Can you provide a simple attack API for single sentence attack test?

[yangheng95]

Is your feature request related to a problem? Please describe. No

Describe the solution you'd like Here is a simply idea for single text attack which is rewrited from original batch attack function

    def simple_attack(self, text, label):
        if torch.cuda.is_available():
            self.attack.cuda_()

        example, ground_truth_output = text, label
        try:
            example = textattack.shared.AttackedText(example)
            if self.dataset.label_names is not None:
                example.attack_attrs["label_names"] = self.dataset.label_names
            try:
                result = self.attack.attack(example, ground_truth_output)
            except Exception as e:
                raise e
            if (isinstance(result, SkippedAttackResult) and self.attack_args.attack_n) or (
                not isinstance(result, SuccessfulAttackResult)
                and self.attack_args.num_successful_examples
            ):
                return
            else:
                return result
        except KeyboardInterrupt as e:
            raise e

In this way, we need to initialize the attacker as usual, and the dataset loading method can be refactored, e.g., provide a default null dataset object instead of compulsory loading dataset from a file. e.g.,

        # dataset = HuggingFaceDataset("sst", split="test")
        # data = pandas.read_csv('examples.csv')
        dataset = [('', 0)]
        dataset = Dataset(dataset)

        self.attacker = Attacker(recipe, dataset)

Describe alternatives you've considered No

Additional context I also suggest to support mirror the tfhub which will help people in China(unable to access tfhub.dev). e.g., https://github.com/yangheng95/TextAttack/blob/018c561b27182164dc76fb5e43516f7bc64801b1/textattack/constraints/semantics/sentence_encoders/universal_sentence_encoder/universal_sentence_encoder.py#L21 and https://github.com/yangheng95/TextAttack/blob/018c561b27182164dc76fb5e43516f7bc64801b1/textattack/constraints/semantics/sentence_encoders/universal_sentence_encoder/multilingual_universal_sentence_encoder.py#L23 . However, this is up to you.

Finally, I recommand to distinguish the name of attacked_text in the original_result and perturded_result, as I got trouble in confusing them in experiments, and lost some time.

Thanks very much for this great work!