2-Make_Duplex_PDFs

#!/usr/bin/python2
import pygtk
pygtk.require('2.0')
import gtk
import sys, os, logging, re, subprocess

class filegroup:
    count = 0
    prefix = ""

#Simple alert script from:
#http://www.ibm.com/developerworks/linux/library/l-script-linux-desktop-2/index.html
def alert(msg):
    """Show a dialog with a simple message."""
    dialog = gtk.MessageDialog()
    dialog.set_markup(msg)
    dialog.run()

#cool logging class from
#http://www.electricmonk.nl/log/2011/08/14/redirect-stdout-and-stderr-to-a-logger-in-python/
class StreamToLogger(object):
   """
   Fake file-like stream object that redirects writes to a logger instance.
   """
   def __init__(self, logger, log_level=logging.INFO):
      self.logger = logger
      self.log_level = log_level
      self.linebuf = ''
 
   def write(self, buf):
      for line in buf.rstrip().splitlines():
         self.logger.log(self.log_level, line.rstrip())

def loggerSetup():
   logging.basicConfig(
      level=logging.DEBUG,
      format='%(asctime)s:%(levelname)s:%(name)s:%(message)s',
      filename="out.log",
      filemode='a'
   )

   stdout_logger = logging.getLogger('STDOUT')
   sl = StreamToLogger(stdout_logger, logging.INFO)
   sys.stdout = sl
    
   stderr_logger = logging.getLogger('STDERR')
   sl = StreamToLogger(stderr_logger, logging.ERROR)
   sys.stderr = sl

def main():

   loggerSetup()

   mydir = os.getenv('NAUTILUS_SCRIPT_CURRENT_URI')
   files = os.getenv('NAUTILUS_SCRIPT_SELECTED_FILE_PATHS')
   myfiles = files.split()
   print myfiles
   filevers = {}


   for file in myfiles:
      #get rid of single quotes if they exist (Thunar workaround) 
      if file.startswith("'") and file.endswith("'"):
          file = file[1:-1]       
      basename = os.path.basename(file)
      dirname = os.path.dirname(file)

      m = re.match('(?P<prefix>rotate-scan|scan)(?P<time>\d+)-(?P<num>\d+)\.pdf', basename)
      if (m != None):
         prefix = m.group('prefix')
         time = int(m.group('time'))
         num = int(m.group('num'))
         #all this does is count up how many files we have for a specific time
         filevers[time] = filevers.setdefault(time, filegroup())
         filevers[time].count += 1
         filevers[time].prefix = prefix
      else:
         alert('At least one of the files you have chosen does not have the\n\
                expected filename: scanxxxxxxxxxx-x.pdf')
         print('exit')
         sys.exit()

   groups = filevers.keys()  #this should return two values, the time from filegroup 1 and the time from filegroup 2
   groups.sort()             #put them in order from low --> high

   # --------------------- ERROR CHECKING ---------------------------
   if (len(groups) == 2):
      #Check that the size of the groups is the same
      if (filevers[groups[0]].count != filevers[groups[1]].count):
         alert('Different sized scan groups: %d vs %d' %(filevers[groups[0]].count, filevers[groups[1]].count))
         sys.exit()
   else:
      alert('You have selected more or less than two scan groups.')
      sys.exit()

   # --------------------- MATCH THEM UP ---------------------------

   num = filevers[groups[0]].count  #The number of files to process
   oddpages = 1
   evenpages = num

   for i in range(num):
      firstfile = dirname+"/%s%d-%d.pdf" %(filevers[groups[0]].prefix, groups[0], oddpages)
      secondfile = dirname+"/%s%d-%d.pdf" %(filevers[groups[1]].prefix, groups[1], evenpages)
      finalfile = dirname+"/dplx-scan%d-%02d-%02d.pdf" %(groups[0], oddpages, evenpages)
      print firstfile, secondfile, finalfile
      os.system("pdftk %s %s cat output %s" %(firstfile, secondfile, finalfile))
      oddpages += 1
      evenpages -= 1

   alert('Created duplex scans for %d documents' %(num))

if __name__ == "__main__":
    main()