bcp47_spec 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 1b7ac3631986a8b1fd3df0f12f8a7358ba0523dbdb7d16c5bba5b61a53ae5a02
+  data.tar.gz: 99813e4da3415417889603d1ee9daab2c31b5468ecc1246cb7095140b49791d0
+SHA512:
+  metadata.gz: 27717b3a58240861bd7bbfa8ed2ac94370d01039c0c2ae002959fdd5a5e98e4a2e3f67b262120c46347f9ce9d4cfc00cdd9dd2dc39e70f5bca0312979b9f4a6f
+  data.tar.gz: d36beae7a694d77563b09cac2958515edc9f6d630bf54f01786fa13e7f57defc3d5639f42a1b2e429e97d74b59c8b38c9f757efe5a95f51c9b7b191afbc8fe1f

data/Readme.md

@@ -0,0 +1,45 @@
+# bcp47_spec [![Build Status](https://travis-ci.org/dadah89/bcp47_spec.svg?branch=master)](https://travis-ci.org/dadah89/bcp47_spec)
+A subset of the BCP 47 spec: https://tools.ietf.org/html/bcp47
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'bcp47_spec'
+```
+
+And then execute:
+```
+$ bundle
+```
+
+Or install it yourself as:
+```
+$ gem install bcp47_spec
+```
+
+## Usage
+
+```ruby
+BCP47.valid?('de-Latn-DE-1996-u-attr-co-phonebk-t-und-cyrl-x-private-test') # true
+```
+
+```ruby
+tag = BCP47.parse('de-Latn-DE-1996-u-attr-co-phonebk-t-und-cyrl-x-private-test')
+tag.language  # de
+tag.script    # Latn
+tag.region    # DE
+tag.variant   # [1996]
+tag.extension # [['t', 'und-cyrl'], ['u', 'attr-co-phonebk']]
+tag.private   # ['private', 'test']
+```
+
+```ruby
+BCP47.parse('blahblahblah') # raises InvalidLanguageTag
+```
+
+## TODO
+
+* Parse private and grandfathered language tags (maybe?)
+* Parse extensions T (https://tools.ietf.org/html/rfc6497) and U (https://tools.ietf.org/html/rfc6067)

