Question

just wondering if anyone has a suggestion for how I can optimize my simple but slow file replacement script:

def switchFiles(args):
for root1, dirs1, files1 in os.walk(args.folder):
    for f1 in files1:
        for root2, dirs2, files2 in os.walk(args.database):
            for f2 in files2:
                if fnmatch.fnmatch(f1, f2):
                    command = 'cp '+os.path.join(root1, f1)+' '+os.path.join(root2, f2)
                    print(command)
                    os.system(command)

Thanks!

Answer 1

This is a clean up code:

def switchFiles(args):
    pairs = []
    for root1, dirs1, files1 in os.walk(args.folder):
        for f1 in files1:
            for root2, dirs2, files2 in os.walk(args.database):
                for f2 in files2:
                    if f1 == f2:
                        pairs.append(os.path.join(root1, f1), os.path.join(root2, f2))
    for src, dst in pairs:
        shutil.copyfile(src, dst)

if args.folder and args.database are separate (not subdir), and all file’s name in their dir are unique, then you can do this:

def switchFiles(args):
    f, d = {}, {}
    for root1, dirs1, files1 in os.walk(args.folder):
        for f1 in files1:
            f[f1] = os.path.join(root1, f1)
    for root2, dirs2, files2 in os.walk(args.database):
        for f2 in files2:
            d[f2] = os.path.join(root2, f2)
    ns = set(f.keys()) & set(d.keys())
    for n in ns:
        shutil.copyfile(f[n], d[n])