nlp 0.2.5 → 0.2.6

data/lib/word.rb

@@ -2,22 +2,22 @@ require 'inflectable'
 require 'meaningable'
 
 module NLP
-    class Word < Token
-        include Inflectable
-        include Meaningable
+  class Word < Token
+    
+    include Inflectable
+    include Meaningable
 
-        attr_reader :lemat, :orth
-        attr_accessor :category
-        
-        def initialize(word, lemat, tags)
-            super(word,tags)
-            @lemat = lemat
-        end
-
-        def inflection
-            @tags
-        end
+    attr_reader :lemat
+    attr_accessor :category
 
+    def initialize(word, lemat, tags)
+      super(word,tags)
+      @lemat = lemat
+    end
 
+    def inflection
+      @tags
     end
+
+  end
 end

data/test/analyzer_test.rb

@@ -0,0 +1,25 @@
+require '../lib/analyzer.rb'
+
+
+class AnalyzerTest < Test::Unit::TestCase
+
+  include NLP
+
+  def setup
+    sample = "Ja byłam wtedy bardzo szczęśliwa" 
+    @text = Lemmatizer.lemmatize(sample,:takipi,:local)
+    @scanner = TokenScanner.new(@text)
+    @rid_analyzer = Analyzer.new(:rid)
+    @liwc_analyzer = Analyzer.new(:liwc)
+  end
+
+  def test_analyze
+    stats = @rid_analyzer.analyze(@scanner) 
+    assert_kind_of Statistic, stats
+    assert_equal 5, stats.total_words
+    assert_equal 1, stats.word_count
+
+  end
+
+end
+

data/test/lemmatizer_test.rb

@@ -0,0 +1,73 @@
+require 'helper'
+require '../lib/lemmatizer.rb'
+
+class LemmatizerTest < Test::Unit::TestCase
+
+  include NLP
+
+  def setup
+    @sample = "Złe czasy już minęły."
+
+
+    @zle_word = Word.new('złe','zły','adj:pl:nom:m3:pos')
+    @czasy_word = Word.new('czasy','czas','subst:pl:nom:m3')
+    @minely_word = Word.new('minęły','minąć','praet:pl:m3:perf')
+    @juz_word = Word.new('już','już','qub')
+    @period = Token.new('.','interp')
+    
+  end
+
+  
+
+  def test_takipi_remote_lemmatizer
+    text = Lemmatizer.lemmatize(@sample,:takipi,:remote)
+    test_takipi_lemmatizer(text)
+  end
+
+
+  def test_takipi_local_lemmatizer
+    text = Lemmatizer.lemmatize(@sample,:takipi,:local)
+    test_takipi_lemmatizer(text)
+  end
+
+
+  def test_morfeusz_leamtizer
+    text = Lemmatizer.lemmatize(@sample)
+    assert_equal Text, text.class
+    assert_equal 1, text.sentences.size
+    assert_equal 4, text.sentences[0].words_number
+    
+    tokens = text.sentences[0].tokens
+    zle,czasy,juz,minely,period = *tokens
+    assert_equal 'zły', zle.lemat
+    assert_equal 'czas', czasy.lemat
+    assert_equal 'już', juz.lemat
+    assert_equal 'minąć', minely.lemat
+
+  end
+
+  private
+  def test_takipi_lemmatizer(text)
+    
+    assert_equal Text, text.class
+    assert_equal 1, text.sentences.size
+    assert_equal 4, text.sentences[0].words_number
+    
+    tokens = text.sentences[0].tokens
+    zle, czasy, juz, minely, period = *tokens
+    assert_equal @zle_word.inflection, zle.inflection 
+    assert_equal @czasy_word.inflection, czasy.inflection
+    assert_equal @juz_word.inflection, juz.inflection
+    assert_equal @minely_word.inflection, minely.inflection
+    assert_equal @period.tags, period.tags
+
+    assert_equal 'zły', zle.lemat
+    assert_equal 'czas', czasy.lemat
+    assert_equal 'już', juz.lemat
+    assert_equal 'minąć', minely.lemat
+
+  end
+
+
+    
+end

