Pull request for Shakespeare Analyzer challenge

.gitignore

@@ -0,0 +1,2 @@
+text.xml
+macbeth.xml

.rvmrc

@@ -0,0 +1,2 @@
+rvm use ruby-1.9.3-p327
+rvm gemset use rails3213

bin/shakespeare_analyzer

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+load "lib/shakespeare_analyzer.rb"
+
+if ARGV[0].nil? then
+  puts "usage: shakespeare_analyzer <input-file>" 
+  exit 1
+end
+
+analyzer = ShakespeareAnalyzer.new(ARGV[0])
+analyzer.analyze
+analyzer.list_by_speaker_count

lib/shakespeare_analyzer.rb

@@ -0,0 +1,73 @@
+require 'pp'
+require 'nokogiri'
+require 'net/http'
+require 'uri'
+
+class ShakespeareAnalyzer
+  def initialize(file)
+    @file = file
+    @persona = {}
+  end
+
+  def analyze
+    #TODO: Probably better name of 'parse'
+    @file = checked_file_for_open
+    doc = Nokogiri::XML(open(@file)) { |config| config.noerror }
+    get_persona(doc)
+    analyze_speeches(doc)
+  end
+
+  def get_persona(doc)
+    doc.css('PERSONA').each do |p|
+      pname = p.children.text.tr('"','')
+      @persona[pname] = 0
+    end
+  end
+
+  def analyze_speeches(doc)
+    doc.css('SPEECH').each do |speech|
+      speech.css('SPEAKER').each do |speaker|
+        get_speaker_lines(speaker, speech)
+      end
+    end
+  end
+
+  def get_speaker_lines(speaker, speech)
+    ## Sometimes the speaker is 'ALL', but who that is depends on who's on stage...
+    ## Ignoring this for now
+    ## Turns out there are speakers without @persona!
+    speaker_name = speaker.children.text.tr('"','')
+    @persona[speaker_name] = 0 if @persona[speaker_name].nil?
+    speech.css('LINE').each do |line|
+      @persona[speaker_name] += 1
+    end
+  end
+
+  def list_by_speaker_count
+    sorted_output = (@persona.sort_by {|k,v| v}).reverse
+    sorted_output.each do |a| 
+      name = (a[0].split(' ').map {|n| n.capitalize }).join(" ")
+      puts "#{a[1]} #{name}" 
+    end
+  end
+
+  def checked_file_for_open
+    return @file if File.file?(@file)
+    return get_http_file
+  end
+
+  def get_http_file
+    uri = URI(@file)
+    raise "Unreadable file" if uri.scheme != "http"
+    @file = 'play.xml'
+    Net::HTTP.start(uri.host) do |http|
+      resp = http.get(uri.path)
+      raise "Unreadable file" unless (resp.code.to_i >= 200 && resp.code.to_i <= 299)
+      open(@file, 'wb') do |file|
+        file.write(resp.body)
+      end
+    end
+    @file
+  end
+
+end

macbeth.output

@@ -0,0 +1,55 @@
+719 Macbeth
+265 Lady Macbeth
+212 Malcolm
+180 Macduff
+135 Ross
+113 Banquo
+74 Lennox
+70 Duncan
+62 First Witch
+46 Porter
+45 Doctor
+41 Lady Macduff
+39 Hecate
+35 Sergeant
+30 Siward
+30 First Murderer
+27 Third Witch
+27 Second Witch
+23 Gentlewoman
+23 Messenger
+21 Lord
+21 Angus
+20 Son
+15 Second Murderer
+12 Menteith
+11 Caithness
+11 Old Man
+10 Donalbain
+8 Third Murderer
+7 Young Siward
+5 Third Apparition
+5 Seyton
+5 Servant
+4 Second Apparition
+3 Lords
+2 Fleance
+2 Both Murderers
+2 First Apparition
+1 Attendant
+1 Soldiers
+0 Lords, Gentlemen, Officers, Soldiers, Murderers, Attendants, And Messengers.
+0 Young Siward, His Son.
+0 Siward, Earl Of Northumberland, General Of The English Forces.
+0 Fleance, Son To Banquo.
+0 Boy, Son To Macduff.
+0 An English Doctor.
+0 A Scotch Doctor.
+0 A Soldier.
+0 A Porter.
+0 An Old Man.
+0 Gentlewoman Attending On Lady Macbeth.
+0 Three Witches.
+0 Apparitions.
+0 Seyton, An Officer Attending On Macbeth.
+0 Duncan, King Of Scotland.