uri-idna 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 06523fb12f478c36affa14f66e65ff8561afdb51a893df0e25a03d1d34325954
-  data.tar.gz: 78a948f74aee704e82e25dfb7d2d1be3b97ab43125b852623d95a5551944bdf0
+  metadata.gz: 6682f4500b6119fcd467ff88793d5a2d4522308ea4884cc6f69f04cb073d1089
+  data.tar.gz: 1e63bd541e8020f789916a82950a81d2f67b8d29a882f45d7c4a369a10c15de1
 SHA512:
-  metadata.gz: e72151513e38a309ad3869a2ffaff53a207c8d4833d71d4faf1356b14ca6e6efc887c3761b20197f67b3ccb918afafd03eb9f0ba000e2707b6765d0f4f10f691
-  data.tar.gz: 2a02097ddf70e302367ad56088994a35511d81dac6735ded5d5d5f3badeed329ed19387eeda9e07d2243fa21e7826f5adb14728394d4738971568273db1759da
+  metadata.gz: 86032ea0573558c6386154a29265dddc81e8914a9720643bceab6f80de49d9f11ff2fc8bf5bfa789c84a515050457e9493937040541831a8d14394f49e15549d
+  data.tar.gz: 493f974a03ccf2abc69e1090f2a61d029a5f2e47a3725f87bdc3bf6ced69a7d9e052a424ddc95268c0b26a4354c7b31d72268c9a404d4b16180e77db8c5ff009

data/CHANGELOG.md

@@ -7,6 +7,22 @@ and this project adheres to [Semantic Versioning].
 
 ## [Unreleased]
 
+## [0.2.0] - 2023-11-14
+
+### Added
+
+- WHATWG IDNA functions
+
+### Changed
+
+- **BREAKING!** Names of options updated to match UTS46 flags
+- Unicode version updated to 15.1
+- UTS46 functions now support Revision 31
+
+### Fixed
+
+- IDNA2008 functions now support not only labels, but full domains 
+
 ## [0.1.0] - 2023-08-05
 
 ### Added
@@ -15,7 +31,8 @@ and this project adheres to [Semantic Versioning].
 
 [@skryukov]: https://github.com/skryukov
 
-[Unreleased]: https://github.com/skryukov/uri-idna/compare/v0.1.0...HEAD
+[Unreleased]: https://github.com/skryukov/uri-idna/compare/v0.2.0...HEAD
+[0.2.0]: https://github.com/skryukov/uri-idna/compare/v0.1.0...v0.2.0
 [0.1.0]: https://github.com/skryukov/uri-idna/commits/v0.1.0
 
 [Keep a Changelog]: https://keepachangelog.com/en/1.0.0/

data/README.md

@@ -3,11 +3,11 @@
 [![Gem Version](https://badge.fury.io/rb/uri-idna.svg)](https://rubygems.org/gems/uri-idna)
 [![Ruby](https://github.com/skryukov/uri-idna/actions/workflows/main.yml/badge.svg)](https://github.com/skryukov/uri-idna/actions/workflows/main.yml)
 
-A IDNA 2008, UTS 46 and Punycode implementation in pure Ruby.
+A IDNA2008, UTS46, IDNA from WHATWG URL Standard and Punycode implementation in pure Ruby.
 
 This gem provides a number of functions for converting internationalized domain names (IDNs) between the Unicode and ASCII Compatible Encoding (ACE) forms.
 
-<a href="https://evilmartians.com/?utm_source=rubocop-gradual&utm_campaign=project_page">
+<a href="https://evilmartians.com/?utm_source=uri-idna&utm_campaign=project_page">
 <img src="https://evilmartians.com/badges/sponsored-by-evil-martians.svg" alt="Sponsored by Evil Martians" width="236" height="54">
 </a>
 
@@ -15,7 +15,7 @@ This gem provides a number of functions for converting internationalized domain
 
 Add to your Gemfile:
 ```ruby
-gem "idna-idna"
+gem "uri-idna"
 ```
 
 And then run `bundle install`.
@@ -24,23 +24,33 @@ And then run `bundle install`.
 
