def test_match_references_finds_match_when_repeated_record_with_different_scores(
mocked_inspire_matcher_match, inspire_app):
references = [{
"reference": {
"publication_info": {
"artid": "045",
"journal_title": "JHEP",
"journal_volume": "06",
"page_start": "045",
"year": 2007,
}
}
}]
schema = load_schema("hep")
subschema = schema["properties"]["references"]
assert validate(references, subschema) is None
match_result = match_references(references)
references = match_result["matched_references"]
assert len(references) == 1
assert references[0]["record"][
"$ref"] == "http://localhost:5000/api/literature/1"
assert validate(references, subschema) is None
assert match_result["any_link_modified"]
assert match_result["added_recids"] == [1]
assert match_result["removed_recids"] == []
def refextract_url():
"""Run refextract on a URL."""
if current_app.config.get("FEATURE_FLAG_ENABLE_REFEXTRACT_SERVICE"):
headers = {
"Content-Type": "application/json",
"Accept": "application/json"
}
data = {
"journal_kb_data": create_journal_dict(),
"url": request.json["url"]
}
response = requests.post(
f"{current_app.config['REFEXTRACT_SERVICE_URL']}/extract_references_from_url",
headers=headers,
data=orjson.dumps(data),
)
if response.status_code != 200:
return jsonify({"message": "Can not extract references"}, 500)
extracted_references = response.json()["extracted_references"]
else:
extracted_references = extract_references_from_url(
request.json["url"],
override_kbs_files={"journals": create_journal_dict()},
reference_format="{title},{volume},{page}",
)
deduplicated_extracted_references = dedupe_list(extracted_references)
references = map_refextract_to_schema(deduplicated_extracted_references)
match_result = match_references(references)
return jsonify(match_result.get("matched_references"))
def refextract_url():
"""Run refextract on a URL."""
extracted_references = extract_references_from_url(
request.json["url"],
override_kbs_files={"journals": create_journal_dict()},
reference_format="{title},{volume},{page}",
)
references = map_refextract_to_schema(extracted_references)
match_result = match_references(references)
return jsonify(match_result.get("matched_references"))
def refextract_url():
"""Run refextract on a URL."""
with local_refextract_kbs_path() as kbs_path:
extracted_references = extract_references_from_url(
request.json["url"],
override_kbs_files=kbs_path,
reference_format="{title},{volume},{page}",
)
references = map_refextract_to_schema(extracted_references)
match_result = match_references(references)
return jsonify(match_result.get("matched_references"))
def refextract_text():
"""Run refextract on a piece of text."""
with local_refextract_kbs_path() as kbs_path:
extracted_references = extract_references_from_string(
request.json["text"],
override_kbs_files=kbs_path,
reference_format="{title},{volume},{page}",
)
references = map_refextract_to_schema(extracted_references)
references = match_references(references)
return jsonify(references)
def test_match_references_doesnt_use_relaxed_title_matching(inspire_app):
non_cited_record_with_pub_info_json = {
"$schema":
"http://localhost:5000/schemas/records/hep.json",
"_collections": ["Literature"],
"control_number":
1,
"document_type": ["article"],
"publication_info": [{
"artid": "101",
"journal_title": "Phys. Rev. B.",
"journal_volume": "100",
"page_start": "100",
"year": 2020,
}],
"titles": [{
"title": "The Strongly-Interacting Light Higgs"
}],
}
create_record("lit", non_cited_record_with_pub_info_json)
cited_record_with_pub_info_json = {
"$schema": "http://localhost:5000/schemas/records/hep.json",
"_collections": ["Literature"],
"control_number": 2,
"document_type": ["article"],
"texkeys": ["Shaikh:2022ynt"],
"titles": [{
"title": "The Strongly-Interacting Light Higgs"
}],
}
create_record("lit", cited_record_with_pub_info_json)
references = [{
"reference": {
"publication_info": {
