tanuki_emoji 0.5.0 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fe0dc4ae27d764f4f8e197ab0736035eb6cb082f3f3c7e365a7242af4fcc895c
-  data.tar.gz: 63306c6bfebf28a9ec7f762132d12370094f8d6121f441e621adec62e76d6563
+  metadata.gz: 31696b93726ca04628ec4659e4f0a0f41dafa4223791e1a51ec3ad08760c66af
+  data.tar.gz: 9784c1d059e0a3cf8db903a97375636b5679e40ddb59dee450ceb721e0178a89
 SHA512:
-  metadata.gz: 8da28b3ee32bbadba7c28581c840f2cb80e16a7f978fb8d14117204642324da8341868fc76f56ae47e51f50f179113ae007cec5c33f8965eeb8cd7608ab2abca
-  data.tar.gz: 1d4a177f172eeb488bd0016abfa5710a7154132c9a95882e802d6ee796334b485db611dc69233ad5b18befe02c83603902914a5169aab919c9313bb7394b969a
+  metadata.gz: df6ef5d255eef71dca9c1a17b2f67d01116d55cdc2c24ed1c26b62b04d9b8ac40c04c25b432d5cf64dd29043965457669906bbe57f57e9120e09a728b1011c35
+  data.tar.gz: f2c23bfc342a090d801bd09d1e952cc9aa8cfdd9905b5fc6e3c7be96b75b16ccccd6b3e07cf5ccaf389775baaa34ecb801416d78beeb050441465a758454d4e5

data/.gitlab/changelog_config.yml

@@ -0,0 +1,8 @@
+---
+categories:
+  added: Added
+  changed: Changed
+  deprecated: Deprecated
+  removed: Removed
+  fixed: Fixed
+  security: Security

data/.gitlab-ci.yml

@@ -1,14 +1,23 @@
+---
+workflow:
+  rules:
+    # for default branch (pushes, merges, etc.)
+    - if: '$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH'
+    # for all merge requests
+    - if: '$CI_MERGE_REQUEST_IID'
+    # for all tags
+    - if: '$CI_COMMIT_TAG'
+
 .ruby: &ruby
   variables:
     LANG: "C.UTF-8"
   before_script:
     - ruby -v                                   # Print out ruby version for debugging
-    - gem install bundler  --no-document        # Bundler is not installed with the image
-    - bundle config set --local path 'vendor'
+    - bundle config set --local deployment true
     - bundle install -j $(nproc)                # Install dependencies into ./vendor/ruby
   parallel:
     matrix:
-      - RUBY_VERSION: ['2.7', '3.0']
+      - RUBY_VERSION: ['2.7', '3.0', '3.1', '3.2']
   image: "ruby:$RUBY_VERSION"
   cache:
     paths:
@@ -25,7 +34,9 @@ rspec:
   artifacts:
     reports:
       junit: rspec.xml
-      cobertura: coverage/coverage.xml
+      coverage_report:
+        path: coverage/coverage.xml
+        coverage_format: cobertura
 
 gem:
   extends: .ruby
@@ -44,6 +55,42 @@ rubocop:
 
 include:
   - template: Security/SAST.gitlab-ci.yml
-  - template: Dependency-Scanning.gitlab-ci.yml
+  - template: Security/Dependency-Scanning.gitlab-ci.yml
   - template: Security/License-Scanning.gitlab-ci.yml
+  - template: Security/Secret-Detection.gitlab-ci.yml
   - template: Code-Quality.gitlab-ci.yml
+  - project: 'gitlab-org/quality/pipeline-common'
+    file:
+      - '/ci/gem-release.yml'
+      - '/ci/danger-review.yml'
+
+secret_detection:
+  rules:
+    - if: $SECRET_DETECTION_DISABLED
+      when: never
+    # for default branch (pushes, merges, etc.)
+    - if: '$CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH'
+    # for all merge requests
+    - if: '$CI_MERGE_REQUEST_IID'
+    - if: $CI_MERGE_REQUEST_EVENT_TYPE == "merge_train" # specific
+      when: never
+  needs: []
+  dependencies: [] # Don't download artifacts
+
+update-changelog:
+  stage: deploy
+  image: ruby:2.7
+  rules:
+    - if: '$GITLAB_API_TOKEN == null'
+      when: never
+    - changes: ["CHANGELOG.md"]
+      when: never
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+      changes: ["lib/**/version.rb"]
+  variables:
+    GEMSPEC_FILE: "${CI_PROJECT_NAME}.gemspec"
+  script:
+    - |
+      version=$(ruby -e "print Gem::Specification.load('${GEMSPEC_FILE}').version")
+      [ -n "${version}" ] || (echo "VERSION could not be parsed in ${GEMSPEC_FILE}!" && exit 1)
+    - 'curl -X POST --header "PRIVATE-TOKEN: ${GITLAB_API_TOKEN}" "${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/repository/changelog?version=${version}&branch=${CI_MERGE_REQUEST_SOURCE_BRANCH_NAME}"'

