markov_uuid 0.0.5 → 0.0.6

data/lib/markov_uuid.rb

@@ -2,5 +2,5 @@ require_relative './markov_uuid/chain'
 require_relative './markov_uuid/storage'
 
 module MarkovUuid
-  VERSION = "0.0.5"
+  VERSION = "0.0.6"
 end

data/lib/markov_uuid/chain.rb

@@ -4,26 +4,24 @@ module MarkovUuid
     attr_reader :words
 
     class << self
-      def from_file(f)
-        new(strip_punctuation File.read(f))
+      def from_string string
+        from_word_list(strip_punctuation string)
       end
 
-      def strip_punctuation l
-        l.gsub(/[[:punct:]]/," ").gsub!('  ', ' ').split " "
+      def from_word_list words
+        new.tap { |i| i.add words }
       end
-    end
 
-    def initialize words
-      @words = words
+      def strip_punctuation l
+        l.gsub(/[[:punct:]]/," ").gsub('  ', ' ').split " "
+      end
     end
 
-    def new_key(key, word)
-      return SEPARATOR if word == "\n"
-
-      word or key
+    def initialize h={}
+      replace h
     end
 
-    def add
+    def add words
       key = SEPARATOR
 
       words.each do |word|
@@ -33,7 +31,16 @@ module MarkovUuid
       end
     end
 
-    def to_words length = 100
+    def new_key(key, word)
+      return SEPARATOR if word == "\n"
+
+      word or key
+    end
+
+    #note these are not by any means guaranteed to be unique
+    #dependent on uuid length and corpus size
+    #maybe maintain uniqueness elsewhere by regenerating unless unique
+    def uuid length = 100
       key = keys.sample
       word = ""
 
@@ -46,8 +53,11 @@ module MarkovUuid
       format result
     end
 
-    def format words, i=32
-      words.join("-")[0..i.to_i].gsub(/\A\w+-/,'').gsub(/-$/,"").gsub(/-\w+$/,"")
+    def format result, i=32
+      result.join("-")[0..i.to_i].
+        gsub(/\A\w+-/ , "").
+        gsub(/-$/     , "").
+        gsub(/-\w+$/  , "")
     end
   end
 end

data/lib/markov_uuid/storage.rb

@@ -2,21 +2,53 @@ require "yaml"
 require "fileutils"
 module MarkovUuid
   class Storage
-    def initialize filename
-      @filename = filename
+    attr_accessor :data, :cache_file, :input_file
+
+    #note these are not by any means guaranteed to be unique
+    #dependent on uuid length and corpus size
+    #maybe maintain uniqueness elsewhere by regenerating unless unique
+    def uuid
+      chain.uuid
+    end
+
+    def chain
+      @chain ||= MarkovUuid::Chain.new data
+    end
+
+    def initialize input_file, cache_file
+      @input_file, @cache_file =  input_file, cache_file
+
+      preload_data
+    end
+
+    #for testing
+    def file_klass
+      File
     end
 
-    attr_accessor :data, :filename
+    private
 
     def save
-      File.open(filename, "w"){|f| YAML.dump(@data, f) }
+      file_klass.open(cache_file, "w"){|f| YAML.dump(@data, f) }
     end
 
-    def load
-      FileUtils.touch filename
-      File.open(filename) do |f|
+    def open
+      file_klass.open(cache_file) do |f|
         @data = YAML.load f
       end
+
+      @data
+    end
+
+    def data
+      @data ||= MarkovUuid::Chain.from_string file_klass.read(input_file)
+    end
+
+    def preload_data
+      unless open
+        data
+        save
+      end
     end
   end
 end

data/spec/markov_spec.rb

@@ -3,7 +3,7 @@ require File.expand_path('spec/spec_helper')
 require './lib/markov_uuid'
 
 describe MarkovUuid::Chain do
-  let(:file) do
+  let(:string) do
     <<-CONTENTS.gsub(/^\s*/, "")
       CHAPTER I. Down the Rabbit-Hole
 
@@ -18,7 +18,8 @@ describe MarkovUuid::Chain do
 
   specify do
     s = "これは Some text with, random -?! Punctuation in"
-    MarkovUuid::Chain.strip_punctuation(s).should == %w(これは Some text with random Punctuation in)
+    MarkovUuid::Chain.strip_punctuation(s).should ==
+      %w(これは Some text with random Punctuation in)
   end
 
   let(:words) do
@@ -33,20 +34,19 @@ describe MarkovUuid::Chain do
   end
 
   specify do
-    MarkovUuid::Chain.strip_punctuation(file).should == words
+    MarkovUuid::Chain.strip_punctuation(string).should == words
   end
 
   context 'from file' do
-    before do
-      File.stub(:read).and_return file
-    end
-
     specify do
-      chain = MarkovUuid::Chain.from_file ''
-      chain.to_words.split("-").each do |word|
+      chain = MarkovUuid::Chain.from_string string
+      #not sure how to test the randomness right now
+      #so we can just check it's generating a list of words joined by '-'
+      chain.uuid.should =~ /\A(\w+\-)+\w+\z/
+
+      chain.uuid.split("-").each do |word|
         words.should include word
       end
-
     end
   end
 end

data/spec/storage_spec.rb

@@ -0,0 +1,48 @@
+require File.expand_path('spec/spec_helper')
+
+describe MarkovUuid::Storage do
+  let(:file_klass) { mock 'File Class mock', read: file_contents }
+
+  let(:file_contents) { "Down the rabbit hole" }
+
+  before do
+    MarkovUuid::Storage.any_instance.stub(:file_klass).and_return file_klass
+  end
+
+  context "empty cache file" do
+    before do
+      file_klass.stub(:open).and_yield ''
+      YAML.stub(:dump).and_return true
+    end
+
+    specify do
+      storage = MarkovUuid::Storage.new 'input_filename.txt', 'cache_filename.txt'
+
+      storage.chain.should == {
+        MarkovUuid::Chain::SEPARATOR => ["Down"],
+        "Down"                       => ["the"],
+        "rabbit"                     => ["hole"],
+        "the"                        => ["rabbit"]
+      }
+    end
+
+  end
+
+  context "cached file" do
+    before do
+      yaml = <<-YAML.gsub(/^\s{6}/, "")
+      ---
+      a:
+      - b
+      - c
+      YAML
+
+      file_klass.stub(:open).and_yield yaml
+    end
+
+    specify do
+      storage = MarkovUuid::Storage.new 'input_filename', 'cache_filename'
+      storage.chain.should == {"a" => ["b", "c"]}
+    end
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: markov_uuid
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-10-02 00:00:00.000000000 Z
+date: 2012-10-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -69,6 +69,7 @@ files:
 - markov_uuid.gemspec
 - spec/markov_spec.rb
 - spec/spec_helper.rb
+- spec/storage_spec.rb
 - storage.rb
 homepage: http://github.com/markburns/markov_uuid
 licenses: []
@@ -98,4 +99,5 @@ summary: Easily generate random English-like UUIDs (or any other language) that
 test_files:
 - spec/markov_spec.rb
 - spec/spec_helper.rb
+- spec/storage_spec.rb
 has_rdoc: