# Copyright (c) Alibaba, Inc. and its affiliates.
from typing import Any, Dict

import numpy as np

from modelscope.metainfo import TaskModels
from modelscope.models.builder import MODELS
from modelscope.models.nlp.task_models.task_model import EncoderModel
from modelscope.outputs import FeatureExtractionOutput, OutputKeys
from modelscope.utils.constant import Tasks

__all__ = ['ModelForFeatureExtraction']


@MODELS.register_module(
    Tasks.feature_extraction, module_name=TaskModels.feature_extraction)
class ModelForFeatureExtraction(EncoderModel):
    task = Tasks.feature_extraction

    # There is no head for feature extraction method
    head_type = None

    def forward(self,
                input_ids=None,
                attention_mask=None,
                token_type_ids=None,
                position_ids=None,
                head_mask=None,
                inputs_embeds=None,
                labels=None,
                output_attentions=None,
                output_hidden_states=None,
                return_dict=None,
                **kwargs):
        r"""
        Args:
        input_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`):
            Indices of input sequence tokens in the vocabulary.

            Indices can be obtained using :class:`~modelscope.models.nlp.structbert.SbertTokenizer`. See
            :meth:`transformers.PreTrainedTokenizer.encode` and :meth:`transformers.PreTrainedTokenizer.__call__` for
            details.

        attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
            Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.

        token_type_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
            Segment token indices to indicate first and second portions of the inputs. Indices are selected in ``[0,
            1]``:

            - 0 corresponds to a `sentence A` token,
            - 1 corresponds to a `sentence B` token.

        position_ids (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
            Indices of positions of each input sequence tokens in the position embeddings. Selected in the range ``[0,
            config.max_position_embeddings - 1]``.

        head_mask (:obj:`torch.FloatTensor` of shape :obj:`(num_heads,)` or :obj:`(num_layers, num_heads)`, `optional`):
            Mask to nullify selected heads of the self-attention modules. Mask values selected in ``[0, 1]``:

            - 1 indicates the head is **not masked**,
            - 0 indicates the head is **masked**.

        inputs_embeds (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
            Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
            This is useful if you want more control over how to convert :obj:`input_ids` indices into associated
            vectors than the model's internal embedding lookup matrix.
        output_attentions (:obj:`bool`, `optional`):
            Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned
            tensors for more detail.
        output_hidden_states (:obj:`bool`, `optional`):
            Whether or not to return the hidden states of all layers. See ``hidden_states`` under returned tensors for
            more detail.
        return_dict (:obj:`bool`, `optional`):
            Whether or not to return a :class:`~transformers.ModelOutput` instead of a plain tuple.
        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`):
            Labels for computing the sequence classification/regression loss. Indices should be in :obj:`[0, ...,
            config.num_labels - 1]`. If :obj:`config.num_labels == 1` a regression loss is computed (Mean-Square loss),
            If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).

        Returns:
            Returns `modelscope.outputs.AttentionTextClassificationModelOutput`

        Examples:
            >>> from modelscope.models import Model
            >>> from modelscope.preprocessors import Preprocessor
            >>> model = Model.from_pretrained('damo/nlp_structbert_sentence-similarity_chinese-base')
            >>> preprocessor = Preprocessor.from_pretrained('damo/nlp_structbert_sentence-similarity_chinese-base')
            >>> print(model(**preprocessor(('This is a test', 'This is also a test'))))
        """

        # backbone do not need labels, only head need for loss compute
        feature = self.extract_feature(
            input_ids=input_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            head_mask=head_mask,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        return FeatureExtractionOutput(
            text_embedding=feature.last_hidden_state)