analyzer.rb in twexicon-0.1.8

- old
+ new

@@ -11,11 +11,11 @@
   def run
     quit = false
     until quit
       @input = nil
       @int = ""
-      puts "What would you like to do next? For options, type 'help'."
+      puts "\nWhat would you like to do next? For options, type 'help'."
       until is_valid?
         @input = gets.strip.gsub(/\W/, "").downcase
       end
       case input
       when "help", "h"
@@ -67,18 +67,20 @@
       end
       puts "\n@#{username} said: #{tweets[int.to_i].keys[0]}"
     end
   end
 
-  # 38 words from https://en.wikipedia.org/wiki/Most_common_words_in_English –– Left out some common yet still interesting ones (People, Good, Think, Work, First, One, Two, Want, New, Give, Know)
+  # Words from https://en.wikipedia.org/wiki/Most_common_words_in_English –– Left out some common yet still interesting ones (People, Good, Think, Work, First, One, Two, Want, New, Give, Know)
   COMMON_WORDS = ["A", "About", "An", "And", "Are", "As", "At", "Be", "Been", "But", "By", "For", "From", "Get", "Had", "Has", "Have", "In", "Into", "Is", "It", "It's", "Its", "Just", "Not", "Of", "On", "Or", "Say", "So", "Some", "That", "The", "There", "These", "This", "Those", "To", "Up", "With", "I", "My", "Your", "They", "He", "You", "Do", "His", "We", "Her", "She", "Will", "All", "Would", "Their", "What", "Out", "If", "Who", "Which", "Go", "Me", "When", "Make", "Can", "Time", "No", "Him", "Take", "Year", "Could", "Them", "See", "Other", "Than", "Then", "Now", "Look", "Only", "Come", "Over", "Also", "Back", "After", "Use", "How", "Our", "Well", "Way", "Even", "Because", "Any", "Day", "Most", "Us",
     # other additions
-    "Wouldn't", "Couldn't", "Shouldn't", "Mustn't", "Would've", "Could've", "Should've", "Must've", "Hadn't", "Wasn't", "Weren't", "Ain't", "Aint", "Here", "Seem", "Seems", "That's", "Took", "Much", "More", "You're", "We're", "We've", "I've", "I'm",
+    "Wouldn't", "Couldn't", "Shouldn't", "Mustn't", "Would've", "Could've", "Should've", "Must've", "Hadn't", "Wasn't", "Weren't", "Ain't", "Aint", "Here", "Seem", "Seems", "That's", "Took", "Much", "More", "You're", "We're", "We've", "I've", "I'm", "Don't", "Got", "Soon",
     # contraction endings until I fix the parsing error
     "Re", "Ll", "Ve",
     # Letters until I fix the contraction parsing error
-    "B", "C", "D", "E", "F", "G", "H", "J", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z"]
+    "B", "C", "D", "E", "F", "G", "H", "J", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "U", "V", "W", "X", "Y", "Z",
+    # Common words in other languages that *aren't* uncommon English words (so, "Con" doesn't count)
+    "En"]
 
   def get_words
     words = {}
     word_array = []
     tweets.each_value do |v| # Count up instances of each word
@@ -91,18 +93,20 @@
         end
       end
     end
     words.each do |w, n| # Create strings for the words that occur >1 times
       case n
-      when 1..9 then word_array << "0#{n}x #{w}"
-      when 10..99 then word_array << "#{n}x #{w}"
+      when 1..9 then word_array << "000#{n}x #{w}"
+      when 10..99 then word_array << "00#{n}x #{w}"
+      when 100..999 then word_array << "0#{n}x #{w}"
+      when 1000..9999 then word_array << "#{n}x #{w}"
       end
     end
     if word_array.empty?
       puts "\nIt appears that @#{username} is not much of a talker."
     else
       puts "\n@#{username}'s current favorite word(s):"
-      puts word_array.sort.reverse.take(10)
+      puts word_array.sort.reverse.each{|w| w.sub!(/^0+/, "")}.take(10)
     end
   end
 
   def get_shouts
     collection = []