tanuki_emoji 0.2.2 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 645689214f62f8cecd946ba6976840c6c590d4c005ba0e7453bfff581a92a8c6
-  data.tar.gz: 6a513c16e4a198a2c6b583421f84fd63b2be942fc6f3c4504f57a331a0e2c098
+  metadata.gz: 80827a5454f2eb6ed96102851f315c04215bda544c83892570e6b035ce43cbdd
+  data.tar.gz: c3a97c5c042b909a8544173865f8921e23093333b465fc47ee4f6e306df9480f
 SHA512:
-  metadata.gz: 79b2910f7c1cdf7526fac4daf312577b88b2c00c2c8915ba29f5f83946271378bcfc0223938a501088a58072009dd881079f8ff5bd2a5aecc6b5c9162e49b108
-  data.tar.gz: 5d1dc520b29a272f279465afd4fcdc48669a59bfd6edc98250a1592ba377dc7f90e1ba9ba27b3fa451613e6b1a8fb0a6d7c2c43edf9f09b84ac172a421050a85
+  metadata.gz: b5d4fa24f4a0a954df5000d6a04f5c7f8621f6e1b9c2aa5fcb448b3e15af4df927f7033f57c125d9d1b0e11132175cf7351b631c19fe05aa4678c07f402e7636
+  data.tar.gz: 59439b83f98f62e9ace8756accfa327499182309b777864ad87847e567ddfe157b5056844a9033b50548784dec78d51b3d6ab358ef9b0c0a78ffff0e2fe20a67

data/.gitlab-ci.yml

@@ -47,3 +47,6 @@ include:
   - template: Dependency-Scanning.gitlab-ci.yml
   - template: Security/License-Scanning.gitlab-ci.yml
   - template: Code-Quality.gitlab-ci.yml
+  - project: 'gitlab-org/quality/pipeline-common'
+    file:
+      - '/ci/danger-review.yml'

data/.ruby-version

@@ -0,0 +1 @@
+2.7.5

data/CHANGELOG.md

@@ -6,7 +6,33 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [0.2.2] - 2021-08-32
+## [0.6.0] - 2022-02-16
+### Added
+- `Character` responds to `ascii_aliases` which contain ASCII aliases from Gemojione
+
+### Fixed
+- Fixed `TanukiEmoji.add` command, which should now require `category:` to be provided
+- Fixed issue where `TanukiEmoji::Index#codepoints_pattern` would split apart emoji-modifier pairs
+
+## [0.5.0] - 2021-09-16
+### Added
+- Add Category information into `Character`
+- Add Character.unicode_version and index in which unicode version an emoji was introduced
+
+## [0.4.0] - 2021-09-07
+### Added
+- Index can return the `alpha_code_pattern` and `codepoints_pattern` to be used as text extraction sources
+
+### Fixed
+- Fixed `registered sign`, `copyright sign` and `trade mark sign` codepoints from gemojione index
+
+## [0.3.0] - 2021-08-26
+### Modified
+- Characters can be compared and will be considered equal when all of its attributes matches
+- `:+1:` and `:-1:` which are aliases for `:thumbsup:` and `:thumbsdown:` can now be used with `find_by_alpha_code`
+- added tests for both `find_by_alpha_code` and `find_by_codepoints` and make sure `find_by_alpha_code` can handle `nil` correctly
+
+## [0.2.2] - 2021-08-23
 ### Modified
 - Fixed autoload load_path
 
