unicoder 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: f79eb48ad06b13b61fc4ceb7fc5e176ee4e9e984
+  data.tar.gz: 94a62eb108e01e1d7da774b58352ab0585235bc7
+SHA512:
+  metadata.gz: 01714742c72568ab92a9c3df0b700f3918e32482b7f658da8f099e2cfb54359e098e90fa1caa72a343cbdf2ede36081a9c01a6d65ee76cee841e65b87c9083ad
+  data.tar.gz: dd5b55100962d9408a503b338ebf25062c3dee7dc1ff9ceaccd97e30d57f97d131191ef96ce266e267cc729d70e6a0860702f22fbb1c9a6e4b512547ff1b5805

data/.gitignore

@@ -0,0 +1,3 @@
+Gemfile.lock
+/pkg
+/data

data/.travis.yml

@@ -0,0 +1,20 @@
+sudo: false
+language: ruby
+
+script: bundle exec ruby spec/unicoder_spec.rb
+
+rvm:
+- 2.3.0
+- 2.2
+- 2.1
+- 2.0
+- ruby-head
+- rbx-2
+- jruby-head
+- jruby-9000
+
+cache:
+- bundler
+
+# matrix:
+#   fast_finish: true

data/CHANGELOG.md

@@ -0,0 +1,5 @@
+## CHANGELOG
+
+### 0.1.0
+
+* WIP

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at opensource@janlelis.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,5 @@
+source 'https://rubygems.org'
+
+gemspec
+
+gem 'minitest'

data/MIT-LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2016 Jan Lelis, mail@janlelis.de
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,15 @@
+# unicoder [![[version]](https://badge.fury.io/rb/unicoder.svg)](http://badge.fury.io/rb/unicoder)
+
+WIP
+
+
+## Usage
+
+```
+$ unicoder build index_name
+```
+
+
+## MIT License
+
+Copyright (C) 2016 Jan Lelis <http://janlelis.com>. Released under the MIT license.

data/Rakefile

@@ -0,0 +1,35 @@
+# # #
+# Get gemspec info
+
+gemspec_file = Dir['*.gemspec'].first
+gemspec = eval File.read(gemspec_file), binding, gemspec_file
+info = "#{gemspec.name} | #{gemspec.version} | " \
+       "#{gemspec.runtime_dependencies.size} dependencies | " \
+       "#{gemspec.files.size} files"
+
+
+# # #
+# Gem build and install task
+
+desc info
+task :gem do
+  puts info + "\n\n"
+  print "  "; sh "gem build #{gemspec_file}"
+  FileUtils.mkdir_p 'pkg'
+  FileUtils.mv "#{gemspec.name}-#{gemspec.version}.gem", 'pkg'
+  puts; sh %{gem install --no-document pkg/#{gemspec.name}-#{gemspec.version}.gem}
+end
+
+
+# # #
+# Start an IRB session with the gem loaded
+
+desc "#{gemspec.name} | IRB"
+task :irb do
+  sh "irb -I ./lib -r #{gemspec.name.gsub '-','/'}"
+end
+
+# # #
+# Require self
+
+require_relative 'lib/unicoder'

data/bin/unicoder

@@ -0,0 +1,40 @@
+#!/usr/bin/env ruby
+
+require_relative "../lib/unicoder"
+require "rationalist"
+
+args = Rationalist.parse
+command = args[:_][0]
+identifier = args[:_][1]
+KNOWN_OPTIONS = [:version, :help, :verbose, :format, :gzip]
+options = args.select { |option,| KNOWN_OPTIONS.include? option }
+
+if options.has_key?(:version)
+  puts "unicoder #{Unicoder::VERSION}"
+elsif options.has_key?(:help)
+  puts <<USAGE_INSTRUCTIONS
+
+  USAGE
+
+    unicoder fetch <data_identifier>
+    unicoder build <builder_name> <output_file>
+
+  DATA FILE IDENTIFIERS
+
+    …
+
+  BUILDERS
+
+    …
+
+USAGE_INSTRUCTIONS
+else
+  case command
+  when "fetch"
+    Unicoder::Downloader.fetch(identifier, **options)
+  when "build"
+    Unicoder::Builder.build(identifier, **options)
+  else
+    raise ArgumentError, "Unknown unicoder command!"
+  end
+end

data/lib/unicoder.rb

@@ -0,0 +1,8 @@
+require_relative "unicoder/constants"
+require_relative "unicoder/downloader"
+require_relative "unicoder/builder"
+require_relative "unicoder/multi_dimensional_array_builder"
+
+if defined?(Rake)
+  Rake.add_rakelib(File.expand_path('../unicoder', __FILE__))
+end

