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_map_refextract_to_schema():
refextract_input = [{
"author": [u"F. Englert and R. Brout"],
"doi": [u"doi:10.1103/PhysRevLett.13.321"],
"journal_page": [u"321"],
"journal_reference": [u"Phys. Rev. Lett. 13 (1964) 321"],
"journal_title": [u"Phys. Rev. Lett."],
"journal_volume": [u"13"],
"journal_year": [u"1964"],
"linemarker": [u"1"],
"raw_ref": [
u"[1] F. Englert and R. Brout, \u201cBroken symmetry and the mass of gauge vector mesons\u201d, Phys. Rev. Lett. 13 (1964) 321, doi:10.1103/PhysRevLett.13.321."
],
"texkey": [u"Englert:1964et"],
"year": [u"1964"],
}]
expected_output = [{
"reference": {
"authors": [{
"full_name": "Englert, F."
}, {
"full_name": "Brout, R."
}],
"dois": ["10.1103/PhysRevLett.13.321"],
"misc": ["Phys. Rev. Lett. 13 (1964) 321"],
"label": "1",
"texkey": "Englert:1964et",
"publication_info": {
"year": 1964
},
},
"raw_refs": [{
"schema":
"text",
"value":
"[1] F. Englert and R. Brout, “Broken symmetry and the mass of gauge vector mesons”, Phys. Rev. Lett. 13 (1964) 321, doi:10.1103/PhysRevLett.13.321.",
}],
}]
result = map_refextract_to_schema(refextract_input)
assert result == expected_output