@@ -27,3 +53,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [0.1.0]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.1.0
 [0.2.0]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.2.0
 [0.2.1]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.2.1
+[0.2.2]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.2.2
+[0.3.0]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.3.0
+[0.4.0]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.4.0
+[0.5.0]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.5.0
+[0.6.0]:https://gitlab.com/gitlab-org/tanuki_emoji/-/releases/v0.6.0

data/Dangerfile

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+require 'gitlab-dangerfiles'
+
+Gitlab::Dangerfiles.for_project(self, &:import_defaults)

data/Gemfile.lock

@@ -1,19 +1,98 @@
 PATH
   remote: .
   specs:
-    tanuki_emoji (0.2.2)
+    tanuki_emoji (0.6.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
+    addressable (2.8.0)
+      public_suffix (>= 2.0.2, < 5.0)
     ast (2.4.2)
+    claide (1.1.0)
+    claide-plugins (0.9.2)
+      cork
+      nap
+      open4 (~> 1.3)
+    colored2 (3.1.2)
+    cork (0.3.0)
+      colored2 (~> 3.1)
+    danger (8.4.2)
+      claide (~> 1.0)
+      claide-plugins (>= 0.9.2)
+      colored2 (~> 3.1)
+      cork (~> 0.1)
+      faraday (>= 0.9.0, < 2.0)
+      faraday-http-cache (~> 2.0)
+      git (~> 1.7)
+      kramdown (~> 2.3)
+      kramdown-parser-gfm (~> 1.0)
+      no_proxy_fix
+      octokit (~> 4.7)
+      terminal-table (>= 1, < 4)
+    danger-gitlab (8.0.0)
+      danger
+      gitlab (~> 4.2, >= 4.2.0)
     diff-lcs (1.4.4)
     docile (1.4.0)
+    faraday (1.9.3)
+      faraday-em_http (~> 1.0)
+      faraday-em_synchrony (~> 1.0)
+      faraday-excon (~> 1.1)
+      faraday-httpclient (~> 1.0)
+      faraday-multipart (~> 1.0)
+      faraday-net_http (~> 1.0)
+      faraday-net_http_persistent (~> 1.0)
+      faraday-patron (~> 1.0)
+      faraday-rack (~> 1.0)
+      faraday-retry (~> 1.0)
+      ruby2_keywords (>= 0.0.4)
+    faraday-em_http (1.0.0)
+    faraday-em_synchrony (1.0.0)
+    faraday-excon (1.1.0)
+    faraday-http-cache (2.2.0)
+      faraday (>= 0.8)
+    faraday-httpclient (1.0.1)
+    faraday-multipart (1.0.3)
+      multipart-post (>= 1.2, < 3)
+    faraday-net_http (1.0.1)
+    faraday-net_http_persistent (1.2.0)
+    faraday-patron (1.0.0)
+    faraday-rack (1.0.0)
+    faraday-retry (1.0.3)
+    git (1.10.2)
+      rchardet (~> 1.8)
+    gitlab (4.18.0)
+      httparty (~> 0.18)
+      terminal-table (>= 1.5.1)
+    gitlab-dangerfiles (2.8.0)
+      danger (>= 8.3.1)
+      danger-gitlab (>= 8.0.0)
+    httparty (0.20.0)
+      mime-types (~> 3.0)
+      multi_xml (>= 0.5.2)
+    kramdown (2.3.1)
+      rexml
+    kramdown-parser-gfm (1.1.0)
+      kramdown (~> 2.0)
+    mime-types (3.4.1)
+      mime-types-data (~> 3.2015)
+    mime-types-data (3.2022.0105)
+    multi_xml (0.6.0)
+    multipart-post (2.1.1)
+    nap (1.1.0)
+    no_proxy_fix (0.1.2)
+    octokit (4.22.0)
+      faraday (>= 0.9)
+      sawyer (~> 0.8.0, >= 0.5.3)
+    open4 (1.3.4)
     parallel (1.20.1)
     parser (3.0.2.0)
       ast (~> 2.4.1)
+    public_suffix (4.0.6)
     rainbow (3.0.0)
     rake (13.0.6)
+    rchardet (1.8.0)
     regexp_parser (2.1.1)
     rexml (3.2.5)
     rspec (3.10.0)
@@ -43,6 +122,10 @@ GEM
     rubocop-ast (1.8.0)
       parser (>= 3.0.1.1)
     ruby-progressbar (1.11.0)
+    ruby2_keywords (0.0.5)
+    sawyer (0.8.2)
+      addressable (>= 2.3.5)
+      faraday (> 0.8, < 2.0)
     simplecov (0.21.2)
       docile (~> 1.1)
       simplecov-html (~> 0.11)
@@ -51,12 +134,17 @@ GEM
       simplecov (~> 0.8)
     simplecov-html (0.12.3)
     simplecov_json_formatter (0.1.3)
+    terminal-table (3.0.2)
+      unicode-display_width (>= 1.1.1, < 3)
     unicode-display_width (2.0.0)
 
