from typing import Optional, List, Union, Tuple

import torch
from torch.nn import MSELoss, CrossEntropyLoss, BCEWithLogitsLoss
from transformers import BartPretrainedModel, BartConfig, BartModel

# from transformers.modeling_outputs import Seq2SeqSequenceClassifierOutput
from transformers.models.bart.modeling_bart import BartClassificationHead
from transformers.utils import ModelOutput


class Seq2SeqSequenceClassifierOutput(ModelOutput):
    loss: Optional[torch.FloatTensor] = None
    logits: torch.FloatTensor = None
    sentence_representation: torch.FloatTensor = None
    past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None
    decoder_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
    decoder_attentions: Optional[Tuple[torch.FloatTensor]] = None
    cross_attentions: Optional[Tuple[torch.FloatTensor]] = None
    encoder_last_hidden_state: Optional[torch.FloatTensor] = None
    encoder_hidden_states: Optional[Tuple[torch.FloatTensor]] = None
    encoder_attentions: Optional[Tuple[torch.FloatTensor]] = None


class BartForSequenceClassification(BartPretrainedModel):
    def __init__(self, config: BartConfig, **kwargs):
        super().__init__(config, **kwargs)
        self.model = BartModel(config)
        self.classification_head = BartClassificationHead(
            config.d_model,
            config.d_model,
            config.num_labels,
            config.classifier_dropout,
        )
        self.model._init_weights(self.classification_head.dense)
        self.model._init_weights(self.classification_head.out_proj)

    def forward(
        self,
        input_ids: torch.LongTensor = None,
        attention_mask: Optional[torch.Tensor] = None,
        decoder_input_ids: Optional[torch.LongTensor] = None,
        decoder_attention_mask: Optional[torch.LongTensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        decoder_head_mask: Optional[torch.Tensor] = None,
        cross_attn_head_mask: Optional[torch.Tensor] = None,
        encoder_outputs: Optional[List[torch.FloatTensor]] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        decoder_inputs_embeds: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, Seq2SeqSequenceClassifierOutput]:
        r"""
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        return_dict = (
            return_dict if return_dict is not None else self.config.use_return_dict
        )
        if labels is not None:
            use_cache = False

        if input_ids is None and inputs_embeds is not None:
            raise NotImplementedError(
                f"Passing input embeddings is currently not supported for {self.__class__.__name__}"
            )

        outputs = self.model(
            input_ids,
            attention_mask=attention_mask,
            decoder_input_ids=decoder_input_ids,
            decoder_attention_mask=decoder_attention_mask,
            head_mask=head_mask,
            decoder_head_mask=decoder_head_mask,
            cross_attn_head_mask=cross_attn_head_mask,
            encoder_outputs=encoder_outputs,
            inputs_embeds=inputs_embeds,
            decoder_inputs_embeds=decoder_inputs_embeds,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        hidden_states = outputs[0]  # last hidden state

        seq_len = input_ids.ne(self.config.pad_token_id).sum(dim=-1) - 1

        sentence_representation = hidden_states[range(len(seq_len)), seq_len, :]
        logits = self.classification_head(sentence_representation)

        loss = None
        if labels is not None:
            if self.config.problem_type is None:
                if self.config.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.config.num_labels > 1 and (
                    labels.dtype == torch.long or labels.dtype == torch.int
                ):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                loss_fct = MSELoss()
                if self.config.num_labels == 1:
                    loss = loss_fct(logits.squeeze(), labels.squeeze())
                else:
                    loss = loss_fct(logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = CrossEntropyLoss()
                loss = loss_fct(
                    logits.view(-1, self.config.num_labels), labels.view(-1)
                )
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = BCEWithLogitsLoss()
                loss = loss_fct(logits, labels)
        if not return_dict:
            output = (logits,) + outputs[1:]
            return ((loss,) + output) if loss is not None else output

        return Seq2SeqSequenceClassifierOutput(
            loss=loss,
            logits=logits,
            sentence_representation=sentence_representation,
            past_key_values=outputs.past_key_values,
            decoder_hidden_states=outputs.decoder_hidden_states,
            decoder_attentions=outputs.decoder_attentions,
            cross_attentions=outputs.cross_attentions,
            encoder_last_hidden_state=outputs.encoder_last_hidden_state,
            encoder_hidden_states=outputs.encoder_hidden_states,
            encoder_attentions=outputs.encoder_attentions,
        )