lexical_units 0.0.8 → 0.0.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: fedd5fd50283e6f7f2fb2881a8c46326cdeffb7b
-  data.tar.gz: ec83c68109e1568fdd8b7b1b2e4628ea28038b2c
+  metadata.gz: 9e7452aeb319ad29ed2bd345360a1908293e1bc9
+  data.tar.gz: 1763722a67cca06bac3dcb0aa5021ddbf8b2e5b3
 SHA512:
-  metadata.gz: b92570fd96372f27851e2dd3c9d771d534ae99f5a49847ba9289dc61f6c716a446ff3148d33bb409c0a38a6953856ee9f71683648d12c4d1da56fd5960de44a1
-  data.tar.gz: f749de922a2cd228733abc2de4690ffd9853e49bbba5533fe46625f41230147e0c78d5db11155b2b40be33287d4a854d597bc34e10747c5105554d337271cacc
+  metadata.gz: 995dce0a37c0bcf20f60f3e9378e7fb3e5577dc4dc29919878f1c81dc01dc080346e683bd73fe900d7e844893210ee9c5fe603ecdd42461c7d580d5f9b4ed4c2
+  data.tar.gz: ca5991b36cc8dd1fffe0dd87ea4f352311f4b62f55542937851e477f935c879aca9e81ddc5ee2aef87e57a5074b2fd0cc22428920c5a80462a3a37b6316d8c62

data/CHANGELOG.md

@@ -29,3 +29,7 @@
 ## v0.0.8
 
 * code clean up
+
+## v0.0.9
+
+* added split into sentences and each into words

data/lib/lexical_units/sentences.rb

@@ -4,8 +4,8 @@
 module LexicalUnits
   # Split text into sentences
   #
-  #   self.words("Lorem, ipsum. Dolor?") #=> ["Lorem, ipsum.", "Dolor?"]
-  #   self.words("Lorem! Ipsum dolor?") #=> ["Lorem!", "Ipsum dolor?"]
+  #   self.words('Lorem, ipsum. Dolor?') #=> ['Lorem, ipsum.', 'Dolor?']
+  #   self.words('Lorem! Ipsum dolor?') #=> ['Lorem!', 'Ipsum dolor?']
   def self.sentences(text)
     separators = LexicalUnits.sentence_separators
     regexp = Regexp.new("[^#{separators}]+[#{separators}]{1,3}")

data/lib/lexical_units/string.rb

@@ -10,6 +10,10 @@ module LexicalUnits
       LexicalUnits.sentences(self)
     end
 
+    def words_and_sentences
+      LexicalUnits.words_and_sentences(self)
+    end
+
     def words_without_digits
       LexicalUnits.words_without_digits(self)
     end

data/lib/lexical_units/version.rb

@@ -1,4 +1,4 @@
 # Gem version
 module LexicalUnits
-  VERSION = '0.0.8'
+  VERSION = '0.0.9'
 end

data/lib/lexical_units/words.rb

@@ -4,8 +4,8 @@
 module LexicalUnits
   # Split text into words
   #
-  #   self.words("Lorem ipsum dolor sit") #=> ["Lorem","ipsum", "dolor", "sit"]
-  #   self.words("Lorem, ipsum. Dolor?") #=> ["Lorem", "ipsum", "Dolor"]
+  #   self.words('Lorem ipsum dolor sit') #=> ['Lorem','ipsum', 'dolor', 'sit']
+  #   self.words('Lorem, ipsum. Dolor?') #=> ['Lorem', 'ipsum', 'Dolor']
   def self.words(text)
     regexp = Regexp.new("[#{LexicalUnits.separators}]")
     text.gsub(regexp, ' ').split(' ')

