unicodedata_rb 0.1.0

data/lib/unicodedata_rb/codepoint.rb

@@ -0,0 +1,24 @@
+# Format of UnicodeData.txt: https://www.unicode.org/L2/L1999/UnicodeData.html
+
+module UnicodedataRb
+  CODEPOINT_FIELDS = [
+    :codepoint, :name, :category, :combining_class, :bidi_class,
+    :decomposition, :digit_value, :non_decimal_digit_value,
+    :numeric_value, :bidi_mirrored, :unicode1_name, :iso_comment,
+    :simple_uppercase_map, :simple_lowercase_map, :simple_titlecase_map,
+  ]
+
+  NUMERIC_FIELDS = [:digit_value, :non_decimal_digit_value, :numeric_value]
+
+  class Codepoint < Struct.new(*UnicodedataRb::CODEPOINT_FIELDS)
+    def initialize(*args)
+      super
+      self.codepoint = self.codepoint.to_i(16)
+      NUMERIC_FIELDS.each { |f| send("#{f}=", send(f).to_r) }
+    end
+
+    def self.from_line(line)
+      new *(line.chomp.split ';')
+    end
+  end
+end

data/lib/unicodedata_rb/constants.rb

@@ -0,0 +1,6 @@
+module UnicodedataRb
+  class Constants
+    UNICODEDATA_TXT_PATH = File.dirname(__FILE__) + "/UnicodeData.txt"
+    UNICODEDATA_INDEX_PATH = File.dirname(__FILE__) + "/UnicodeData.index"
+  end
+end

data/lib/unicodedata_rb/generate_index.rb

@@ -0,0 +1,65 @@
+# Download data and build indices
+# Inspired by https://github.com/runpaint/unicode-data
+require "logger"
+require "net/http"
+require_relative "codepoint"
+require_relative "constants"
+
+
+module UnicodedataRb
+  class GenerateIndex
+    def self.call(...)
+      new(...).call
+    end
+
+    attr_reader :logger
+    def initialize(logger: Logger.new(STDOUT))
+      @logger = logger
+    end
+    private_class_method :new
+
+    def call
+      download_file("#{unicodedata_url_prefix}UnicodeData.txt", UnicodedataRb::Constants::UNICODEDATA_TXT_PATH)
+
+      # Format of UnicodeData.txt: https://www.unicode.org/L2/L1999/UnicodeData.html
+      File.open(UnicodedataRb::Constants::UNICODEDATA_TXT_PATH) do |f|
+        codepoint_index = {}
+        name_index = {}
+
+        f.each_line do |line|
+          start_line_pos = f.pos - line.size
+          codepoint = UnicodedataRb::Codepoint.from_line(line)
+          codepoint_index[codepoint.codepoint] = start_line_pos
+          name_index[codepoint.name] = start_line_pos
+        end
+
+        index = {
+          codepoint: codepoint_index,
+          name: name_index
+        }
+        File.open(UnicodedataRb::Constants::UNICODEDATA_INDEX_PATH, 'wb') { |f| Marshal.dump(index, f) }
+      end
+    end
+
+    def download_file(url, save_path)
+      logger.info("Downloading #{url}")
+      uri = URI(url)
+
+      Net::HTTP.start(uri.host, :use_ssl => true) do |http|
+        request = Net::HTTP::Get.new uri
+
+        http.request request do |response|
+          open save_path, "w:UTF-8" do |io|
+            response.read_body do |chunk|
+              io.write chunk
+            end
+          end
+        end
+      end
+    end
+
+    def unicodedata_url_prefix
+      @unicodedata_url_prefix ||= "https://unicode.org/Public/#{RbConfig::CONFIG["UNICODE_VERSION"]}/ucd/"
+    end
+  end
+end

data/lib/unicodedata_rb/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module UnicodedataRb
+  VERSION = "0.1.0"
+end

