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 #[macro_use]
36 extern crate matches;
37
38 pub mod punycode;
39 mod uts46;
40
41 pub use crate::uts46::{Config, Errors, Idna};
42
43 /// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm.
44 ///
45 /// Return the ASCII representation a domain name,
46 /// normalizing characters (upper-case to lower-case and other kinds of equivalence)
47 /// and using Punycode as necessary.
48 ///
49 /// This process may fail.
domain_to_ascii(domain: &str) -> Result<String, uts46::Errors>50 pub fn domain_to_ascii(domain: &str) -> Result<String, uts46::Errors> {
51 Config::default().to_ascii(domain)
52 }
53
54 /// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm,
55 /// with the `beStrict` flag set.
domain_to_ascii_strict(domain: &str) -> Result<String, uts46::Errors>56 pub fn domain_to_ascii_strict(domain: &str) -> Result<String, uts46::Errors> {
57 Config::default()
58 .use_std3_ascii_rules(true)
59 .verify_dns_length(true)
60 .to_ascii(domain)
61 }
62
63 /// The [domain to Unicode](https://url.spec.whatwg.org/#concept-domain-to-unicode) algorithm.
64 ///
65 /// Return the Unicode representation of a domain name,
66 /// normalizing characters (upper-case to lower-case and other kinds of equivalence)
67 /// and decoding Punycode as necessary.
68 ///
69 /// This may indicate [syntax violations](https://url.spec.whatwg.org/#syntax-violation)
70 /// but always returns a string for the mapped domain.
domain_to_unicode(domain: &str) -> (String, Result<(), uts46::Errors>)71 pub fn domain_to_unicode(domain: &str) -> (String, Result<(), uts46::Errors>) {
72 Config::default().to_unicode(domain)
73 }
74