# Copyright (c) Alibaba, Inc. and its affiliates.
# Part of the implementation is borrowed from espnet/espnet.

import numpy as np
import torch


def load_cmvn(cmvn_file):
    with open(cmvn_file, 'r', encoding='utf-8') as f:
        lines = f.readlines()
    means_list = []
    vars_list = []
    for i in range(len(lines)):
        line_item = lines[i].split()
        if line_item[0] == '<AddShift>':
            line_item = lines[i + 1].split()
            if line_item[0] == '<LearnRateCoef>':
                add_shift_line = line_item[3:(len(line_item) - 1)]
                means_list = list(add_shift_line)
                continue
        elif line_item[0] == '<Rescale>':
            line_item = lines[i + 1].split()
            if line_item[0] == '<LearnRateCoef>':
                rescale_line = line_item[3:(len(line_item) - 1)]
                vars_list = list(rescale_line)
                continue
    means = np.array(means_list).astype(np.float)
    vars = np.array(vars_list).astype(np.float)
    cmvn = np.array([means, vars])
    cmvn = torch.as_tensor(cmvn)
    return cmvn


def apply_cmvn(inputs, cmvn_file):  # noqa
    """
    Apply CMVN with mvn data
    """

    device = inputs.device
    dtype = inputs.dtype
    frame, dim = inputs.shape

    cmvn = load_cmvn(cmvn_file)
    means = np.tile(cmvn[0:1, :dim], (frame, 1))
    vars = np.tile(cmvn[1:2, :dim], (frame, 1))
    inputs += torch.from_numpy(means).type(dtype).to(device)
    inputs *= torch.from_numpy(vars).type(dtype).to(device)

    return inputs.type(torch.float32)


def apply_lfr(inputs, lfr_m, lfr_n):
    LFR_inputs = []
    T = inputs.shape[0]
    T_lfr = int(np.ceil(T / lfr_n))
    left_padding = inputs[0].repeat((lfr_m - 1) // 2, 1)
    inputs = torch.vstack((left_padding, inputs))
    T = T + (lfr_m - 1) // 2
    for i in range(T_lfr):
        if lfr_m <= T - i * lfr_n:
            LFR_inputs.append((inputs[i * lfr_n:i * lfr_n + lfr_m]).view(1, -1))
        else:  # process last LFR frame
            num_padding = lfr_m - (T - i * lfr_n)
            frame = (inputs[i * lfr_n:]).view(-1)
            for _ in range(num_padding):
                frame = torch.hstack((frame, inputs[-1]))
            LFR_inputs.append(frame)
    LFR_outputs = torch.vstack(LFR_inputs)
    return LFR_outputs.type(torch.float32)