Dave Short

import os # for files and paths
import sys # for command line arguments
 
def matches (path, fileName, filter):
    """Returns true if the given file matches the filter or is a directory, false otherwise.
    path - the directory the file resides in
    fileName - the name of the file in question
    filter - Either None to indicate no filtering should be applied, or a list of allowed extensions."""
    if filter == None:
        return True
    else:
        # if it's a directory, return true
        if (os.path.isdir(os.path.join(path, fileName))):
            return True
        ext = fileName.split(".").pop()
        return (ext in filter)
 
 
def compareDirectories (leftPath, rightPath, uniqueLeft, uniqueRight, filter = None):
    """Recursive function to compare the contents of two given directories. Two lists are
supplied to keep track of the unique files. An optional filter is allowed.
    leftPath - The path to the first directory.
    rightPath - The path to the second directory.
    uniqueLeft - A master list of files unique to the left directory tree.
    uniqueRight - A master list of files unique to the right directory tree.
    filter - Either None, or a list of allowed (whitelist) extensions for files. A unique file in
            either the left or right directory will not be counted as unique if its extension
            does not match one of the filter items."""
 
    # get contents of directories
    left = sorted(os.listdir(leftPath));
    right = sorted(os.listdir(rightPath));
 
    # without a filter, just add all unique files
    if (filter == None):
        # append unique files by using a list comprehension to get all files on one side
        # that are not on the other side
        uniqueLeft[len(uniqueLeft):] = [os.path.join(rightPath, fileName) for fileName in right if fileName not in left]
        uniqueRight[len(uniqueRight):] = [os.path.join(leftPath, fileName) for fileName in left if fileName not in right]
    # otherwise, use the filter function
    else:
        # same as above, but also checks to see that the files match the given filters
        uniqueLeft[len(uniqueLeft):] = [os.path.join(rightPath, fileName) for fileName in right
                                        if fileName not in left and matches(rightPath, fileName, filter)]
        uniqueRight[len(uniqueRight):] = [os.path.join(leftPath, fileName) for fileName in left
                                          if fileName not in right and matches(leftPath, fileName, filter)]
 
    # get a list of files in both directores. Since they by definition must be in both,
    # we can pull them from either side using a list comprehension to check that they're
    # in the other.
    both = [fileName for fileName in left if fileName in right]
 
    # now go through and recursively call the function for any directories in both parent directories
    for fileName in both:
        leftChild = os.path.join(leftPath, fileName)
        rightChild = os.path.join(rightPath, fileName)
        if (os.path.isdir(leftChild) and os.path.isdir(rightChild)):
            compareDirectories(leftChild, rightChild, uniqueLeft, uniqueRight, filter)
 
def usage ():
    print "\n\ncompare.py"
    print "Compares two directories recursively and lists files or folders unique to each one.\n"
    print "compare.py left right outfile [filter1,filter2...]"
    print "\tleft\tFirst directory to compare"
    print "\tright\tSecond directory to compare"
    print "\toutfile\tText file that results are written to"
    print "\t[filter1,filter2]\tOptional comma-separated whitelist"
    print" \t\t\t\tof extensions for files"
    exit()
 
if __name__ == "__main__":
    # slice off name of program from args
    args = sys.argv[1:]
 
    # if there's an incorrect number of parameters, print the usage
    if len(args) < 3 or len(args) > 4:
        usage()
 
    # set up filter whitelist, if any
    filter = None
    if len(args) == 4:
        filter = args[3].split(",")
 
    # set up lists of unique files on both sides
    uniqueRight = list();
    uniqueLeft = list();
 
    # do the comparison recursively
    compareDirectories(args[0], args[1], uniqueLeft, uniqueRight, filter)
 
    # write to the file
    out = open(args[2], 'w')
 
    out.write("UNIQUE TO LEFT:\n")
    for fileName in uniqueLeft:
        out.write(fileName + "\n")
 
    out.write("\nUNIQUE TO RIGHT:\n")
    for fileName in uniqueRight:
       out.write(fileName + "\n")
 
    out.close()