data/lib/unicoder/builder.rb

@@ -0,0 +1,76 @@
+require "json"
+
+module Unicoder
+  # A builder defines a parse function which translates one (ore more) unicode data
+  # files into an index hash
+  module Builder
+    attr_reader :index
+
+    def initialize(unicode_version = nil)
+      @unicode_version = unicode_version
+      initialize_index
+    end
+
+    def initialize_index
+      @index = {}
+    end
+
+    def assign_codepoint(codepoint, value, index = @index)
+      index[codepoint] = value
+    end
+
+    def parse!
+      raise ArgumentError, "abstract"
+    end
+
+    def parse_file(identifier, parse_mode, **parse_options)
+      filename = UNICODE_FILES[identifier.to_sym] || filename
+      raise ArgumentError, "No valid file identifier or filename given" if !filename
+      filename.sub! 'VERSION', @unicode_version
+      Downloader.fetch(identifier) unless File.exists?(filename)
+      file = File.read(LOCAL_DATA_DIRECTORY + filename)
+
+      if parse_mode == :line
+        file.each_line{ |line|
+          yield Hash[ $~.names.zip( $~.captures ) ] if line =~ parse_options[:regex]
+        }
+      end
+    end
+
+    def export(format: :marshal, **options)
+      p index if options[:verbose]
+
+      case format.to_sym
+      when :marshal
+        index_file = Marshal.dump(index)
+      when :json
+        index_file = JSON.dump(index)
+      end
+
+      # if false# || options[:gzip]
+      if options[:gzip]
+        Gem.gzip(index_file)
+      else
+        index_file
+      end
+    end
+    
+    def self.build(identifier, **options)
+      format = options[:format] || :marshal
+      require_relative "builders/#{identifier}"
+      # require "unicoder/builders/#{identifier}"
+      builder_class = self.const_get(identifier.to_s.gsub(/(?:^|_)([a-z])/){ $1.upcase })
+      builder = builder_class.new(options[:unicode_version] || CURRENT_UNICODE_VERSION)
+      puts "Building index for #{identifier}…"
+      builder.parse!
+      index_file = builder.export(options)
+
+      destination ||= options[:destination] || identifier.to_s
+      destination += ".#{format}"
+      destination += ".gz" if options[:gzip]
+      bytes = File.write destination, index_file
+
+      puts "Index created at: #{destination} (#{bytes} bytes written)"
+    end
+  end
+end

data/lib/unicoder/builders/blocks.rb

@@ -0,0 +1,17 @@
+module Unicoder
+  module Builder
+    class Blocks
+      include Builder
+
+      def initialize_index
+        @index = []
+      end
+
+      def parse!
+        parse_file :blocks, :line, regex: /^(?<from>\S+?)\.\.(?<to>\S+);\s(?<name>.+)$/ do |line|
+          @index << [line["from"].to_i(16), line["to"].to_i(16), line["name"]]
+        end
+      end
+    end
+  end
+end

data/lib/unicoder/builders/categories.rb

@@ -0,0 +1,43 @@
+module Unicoder
+  module Builder
+    # Assigns categories to every codepoint using a multi dimensional Array index structure
+    class Categories
+      include Builder
+      include MultiDimensionalArrayBuilder
+
+      def initialize_index
+        @index = {
+          CATEGORIES: [],
+          CATEGORY_NAMES: {},
+        }
+        @range_start = nil
+      end
+
+      def parse!
+        parse_file :unicode_data, :line, regex: /^(?<codepoint>.+?);(?<range><(?!control).+>)?.*?;(?<category>.+?);.*$/ do |line|
+          if line["range"]
+            if line["range"] =~ /First/
+              @range_start = line["codepoint"].to_i(16)
+            elsif line["range"] =~ /Last/ && @range_start
+              (@range_start..line["codepoint"].to_i(16)).each{ |codepoint|
+                assign_codepoint(codepoint, line["category"], @index[:CATEGORIES])
+              }
+            else
+              raise ArgumentError, "inconsistent range found in data, don't know what to do"
+            end
+          else
+            assign_codepoint(line["codepoint"].to_i(16), line["category"], @index[:CATEGORIES])
+          end
+        end
+
+        4.times{ compress! @index[:CATEGORIES] }
+
+        parse_file :property_value_aliases, :line, regex: /^gc ; (?<short>\S{2}?) *; (?<long>\S+).*$/ do |line|
+          @index[:CATEGORY_NAMES][line["short"]] = line["long"]
+        end
+
+        @index
+      end
+    end
+  end
+end

