sastrawi 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2c5b1727acdc71972e767e95a444969a59982660
-  data.tar.gz: 0cba68fa48adbfc2004b47b0050bd6bbfad921dd
+  metadata.gz: 18d883e3d11d60b35c08f9161c338da411e0b19f
+  data.tar.gz: b9b9c4aab58ca6c23d03f991cfe69851850a556f
 SHA512:
-  metadata.gz: 1aabe63a7cc2d94eb34e7445fd2912e3a415248d62e871578ee9e9d0c3790e822eb1d76b2bcd092fb4137a42f18734ca78f82d0c24455244103b436f2b46406a
-  data.tar.gz: 70114d83ab5d39081490308ed2437244445136282e439edfe19a76a556c3e4cfbbeda8c30e22546c780f4d8f9f1adbddcf91aedb9974f8bc98763b80ec42db0d
+  metadata.gz: 3e0838a8500a8225083c4504ead591ab769536c62cc93202da4bee6bd24cb4cde4f49121914346106f98f9344a326466ee10cedfed546abce8f33e4d6ba4a6c6
+  data.tar.gz: 8f5cf8a627c7a474dc64de6729843c4fd5f3bbf6e4e70f9d3ef6065efe7f53592185cee8894d3f5dacffb6ab13b145863a5762e24af781818aee2bdc6d29d3b9

data/CONTRIBUTING.md

@@ -0,0 +1,22 @@
+# Contributing to sastrawi-ruby
+
+If you find a bug, please report it to [issue tracker][issue]. You can also
+contribute by writing codes.
+
+## How to contribute
+
+There are some steps you must follow:
+
+1. Fork this repository and clone it to your local environment
+2. Create a named brached that contains your change
+3. Install the development dependencies by running `bundle install`
+4. Code
+5. Add or adjust unit tests and make sure everything passes by running `bundle
+   exec rake`
+6. Push your branch to GitHub
+7. Send a pull request for your branch
+
+Use `dev` branch as a target of your branch for pull request. Both issue and pull
+request details must be written in English.
+
+[issue]: https://github.com/meisyal/sastrawi-ruby/issues

data/README.md

@@ -77,9 +77,8 @@ puts stemmer.stem('internetan')
 
 ## Contributing
 
-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.
+Contributions are welcome. Please, read [CONTRIBUTING][contributing]
+guidelines.
 
 ## License
 
@@ -92,7 +91,7 @@ Attribution-NonCommercial-ShareAlike 3.0 Unported License][kateglolicense].
 [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
+[contributing]: https://github/com/meisyal/sastrawi-ruby/blob/master/CONTRIBUTING.md
 [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/Rakefile

@@ -1,5 +1,5 @@
-require "bundler/gem_tasks"
-require "rspec/core/rake_task"
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
 

data/_config.yml

@@ -0,0 +1 @@
+theme: jekyll-theme-cayman

data/lib/sastrawi/dictionary/array_dictionary.rb

@@ -9,26 +9,41 @@ module Sastrawi
         add_words(words)
       end
 
+      ##
+      # Check whether a word is contained in the dictionary
+
       def contains?(word)
         @words.include?(word)
       end
 
+      ##
+      # Count how many words in the dictionary
+
       def count
         @words.length
       end
 
+      ##
+      # Add multiple words to the dictionary
+
       def add_words(new_words)
         new_words.each do |word|
           add(word)
         end
       end
 
+      ##
+      # Add a word to the dictionary
+
       def add(word)
         return if word == ''
 
         @words.push(word)
       end
 
+      ##
+      # Add words from a text file to the dictionary
+
       def add_words_from_text_file(file_path)
         words = []
 
@@ -41,6 +56,9 @@ module Sastrawi
         add_words(words)
       end
 
+      ##
+      # Remove a word from the dictionary
+
       def remove(word)
         @words.delete(word)
       end

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule37a.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule37a
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])(er[aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])(er[aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule37b.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule37b
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])er([aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])er([aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule38a.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule38a
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])(el[aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])(el[aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule38b.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule38b
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])el([aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])el([aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule39a.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule39a
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])(em[aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])(em[aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule39b.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule39b
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])em([aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])em([aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule40a.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule40a
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])(in[aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])(in[aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule40b.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule40b
         def disambiguate(word)
-          contains = /^([bcdfghjklmnpqstvwxyz])in([aiueo])(.*)$/.match(word)
+          contains = /^([bcdfghjklmnpqrstvwxyz])in([aiueo])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/disambiguator/disambiguator_prefix_rule5.rb

