src/vendor/idna/src/lib.rs

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