sastrawi 0.1.0.pre → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 85c8c97313e9ebf76008045f30bec9a9eaca39dd
-  data.tar.gz: f4353fd69f5a722fd8003c37e8c0a61c43ce8c34
+  metadata.gz: 2c5b1727acdc71972e767e95a444969a59982660
+  data.tar.gz: 0cba68fa48adbfc2004b47b0050bd6bbfad921dd
 SHA512:
-  metadata.gz: 86ac9f0de919863b86bc7e41b2428f958c43d921453fc34336282996352005bde335c5790ac509a894251b79fa9c79685a638c1ca97469921493fc54f91cad7a
-  data.tar.gz: 826cef4036c182fd855b399c0db1f7a417b43950f8ac9e710a4e8bb335880369f589196bc947162ccb664e427b6ea7e79d014a6ee9cbf0053084665c6df82fa9
+  metadata.gz: 1aabe63a7cc2d94eb34e7445fd2912e3a415248d62e871578ee9e9d0c3790e822eb1d76b2bcd092fb4137a42f18734ca78f82d0c24455244103b436f2b46406a
+  data.tar.gz: 70114d83ab5d39081490308ed2437244445136282e439edfe19a76a556c3e4cfbbeda8c30e22546c780f4d8f9f1adbddcf91aedb9974f8bc98763b80ec42db0d

data/.travis.yml

@@ -1,8 +1,10 @@
 sudo: false
 language: ruby
 rvm:
-  - 1.9.3
-  - 2.2.6
-  - 2.3.1
-  - 2.4.0
+  - 2.2.7
+  - 2.3.4
+  - 2.4.1
 before_install: gem install bundler -v 1.12.5
+notifications:
+  email:
+    on_success: never

data/README.md

@@ -6,7 +6,9 @@ written in PHP and this library is written in Ruby language.
 
 Taken from [Wikipedia][stemmingwiki], stemming is the process of reducing
 inflected (or sometimes derived) words to their word stem, base or root form.
-For instance, "menahan" has "tahan" as its base form.
+For instance, "menahan" has "tahan" as its base form. If you want to know how
+stemming works, please read this [page][howstemmingworks] (in Bahasa Indonesia)
+for further details.
 
 ## Documentation
 
@@ -33,27 +35,51 @@ on your system. I would recommend to choose the stable versions.
 
 ## Usage
 
-Currently, this library supports stemming words with provided base forms. You
-can't add or remove any base form. This feature will be implemented for next
-release.
+This library supports stemming words with provided base forms.
 
 ```ruby
 require 'sastrawi'
 
+# create stemmer
+stemmer_factory = Sastrawi::Stemmer::StemmerFactory.new
+stemmer = stemmer_factory.create_stemmer
+
 # prepare a sentence or words to be stemmed and call the stem API
 sentence = 'Perekonomian Indonesia sedang dalam pertumbuhan yang membanggakan.'
-stemming_result = Sastrawi.stem(sentence)
+stemming_result = stemmer.stem(sentence)
 
-# the stemming result should be "ekonomi indonesia sedang dalam tumbuh yang
-bangga"
+# the stemming result should be "ekonomi indonesia sedang dalam tumbuh yang bangga"
 puts stemming_result
 ```
 
+Beside that, you can add or remove any base form.
+
+```ruby
+require 'sastrawi'
+
+# create stemmer
+stemmer_factory = Sastrawi::Stemmer::StemmerFactory.new
+
+# create default dictionary and add a text file that contains words into it
+dictionary = stemmer_factory.create_default_dictionary
+dictionary.add_words_from_text_file('my-dictionary.txt')
+
+# add or remove words
+dictionary.add('internet')
+dictionary.remove('desa')
+
+# stem a word, "internetan", for example
+stemmer = Sastrawi::Stemmer::Stemmer.new(dictionary)
+
+# the stemming result should be "internet"
+puts stemmer.stem('internetan')
+```
+
 ## Contributing
 
-Contributions are welcome. If you find a bug, please report it to issue
-tracker. Use `dev` branch as a target of your feature branch for pull request.
-Both issue and pull request details should be written in English.
+Contributions are welcome. If you find a bug, please report it to [issue
+tracker][issue]. Use `dev` branch as a target of your feature branch for pull
+request. Both issue and pull request details must be written in English.
 
