#!/usr/bin/env python3
# Copyright    2021  Xiaomi Corp.        (authors: Fangjun Kuang)
#
# See ../../../../LICENSE for clarification regarding multiple authors
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


"""
This file computes fbank features of the LibriSpeech dataset.
It looks for manifests in the directory data/manifests.
The generated fbank features are saved in data/fbank.
"""

import argparse
import logging
import os
from pathlib import Path
from typing import Optional

import sentencepiece as spm
import torch
from filter_cuts import filter_cuts
from lhotse import CutSet, Fbank, FbankConfig, LilcomChunkyWriter
from lhotse.recipes.utils import read_manifests_if_cached

from icefall.utils import get_executor

# Torch's multithreaded behavior needs to be disabled or
# it wastes a lot of CPU and slow things down.
# Do this outside of main() in case it needs to take effect
# even when we are not invoking the main (e.g. when spawning subprocesses).
torch.set_num_threads(1)
torch.set_num_interop_threads(1)


def get_args():
    parser = argparse.ArgumentParser()

    parser.add_argument(
        "--bpe-model",
        type=str,
        help="""Path to the bpe.model. If not None, we will remove short and
        long utterances before extracting features""",
    )

    parser.add_argument(
        "--dataset",
        type=str,
        help="""Dataset parts to compute fbank. If None, we will use all""",
    )
    parser.add_argument(
        "--manifestpath",
        type=str,
        help="""Dataset parts to compute fbank. If None, we will use all""",
    )
    parser.add_argument(
        "--fbankpath",
        type=str,
        help="""Dataset parts to compute fbank. If None, we will use all""",
    )

    return parser.parse_args()


def compute_fbank_mucs(
    bpe_model: Optional[str] = None,
    dataset: Optional[str] = None,
):
    src_dir = Path(args.manifestpath)
    output_dir = Path(args.fbankpath)
    num_jobs = min(48, os.cpu_count())
    num_mel_bins = 80

    if bpe_model:
        logging.info(f"Loading {bpe_model}")
        sp = spm.SentencePieceProcessor()
        sp.load(bpe_model)

    dataset_parts = (
            "train",
            "test",
            "dev",
    )

    prefix = "mucs"
    suffix = "jsonl.gz"
    manifests = read_manifests_if_cached(
        dataset_parts=dataset_parts,
        output_dir=src_dir,
        prefix=prefix,
        suffix=suffix,
    )
    assert manifests is not None

    assert len(manifests) == len(dataset_parts), (
        len(manifests),
        len(dataset_parts),
        list(manifests.keys()),
        dataset_parts,
    )

    extractor = Fbank(FbankConfig(num_mel_bins=num_mel_bins))

    with get_executor() as ex:  # Initialize the executor only once.
        for partition, m in manifests.items():
       
            cuts_filename = f"{prefix}_cuts_{partition}.{suffix}"
            if (output_dir / cuts_filename).is_file():
                logging.info(f"{partition} already exists - skipping.")
                continue
            logging.info(f"Processing {partition}")
            cut_set = CutSet.from_manifests(
                recordings=m["recordings"],
                supervisions=m["supervisions"],
            )
 
            cut_set = cut_set.compute_and_store_features(
                extractor=extractor,
                storage_path=f"{output_dir}/{prefix}_feats_{partition}",
                # when an executor is specified, make more partitions
                num_jobs=num_jobs if ex is None else 80,
                executor=ex,
                storage_type=LilcomChunkyWriter,
            )
            cut_set = cut_set.trim_to_supervisions(
            keep_overlapping=False, min_duration=None, keep_all_channels=False,
            
        )
            cut_set.to_file(output_dir / cuts_filename)


if __name__ == "__main__":
    formatter = "%(asctime)s %(levelname)s [%(filename)s:%(lineno)d] %(message)s"

    logging.basicConfig(format=formatter, level=logging.INFO)
    args = get_args()
    logging.info(vars(args))
    compute_fbank_mucs(bpe_model=args.bpe_model, dataset=args.dataset)