docker-compose.yml

# -*- coding: utf-8 -*-
#
# This file is part of INSPIRE.
# Copyright (C) 2014-2017 CERN.
#
# INSPIRE is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# INSPIRE is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with INSPIRE. If not, see <http://www.gnu.org/licenses/>.
#
# In applying this license, CERN does not waive the privileges and immunities
# granted to it by virtue of its status as an Intergovernmental Organization
# or submit itself to any jurisdiction.

version: '2.3'

services:
  service_base:
    # Overrides default inspirehep config.
    extends:
      file: services.yml
      service: base
    environment:
      - APP_SQLALCHEMY_DATABASE_URI=postgresql+psycopg2://scoap3:dbpass123@database:5432/scoap3
      - APP_CELERY_BROKER_URL=pyamqp://guest:guest@rabbitmq:5672//
      - APP_CELERY_RESULT_BACKEND=redis://redis:6379/1
      - CELERY_BROKER_URL=pyamqp://guest:guest@rabbitmq:5672//
      - CELERY_RESULT_BACKEND=redis://redis:6379/1
      - APP_CACHE_REDIS_URL=redis://redis:6379/0
      - APP_ACCOUNTS_SESSION_REDIS_URL=redis://redis:6379/2
      - APP_SEARCH_ELASTIC_HOSTS=indexer
      - APP_ES_BULK_TIMEOUT=240
      - APP_CRAWLER_HOST_URL=http://localhost:6800
      - APP_CRAWLER_API_PIPELINE_URL=http://flower:5555/api/task/async-apply
      - APP_LAST_RUNS_PATH=.lastruns
      - APP_OAIHARVESTER_WORKDIR=/virtualenv/oaiharvest_workdir
      - SCRAPY_FEED_URI=/virtualenv/scrapy_feed.json
      - APP_JSONSCHEMAS_HOST=web:5000
      - APP_SCOAP_DEFAULT_LOCATION=/tmp/

  # Services using the inspirehep code.
  web:
    extends:
      service: service_base
    command: gunicorn -b 0.0.0.0:5000 -t 3600 --access-logfile "-" --reload scoap3.wsgi
    ports:
      - "5000:5000"
    environment:
      - APP_DEBUG=False
      - APP_ASSETS_DEBUG=False  

  worker:
    extends:
      service: service_base
    command: celery worker -E -A scoap3.celery --loglevel=INFO --queues celery,harvests --concurrency=1 --purge

  redis:
    platform: linux/x86_64
    image: redis:5.0-alpine
    ports:
      - '6379:6379'
  indexer:
    extends:
      file: services.yml
      service: indexer
    ports:
      - "9200:9200"
    environment:
      - discovery.type=single-node
      - TAKE_FILE_OWNERSHIP="true"
    ports:
      - '9200:9200'
      - '9300:9300'

  rabbitmq:
    image: rabbitmq:3.8-management-alpine
    ports:
      - '5672:5672'
  database:
    extends:
      file: services.yml
      service: database
    ports:
      - '5432:5432'

  scrapyd:
    extends:
      service: service_base
    command: bash -c "rm -f twistd.pid && exec scrapyd"
    environment:
      - HEPCRAWL_BASE_WORKING_DIR=/tmp/data/