data/.ruby-version

@@ -1 +1 @@
-2.7.4
+2.7.5

data/CHANGELOG.md

@@ -4,48 +4,64 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## 0.6.0 (2022-02-16)
 
-## [0.5.0] - 2021-09-16
 ### 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
+## 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
+## 0.3.0 - (2021-08-26)
+
+### Changed
+
 - 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
+## 0.2.2 - (2021-08-23)
+
+### Changed
+
 - Fixed autoload load_path
 
-## [0.2.1] - 2021-07-09
-### Modified
+## 0.2.1 - (2021-07-09)
+
+### Changed
+
 - Noto Emoji assets were not included due to bug in gemspec code. Now it is.
 
-## [0.2.0] - 2021-07-09
+## 0.2.0 - (2021-07-09)
+
 ### Added
+
 - Bundled Noto Emoji assets for each corresponding indexed Emoji
 - `Character` responds to `#image_name` pointing to Noto Emoji filenames
 - `TanukiEmoji` responds to `.images_path` pointing to Emoji assets folder
 
-## [0.1.0] - 2021-07-04
+## 0.1.0 - (2021-07-04)
+
 ### Added
-- Initial release with index and Character information support
 
-[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
+- Initial release with index and Character information support

data/Dangerfile

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+require 'gitlab-dangerfiles'
+
+Gitlab::Dangerfiles.for_project(self) do |dangerfiles|
+  dangerfiles.import_plugins
+
+  excluded_dangerfiles = []
+
+  # Skip changelog check when preparing a new release. This check fails because
+  # CHANGELOG.md gets modified by the update-changelog job.
+  excluded_dangerfiles << 'changelog' if plugins[Danger::Helper].modified_files.include?('lib/tanuki_emoji/version.rb')
+
+  dangerfiles.import_dangerfiles(except: excluded_dangerfiles)
+end

data/Gemfile.lock

@@ -1,19 +1,98 @@
 PATH
   remote: .
   specs:
-    tanuki_emoji (0.5.0)
+    tanuki_emoji (0.7.0)
 
 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 (8.4.5)
+      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 (1.10.0)
+      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 (2.11.0)
+      danger (>= 8.4.5)
+      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)
@@ -51,7 +134,9 @@ GEM
       simplecov (~> 0.8)
     simplecov-html (0.12.3)
     simplecov_json_formatter (0.1.3)
-    unicode-display_width (2.0.0)
+    terminal-table (3.0.2)
+      unicode-display_width (>= 1.1.1, < 3)
+    unicode-display_width (2.1.0)
 
 PLATFORMS
   ruby
@@ -59,6 +144,7 @@ PLATFORMS
   x86_64-linux
 
 DEPENDENCIES
+  gitlab-dangerfiles (~> 2.11.0)
   rake (~> 13.0)
   rspec (~> 3.0)
   rspec_junit_formatter (~> 0.4.0)

data/README.md

@@ -1,6 +1,6 @@
 # Tanuki Emoji
 
-This library helps you implement Emoji support in a ruby application by providing you access to native Emoji character 
+This library helps you implement Emoji support in a ruby application by providing you access to native Emoji character
 information.
 
 We currently provides a pre-indexed set of Emojis, compatible with [Gemojione](https://github.com/bonusly/gemojione)
@@ -9,6 +9,16 @@ index from 3.3.0. In the future we expect to cover the most recent version of Un
 This gem bundles Emoji assets from [Noto Emoji](https://github.com/googlefonts/noto-emoji), to be used as fallback when
 Emoji is not available or not fully supported on target system.
 
