diff options
Diffstat (limited to 'third_party/rust/unic-langid')
| -rw-r--r-- | third_party/rust/unic-langid/.cargo-checksum.json | 1 | ||||
| -rw-r--r-- | third_party/rust/unic-langid/Cargo.toml | 43 | ||||
| -rw-r--r-- | third_party/rust/unic-langid/README.md | 70 | ||||
| -rw-r--r-- | third_party/rust/unic-langid/src/lib.rs | 136 |
4 files changed, 250 insertions, 0 deletions
diff --git a/third_party/rust/unic-langid/.cargo-checksum.json b/third_party/rust/unic-langid/.cargo-checksum.json new file mode 100644 index 0000000000..a24497bb69 --- /dev/null +++ b/third_party/rust/unic-langid/.cargo-checksum.json @@ -0,0 +1 @@ +{"files":{"Cargo.toml":"22c66abe20079b152feec2c6e54c2026fcfe5b896fb20f7b45b1f5d11690aecd","README.md":"f68b87b732b8a0d7fe6bc3b4ff5989207e87bd51f98220136ced4cd65f814f7c","src/lib.rs":"af8a91215b975e94cfff7282d948ed74236c1cb10ad047df583ea1b01e2fe4cd"},"package":"398f9ad7239db44fd0f80fe068d12ff22d78354080332a5077dc6f52f14dcf2f"}
\ No newline at end of file diff --git a/third_party/rust/unic-langid/Cargo.toml b/third_party/rust/unic-langid/Cargo.toml new file mode 100644 index 0000000000..7455943612 --- /dev/null +++ b/third_party/rust/unic-langid/Cargo.toml @@ -0,0 +1,43 @@ +# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO +# +# When uploading crates to the registry Cargo will automatically +# "normalize" Cargo.toml files for maximal compatibility +# with all versions of Cargo and also rewrite `path` dependencies +# to registry (e.g., crates.io) dependencies. +# +# If you are reading this file be aware that the original Cargo.toml +# will likely look very different (and much more reasonable). +# See Cargo.toml.orig for the original contents. + +[package] +edition = "2018" +name = "unic-langid" +version = "0.9.1" +authors = ["Zibi Braniecki <gandalf@mozilla.com>"] +include = [ + "src/**/*", + "benches/*.rs", + "Cargo.toml", + "README.md", +] +description = "API for managing Unicode Language Identifiers" +readme = "README.md" +categories = ["internationalization"] +license = "MIT/Apache-2.0" +repository = "https://github.com/zbraniecki/unic-locale" + +[dependencies.unic-langid-impl] +version = "0.9" + +[dependencies.unic-langid-macros] +version = "0.9" +optional = true + +[dev-dependencies.unic-langid-macros] +version = "0.9" + +[features] +default = [] +likelysubtags = ["unic-langid-impl/likelysubtags"] +macros = ["unic-langid-macros"] +serde = ["unic-langid-impl/serde"] diff --git a/third_party/rust/unic-langid/README.md b/third_party/rust/unic-langid/README.md new file mode 100644 index 0000000000..4ec1f31950 --- /dev/null +++ b/third_party/rust/unic-langid/README.md @@ -0,0 +1,70 @@ +# unic-langid [](https://travis-ci.org/zbraniecki/unic-locale) [](https://coveralls.io/github/zbraniecki/unic-locale?branch=master) + +`unic-langid` is an API for managing [Unicode Language Identifiers](http://unicode.org/reports/tr35/#Unicode_language_identifier). + +The crate provides a way to create a struct from a string, manipulate its fields, canonicalize it, and serialize into a string. + +Usage +----- + +```rust +use unic_langid::LanguageIdentifier; + +let loc: LanguageIdentifier = "en-US".parse().expect("Parsing failed."); + +assert_eq!(loc.language(), "en"); +assert_eq!(loc.script(), None); +assert_eq!(loc.region(), Some("US")); + +loc.set_script(Some("latn")); + +assert_eq!(&loc.to_string(), "en-Latn-US"); +``` + +```rust +use unic_langid::LanguageIdentifier; + +let langid = LanguageIdentifier::from_parts( + Some("en"), + None, + None, + Some(&["nedis", "macos"]) +).expect("Parsing failed."); + +assert_eq!(&langid.to_string(), "en-macos-nedis") +``` + +Macros +------ + +`unic-langid` can be also compiled with `features = ["macros"]` which enables `langid!` macro: + +```rust +use unic_langid::langid; + +// The `const` assignment will currently work only +// if the langid doesn't contain any variants. +const EN_US: LanguageIdentifier = langid!("en-US"); + +fn main() { + let de_at = langid!("de-AT"); + + assert_eq!(&de_at.to_string(), "de-AT") + assert_eq!