 There are plenty of ways to convert IDNs between Unicode and ACE forms.
 
-### IDNA 2008
+### IDNA2008
 
-The [RFC 5890] defines two protocols for IDN conversion: [Registration](https://datatracker.ietf.org/doc/html/rfc5891#section-4) and [Domain Name Lookup](https://datatracker.ietf.org/doc/html/rfc5891#section-5).
+The [RFC 5891] defines two protocols for IDN conversion: [Registration](https://datatracker.ietf.org/doc/html/rfc5891#section-4) and [Domain Name Lookup](https://datatracker.ietf.org/doc/html/rfc5891#section-5).
 
 #### Registration protocol
 
+`URI::IDNA.register(alabel:, ulabel:, **options)`
+
+##### Options
+
+- `check_hyphens`: `true` – whether to check hyphens according to [Section 5.4](https://datatracker.ietf.org/doc/html/rfc5891#section-5.4).
+- `leading_combining`: `true` – whether to check leading combining marks according to [Section 5.4](https://datatracker.ietf.org/doc/html/rfc5891#section-5.4).
+- `check_joiners`: `true` – whether to check `CONTEXTJ` code points according to [Section 5.4](https://datatracker.ietf.org/doc/html/rfc5891#section-5.4).
+- `check_others`: `true` – whether to check `CONTEXTO` code points according to [Section 5.4](https://datatracker.ietf.org/doc/html/rfc5891#section-5.4).
+- `check_bidi`: `true` – whether to check bidirectional characters according to [Section 5.4](https://datatracker.ietf.org/doc/html/rfc5891#section-5.4).
+
 ```ruby
 require "uri/idna"
 
-URI::IDNA.register(alabel: "xn--gdkl8fhk5egc", ulabel: "ハロー・ワールド")
-#=> "xn--gdkl8fhk5egc"
+URI::IDNA.register(alabel: "xn--gdkl8fhk5egc.jp", ulabel: "ハロー・ワールド.jp")
+#=> "xn--gdkl8fhk5egc.jp"
 
-URI::IDNA.register(ulabel: "ハロー・ワールド")
-#=> "xn--gdkl8fhk5egc"
+URI::IDNA.register(ulabel: "ハロー・ワールド.jp")
+#=> "xn--gdkl8fhk5egc.jp"
 
-URI::IDNA.register(alabel: "xn--gdkl8fhk5egc")
-#=> "xn--gdkl8fhk5egc"
+URI::IDNA.register(alabel: "xn--gdkl8fhk5egc.jp")
+#=> "xn--gdkl8fhk5egc.jp"
 
 URI::IDNA.register(ulabel: "☕.us")
 #<URI::IDNA::InvalidCodepointError: Codepoint U+2615 at position 1 of "☕" not allowed>
@@ -48,43 +58,79 @@ URI::IDNA.register(ulabel: "☕.us")
 
 #### Domain Name Lookup Protocol
 
+`URI::IDNA.lookup(domain_name, **options)`
+
+##### Options
+
+- `check_hyphens`: `true` – whether to check hyphens according to [Section 4.2.3.1](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.1).
+- `leading_combining`: `true` – whether to check leading combining marks according to [Section 4.2.3.2](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.2).
+- `check_joiners`: `true` – whether to check CONTEXTJ code points according to [Section 4.2.3.3](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.3).
+- `check_others`: `true` – whether to check CONTEXTO code points according to [Section 4.2.3.3](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.3).
+- `check_bidi`: `true` – whether to check bidirectional characters according to [Section 4.2.3.4](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.4).
+- `verify_dns_length`: `true` – whether to check DNS length according to [Section 4.4](https://datatracker.ietf.org/doc/html/rfc5891#section-4.4).
+
 ```ruby
 require "uri/idna"
 
