marky_markov 0.3.4 → 0.3.5

data/MIT-LICENSE

@@ -0,0 +1,20 @@
+Copyright 2014 Matt Furden
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+Software), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED AS IS, WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/lib/marky_markov.rb

@@ -4,12 +4,12 @@
 require_relative 'marky_markov/persistent_dictionary'
 require_relative 'marky_markov/markov_sentence_generator'
 
-# @version = 0.3.4
+# @version = 0.3.5
 # @author Matt Furden
 # Module containing TemporaryDictionary and Dictionary for creation of
 # Markov Chain Dictionaries and generating sentences from those dictionaries.
 module MarkyMarkov
-  VERSION = '0.3.4'
+  VERSION = '0.3.5'
 
   class TemporaryDictionary
     # Create a new Temporary Markov Chain Dictionary and sentence generator for use.
@@ -150,8 +150,8 @@ module MarkyMarkov
     # Alternatively, pass in a MarkyMarkov::Dictionary object in
     # directly and it will delete that objects dictionary from disk.
     #
-    # @note To ensure that someone doesn't pass in something that shouldn't 
-    # be deleted by accident, the filetype .mmd is added to the end of the 
+    # @note To ensure that someone doesn't pass in something that shouldn't
+    # be deleted by accident, the filetype .mmd is added to the end of the
     # supplied argument, so do not include the extension when calling the method.
     #
     # @example Delete the dictionary located at '~/markov_dictionary.mmd'

data/lib/marky_markov/markov_dictionary.rb

@@ -3,7 +3,7 @@ class MarkovDictionary # :nodoc:
   attr_reader :dictionary, :depth
   def initialize(depth=2) @dictionary = {}
     @depth = depth
-    @split_words = /([.?!])|[\s]+/
+    @split_words = /(\.\s+)|(\.$)|([?!])|[\s]+/
     @split_sentence = /(?<=[.!?])\s+/
   end
 
@@ -39,7 +39,14 @@ class MarkovDictionary # :nodoc:
   # @example Add a string
   #   parse_source("Hi, how are you doing?", false)
   def parse_source(source, file=true)
-    contents = file ? open_source(source) : contents = source.split(@split_sentence)
+    if !source.nil?
+      contents = file ? open_source(source) : contents = source.split(@split_sentence)
+    else
+      contents = []
+    end
+    if( !contents.empty? && !['.', '!', '?'].include?( contents[-1].strip[-1] ) )
+      contents[-1] = contents[-1].strip + '.'
+    end
     contents.map! {|sentence| sentence.gsub(/["()]/,"")}
     contents.each do |sentence|
       sentence.split(@split_words).each_cons(@depth+1) do |words|

data/lib/marky_markov/markov_sentence_generator.rb

@@ -15,6 +15,10 @@ end
 # @private
 NULL_OBJECT = NullObject.new # :nodoc:
 
+# @private
+class EmptyDictionaryError < Exception # :nodoc:
+end
+
 # @private
 class MarkovSentenceGenerator # :nodoc:
   def initialize(dictionary)
@@ -22,7 +26,7 @@ class MarkovSentenceGenerator # :nodoc:
     @depth = @dictionary.depth
   end
 
-  # Returns a random word vsjfia picking a random key from the dictionary.
+  # Returns a random word via picking a random key from the dictionary.
   # In the case of the TwoWordDictionary, it returns two words to ensure
   # that the sentence will have a valid two word string to pick the next
   # word from.
@@ -61,7 +65,7 @@ class MarkovSentenceGenerator # :nodoc:
   end
 
   def punctuation?(word)
-    word =~ /[.!?]/
+    ( word =~ /[!?]/ || word == '.' )
   end
 
   # Generates a sentence of (wordcount) length using the weighted_random function.
@@ -69,12 +73,16 @@ class MarkovSentenceGenerator # :nodoc:
   # @param [Int] wordcount The number of words you want the generated string to contain.
   # @return [String] the words, hopefully forming sentences generated.
   def generate(wordcount)
+    if @dictionary.dictionary.empty?
+      raise EmptyDictionaryError.new("The dictionary is empty! Parse a source file/string!")
+    end
     sentence = []
     sentence.concat(random_capitalized_word)
     (wordcount-1).times do
       word = weighted_random(sentence.last(@depth))
       if punctuation?(word)
         sentence[-1] = sentence.last.dup << word
+        sentence.concat(random_capitalized_word)
       elsif word.nil?
         sentence.concat(random_capitalized_word)
       else
@@ -89,7 +97,10 @@ class MarkovSentenceGenerator # :nodoc:
   #
   # @param [Int] sentencecount The number of sentences you want the generated string to contain.
   # @return [String] the sentence(s) generated.
-  def generate_sentence(sentencecount) 
+  def generate_sentence(sentencecount)
+    if @dictionary.dictionary.empty?
+      raise EmptyDictionaryError.new("The dictionary is empty! Parse a source file/string!")
+    end
     sentence = []
     # Find out how many actual keys are in the dictionary.
     key_count = @dictionary.dictionary.keys.length

data/lib/marky_markov/persistent_dictionary.rb

@@ -1,4 +1,4 @@
-require 'ox'
+require 'msgpack'
 require_relative 'markov_dictionary'
 