data/lib/lexical_units/words_and_sentences.rb

@@ -0,0 +1,17 @@
+# encoding: utf-8
+
+# Part of split into sentences and words
+module LexicalUnits
+  # Split text into sentences and each into words
+  #
+  #   self.words_and_sentences('Lorem, ipsum. Dolor?') #=>
+  #   [
+  #     ['Lorem', 'ipsum'],
+  #     ['Dolor']
+  #   ]
+  def self.words_and_sentences(text)
+    LexicalUnits.sentences(text).map do |sentence|
+      LexicalUnits.words(sentence)
+    end
+  end
+end

data/lib/lexical_units/words_without_digits.rb

@@ -4,8 +4,8 @@
 module LexicalUnits
   # Split text into words without digits
   #
-  #   self.words("Lorem 0 ipsum") #=> ["Lorem", "ipsum"]
-  #   self.words("Lorem ipsum 100") #=> ["Lorem", "ipsum"]
+  #   self.words('Lorem 0 ipsum') #=> ['Lorem', 'ipsum']
+  #   self.words('Lorem ipsum 100') #=> ['Lorem', 'ipsum']
   def self.words_without_digits(text)
     LexicalUnits.words(text).delete_if { |word| numeric?(word) }
   end

data/lib/lexical_units.rb

@@ -1,6 +1,7 @@
 require 'lexical_units/words'
 require 'lexical_units/sentences'
 require 'lexical_units/syllables'
+require 'lexical_units/words_and_sentences'
 require 'lexical_units/words_without_digits'
 require 'lexical_units/string'
 require 'lexical_units/version'

data/spec/lexical_units/string_spec.rb

@@ -25,6 +25,17 @@ describe LexicalUnits::String do
     end
   end
 
+  context '#words_and_sentences' do
+    it 'splits String into words and sentences' do
+      array = [%w(Lorem ipsum), %w(Dolor sit), %w(Amet)]
+      string = array.map do |sentence|
+        sentence.join(' ')
+      end.join('. ') + '.'
+
+      string.words_and_sentences.should eq(array)
+    end
+  end
+
   context '#words_without_digits' do
     it 'splits String into words (no ditigs)' do
       array = %w(Lorem ipsum dolor sit amet)

data/spec/lexical_units/words_and_sentences_spec.rb

@@ -0,0 +1,17 @@
+# coding: utf-8
+require 'spec_helper'
+
+describe LexicalUnits do
+  context '.words_and_sentences' do
+    it 'splits text into sentences and each into words' do
+      text = 'Lorem ipsum dolor! Sit amet? Consectetur adipiscing elit.'
+      array = [
+        %w(Lorem ipsum dolor),
+        %w(Sit amet),
+        %w(Consectetur adipiscing elit)
+      ]
+
+      subject.words_and_sentences(text).should eq(array)
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lexical_units
 version: !ruby/object:Gem::Version
-  version: 0.0.8
+  version: 0.0.9
 platform: ruby
 authors:
 - Aleksander Malaszkiewicz
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-08-15 00:00:00.000000000 Z
+date: 2013-11-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -63,10 +63,12 @@ files:
 - lib/lexical_units/syllables.rb
 - lib/lexical_units/version.rb
 - lib/lexical_units/words.rb
+- lib/lexical_units/words_and_sentences.rb
 - lib/lexical_units/words_without_digits.rb
 - spec/lexical_units/sentences_spec.rb
 - spec/lexical_units/string_spec.rb
 - spec/lexical_units/syllables_spec.rb
+- spec/lexical_units/words_and_sentences_spec.rb
 - spec/lexical_units/words_spec.rb
 - spec/lexical_units/words_without_digits_spec.rb
 - spec/spec_helper.rb
@@ -98,6 +100,7 @@ test_files:
 - spec/lexical_units/sentences_spec.rb
 - spec/lexical_units/string_spec.rb
 - spec/lexical_units/syllables_spec.rb
+- spec/lexical_units/words_and_sentences_spec.rb
 - spec/lexical_units/words_spec.rb
 - spec/lexical_units/words_without_digits_spec.rb
 - spec/spec_helper.rb