#!/usr/bin/env bash

set -eou pipefail

nj=30
stage=3
stop_stage=3

# We assume dl_dir (download dir) contains the following
# directories and files. If not, you need to apply aishell2 through
# their official website.
#
#  - $dl_dir/aishell2
#
#
#  - $dl_dir/musan
#      This directory contains the following directories downloaded from
#       http://www.openslr.org/17/
#
#     - music
#     - noise
#     - speech

dl_dir=$PWD/download

. shared/parse_options.sh || exit 1

# All files generated by this script are saved in "data".
# You can safely remove "data" and rerun this script to regenerate it.
mkdir -p data

log() {
  # This function is from espnet
  local fname=${BASH_SOURCE[1]##*/}
  echo -e "$(date '+%Y-%m-%d %H:%M:%S') (${fname}:${BASH_LINENO[0]}:${FUNCNAME[1]}) $*"
}

log "dl_dir: $dl_dir"

if [ $stage -le 0 ] && [ $stop_stage -ge 0 ]; then
  log "stage 0: Download data"

  # If you have pre-downloaded it to /path/to/aishell2,
  # you can create a symlink
  #
  #   ln -sfv /path/to/aishell2 $dl_dir/aishell2
  #
  # The directory structure is
  # aishell2/
  # |-- AISHELL-2
  # |   |-- iOS
  #         |-- data
  #             |-- wav
  #             |-- trans.txt
  #         |-- dev
  #             |-- wav
  #             |-- trans.txt
  #         |-- test
  #             |-- wav
  #             |-- trans.txt


  # If you have pre-downloaded it to /path/to/musan,
  # you can create a symlink
  #
  #   ln -sfv /path/to/musan $dl_dir/musan
  #
  if [ ! -d $dl_dir/musan ]; then
    lhotse download musan $dl_dir
  fi
fi

if [ $stage -le 1 ] && [ $stop_stage -ge 1 ]; then
  log "Stage 1: Prepare aishell2 manifest"
  # We assume that you have downloaded and unzip the aishell2 corpus
  # to $dl_dir/aishell2
  if [ ! -f data/manifests/.aishell_manifests.done ]; then
    mkdir -p data/manifests
    lhotse prepare aishell2 $dl_dir/aishell2 data/manifests -j $nj
    touch data/manifests/.aishell2_manifests.done
  fi
fi

if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
  log "Stage 2: Prepare musan manifest"
  # We assume that you have downloaded the musan corpus
  # to data/musan
  if [ ! -f data/manifests/.musan_manifests.done ]; then
    log "It may take 6 minutes"
    mkdir -p data/manifests
    lhotse prepare musan $dl_dir/musan data/manifests
    touch data/manifests/.musan_manifests.done
  fi
fi

if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
  log "Stage 3: Compute fbank for aishell"
  if [ ! -f data/fbank/.aishell2.done ]; then
    mkdir -p data/fbank
    ./local/compute_fbank_aishell2.py
    touch data/fbank/.aishell2.done
  fi
fi

if [ $stage -le 4 ] && [ $stop_stage -ge 4 ]; then
  log "Stage 4: Compute fbank for musan"
  if [ ! -f data/fbank/.msuan.done ]; then
    mkdir -p data/fbank
    ./local/compute_fbank_musan.py
    touch data/fbank/.msuan.done
  fi
fi

if [ $stage -le 5 ] && [ $stop_stage -ge 5 ]; then
  log "Stage 6: Prepare char based lang"
  lang_char_dir=data/lang_char
  mkdir -p $lang_char_dir

  # Prepare text.
  grep "\"text\":" data/manifests/aishell2_supervisions_train.json \
    | sed -e 's/["text:\t ]*//g' | sed 's/,//g' \
    | ./local/text2token.py -t "char" > $lang_char_dir/text

  # Prepare words.txt
  grep "\"text\":" data/manifests/aishell2_supervisions_train.json \
    | sed -e 's/["text:\t]*//g' | sed 's/,//g' \
    | ./local/text2token.py -t "char" > $lang_char_dir/text_words

  cat $lang_char_dir/text_words | sed 's/ /\n/g' | sort -u | sed '/^$/d' \
    | uniq > $lang_char_dir/words_no_ids.txt

  if [ ! -f $lang_char_dir/words.txt ]; then
    ./local/prepare_words.py \
      --input-file $lang_char_dir/words_no_ids.txt
      --output-file $lang_char_dir/words.txt
  fi

  if [ ! -f $lang_char_dir/L_disambig.pt ]; then
    ./local/prepare_char.py
  fi
fi