@@ -3,7 +3,7 @@ module Sastrawi
     module Disambiguator
       class DisambiguatorPrefixRule5
         def disambiguate(word)
-          contains = /^be([bcdfghjklmnpqrstvwxyz])(er[bcdfghjklmnpqrstvwxyz])(.*)$/.match(word)
+          contains = /^be([bcdfghjklmnpqstvwxyz])(er[bcdfghjklmnpqrstvwxyz])(.*)$/.match(word)
 
           if contains
             matches = contains.captures

data/lib/sastrawi/morphology/invalid_affix_pair_specification.rb

@@ -1,3 +1,7 @@
+##
+# Asian J. (2007) "Effective Techniques for Indonesian Text Retrieval". page 26
+# http://researchbank.rmit.edu.au/eserv/rmit:6312/Asian.pdf
+
 module Sastrawi
   module Morphology
     class InvalidAffixPairSpecification

data/lib/sastrawi/stemmer/confix_stripping/precedence_adjustment_specification.rb

@@ -1,3 +1,8 @@
+##
+# Confix Stripping Rule Precendence Adjustment Specification
+# Asian J. (2007) "Effective Techniques for Indonesian Text Retrieval" page 78-79
+# http://researchbank.rmit.edu.au/eserv/rmit:6312/Asian.pdf
+
 module Sastrawi
   module Stemmer
     module ConfixStripping

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

@@ -1,5 +1,9 @@
 require 'sastrawi/stemmer/confix_stripping/precedence_adjustment_specification'
 
+##
+# Stemming context using Nazief and Adriani, Confix Stripping (CS),
+# Enhanced Confix Stripping (ECS), and Improved (ECS)
+
 module Sastrawi
   module Stemmer
     module Context
@@ -37,6 +41,9 @@ module Sastrawi
           @removals.push(removal)
         end
 
+        ##
+        # Execute stemming process
+
         def execute
           start_stemming_process
 
@@ -56,6 +63,10 @@ module Sastrawi
 
           cs_precendence_adjustment_specification = Sastrawi::Stemmer::ConfixStripping::PrecedenceAdjustmentSpecification.new
 
+          ##
+          # Confix stripping
+          # try to remove prefix before suffix if the specification is met
+
           if cs_precendence_adjustment_specification.satisfied_by?(@original_word)
             remove_prefixes
             return if @dictionary.contains?(@current_word)
@@ -78,6 +89,9 @@ module Sastrawi
           loop_last_return
         end
 
+        ##
+        # ECS loop last return
+
         def loop_last_return
           restore_prefix
 
@@ -147,10 +161,16 @@ module Sastrawi
           end
         end
 
+        ##
+        # Check whether the removed part is a suffix
+
         def suffix_removal?(removal)
           removal.affix_type == 'DS' || removal.affix_type == 'PP' || removal.affix_type == 'P'
         end
 
+        ##
+        # Restore prefix to proceed with ECS loop last return
+
         def restore_prefix
           @removals.each do |removal|
             if removal.affix_type == 'DP'

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

@@ -1,5 +1,10 @@
 require 'sastrawi/stemmer/context/removal'
 
+##
+# Remove derivational suffix
+# Asian J. (2007) "Effective Techniques for Indonesian Text Retrieval" page 61
+# http://researchbank.rmit.edu.au/eserv/rmit:6312/Asian.pdf
+
 module Sastrawi
   module Stemmer
     module Context
@@ -18,6 +23,10 @@ module Sastrawi
             end
           end
 
+          ##
+          # Original rule: i|kan|an
+          # Added the adopted foreign suffix rule: is|isme|isasi
+
           def remove_suffix(word)
             word.sub(/(is|isme|isasi|i|kan|an)$/, '')
           end

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

@@ -1,3 +1,8 @@
+##
+# Remove inflectional particle
+# Asian J. (2007) "Effective Techniques for Indonesian Text Retrieval" page 60
+# http://researchbank.rmit.edu.au/eserv/rmit:6312/Asian.pdf
+
 module Sastrawi
   module Stemmer
     module Context
@@ -16,6 +21,9 @@ module Sastrawi
             end
           end
 
+          ##
+          # Remove inflectional particle: lah|kah|tah|pun
+
           def remove(word)
             word.sub(/-*(lah|kah|tah|pun)$/, '')
           end

