accept_language 2.1.0 → 2.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7273e9328183e3dee11fd68a6598d82c67efbb8bab156d6d9b3424d9ed45dcca
-  data.tar.gz: ec31e8a4ac07501f1c481e65452f362be2d7669d93eea626977f25c3aca88dc2
+  metadata.gz: c1d4f90fc40c062ac4f250c1c3b8ac8540796b232cf63b7d5c25b5e2e3c9124e
+  data.tar.gz: 150bb9def9e5f4799c432df6d6c364fedf88132b117d28e79a6ed44f467dcc70
 SHA512:
-  metadata.gz: 36120af5b03b49ea9dce1d50e5c7915c62bf9b0fa09c1130516090e4e3c882b924035f963ad2dc559fda0e818633b6a3e77aba3e46b25533bc972f5dc23ca729
-  data.tar.gz: d11855f60c7a4a35c8f675ea5ffc4b320db5a4b40cc95e57143b3dad3c188580830ae0052ac7e934f5ae4c5f2be582db47b4e85b9513b78b4ec1fc69a97ee850
+  metadata.gz: 537d924a23dc3c0fe8fb523556a6da653e16471b6b8ca94e0ee57f36fa1d6842103e380c3ea1e2dbd468b06a65a698ecdbf8923235f4eac0031a52801ba446f8
+  data.tar.gz: 8e48f57d2f0a4005483d29cf5503accc39eecffe19f78e8848dfa216422d1b2792f50cc5199c938674a483ef90ca20127fbfe452c0eebae9e30b36d7b8dc0bc2

data/README.md

@@ -1,6 +1,6 @@
 # AcceptLanguage
 
-A lightweight, thread-safe Ruby library for parsing `Accept-Language` HTTP headers as defined in [RFC 2616](https://tools.ietf.org/html/rfc2616#section-14.4).
+A lightweight, thread-safe Ruby library for parsing `Accept-Language` HTTP headers as defined in [RFC 2616](https://tools.ietf.org/html/rfc2616#section-14.4), with full support for [BCP 47](https://tools.ietf.org/html/bcp47) language tags.
 
 [![Version](https://img.shields.io/github/v/tag/cyril/accept_language.rb?label=Version&logo=github)](https://github.com/cyril/accept_language.rb/tags)
 [![Yard documentation](https://img.shields.io/badge/Yard-documentation-blue.svg?logo=github)](https://rubydoc.info/github/cyril/accept_language.rb/main)
@@ -69,6 +69,24 @@ AcceptLanguage.parse("en-GB").match("en-gb") # => "en-gb"
 AcceptLanguage.parse("en-gb").match("en-GB") # => "en-GB"
 ```
 
+### BCP 47 support
+
+This library supports [BCP 47](https://tools.ietf.org/html/bcp47) language tags, including:
+
+- **Script subtags**: `zh-Hans` (Simplified Chinese), `zh-Hant` (Traditional Chinese)
+- **Region subtags**: `en-US`, `pt-BR`
+- **Variant subtags**: `sl-nedis` (Slovenian Nadiza dialect), `de-1996` (German orthography reform)
+
+```ruby
+# Script variants
+AcceptLanguage.parse("zh-Hans").match(:"zh-Hans-CN", :"zh-Hant-TW")
+# => :"zh-Hans-CN"
+
+# Orthography variants (numeric subtags)
+AcceptLanguage.parse("de-1996, de;q=0.9").match(:"de-CH-1996", :"de-CH")
+# => :"de-CH-1996"
+```
+
 ## Rails integration
 
 ```ruby

data/lib/accept_language/matcher.rb

@@ -21,6 +21,10 @@ module AcceptLanguage
 
       languages_range.select do |langtag, quality|
         if quality.zero?
+          # Exclude specific language tags, but NOT the wildcard.
+          # When "*;q=0" is specified, all non-listed languages become
+          # unacceptable implicitly (they won't match any preferred_langtags).
+          # Adding "*" to excluded_langtags would break prefix_match? logic.
           @excluded_langtags << langtag unless wildcard?(langtag)
         else
           level = (quality * 1_000).to_i
@@ -61,37 +65,43 @@ module AcceptLanguage
     end
 
     def find_matching_tag(preferred_tag, available_langtags)
-      pattern = /\A#{::Regexp.escape(preferred_tag)}/i
-      available_langtags.find { |tag| tag.match?(pattern) }
+      available_langtags.find { |tag| prefix_match?(preferred_tag, String(tag.downcase)) }
     end
 
