mut H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for DataLocale

fn eq(&self, other: &Self) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Writeable for DataLocale

fn write_to<W: Write + ?Sized>(&self, sink: &mut W) -> Result

Writes a string to the given sink. Errors from the sink are bubbled up. The default implementation delegates to write_to_parts, and discards any Part annotations.

fn writeable_length_hint(&self) -> LengthHint

Returns a hint for the number of UTF-8 bytes that will be written to the sink.

fn write_to_string(&self) -> Cow<'_, str>

Creates a new String with the data from this Writeable. Like ToString, but smaller and faster.

fn write_to_parts<S>(&self, sink: &mut S) -> Result<(), Error>

where S: PartsWrite + ?Sized,

Write bytes and Part annotations to the given sink. Errors from the sink are bubbled up. The default implementation delegates to write_to, and doesn’t produce any Part annotations.

impl Eq for DataLocale