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 test_create_journal_dict(inspire_app):
data = {
"journal_title": {
"title": "Journal of Physical Science and Application"
},
"short_title": "J.Phys.Sci.Appl.",
"title_variants": ["PHYS SCI APPL"],
}
create_record("jou", data=data)
data = {
"journal_title": {
"title": "Image and Vision Computing"
},
"short_title": "Image Vision Comput.",
"title_variants": ["IMAGE VISION COMPUT", "IMAGE VISION - COMPUTING"],
}
create_record("jou", data=data)
expected = {
"J PHYS SCI APPL": "J.Phys.Sci.Appl.",
"JOURNAL OF PHYSICAL SCIENCE AND APPLICATION": "J.Phys.Sci.Appl.",
"PHYS SCI APPL": "J.Phys.Sci.Appl.",
"IMAGE VISION COMPUT": "Image Vision Comput.",
"IMAGE AND VISION COMPUTING": "Image Vision Comput.",
"IMAGE VISION COMPUTING": "Image Vision Comput.",
}
result = create_journal_dict()
assert expected == result
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"))