data/lib/unicoder/builders/confusable.rb

@@ -0,0 +1,21 @@
+module Unicoder
+  module Builder
+    class Confusable
+      include Builder
+
+      def parse!
+        parse_file :confusables, :line, regex: /^(?<from>\S+)\s+;\s+(?<to>.+)\s+;.*$/ do |line|
+          source = line["from"].to_i(16)
+          if line["to"].include?(" ")
+            replace_with = line["to"].split(" ").map{ |codepoint|
+              codepoint.to_i(16)
+            }
+          else
+            replace_with = line["to"].to_i(16)
+          end
+          @index[source] = replace_with
+        end
+      end
+    end
+  end
+end

data/lib/unicoder/builders/display_width.rb

@@ -0,0 +1,71 @@
+module Unicoder
+  module Builder
+    class DisplayWidth
+      include Builder
+      include MultiDimensionalArrayBuilder
+
+      IGNORE_CATEGORIES     = %w[Cs Co Cn].freeze
+      ZERO_WIDTH_CATEGORIES = %w[Mn Me Cf].freeze
+      ZERO_WIDTH_CODEPOINTS = [*0x1160..0x11FF].freeze
+      SPECIAL_WIDTHS = {
+        0x0    =>  0, # \0 NULL
+        0x5    =>  0, #    ENQUIRY
+        0x7    =>  0, # \a BELL
+        0x8    => -1, # \b BACKSPACE
+        0xA    =>  0, # \n LINE FEED
+        0xB    =>  0, # \v LINE TABULATION
+        0xC    =>  0, # \f FORM FEED
+        0xD    =>  0, # \r CARRIAGE RETURN
+        0xE    =>  0, #    SHIFT OUT
+        0xF    =>  0, #    SHIFT IN
+        0x00AD =>  1, #    SOFT HYPHEN
+        0x2E3A =>  2, #    TWO-EM DASH
+        0x2E3B =>  3, #    THREE-EM DASH
+      }.freeze
+
+      def initialize_index
+        @index = []
+      end
+
+      def parse!
+        parse_file :east_asian_width, :line, regex: /^(?<codepoints>\S+?);(?<width>\S+)\s+#\s(?<category>\S+).*$/ do |line|
+          next if IGNORE_CATEGORIES.include?(line["category"])
+
+          if line["codepoints"]['..']
+            codepoints = Range.new(*line["codepoints"].split('..').map{ |codepoint|
+              codepoint.to_i(16)
+            })
+          else
+            codepoints = [line["codepoints"].to_i(16)]
+          end
+
+          codepoints.each{ |codepoint|
+            assign_codepoint codepoint, determine_width(codepoint, line["category"], line["width"])
+          }
+        end
+
+        SPECIAL_WIDTHS.each{ |codepoint, value|
+          assign_codepoint codepoint, value
+        }
+
+        4.times{ compress! }
+
+        p @index
+      end
+
+      def determine_width(codepoint, category, east_asian_width)
+        if  ( ZERO_WIDTH_CATEGORIES.include?(category) &&
+              [codepoint].pack('U') !~ /\p{Cf}(?<=\p{Arabic})/ ) ||
+            ZERO_WIDTH_CODEPOINTS.include?(codepoint)
+          0
+        elsif east_asian_width == "F" || east_asian_width == "W"
+          2
+        elsif east_asian_width == "A"
+          :A
+        else
+          nil
+        end
+      end
+    end
+  end
+end