 # @private
@@ -30,9 +30,9 @@ class PersistentDictionary < MarkovDictionary # :nodoc:
   # otherwise it creates an empty hash.
   def open_dictionary
     if File.exists?(@dictionarylocation)
-      file = File.new(@dictionarylocation, 'r').read
+      file = File.new(@dictionarylocation, 'rb').read
         @depth = file[0].to_i
-        @dictionary = Ox.parse_obj(file[1..-1])
+        @dictionary = MessagePack.unpack(file[1..-1])
     else
       @dictionary = {}
     end
@@ -41,8 +41,8 @@ class PersistentDictionary < MarkovDictionary # :nodoc:
   # Saves the PersistentDictionary objects @dictionary hash 
   # to disk in JSON format.
   def save_dictionary!
-    packed = Ox.dump(@dictionary)
-    File.open(@dictionarylocation, 'w') do |f|
+    packed = @dictionary.to_msgpack
+    File.open(@dictionarylocation, 'wb') do |f|
       f.write @depth.to_s + packed
     end
     true

data/marky_markov.gemspec

@@ -13,8 +13,8 @@ Gem::Specification.new do |s|
   ## If your rubyforge_project name is different, then edit it and comment out
   ## the sub! line in the Rakefile
   s.name              = 'marky_markov'
-  s.version           = '0.3.4'
-  s.date              = '2012-02-27'
+  s.version           = '0.3.5'
+  s.date              = '2014-03-17'
   s.rubyforge_project = 'marky_markov'
 
   ## Make sure your summary is short. The description may be as long
@@ -49,7 +49,7 @@ Gem::Specification.new do |s|
 
   ## List your runtime dependencies here. Runtime dependencies are those
   ## that are needed for an end user to actually USE your code.
-  s.add_dependency('ox', "~> 1.4")
+  s.add_dependency('msgpack')
 
   ## List your development dependencies here. Development dependencies are
   ## those that are only needed during development
@@ -60,6 +60,7 @@ Gem::Specification.new do |s|
   ## THE MANIFEST COMMENTS, they are used as delimiters by the task.
   # = MANIFEST =
   s.files = %w[
+    MIT-LICENSE
     README.md
     bin/marky_markov
     lib/marky_markov.rb

data/spec/marky_markov/marky_markov_spec.rb

@@ -1,65 +1,131 @@
 require 'spec_helper'
+require 'marky_markov'
 
 describe MarkyMarkov do
-  before(:each) do
-    @textsource = "spec/data/test.txt"
-    @onedictcompare = { ["The"] => ["cat"],
-                        ["cat"] => ["likes"],
-                        ["likes"] => ["pie"],
-                        ["pie"] => ["and"],
-                        ["and"] => ["chainsaws"],
-                        ["chainsaws"] => ["!"]}
-    @twodictcompare = {["The", "cat"] => ["likes"],
-                       ["and", "chainsaws"] => ["!"],
-                       ["cat", "likes"] => ["pie"],
-                       ["likes", "pie"] => ["and"],
-                       ["pie", "and"] => ["chainsaws"]}
-  end
+
+  let(:onedictcompare) {
+    { ["The"] => ["cat"],
+      ["cat"] => ["likes"],
+      ["likes"] => ["pie"],
+      ["pie"] => ["and"],
+      ["and"] => ["chainsaws"],
+      ["chainsaws"] => ["!"]}
+  }
+  let(:twodictcompare) {
+    {["The", "cat"] => ["likes"],
+     ["and", "chainsaws"] => ["!"],
+     ["cat", "likes"] => ["pie"],
+     ["likes", "pie"] => ["and"],
+     ["pie", "and"] => ["chainsaws"]}
+  }
 
   context "TemporaryDictionary" do
-    before(:each) do
-      @dictionary = MarkyMarkov::TemporaryDictionary.new
-    end
+    let(:dictionary) { MarkyMarkov::TemporaryDictionary.new }
 
     it "should be able to parse a string" do
-     @dictionary.parse_string "The cat likes pie and chainsaws!"
-      @dictionary.dictionary.should eql(@twodictcompare)
+      dictionary.parse_string "The cat likes pie and chainsaws!"
+      dictionary.dictionary.should eql(twodictcompare)
     end
 
     it "should generate the right number of sentences" do
-      @dictionary.parse_string "Hey man. How are you doing? Let's get pie!"
-      sentence = @dictionary.generate_5_sentences
+      dictionary.parse_string "Hey man. How are you doing? Let's get pie!"
+      sentence = dictionary.generate_5_sentences
       sentence.should have(5).scan(/[.?!]/)
     end
 