+## Development dependencies
+
+Install [cairo](https://cairographics.org/) on your local machine.
+
+```shell
+# For osx users
+
+$ brew install cairo
+```
+
 ## Installation
 
 Add this line to your application's Gemfile:
@@ -28,7 +38,7 @@ $ bundle install
 To access the index and list all known Emoji Characters:
 
 ```ruby
-TanukiEmoji.index.all 
+TanukiEmoji.index.all
 ```
 
 To search for an Emoji by it's codepoints (the unicode character):
@@ -70,17 +80,44 @@ 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:
+
+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 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 
-[rubygems.org](https://rubygems.org).
+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 the version number in `lib/tanuki_emoji/version.rb`.
+
+With that MR approved and merged, a [CI job](https://gitlab.com/gitlab-org/quality/pipeline-common/-/blob/master/ci/gem-release.yml) will
+create a new release, generate the changelog, 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 with a new feature, a feature change, or a fix, consider adding a changelog entry
+using a [Git trailer](https://docs.gitlab.com/ee/api/repositories.html#how-it-works), for example `Changelog: added`.
+
+You may use the [following values](.gitlab/changelog_config.yml):
+
+- `added` for new features.
+- `changed` for changes in existing functionality.
+- `deprecated` for soon-to-be removed features.
+- `removed` for now removed features.
+- `fixed` for any bug fixes.
+- `security` in case of vulnerabilities.
+
+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/lib/tanuki_emoji/character.rb

@@ -16,11 +16,12 @@ module TanukiEmoji
 
     # 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, :category
+    attr_reader :name, :codepoints, :codepoints_alternates, :alpha_code, :aliases, :ascii_aliases, :description, :category
 
     attr_accessor :unicode_version
 
@@ -35,6 +36,7 @@ module TanukiEmoji
       @codepoints_alternates = []
       @alpha_code = self.class.format_alpha_code(alpha_code)
       @aliases = []
+      @ascii_aliases = []
       @description = description
       @category = category
     end
@@ -53,6 +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
@@ -94,6 +103,7 @@ module TanukiEmoji
         codepoints_alternates == other.codepoints_alternates &&
         alpha_code == other.alpha_code &&
         aliases == other.aliases &&
+        ascii_aliases == other.ascii_aliases &&
         description == other.description
     end
 

data/lib/tanuki_emoji/db/emoji_data.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module TanukiEmoji
+  module Db
+    EmojiData = Struct.new(:codepoints, :property, :version, :range_size, :examples, :description)
+  end
+end