 PLATFORMS
+  ruby
   x86_64-darwin-20
+  x86_64-linux
 
 DEPENDENCIES
+  gitlab-dangerfiles (~> 2.8.0)
   rake (~> 13.0)
   rspec (~> 3.0)
   rspec_junit_formatter (~> 0.4.0)
@@ -66,4 +154,4 @@ DEPENDENCIES
   tanuki_emoji!
 
 BUNDLED WITH
-   2.2.15
+   2.2.22

data/README.md

@@ -70,17 +70,36 @@ File.join(TanukiEmoji.images_path, c.image_name)
 
 ## Development
 
-After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. 
-You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+In order to contribute to TanukiEmoji gem, you need to:
 
-To install this gem onto your local machine, run `bundle exec rake install`. 
-To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, 
-which will create a git tag for the version, push git commits and the created tag, and push the `.gem` file to 
+1. Clone the repository to your local machine.
+1. Run `bin/setup` to initialize `git submodules` and install ruby dependencies.
+
+Many workflow tasks are available as Rake tasks:
+
+- `bundle exec rake spec` can be used to run tests.
+- `bundle exec rake install` will build and install the gem on your local machine.
+
+To load an interactive console with the gem you can use `bin/console`.
+
+### Releasing a new version
+
+Before releasing a new gem, create a MR with the following changes:
+
+- Update `CHANGELOG.md` by adding a version section and moving any changes from `[Unreleased]` to it.
+- Update the version number in `lib/tanuki_emoji/version.rb`.
+
+With that MR approved and merged, pull the changes to your `main` branch and run `bundle exec rake release`.
+This command will create a git tag for the version and push it, generate a new `.gem` file and publish into
 [rubygems.org](https://rubygems.org).
 
 ## Contributing
 
-See [CONTRIBUTING.md](CONTRIBUTING.md).
+See [CONTRIBUTING.md](CONTRIBUTING.md) and [Development](#development) section.
+
+When you create a new Merge Request, consider adding your change to the `CHANGELOG.md` if it includes a new feature, a feature change or a fix.
+
+Please do not increase the version numbers, as this is handled by a separate process when we [release a new version](#releasing-a-new-version).
 
 ## License
 

data/Rakefile

@@ -42,12 +42,11 @@ namespace :noto_emoji do
 
   task :generate_flags do
     chdir(File.expand_path(noto_emoji_path)) do
-      Dir['third_party/region-flags/png/*.png'].each do |file|
-        filename = File.basename(file)
-        puts filename
-
-        sh("make build/flags/#{filename}")
+      flags = Dir['third_party/region-flags/png/*.png'].map do |file|
+        File.join('build/flags', File.basename(file))
       end
+
+      sh('make', *flags)
     end
   end
 end

data/lib/tanuki_emoji/character.rb

@@ -9,28 +9,36 @@ module TanukiEmoji
     IMAGE_PREFIX = 'emoji_u'
     IMAGE_EXTENSION = '.png'
     FLAG_REGEXP = /[🇦-🇿]{2}/u.freeze
+    ALPHA_CODE_REGEXP = /:(?<alpha_text>[_+\-a-z0-9]+):/.freeze
 
     # This denotes a "color" or "emoji" version
     EMOJI_VARIATION_SELECTOR = 0xFE0F
 
     # This denotes a "plain" (black/white) or "textual" version
     PLAIN_VARIATION_SELECTOR = 0xFE0E
+    PLAIN_VARIATION_SELECTOR_STRING = PLAIN_VARIATION_SELECTOR.chr(Encoding::UTF_8)
 
