Splitting Kongsberg water column data into .all and .wcd files.

I goofed up on my previous post about this, I'm learning blog formatting as I go and apparently my code got a little funky when I cut and paste it into the blog.  Here's another attempt that should be safer (I think).

Have fun!!

 #!/usr/bin/env python2.6  
   
 import os  
 import struct  
 import time  
 import sys  
   
 file_count=0  
 debug=False  
   
 dir="split"  
   
 for filename in sys.argv:  
   
   file_count += 1  
   
   if (file_count == 1):  
     # I'm too lazy to parse command line args so just skipping over the   
     # script name (which is arg zero in the list)  
     continue  
   
   file = open(filename, 'rb')  
   filesize = os.path.getsize(filename)  
   
   # What is the path to the input file without the filename?  
   filepath=os.path.dirname(filename)  
   fileprefix=os.path.basename(filename)  
   if debug or True:  
     print "Doing file",filename  
     print "Got file path",filepath  
     print "Got file basename",fileprefix  
   
   # Join the file's directory path with the usual output subdirectory name  
   outdir=os.path.join(filepath,dir)  
   
   if not os.path.exists(outdir):  
     os.makedirs(outdir)  
   
   split_allname = os.path.join(outdir, fileprefix)  
   split_wcdname = split_allname.replace(".all",".wcd")  
   
   if debug or True:  
     print filename, "will split into", split_allname, split_wcdname  
   
   if not os.path.exists(split_allname):  
     split_allfile = open(split_allname,"wb")  
     split_wcdfile = open(split_wcdname,"wb")  
   else:  
     print "Skipping", filename, "since it's already split!"  
     file.close()  
     continue  
   
   last_percent = 0  
   while True:  
   
     # Make sure we don't try to read beyond the EOF  
     if (file.tell() + 6 > filesize):  
       break  
   
     line = file.read(6)  
   
     header = struct.unpack("<IBB",line)  
   
     rawlength=line[0:3]  
     length = header[0]  
     stx = header[1]  
     id = header[2]  
   
     if (stx != 2):  
       if debug:  
         print 'STX not found, trying next datagram at position',file.tell()-5  
       file.seek(-5,1)  
       continue  
   
     if debug:  
       print 'STX found, going to try for ETX now'  
   
     # Make sure we don't try to read beyond the EOF  
     if (file.tell() + (length-5) > filesize):  
       file.seek(-5,1)  
       continue  
   
     file.seek(length-5,1)  
   
     # Make sure we don't try to read beyond the EOF  
     if (file.tell() + 3 > filesize):  
       break  
   
     line = file.read(3)  
     footer = struct.unpack("<BH",line)  
     etx = footer[0]  
     checksum = footer[1]  
   
     if (etx != 3):  
       if debug:  
         print 'ETX not found, trying next datagram at position',file.tell()-(length+3)  
       file.seek(-(length+3),1)  
       continue  
   
     # Rewind to very beginning of the datagram, including the length field  
     file.seek(-(length+4),1)  
     data = file.read(length+4)  
   
     if debug:  
       print "Got id", id, "and length", length  
   
     if (id == 0x49 or id == 0x69 or id == 0x52 or id == 0x55):  
       # Stuff for both files  
       split_allfile.write(data)  
       split_wcdfile.write(data)  
     elif (id == 0x6B):  
       # Just for the watercolumn file  
       split_wcdfile.write(data)  
     else:  
       # Everything else goes into the raw file  
       split_allfile.write(data)  
   
     percent=int(100.0 * file.tell()/filesize)  
   
     if (percent%5 == 0 and percent != last_percent):  
       print percent, "% done, ALL:",split_allfile.tell()," WCD:",split_wcdfile.tell()  
       last_percent = percent  
   
     if file.tell() >= filesize:  
       break  
   
   file.close()  
   split_allfile.close()  
   split_wcdfile.close()  
   
 print 'All done!'