added .gitignore

.gitignore

@@ -0,0 +1,3 @@
+test-data/*
+master.csv
+bins.csv

sorter.rb

@@ -47,9 +47,14 @@ end
 # output - a hash containing all of our output
 #This method converts the output hash to JSON and writes it to "output.json"
 def write_output_json (output, filename)
-  outfile = File.open(filename,'w')
+  begin
-  outfile.write(output.to_json)
+    outfile = File.open(filename,'w')
-  outfile.close
+    outfile.write(output.to_json)
+    outfile.close
+  rescue
+    pp output
+    abort
+  end
 end
 
 def write_output_csv (output, filename)
@@ -147,8 +152,13 @@ def process_file (file_name, binfile, type)
     sections = text.lines("Date and time:", chomp: true) #sections is an arrary of each date section from the text
     sections.delete_at(0) #we can ignore the first chunk of text
     sections.each do |chunk|
-      timestamp = chunk.lines.delete_if {|line| line == "\r\n"}[0] #pulling out the timestamp
+      begin
-      timestamp.tr!('/','-').tr!(':','').tr!(' ','_') #remove slashes and colons from timestamp, replaces spaces with underscores
+        timestamp = chunk.lines.delete_if {|line| line == "\r\n"}[0] #pulling out the timestamp
+        timestamp.tr!('/','-').tr!(':','').tr!(' ','_') #remove slashes and colons from timestamp, replaces spaces with unserscores
+      rescue
+        pp timestamp
+        abort
+      end
       timestamp.strip!
       output = Hash.new #Creating the output storage object
       outfile = file_name + '_' + timestamp
@@ -161,10 +171,7 @@ def process_file (file_name, binfile, type)
         output[key] = Hash.new
         output[key][:words] = bin_counter(bins[bin_number], text)
         output[key][:total] = count_total(output[key])
-        output[key][:frequency] = 0
+        output[key][:frequency] = output[key][:total].to_f / output[:total_words].to_f
-        #output[key][:frequency] = output[key][:total].to_f / output[:total_words].to_f if output[[:total_words] != 0
-        freq = output[key][:total].to_f / output[:total_words].to_f
-        output[key][:frequency] = freq.to_s
       end
       write_output_json(output,outfile + '-out.json')
       write_output_csv(output,outfile + '-out.csv')
@@ -179,14 +186,10 @@ end
 #
 #This method will process all .txt files in the supplied directory
 def process_dir(dir_name, binfile, type)
-  threads = []
   Dir.glob(dir_name + '*.txt') do |file_name|
-    threads << Thread.new do
+    puts "Processing " + file_name
-      puts "Processing " + file_name
+    process_file(file_name, binfile, type)
-      process_file(file_name, binfile, type)
-    end
   end
-  threads.each { |thr| thr.join }
 end
 
 def generate_master_output(dir_name, binfile)