clarifier 0.0.1 → 0.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d53807d854a8ce086196afc575ba901abc29bb7e
-  data.tar.gz: ab905fce3c0436754135fbf76de9f495a62f8ffa
+  metadata.gz: 58565ee983a2150f10fc30a134866966f258035f
+  data.tar.gz: e64ca90da702b11ae24be30968b036b550be4d3a
 SHA512:
-  metadata.gz: b9c761e333acd0cfcf8ecbda6c66448303d98aef4e45937a23f7260e7a538ca808b1b23927d058f37309754ccdbd332c977e7301fa6b79af283d58e68c2098d9
-  data.tar.gz: fb0362001038e405b7f37e4ebd14c2bbe97fa43349a53b54acbadc53e28086b5736a2a4da791749bbd58e2a3e72ccb6e92b4f01dfbcfa92d14451dc614764ee5
+  metadata.gz: 51cf55d7abfaf2610c86a9d73f1f3a305770e7bf28aa6d6235836dd5789c36b91e534d9fddcb5506dc1b4b45b80765724a6b751d05ba836243edf2dd7dc58b81
+  data.tar.gz: 1cbd8554f5703f4bc593a718f0e691cff000282a5652c518e7ceb07a491a740a6cb20ddec493fa61a63cff8f69247837625499192f9e10ad1ef81fd4ef89ce4d

data/CHANGELOG.md

@@ -1,2 +1,5 @@
+# 0.0.2 / 2014-03-12
+* [FEATURE] Added n-gram generator
+
 # 0.0.1 / 2014-03-04
 * [FEATURE] Initial Release

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    clarifier (0.0.1)
+    clarifier (0.0.2)
 
 GEM
   remote: https://rubygems.org/

data/lib/clarifier.rb

@@ -1,5 +1,6 @@
 require 'clarifier/version'
 require 'clarifier/stop_words'
+require 'clarifier/n_grams'
 
 require 'clarifier/word_lists/en_gb_basic'
 require 'clarifier/word_lists/en_gb_mysql'

data/lib/clarifier/n_grams.rb

@@ -0,0 +1,15 @@
+module Clarifier
+  class NGrams
+
+    def n_grams(input, size = 2)
+      words = input.split(/\W+/)
+      ngrams = []
+      words.each_with_index do |word, i|
+        upper_limit = i + size - 1
+        ngrams << words[i..upper_limit].join(' ') unless upper_limit >= words.length
+      end
+      ngrams
+    end
+
+  end
+end

data/lib/clarifier/version.rb

@@ -1,3 +1,3 @@
 module Clarifier
-  VERSION = "0.0.1"
+  VERSION = "0.0.2"
 end

data/test/n_grams_test.rb

@@ -0,0 +1,23 @@
+require_relative 'test_helper'
+require_relative 'test_docs'
+
+module Clarifier
+
+  class ClarifierNGramsTest < Minitest::Test
+
+    def test_creates_2_word_n_grams_by_default
+      ng = Clarifier::NGrams.new
+      input = 'The quick brown fox jumped over the lazy dog.'
+      expected = ['The quick', 'quick brown', 'brown fox', 'fox jumped', 'jumped over', 'over the', 'the lazy', 'lazy dog']
+      assert_equal expected, ng.n_grams(input)
+    end
+
+    def test_creates_3_word_n_grams
+      ng = Clarifier::NGrams.new
+      input = 'The quick brown fox jumped over the lazy dog.'
+      expected = ['The quick brown', 'quick brown fox', 'brown fox jumped', 'fox jumped over', 'jumped over the', 'over the lazy', 'the lazy dog']
+      assert_equal expected, ng.n_grams(input, 3)
+    end
+
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: clarifier
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.0.2
 platform: ruby
 authors:
 - Rob Styles
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-03-04 00:00:00.000000000 Z
+date: 2014-03-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -82,10 +82,12 @@ files:
 - Rakefile
 - clarifier.gemspec
 - lib/clarifier.rb
+- lib/clarifier/n_grams.rb
 - lib/clarifier/stop_words.rb
 - lib/clarifier/version.rb
 - lib/clarifier/word_lists/en_gb_basic.rb
 - lib/clarifier/word_lists/en_gb_mysql.rb
+- test/n_grams_test.rb
 - test/stop_words_test.rb
 - test/test_docs.rb
 - test/test_helper.rb
@@ -114,6 +116,7 @@ signing_key:
 specification_version: 4
 summary: Clarifier is a stopwords library for removing common words from text
 test_files:
+- test/n_grams_test.rb
 - test/stop_words_test.rb
 - test/test_docs.rb
 - test/test_helper.rb