     it "should create the right number of words" do
-      @dictionary.parse_string "Hey man. How are you doing? Let's get pie!"
-      sentence = @dictionary.generate_10_words
+      dictionary.parse_string "Hey man. How are you doing? Let's get pie!"
+      sentence = dictionary.generate_10_words
       sentence.split.should have(10).words
     end
+
+    it "should not choke on parsing empty string" do
+      lambda {
+        dictionary.parse_string ""
+      }.should_not raise_error
+    end
+
+    it "should not choke on parsing nil" do
+      lambda {
+        dictionary.parse_string nil
+      }.should_not raise_error
+    end
+    it "should raise EmptyDictionaryError if you try to generate from empty dictionary" do
+      lambda {
+        dictionary.parse_string nil
+        dictionary.generate_1_sentences
+      }.should raise_error(EmptyDictionaryError)
+    end
+
+    context "if the sentence doesn't finish with a punctuation" do
+      # null objects?
+      it "should not have trailing spaces in a row" do
+        dictionary.parse_string "I have a pen somewhere "
+        dictionary.generate_4_sentences.should_not match( /  / )
+      end
+    end
+
+    context "parsing web addresses" do
+      it "should treat 'example.net' as single word" do
+        dictionary.parse_string "i am at example.net now."
+        dictionary.dictionary.values.should include( ['example.net'] )
+      end
+      it "should not break up 'example.net'" do
+        dictionary.parse_string "i am at example.net now."
+        dictionary.dictionary.values.should_not include( ['example'] )
+      end
+    end
+
+    context "handling 'http://...'" do
+      # previously, anything containing '.' was considered punctuation
+      it "should generate sentence with space before 'http//:...'" do
+        dictionary.parse_string "I'm viewing some stuff which is at http://example.net now."
+        dictionary.generate_4_sentences.should_not match( /\whttp/ )
+      end
+    end
+    context "when using key depth of 1 word" do
+      let(:depth1dict) { MarkyMarkov::TemporaryDictionary.new(1) }
+      it "should not raise 'negative array size'" do
+        depth1dict.parse_string "short text. with many. full. stops."
+        lambda {
+          depth1dict.generate_15_words
+        }.should_not raise_error
+      end
+    end
   end
 
   context "PersistentDictionary" do
-    before do
-      @dictionary = MarkyMarkov::Dictionary.new("spec/data/temptextdict")
-      @dictionary.parse_file "spec/data/test.txt"
+    let!(:dictionary) do |dict|
+      MarkyMarkov::Dictionary.new("spec/data/temptextdict").tap do |d|
+        d.parse_file "spec/data/test.txt"
+      end
     end
 
     it "should be able to save a dictionary" do
-      @dictionary.save_dictionary!.should eql(true)
+      dictionary.save_dictionary!.should eql(true)
     end
 
     it "should be able to load an existing dictionary" do
       otherdict = MarkyMarkov::Dictionary.new("spec/data/textdictcompare")
-      @dictionary.dictionary.should eql(otherdict.dictionary)
+      dictionary.dictionary.should eql(otherdict.dictionary)
     end
 
     it "should load the saved dictionary" do
-      @dictionary.dictionary.should include(@twodictcompare)
+      dictionary.dictionary.should include(twodictcompare)
+    end
+
+    it "should have the correct failure when dictionary is empty: words" do
+      emptydict = MarkyMarkov::Dictionary.new("spec/data/nothing")
+      expect {emptydict.generate_10_words}.to raise_error(EmptyDictionaryError)
+    end
+
+    it "should have the correct failure when dictionary is empty: sentences" do
+      emptydict = MarkyMarkov::Dictionary.new("spec/data/nothing")
+      expect {emptydict.generate_10_sentences}.to raise_error(EmptyDictionaryError)
     end
 
     after do
-      PersistentDictionary.delete_dictionary!(@dictionary)
+      PersistentDictionary.delete_dictionary!(dictionary)
     end
   end
 end

data/spec/spec_helper.rb

@@ -1,2 +1 @@
-require_relative '../lib/marky_markov'
 require 'rspec/autorun'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: marky_markov
 version: !ruby/object:Gem::Version
-  version: 0.3.4
+  version: 0.3.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,19 +9,24 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-02-27 00:00:00.000000000 Z
+date: 2014-03-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: ox
-  requirement: &70229846255560 !ruby/object:Gem::Requirement
+  name: msgpack
+  requirement: !ruby/object:Gem::Requirement
     none: false
     requirements:
-    - - ~>
+    - - ! '>='
       - !ruby/object:Gem::Version
-        version: '1.4'
+        version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *70229846255560
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 description: ! "MarkyMarkov makes it easy to generate simply Markov Chains based upon
   input from\n  either a source file or a string. While usable as a module in your
   code it can also be called on\n  from the command line and piped into like a standard
@@ -33,6 +38,7 @@ extensions: []
 extra_rdoc_files:
 - README.md
 files:
+- MIT-LICENSE
 - README.md
 - bin/marky_markov
 - lib/marky_markov.rb
@@ -66,7 +72,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: marky_markov
-rubygems_version: 1.8.16
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 2
 summary: Simple Markov Chain generation available in the command-line