data/lib/unicoder/builders/scripts.rb

@@ -0,0 +1,59 @@
+module Unicoder
+  module Builder
+    class Scripts
+      include Builder
+      include MultiDimensionalArrayBuilder
+
+      def initialize_index
+        @index = {
+          SCRIPTS: [],
+          SCRIPT_EXTENSIONS: {},
+          SCRIPT_ALIASES: {},
+          SCRIPT_NAMES: [],
+        }
+        @reverse_script_names = {}
+        @reverse_script_extension_names = {}
+      end
+
+      def lookup_extension_names(extension_scripts_string)
+        extension_scripts_string.split(" ").map{ |extension_script|
+          @reverse_script_extension_names[extension_script]
+        }
+      end
+
+      def parse!
+        parse_file :property_value_aliases, :line, regex: /^sc ; (?<short>\S+?)\s*; (?<long>\S+?)(?:\s*; (?<short2>\S+))?$/ do |line|
+          @index[:SCRIPT_NAMES] << line["long"]
+          script_number = @reverse_script_names.size
+          @reverse_script_names[line["long"]] = script_number
+
+          @index[:SCRIPT_ALIASES][line["short" ]] = script_number
+          @index[:SCRIPT_ALIASES][line["short2"]] = script_number if line["short2"]
+          @reverse_script_extension_names[line["short"]] = script_number
+        end
+
+        parse_file :scripts, :line, regex: /^(?<from>\S+?)(\.\.(?<to>\S+))?\s+; (?<script>\S+) #.*$/ do |line|
+          if line["to"]
+            (line["from"].to_i(16)..line["to"].to_i(16)).each{ |codepoint|
+              assign_codepoint codepoint, @reverse_script_names[line["script"]], @index[:SCRIPTS]
+            }
+          else
+            assign_codepoint line["from"].to_i(16), @reverse_script_names[line["script"]], @index[:SCRIPTS]
+          end
+        end
+
+        4.times{ compress! @index[:SCRIPTS] }
+
+        parse_file :script_extensions, :line, regex: /^(?<from>\S+?)(\.\.(?<to>\S+))?\s+; (?<scripts>.+?) #.*$/ do |line|
+          if line["to"]
+            (line["from"].to_i(16)..line["to"].to_i(16)).each{ |codepoint|
+              @index[:SCRIPT_EXTENSIONS][codepoint] = lookup_extension_names(line["scripts"])
+            }
+          else
+            @index[:SCRIPT_EXTENSIONS][line["from"].to_i(16)] = lookup_extension_names(line["scripts"])
+          end
+        end
+      end
+    end
+  end
+end

data/lib/unicoder/constants.rb

@@ -0,0 +1,29 @@
+module Unicoder
+  VERSION = "0.1.0".freeze
+
+  CURRENT_UNICODE_VERSION = "8.0.0".freeze
+
+  UNICODE_VERSIONS = %w[
+     6.3.0
+     7.0.0
+     8.0.0
+     9.0.0
+  ].freeze
+
+  UNICODE_DATA_ENDPOINT = "ftp://ftp.unicode.org/Public".freeze
+
+  LOCAL_DATA_DIRECTORY = File.expand_path(File.dirname(__FILE__) + "/../../data/unicode").freeze
+
+  UNICODE_FILES = {
+    east_asian_width:         "/VERSION/ucd/EastAsianWidth.txt",
+    unicode_data:             "/VERSION/ucd/UnicodeData.txt",
+    name_aliases:             "/VERSION/ucd/NameAliases.txt",
+    confusables:              "/security/VERSION/confusables.txt",
+    blocks:                   "/VERSION/ucd/Blocks.txt",
+    scripts:                  "/VERSION/ucd/Scripts.txt",
+    script_extensions:        "/VERSION/ucd/ScriptExtensions.txt",
+    property_value_aliases:   "/VERSION/ucd/PropertyValueAliases.txt",
+    general_categories:       "/VERSION/ucd/extracted/DerivedGeneralCategory.txt",
+  }
+end
+

data/lib/unicoder/downloader.rb

@@ -0,0 +1,28 @@
+require "open-uri"
+require "fileutils"
+
+module Unicoder
+  module Downloader
+    def self.fetch(identifier,
+        unicode_version: CURRENT_UNICODE_VERSION,
+        destination_directory: LOCAL_DATA_DIRECTORY,
+        destination: nil,
+        filename: nil
+      )
+      filename = UNICODE_FILES[identifier.to_sym] || filename
+      raise ArgumentError, "No valid file identifier or filename given" if !filename
+      filename.sub! 'VERSION', unicode_version
+      source = UNICODE_DATA_ENDPOINT + filename
+      destination ||= destination_directory + filename
+
+      open(source){ |f|
+        FileUtils.mkdir_p(File.dirname(destination))
+        File.write(destination, f.read)
+      }
+
+      puts "GET #{source} => #{destination}"
+    rescue => e
+      $stderr.puts "#{e.class}: #{e.message}"
+    end
+  end
+end

