lexical_units 0.0.7 → 0.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: e0900a1a365540816cacaf4ea41ae0ce6d70a37f
-  data.tar.gz: 77c84fbc21845351e53eb83fd912afc389700e34
+  metadata.gz: fedd5fd50283e6f7f2fb2881a8c46326cdeffb7b
+  data.tar.gz: ec83c68109e1568fdd8b7b1b2e4628ea28038b2c
 SHA512:
-  metadata.gz: 2ccaaba2910f859a987252cb9dfe38b0812462657077382fcb377e4c05d59259df9b565d56977e3699d0c6427b12da8e9d3bf1390948bd1e10fcb5cd9ca05639
-  data.tar.gz: 2a3bec215bdf473fe76287090aafe31f25d75ca481c0515c5c90011cd81444a9e957b32b3cfdd1a61a86046b89884a53549da05fc264534badbe652034c54ac9
+  metadata.gz: b92570fd96372f27851e2dd3c9d771d534ae99f5a49847ba9289dc61f6c716a446ff3148d33bb409c0a38a6953856ee9f71683648d12c4d1da56fd5960de44a1
+  data.tar.gz: f749de922a2cd228733abc2de4690ffd9853e49bbba5533fe46625f41230147e0c78d5db11155b2b40be33287d4a854d597bc34e10747c5105554d337271cacc

data/CHANGELOG.md

@@ -25,3 +25,7 @@
 ## v0.0.7
 
 * added split into words without digits
+
+## v0.0.8
+
+* code clean up

data/README.md

@@ -1,4 +1,5 @@
-# LexicalUnits [![Gem Version](https://badge.fury.io/rb/lexical_units.png)](http://badge.fury.io/rb/lexical_units) [![Build Status](https://travis-ci.org/fractalsoft/lexical_units.png)](https://travis-ci.org/fractalsoft/lexical_units) [![Dependency Status](https://gemnasium.com/fractalsoft/lexical_units.png)](https://gemnasium.com/fractalsoft/lexical_units) [![Coverage Status](https://coveralls.io/repos/fractalsoft/lexical_units/badge.png)](https://coveralls.io/r/fractalsoft/lexical_units)
+# LexicalUnits [![Gem Version](https://badge.fury.io/rb/lexical_units.png)](http://badge.fury.io/rb/lexical_units) [![Build Status](https://travis-ci.org/fractalsoft/lexical_units.png)](https://travis-ci.org/fractalsoft/lexical_units) [![Dependency Status](https://gemnasium.com/fractalsoft/lexical_units.png)](https://gemnasium.com/fractalsoft/lexical_units) [![Coverage Status](https://coveralls.io/repos/fractalsoft/lexical_units/badge.png)](https://coveralls.io/r/fractalsoft/lexical_units) [![Stories in Ready](https://badge.waffle.io/fractalsoft/lexical_units.png)](http://waffle.io/fractalsoft/lexical_units)
+
 [![endorse](https://api.coderwall.com/torrocus/endorsecount.png)](https://coderwall.com/torrocus)
 
 Lexical unit is a single word, a part of a word, or a chain of words that forms the basic elements of a language's lexicon.
@@ -22,6 +23,7 @@ Or install it yourself as:
 ```ruby
 LexicalUnits::words(text)
 LexicalUnits::sentences(text)
+LexicalUnits::words_without_digits(text)
 ```
 
 You can include methods into String class:

data/lexical_units.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.authors       = ["Aleksander Malaszkiewicz"]
   spec.email         = ["info@fractalsoft.org"]
   spec.summary       = %q{Split text into lexical units}
-  spec.homepage      = ""
+  spec.homepage      = "https://github.com/fractalsoft/lexical_units"
   spec.license       = "MIT"
 
   spec.files         = `git ls-files`.split($/)

data/lib/lexical_units/sentences.rb

@@ -1,20 +1,23 @@
 # encoding: utf-8
+
+# Part of split into sentences
 module LexicalUnits
   # Split text into sentences
   #
   #   self.words("Lorem, ipsum. Dolor?") #=> ["Lorem, ipsum.", "Dolor?"]
   #   self.words("Lorem! Ipsum dolor?") #=> ["Lorem!", "Ipsum dolor?"]
   def self.sentences(text)
-    separators = LexicalUnits::sentence_separators
+    separators = LexicalUnits.sentence_separators
     regexp = Regexp.new("[^#{separators}]+[#{separators}]{1,3}")
     text.scan(regexp).map(&:strip)
   end
 