-URI::IDNA.lookup("ハロー・ワールド")
-#=> "xn--pck0a1b0a6a2e"
+URI::IDNA.lookup("ハロー・ワールド.jp")
+#=> "xn--pck0a1b0a6a2e.jp"
 
-URI::IDNA.lookup("xn--pck0a1b0a6a2e")
-#=> "xn--pck0a1b0a6a2e"
+URI::IDNA.lookup("xn--pck0a1b0a6a2e.jp")
+#=> "xn--pck0a1b0a6a2e.jp"
 
 URI::IDNA.lookup("Ῠ.me")
 #<URI::IDNA::InvalidCodepointError: Codepoint U+1FE8 at position 1 of "Ῠ" not allowed>
 ```
 
-### Unicode UTS 46(TR46)
+### Unicode UTS46 (TR46)
 
-The [UTS 46](https://www.unicode.org/reports/tr46) defines two IDN conversion functions: [ToASCII](https://www.unicode.org/reports/tr46/#ToASCII) and [ToUnicode](https://www.unicode.org/reports/tr46/#ToUnicode).
+_Current revision: 31_
+
+The [UTS46] defines two IDN conversion functions: [ToASCII](https://www.unicode.org/reports/tr46/#ToASCII) and [ToUnicode](https://www.unicode.org/reports/tr46/#ToUnicode).
 
 #### ToASCII
 
+`URI::IDNA.to_ascii(domain_name, **options)`
+
+##### Options
+
+- `use_std3_ascii_rules`: `true` – whether to apply [STD3 rules](https://www.unicode.org/reports/tr46/#STD3_Rules) for both mapping and validation.
+- `check_hyphens`: `true` – whether to check hyphens according to [Section 4.2.3.1](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.1) of [RFC 5891].
+- `check_bidi`: `true` – whether to check bidirectional characters according to [Section 4.2.3.4](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.4) of [RFC 5891].
+- `check_joiners`: `true` – whether to check CONTEXTJ code points according to [Section 4.2.3.3](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.3) of [RFC 5891].
+- `transitional_processing`: `false` – (deprecated) whether to apply [transitional processing](https://www.unicode.org/reports/tr46/#ProcessingStepMap) for mapping.
+- `ignore_invalid_punycode`: `false` – whether to fast-path invalid Punycode labels according to [4th step of Processing](https://www.unicode.org/reports/tr46/#ProcessingStepPunycode).
+- `verify_dns_length`: `true` – whether to check DNS length according to [Section 4.4](https://datatracker.ietf.org/doc/html/rfc5891#section-4.4) of [RFC 5891].
+
 ```ruby
 require "uri/idna"
 
 URI::IDNA.to_ascii("Bloß.de")
 #=> "xn--blo-7ka.de"
 
-# UTS 46 transitional processing is disabled by default,
+# UTS46 transitional processing is disabled by default,
 # but can be enabled via option:
-URI::IDNA.to_ascii("Bloß.de", uts46_transitional: true)
+URI::IDNA.to_ascii("Bloß.de", transitional_processing: true)
 #=> "bloss.de"
 
-# Note that UTS 46 transitional processing is not fully IDNA 2008 compliant:
+# Note that UTS46 processing is not fully IDNA2008 compliant:
 URI::IDNA.to_ascii("☕.us")
 #=> "xn--53h.us"
 ```
 
 #### ToUnicode
 
+`URI::IDNA.to_unicode(domain_name, **options)`
+
+##### Options
+
+- `use_std3_ascii_rules`: `true` – whether to apply [STD3 rules](https://www.unicode.org/reports/tr46/#STD3_Rules) for both mapping and validation.
+- `check_hyphens`: `true` – whether to check hyphens according to [Section 4.2.3.1](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.1) of [RFC 5891].
+- `check_bidi`: `true` – whether to check bidirectional characters according to [Section 4.2.3.4](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.4) of [RFC 5891].
+- `check_joiners`: `true` – whether to check CONTEXTJ code points according to [Section 4.2.3.3](https://datatracker.ietf.org/doc/html/rfc5891#section-4.2.3.3) of [RFC 5891].
+- `transitional_processing`: `false` – (deprecated) whether to apply [transitional processing](https://www.unicode.org/reports/tr46/#ProcessingStepMap) for mapping.
+- `ignore_invalid_punycode`: `false` – whether to fast-path invalid Punycode labels according to [4th step of Processing](https://www.unicode.org/reports/tr46/#ProcessingStepPunycode).
+
 ```ruby
 require "uri/idna"
 