(&EN_US.to_string(), "en-US") +} +``` + +The macro allows for compile-time parsing and validation of literal language identifiers. + +Status +------ + +The crate is mostly complete on the `well-formed` level. The next batch of work will go into +API maturity. + +Get Involved +------------ + +`unic-langid` is open-source, licensed under the Apache License, Version 2.0. We +encourage everyone to take a look at our code and we'll listen to your +feedback. diff --git a/third_party/rust/unic-langid/src/lib.rs b/third_party/rust/unic-langid/src/lib.rs new file mode 100644 index 0000000000..f66fb444a3 --- /dev/null +++ b/third_party/rust/unic-langid/src/lib.rs @@ -0,0 +1,136 @@ +//! `unic-langid` is a core API for parsing, manipulating, and serializing Unicode Language +//! Identifiers. +//! +//! The crate provides algorithms for parsing a string into a well-formed language identifier +//! as defined by [`UTS #35: Unicode LDML 3.1 Unicode Language Identifier`]. +//! +//! # Examples +//! +//! ``` +//! use unic_langid::LanguageIdentifier; +//! use unic_langid::subtags::{Language, Script, Region}; +//! +//! let mut li: LanguageIdentifier = "en-US".parse() +//! .expect("Parsing failed."); +//! +//! let lang: Language = "en".parse().expect("Parsing failed."); +//! let region: Region = "US".parse().expect("Parsing failed."); +//! assert_eq!(li.language, lang); +//! assert_eq!(li.script, None); +//! assert_eq!(li.region, Some(region)); +//! assert_eq!(li.variants().len(), 0); +//! +//! let region: Region = "GB".parse().expect("Parsing failed."); +//! li.region = Some(region); +//! +//! assert_eq!(li.to_string(), "en-GB"); +//! ``` +//! +//! For more details, see [`LanguageIdentifier`]. +//! +//! # Optional features +//! +//! ## `langid!`, `langids!`, and `langid_slice!` macros +//! +//! If `feature = "macros"` is selected, the crate provides a procedural macro +//! which allows to construct build-time well-formed language identifiers with zero-cost at runtime. +//! +//! ``` ignore +//! use unic_langid::{langid, langid_slice, langids, lang, region, script, variant, LanguageIdentifier}; +//! use unic_langid::subtags::{Language, Script, Region, Variant}; +//! use std::str::FromStr; +//! +//! let es_ar = langid!("es-AR"); +//! let en_us = langid!("en-US"); +//! +//! assert_eq!(&es_ar.to_string(), "es-AR"); +//! assert_eq!(&en_us.to_string(), "en-US"); +//! +//! let lang_ids = langids!("es-AR", "en-US", "de"); +//! +//! assert_eq!(lang_ids[0], "es-AR"); +//! assert_eq!(lang_ids[1], "en-US"); +//! assert_eq!(lang_ids[2], "de"); +//! +//! const LANGUAGES: &[LanguageIdentifier] = langid_slice!["en-GB", "fr"]; +//! +//! assert_eq!(lang!("pl"), "pl"); +//! assert_eq!(lang!("pl"), Language::from_str("pl").unwrap()); +//! +//! assert_eq!(script!("latn"), "Latn"); +//! assert_eq!(script!("latn"), Script::from_str("Latn").unwrap()); +//! +//! assert_eq!(region!("us"), "US"); +//! assert_eq!(region!("us"), Region::from_str("us").unwrap()); +//! +//! assert_eq!(variant!("macos"), "macos"); +//! assert_eq!(variant!("macos"), Variant::from_str("macos").unwrap()); +//! ``` +//! +//! The macros produce instances of `LanguageIdentifier` the same way as parsing from `&str` does, +//! but since the parsing is performed at build time, it doesn't need a `Result`. +//! +//! At the moment `langid!` can also be used for const variables, but only if no variants are used. +//! +//! The macros are optional to reduce the dependency chain and compilation time of `unic-langid`. +//! +//! ## Likely Subtags +//! +//! If `feature = "likelysubtags"` is selected, the `LanguageIdentifier` gains two more methods: +//! +//! * add_likely_subtags +//! * remove_likely_subtags +//! +//! Both of them operate in place updating the existing `LanguageIdentifier` by either extending +//! subtags to most likely values, or removing the subtags that are not needed. +//! +//! Both methods return a `bool` that indicates if the identifier has been modified. +//! +//! ``` ignore +//! use unic_langid::LanuageIdentifier; +//! +//! let mut li: LanguageIdentifier = "fr-FR".parse() +//! .expect("Parsing failed."); +//! +//! assert_eq!(li.add_likely_subtags(), true); +//! assert_eq!(li, "fr-Latn-FR"); +//! +//! assert_eq!(li.remove_likely_subtags(), true); +//! assert_eq!(li, "fr"); +//! ``` +//! +//! The feature is optional because it increases the binary size of the library by including +//! a data table for CLDR likelySubtags. +//! +//! [`UTS #35: Unicode LDML 3.1 Unicode Language Identifier`]: https://unicode.org/reports/tr35/tr35.html#Unicode_language_identifier +//! [`LanguageIdentifier`]: ./struct.LanguageIdentifier.html + +pub use unic_langid_impl::*; + +#[cfg(feature = "unic-langid-macros")] +pub use unic_langid_macros::{lang, langid, region, script, variant}; + +#[cfg(feature = "unic-langid-macros")] +#[macro_export] +macro_rules! langids { + ( $($langid:expr),* ) => { + vec![$( + $crate::langid!($langid), + )*] + }; + ( $($langid:expr,)* ) => { + $crate::langids![$($langid),*] + }; +} +#[cfg(feature = "unic-langid-macros")] +#[macro_export] +macro_rules! langid_slice { + ( $($langid:expr),* ) => { + &[$( + $crate::langid!($langid), + )*] + }; + ( $($langid:expr,)* ) => { + $crate::langid_slice![$($langid),*] + }; +} |