from transformers.models.bert.modeling_bert import BertEncoder, BertPooler, BertEmbeddings, BertForMaskedLM, MaskedLMOutput
from transformers import BertModel
from typing import List, Optional, Tuple, Union
import torch

class BertEmbeddingsV2(BertEmbeddings):
    def __init__(self, config):
        super().__init__(config)
        self.pad_token_id = config.pad_token_id
        self.position_embeddings = torch.nn.Embedding(config.max_position_embeddings, config.hidden_size, padding_idx=0) # here padding_idx is always 0

    def forward(
        self,
        input_ids: torch.LongTensor,
        token_type_ids: Optional[torch.LongTensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        past_key_values_length: int = 0,
    ) -> torch.Tensor:
        inputs_embeds = self.word_embeddings(input_ids)
        position_ids = self.create_position_ids_from_input_ids(input_ids)  
        position_embeddings = self.position_embeddings(position_ids)
        embeddings = inputs_embeds + position_embeddings
        return self.dropout(self.LayerNorm(embeddings))
    
    def create_position_ids_from_input_ids(self, input_ids: torch.LongTensor) -> torch.Tensor:
        mask = input_ids.ne(self.pad_token_id).int()
        return torch.cumsum(mask, dim=1).long() * mask
    

class BertModelV2(BertModel):
    def __init__(self, config):
        super().__init__(config)
        self.embeddings = BertEmbeddingsV2(config)


class BertForMaskedLMV2(BertForMaskedLM):
    def __init__(self, config):
        super().__init__(config)

    def forward(
        self,
        input_ids: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        token_type_ids: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.Tensor] = None,
        head_mask: Optional[torch.Tensor] = None,
        inputs_embeds: Optional[torch.Tensor] = None,
        encoder_hidden_states: Optional[torch.Tensor] = None,
        encoder_attention_mask: Optional[torch.Tensor] = None,
        labels: Optional[torch.Tensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple[torch.Tensor], MaskedLMOutput]:
        r"""
        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
            Labels for computing the masked language modeling loss. Indices should be in `[-100, 0, ...,
            config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
            loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`
        """

        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.bert(
            input_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        sequence_output = outputs[0]
        prediction_scores = sequence_output[:, :, 0:24]
        
        masked_lm_loss = None
        if labels is not None:
            loss_fct = torch.nn.CrossEntropyLoss()  # -100 index = padding token
            masked_lm_loss = loss_fct(prediction_scores.view(-1, self.config.vocab_size), labels.view(-1))

        if not return_dict:
            output = (prediction_scores,) + outputs[2:]
            return ((masked_lm_loss,) + output) if masked_lm_loss is not None else output

        return MaskedLMOutput(
            loss=masked_lm_loss,
            logits=prediction_scores,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    def prepare_inputs_for_generation(self, input_ids, attention_mask=None, **model_kwargs):
        input_shape = input_ids.shape
        effective_batch_size = input_shape[0]

        #  add a dummy token
        if self.config.pad_token_id is None:
            raise ValueError("The PAD token should be defined for generation")

        attention_mask = torch.cat([attention_mask, attention_mask.new_zeros((attention_mask.shape[0], 1))], dim=-1)
        dummy_token = torch.full(
            (effective_batch_size, 1), self.config.pad_token_id, dtype=torch.long, device=input_ids.device
        )
        input_ids = torch.cat([input_ids, dummy_token], dim=1)

        return {"input_ids": input_ids, "attention_mask": attention_mask}