compare_dirs_old.py

#!/usr/bin/env python3

import os, sys, hashlib

MD5 = True

def md5sum(fn):
    hasher = hashlib.md5()
    with open(fn, 'rb') as f:
        hasher.update(f.read())
        return hasher.hexdigest()

def compare_dirs(d1: "old directory name", d2: "new directory name"):
    def print_local(a, msg):
        print('DIR ' if a[2] else 'FILE', a[1], msg)
    # ensure validity
    for d in [d1,d2]:
        if not os.path.isdir(d):
            raise ValueError("not a directory: " + d)
    # get relative path
    l1 = [(x,os.path.join(d1,x)) for x in os.listdir(d1)]
    l2 = [(x,os.path.join(d2,x)) for x in os.listdir(d2)]
    # determine type: directory or file?
    l1 = sorted([(x,y,os.path.isdir(y)) for x,y in l1])
    l2 = sorted([(x,y,os.path.isdir(y)) for x,y in l2])
    i1 = i2 = 0
    cnt = 0
    common_dirs = []
    while i1<len(l1) and i2<len(l2):
        if l1[i1][0] == l2[i2][0]:      # same name
            if l1[i1][2] == l2[i2][2]:  # same type
                if l1[i1][2]:           # remember this folder for recursion
                    common_dirs.append((l1[i1][1], l2[i2][1]))
                else:
                    # Compare file sizes
                    size1 = os.stat(l1[i1][1]).st_size
                    size2 = os.stat(l2[i2][1]).st_size
                    if size1!=size2:
                        print_local(l1[i1],'size changed: %d -> %d' % (size1, size2))
                    elif MD5:
                        if md5sum(l1[i1][1])!=md5sum(l2[i2][1]):
                            print_local(l1[i1],'hash changed')
            else:
                print_local(l1[i1],'type changed')
            i1 += 1
            i2 += 1
        elif l1[i1][0]<l2[i2][0]:
            print_local(l1[i1],'removed')
            i1 += 1
        elif l1[i1][0]>l2[i2][0]:
            print_local(l2[i2],'added')
            i2 += 1
        cnt += 1
    while i1<len(l1):
        print_local(l1[i1],'removed')
        i1 += 1
        cnt += 1
    while i2<len(l2):
        print_local(l2[i2],'added')
        i2 += 1
        cnt += 1
    # compare subfolders recursively
    for sd1,sd2 in common_dirs:
        cnt += compare_dirs(sd1, sd2)
    return cnt

if __name__=="__main__":
    if MD5: print ('MD5 checking enabled')
    print (compare_dirs(sys.argv[1], sys.argv[2]), 'items compared')