Merge pull request #1 from sd/master

Patches from Sebastian Delmont for Unicode-compliant regexps and Gemfile

Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+ruby "1.9.3"
+
+gem "twitter"
+gem "typhoeus"
+gem "iron_worker_ng"

README.md

@@ -11,9 +11,10 @@ A simple and hackish ruby script for pseudorandomly posting to a _ebooks account
 5. Sign into dev.twitter.com with the same credentials
 6. Create an application for your _ebooks account (generate the credentials)
 7. Create a file named twitter_init.rb in this directory with the OAuth credentials and the source account you want to use for seeding the markov process
-8. Upload to iron.io with `iron_worker upload ebook`
-9. Run it with `iron_worker queue ebook` a few times
-10. You can schedule it now to run regularly using the scheduler. I'd suggest once every 53 minutes or so.
+8. Run "bundle install"
+9. Upload to iron.io with `bundle exec iron_worker upload ebook`
+10. Run it with `bundle exec iron_worker queue ebook` a few times
+11. You can schedule it now to run regularly using the scheduler. I'd suggest once every 53 minutes or so.
 
 ## Configuring
 

ebook.rb

@@ -60,7 +60,7 @@ else
   source_tweets.each do |twt|
     text = twt
 
-    if text !~ /[\.\"\'\?\!]/
+    if text !~ /\p{Punct}/
       text += "."
     end
     
@@ -72,9 +72,9 @@ else
   10.times do
     tweet = markov.generate_sentence
 
-    if rand(3) == 0 && tweet =~ /(in|to|from|for|with|by|our|of|your|around|under|beyond)\s\w+$/ 
+    if rand(3) == 0 && tweet =~ /(in|to|from|for|with|by|our|of|your|around|under|beyond)\p{Space}\w+$/ 
       puts "Losing last word randomly"
-      tweet.gsub(/\s\w+.$/, '')   # randomly losing the last word sometimes like horse_ebooks
+      tweet.gsub(/\p{Space}\p{Word}+.$/, '')   # randomly losing the last word sometimes like horse_ebooks
     end
 
     if tweet.length < 40 && rand(5) == 0
@@ -86,8 +86,8 @@ else
       puts "MARKOV: #{tweet}"
     end
 
-    tweet_letters = tweet.gsub(/\W/, '')
-    break if !tweet.nil? && tweet.length < 110 && !source_tweets.any? {|t| t.gsub(/\W/, '') =~ /#{tweet_letters}/ }
+    tweet_letters = tweet.gsub(/\P{Word}/, '')
+    break if !tweet.nil? && tweet.length < 110 && !source_tweets.any? {|t| t.gsub(/\P{Word}/, '') =~ /#{tweet_letters}/ }
   end
   
   if params["tweet"]

markov.rb

@@ -10,9 +10,9 @@ class MarkovChainer
 
    def add_text(text)
      # make sure each paragraph ends with some sentence terminator
-     text.gsub!(/\n\s*\n/m, ".")
+     text.gsub!(/[\r\n]+\p{Space}*[\r\n]+/m, ".")
      text << "."
-     seps = /([.!?;])/
+     seps = /(\p{Punct})/
      sentence = ""
      text.split(seps).each { |p|
        if seps =~ p
@@ -37,7 +37,7 @@ class MarkovChainer
 
 private
    def add_sentence(str, terminator)
-     words = str.scan(/[\w'’\-]+/)
+     words = str.scan(/[\p{Word}'’\-]+/)
      return unless words.size > order # ignore short sentences
      words << terminator
      buf = []