de_dupe.rb

gistfile1.rb

# de_dupe.rb
# Sean (2009-08-25)
# reads line of data from parent.txt
# which is a super set of child.txt
# and outputs all lines of parent
# file not found in the child file

# WORD OF CAUTION: MAKE SURE THAT
# BOTH PARENT AND CHILD TEXT FILES
# ARE CONSISTENT WITH HAVING OR NOT
# HAVING AN ENDLINE, IF ONE HAS "\n"
# AND THE OTHER DOESN'T - YOU'RE F'D

file_A = File.new("parent.txt", "r+")
file_C = File.new("out.txt", "r+")

#iterate thru parent one line at a time
while (line_A = file_A.gets)

  #set found flag to zero
  @found = 0
  
  #open child file. we'll open and close
  #this file for each line in parent
  file_B = File.new("child.txt", "r+")
  
  while (line_B = file_B.gets)
    if (line_A == line_B)
      @found = 1 #set flag to one if found
      break
    end #if else
  end #while
  
  #close it, will open next iteration
  file_B.close  
    
  if (@found == 1)
    next 
  else
    #this only happens if line exists in
    #parent file, but nowhere in child
    file_C.puts "#{line_A}"
  end #if else
  
end #while

file_A.close
file_C.close