import abc
from typing import List, Union

from numpy.typing import NDArray
from sentence_transformers import SentenceTransformer

from type_aliases import ENCODER_DEVICE_TYPE


class Encoder(abc.ABC):
    @abc.abstractmethod
    def encode(self, prediction: List[str]) -> NDArray:
        """
            Abstract method to encode a list of sentences into sentence embeddings.

            Args:
                prediction (List[str]): List of sentences to encode.

            Returns:
                NDArray: Array of sentence embeddings with shape (num_sentences, embedding_dim).

            Raises:
                NotImplementedError: If the method is not implemented in the subclass.
        """
        raise NotImplementedError("Method 'encode' must be implemented in subclass.")


class USE(Encoder):
    def __init__(self):
        pass

    def encode(self, prediction: List[str]) -> NDArray:
        pass


class SBertEncoder(Encoder):
    def __init__(self, model_name: str, device: ENCODER_DEVICE_TYPE, batch_size: int, verbose: bool):
        """
            Initialize SBertEncoder instance.

            Args:
                model_name (str): Name or path of the Sentence Transformer model.
                device (Union[str, int, List[Union[str, int]]]): Device specification for encoding
                batch_size (int): Batch size for encoding.
                verbose (bool): Whether to print verbose information during encoding.
        """
        self.model = SentenceTransformer(model_name)
        self.device = device
        self.batch_size = batch_size
        self.verbose = verbose

    def encode(self, prediction: List[str]) -> NDArray:
        """
           Encode a list of sentences into sentence embeddings.

           Args:
               prediction (List[str]): List of sentences to encode.

           Returns:
               NDArray: Array of sentence embeddings with shape (num_sentences, embedding_dim).
        """

        # SBert output is always Batch x Dim
        if isinstance(self.device, list):
            # Use multiprocess encoding for list of devices
            pool = self.model.start_multi_process_pool(target_devices=self.device)
            embeddings = self.model.encode_multi_process(prediction, pool=pool, batch_size=self.batch_size)
            self.model.stop_multi_process_pool(pool)
        else:
            # Single device encoding
            embeddings = self.model.encode(
                prediction,
                device=self.device,
                batch_size=self.batch_size,
                show_progress_bar=self.verbose,
            )

        return embeddings


def get_encoder(model_name: str, device: ENCODER_DEVICE_TYPE, batch_size: int, verbose: bool) -> Encoder:
    """
        Get the encoder instance based on the specified model name.

        Args:
            model_name (str): Name of the model to instantiate
                Options: [pv1, stsb, use]
                    pv1 - paraphrase-distilroberta-base-v1 (Default)
                    stsb - stsb-roberta-large
                    use - Universal Sentence Encoder
            device (Union[str, int, List[Union[str, int]]): Device specification for the encoder
                (e.g., "cuda", 0 for GPU, "cpu").
            batch_size (int): Batch size for encoding.
            verbose (bool): Whether to print verbose information during encoder initialization.

        Returns:
            Encoder: Instance of the selected encoder based on the model_name.

        Raises:
            ValueError: If an unsupported model_name is provided.
        """

    # TODO: chnage this when changing the TF model
    if model_name == "use":
        return SBertEncoder("sentence-transformers/use-cmlm-multilingual", device, batch_size, verbose)
        # return USE()
    else:
        return SBertEncoder(model_name, device, batch_size, verbose)