 ## License
 
@@ -64,7 +90,9 @@ Attribution-NonCommercial-ShareAlike 3.0 Unported License][kateglolicense].
 
 [sastrawi]: https://github.com/sastrawi/sastrawi
 [stemmingwiki]: https://en.wikipedia.org/wiki/Stemming
+[howstemmingworks]: https://github.com/sastrawi/sastrawi/wiki/Stemming-Bahasa-Indonesia
 [documentation]: https://github.com/meisyal/sastrawi-ruby/wiki
+[issue]: https://github.com/meisyal/sastrawi-ruby/issues
 [license]: https://github.com/meisyal/sastrawi-ruby/blob/master/LICENSE.txt
 [kateglo]: http://kateglo.com
 [kateglolicense]: https://creativecommons.org/licenses/by-nc-sa/3.0/

data/lib/sastrawi.rb

@@ -1,12 +1,3 @@
 require 'sastrawi/version'
 
 require 'sastrawi/stemmer/stemmer_factory'
-
-module Sastrawi
-  def self.stem(sentence)
-    stemmer_factory = Sastrawi::Stemmer::StemmerFactory.new
-    stemmer = stemmer_factory.create_stemmer
-
-    stemmer.stem(sentence)
-  end
-end

data/lib/sastrawi/dictionary/array_dictionary.rb

@@ -1,7 +1,7 @@
 module Sastrawi
   module Dictionary
     class ArrayDictionary
-      attr_accessor :words
+      attr_reader :words
 
       def initialize(words = [])
         @words = []
@@ -28,6 +28,22 @@ module Sastrawi
 
         @words.push(word)
       end
+
+      def add_words_from_text_file(file_path)
+        words = []
+
+        File.open(file_path, 'r') do |file|
+          file.each do |line|
+            words.push(line.chomp)
+          end
+        end
+
+        add_words(words)
+      end
+
+      def remove(word)
+        @words.delete(word)
+      end
     end
   end
 end

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule29.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule29
         def disambiguate(word)
-          contains = /^pen([bcdfghjklmnpqrstvwxyz])(.*)$/.match(word)
+          contains = /^peng([bcdfghjklmnpqrstvwxyz])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule9.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule9
         def disambiguate(word)
-          contains = /^te([bcdfghjklmnpqrstvwxyz])er(([bcdfghjklmnpqrstvwxyz]).*)$/.match(word)
+          contains = /^te([bcdfghjklmnpqrstvwxyz])er([bcdfghjklmnpqrstvwxyz])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/stemmer/cache/array_cache.rb

@@ -2,7 +2,7 @@ module Sastrawi
   module Stemmer
     module Cache
       class ArrayCache
-        attr_accessor :data
+        attr_reader :data
 
         def initialize
           @data = {}

data/lib/sastrawi/stemmer/cached_stemmer.rb

@@ -3,7 +3,7 @@ require 'sastrawi/stemmer/filter/text_normalizer'
 module Sastrawi
   module Stemmer
     class CachedStemmer
-      attr_accessor :cache, :delegated_stemmer
+      attr_reader :cache, :delegated_stemmer
 
       def initialize(cache, delegated_stemmer)
         @cache = cache

data/lib/sastrawi/stemmer/context/context.rb

@@ -4,7 +4,8 @@ module Sastrawi
   module Stemmer
     module Context
       class Context
-        attr_accessor :original_word, :current_word, :dictionary, :visitor_provider, :process_is_stopped, :removals, :visitors, :suffix_visitors, :prefix_visitors, :result
+        attr_reader :original_word, :dictionary, :visitor_provider, :visitors, :suffix_visitors, :prefix_visitors
+        attr_accessor :current_word, :process_is_stopped, :removals, :result
 
         def initialize(original_word, dictionary, visitor_provider)
             @original_word = original_word
@@ -14,10 +15,10 @@ module Sastrawi
 
