def test_indexer_populates_referenced_authors_bais(inspire_app):
data_authors = {
"authors": [
{
"full_name": "Jean-Luc Picard",
"ids": [{
"schema": "INSPIRE BAI",
"value": "Jean.L.Picard.1"
}],
},
{
"full_name": "John Doe",
"ids": [{
"schema": "INSPIRE BAI",
"value": "J.Doe.1"
}],
},
]
}
cited_record_1 = create_record("lit", data=data_authors)
data_authors = {
"authors": [
{
"full_name": "Jean-Luc Picard",
"ids": [{
"schema": "INSPIRE BAI",
"value": "Jean.L.Picard.1"
}],
},
{
"full_name": "Steven Johnson",
"ids": [{
"schema": "INSPIRE BAI",
"value": "S.Johnson.1"
}],
},
]
}
cited_record_2 = create_record("lit", data=data_authors)
citing_record = create_record(
"lit",
literature_citations=[
cited_record_1["control_number"],
cited_record_2["control_number"],
],
)
expected_rec3_referenced_authors_bais = [
"J.Doe.1",
"Jean.L.Picard.1",
"S.Johnson.1",
]
rec1_es = LiteratureSearch.get_record_data_from_es(cited_record_1)
rec2_es = LiteratureSearch.get_record_data_from_es(cited_record_2)
rec3_es = LiteratureSearch.get_record_data_from_es(citing_record)
assert "referenced_authors_bais" not in rec1_es
assert "referenced_authors_bais" not in rec2_es
assert (sorted(rec3_es["referenced_authors_bais"]) ==
expected_rec3_referenced_authors_bais)
def assert_disambiguation_cli():
record_from_es = LiteratureSearch.get_record_data_from_es(record)
for author in record_from_es["authors"]:
if author["full_name"] == "Test Author Dismabiguated":
assert author["record"]["$ref"] == disambiguated_author_ref
else:
assert "record" in author
def test_indexer_oai_set_CERN_arxiv_and_CDS(inspire_app):
extra_data = {
"report_numbers": [{
"value": "CERN-2020-001"
}],
"arxiv_eprints": [{
"value": "2009.01484"
}],
"_export_to": {
"CDS": True
},
}
record_data = faker.record("lit", data=extra_data)
record = LiteratureRecord.create(record_data)
record.index(delay=False)
result_record = LiteratureSearch.get_record_data_from_es(record)
expected_id = f"oai:inspirehep.net:{record['control_number']}"
expected_updated = record.updated.strftime(OAI_TIME_FORMAT)
expected_sets = [
inspire_app.config["OAI_SET_CDS"],
inspire_app.config["OAI_SET_CERN_ARXIV"],
]
assert expected_id == result_record["_oai"]["id"]
assert expected_updated == result_record["_oai"]["updated"]
assert expected_sets == result_record["_oai"]["sets"]
def assert_assign():
for literature in [literature_1, literature_2]:
current_search.flush_and_refresh("*")
literature_after = LiteratureSearch.get_record_data_from_es(
literature)
literature_author = literature_after["authors"][0]
assert literature_author["record"] == {
"$ref":
f"http://localhost:5000/api/authors/{to_author['control_number']}"
}
assert literature_author["curated_relation"]
assert literature_author["ids"] == to_author["ids"]
def assert_assign():
current_search.flush_and_refresh("*")
literature_after = LiteratureSearch.get_record_data_from_es(literature)
literature_author = literature_after["authors"][1]
to_author_after = AuthorsRecord.get_record_by_pid_value(
to_author["control_number"])
assert literature_author["record"] == {
"$ref":
f"http://localhost:5000/api/authors/{to_author['control_number']}"
}
assert literature_author["curated_relation"]
assert literature_author["ids"] == to_author["ids"]
assert not to_author_after["stub"]
def test_indexer_oai_set_CDS(inspire_app):
extra_data = {"_export_to": {"CDS": True}}
record_data = faker.record("lit", data=extra_data)
record = LiteratureRecord.create(record_data)
record.index(delay=False)
result_record = LiteratureSearch.get_record_data_from_es(record)
expected_id = f"oai:inspirehep.net:{record['control_number']}"
expected_updated = "1994-12-19T00:00:00"
expected_sets = [inspire_app.config["OAI_SET_CDS"]]
assert expected_id == result_record["_oai"]["id"]
assert expected_updated == result_record["_oai"]["updated"]
assert expected_sets == result_record["_oai"]["sets"]
def test_indexer_oai_set_CERN_arxiv(inspire_app):
extra_data = {
"report_numbers": [{"value": "CERN-2020-001"}],
"arxiv_eprints": [{"value": "2009.01484"}],
}
record_data = faker.record("lit", data=extra_data)
record = LiteratureRecord.create(record_data)
record.index(delay=False)
result_record = LiteratureSearch.get_record_data_from_es(record)
expected_id = f"oai:inspirehep.net:{record['control_number']}"
expected_updated = "1994-12-19T00:00:00"
expected_sets = [inspire_app.config["OAI_SET_CERN_ARXIV"]]
assert expected_id == result_record["_oai"]["id"]
assert expected_updated == result_record["_oai"]["updated"]
assert expected_sets == result_record["_oai"]["sets"]
def test_indexer_does_not_have_oai_set(inspire_app):
record_data = faker.record("lit")
record = LiteratureRecord.create(record_data)
record.index(delay=False)
result_record = LiteratureSearch.get_record_data_from_es(record)
assert "_oai" not in result_record
def assert_records_in_es():
lit_record_from_es = LiteratureSearch.get_record_data_from_es(
lit_record)
assert lit_record_from_es