@@ -92,24 +138,83 @@ URI::IDNA.to_unicode("xn--blo-7ka.de")
 #=> "bloß.de"
 ```
 
-#### IDNA 2008 compatibility
+#### IDNA2008 compatibility
 
-It's possible to apply both IDNA 2008 and UTS 46 at once:
+It's possible to use UTS46 mapping first and then apply IDNA2008, so the processing fully conforms IDNA2008:
 
 ```ruby
 require "uri/idna"
 
-URI::IDNA.to_ascii("☕.us", idna_validity: true, contexto: true)
-#<URI::IDNA::InvalidCodepointError: Codepoint U+2615 at position 1 of "☕" not allowed>
+# For example we can use UTS46 mapping to downcase some characters
+char = "⼤"
+char.ord # "\u2F24"
+#=> 12068
+
+# just downcase doesn't work in this case
+char.downcase.ord
+#=> 12068
 
-# It's also possible to apply UTS 46 to IDNA 2008 protocols:
-URI::IDNA.lookup("Ῠ.me", check_dot: true, uts46: true, uts46_std3: true)
-#=> "xn--rtg.me"
+# but UTS46 mapping does it's thing:
+URI::IDNA::UTS46::Mapping.call(char).ord 
+#=> 22823
+
+# so here is a full example:
+domain = "⼤.cn" # "\u2F24.cn"
+URI::IDNA.lookup(domain)
+# <URI::IDNA::InvalidCodepointError: Codepoint U+2F24 at position 1 of "⼤" not allowed>
+
+mapped_domain = URI::IDNA::UTS46::Mapping.call(domain)
+URI::IDNA.lookup(mapped_domain)
+#=> "xn--pss.cn"
+```
+
+### WHATWG
+
+WHATWG's [URL Standard] uses UTS46 algorithm to define ToASCII and ToUnicode functions, it abstracts all available flags and provides only one—the `be_btrict` flag instead.
+
+Note that the `check_hyphens` UTS46 option is set to `false` in this algorithm.
+
+#### ToASCII
+
+`URI::IDNA.whatwg_to_ascii(domain_name, **options)`
+
+##### Options
+
+- `be_strict`: `true` – defines values of `use_std3_ascii_rules` and `verify_dns_length` UTS46 options.
+
+```ruby
+require "uri/idna"
+
+URI::IDNA.whatwg_to_ascii("Bloß.de")
+#=> "xn--blo-7ka.de"
+
+# The be_strict flag sets use_std3_ascii_rules and verify_dns_length UTS46 flags to its value
+URI::IDNA.whatwg_to_ascii("2003_rules.com", be_strict: false)
+#=> "2003_rules.com"
+
+# By default be_strict is set to true
+URI::IDNA.whatwg_to_ascii("2003_rules.com")
+#<URI::IDNA::InvalidCodepointError: Codepoint U+005F at position 5 of "2003_rules" not allowed>
+```
+
+#### ToUnicode
+
+`URI::IDNA.whatwg_to_unicode(domain_name, **options)`
+
+##### Options
+
+- `be_strict`: `true` - `be_strict`: `true` – defines value of `use_std3_ascii_rules` UTS46 option.
+
+```ruby
+require "uri/idna"
+
+URI::IDNA.whatwg_to_unicode("xn--blo-7ka.de")
+#=> "bloß.de"
 ```
 
 ### Punycode
 
-Punycode module performs conversion between Unicode and Punycode. Note that Punycode is not IDNA 2008 compliant, it is only used for conversion, no validations performed.
+Punycode module performs conversion between Unicode and Punycode. Note that Punycode is not IDNA2008 compliant, it is only used for conversion, no validations performed.
 
