make it actually work

lib/maxixe.rb

@@ -106,15 +106,15 @@ def self.generate_and_dump(n, output, *files)
     end
 
     def self.generate_training_data(n, *files)
-      result = n.inject({}){|r, c_n| r[c_n] = Hash.new{0}; r} 
+      result = n.inject({}){|r, c_n| r[c_n.to_s] = Hash.new{0}; r} 
 
       files.each do |file|
         input = open(file)
         input.each_line do |line|
           n.each do |c_n|
             n_grams = line.each_char.each_cons(c_n).map(&:join).to_a
             n_grams.each do |n_gram|
-              result[c_n][n_gram] += 1
+              result[c_n.to_s][n_gram] += 1
             end
           end
         end

spec/segmenter/segmenter_spec.rb

@@ -7,7 +7,7 @@
       @sentence = "1234567"
       @two_grams = @sentence.each_char.each_cons(2).to_a
       @three_grams = @sentence.each_char.each_cons(3).to_a
-      @segmenter = Maxixe::Segmenter.new({"2" => "", "3" => ""}, nil)
+      @segmenter = Maxixe::Segmenter.new({})
     end
 
     it "should give all non_straddling n_grams for a given position" do
@@ -54,4 +54,14 @@
       @segmenter.average_votes(votes).should == [0.5, 0.5, 0.5, 0.5]
     end
   end
+
+  describe "Segmenting Text" do
+    before(:each) do 
+      @segmenter = Maxixe::Segmenter.new({"2"=>{"AB"=>2, "BC"=>2, "CD"=>1, "DE"=>1, "EF"=>1, "FG"=>1, "G\n"=>1, "CX"=>1, "XY"=>1, "YZ"=>1, "Z\n"=>1}, "3"=>{"ABC"=>2, "BCD"=>1, "CDE"=>1, "DEF"=>1, "EFG"=>1, "FG\n"=>1, "BCX"=>1, "CXY"=>1, "XYZ"=>1, "YZ\n"=>1}})
+    end
+
+    it "should be able to segment text" do
+      @segmenter.segment("ABCDE").should == "ABC DE"
+    end
+  end
 end

spec/trainer/trainer_spec.rb

@@ -6,7 +6,7 @@
 
     pwd = File.dirname(__FILE__)
 
-    Maxixe::Trainer.generate_training_data([2,3], File.join(pwd, "first_file"), File.join(pwd,"second_file")).should == {2=>{"AB"=>2, "BC"=>2, "CD"=>1, "DE"=>1, "EF"=>1, "FG"=>1, "G\n"=>1, "CX"=>1, "XY"=>1, "YZ"=>1, "Z\n"=>1}, 3=>{"ABC"=>2, "BCD"=>1, "CDE"=>1, "DEF"=>1, "EFG"=>1, "FG\n"=>1, "BCX"=>1, "CXY"=>1, "XYZ"=>1, "YZ\n"=>1}}
+    Maxixe::Trainer.generate_training_data([2,3], File.join(pwd, "first_file"), File.join(pwd,"second_file")).should == {"2"=>{"AB"=>2, "BC"=>2, "CD"=>1, "DE"=>1, "EF"=>1, "FG"=>1, "G\n"=>1, "CX"=>1, "XY"=>1, "YZ"=>1, "Z\n"=>1}, "3"=>{"ABC"=>2, "BCD"=>1, "CDE"=>1, "DEF"=>1, "EFG"=>1, "FG\n"=>1, "BCX"=>1, "CXY"=>1, "XYZ"=>1, "YZ\n"=>1}}
 
   end