data/lib/unicoder/multi_dimensional_array_builder.rb

@@ -0,0 +1,64 @@
+require "json"
+
+module Unicoder
+  # Include after Builder
+  module MultiDimensionalArrayBuilder
+    def initialize_index
+      @index = []
+    end
+
+    def assign_codepoint(codepoint, value, index = @index)
+      plane         = codepoint    / 0x10000
+      plane_offset  = codepoint    % 0x10000
+      row           = plane_offset / 0x1000
+      row_offset    = plane_offset % 0x1000
+      byte          = row_offset   / 0x100
+      byte_offset   = row_offset   % 0x100
+      nibble        = byte_offset  / 0x10
+      nibble_offset = byte_offset  % 0x10
+
+      index[plane] ||= []
+      index[plane][row] ||= []
+      index[plane][row][byte] ||= []
+      index[plane][row][byte][nibble] ||= []
+      index[plane][row][byte][nibble][nibble_offset] = value
+    end
+
+    def compress!(index = @index)
+      index.map!{ |plane|
+        if !plane.is_a?(Array)
+          plane
+        elsif plane.flatten.uniq.size == 1
+          plane[0]
+        else
+          plane.map!{ |row|
+            if !row.is_a?(Array)
+              row
+            elsif row.flatten.uniq.size == 1
+              row[0]
+            else
+              row.map!{ |byte|
+                if !byte.is_a?(Array)
+                  byte
+                elsif byte.uniq.size == 1
+                  byte[0]
+                else
+                  byte.map! { |nibble|
+                    if !nibble.is_a?(Array)
+                      nibble
+                    elsif nibble.uniq.size == 1
+                      nibble[0]
+                    else
+                      nibble
+                    end
+                  }
+                end
+              }
+            end
+          }
+        end
+      }
+    end
+  
+  end
+end

data/lib/unicoder/tasks.rake

@@ -0,0 +1,11 @@
+namespace :unicoder do
+  desc "(fetch)"
+  task :fetch, [:identifier] do |t, args|
+    Unicoder::Downloader.fetch(args.identifier)
+  end
+
+  desc "(index)"
+  task :index, [:identifier] do |t, args|
+    Unicoder::Builder.build(args.identifier)
+  end
+end

data/spec/unicoder_spec.rb

@@ -0,0 +1,9 @@
+require_relative "../lib/unicoder"
+require "minitest/autorun"
+
+describe Unicoder do
+  it "works" do
+    assert_equal true, false
+  end
+end
+

data/unicoder.gemspec

@@ -0,0 +1,22 @@
+# -*- encoding: utf-8 -*-
+
+require File.dirname(__FILE__) + "/lib/unicoder/constants"
+
+Gem::Specification.new do |gem|
+  gem.name          = "unicoder"
+  gem.version       = Unicoder::VERSION
+  gem.summary       = "Create specialized indexes for Unicode data lookup"
+  gem.description   = "Generate specialized indexes for Unicode data lookup"
+  gem.authors       = ["Jan Lelis"]
+  gem.email         = ["mail@janlelis.de"]
+  gem.homepage      = "https://github.com/janlelis/unicoder"
+  gem.license       = "MIT"
+
+  gem.files         = Dir["{**/}{.*,*}"].select{ |path| File.file?(path) && path !~ /^pkg/ }
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.required_ruby_version = "~> 2.0"
+  gem.add_dependency "rationalist", "~> 2.0"
+end

metadata

@@ -0,0 +1,93 @@
+--- !ruby/object:Gem::Specification
+name: unicoder
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jan Lelis
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-04-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rationalist
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+description: Generate specialized indexes for Unicode data lookup
+email:
+- mail@janlelis.de
+executables:
+- unicoder
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- Gemfile
+- MIT-LICENSE.txt
+- README.md
+- Rakefile
+- bin/unicoder
+- data/.keep
+- data/unicode/8.0.0/ucd/Blocks.txt
+- data/unicode/8.0.0/ucd/EastAsianWidth.txt
+- data/unicode/8.0.0/ucd/NameAliases.txt
+- data/unicode/8.0.0/ucd/PropertyValueAliases.txt
+- data/unicode/8.0.0/ucd/ScriptExtensions.txt
+- data/unicode/8.0.0/ucd/Scripts.txt
+- data/unicode/8.0.0/ucd/UnicodeData.txt
+- data/unicode/8.0.0/ucd/extracted/DerivedGeneralCategory.txt
+- data/unicode/security/8.0.0/confusables.txt
+- lib/unicoder.rb
+- lib/unicoder/builder.rb
+- lib/unicoder/builders/blocks.rb
+- lib/unicoder/builders/categories.rb
+- lib/unicoder/builders/confusable.rb
+- lib/unicoder/builders/display_width.rb
+- lib/unicoder/builders/scripts.rb
+- lib/unicoder/constants.rb
+- lib/unicoder/downloader.rb
+- lib/unicoder/multi_dimensional_array_builder.rb
+- lib/unicoder/tasks.rake
+- spec/unicoder_spec.rb
+- unicoder.gemspec
+homepage: https://github.com/janlelis/unicoder
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: '2.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.3
+signing_key: 
+specification_version: 4
+summary: Create specialized indexes for Unicode data lookup
+test_files:
+- spec/unicoder_spec.rb
+has_rdoc: