Sage Sandbox

Back to SAGE & cryptology

Helper functions

Conversion from int or long to raw string and back is discussed on the Python bug tracking list but since the problem is not yet solved, let's see how to make our own helper functions in a clean and fast way: (measures with %timeit of ipython)

###############################  long2string  ########################################
def long2string(i):
	l=[]
	while i:
		l[0:0]=chr(i&0xff)
		i=i>>8
	return ''.join(l)
long2string(123456789012345678901234)
#46 µs per loop
long2string(1234567890123456789012345)
#51.8 µs per loop
###################################################################################
def long2string(i):
	l=[]
	while i:
		l.append(chr(i&0xff))
		i=i>>8
	return ''.join(l[::-1])
long2string(123456789012345678901234)
#15.1 µs per loop
long2string(1234567890123456789012345)
#16.4 µs per loop
###################################################################################
def long2string(i): 
        return ''.join([chr(i>>j & 0xFF) for j in range(int(math.log(i,2)//8)<<3,-1,-8)])
long2string(123456789012345678901234)
#15.5 µs per loop
long2string(1234567890123456789012345)
#16.7 µs per loop
###################################################################################
import math
def long2string(i):
	return binascii.unhexlify('%0*x' % (int(math.ceil(math.log(i,2)/8)*2) , i))
long2string(123456789012345678901234)
#4.77 µs per loop
long2string(1234567890123456789012345)
#4.83 µs per loop
###################################################################################
def long2string(i):
	return binascii.unhexlify('%0*x' % (len(hex(i)) & -2 , i)).lstrip('\x00')
long2string(123456789012345678901234)
#3.64 µs per loop
long2string(1234567890123456789012345)
#3.78 µs per loop
###################################################################################
binascii.unhexlify('%0*x' % (32 , 123456789012345678901234))
#2.06 µs per loop
binascii.unhexlify('%0*x' % (32 , 1234567890123456789012345))
#2.01 µs per loop
#Ok if you want fixed length buffer, e.g. 32 bytes
###################################################################################
def long2string(i):
    s=hex(i)[2:].rstrip('L')
    if len(s) % 2:
        s='0'+s
    return binascii.unhexlify(s)
long2string(123456789012345678901234)
#2.88 µs per loop
long2string(1234567890123456789012345)
#3.22 µs per loop
###################################################################################
def long2string(i):
    s='0'+hex(long(i))[2:-1]
    return binascii.unhexlify(s[len(s) % 2:])
long2string(123456789012345678901234)
#3.04 µs per loop
long2string(1234567890123456789012345)
#3.03 µs per loop
###################################################################################
def long2string(i):
    s=hex(long(i))[2:-1]
    if len(s) % 2:
        s='0'+s
    return binascii.unhexlify(s)
long2string(123456789012345678901234)
#2.75 µs per loop
long2string(1234567890123456789012345)
#3.06 µs per loop
###################################################################################
#If we are sure our argument is a long we can remove the cast in the 2 previous codes:
def long2string(i):
    s='0'+hex(i)[2:-1]
    return binascii.unhexlify(s[len(s) % 2:])
long2string(123456789012345678901234)
#2.66 µs per loop
long2string(1234567890123456789012345)
#2.62 µs per loop
###################################################################################
def long2string(i):
    s=hex(i)[2:-1]
    if len(s) % 2:
        s='0'+s
    return binascii.unhexlify(s)
long2string(123456789012345678901234)
#2.42 µs per loop
long2string(1234567890123456789012345)
#2.76 µs per loop
###################################################################################
# There is still room ;-)
binascii.unhexlify('1a249b1f10a06c96aff2')
#990 ns per loop
###################################################################################
###############################  string2long  ########################################
def string2long(s):
	i=0
	for c in s:
		i=(i<<8)+ord(c)
	return i
string2long('\x01\x05n\x0f6\xa6D=\xe2\xdfy')
#8.91 µs per loop
###################################################################################
int('\x01\x05n\x0f6\xa6D=\xe2\xdfy'.encode('hex'),16)
#3.15 µs per loop
###################################################################################
int(binascii.hexlify('\x01\x05n\x0f6\xa6D=\xe2\xdfy'),16)
#1.64 µs per loop
###################################################################################
long(binascii.hexlify('\x01\x05n\x0f6\xa6D=\xe2\xdfy'),16)
#1.38 µs per loop

Learning Python

Some code to make some padding functions available. The code is used as a way to learn python, so it contains things that don't make sense or could be done better.