data/test/meaningable_test.rb

@@ -0,0 +1,28 @@
+require 'helper'
+require '../lib/word.rb'
+
+class MeaningableTest < Test::Unit::TestCase
+  include NLP
+
+  def setup 
+    
+    @word_kochamy = Word.new('kochamy','kochać', 'fin:pl:pri:imperf')
+    psych_cat  = LIWCCategory.new('PROCESY_PSYCHOLOGICZNE')
+    emotion_cat = LIWCCategory.new('EMOCJE',psych_cat)
+    pos_emotion_cat = LIWCCategory.new('POZYTYWNE_EMOCJE',emotion_cat)
+    @word_kochamy.category = pos_emotion_cat
+
+  end
+
+  def test_category_recognition
+
+   assert @word_kochamy.psychological?
+   assert @word_kochamy.positive_emotion?
+   assert @word_kochamy.emotion?
+
+   assert !@word_kochamy.negative_emotion?
+  end
+
+
+end
+

data/test/nlp_test_suite.rb

@@ -0,0 +1,11 @@
+require 'test/unit'
+require 'helper'
+require "lemmatizer_test"
+require "word_test"
+require "token_test"
+require "text_test"
+require "sentence_test"
+require "token_scanner_test"
+require "meaningable_test"
+
+

data/test/sentence_test.rb

@@ -0,0 +1,26 @@
+require 'helper'
+require '../lib/token.rb'
+
+class SentenceTest < Test::Unit::TestCase
+
+  include NLP
+
+  def setup 
+    @sentence = Sentence.new
+    @comma = Token.new(',','interp')
+    @integer = Token.new('32','tnum:integer')
+    @float = Token.new('3,12','tnum:frac')
+    @symbol = Token.new('nie_istniejace_slowo','tsym')
+  end
+
+
+  def test_sentence_size
+    assert_equal 0, @sentence.words_number
+    @sentence << @symbol
+    assert_equal 1, @sentence.words_number
+    @sentence << @integer << @comma << @float 
+    assert_equal 3, @sentence.words_number
+  end
+
+    
+end

data/test/text_test.rb

@@ -0,0 +1,29 @@
+require 'helper'
+require '../lib/token.rb'
+
+class TextTest < Test::Unit::TestCase
+
+  include NLP
+
+  def setup 
+    @s1 = Sentence.new
+    @s2 = Sentence.new
+    @comma = Token.new(',','interp')
+    @integer = Token.new('32','tnum:integer')
+    @float = Token.new('3,12','tnum:frac')
+    @symbol = Token.new('nie_istniejace_slowo','tsym')
+    @s1 << @integer << @comma << @symbol
+    @s2 << @integer << @symbol
+    @text = Text.new
+
+  end
+
+
+  def test_text
+    @text << @s1 
+    @text << @s2
+    assert_equal 2, @text.words_per_sentence
+  end
+
+    
+end

data/test/token_scanner_test.rb

@@ -0,0 +1,28 @@
+require 'helper'
+require '../lib/token_scanner.rb'
+
+class TokenScannerTest < Test::Unit::TestCase
+
+  include NLP
+
+  def setup
+    sentence = "To, jest zdanie." 
+    @text = Lemmatizer.lemmatize(sentence,:takipi,:local)
+    @scanner = TokenScanner.new(@text)
+
+  end
+
+  def test_scanner
+    assert_equal "To", @scanner.current.orth
+    @scanner.next(:word)
+    assert_equal "jest", @scanner.current.orth
+    @scanner.next(:interp)
+    assert_equal ".", @scanner.current.orth
+    @scanner.next(:word)
+    assert @scanner.end?
+    @scanner.rewind
+    assert_equal 0, @scanner.index
+  end
+
+end
+

data/test/token_test.rb

@@ -0,0 +1,37 @@
+require 'helper'
+require '../lib/token.rb'
+
+class TokenTest < Test::Unit::TestCase
+
+  include NLP
+
+  def setup 
+    @comma = Token.new(',','interp')
+    @integer = Token.new('32','tnum:integer')
+    @float = Token.new('3,12','tnum:frac')
+    @symbol = Token.new('nie_istniejace_slowo','tsym')
+  end
+
+
+  def test_recognizing_interpunction
+    assert @comma.interp?
+    assert !@comma.word?
+  end
+
+  def test_recognizing_numbers
+    assert @integer.integer?
+    assert !@integer.word?
+
+    assert @float.float?
+    assert @float.number?
+
+    assert !@float.word?
+    assert !@float.integer?
+  end
+
+  def test_symbol
+    assert @symbol.symbol?
+  end
+    
+    
+end