data/lib/bcp47_spec/parser.rb

@@ -0,0 +1,135 @@
+# frozen_string_literal: true
+
+module BCP47::Parser
+  # https://tools.ietf.org/html/bcp47#section-2.1
+  # Augmented BNF for Syntax Specifications: https://tools.ietf.org/html/rfc5234
+
+  # Language-Tag  = langtag             ; normal language tags
+  #               / privateuse          ; private use tag
+  #               / grandfathered       ; grandfathered tags
+
+  # langtag       = language
+  #                 ["-" script]
+  #                 ["-" region]
+  #                 *("-" variant)
+  #                 *("-" extension)
+  #                 ["-" privateuse]
+
+  # language      = 2*3ALPHA            ; shortest ISO 639 code
+  #                 ["-" extlang]       ; sometimes followed by
+  #                                     ; extended language subtags
+  #               / 4ALPHA              ; or reserved for future use
+  #               / 5*8ALPHA            ; or registered language subtag
+
+  # extlang       = 3ALPHA              ; selected ISO 639 codes
+  #                 *2("-" 3ALPHA)      ; permanently reserved
+
+  # script        = 4ALPHA              ; ISO 15924 code
+
+  # region        = 2ALPHA              ; ISO 3166-1 code
+  #               / 3DIGIT              ; UN M.49 code
+
+  # variant       = 5*8alphanum         ; registered variants
+  #               / (DIGIT 3alphanum)
+
+  # extension     = singleton 1*("-" (2*8alphanum))
+
+  #                                     ; Single alphanumerics
+  #                                     ; "x" reserved for private use
+  # singleton     = DIGIT               ; 0 - 9
+  #               / %x41-57             ; A - W
+  #               / %x59-5A             ; Y - Z
+  #               / %x61-77             ; a - w
+  #               / %x79-7A             ; y - z
+
+  # privateuse    = "x" 1*("-" (1*8alphanum))
+
+  # grandfathered = irregular           ; non-redundant tags registered
+  #               / regular             ; during the RFC 3066 era
+
+  # irregular     = "en-GB-oed"         ; irregular tags do not match
+  #               / "i-ami"             ; the 'langtag' production and
+  #               / "i-bnn"             ; would not otherwise be
+  #               / "i-default"         ; considered 'well-formed'
+  #               / "i-enochian"        ; These tags are all valid,
+  #               / "i-hak"             ; but most are deprecated
+  #               / "i-klingon"         ; in favor of more modern
+  #               / "i-lux"             ; subtags or subtag
+  #               / "i-mingo"           ; combination
+  #               / "i-navajo"
+  #               / "i-pwn"
+  #               / "i-tao"
+  #               / "i-tay"
+  #               / "i-tsu"
+  #               / "sgn-BE-FR"
+  #               / "sgn-BE-NL"
+  #               / "sgn-CH-DE"
+
+  # regular       = "art-lojban"        ; these tags match the 'langtag'
+  #               / "cel-gaulish"       ; production, but their subtags
+  #               / "no-bok"            ; are not extended language
+  #               / "no-nyn"            ; or variant subtags: their meaning
+  #               / "zh-guoyu"          ; is defined by their registration
+  #               / "zh-hakka"          ; and all of these are deprecated
+  #               / "zh-min"            ; in favor of a more modern
+  #               / "zh-min-nan"        ; subtag or sequence of subtags
+  #               / "zh-xiang"
+
+  # alphanum      = (ALPHA / DIGIT)     ; letters and numbers
+
+  # Simplified check. Not implementing high level privateuse / grandfathered.
+  # Should replace with a proper check at some point.
+  ALPHANUM = /[a-zA-Z\d]/
+  SINGLETON = /[\dA-WY-Za-wy-z]/
+
+  EXTLANG = /[a-zA-Z]{3}(-[a-zA-Z]{3}){0,2}/
+
+  LANGUAGE   = /([a-zA-Z]{2,3}(-#{EXTLANG})?|[a-zA-Z]{4}|[a-zA-Z]{5,8})/
+  SCRIPT     = /[a-zA-Z]{4}/
+  REGION     = /([a-zA-Z]{2}|\d{3})/
+  VARIANT    = /(#{ALPHANUM}{5,8}|\d#{ALPHANUM}{3})/
+  EXTENSION  = /#{SINGLETON}(-[a-zA-Z]{2,8})+/
+  PRIVATEUSE = /x(-#{ALPHANUM}{1,8})+/
+
+  # Ruby .match only keeps the first captured group, so expressions like variants/extensions we need to keep everything
+  # in one captured group, then break them down in multipe groups separately
+  LANGTAG = %r{
+    (?<language>#{LANGUAGE})
+    (-(?<script>#{SCRIPT}))?
+    (-(?<region>#{REGION}))?
+    (?<variants>(-#{VARIANT})*)
+    (?<extensions>(-#{EXTENSION})*)
+    (-(?<private>#{PRIVATEUSE}))?
+  }x
+
+  LANGUAGE_TAG = /\A#{LANGTAG}\z/
+
+  class << self
+    def parse(language_tag)
+      return unless match = language_tag.match(LANGUAGE_TAG)
+
+      named_captures(match).tap do |captures|
+        captures['variants']   = captures['variants'].to_s.empty? ? [] : captures['variants'][/-(.*)/, 1].split('-').sort
+        captures['extensions'] = split_extensions(captures['extensions'])
+        captures['private']    = captures['private'].to_s.empty? ? [] : captures['private'][/x-(.*)/, 1].split('-').sort
+      end
+    end
+
+    private
+
+    def named_captures(match)
+      return match.named_captures if match.respond_to?(:named_captures)
+
+      match.names.each_with_object({}) { |name, acc| acc[name] = match[name] }
+    end
+
+    def split_extensions(extensions)
+      return [] if extensions.to_s.empty?
+
+      # [["u-attr-co-phonebk"], ["t-und-cyrl"]]
+      extensions = extensions.scan(/\b(?<ext>#{EXTENSION})\b/)
+      # [["t", "und-cyrl"], ["u", "attr-co-phonebk"]]
+      extensions.flatten.sort.map { |st| st.split('-', 2) }
+    end
+  end
+end

data/lib/bcp47_spec/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module BCP47
+  VERSION = '0.2.0'.freeze
+end

data/lib/bcp47_spec.rb

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+require 'bcp47_spec/parser'
+require 'bcp47_spec/version'
+
+module BCP47
+  class InvalidLanguageTag < StandardError; end
+
+  Tag = Struct.new(:language, :script, :region, :variants, :extensions, :private)
+
+  class << self
+    def valid?(language_tag)
+      !Parser.parse(language_tag).nil?
+    end
+
+    def parse(language_tag)
+      result = Parser.parse(language_tag)
+      raise InvalidLanguageTag, "Invalid language tag: #{language_tag}" unless result
+
+      fields = %w[language script region variants extensions private]
+      Tag.new(*result.values_at(*fields))
+    end
+  end
+end

metadata

@@ -0,0 +1,159 @@
+--- !ruby/object:Gem::Specification
+name: bcp47_spec
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Igor Justino
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-09-26 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bump
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: maxitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: mocha
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: single_cov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 
+email: 
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- Readme.md
+- lib/bcp47_spec.rb
+- lib/bcp47_spec/parser.rb
+- lib/bcp47_spec/version.rb
+homepage: https://github.com/dadah89/bcp47_spec
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
+specification_version: 4
+summary: A subset of the BCP 47 spec.
+test_files: []