dupe_names_only.py

#!/usr/bin/env python
# encoding: utf-8

import sys
import os


def finish(data_set):
    base_names = {}
    for dup in data_set:
        base_names.setdefault(os.path.basename(dup), []).append(dup)

    for basename, full_paths in base_names.items():
        if len(full_paths) > 1:
            print('\n#' + ' ' + basename)
            for path in full_paths:
                print(path)


if __name__ == '__main__':
    if len(sys.argv) > 1:
        dups_list = []
        with open(sys.argv[1], 'r') as f:
            for line in f:
                if 'DUPL' in line:
                    split = line.split('//')
                    if len(split) > 2:
                        dups_list.append(split[2])

        finish(dups_list)
    else:
        print('''Usage: {name} /path/to/rmlint.log

Parse rmlint.log and print all dups that have double basenames.'''.format(name=sys.argv[0]))