   private
+
     def self.sentence_separators
       [
         '\.', '\?', '\!',
-        "‽"
+        '‽'
       ].join
     end
 end

data/lib/lexical_units/string.rb

@@ -1,12 +1,17 @@
 # encoding: utf-8
 module LexicalUnits
+  # Use lexical units inside String class
   module String
     def words
-      LexicalUnits::words(self)
+      LexicalUnits.words(self)
     end
 
     def sentences
-      LexicalUnits::sentences(self)
+      LexicalUnits.sentences(self)
+    end
+
+    def words_without_digits
+      LexicalUnits.words_without_digits(self)
     end
   end
 end

data/lib/lexical_units/syllables.rb

@@ -1,4 +1,6 @@
 # encoding: utf-8
+
+#
 module LexicalUnits
   def self.syllables(text)
   end

data/lib/lexical_units/version.rb

@@ -1,3 +1,4 @@
+# Gem version
 module LexicalUnits
-  VERSION = "0.0.7"
+  VERSION = '0.0.8'
 end

data/lib/lexical_units/words.rb

@@ -1,27 +1,28 @@
 # encoding: utf-8
+
+# Part of split into words
 module LexicalUnits
   # Split text into words
   #
-  #   self.words("Lorem ipsum dolor sit") #=> ["Lorem", "ipsum", "dolor", "sit"]
+  #   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(" ")
+    regexp = Regexp.new("[#{LexicalUnits.separators}]")
+    text.gsub(regexp, ' ').split(' ')
   end
 
   private
+
     def self.separators
       [
-        '\,', '\:', '\;',
-        '\.', '\?', '\!',
-        '\/',
-        '\(', '\)',
-        '\[', '\]',
-        '\>', '\<',
-        '\{', '\}',
+        '\,', '\:', '\;', '\.', '\?', '\!', '\/',
+        '\(', '\)', '\[', '\]', '\>', '\<', '\{', '\}',
         '\|', '\~',
         "\¿", "\¡",
-        '\=', '\"'
+        '\=', '\"',
+        "\»", "\«",
+        '\@', '\#',
+        '\+'
       ].join
     end
 end

data/lib/lexical_units/words_without_digits.rb

@@ -1,16 +1,21 @@
 # encoding: utf-8
+
+# Part of split into words, but excluding digits
 module LexicalUnits
   # Split text into words without digits
   #
   #   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) }
+    LexicalUnits.words(text).delete_if { |word| numeric?(word) }
   end
 
   private
+
     def self.numeric?(value)
       return true if value =~ /^\d+$/
-      true if Float(value) rescue false
+      true if Float(value)
+    rescue
+      false
     end
 end

data/lib/lexical_units.rb

@@ -1,9 +1,6 @@
-require "lexical_units/words"
-require "lexical_units/sentences"
-require "lexical_units/syllables"
-require "lexical_units/words_without_digits"
-require "lexical_units/string"
-require "lexical_units/version"
-
-module LexicalUnits
-end
+require 'lexical_units/words'
+require 'lexical_units/sentences'
+require 'lexical_units/syllables'
+require 'lexical_units/words_without_digits'
+require 'lexical_units/string'
+require 'lexical_units/version'

data/spec/lexical_units/sentences_spec.rb

@@ -2,48 +2,49 @@
 require 'spec_helper'
 
 describe LexicalUnits do
-  context ".sentences" do
-    it "splits text into sentences" do
-      text = %q{Lorem ipsum dolor sit amet, consectetur adipiscing elit.
+  context '.sentences' do
+    it 'splits text into sentences' do
+      text = %q{Lorem ipsum dolor sit amet. Consectetur adipiscing elit.
         Fusce ut lacinia lorem. Nullam a sem quam. Duis faucibus tortor in.}
       array = [
-        "Lorem ipsum dolor sit amet, consectetur adipiscing elit.",
-        "Fusce ut lacinia lorem.",
-        "Nullam a sem quam.",
-        "Duis faucibus tortor in."
+        'Lorem ipsum dolor sit amet.',
+        'Consectetur adipiscing elit.',
+        'Fusce ut lacinia lorem.',
+        'Nullam a sem quam.',
+        'Duis faucibus tortor in.'
       ]
 
