indonesian_stemmer 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rvmrc

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+
+# This is an RVM Project .rvmrc file, used to automatically load the ruby
+# development environment upon cd'ing into the directory
+
+# First we specify our desired <ruby>[@<gemset>], the @gemset name is optional,
+# Only full ruby name is supported here, for short names use:
+#     echo "rvm use 1.9.3" > .rvmrc
+environment_id="ruby-1.9.3-p392@indonesian_stemmer"
+
+# Uncomment the following lines if you want to verify rvm version per project
+# rvmrc_rvm_version="1.18.19 (stable)" # 1.10.1 seams as a safe start
+# eval "$(echo ${rvm_version}.${rvmrc_rvm_version} | awk -F. '{print "[[ "$1*65536+$2*256+$3" -ge "$4*65536+$5*256+$6" ]]"}' )" || {
+#   echo "This .rvmrc file requires at least RVM ${rvmrc_rvm_version}, aborting loading."
+#   return 1
+# }
+
+# First we attempt to load the desired environment directly from the environment
+# file. This is very fast and efficient compared to running through the entire
+# CLI and selector. If you want feedback on which environment was used then
+# insert the word 'use' after --create as this triggers verbose mode.
+if [[ -d "${rvm_path:-$HOME/.rvm}/environments"
+  && -s "${rvm_path:-$HOME/.rvm}/environments/$environment_id" ]]
+then
+  \. "${rvm_path:-$HOME/.rvm}/environments/$environment_id"
+  [[ -s "${rvm_path:-$HOME/.rvm}/hooks/after_use" ]] &&
+    \. "${rvm_path:-$HOME/.rvm}/hooks/after_use" || true
+else
+  # If the environment file has not yet been created, use the RVM CLI to select.
+  rvm --create  "$environment_id" || {
+    echo "Failed to create RVM environment '${environment_id}'."
+    return 1
+  }
+fi
+
+# If you use bundler, this might be useful to you:
+# if [[ -s Gemfile ]] && {
+#   ! builtin command -v bundle >/dev/null ||
+#   builtin command -v bundle | GREP_OPTIONS= \grep $rvm_path/bin/bundle >/dev/null
+# }
+# then
+#   printf "%b" "The rubygem 'bundler' is not installed. Installing it now.\n"
+#   gem install bundler
+# fi
+# if [[ -s Gemfile ]] && builtin command -v bundle >/dev/null
+# then
+#   bundle install | GREP_OPTIONS= \grep -vE '^Using|Your bundle is complete'
+# fi

data/Gemfile

@@ -0,0 +1,21 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in indonesian_stemmer.gemspec
+gemspec
+
+# Declare any dependencies that are still in development here instead of in
+# your gemspec. Remember to move these dependencies to your gemspec before
+# releasing your gem to rubygems.org.
+
+# To use in development
+group :development do
+  gem 'guard'
+  gem 'guard-rspec'
+  gem 'pry', require: true
+  gem 'pry-debugger'
+
+  if RbConfig::CONFIG['host_os'] =~ /darwin/
+    gem 'growl'
+    gem 'rb-fsevent', require: false
+  end
+end

data/Guardfile

@@ -0,0 +1,9 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+guard 'rspec' do
+  watch(%r{^spec/.+_spec\.rb$})
+  watch(%r{^lib/(.+)\.rb$})     { |m| "spec/lib/#{m[1]}_spec.rb" }
+  watch('spec/spec_helper.rb')  { "spec" }
+end
+

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Adinda Praditya
+
+MIT License
+
+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 +1,29 @@
+# IndonesianStemmer
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'indonesian_stemmer'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install indonesian_stemmer
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,7 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new
+
+task :default => :spec
+task :test => :spec

data/indonesian_stemmer.gemspec

@@ -0,0 +1,23 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'indonesian_stemmer/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "indonesian_stemmer"
+  gem.version       = IndonesianStemmer::VERSION
+  gem.authors       = ["Adinda Praditya"]
+  gem.email         = ["apraditya@gmail.com"]
+  gem.description   = %q{Stems Indonesian words based on Porter Stemmer, with the algorithm presented in "A Study of Stemming Effects on Information Retrieval in Bahasa Indonesia", Fadillah Z Tala.}
+  gem.summary       = %q{Porter Stemmer for Bahasa Indonesia.}
+  gem.homepage      = "https://github.com/apraditya/indonesian_stemmer"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec)/})
+  gem.require_paths = ["lib"]
+
+  gem.add_development_dependency 'rake'
+  gem.add_development_dependency 'rspec'
+
+end