             @process_is_stopped = false
             @removals = []
-            @visitors = []
-            @suffix_visitors = []
-            @prefix_visitors = []
-            @result = ''
+            @visitors = nil
+            @suffix_visitors = nil
+            @prefix_visitors = nil
+            @result = nil
 
             init_visitors
         end

data/lib/sastrawi/stemmer/context/removal.rb

@@ -2,7 +2,7 @@ module Sastrawi
   module Stemmer
     module Context
       class Removal
-        attr_accessor :visitor, :subject, :result, :removed_part, :affix_type
+        attr_reader :visitor, :subject, :result, :removed_part, :affix_type
 
         def initialize(visitor, subject, result, removed_part, affix_type)
           @visitor = visitor

data/lib/sastrawi/stemmer/context/visitor/prefix_disambiguator.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Context
       module Visitor
         class PrefixDisambiguator
-          attr_accessor :disambiguators
+          attr_reader :disambiguators
 
           def initialize(disambiguators = [])
             @disambiguators = []
@@ -22,7 +22,7 @@ module Sastrawi
 
             return if result.nil?
 
-            removed_part = context.current_word.sub(result, '')
+            removed_part = context.current_word.sub(/#{Regexp.quote(result)}/, '')
 
             removal = Removal.new(self, context.current_word, result, removed_part, 'DP')
 

data/lib/sastrawi/stemmer/context/visitor/remove_derivational_suffix.rb

@@ -9,7 +9,7 @@ module Sastrawi
             result = remove_suffix(context.current_word)
 
             if result != context.current_word
-              removed_part = context.current_word.sub(result, '')
+              removed_part = context.current_word.sub(/#{Regexp.quote(result)}/, '')
 
               removal = Sastrawi::Stemmer::Context::Removal.new(self, context.current_word, result, removed_part, 'DS')
 

data/lib/sastrawi/stemmer/context/visitor/remove_inflectional_particle.rb

@@ -7,7 +7,7 @@ module Sastrawi
             result = remove(context.current_word)
 
             if result != context.current_word
-              removed_part = context.current_word.sub(result, '')
+              removed_part = context.current_word.sub(/#{Regexp.quote(result)}/, '')
 
               removal = Removal.new(self, context.current_word, result, removed_part, 'P')
 

data/lib/sastrawi/stemmer/context/visitor/remove_inflectional_possessive_pronoun.rb

@@ -7,7 +7,7 @@ module Sastrawi
             result = remove(context.current_word)
 
             if result != context.current_word
-              removed_part = context.current_word.sub(result, '')
+              removed_part = context.current_word.sub(/#{Regexp.quote(result)}/, '')
 
               removal = Removal.new(self, context.current_word, result, removed_part, 'PP')
 

data/lib/sastrawi/stemmer/context/visitor/remove_plain_prefix.rb

@@ -7,7 +7,7 @@ module Sastrawi
             result = remove(context.current_word)
 
             if result != context.current_word
-              removed_part = context.current_word.sub(result, '')
+              removed_part = context.current_word.sub(/#{Regexp.quote(result)}/, '')
 
               removal = Removal.new(self, context.current_word, result, removed_part, 'DP')
 

data/lib/sastrawi/stemmer/context/visitor/visitor_provider.rb

@@ -69,7 +69,7 @@ module Sastrawi
     module Context
       module Visitor
         class VisitorProvider
-          attr_accessor :visitors, :suffix_visitors, :prefix_visitors
+          attr_reader :visitors, :suffix_visitors, :prefix_visitors
 
           def initialize
             @visitors = []

data/lib/sastrawi/stemmer/stemmer.rb

@@ -1,11 +1,13 @@
 require 'sastrawi/stemmer/context/context'
+
 require 'sastrawi/stemmer/context/visitor/visitor_provider'
+
 require 'sastrawi/stemmer/filter/text_normalizer'
 
 module Sastrawi
   module Stemmer
     class Stemmer
-      attr_accessor :dictionary, :visitor_provider
+      attr_reader :dictionary, :visitor_provider
 
       def initialize(dictionary)
         @dictionary = dictionary
@@ -36,35 +38,31 @@ module Sastrawi
       def plural?(word)
         matches = /^(.*)-(ku|mu|nya|lah|kah|tah|pun)$/.match(word)
 