       subject.sentences(text).should eq(array)
     end
 
-    it "splits text with question mark and exclamation mark into sentences" do
-      text = "Lorem ipsum dolor! Sit amet? Consectetur adipiscing elit."
+    it 'splits text with question mark and exclamation mark into sentences' do
+      text = 'Lorem ipsum dolor! Sit amet? Consectetur adipiscing elit.'
       array = [
-        "Lorem ipsum dolor!",
-        "Sit amet?",
-        "Consectetur adipiscing elit."
+        'Lorem ipsum dolor!',
+        'Sit amet?',
+        'Consectetur adipiscing elit.'
       ]
 
       subject.sentences(text).should eq(array)
     end
 
-    it "splits text with ellipsis into sentences" do
-      text = "Lorem ipsum dolor, sit amet... Consectetur adipiscing elit."
+    it 'splits text with ellipsis into sentences' do
+      text = 'Lorem ipsum dolor, sit amet... Consectetur adipiscing elit.'
       array = [
-        "Lorem ipsum dolor, sit amet...",
-        "Consectetur adipiscing elit."
+        'Lorem ipsum dolor, sit amet...',
+        'Consectetur adipiscing elit.'
       ]
 
       subject.sentences(text).should eq(array)
     end
 
-    it "splits text with interrobangs into sentences" do
+    it 'splits text with interrobangs into sentences' do
       text = "Say what‽ She's pregnant‽ Who is the father‽‽‽ Really?"
       array = [
-        "Say what‽",
+        'Say what‽',
         "She's pregnant‽",
-        "Who is the father‽‽‽",
-        "Really?"
+        'Who is the father‽‽‽',
+        'Really?'
       ]
 
       subject.sentences(text).should eq(array)

data/spec/lexical_units/string_spec.rb

@@ -2,12 +2,13 @@
 require 'spec_helper'
 
 describe LexicalUnits::String do
+  # Testing class
   class String
     include LexicalUnits::String
   end
 
-  context "#words" do
-    it "splits String into words" do
+  context '#words' do
+    it 'splits String into words' do
       array = %w(Lorem ipsum dolor sit amet)
       string = array.join(' ')
 
@@ -15,12 +16,21 @@ describe LexicalUnits::String do
     end
   end
 
-  context "#sentences" do
-    it "splits String into sentences" do
-      array = ["Lorem ipsum!", "Dolor sit?", "Amet."]
+  context '#sentences' do
+    it 'splits String into sentences' do
+      array = ['Lorem ipsum!', 'Dolor sit?', 'Amet.']
       string = array.join
 
       string.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)
+      string = 'Lorem 1 ipsum 23 dolor 456 sit 7890 amet'
+
+      string.words_without_digits.should eq(array)
+    end
+  end
 end

data/spec/lexical_units/syllables_spec.rb

@@ -2,7 +2,6 @@
 require 'spec_helper'
 
 describe LexicalUnits do
-  context ".syllables" do
-    let(:klass) { LexicalUnits }
+  context '.syllables' do
   end
 end

data/spec/lexical_units/words_spec.rb

@@ -2,102 +2,126 @@
 require 'spec_helper'
 
 describe LexicalUnits do
-  context ".words" do
+  context '.words' do
     before do
       @array = %w(Lorem ipsum dolor sit amet)
     end
 
-    it "splits text with whitespaces into words" do
-      text = "Lorem ipsum dolor sit amet"
+    it 'splits text with whitespaces into words' do
+      text = 'Lorem ipsum dolor sit amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with comma, colon and semicolon into words" do
-      text = "Lorem ipsum,dolor:sit;amet"
+    it 'splits text with comma, colon and semicolon into words' do
+      text = 'Lorem ipsum,dolor:sit;amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with dot, question mark and exclamation mark into words" do
-      text = "Lorem ipsum.dolor?sit!amet"
+    it 'splits text with dot, question mark and exclamation mark into words' do
+      text = 'Lorem ipsum.dolor?sit!amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits other text with whitespaces, comma and dot into words" do
-      text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit."
+    it 'splits other text with whitespaces, comma and dot into words' do
+      text = 'Lorem ipsum dolor sit amet, consectetur adipiscing elit.'
       array = %w(Lorem ipsum dolor sit amet consectetur adipiscing elit)
 
       subject.words(text).should eq(array)
     end
 
-    it "no splits text with hyphen into words" do
-      text = "Lorem ipsum dolor-sit amet"
+    it 'no splits text with hyphen into words' do
+      text = 'Lorem ipsum dolor-sit amet'
       array = %w(Lorem ipsum dolor-sit amet)
 
