Differential D4735 Diff 16785 swh/deposit/tests/test_utils.py

Changeset View

Standalone View

swh/deposit/tests/test_utils.py

# Copyright (C) 2018-2020 The Software Heritage developers		# Copyright (C) 2018-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution		# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version		# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information		# See top-level LICENSE file for more information

from typing import Union		from typing import Union
from unittest.mock import patch		from unittest.mock import patch

import pytest		import pytest

from swh.deposit import utils		from swh.deposit import utils
		from swh.deposit.parsers import parse_xml
		from swh.model.exceptions import ValidationError
from swh.model.identifiers import SWHID, parse_swhid		from swh.model.identifiers import SWHID, parse_swhid
from swh.model.model import MetadataTargetType		from swh.model.model import MetadataTargetType


		@pytest.fixture
		def xml_with_origin_reference():
		xml_data = """<?xml version="1.0"?>
		<entry xmlns="http://www.w3.org/2005/Atom"
		xmlns:codemeta="https://doi.org/10.5063/SCHEMA/CODEMETA-2.0"
		xmlns:swh="https://www.softwareheritage.org/schema/2018/deposit">
		<swh:deposit>
		<swh:reference>
		<swh:origin url="{url}"/>
		</swh:reference>
		</swh:deposit>
		</entry>
		"""
		return xml_data.strip()


def test_merge():		def test_merge():
"""Calling utils.merge on dicts should merge without losing information		"""Calling utils.merge on dicts should merge without losing information

"""		"""
d0 = {"author": "someone", "license": [["gpl2"]], "a": 1}		d0 = {"author": "someone", "license": [["gpl2"]], "a": 1}

d1 = {		d1 = {
"author": ["author0", {"name": "author1"}],		"author": ["author0", {"name": "author1"}],
▲ Show 20 Lines • Show All 169 Lines • ▼ Show 20 Lines	):
if expected_type != MetadataTargetType.ORIGIN:		if expected_type != MetadataTargetType.ORIGIN:
assert isinstance(swhid_or_origin, str)		assert isinstance(swhid_or_origin, str)
swhid_or_origin = parse_swhid(swhid_or_origin)		swhid_or_origin = parse_swhid(swhid_or_origin)

object_type, metadata_context = utils.compute_metadata_context(swhid_or_origin)		object_type, metadata_context = utils.compute_metadata_context(swhid_or_origin)

assert object_type == expected_type		assert object_type == expected_type
assert metadata_context == expected_metadata_context		assert metadata_context == expected_metadata_context


		def test_parse_swh_reference_origin(xml_with_origin_reference):
		url = "https://url"
		xml_data = xml_with_origin_reference.format(url=url)
		metadata = parse_xml(xml_data)

		actual_origin = utils.parse_swh_reference(metadata)
		assert actual_origin == url


		@pytest.fixture
		def xml_with_empty_reference():
		xml_data = """<?xml version="1.0"?>
		<entry xmlns:swh="https://www.softwareheritage.org/schema/2018/deposit">
		<swh:deposit>
		{swh_reference}
		</swh:deposit>
		</entry>
		"""
		return xml_data.strip()


		@pytest.mark.parametrize(
		"xml_ref",
		[
		"",
		"<swh:reference></swh:reference>",
		"<swh:reference><swh:object /></swh:reference>",
		"""<swh:reference><swh:object swhid="" /></swh:reference>""",
		],
		)
		def test_parse_swh_reference_empty(xml_with_empty_reference, xml_ref):
		xml_body = xml_with_empty_reference.format(swh_reference=xml_ref)
		metadata = utils.parse_xml(xml_body)

		assert utils.parse_swh_reference(metadata) is None


		@pytest.fixture
		def xml_with_swhid(atom_dataset):
		return atom_dataset["entry-data-with-swhid"]


		@pytest.mark.parametrize(
		"swhid",
		[
		"swh:1:cnt:31b5c8cc985d190b5a7ef4878128ebfdc2358f49;origin=https://hal.archives-ouvertes.fr/hal-01243573;visit=swh:1:snp:4fc1e36fca86b2070204bedd51106014a614f321;anchor=swh:1:rev:9c5de20cfb54682370a398fcc733e829903c8cba;path=/moranegg-AffectationRO-df7f68b/", # noqa
		"swh:1:dir:31b5c8cc985d190b5a7ef4878128ebfdc2358f49;anchor=swh:1:dir:9c5de20cfb54682370a398fcc733e829903c8cba", # noqa
		"swh:1:rev:31b5c8cc985d190b5a7ef4878128ebfdc2358f49;anchor=swh:1:rev:9c5de20cfb54682370a398fcc733e829903c8cba", # noqa
		"swh:1:rel:31b5c8cc985d190b5a7ef4878128ebfdc2358f49;anchor=swh:1:rel:9c5de20cfb54682370a398fcc733e829903c8cba", # noqa
		"swh:1:snp:31b5c8cc985d190b5a7ef4878128ebfdc2358f49;anchor=swh:1:snp:9c5de20cfb54682370a398fcc733e829903c8cba", # noqa
		"swh:1:dir:31b5c8cc985d190b5a7ef4878128ebfdc2358f49",
		],
		)
		def test_parse_swh_reference_swhid(swhid, xml_with_swhid):
		xml_data = xml_with_swhid.format(swhid=swhid)
		metadata = utils.parse_xml(xml_data)

		actual_swhid = utils.parse_swh_reference(metadata)
		assert actual_swhid is not None

		expected_swhid = parse_swhid(swhid)
		assert actual_swhid == expected_swhid


		@pytest.mark.parametrize(
		"invalid_swhid,error_msg",
		[
		("swh:1:cnt:31b5c8cc985d190b5a7ef4878128ebfdc235", "Unexpected length"),
		(
		"swh:1:dir:c4993c872593e960dc84e4430dbbfbc34fd706d0;visit=swh:1:rev:0175049fc45055a3824a1675ac06e3711619a55a", # noqa
		"visit qualifier should be a core SWHID with type",
		),
		(
		"swh:1:rev:c4993c872593e960dc84e4430dbbfbc34fd706d0;anchor=swh:1:cnt:b5f505b005435fa5c4fa4c279792bd7b17167c04;path=/", # noqa
		"anchor qualifier should be a core SWHID with type one of",
		),
		(
		"swh:1:rev:c4993c872593e960dc84e4430dbbfbc34fd706d0;visit=swh:1:snp:0175049fc45055a3824a1675ac06e3711619a55a;anchor=swh:1:snp:b5f505b005435fa5c4fa4c279792bd7b17167c04", # noqa
		"anchor=swh:1:snp",
		),
		],
		)
		def test_parse_swh_reference_invalid_swhid(invalid_swhid, error_msg, xml_with_swhid):
		"""Unparsable swhid should raise

		"""
		xml_invalid_swhid = xml_with_swhid.format(swhid=invalid_swhid)
		metadata = utils.parse_xml(xml_invalid_swhid)

		with pytest.raises(ValidationError, match=error_msg):
		utils.parse_swh_reference(metadata)