wiktionary 0.1.0

data/lib/wiktionary/noun.rb

@@ -0,0 +1,83 @@
+require 'csv'
+
+module Wiktionary
+  class Noun
+    FILES = %w[
+      noun
+      noun_uncountable
+      noun_usually_uncountable
+      noun_countable_and_uncountable
+      noun_non_attested
+      noun_unknown
+      noun_pluralia_tantum
+      noun_proper
+    ]
+    PLURALS = %w[noun
+      noun_usually_uncountable
+      noun_countable_and_uncountable
+    ]
+    UNCOUNTABLE = 'noun_uncountable'
+    PLURALIA_TANTUM = 'noun_pluralia_tantum'
+
+    # Argument path locates directory with CSV files form Wiktionary
+    # @param [String] path
+    def initialize(path=File.join(File.dirname(__FILE__),'..','..','data/'))
+      @plural_to_singulars = Hash.new{|h,e| h[e] = [] }
+      @singular_to_plurals = Hash.new{|h,e| h[e] = [] }
+      load_files(path)
+    end
+
+    # Indicate if noun is in singular form (or uncountable).
+    def singular?(noun)
+      @singular_to_plurals.has_key?(noun)
+    end
+
+    # Indicate if noun is in plural form.
+    def plural?(noun)
+      @plural_to_singulars.has_key?(noun)
+    end
+
+    # Returns list of possible singular forms of noun.
+    def singularize(noun)
+      @plural_to_singulars[noun]
+    end
+
+    private
+
+    def load_files(path)
+      files = Hash.new
+      FILES.each do |file_name|
+        files[file_name]=CSV.open(path+'/'+file_name+'.csv')
+      end
+
+      PLURALS.each do |file_name|
+        files[file_name].each do |singular,*plurals|
+          add(singular,plurals)
+        end
+      end
+
+      files[UNCOUNTABLE].each do |singular|
+        add_uncountable(singular.first)
+      end
+
+      files[PLURALIA_TANTUM].each do |singular|
+        add(singular.first,singular)
+      end
+
+      files.each do |_,file|
+        file.close
+      end
+    end
+
+    def add(singular,plurals)
+      plurals.each do |plural|
+        @plural_to_singulars[plural] << singular
+        @singular_to_plurals[singular] << plural
+      end
+    end
+
+    def add_uncountable(singular)
+      @singular_to_plurals[singular] ||= []
+    end
+  end
+end

data/spec/noun.rb

@@ -0,0 +1,29 @@
+$:.unshift "lib"
+require 'wiktionary/noun'
+
+RSpec.describe Wiktionary::Noun do
+  before(:all) do
+    @nouns = Wiktionary::Noun.new
+  end
+
+  it "tells if noun is singular" do
+    expect(@nouns.singular?("dog")).to eq true
+    expect(@nouns.singular?("dogs")).to eq false
+    expect(@nouns.singular?("politics")).to eq true
+  end
+
+  it "tells if noun is plural" do
+    expect(@nouns.plural?("dogs")).to eq true
+    expect(@nouns.plural?("oxen")).to eq true
+    expect(@nouns.plural?("dog")).to eq false
+    expect(@nouns.plural?("abidingness")).to eq false
+  end
+
+  it "returns singular form of a noun" do
+    expect(@nouns.singularize("dogs")).to include "dog"
+    expect(@nouns.singularize("boxes")).to include "box"
+    expect(@nouns.singularize("politics")).to include "politics"
+    expect(@nouns.singularize("oxen")).to include "ox"
+    expect(@nouns.singularize("feet")).to include "foot"
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,91 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+  #   - http://teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end

metadata

@@ -0,0 +1,102 @@
+--- !ruby/object:Gem::Specification
+name: wiktionary
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Krzysztofsz Wróbel
+- Aleksander Smywiński-Pohl
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-08-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 3.2.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 4.0.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 3.2.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 4.0.0
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 10.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 11.0.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 10.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 11.0.0
+description: English words morphological description and basic conversion rules based
+  on the English Wiktionary.
+email:
+- djstrong@gmail.com
+- apohllo@o2.pl
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .rspec
+- data/noun.csv
+- data/noun_countable_and_uncountable.csv
+- data/noun_non_attested.csv
+- data/noun_pluralia_tantum.csv
+- data/noun_proper.csv
+- data/noun_uncountable.csv
+- data/noun_unknown.csv
+- data/noun_usually_uncountable.csv
+- lib/wiktionary/noun.rb
+- spec/noun.rb
+- spec/spec_helper.rb
+homepage: http://github.com/cycloped-io/wiktionary
+licenses:
+- http://opensource.org/licenses/MIT
+metadata: {}
+post_install_message: 
+rdoc_options:
+- --main
+- Readme.md
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: 2.0.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: wiktionary
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Word morphology and conversion based on Wiktionary
+test_files: []
+has_rdoc: