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 | #![no_std ] |
35 | |
36 | // For forwards compatibility |
37 | #[cfg (feature = "std" )] |
38 | extern crate std; |
39 | |
40 | extern crate alloc; |
41 | |
42 | #[cfg (not(feature = "alloc" ))] |
43 | compile_error!("the `alloc` feature must be enabled" ); |
44 | |
45 | #[cfg (test)] |
46 | #[macro_use ] |
47 | extern crate assert_matches; |
48 | |
49 | use alloc::string::String; |
50 | |
51 | pub mod punycode; |
52 | mod uts46; |
53 | |
54 | pub use crate::uts46::{Config, Errors, Idna}; |
55 | |
56 | /// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm. |
57 | /// |
58 | /// Return the ASCII representation a domain name, |
59 | /// normalizing characters (upper-case to lower-case and other kinds of equivalence) |
60 | /// and using Punycode as necessary. |
61 | /// |
62 | /// This process may fail. |
63 | pub fn domain_to_ascii(domain: &str) -> Result<String, uts46::Errors> { |
64 | Config::default().to_ascii(domain) |
65 | } |
66 | |
67 | /// The [domain to ASCII](https://url.spec.whatwg.org/#concept-domain-to-ascii) algorithm, |
68 | /// with the `beStrict` flag set. |
69 | pub fn domain_to_ascii_strict(domain: &str) -> Result<String, uts46::Errors> { |
70 | ConfigConfig::default() |
71 | .use_std3_ascii_rules(true) |
72 | .verify_dns_length(true) |
73 | .to_ascii(domain) |
74 | } |
75 | |
76 | /// The [domain to Unicode](https://url.spec.whatwg.org/#concept-domain-to-unicode) algorithm. |
77 | /// |
78 | /// Return the Unicode representation of a domain name, |
79 | /// normalizing characters (upper-case to lower-case and other kinds of equivalence) |
80 | /// and decoding Punycode as necessary. |
81 | /// |
82 | /// This may indicate [syntax violations](https://url.spec.whatwg.org/#syntax-violation) |
83 | /// but always returns a string for the mapped domain. |
84 | pub fn domain_to_unicode(domain: &str) -> (String, Result<(), uts46::Errors>) { |
85 | Config::default().to_unicode(domain) |
86 | } |
87 | |