Rough outline of assembler.

assembler-outline.py

# Your program should probably end with this function, and call
# it to do everything.

def main():
  inf = sys.argv[1]
  outf = sys.argv[2]
  
  los = readFileToListOfLines(inf)
  # Print here to see if things look right
  losclean = stripEveryLine(los)
  # etc.
  
  # At this point, lolclean should contain an array of 
  # strings, with newlines and spaces at the beginning/end
  # removed.
  
  # Remove all of the comments from the file.
  los = removeComments(losclean)
  
  # Assuming that you have a symbol table (dictionary) that
  # is global...
  
  # Find all of the jump label locations, and load them
  # into the symbol table. You should remove them as you
  # go, because they don't count as lines of code. Return
  # a new list-of-strings that doesn't contain labels.
  los = findLabelLocations(los)
  
  # Find all of the variables, and add them to the symbol
  # table, assigning locations as you go. This will
  # not modify anything in your code, so you don't have to
  # return anything.
  assignVariableRAMLocations(los)
  
  # Remove jump labels
  # Emit microcode for each line in the file. This is 
  # where you would substitute jump and variable values
  # from the lookup table (dictionary) into the output.
  emitMicrocode(lol, outf)
  
  # So, for example, the line
  # @8
  # will become
  # 
  # 0000000000000100
  # 
  # and the simulator will load each sixteen digit string
  # and uncompile it, so you can see if you have things correct.
  
# This calls "main" as the last thing in the script.
main()