# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
#     http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file 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.
from __future__ import absolute_import

import sys

import shlex
import subprocess
from retrying import retry
from sagemaker_inference import model_server
from subprocess import CalledProcessError


def _retry_if_error(exception):
    return isinstance(exception, CalledProcessError or OSError)


@retry(stop_max_delay=1000 * 50, retry_on_exception=_retry_if_error)
def _start_mms():
    # by default the number of workers per model is 1, but we can configure it through the
    # environment variable below if desired.
    # os.environ['SAGEMAKER_MODEL_SERVER_WORKERS'] = '2'
    model_server.start_model_server(handler_service="/home/model-server/model_handler.py:handle")


def main():
    if sys.argv[1] == "serve":
        _start_mms()
    else:
        subprocess.check_call(shlex.split(" ".join(sys.argv[1:])))

    # prevent docker exit
    subprocess.call(["tail", "-f", "/dev/null"])


main()