data/test/word_test.rb

@@ -1,42 +1,45 @@
 require 'helper'
 require '../lib/word.rb'
+
 class WordTest < Test::Unit::TestCase
-    def setup 
-        @word_kota = NLP::Word.new('kota','kot','subst:sg:gen.acc:m2')
-        @word_siebie = NLP::Word.new('siebie','się','siebie:gen.acc')
-    end
-
-      def test_word_lematization
-            assert_equal 'kot', @word_kota.lemat 
-            assert_equal 'się', @word_siebie.lemat
-      end
-
-      def test_word_orth
-          assert_equal 'kota', @word_kota.orth
-          assert_equal 'siebie', @word_siebie.orth
-      end
-
-      def test_recognizing_part_of_speech
-          assert @word_kota.rzeczownik?
-          assert @word_siebie.zaimek?
-      end
-
-     def test_recognizing_inflection
-        assert @word_kota.liczba_pojedyncza?
-        assert @word_kota.dopelniacz?
-        assert @word_kota.biernik?
-        assert @word_kota.meski_zwierzecy?
-
-        assert_equal false,  @word_kota.liczba_mnoga?
-        assert_equal false, @word_kota.mianownik?
-
-        assert @word_siebie.biernik?
-        assert @word_siebie.dopelniacz?
-     end
-
-     def test_inflection_string
-         assert_equal  @word_kota.inflection, 'subst:sg:gen.acc:m2'
-     end
+  include NLP
+
+  def setup 
+    @word_kota = Word.new('kota','kot','subst:sg:gen.acc:m2')
+    @word_siebie = Word.new('siebie','się','siebie:gen.acc')
+  end
+
+  def test_word_lematization
+    assert_equal 'kot', @word_kota.lemat 
+    assert_equal 'się', @word_siebie.lemat
+  end
+
+  def test_word_orth
+    assert_equal 'kota', @word_kota.orth
+    assert_equal 'siebie', @word_siebie.orth
+  end
+
+  def test_recognizing_part_of_speech
+    assert @word_kota.rzeczownik?
+    assert @word_siebie.zaimek?
+  end
+
+  def test_recognizing_inflection
+    assert @word_kota.liczba_pojedyncza?
+    assert @word_kota.dopelniacz?
+    assert @word_kota.biernik?
+    assert @word_kota.meski_zwierzecy?
+
+    assert !@word_kota.liczba_mnoga?
+    assert !@word_kota.mianownik?
+
+    assert @word_siebie.biernik?
+    assert @word_siebie.dopelniacz?
+  end
+
+  def test_inflection_string
+    assert_equal  @word_kota.inflection, 'subst:sg:gen.acc:m2'
+  end
 
 
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: nlp
 version: !ruby/object:Gem::Version 
-  hash: 29
+  hash: 27
   prerelease: false
   segments: 
   - 0
   - 2
-  - 5
-  version: 0.2.5
+  - 6
+  version: 0.2.6
 platform: ruby
 authors: 
 - knife
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-09-22 00:00:00 +02:00
+date: 2011-06-21 00:00:00 +02:00
 default_executable: 
 dependencies: []
 
@@ -45,10 +45,10 @@ files:
 - lib/rid_analyzer.rb
 - lib/rid_category.rb
 - lib/sentence.rb
+- lib/statistic.rb
 - lib/stdlib/ext/array.rb
 - lib/stdlib/ext/string.rb
 - lib/stree.rb
-- lib/takipi_web_service
 - lib/takipi_web_service.rb
 - lib/text.rb
 - lib/token.rb
@@ -56,9 +56,17 @@ files:
 - lib/word.rb
 - LICENSE
 - README.rdoc
+- test/sentence_test.rb
+- test/analyzer_test.rb
+- test/meaningable_test.rb
+- test/token_scanner_test.rb
 - test/helper.rb
+- test/nlp_test_suite.rb
 - test/test_nlp.rb
 - test/word_test.rb
+- test/lemmatizer_test.rb
+- test/token_test.rb
+- test/text_test.rb
 has_rdoc: true
 homepage: http://github.com/knife/nlp
 licenses: []
@@ -94,6 +102,14 @@ signing_key:
 specification_version: 3
 summary: Linguistics tools for processing polish language.
 test_files: 
+- test/sentence_test.rb
+- test/analyzer_test.rb
+- test/meaningable_test.rb
+- test/token_scanner_test.rb
 - test/helper.rb
+- test/nlp_test_suite.rb
 - test/test_nlp.rb
 - test/word_test.rb
+- test/lemmatizer_test.rb
+- test/token_test.rb
+- test/text_test.rb