def test_previously_rejected_from_not_fully_harvested_category_is_not_auto_approved(
mocked_refextract_extract_refs,
mocked_api_request_magpie,
mocked_api_request_beard,
mocked_is_pdf_link,
mocked_package_download,
mocked_arxiv_download,
workflow_app,
mocked_external_services,
):
record, categories = core_record()
record["arxiv_eprints"][0]["categories"] = ["q-bio.GN"]
obj = workflow_object_class.create(data=record,
status=ObjectStatus.COMPLETED,
data_type="hep")
obj.extra_data["approved"] = False # reject it
obj.save()
es.indices.refresh("holdingpen-hep")
extra_config = {
"BEARD_API_URL": "http://example.com/beard",
"MAGPIE_API_URL": "http://example.com/magpie",
"ARXIV_CATEGORIES": categories,
}
with workflow_app.app_context():
with mock.patch.dict(workflow_app.config, extra_config):
workflow_id = build_workflow(record).id
eng_uuid = start("article", object_id=workflow_id)
eng = WorkflowEngine.from_uuid(eng_uuid)
obj2 = eng.processed_objects[0]
assert not obj2.extra_data["auto-approved"]
assert len(obj2.extra_data["previously_rejected_matches"]) > 0
assert obj2.status == ObjectStatus.COMPLETED
def test_harvesting_arxiv_workflow_core_record_auto_accepted(
mocked_refextract_extract_refs,
mocked_api_request_magpie,
mocked_api_request_beard,
mocked_is_pdf_link,
mocked_package_download,
mocked_arxiv_download,
workflow_app,
mocked_external_services,
):
"""Test a full harvesting workflow."""
record, categories = core_record()
extra_config = {
"BEARD_API_URL": "http://example.com/beard",
"MAGPIE_API_URL": "http://example.com/magpie",
"ARXIV_CATEGORIES": categories,
}
with workflow_app.app_context():
workflow_id = build_workflow(record).id
with mock.patch.dict(workflow_app.config, extra_config):
workflow_uuid = start("article", object_id=workflow_id)
eng = WorkflowEngine.from_uuid(workflow_uuid)
obj = eng.processed_objects[0]
assert obj.extra_data["approved"] is True
assert obj.extra_data["auto-approved"] is True
assert obj.data["core"] is True
def test_keep_previously_rejected_from_fully_harvested_category_is_auto_approved(
mocked_refextract_extract_refs,
mocked_api_request_magpie,
mocked_api_request_beard,
mocked_is_pdf_link,
mocked_package_download,
mocked_arxiv_download,
workflow_app,
mocked_external_services,
):
record, categories = core_record()
obj = workflow_object_class.create(
data=record,
status=ObjectStatus.COMPLETED,
data_type='hep',
)
obj.extra_data['approved'] = False # reject it
obj.save()
es.indices.refresh('holdingpen-hep')
extra_config = {
"BEARD_API_URL": "http://example.com/beard",
"MAGPIE_API_URL": "http://example.com/magpie",
'ARXIV_CATEGORIES': categories,
}
with workflow_app.app_context():
with mock.patch.dict(workflow_app.config, extra_config):
workflow_uuid = start('article', [record])
eng = WorkflowEngine.from_uuid(workflow_uuid)
obj2 = eng.processed_objects[0]
assert obj2.extra_data['auto-approved']
assert len(obj2.extra_data['previously_rejected_matches']) > 0
assert obj.status == ObjectStatus.COMPLETED
def test_previously_rejected_from_not_fully_harvested_category_is_not_auto_approved(
mocked_refextract_extract_refs,
mocked_api_request_magpie,
mocked_api_request_beard,
mocked_is_pdf_link,
mocked_package_download,
mocked_arxiv_download,
workflow_app,
mocked_external_services,
):
record, categories = core_record()
record["arxiv_eprints"][0]["categories"] = ["q-bio.GN"]
obj = workflow_object_class.create(
data=record, status=ObjectStatus.COMPLETED, data_type="hep"
)
obj.extra_data["approved"] = False # reject it
obj.save()
es.indices.refresh("holdingpen-hep")
extra_config = {
"BEARD_API_URL": "http://example.com/beard",
"MAGPIE_API_URL": "http://example.com/magpie",
"ARXIV_CATEGORIES": categories,
}
with workflow_app.app_context():
with mock.patch.dict(workflow_app.config, extra_config):
workflow_id = build_workflow(record).id
eng_uuid = start("article", object_id=workflow_id)
eng = WorkflowEngine.from_uuid(eng_uuid)
obj2 = eng.processed_objects[0]
assert not obj2.extra_data["auto-approved"]
assert len(obj2.extra_data["previously_rejected_matches"]) > 0
assert obj2.status == ObjectStatus.COMPLETED
def test_harvesting_arxiv_workflow_core_record_auto_accepted(
mocked_refextract_extract_refs,
mocked_api_request_magpie,
mocked_api_request_beard,
mocked_is_pdf_link,
mocked_package_download,
mocked_arxiv_download,
workflow_app,
mocked_external_services,
):
"""Test a full harvesting workflow."""
record, categories = core_record()
extra_config = {
"BEARD_API_URL": "http://example.com/beard",
"MAGPIE_API_URL": "http://example.com/magpie",
"ARXIV_CATEGORIES": categories,
}
with workflow_app.app_context():
workflow_id = build_workflow(record).id
with mock.patch.dict(workflow_app.config, extra_config):
workflow_uuid = start("article", object_id=workflow_id)
eng = WorkflowEngine.from_uuid(workflow_uuid)
obj = eng.processed_objects[0]
assert obj.extra_data["approved"] is True
assert obj.extra_data["auto-approved"] is True
assert obj.data["core"] is True
def test_harvesting_arxiv_workflow_core_record_auto_accepted(
mocked_download, mocked_is_pdf, mocked_refextract_extract_refs,
mocked_api_request_magpie, mocked_api_request_beard, workflow_app,
mocked_external_services):
"""Test a full harvesting workflow."""
record, categories = core_record()
extra_config = {
"BEARD_API_URL": "http://example.com/beard",
"MAGPIE_API_URL": "http://example.com/magpie",
'ARXIV_CATEGORIES': categories,
}
with workflow_app.app_context():
with mock.patch.dict(workflow_app.config, extra_config):
workflow_uuid = start('article', [record])
eng = WorkflowEngine.from_uuid(workflow_uuid)
obj = eng.processed_objects[0]
assert obj.extra_data['approved'] is True
assert obj.extra_data['auto-approved'] is True
assert obj.data['core'] is True