 ```ruby
 require "uri/idna/punycode"
@@ -123,7 +228,7 @@ URI::IDNA::Punycode.decode("gdkl8fhk5egc")
 
 ## Full technical reference:
 
-### IDNA 2008
+### IDNA2008
 - [RFC 5890] – Definitions and Document Framework
 - [RFC 5891] – Protocol
 - [RFC 5892] – The Unicode Code Points
@@ -133,9 +238,9 @@ URI::IDNA::Punycode.decode("gdkl8fhk5egc")
 
 - [RFC 3492] – Punycode: A Bootstring encoding of Unicode
 
-### UTS 46 (also referenced as TS46)
+### UTS46 (also referenced as TS46)
 
-- [Unicode IDNA Compatibility Processing]
+- [Unicode IDNA Compatibility Processing][UTS46]
 
 ## Development
 
@@ -147,7 +252,7 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
 
 This gem uses Unicode data files to perform IDN conversion. To generate new Unicode data files, run `bundle exec rake idna:generate`.
 
-To specify Unicode version, use `UNICODE_VERSION` environment variable, e.g. `UNICODE_VERSION=14.0.0 bundle exec rake idna:generate`.
+To specify Unicode version, use `VERSION` environment variable, e.g. `VERSION=15.1.0 bundle exec rake idna:generate`.
 
 By default, used Unicode version is the one used by the Ruby version (`RbConfig::CONFIG["UNICODE_VERSION"]`).
 
@@ -157,15 +262,13 @@ Unicode data cached in the `tmp` directory by default, to change it, use `CACHE_
 
 ### Inspect Unicode data
 
-To inspect Unicode data, run `bundle exec rake idna:inspect[<HEX_CODE>]`.
-
-To specify Unicode version, or cache directory, use `UNICODE_VERSION` or `CACHE_DIR` environment variables, e.g. `UNICODE_VERSION=15.0.0 bundle exec rake idna:inspect[1f495]`.
+To inspect Unicode data, run `bundle exec rake 'idna:inspect[<HEX_CODE>]'`.
 
-Note: if you getting the `no matches found: idna:inspect[1f495]` error, try to escape the brackets: `bundle exec rake idna:inspect\[1f495\]`.
+To specify Unicode version, or cache directory, use `VERSION` or `CACHE_DIR` environment variables, e.g. `VERSION=15.1.0 bundle exec rake 'idna:inspect[1f495]'`.
 
-### Update UTS 46 test suite data
+### Update UTS46 test suite data
 
-To update UTS 46 test suite data, run `bundle exec rake idna:update_uts46_test_suite`.
+To update UTS46 test suite data, run `bundle exec rake idna:update_uts46_test_suite`.
 
 ## Contributing
 
@@ -175,10 +278,11 @@ Bug reports and pull requests are welcome on GitHub at https://github.com/skryuk
 
 The gem is available as open source under the terms of the [MIT License].
 
-[RFC 5890]: (https://datatracker.ietf.org/doc/html/rfc5890)
-[RFC 5891]: (https://datatracker.ietf.org/doc/html/rfc5891)
-[RFC 5892]: (https://datatracker.ietf.org/doc/html/rfc5892)
-[RFC 5893]: (https://datatracker.ietf.org/doc/html/rfc5893)
-[RFC 3492]: (https://datatracker.ietf.org/doc/html/rfc3492)
-[Unicode IDNA Compatibility Processing]: (https://www.unicode.org/reports/tr46)
-[MIT License]: (https://opensource.org/licenses/MIT)
+[RFC 5890]: https://datatracker.ietf.org/doc/html/rfc5890
+[RFC 5891]: https://datatracker.ietf.org/doc/html/rfc5891
+[RFC 5892]: https://datatracker.ietf.org/doc/html/rfc5892
+[RFC 5893]: https://datatracker.ietf.org/doc/html/rfc5893
+[RFC 3492]: https://datatracker.ietf.org/doc/html/rfc3492
+[UTS46]: https://www.unicode.org/reports/tr46
+[URL Standard]: https://url.spec.whatwg.org/#idna
+[MIT License]: https://opensource.org/licenses/MIT