     # Zero Width Joiner is used in sequences to indicate they should all be evaluated and displayed as a single thing
     ZWJ_TAG = 0x200D
 
-    attr_reader :name, :codepoints, :codepoints_alternates, :alpha_code, :aliases, :description
+    attr_reader :name, :codepoints, :codepoints_alternates, :alpha_code, :aliases, :ascii_aliases, :description, :category
+
+    attr_accessor :unicode_version
 
     # @param [String] name
     # @param [String] codepoints
     # @param [String] alpha_code
-    def initialize(name, codepoints:, alpha_code:, description:)
-      @name = name
+    # @param [String] description
+    # @param [String] category
+    def initialize(name, codepoints:, alpha_code:, description:, category:)
+      @name = self.class.format_name(name)
       @codepoints = codepoints
       @codepoints_alternates = []
       @alpha_code = self.class.format_alpha_code(alpha_code)
       @aliases = []
+      @ascii_aliases = []
       @description = description
+      @category = category
     end
 
     # Add alternative codepoints to this character
@@ -47,6 +55,13 @@ module TanukiEmoji
       aliases << self.class.format_alpha_code(alpha_code)
     end
 
+    # Add alternative ASCII aliases to this character
+    #
+    # @param [String] ascii_string
+    def add_ascii_alias(ascii_string)
+      ascii_aliases << ascii_string
+    end
+
     # Return a Hex formatted version of the Unicode code points
     #
     # @return [String] Hex formatted version of the unicode
@@ -82,14 +97,28 @@ module TanukiEmoji
       "#<#{self.class.name}:#{name} #{codepoints}(#{hex})>"
     end
 
-    # Convert Unicode code points to Hex format for inspection
-    #
-    # ensure alpha code is formatted with colons
+    def ==(other)
+      name == other.name &&
+        codepoints == other.codepoints &&
+        codepoints_alternates == other.codepoints_alternates &&
+        alpha_code == other.alpha_code &&
+        aliases == other.aliases &&
+        ascii_aliases == other.ascii_aliases &&
+        description == other.description
+    end
+
+    # Ensure alpha code is formatted with colons
     #
     # @param [String] alpha_code
     # @return [String] formatted alpha code
     def self.format_alpha_code(alpha_code)
-      alpha_code.match?(/:([a-z_0-9]+):/) ? alpha_code : ":#{alpha_code}:"
+      alpha_code.to_s.match?(ALPHA_CODE_REGEXP) ? alpha_code.to_s : ":#{alpha_code}:"
+    end
+
+    def self.format_name(raw_name)
+      matched = raw_name.match(ALPHA_CODE_REGEXP)
+
+      matched ? matched['alpha_text'] : raw_name
     end
 
     private

data/lib/tanuki_emoji/db/gemojione.rb

@@ -28,7 +28,8 @@ module TanukiEmoji
           emoji = Character.new(emoji_name.to_s,
                                 codepoints: emoji_data[:moji],
                                 alpha_code: emoji_data[:shortname],
-                                description: emoji_data[:name])
+                                description: emoji_data[:name],
+                                category: emoji_data[:category])
 
           emoji_data[:unicode_alternates].each do |unicode_alternates|
             codepoints = unicode_hex_to_codepoint(unicode_alternates)
@@ -40,6 +41,10 @@ module TanukiEmoji
             emoji.add_alias(alpha_code)
           end
 