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

@@ -1,3 +1,8 @@
+##
+# Remove inflectional possessive pronoun
+# Asian J. (2007) "Effective Techniques for Indonesia Text Retrieval" page 60
+# http://researchbank.rmit.edu.au/eserv/rmit:6312/Asian.pdf
+
 module Sastrawi
   module Stemmer
     module Context
@@ -16,6 +21,9 @@ module Sastrawi
             end
           end
 
+          ##
+          # Remove inflectional possessive pronoun: ku|mu|nya|
+
           def remove(word)
             word.sub(/-*(ku|mu|nya)$/, '')
           end

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

@@ -1,3 +1,8 @@
+##
+# Remove plain prefix
+# Asian J. (2007) "Effective Techniques for Indonesian Text Retrieval" page 61
+# http://researchbank.rmit.edu.au/eserv/rmit:6312/Asian.pdf
+
 module Sastrawi
   module Stemmer
     module Context
@@ -16,6 +21,9 @@ module Sastrawi
             end
           end
 
+          ##
+          # Remove plain prefix: di|ke|se
+
           def remove(word)
             word.sub(/^(di|ke|se)/, '')
           end

data/lib/sastrawi/stemmer/stemmer.rb

@@ -4,6 +4,10 @@ require 'sastrawi/stemmer/context/visitor/visitor_provider'
 
 require 'sastrawi/stemmer/filter/text_normalizer'
 
+##
+# Indonesian Stemmer
+# Nazief & Adriani, CS Stemmer, ECS Stemmer, Improved ECS
+
 module Sastrawi
   module Stemmer
     class Stemmer
@@ -14,6 +18,9 @@ module Sastrawi
         @visitor_provider = Sastrawi::Stemmer::Context::Visitor::VisitorProvider.new
       end
 
+      ##
+      # Stem a string to its base form
+
       def stem(text)
         normalized_text = Sastrawi::Stemmer::Filter::TextNormalizer.normalize_text(text)
 
@@ -27,6 +34,9 @@ module Sastrawi
         stems.join(' ')
       end
 
+      ##
+      # Stem a word to its base form
+
       def stem_word(word)
         if plural?(word)
           stem_plural_word(word)
@@ -43,6 +53,11 @@ module Sastrawi
         return word.include?('-')
       end
 
+      ##
+      # Stem a plural word to its base form
+      # Asian J. (2007) "Effective Techniques for Indonesian Text Retrieval"
+      # page 76-77
+
       def stem_plural_word(word)
         first_match = /^(.*)-(.*)$/.match(word)
 
@@ -72,6 +87,9 @@ module Sastrawi
         end
       end
 
+      ##
+      # Stem a singular word to its base form
+
       def stem_singular_word(word)
         context = Sastrawi::Stemmer::Context::Context.new(word, @dictionary, @visitor_provider)
         context.execute

data/lib/sastrawi/stemmer/stemmer_factory.rb

@@ -5,6 +5,9 @@ require 'sastrawi/stemmer/stemmer'
 
 require 'sastrawi/stemmer/cache/array_cache'
 
+##
+# Stemmer factory helps creating a pre-configured stemmer
+
 module Sastrawi
   module Stemmer
     class StemmerFactory

data/lib/sastrawi/stop_word_remover/stop_word_remover.rb

@@ -7,6 +7,9 @@ module Sastrawi
         @dictionary = dictionary
       end
 
+      ##
+      # Remove stop words
+
       def remove(text)
         words = text.split(' ')
         stop_words = []

data/lib/sastrawi/stop_word_remover/stop_word_remover_factory.rb

@@ -4,7 +4,7 @@ require 'sastrawi/stop_word_remover/stop_word_remover'
 
 module Sastrawi
   module StopWordRemover
-    module StopWordRemoverFactory
+    class StopWordRemoverFactory
       def create_stop_word_remover
         stop_words = get_stop_word
 

data/lib/sastrawi/version.rb

@@ -1,3 +1,3 @@
 module Sastrawi
-  VERSION = "0.1.0"
+  VERSION = "0.1.1"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sastrawi
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Andrias Meisyal
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-05-21 00:00:00.000000000 Z
+date: 2017-09-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -61,10 +61,12 @@ extra_rdoc_files: []
 files:
 - ".gitignore"
 - ".travis.yml"
+- CONTRIBUTING.md
 - Gemfile
 - LICENSE.txt
 - README.md
 - Rakefile
+- _config.yml
 - data/base-word.txt
 - lib/sastrawi.rb
 - lib/sastrawi/dictionary/array_dictionary.rb