{{#fileanchor: helper.py}}

from __future__ import division #http://www.python.org/dev/peps/pep-0238/
import math

def roundUp (n, p):
	"""Round an integer up to the nearest multiple

	A given integer n will be round up to the nearest multiple of p

	Example:
	>>> roundUp(13,8)
	    16
	"""
	return int(math.ceil(n/p)*p)
	#return (n+p)/p*p

Download code: [{{#filelink: helper.py}} helper.py]

{{#fileanchor: padding.py}}

from binascii import hexlify
import random

import sys
import getopt

try:
	import helper
except ImportError:
	print 'ERROR: helper.py should be placed in the same location as padding.py'
	raise ImportError

class BlockOperator:
	"""Class for BlockOperator

	Only holds a variable blocksize. Class only exist for testing purpose.
	"""

	def __init__(self, bs=8):
		self.blockSize = bs

class Padding(BlockOperator):
	"""Class for padding functions

	Inherits from the BlockOperator class

	padding info here: http://en.wikipedia.org/wiki/Padding_(cryptography)

	Example:
		from padding import *
		padder = Padding()
		padded = padder.pad('test','bitpadding)
		padder.unpad(padded,'bitpadding)

	After changing the source:
		del(padder)
		del(Padding)
		from padding import *
	"""		

	def pad (self, toPad, algo):
		return getattr(self,"_Padding__%s" % algo)(toPad) #private function has to be accessed by it's public name...

	def unpad (self, padded, algo):
		#there is no switch statement in python
		#discussion with alternatives: http://simonwillison.net/2004/May/7/switch/
		if algo == 'bitPadding':
			return self.__bitPadding_unpad(padded)
		elif algo == 'zerosPadding':
			return self.__zerosPadding_unpad(padded)
		elif algo == 'PKCS7':
			return self.__PKCS7_unpad(padded)
		elif algo == 'ANSI_X923':
			return self.__ANSI_X923_unpad(padded)
		elif algo == 'ISO_10126':
			return self.__ISO_10126_unpad(padded)
		raise NotImplementedError()

	def __bitPadding (self, toPad ):
		padded = toPad + '\x80' + '\x00'*(self.blockSize - len(toPad)%self.blockSize -1)
		return padded

	def __bitPadding_unpad (self, padded ):
		if padded.rstrip('\x00')[-1] == '\x80':
			return padded.rstrip('\x80' + '\x00')
		else:
			return padded

	def __zerosPadding (self, toPad ):
		totalLength = helper.roundUp(len(toPad),self.blockSize)
		return toPad.ljust(totalLength,'\x00')
		

	def __zerosPadding_unpad (self, padded ):
		return padded.rstrip('\x00')		

	def __PKCS7 (self, toPad ):
		"""Pad a binary string

		Input:
			toPad: binary string to be padded
			self.blockSize: the padded result will be a multiple of the self.blockSize(default=8)
		Output:
			return a binary string
		"""

		pattern = self.blockSize - len(toPad)%self.blockSize
	  	# 0 -> zero padding for numeric values; 2 -> print "String to be padded: %r" % toPadlength modifier; x -> hex output
		# string formatting options: http://docs.python.org/lib/typesseq-strings.html
		code = "%02x" % pattern
		patternstring = ('\\x' + code).decode('string_escape')			
		amount = self.blockSize - len(toPad)%self.blockSize
		pad = ''.join(patternstring for x in range(0,amount))
		return toPad + pad

	def __PKCS7_unpad (self, padded ):
		pattern = padded[-1]
		length = int(hexlify(pattern),16)
		flag = 0
		for i in range(1,length + 1):
			if padded[-i] <> pattern:
				flag = 1
		if flag == 0:
			unpadded = padded[:-length]
		else:
			unpadded = padded
			print 'error: padding pattern not recognized'
		return unpadded

	def __ANSI_X923 (self, toPad ):
		bytesToPad = self.blockSize - len(toPad)%self.blockSize
		trail = "%02x" % bytesToPad
		pattern = '\x00'*(bytesToPad -1) + ('\\x' + trail).decode('string_escape')
		return toPad + pattern

	def __ANSI_X923_unpad (self, padded ):
		length = int(hexlify(padded[-1]),16)
		#check if the bytes to be removed are all zero
		if padded.count('\x00',-length,-1) == length - 1:
			return padded[:-length]
		else:
			unpadded = padded
			print 'error: padding pattern not recognized %s' % padded.count('\x00',-length,-1)
		return unpadded

	def __ISO_10126 (self, toPad):
		bytesToPad = self.blockSize - len(toPad)%self.blockSize
		pattern1 = ''.join(("\\x%02x" % random.randint(0,255)).decode('string_escape') for x in range(0,bytesToPad-1))
		pattern2 = ("\\x%02x" % bytesToPad).decode('string_escape')
		return toPad + pattern1 + pattern2

	def __ISO_10126_unpad (self, padded):
		return padded[0:len(padded)-int(hexlify(padded[-1]),16)]

def main():
	try:
        	opts, args = getopt.getopt(sys.argv[1:], "")
   	except getopt.GetoptError, err:
   		print str(err)
        	sys.exit(2)
	if len(args) > 1:
		sys.exit("Program takes maximum 1 argument")
	try:
		testbench(args[0])
	except IndexError:
		testbench()

def testbench(toPad='test'):
	testbench = ('bitPadding','zerosPadding','PKCS7','ANSI_X923','ISO_10126')
	padder = Padding()
	print "String to be padded: %r, with length %i\n" % (toPad,len(toPad))
	for test in testbench:
		padded = padder.pad(toPad,'%s'%test)
		print "padded: %r" % padded
		unpadded = padder.unpad(padded,'%s'%test)
		print "unpadded: %r" % unpadded
		if unpadded == toPad:
			print "%s test OK!\n" % test
		else:
			print "%s test not OK!\n" % test


if __name__ == "__main__":
	main()

Download code: [{{#filelink: padding.py}} padding.py]