-        if matches
-          true
-        else
-          false
-        end
+        return matches[1].include?('-') if matches
+
+        return word.include?('-')
       end
 
       def stem_plural_word(word)
         first_match = /^(.*)-(.*)$/.match(word)
 
-        unless first_match
-          return word
-        end
-
-        words = [first_match.captures[0], first_match.captures[1]]
+        return word unless first_match
 
+        words = [first_match[1], first_match[2]]
         suffix = words[1]
-        suffixes = ['ku', 'mu', 'nya', 'lah', 'kah', 'tah', 'pun']
+        suffixes = %w[ku mu nya lah kah tah pun]
         second_match = /^(.*)-(.*)$/.match(words[0])
 
         if suffixes.include?(suffix) && second_match
-          words[1] = words[1] + '-' + suffix
+          words[0] = second_match[1]
+          words[1] = second_match[2] << '-' << suffix
         end
 
         root_first_word = stem_singular_word(words[0])
         root_second_word = stem_singular_word(words[1])
 
-        unless @dictionary.contains?(words[1]) && root_second_word == words[1]
-          root_second_word = stem_singular_word('me' + words[1])
+        if !@dictionary.contains?(words[1]) && root_second_word == words[1]
+          root_second_word = stem_singular_word('me' << words[1])
         end
 
         if root_first_word == root_second_word

data/lib/sastrawi/stemmer/stemmer_factory.rb

@@ -1,8 +1,9 @@
 require 'sastrawi/dictionary/array_dictionary'
+
 require 'sastrawi/stemmer/cached_stemmer'
 require 'sastrawi/stemmer/stemmer'
-require 'sastrawi/stemmer/cache/array_cache'
 
+require 'sastrawi/stemmer/cache/array_cache'
 
 module Sastrawi
   module Stemmer
@@ -29,7 +30,7 @@ module Sastrawi
 
       def get_words_from_file
         root_directory = File.expand_path('../../../..', __FILE__)
-        dictionary_file_path = File.join(root_directory, 'data/kata-dasar.txt')
+        dictionary_file_path = File.join(root_directory, 'data/base-word.txt')
 
         dictionary_content = []
         File.open(dictionary_file_path, 'r') do |file|

data/lib/sastrawi/stop_word_remover/stop_word_remover.rb

@@ -1,7 +1,7 @@
 module Sastrawi
   module StopWordRemover
     class StopWordRemover
-      attr_accessor :dictionary
+      attr_reader :dictionary
 
       def initialize(dictionary)
         @dictionary = dictionary
@@ -12,7 +12,7 @@ module Sastrawi
         stop_words = []
 
         words.each do |word|
-          unless @dictionary.include?(word)
+          unless @dictionary.contains?(word)
             stop_words.push(word)
           end
         end

data/lib/sastrawi/stop_word_remover/stop_word_remover_factory.rb

@@ -1,4 +1,5 @@
 require 'sastrawi/dictionary/array_dictionary'
+
 require 'sastrawi/stop_word_remover/stop_word_remover'
 
 module Sastrawi

data/lib/sastrawi/version.rb

@@ -1,3 +1,3 @@
 module Sastrawi
-  VERSION = "0.1.0.pre"
+  VERSION = "0.1.0"
 end

data/sastrawi.gemspec

@@ -6,6 +6,7 @@ require 'sastrawi/version'
 Gem::Specification.new do |spec|
   spec.name          = "sastrawi"
   spec.version       = Sastrawi::VERSION
+  spec.required_ruby_version = ">= 1.9.3"
   spec.authors       = ["Andrias Meisyal"]
   spec.email         = ["andriasonline@gmail.com"]
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sastrawi
 version: !ruby/object:Gem::Version
-  version: 0.1.0.pre
+  version: 0.1.0
 platform: ruby
 authors:
 - Andrias Meisyal
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-02-13 00:00:00.000000000 Z
+date: 2017-05-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -65,7 +65,7 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
-- data/kata-dasar.txt
+- data/base-word.txt
 - lib/sastrawi.rb
 - lib/sastrawi/dictionary/array_dictionary.rb
 - lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule10.rb
@@ -158,12 +158,12 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.9.3
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">"
+  - - ">="
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.5.1