mat

#!/usr/bin/env python
"""
    Metadata anonymisation toolkit - CLI edition
"""

import sys
import argparse
import os

import hachoir_core

from libmat import mat
from libmat import archive


def parse():
    """ Get, and parse options passed to the program
    """
    parser = argparse.ArgumentParser(description='Metadata anonymisation toolkit')
    parser.add_argument('files', nargs='*')

    options = parser.add_argument_group('Options')
    options.add_argument('-a', '--add2archive', action='store_true',
                         help='add to output archive non-supported filetypes (Off by default)')
    options.add_argument('-b', '--backup', '-b', action='store_true',
                         help='keep a backup copy')
    options.add_argument('-L', '--low-pdf-quality', '-L', action='store_true',
                         help='produces a lighter, but lower quality PDF')

    info = parser.add_argument_group('Information')
    info.add_argument('-c', '--check', action='store_true',
                      help='check if a file is free of harmful metadatas')
    info.add_argument('-d', '--display', action='store_true',
                      help='list all the harmful metadata of a file without removing them')
    info.add_argument('-l', '--list', action='store_true',
                      help='list all supported fileformats')
    info.add_argument('-v', '--version', action='version',
                      version='MAT %s - Hachoir %s' % (mat.__version__, hachoir_core.__version__))

    return parser.parse_args()


def list_meta(class_file, filename, add2archive):
    """ Print all the metadata of 'filename' on stdout
    """
    print('[+] File %s :' % filename)
    if class_file.is_clean():
        print('No harmful metadata found')
    else:
        print ('Harmful metadata found:')
        meta = class_file.get_meta()
        if meta:
            for key, value in class_file.get_meta().iteritems():
                print('\t%s: %s' % (key, value))
    return 0


def is_clean(class_file, filename, add2archive):
    """ Tell if 'filename' is clean or not """
    if class_file.is_clean():
        print('[+] %s is clean' % filename)
    else:
        print('[+] %s is not clean' % filename)
    return 0


def clean_meta(class_file, filename, add2archive):
    """ Clean the file 'filename' """
    if not class_file.is_writable:
        print('[-] %s is not writable' % filename)
        return 1
    print('[*] Cleaning %s' % filename)
    if not add2archive:
        is_archive = isinstance(class_file, archive.GenericArchiveStripper)
        is_terminal = isinstance(class_file, archive.TerminalZipStripper)
        if is_archive and not is_terminal:
            unsupported_list = class_file.list_unsupported()
            if type(unsupported_list) == list and unsupported_list:
                print('[-] Can not clean: %s.'
                      'It contains unsupported filetypes:' % filename)
                for i in unsupported_list:
                    print('- %s' % i)
                return 1
    if class_file.remove_all():
        print('[+] %s cleaned!' % filename)
    else:
        print('[-] Unable to clean %s', filename)
        return 1
    return 0


def list_supported():
    """ Print all supported fileformat """
    for item in mat.list_supported_formats():
        print('%s (%s)' % (item['name'], item['extension']))
        print('\tsupport: %s' % item['support'])
        print('\tmetadata: %s' % item['metadata'])
        print('\tmethod: %s' % item['method'])
        print('\tremaining: %s' % item['remaining'])
        print('\n')


def main():
    """ Main function: get args and launch the appropriate function """
    args = parse()

    # func receives the function corresponding to the options given as parameters
    if args.display:  # only print metadatas
        func = list_meta
    elif args.check:  # only check if the file is clean
        func = is_clean
    elif args.list:  # print the list of all supported format
        list_supported()
        sys.exit(0)
    else:  # clean the file
        func = clean_meta

    ret = 0
    # We're using a while loop, instead of a for,
    # because we support folders. This allow us
    # to add their content, and to process it.
    while args.files:
        filename = args.files.pop()
        if os.path.isdir(filename):
            for root, sub, files in os.walk(filename):
                for fname in files:
                    args.files.append(os.path.join(root, fname))
            continue

        class_file = mat.create_class_file(filename, args.backup,
                                           add2archive=args.add2archive, low_pdf_quality=args.low_pdf_quality)
        if class_file:
            ret += func(class_file, filename, args.add2archive)
        else:
            ret = 1
            print('[-] Unable to process %s' % filename)
    sys.exit(ret)


if __name__ == '__main__':
    main()