"journal_title": "Phys. Rev.",
"journal_volume": "100",
"page_start": "100",
},
"texkey": "Shaikh:2022ynt",
}
}]
expected_ref = {"$ref": "http://localhost:5000/api/literature/2"}
result = match_references(references)
assert expected_ref == result["matched_references"][0]["record"]
def test_match_references_no_match_when_multiple_match_different_from_previous(
inspire_app, ):
"""Test reference matcher for when inspire-matcher returns multiple matches
where the matched record id is not the same as the previous matched record id"""
original_cited_record_json = {
"$schema":
"http://localhost:5000/schemas/records/hep.json",
"_collections": ["Literature"],
"control_number":
1,
"document_type": ["article"],
"publication_info": [
{
"artid": "159",
"journal_title": "JHEP",
"journal_volume": "03",
"page_start": "159",
"year": 2016,
},
{
"artid": "074",
"journal_title": "JHEP",
"journal_volume": "05",
"material": "erratum",
"page_start": "074",
"year": 2017,
},
],
}
errata_cited_record_json = {
"$schema":
"http://localhost:5000/schemas/records/hep.json",
"_collections": ["Literature"],
"control_number":
2,
"document_type": ["article"],
"publication_info": [{
"artid": "074",
"journal_title": "JHEP",
"journal_volume": "05",
"material": "erratum",
"page_start": "074",
"year": 2017,
}],
}
create_record("lit", data=original_cited_record_json)
create_record("lit", data=errata_cited_record_json)
references = [{
"reference": {
"publication_info": {
"artid": "074",
"journal_title": "JHEP",
"journal_volume": "05",
"page_start": "074",
"year": 2017,
}
}
}]
schema = load_schema("hep")
subschema = schema["properties"]["references"]
assert validate(references, subschema) is None
references = match_references(references)
assert get_value(references[0], "record") is None
assert validate(references, subschema) is None
def test_match_references_matches_when_multiple_match_if_same_as_previous(
inspire_app):
"""Test reference matcher for when inspire-matcher returns multiple matches
where the matched record id is one of the previous matched record id as well"""
original_cited_record_json = {
"$schema":
"http://localhost:5000/schemas/records/hep.json",
"_collections": ["Literature"],
"control_number":
1,
"document_type": ["article"],
"publication_info": [
{
"artid": "159",
"journal_title": "JHEP",
"journal_volume": "03",
"page_start": "159",
"year": 2016,
},
{
"artid": "074",
"journal_title": "JHEP",
"journal_volume": "05",
"material": "erratum",
"page_start": "074",
"year": 2017,
},
],
}
errata_cited_record_json = {
"$schema":
"http://localhost:5000/schemas/records/hep.json",
"_collections": ["Literature"],
"control_number":
2,
"document_type": ["article"],
"publication_info": [{
"artid": "074",
"journal_title": "JHEP",
"journal_volume": "05",
"material": "erratum",
"page_start": "074",
"year": 2017,
}],
}
create_record("lit", data=original_cited_record_json)
create_record("lit", data=errata_cited_record_json)
references = [
{
"reference": {
"publication_info": {
"artid": "159",
"journal_title": "JHEP",
"journal_volume": "03",
"page_start": "159",
"year": 2016,
}
}
},
{
"reference": {
"publication_info": {
"artid": "074",
"journal_title": "JHEP",
"journal_volume": "05",
"page_start": "074",
"year": 2017,
}
}
},
]
schema = load_schema("hep")
subschema = schema["properties"]["references"]
assert validate(references, subschema) is None
match_result = match_references(references)
matched_references = match_result["matched_references"]
assert (matched_references[1]["record"]["$ref"] ==
"http://localhost:5000/api/literature/1")
assert validate(matched_references, subschema) is None
assert match_result["any_link_modified"]
assert match_result["added_recids"] == [1, 1]
assert match_result["removed_recids"] == []
def get_linked_refs():
data = request.json
match_result = match_references(data["references"])
return jsonify({"references": match_result.get("matched_references")})
