'''
  Data management input/output
  '''
  
  # Import packages and modules
  import numpy as np

  import sys

  
  # Defining some types

  from typing import List, Dict, Tuple
  
  from numpy.lib.shape_base import expand_dims

  KeyToList = Dict[str, List[str]]

  KeyToLabels = Dict[str, List[str]]
  KeyToIntLabels = Dict[str, List[int]]

  KeyToFeatures = Dict[str, List[float]]
  
  
  def read_lst(file_path: str) -> KeyToList:
      '''
      Read lst file with this structure:

      [id_1]
      [id_2]
      ...
      [id_n]
      
      Return a list of ids.
      '''
      lst = []
      with open(file_path, "r") as f:
          for line in f:
              lst.append(line.replace("
  ", ""))
      return lst
  
  
  def read_id_values(file_path: str, value_type=str):
      '''
      Read file where each line is an id with its corresponding values:
      [id_1] [value_1_1] [value_1_2] ... [value_1_k]
      [id_2] [value_2_1] [value_2_2] ... [value_2_k]
      ...
      [id_n] [value_n_1] [value_n_2] ... [value_n_k]
  
      where values are value_type type.

      Used in many reader functions with specific value_type.
      Return a dictionary with id as key and values as associated values.

      '''

      id_values = {}

      with open(file_path, "r") as f:
          for line in f:
              splited = line.replace("
  ", "").split(" ")

              id_values[splited[0]] = np.asarray(splited[1:], dtype=value_type)
      return id_values

  
  
  def read_features(file_path: str) -> KeyToFeatures:
      '''

      Read features files with the following structure:
      [id_1] [value_1_1] [value_1_2] ... [value_1_k]
      [id_2] [value_2_1] [value_2_2] ... [value_2_k]
      ...
      [id_n] [value_n_1] [value_n_2] ... [value_n_k]
  
      where values are float
  
      Returns a dictionary with id as key and a list of values as associated values

      '''

      return read_id_values(file_path, np.float64)

  def read_features_with_matrix(file_path: str) -> Tuple[List[str], np.ndarray]:
      """Read a features file and returns the keys (utterances ids) 
      with the corresponding matrix of values.
  
      Args:
          file_path (str): path of the features file
  
      Returns:
          [Tuple(List[str], np.ndarray)]: a tuple with a list of keys and the matrix
      """
      data = read_id_values(file_path, np.float64)
      keys = []
      matrix = None
      for key, values in data.items():
          keys.append(key)
          if matrix is None:
              matrix = np.expand_dims(values, axis=0)
          matrix = np.append(matrix, np.expand_dims(values, axis=0), axis=0)
      
      return (keys, matrix)

  def read_labels(file_path: str) -> KeyToLabels:
      '''
      Read features files with the following structure :
      [id_1] [value_1_1] [value_1_2] ... [value_1_k]
      [id_2] [value_2_1] [value_2_2] ... [value_2_k]
      ...
      [id_n] [value_n_1] [value_n_2] ... [value_n_k]
  
      where values are int
      '''
      return read_id_values(file_path, str)
  
  
  def read_labels_integer(file_path: str) -> KeyToIntLabels:
      '''
      Read features files with the following structure :
      [id_1] [value_1_1] [value_1_2] ... [value_1_k]
      [id_2] [value_2_1] [value_2_2] ... [value_2_k]
      ...
      [id_n] [value_n_1] [value_n_2] ... [value_n_k]
  
      where values are int
      '''
      return read_id_values(file_path, int)
  
  
  def write_line(id_, values=[], out=sys.stdout):
      """
      Write a line in list, labels or features files.
      If you want to write a list, specify an empty
      array for *values*. 

      Args:
          id_ (str): id in string.
          values (list, optional): list of values to write, features or labels. Defaults to [].
          out (_io.TextIOWrapper, optional): . Defaults to sys.stdout.
      """

      if hasattr(values, '__len__'):
          if len(values) == 0:
              out.write(str(id_) + "
  ")
          else:
              out.write(str(id_) + " " + " ".join(values) + "
  ")

      else:

          out.write(str(id_) + " " + str(values) + "
  ")