     def any_other_langtag(*available_langtags)
+      langtags = preferred_langtags - [WILDCARD]
+
       available_langtags.find do |available_langtag|
-        langtags = preferred_langtags - [WILDCARD]
-        langtags.none? do |tag|
-          pattern = /\A#{::Regexp.escape(tag)}/i
-          available_langtag.match?(pattern)
-        end
+        available_downcased = available_langtag.downcase
+        langtags.none? { |tag| prefix_match?(tag, String(available_downcased)) }
       end
     end
 
     def drop_unacceptable(*available_langtags)
-      available_langtags.inject(::Set[]) do |langtags, available_langtag|
-        next langtags if unacceptable?(available_langtag)
-
-        langtags + ::Set[available_langtag]
+      available_langtags.each_with_object(::Set[]) do |available_langtag, langtags|
+        langtags << available_langtag unless unacceptable?(available_langtag)
       end
     end
 
     def unacceptable?(langtag)
-      excluded_langtags.any? do |excluded_tag|
-        pattern = /\A#{::Regexp.escape(excluded_tag)}/i
-        langtag.match?(pattern)
-      end
+      langtag_downcased = langtag.downcase
+      excluded_langtags.any? { |excluded_tag| prefix_match?(excluded_tag, String(langtag_downcased)) }
     end
 
     def wildcard?(value)
       value.eql?(WILDCARD)
     end
+
+    # Implements RFC 2616 Section 14.4 prefix matching rule:
+    # "A language-range matches a language-tag if it exactly equals the tag,
+    # or if it exactly equals a prefix of the tag such that the first tag
+    # character following the prefix is '-'."
+    #
+    # @param prefix [String] The language-range to match (downcased)
+    # @param tag [String] The language-tag to test (downcased)
+    # @return [Boolean] true if prefix matches tag per RFC 2616 rules
+    def prefix_match?(prefix, tag)
+      tag == prefix || tag.start_with?("#{prefix}-")
+    end
   end
 end

data/lib/accept_language/parser.rb

@@ -22,8 +22,21 @@ module AcceptLanguage
     # @api private
     SUFFIX = ";q="
     # @api private
-    QVALUE_PATTERN = /\A(?:0(?:\.[0-9]{1,3})?|1(?:\.0{1,3})?|\.[0-9]{1,3})\z/
+    # RFC 2616 Section 3.9 qvalue syntax:
+    #   qvalue = ( "0" [ "." 0*3DIGIT ] ) | ( "1" [ "." 0*3("0") ] )
+    QVALUE_PATTERN = /\A(?:0(?:\.[0-9]{1,3})?|1(?:\.0{1,3})?)\z/
     # @api private
+    # Language tag pattern supporting BCP 47 (RFC 5646) alphanumeric subtags.
+    #
+    # RFC 2616 Section 3.10 references RFC 1766, which only allowed ALPHA in subtags.
+    # However, BCP 47 (the current standard) permits alphanumeric subtags:
+    #   subtag = 1*8alphanum
+    #   alphanum = ALPHA / DIGIT
+    #
+    # Examples of valid BCP 47 tags with numeric subtags:
+    #   - "de-CH-1996" (German, Switzerland, orthography variant 1996)
+    #   - "sl-IT-nedis" (Slovenian, Italy, Nadiza dialect)
+    #   - "zh-Hans-CN" (Chinese, Simplified script, China)
     LANGTAG_PATTERN = /\A(?:\*|[a-zA-Z]{1,8}(?:-[a-zA-Z0-9]{1,8})*)\z/
 
     # @api private
@@ -54,7 +67,7 @@ module AcceptLanguage
     private
 
     def import(field)
-      "#{field}".delete(SPACE).split(SEPARATOR).inject({}) do |hash, lang|
+      "#{field}".downcase.delete(SPACE).split(SEPARATOR).inject({}) do |hash, lang|
         tag, quality = lang.split(SUFFIX)
         next hash unless valid_tag?(tag)
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: accept_language
 version: !ruby/object:Gem::Version
-  version: 2.1.0
+  version: 2.1.1
 platform: ruby
 authors:
 - Cyril Kato
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-01-15 00:00:00.000000000 Z
+date: 2026-01-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bigdecimal