from typing import List

import os
import fasttext.util
import re

def preprocess(text):
    text = re.sub(r"&", "and", text)
    text = re.sub(r"[^\w\s]", " ", text)
    text = re.sub("\n", " ", text)
    text = re.sub(" +", " ", text)
    return text.strip().lower()

class PreTrainedPipeline():
    def __init__(self, path=""):
        """
        Initialize model
        """
        self.model = fasttext.load_model(os.path.join(path, 'model.bin'))

    def __call__(self, inputs: str):
        """
        Args:
            inputs (:obj:`str`):
                a string to get the features of.
        Return:
            A :obj:`list` of floats: The features computed by the model.
        """

        inputs = preprocess(inputs)
        return self.model.predict(inputs)