data/lib/tanuki_emoji/db/emoji_data_parser.rb

@@ -0,0 +1,187 @@
+# frozen_string_literal: true
+
+require 'strscan'
+require 'date'
+
+module TanukiEmoji
+  module Db
+    # Reads and extract content from emoji-data.txt and its metadata
+    class EmojiDataParser
+      DATA_FILE = 'vendor/unicode/emoji-data.txt'
+      PROPERTIES = {
+        'Emoji' => :emoji,
+        'Emoji_Presentation' => :emoji_presentation,
+        'Emoji_Modifier' => :emoji_modifier,
+        'Emoji_Modifier_Base' => :emoji_modifier_base,
+        'Emoji_Component' => :emoji_component,
+        'Extended_Pictographic' => :extended_pictographic
+      }.freeze
+
+      # Return the path to the default data file (emoji-data.txt)
+      #
+      # @return [Pathname] path to the default data file
+      def self.data_file
+        Pathname.new(File.expand_path(File.join(__dir__, '../../../', DATA_FILE)))
+      end
+
+      attr_reader :data_file
+
+      def initialize(data_file = self.class.data_file)
+        @data_file = data_file
+      end
+
+      # Return the parsed data from the data file
+      #
+      # @return [Array<EmojiData>] collection of EmojiData
+      def data
+        parsed = []
+        load do |line|
+          parse_data(line).tap do |result|
+            parsed << result unless result.nil?
+          end
+        end
+
+        parsed
+      end
+
+      def raw_data
+        lines = []
+        load do |line|
+          lines << line
+        end
+
+        lines
+      end
+
+      def metadata
+        parsed = []
+
+        load do |line|
+          parse_metadata(line).tap do |result|
+            parsed << result unless result.nil?
+          end
+        end
+
+        meta = {}
+
+        # Extract date
+        raw_datetime = parsed.detect { |data| data[:key] == "Date" }&.fetch(:value)
+        meta[:date] = DateTime.parse(raw_datetime)
+
+        # Extract version
+        meta[:version] = parsed.detect { |data| data[:key] == "Version" }&.fetch(:value)
+
+        # Extract total elements
+        meta[:total_elements] = parsed.select { |data| data[:key] == "Total elements" }.sum { |data| data[:value].to_i }
+
+        meta
+      end
+
+      private
+
+      # Parse a line extracting data and ignoring comments and metadata
+      #
+      # @param [String] line a line from the data file
+      # @return [EmojiData] emoji data parsed from the line
+      def parse_data(line)
+        @scanner = StringScanner.new(line)
+
+        data = {}
+
+        skip_line_breaks
+
+        # Ignore comment lines
+        return if comment_token? || empty_line?
+
+        data[:codepoints] = @scanner.scan(/[0-9A-F]+(?:\.\.[0-9A-F]+)?/)
+
+        skip_spaces
+
+        # match `; <property>`
+        @scanner.scan(/; (?<property>[a-zA-Z_]+)/)
+        data[:property] = convert_property(fetch_first_capture)
+
+        skip_spaces
+
+        # Version in which codepoint was introduced
+        @scanner.scan(/# E(?<version>[0-9]+\.[0-9]+)/)
+        data[:version] = fetch_first_capture
+
+        skip_spaces
+
+        # size of the range being described (1 when single codepoint)
+        @scanner.scan(/\[(?<range_size>[0-9]+)\]/)
+        data[:range_size] = fetch_first_capture&.to_i
+
+        skip_spaces
+
+        # example emojis for described codepoint or range
+        @scanner.scan(/\((?<examples>[^)]+)\)/)
+        data[:examples] = fetch_first_capture.to_s
+
+        skip_spaces
+
+        # description text
+        @scanner.scan(/(?<description>[^\n]+)/)
+        data[:description] = fetch_first_capture
+
+        EmojiData.new(*data.values)
+      end
+
+      # Parse a line extracting metadata from comments only
+      #
+      # @param [String] line a line from the data file
+      # @return [Hash] containing :date, :version and :total_elements
+      def parse_metadata(line)
+        @scanner = StringScanner.new(line)
+
+        data = {}
+
+        skip_line_breaks
+
+        # process only when it's a comment line
+        return unless comment_token?
+
+        @scanner.scan(/# (?<key>[a-zA-Z\s]+): (?<data>[^\n]+)/)
+        data[:key] = fetch_first_capture
+        data[:value] = fetch_second_capture
+
+        return unless data[:key] && data[:value]
+
+        data
+      end
+
+      def skip_line_breaks
+        @scanner.skip(/\n/)
+      end
+
+      def skip_spaces
+        @scanner.skip(/\s+/)
+      end
+
+      def comment_token?
+        @scanner.peek(1) == '#'
+      end
+
+      def empty_line?
+        @scanner.peek(1) == ''
+      end
+
+      def fetch_first_capture
+        @scanner.captures&.dig(0)
+      end
+
+      def fetch_second_capture
+        @scanner.captures&.dig(1)
+      end
+
+      def convert_property(property)
+        PROPERTIES[property] || property
+      end
+
+      def load(&block)
+        File.open(data_file).each(&block)
+      end
+    end
+  end
+end

data/lib/tanuki_emoji/db/gemojione.rb

@@ -41,6 +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.rb

@@ -4,5 +4,7 @@ module TanukiEmoji
   module Db
     autoload :Gemojione, 'tanuki_emoji/db/gemojione'
     autoload :UnicodeVersion, 'tanuki_emoji/db/unicode_version'
+    autoload :EmojiData, 'tanuki_emoji/db/emoji_data'
+    autoload :EmojiDataParser, 'tanuki_emoji/db/emoji_data_parser'
   end
 end