data/lib/uri/idna/base_processing.rb

@@ -0,0 +1,65 @@
+# frozen_string_literal: true
+
+require_relative "validation/label"
+require_relative "validation/codepoint"
+require_relative "validation/bidi"
+
+module URI
+  module IDNA
+    class BaseProcessing
+      def initialize(domain_name, **options)
+        @domain_name = domain_name
+        @options = options_class.new(**options)
+      end
+
+      private
+
+      attr_reader :domain_name, :options
+
+      def options_class
+        raise NotImplementedError, "Implement #options_class method"
+      end
+
+      def punycode_decode(label)
+        raise Error, "Label contains non-ASCII code point" unless label.ascii_only?
+
+        code = label[ACE_PREFIX.length..]
+        raise Error, "Malformed A-label, no Punycode eligible content found" if code.empty?
+
+        Punycode.decode(code)
+      end
+
+      def punycode_encode(label)
+        return label if label.ascii_only?
+
+        ACE_PREFIX + Punycode.encode(label)
+      end
+
+      def process_labels(domain)
+        labels, trailing_dot = split_domain(domain)
+
+        labels.map! do |label|
+          raise Error, "Empty label" if label.empty?
+
+          yield label
+        end
+
+        join_labels(labels, trailing_dot)
+      end
+
+      def join_labels(labels, trailing_dot)
+        labels << "" if trailing_dot
+        labels.join(".")
+      end
+
+      def split_domain(domain)
+        labels = domain.split(".", -1)
+        trailing_dot = labels[-1] && labels[-1].empty? ? labels.pop : false
+
+        raise Error, "Empty domain" if labels.empty? || labels == [""]
+
+        [labels, trailing_dot]
+      end
+    end
+  end
+end

data/lib/uri/idna/data/idna.rb

@@ -1,11 +1,11 @@
 # frozen_string_literal: true
 
 # This file is automatically generated by bin/generate
-# Unicode version 15.0.0
+# Unicode version 15.1.0
 
 module URI
   module IDNA
-    UNICODE_VERSION = "15.0.0"
+    UNICODE_VERSION = "15.1.0"
     SCRIPTS = {
       "Greek" => [
         0x37000000374,
@@ -64,6 +64,7 @@ module URI
         0x2b7400002b81e,
         0x2b8200002cea2,
         0x2ceb00002ebe1,
+        0x2ebf00002ee5e,
         0x2f8000002fa1e,
         0x300000003134b,
         0x31350000323b0,
@@ -2139,6 +2140,7 @@ module URI
         0x2b7400002b81e,
         0x2b8200002cea2,
         0x2ceb00002ebe1,
+        0x2ebf00002ee5e,
         0x300000003134b,
         0x31350000323b0,
       ],
@@ -2621,7 +2623,7 @@ module URI
         0x2e8000002e9a,
         0x2e9b00002ef4,
         0x2f0000002fd6,
-        0x2ff000002ffc,
+        0x2ff000003000,
         0x300100003005,
         0x300800003021,
         0x303000003031,
@@ -2631,6 +2633,7 @@ module URI
         0x30a0000030a1,
         0x30fb000030fc,
         0x31c0000031e4,
+        0x31ef000031f0,
         0x321d0000321f,
         0x325000003260,
         0x327c0000327f,
@@ -3003,13 +3006,13 @@ module URI
         0x2e9a00002e9b,
         0x2ef400002f00,
         0x2fd600002ff0,
-        0x2ffc00003001,
+        0x300000003001,
         0x304000003041,
         0x309700003099,
         0x310000003105,
         0x313000003131,
         0x318f00003190,
-        0x31e4000031f0,
+        0x31e4000031ef,
         0x321f00003220,
         0xa48d0000a490,
         0xa4c70000a4d0,
@@ -3432,7 +3435,8 @@ module URI
         0x2b73a0002b740,
         0x2b81e0002b820,
         0x2cea20002ceb0,
-        0x2ebe10002f800,
+        0x2ebe10002ebf0,
+        0x2ee5e0002f800,
         0x2fa1e00030000,
         0x3134b00031350,
         0x323b0000e0001,
@@ -4194,6 +4198,7 @@ module URI
         0x2b7400002b81e,
         0x2b8200002cea2,
         0x2ceb00002ebe1,
+        0x2ebf00002ee5e,
         0x2f8000002fa1e,
         0x300000003134b,
         0x31350000323b0,