+          emoji_data[:aliases_ascii].each do |ascii_string|
+            emoji.add_ascii_alias(ascii_string)
+          end
+
           @index.add(emoji)
         end
       end

data/lib/tanuki_emoji/db/unicode_version.rb

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+
+require 'json'
+
+module TanukiEmoji
+  module Db
+    # Emoji Unicode Version database
+    class UnicodeVersion
+      DATA_FILE = 'vendor/emoji-unicode-version/emoji-unicode-version-map.json'
+
+      def self.data_file
+        File.expand_path(File.join(__dir__, '../../../', DATA_FILE))
+      end
+
+      attr_reader :data_file
+
+      def initialize(index:, data_file: self.class.data_file)
+        @data_file = data_file
+        @index = index
+      end
+
+      def load!
+        db = File.open(data_file, 'r:UTF-8') do |file|
+          JSON.parse(file.read, symbolize_names: true)
+        end
+
+        db.each do |emoji_name, unicode_version|
+          emoji = @index.find_by_alpha_code(emoji_name)
+
+          next unless emoji
+
+          emoji.unicode_version = unicode_version
+        end
+      end
+    end
+  end
+end

data/lib/tanuki_emoji/db.rb

@@ -3,5 +3,6 @@
 module TanukiEmoji
   module Db
     autoload :Gemojione, 'tanuki_emoji/db/gemojione'
+    autoload :UnicodeVersion, 'tanuki_emoji/db/unicode_version'
   end
 end

data/lib/tanuki_emoji/index.rb

@@ -8,11 +8,13 @@ module TanukiEmoji
     include Singleton
     include Enumerable
 
+    # @return [Array<TanukiEmoji::Character>] a collection of TanukiEmoji::Character
     attr_reader :all
 
     # Add a new Emoji to the index
     #
     # @param [TanukiEmoji::Character] emoji
+    # @return [TanukiEmoji::Character]
     def add(emoji)
       @name_index ||= {}
       @alpha_code_index ||= {}
@@ -36,7 +38,8 @@ module TanukiEmoji
         end
 
         emoji.aliases.each do |alpha_code|
-          @alpha_code_index[alpha_code] = emoji
+          @name_index[::TanukiEmoji::Character.format_name(alpha_code)] = emoji
+          @alpha_code_index[::TanukiEmoji::Character.format_alpha_code(alpha_code)] = emoji
         end
       end
 
@@ -68,11 +71,32 @@ module TanukiEmoji
     def reset!(reload: true)
       @all = []
 
-      load_data_files if reload
-
       remove_instance_variable :@name_index if defined? @name_index
       remove_instance_variable :@alpha_code_index if defined? @alpha_code_index
       remove_instance_variable :@codepoints_index if defined? @codepoints_index
+
+      load_data_files if reload
+    end
+
+    # Return a regular expression that can be used to search for indexed `:alpha_codes:`
+    #
+    # @return [Regexp] regular expression that matches indexed `:alpha_code:`
+    def alpha_code_pattern
+      /(?<=[^[:alnum:]:]|\n|^)
+       :(#{@name_index.keys.map { |name| Regexp.escape(name) }.join('|')}):
+       (?=[^[:alnum:]:]|$)/x
+    end
+
+    # Return a regular expression that can be used to search for emoji codepoints
+    #
+    # @param [Boolean] exclude_text_presentation exclude codepoints and sequences with text presentation selector
+    # @return [Regexp] regular expression that matches indexed emoji codepoints
+    def codepoints_pattern(exclude_text_presentation: false)
+      possible_codepoints = sorted_codepoints.map { |moji, _| Regexp.escape(moji) }.join('|')
+      variation_selector = ""
+      variation_selector = /(?!#{TanukiEmoji::Character::PLAIN_VARIATION_SELECTOR_STRING})/ if exclude_text_presentation
+
+      /(#{possible_codepoints})#{variation_selector}/
     end
 
     private
@@ -89,6 +113,13 @@ module TanukiEmoji
 
     def load_data_files
       Db::Gemojione.new(index: self).load!
+      Db::UnicodeVersion.new(index: self).load!
+    end
+
+    # Order the codepoints to match the most specific (longest) sequences first,
+    # so #gsub doesn't unintentionally split an emoji from its modifier(s).
+    def sorted_codepoints
+      @sorted_codepoints ||= @codepoints_index.dup.sort_by { |_, v| -v.hex.length }
     end
   end
 end