data/lib/indonesian_stemmer.rb

@@ -0,0 +1,51 @@
+require "indonesian_stemmer/version"
+require "indonesian_stemmer/morphological_utility"
+
+module IndonesianStemmer
+
+  class << self
+    include MorphologicalUtility
+
+    attr_accessor :number_of_syllables
+
+    def stem(word, derivational_stemming = true)
+      @flags = 0
+      @number_of_syllables = total_syllables word
+
+      remove_particle(word) if still_has_many_syllables?
+      remove_possessive_pronoun(word) if still_has_many_syllables?
+
+      stem_derivational(word) if derivational_stemming
+
+      word
+    end
+
+
+    private
+      def stem_derivational(word)
+        previous_size = word.size
+        remove_first_order_prefix(word) if still_has_many_syllables?
+        if previous_size != word.size
+          previous_size = word.size
+          remove_suffix(word) if still_has_many_syllables?
+
+          if previous_size != word.size
+            remove_second_order_prefix(word) if still_has_many_syllables?
+          end
+        else
+          remove_second_order_prefix(word) if still_has_many_syllables?
+          remove_suffix(word) if still_has_many_syllables?
+        end
+      end
+
+      def still_has_many_syllables?
+        @number_of_syllables > 2
+      end
+  end
+end
+
+class String
+  def stem
+    IndonesianStemmer.stem(self)
+  end
+end

