test.py

#!/usr/bin/env python3
# encoding: utf-8
#
# ** header v3.0
# This file is a part of the CaosDB Project.
#
# Copyright (C) 2021 Indiscale GmbH <info@indiscale.com>
#               2021 Henrik tom Wörden <h.tomwoerden@indiscale.com>
#               2021 Alexander Schlemmer
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program 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 Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <https://www.gnu.org/licenses/>.
#
# ** end header
#

"""
module description
"""

import argparse
import sys
from argparse import RawTextHelpFormatter
from newcrawler import Crawler
from unittest.mock import Mock
import caosdb as db
from newcrawler.identifiable_adapters import CaosDBIdentifiableAdapter

import os


def rfp(*pathcomponents):
    """
    Return full path.
    Shorthand convenience function.
    """
    return os.path.join(os.path.dirname(__file__), *pathcomponents)


def main(args):
    ident_adapt = CaosDBIdentifiableAdapter()
    # TODO place this definition of identifiables elsewhere
    ident_adapt.register_identifiable(
        "Person", db.RecordType()
        .add_parent(name="Person")
        #.add_property(name="first_name")
        .add_property(name="last_name"))
    ident_adapt.register_identifiable(
        "Measurement", db.RecordType()
        .add_parent(name="Measurement")
        #.add_property(name="identifier")
        .add_property(name="date")
        .add_property(name="project"))
    ident_adapt.register_identifiable(
        "Project", db.RecordType()
        .add_parent(name="Project")
        .add_property(name="date")
        .add_property(name="identifier"))

    crawler = Crawler(debug=True, identifiableAdapter=ident_adapt)
    crawler.copy_attributes = Mock()
    crawler.crawl_directory(rfp("../unittests/test_directories", "examples_article"),
                            rfp("../unittests/scifolder_cfood.yml"))
    ins, ups = crawler.synchronize()
    assert len(ins) == 18
    assert len(ups) == 0

    # Do a second run on the same data, there should be no changes:
    crawler = Crawler(debug=True, identifiableAdapter=ident_adapt)
    crawler.copy_attributes = Mock()
    crawler.crawl_directory(rfp("../unittests/test_directories", "examples_article"),
                            rfp("../unittests/scifolder_cfood.yml"))
    ins, ups = crawler.synchronize()
    assert len(ins) == 0
    assert len(ups) == 0


def parse_args():
    parser = argparse.ArgumentParser(description=__doc__,
                                     formatter_class=RawTextHelpFormatter)
    # parser.add_argument("path",
    #                    help="the subtree of files below the given path will "
    #                    "be considered. Use '/' for everything.")

    return parser.parse_args()


if __name__ == "__main__":
    args = parse_args()
    sys.exit(main(args))