data/lib/tanuki_emoji/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module TanukiEmoji
-  VERSION = "0.2.2"
+  VERSION = "0.6.0"
 end

data/lib/tanuki_emoji.rb

@@ -38,8 +38,15 @@ module TanukiEmoji
   # @param [String] name
   # @param [String] codepoints
   # @param [String] alpha_code
-  def self.add(name, codepoints:, alpha_code:, description:)
-    emoji = Character.new(name, codepoints: codepoints, alpha_code: alpha_code, description: description)
+  # @param [String] description
+  # @param [String] category
+  # @return [TanukiEmoji::Character]
+  def self.add(name, codepoints:, alpha_code:, description:, category:)
+    emoji = Character.new(name,
+                          codepoints: codepoints,
+                          alpha_code: alpha_code,
+                          description: description,
+                          category: category)
 
     index.add(emoji)
   end

data/tanuki_emoji.gemspec

@@ -15,8 +15,9 @@ Gem::Specification.new do |spec|
   spec.required_ruby_version = Gem::Requirement.new(">= 2.7.0")
 
   spec.metadata['homepage_uri'] = spec.homepage
-  spec.metadata['source_code_uri'] = 'https://gitlab.com/gitlab-org/tanuki_emoji'
-  spec.metadata['changelog_uri'] = 'https://gitlab.com/gitlab-org/tanuki_emoji/-/blob/main/CHANGELOG.md'
+  spec.metadata['source_code_uri'] = spec.homepage
+  spec.metadata['changelog_uri'] = "#{spec.homepage}/-/blob/main/CHANGELOG.md"
+  spec.metadata['bug_tracker_uri'] = "#{spec.homepage}/-/issues"
 
   # Specify which files should be added to the gem when it is released.
   # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
@@ -27,4 +28,6 @@ Gem::Specification.new do |spec|
     git_files + asset_files
   end
   spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'gitlab-dangerfiles', '~> 2.8.0'
 end

data/vendor/emoji-unicode-version/README.md

@@ -0,0 +1,57 @@
+[![npm](https://img.shields.io/npm/v/emoji-unicode-version.svg?style=flat-square)](https://www.npmjs.com/package/emoji-unicode-version)
+
+# emoji-unicode-version
+
+Get the unicode version for a given emoji name.
+
+Useful for testing native unicode emoji support. Test a single emoji and assume any other emoji with that same version is supported.
+
+```
+npm install emoji-unicode-version
+```
+
+
+# Usage
+
+```js
+const emojiNameToUnicodeVersion = require('emoji-unicode-version');
+
+// 6.1
+console.log(emojiNameToUnicodeVersion('grinning'));
+// 9.0
+console.log(emojiNameToUnicodeVersion('rofl'));
+```
+
+### Get version from unicode
+
+```js
+const emojiNameToUnicodeVersion = require('emoji-unicode-version');
+const emojione = require('emojione');
+
+function unicodeToName(emojiUnicode) {
+	const emojiShortName = emojione.toShort(emojiUnicode);
+	const emojiName = emojiShortName.slice(1, emojiShortName.length - 1);
+	return emojiName;
+}
+
+// grinning, 6.1
+console.log(emojiNameToUnicodeVersion(unicodeToName('😀')));
+// rofl, 9.0
+console.log(emojiNameToUnicodeVersion(unicodeToName('🤣')));
+```
+
+
+# About
+
+Emoji name list is pulled from [EmojiOne](https://github.com/Ranks/emojione)
+
+We  grab the emoji unicode versions from [Emojipedia](http://emojipedia.org/unicode-6.1/).
+
+[ZWJ sequences](http://emojipedia.org/emoji-zwj-sequences/) use the unicode version for the highest individual emoji in the sequence.
+
+
+Also See
+
+ - http://unicode.org/emoji/charts-beta/full-emoji-list.html
+ - http://www.unicode.org/Public/emoji/5.0/emoji-data.txt
+ - http://unicode.org/Public/emoji/5.0/emoji-zwj-sequences.txt