       subject.words(text).should eq(array)
     end
 
-    it "splits text with slash into words" do
-      text = "Lorem ipsum dolor sit/amet"
+    it 'splits text with slash into words' do
+      text = 'Lorem ipsum dolor sit/amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with round brackets into words" do
-      text = "Lorem ipsum(dolor sit)amet"
+    it 'splits text with round brackets into words' do
+      text = 'Lorem ipsum(dolor sit)amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with square brackets into words" do
-      text = "Lorem ipsum dolor[sit]amet"
+    it 'splits text with square brackets into words' do
+      text = 'Lorem ipsum dolor[sit]amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with pointy brackets into words" do
-      text = "Lorem<ipsum dolor sit>amet"
+    it 'splits text with pointy brackets into words' do
+      text = 'Lorem<ipsum dolor sit>amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with braces into words" do
-      text = "Lorem ipsum{dolor}sit amet"
+    it 'splits text with braces into words' do
+      text = 'Lorem ipsum{dolor}sit amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with vertical bar into words" do
-      text = "Lorem ipsum|dolor sit amet"
+    it 'splits text with vertical bar into words' do
+      text = 'Lorem ipsum|dolor sit amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with tilde into words" do
-      text = "Lorem ipsum dolor~sit amet"
+    it 'splits text with tilde into words' do
+      text = 'Lorem ipsum dolor~sit amet'
 
       subject.words(text).should eq(@array)
     end
 
     # Spanish
-    it "splits text with inverted question and exclamation marks into words" do
-      text = "Lorem¿ipsum?dolor¡sit!amet"
+    it 'splits text with inverted question and exclamation marks into words' do
+      text = 'Lorem¿ipsum?dolor¡sit!amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with equals sign into words" do
-      text = "Lorem ipsum=dolor sit amet"
+    it 'splits text with equals sign into words' do
+      text = 'Lorem ipsum=dolor sit amet'
 
       subject.words(text).should eq(@array)
     end
 
-    it "splits text with typewriter double quotes into words" do
+    it 'splits text with typewriter double quotes into words' do
       text = %Q(Lorem"ipsum dolor"sit amet)
 
       subject.words(text).should eq(@array)
     end
+
+    it 'split text with non-English quotation marks into words' do
+      text = %Q(Lorem»ipsum dolor«sit amet)
+
+      subject.words(text).should eq(@array)
+    end
+
+    it "split text with 'at sign' (@) into words" do
+      text = %Q(Lorem@ipsum dolor sit amet)
+
+      subject.words(text).should eq(@array)
+    end
+
+    it "split text with 'number sign (#) into words" do
+      text = %Q(Lorem ipsum#dolor sit amet)
+
+      subject.words(text).should eq(@array)
+    end
+
+    it 'split text with plus (+) into words' do
+      text = %Q(Lorem+ipsum dolor+sit amet)
+
+      subject.words(text).should eq(@array)
+    end
   end
 end

data/spec/lexical_units/words_without_digits_spec.rb

@@ -2,13 +2,13 @@
 require 'spec_helper'
 
 describe LexicalUnits do
-  context ".words_without_digits" do
+  context '.words_without_digits' do
     [
-      {text: "Lorem ipsum 12345", array: %w(Lorem ipsum)},
-      {text: "dolor 98765 sit amet.", array: %w(dolor sit amet)}
+      { text: 'Lorem ipsum 12345', array: %w(Lorem ipsum) },
+      { text: 'dolor 98765 sit amet.', array: %w(dolor sit amet) }
     ].each do |hash|
       text, array = hash.values
-      it "splits text into words without digits" do
+      it 'splits text into words without digits' do
         subject.words_without_digits(text).should eq(array)
       end
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: lexical_units
 version: !ruby/object:Gem::Version
-  version: 0.0.7
+  version: 0.0.8
 platform: ruby
 authors:
 - Aleksander Malaszkiewicz
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-16 00:00:00.000000000 Z
+date: 2013-08-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -70,7 +70,7 @@ files:
 - spec/lexical_units/words_spec.rb
 - spec/lexical_units/words_without_digits_spec.rb
 - spec/spec_helper.rb
-homepage: ''
+homepage: https://github.com/fractalsoft/lexical_units
 licenses:
 - MIT
 metadata: {}