unaccent 0.1.0

data/lib/unaccent/string.rb

@@ -0,0 +1,23 @@
+require 'unaccent'
+
+module Unaccent
+  module String
+    def unaccent
+      Unaccent.unaccent(self)
+    end
+
+    def unaccent_via_gsub
+      Unaccent.via_gsub(self)
+    end
+
+    def unaccent_via_each_char
+      Unaccent.via_each_char(self)
+    end
+
+    def unaccent_via_split_map
+      Unaccent.via_split_map(self)
+    end
+  end
+end
+
+String.include Unaccent::String

data/lib/unaccent/version.rb

@@ -0,0 +1,3 @@
+module Unaccent
+  VERSION = '0.1.0'.freeze
+end

data/lib/unaccent.rb

@@ -0,0 +1,78 @@
+require 'unaccent/accentmap'
+require 'unaccent/version'
+
+module Unaccent
+  class << self
+    # Replace a string's accented characters with unaccented characters.
+    #
+    # @example
+    #   s = 'Å Ç ß'
+    #   Unaccent.unaccent(s) = > 'AA C ss'
+    #
+    # @return [String] a string that has no accents
+
+    def unaccent(str)
+      via_gsub(str)
+    end
+
+    # Replace a string's accented characters with unaccented characters,
+    # by using string `#gsub` to replace non-ascii characters.
+    #
+    # @example
+    #   str = 'Å Ç ß'
+    #   Unaccent.via_gsub(str) = > 'AA C ss'
+    #
+    # @return [String] a string that has no accents
+
+    def via_gsub(str)
+      return str if str.ascii_only?
+
+      str.gsub(/[^[:ascii:]]/) { |c| ACCENTMAP.fetch(c, c) }
+    end
+
+    # Replace a string's accented characters with unaccented characters,
+    # by using string `#scan` to iterate on characters.
+    #
+    # @example
+    #   str = 'Å Ç ß'
+    #   Unaccent.via_scan(str) = > 'AA C ss'
+    #
+    # @return [String] a string that has no accents
+
+    def via_scan(str)
+      return str if str.ascii_only?
+
+      res = ''; str.scan(/./) { |c| res << ACCENTMAP.fetch(c, c) }; res
+    end
+
+    # Replace a string's accented characters with unaccented characters,
+    # by using string `#each_char` to iterate on characters.
+    #
+    # @example
+    #   str = 'Å Ç ß'
+    #   Unaccent.via_each_char(str) = > 'AA C ss'
+    #
+    # @return [String] a string that has no accents
+
+    def via_each_char(str)
+      return str if str.ascii_only?
+
+      res = ''; str.each_char { |c| res << ACCENTMAP.fetch(c, c) }; res
+    end
+
+    # Replace a string's accented characters with unaccented characters,
+    # by using string `#split` and `#map` to iterate on characters.
+    #
+    # @example
+    #   str = 'Å Ç ß'
+    #   Unaccent.via_split_map(str) = > 'AA C ss'
+    #
+    # @return [String] a string that has no accents
+
+    def via_split_map(str)
+      return str if str.ascii_only?
+
+      str.split(//u).map { |c| ACCENTMAP.fetch(c, c) }.join
+    end
+  end
+end

data/unaccent.gemspec

@@ -0,0 +1,24 @@
+require_relative 'lib/unaccent/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'unaccent'
+  spec.version       = Unaccent::VERSION
+  spec.authors       = ['Jonian Guveli']
+  spec.email         = ['jonian@hardpixel.eu']
+
+  spec.summary       = 'Replace accented characters with unaccented characters'
+  spec.description   = 'Replace accented characters with unaccented characters.'
+  spec.homepage      = 'https://github.com/hardpixel/unaccent'
+  spec.license       = 'MIT'
+
+  # 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(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'minitest', '~> 5.0'
+end

metadata

@@ -0,0 +1,86 @@
+--- !ruby/object:Gem::Specification
+name: unaccent
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jonian Guveli
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2022-08-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.0'
+description: Replace accented characters with unaccented characters.
+email:
+- jonian@hardpixel.eu
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".github/workflows/build.yml"
+- ".gitignore"
+- ".ruby-version"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/benchmark
+- bin/console
+- bin/setup
+- lib/unaccent.rb
+- lib/unaccent/accentmap.rb
+- lib/unaccent/string.rb
+- lib/unaccent/version.rb
+- unaccent.gemspec
+homepage: https://github.com/hardpixel/unaccent
+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: []
+rubygems_version: 3.3.14
+signing_key:
+specification_version: 4
+summary: Replace accented characters with unaccented characters
+test_files: []