idna/
lib.rs

Help
1// Copyright 2016 The rust-url developers.
2//
3// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
4// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
5// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
6// option. This file may not be copied, modified, or distributed
7// except according to those terms.
8
9//! This Rust crate implements IDNA
10//! [per the WHATWG URL Standard](https://url.spec.whatwg.org/#idna).
11//!
12//! It also exposes the underlying algorithms from [*Unicode IDNA Compatibility Processing*
13//! (Unicode Technical Standard #46)](http://www.unicode.org/reports/tr46/)
14//! and [Punycode (RFC 3492)](https://tools.ietf.org/html/rfc3492).
15//!
16//! Quoting from [UTS #46’s introduction](http://www.unicode.org/reports/tr46/#Introduction):
17//!
18//! > Initially, domain names were restricted to ASCII characters.
19//! > A system was introduced in 2003 for internationalized domain names (IDN).
20//! > This system is called Internationalizing Domain Names for Applications,
21//! > or IDNA2003 for short.
22//! > This mechanism supports IDNs by means of a client software transformation
23//! > into a format known as Punycode.
24//! > A revision of IDNA was approved in 2010 (IDNA2008).
25//! > This revision has a number of incompatibilities with IDNA2003.
26//! >
27//! > The incompatibilities force implementers of client software,
28//! > such as browsers and emailers,
29//! > to face difficult choices during the transition period
30//! > as registries shift from IDNA2003 to IDNA2008.
31//! > This document specifies a mechanism
32//! > that minimizes the impact of this transition for client software,
33//! > allowing client software to access domains that are valid under either system.
34
35#[cfg(test)]
36#[macro_use]
37extern crate assert_matches;
38
39pub mod punycode;
40mod uts46;
41
42pub use crate::uts46::{Config, Errors, Idna};
43
44/// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm.
45///
46/// Return the ASCII representation a domain name,
47/// normalizing characters (upper-case to lower-case and other kinds of equivalence)
48/// and using Punycode as necessary.
49///
50/// This process may fail.
51pub fn domain_to_ascii(domain: &str) -> Result<String, uts46::Errors> {
52    Config::default().to_ascii(domain)
53}
54
55/// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm,
56/// with the `beStrict` flag set.
57pub fn domain_to_ascii_strict(domain: &str) -> Result<String, uts46::Errors> {
58    Config::default()
59        .use_std3_ascii_rules(true)
60        .verify_dns_length(true)
61        .to_ascii(domain)
62}
63
64/// The [domain to Unicode](https://url.spec.whatwg.org/#concept-domain-to-unicode) algorithm.
65///
66/// Return the Unicode representation of a domain name,
67/// normalizing characters (upper-case to lower-case and other kinds of equivalence)
68/// and decoding Punycode as necessary.
69///
70/// This may indicate [syntax violations](https://url.spec.whatwg.org/#syntax-violation)
71/// but always returns a string for the mapped domain.
72pub fn domain_to_unicode(domain: &str) -> (String, Result<(), uts46::Errors>) {
73    Config::default().to_unicode(domain)
74}
idna/lib.rs

idna/
lib.rs