data/lib/unicodedata_rb.rb

@@ -0,0 +1,47 @@
+require_relative "unicodedata_rb/codepoint"
+require_relative "unicodedata_rb/generate_index"
+require_relative "unicodedata_rb/constants"
+require_relative "unicodedata_rb/version"
+
+module UnicodedataRb
+  def self.codepoint(num)
+    UnicodedataRb::Codepoint.from_line _unicodedata_txt_line_from(codepoint: num)
+  end
+
+  def self.codepoint_from_char(c)
+    UnicodedataRb::Codepoint.from_line _unicodedata_txt_line_from(codepoint: c.ord)
+  end
+
+  def self.codepoint_from_name(name)
+    UnicodedataRb::Codepoint.from_line _unicodedata_txt_line_from(name:)
+  end
+
+  def self._unicodedata_txt_line_from(codepoint: nil, name: nil)
+    raise ArgumentError if (codepoint.nil? && name.nil?) || (!codepoint.nil? && !name.nil?)
+    _unicodedata_txt_file.rewind
+    offset =
+      if !codepoint.nil?
+        _unicodedata_index[:codepoint][codepoint]
+      else
+        _unicodedata_index[:name][name]
+      end
+
+    raise ArgumentError if offset.nil?
+
+    _unicodedata_txt_file.seek offset
+    _unicodedata_txt_file.readline.chomp
+  end
+
+  def self._unicodedata_txt_file
+    @@_unicodedata_txt_file ||= File.open(UnicodedataRb::Constants::UNICODEDATA_TXT_PATH)
+  end
+
+  def self._unicodedata_index
+    @@_unicodedata_index ||= Marshal.load(File.binread(UnicodedataRb::Constants::UNICODEDATA_INDEX_PATH))
+  end
+
+  def self.generate_index
+    UnicodedataRb::GenerateIndex.call
+  end
+end
+

data/unicodedata_rb.gemspec

@@ -0,0 +1,33 @@
+# frozen_string_literal: true
+
+require_relative "lib/unicodedata_rb/version"
+
+Gem::Specification.new do |spec|
+  spec.name = "unicodedata_rb"
+  spec.version = UnicodedataRb::VERSION
+  spec.authors = ["bubiche"]
+  spec.email = ["bubiche95@gmail.com"]
+
+  spec.summary = "Ruby wrapper for unicode data."
+  spec.homepage = "https://github.com/bubiche/unicodedata_rb"
+  spec.license = "MIT"
+  spec.required_ruby_version = ">= 3.2.0"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = spec.homepage
+  spec.metadata["changelog_uri"] = "https://github.com/bubiche/unicodedata_rb/CHANGELOG.md"
+
+  # 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.
+  spec.files = Dir.chdir(__dir__) do
+    `git ls-files -z`.split("\x0").reject do |f|
+      (File.expand_path(f) == __FILE__) || f.start_with?(*%w[bin/ test/ spec/ features/ .git .circleci appveyor])
+    end
+  end
+  spec.bindir = "exe"
+  spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "rake", "~> 13.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: unicodedata_rb
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- bubiche
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2024-06-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '13.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description:
+email:
+- bubiche95@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".rspec"
+- CHANGELOG.md
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/unicodedata_rb.rb
+- lib/unicodedata_rb/UnicodeData.index
+- lib/unicodedata_rb/UnicodeData.txt
+- lib/unicodedata_rb/codepoint.rb
+- lib/unicodedata_rb/constants.rb
+- lib/unicodedata_rb/generate_index.rb
+- lib/unicodedata_rb/version.rb
+- unicodedata_rb.gemspec
+homepage: https://github.com/bubiche/unicodedata_rb
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/bubiche/unicodedata_rb
+  source_code_uri: https://github.com/bubiche/unicodedata_rb
+  changelog_uri: https://github.com/bubiche/unicodedata_rb/CHANGELOG.md
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 3.2.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.4.10
+signing_key:
+specification_version: 4
+summary: Ruby wrapper for unicode data.
+test_files: []