compare_files.py

#!/usr/bin/env python

# Usage
#  compare_files.py. <file_to_compare_1>   <file_to_compare_2>

# ALGO 
# 1. Check if both the files have same md5 checksum
# 2. If the checksum is same - means files are exactly same ; no need to check line by line
# 3. If the checksum doesnt match; we load the contents fo file to string
# 4. replace all the blank spaces and new line char with nothing. Baiscally get all text in a string.
# 5. Compare these strings if they are equal.


import hashlib    # For using MD5 hashing
import sys        # For reading arguments passed to file

def checksum(file_name):
    """ Function to check the checksum of the file supplied"""
    md5 = hashlib.md5()
    md5.update(open(file_name).read())
    return md5.hexdigest()

def is_contents_same(file1, file2):
    """checks if the files have same checksum"""
    return checksum(file1) == checksum(file2)

def get_contents_of_file(file_name):
    """ for getting the contents of file to string """
    with open(file_name, 'r') as myfile:
        # The line below removes the empty characters
        # and the new line characters from the string read from the file
    	data = myfile.read().strip().replace('\n', '').replace(' ', '')
    return data

def deep_compare(file1, file2):
    """ for comparing contents of file in depth """
	return get_contents_of_file(file1) == get_contents_of_file(file2)

def compare_files(file1 , file2):
    """ function to compare 2 input files for exactly same text contents"""
    if not is_contents_same('foo.txt', 'bar.txt'):
        print 'The hash of the files are not the same!, lets check the content in depth'
        if deep_compare('foo.txt', 'bar.txt'):
    	    print 'The file contents are really equal'
    	    return True
        else:
            print 'the file contents are different'
            return False
    else:
	   print "files are equal"
	   return True

if __name__ == "__main__":
    """ Calling the file with its name, not using as library"""
    file1 = sys.argv[1]
    file2 = sys.argv[2]
    compare_files(file1 , file2)