data/lib/indonesian_stemmer/morphological_utility.rb

@@ -0,0 +1,183 @@
+require "indonesian_stemmer/stemmer_utility"
+
+module IndonesianStemmer
+
+  VOWEL_CHARACTERS                            = %w( a e i o u )
+  PARTICLE_CHARACTERS                         = %w( kah lah pun )
+  POSSESSIVE_PRONOUN_CHARACTERS               = %w( ku mu nya )
+  FIRST_ORDER_PREFIX_CHARACTERS               = %w( meng meny men mem me
+                                                    peng peny pen pem di ter ke )
+  SPECIAL_FIRST_ORDER_PREFIX_CHARACTERS       = %w( meny peny pen )
+  SECOND_ORDER_PREFIX_CHARACTERS              = %w( ber be per pe )
+  SPECIAL_SECOND_ORDER_PREFIX_CHARACTERS      = %w( be )
+  NON_SPECIAL_SECOND_ORDER_PREFIX_CHARACTERS  = %w( ber per pe )
+  SPECIAL_SECOND_ORDER_PREFIX_WORDS           = %w( belajar pelajar belunjur )
+  SUFFIX_CHARACTERS                           = %w( kan an i )
+
+  REMOVED_KE    = 1
+  REMOVED_PENG  = 2
+  REMOVED_DI    = 4
+  REMOVED_MENG  = 8
+  REMOVED_TER   = 16
+  REMOVED_BER   = 32
+  REMOVED_PE    = 64
+
+
+  module MorphologicalUtility
+    include StemmerUtility
+
+    def self.included(receiver)
+      receiver.send :include, InstanceMethods
+    end
+
+    module InstanceMethods
+      def total_syllables(word)
+        result = 0
+        word.size.times do |i|
+          result += 1 if is_vowel?(word[i])
+        end
+        result
+      end
+
+      def remove_particle(word)
+        @number_of_syllables ||= total_syllables(word)
+        remove_characters_matching_collection(word,
+                                              collection_for(:particle),
+                                              :end )
+      end
+
+      def remove_possessive_pronoun(word)
+        @number_of_syllables ||= total_syllables(word)
+        remove_characters_matching_collection(word,
+                                              collection_for(:possessive_pronoun),
+                                              :end )
+      end
+
+      def remove_first_order_prefix(word)
+        @number_of_syllables ||= total_syllables(word)
+
+        word_size = word.size
+        SPECIAL_FIRST_ORDER_PREFIX_CHARACTERS.each do |characters|
+          characters_size = characters.size
+          if starts_with?(word, word_size, characters) && word_size > characters_size && is_vowel?(word[characters_size])
+            @flags ||= collection_for(characters, 'removed')
+            reduce_syllable
+            word = substitute_word_character(word, characters)
+            slice_word_at_position( word,
+                                    characters_size-1,
+                                    :start )
+            return word
+          end
+        end
+
+        remove_characters_matching_collection( word,
+                                              collection_for(:first_order_prefix),
+                                              :start )
+      end
+
+      def remove_second_order_prefix(word)
+        @number_of_syllables ||= total_syllables(word)
+        word_size = word.size
+
+        if SPECIAL_SECOND_ORDER_PREFIX_WORDS.include?(word)
+          @flags ||= REMOVED_BER if word[0..1] == 'be'
+          reduce_syllable
+          slice_word_at_position(word, 3, :start)
+          return word
+        end
+
+        if starts_with?(word, word_size, 'be') && word_size > 4 && !is_vowel?(word[2]) && word[3..4] == 'er'
+          @flags ||= REMOVED_BER
+          reduce_syllable
+          slice_word_at_position(word, 2, :start)
+          return word
+        end
+
+        remove_characters_matching_collection(word,
+                                              collection_for(:non_special_second_order_prefix),
+                                              :start)
+      end
+
+      def remove_suffix(word)
+        @number_of_syllables ||= total_syllables(word)
+
+        SUFFIX_CHARACTERS.each do |character|
+          constants_to_check = case character
+          when 'kan'
+            [REMOVED_KE, REMOVED_PENG, REMOVED_PE]
+          when 'an'
+            [REMOVED_DI, REMOVED_MENG, REMOVED_TER]
+          when 'i'
+            [REMOVED_BER, REMOVED_KE, REMOVED_PENG]
+          end
+
+          if ends_with?(word, word.size, character) &&
+                constants_to_check.all? { |c| (@flags & c) == 0 }
+            reduce_syllable
+            slice_word_at_position(word, character.size, :end)
+            return word
+          end
+        end
+
+        word
+      end
+
+
+      private
+        def is_vowel?(character)
+          VOWEL_CHARACTERS.include? character
+        end
+
+        def collection_for(name, type = 'characters')
+          constant_name = if type == 'characters'
+            "#{name}_#{type}"
+          else
+            name =  case
+                    when %w(meny men mem me).include?(name)
+                      'meng'
+                    when %w(peny pen pem).include?(name)
+                      'peng'
+                    else
+                      name
+                    end
+            "#{type}_#{name}"
+          end
+          const_get("#{constant_name}".upcase.to_sym)
+        rescue NameError
+        end
+
+        def remove_characters_matching_collection(word, collection, position)
+          collection.each do |characters|
+            if send("#{position}s_with?", word, word.size, characters)
+              @flags ||= collection_for(characters, 'removed')
+              reduce_syllable
+              slice_word_at_position(word, characters.size, position)
+              return word
+            end
+          end
+
+          word
+        end
+
+        def slice_word_at_position(word, characters_size, position)
+          multiplier = (position == :start)? 0 : -1
+          word.slice!( multiplier*characters_size, characters_size)
+        end
+
+        def substitute_word_character(word, characters)
+          substitute_char = case
+          when %w(meny peny).include?(characters)
+            's'
+          when characters == 'pen'
+            't'
+          end
+          word[characters.size-1] = substitute_char if substitute_char
+          word
+        end
+
+        def reduce_syllable
+          @number_of_syllables -= 1
+        end
+    end
+  end
+end

data/lib/indonesian_stemmer/stemmer_utility.rb

@@ -0,0 +1,27 @@
+module IndonesianStemmer
+  module StemmerUtility
+
+    def self.included(receiver)
+      receiver.send :include, InstanceMethods
+    end
+
+    module InstanceMethods
+      def starts_with?(text, by_text_size, prefix)
+        return false if prefix.size > by_text_size
+        prefix.size.times do |i|
+          return false if text[i] != prefix[i]
+        end
+        return true
+      end
+
+      def ends_with?(text, by_text_size, suffix)
+        suffix_size = suffix.size
+        return false if suffix_size > by_text_size
+        suffix_size.times do |i|
+          return false if text[0 - (suffix_size - i)] != suffix[i]
+        end
+        return true
+      end
+    end
+  end
+end