The following command line python application will take a file of any size and split it into X number of components. This same tool will combine those file back into the original. The only limitation on file size is system memory - if you split a 10GB file into two peices, you'd better have 5GB of RAM to read each component!
import sys, os, glob
def usage():
print """
****************************************************
PY_FILESPLITTER
Copyright: PSE Entertainment Corp 2009 (all rights reserved)
This utility will split and/or concatenate any file you wish.
Usage: py_file_splitter [action] [filename] [num_files]
Options:
action - combine or split
filename - the full file name
num_files - if the action is split, this is the number of files to create
Output:
The split files will be created and numbered in the same folder as the original.
example: py_file_splitter split blah.jpg 3
result: blah.jpg.1, blah.jpg.2, blah.jpg.3
example: py_file_splitter combine blah.jpg
result: blah.jpg
NOTE: this usage will appear with any errors - check your spelling!
*******************************************************
"""
sys.exit()
def splitter(file_name,split_num):
print
print "Splitting File %s Into %s Chunks" % (file_name, split_num)
try:
file = open(file_name,'rb')
except:
print "no such file..."
usage()
size = os.stat(file_name).st_size
file_chunks,remainder = divmod(size,split_num)[0],divmod(size,split_num)[1]
print "%s is %s bytes. Each chunk will be about %s bytes." % (file_name,size,file_chunks)
print "...Do you have enough memory to do this?..."
question = raw_input("""Do you wish to continue? (y/n): """)
if question.lower == 'n':
sys.exit()
for i in range(split_num):
if i < split_num-1:
chunk = file.read(file_chunks)
outfile = open("%s.%s" % (file_name,i),'wb')
outfile.write(chunk)
print "Created File: %s.%s" % (file_name,i)
outfile.close()
else:
chunk = file.read(file_chunks+remainder)
outfile = open("%s.%s" % (file_name,i),'wb')
outfile.write(chunk)
print "Created File: %s.%s" % (file_name,i)
outfile.close()
print "Finished"
file.close()
def concatenate(file_name):
print "\nCombining..."
print "File: %s" % (file_name)
files = glob.glob('%s.[0-9]*' % file_name)
if len(files) < 1:
print "no such file..."
usage()
#################Sort the glob in a nice human way
import re
def tryint(s):
try:
return int(s)
except:
return s
def alphanum_key(s):
""" Turn a string into a list of string and number chunks.
"z23a" -> ["z", 23, "a"]
"""
return [ tryint(c) for c in re.split('([0-9]+)', s) ]
def sort_nicely(l):
""" Sort the given list in the way that humans expect.
"""
l.sort(key=alphanum_key)
sort_nicely(files)
#################
print files
outfile = open(file_name,'wb')
for x in files:
blah = open(x,'rb')
data = blah.read()
blah.close()
outfile.write(data)
print "Added File: %s" % x
outfile.close()
print "Completed..."
if __name__ == '__main__':
try:
action = sys.argv[1].lower()
except: usage()
if action == "combine":
try:
file_name = sys.argv[2]
except: usage()
concatenate(file_name)
sys.exit()
if action == "split":
try:
file_name = sys.argv[2]
split_num = int(sys.argv[3])
except: usage()
splitter(file_name,split_num)
sys.exit()
else: usage()