data/lib/uri/idna/data/uts46.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 # This file is automatically generated by bin/generate
-# Unicode version 15.0.0
+# Unicode version 15.1.0
 
 module URI
   module IDNA
@@ -1824,7 +1824,7 @@ module URI
       [0x1E9A, "M", "aʾ"],
       [0x1E9B, "M", "ṡ"],
       [0x1E9C, "V"],
-      [0x1E9E, "M", "ss"],
+      [0x1E9E, "M", "ß"],
       [0x1E9F, "V"],
       [0x1EA0, "M", "ạ"],
       [0x1EA1, "V"],
@@ -2323,10 +2323,6 @@ module URI
       [0x222F, "M", "∮∮"],
       [0x2230, "M", "∮∮∮"],
       [0x2231, "V"],
-      [0x2260, "3"],
-      [0x2261, "V"],
-      [0x226E, "3"],
-      [0x2270, "V"],
       [0x2329, "M", "〈"],
       [0x232A, "M", "〉"],
       [0x232B, "V"],
@@ -7646,6 +7642,8 @@ module URI
       [0x2CEA2, "X"],
       [0x2CEB0, "V"],
       [0x2EBE1, "X"],
+      [0x2EBF0, "V"],
+      [0x2EE5E, "X"],
       [0x2F800, "M", "丽"],
       [0x2F801, "M", "丸"],
       [0x2F802, "M", "乁"],

data/lib/uri/idna/idna2008/options.rb

@@ -0,0 +1,59 @@
+# frozen_string_literal: true
+
+module URI
+  module IDNA
+    module IDNA2008
+      class Options
+        attr_reader :flags
+
+        CHECK_HYPHENS        = 1 << 0
+        LEADING_COMBINING    = 1 << 1
+        CHECK_JOINERS        = 1 << 2
+        CHECK_OTHERS         = 1 << 3
+        CHECK_BIDI           = 1 << 4
+        VERIFY_DNS_LENGTH    = 1 << 5
+
+        def initialize(
+          check_hyphens: true,
+          leading_combining: true,
+          check_joiners: true,
+          check_others: true,
+          check_bidi: true,
+          verify_dns_length: true
+        )
+          @flags = 0
+          @flags |= CHECK_HYPHENS if check_hyphens
+          @flags |= LEADING_COMBINING if leading_combining
+          @flags |= CHECK_JOINERS if check_joiners
+          @flags |= CHECK_OTHERS if check_others
+          @flags |= CHECK_BIDI if check_bidi
+          @flags |= VERIFY_DNS_LENGTH if verify_dns_length
+        end
+
+        def check_hyphens?
+          (flags & CHECK_HYPHENS) != 0
+        end
+
+        def leading_combining?
+          (flags & LEADING_COMBINING) != 0
+        end
+
+        def check_joiners?
+          (flags & CHECK_JOINERS) != 0
+        end
+
+        def check_others?
+          (flags & CHECK_OTHERS) != 0
+        end
+
+        def check_bidi?
+          (flags & CHECK_BIDI) != 0
+        end
+
+        def verify_dns_length?
+          (flags & VERIFY_DNS_LENGTH) != 0
+        end
+      end
+    end
+  end
+end