def test_orcids_for_push_orcid_in_author_with_claim(author_in_isolated_app):
record = {
'_collections': ['Literature'],
'authors': [
{
'full_name': 'No Orcid, Jimmy',
},
{
'full_name': 'Smith, John',
'ids': [
{
'schema': 'INSPIRE BAI',
'value': 'J.Smith.1',
},
],
'record': get_record_ref(author_in_isolated_app, 'authors'),
'curated_relation': True,
},
],
'document_type': ['article'],
'titles': [
{'title': 'An interesting paper'},
],
}
assert validate(record, 'hep') is None
assert list(get_orcids_for_push(record)) == ['0000-0002-1825-0097']
def test_orcids_for_push_orcid_in_author_with_claim(author_in_isolated_app):
record = {
"_collections": ["Literature"],
"authors": [
{
"full_name": "No Orcid, Jimmy"
},
{
"full_name": "Smith, John",
"ids": [{
"schema": "INSPIRE BAI",
"value": "J.Smith.1"
}],
"record": get_record_ref(author_in_isolated_app),
"curated_relation": True,
},
],
"document_type": ["article"],
"titles": [{
"title": "An interesting paper"
}],
}
assert validate(record, "hep") is None
assert list(get_orcids_for_push(record)) == ["0000-0002-1825-0097"]
def match_reference(reference):
"""Match references given a reference metadata using InspireMatcher queires.
Args:
reference: The reference metadata
config: The configurtaion(s) for InspireMatcher queries
Returns:
The record ID of the matched reference
"""
config_default = current_app.config[
'WORKFLOWS_REFERENCE_MATCHER_DEFAULT_CONFIG']
config_jcap_and_jhep = current_app.config[
'WORKFLOWS_REFERENCE_MATCHER_JHEP_AND_JCAP_CONFIG']
journal_title = get_value(reference,
'reference.publication_info.journal_title')
config = config_jcap_and_jhep if journal_title in ['JCAP', 'JHEP'
] else config_default
result = next(match(reference, config), None)
if result:
matched_recid = result['_source']['control_number']
reference['record'] = get_record_ref(matched_recid, 'literature')
return reference
def test_orcids_for_push_orcid_in_author_with_claim(author_in_isolated_app):
record = {
'_collections': ['Literature'],
'authors': [
{
'full_name': 'No Orcid, Jimmy',
},
{
'full_name': 'Smith, John',
'ids': [
{
'schema': 'INSPIRE BAI',
'value': 'J.Smith.1',
},
],
'record': get_record_ref(author_in_isolated_app, 'authors'),
'curated_relation': True,
},
],
'document_type': ['article'],
'titles': [
{
'title': 'An interesting paper'
},
],
}
assert validate(record, 'hep') is None
assert list(get_orcids_for_push(record)) == ['0000-0002-1825-0097']
def link_signature_to_author(signature_data, author_control_number):
"""Adds record/$ref of the given author to the given signature.
Args:
author_control_number (int): The control number of the author to which we want to link.
signature_data (list): List containing 2 elements: the publication_id and the signature uuid.
Returns:
dict: The signature data from the publication with the linked author.
"""
record = LiteratureRecord.get_record_by_pid_value(
signature_data["publication_id"])
signature = next(
(author for author in record.get("authors")
if author.get("uuid") == signature_data["signature_uuid"]),
None,
)
if not signature or ("record" in signature
and signature.get("curated_relation")):
return None
if signature.get("curated_relation") and "record" not in signature:
signature["curated_relation"] = False
new_author_record = get_record_ref(author_control_number, "authors")
if new_author_record == signature.get("record"):
# no changes, avoid creating a new useless version of the record
return None
signature["record"] = new_author_record
record.update(dict(record))
return signature
def test_get_record_ref_with_empty_server_name():
config = {'SERVER_NAME': None}
with patch.dict(current_app.config, config):
expected = 'http://inspirehep.net/api/endpoint/123'
result = get_record_ref(123, 'endpoint')
assert expected == result['$ref']
def test_get_record_ref_with_server_name_localhost():
config = {'SERVER_NAME': 'localhost:5000'}
with patch.dict(current_app.config, config):
expected = 'http://localhost:5000/api/endpoint/123'
result = get_record_ref(123, 'endpoint')
assert expected == result['$ref']
def test_get_record_ref_without_endpoint_defaults_to_record():
config = {'SERVER_NAME': None}
with patch.dict(current_app.config, config):
expected = 'http://inspirehep.net/api/record/123'
result = get_record_ref(123)
assert expected == result['$ref']
def test_get_record_ref_with_https_server_name():
config = {'SERVER_NAME': 'https://example.com'}
with patch.dict(current_app.config, config):
expected = 'https://example.com/api/endpoint/123'
result = get_record_ref(123, 'endpoint')
assert expected == result['$ref']
def assign_papers(from_author_recid, to_author_recid, literature_recids):
author_signatures = []
for record in get_literature_records_by_recid(literature_recids):
from_author = get_author_by_recid(record, from_author_recid)
from_author["record"] = get_record_ref(to_author_recid, endpoint="authors")
from_author["curated_relation"] = True
author_signatures.append(from_author)
record.update(dict(record))
return author_signatures
def store_records(obj, eng):
"""Store the records involved in the manual merge.
Performs the following steps:
1. Updates the ``head`` so that it contains the result of the merge.
2. Marks the ``update`` as merged with the ``head`` and deletes it.
3. Populates the ``deleted_records`` and ``new_record`` keys in,
respectively, ``head`` and ``update`` so that they contain a JSON
reference to each other.
Todo:
The last step should be performed by the ``merge`` method itself.
Args:
obj: a workflow object.
eng: a workflow engine.
Returns:
None
"""
head_control_number = obj.extra_data['head_control_number']
update_control_number = obj.extra_data['update_control_number']
head = get_db_record('lit', head_control_number)
update = get_db_record('lit', update_control_number)
# 1. Updates the head so that it contains the result of the merge.
head.clear()
head.update(obj.data)
# 2. Marks the update as merged with the head and deletes it.
update.merge(head)
update.delete()
# 3. Populates the deleted_records and new_record keys.
update['new_record'] = get_record_ref(head_control_number, 'literature')
update_ref = get_record_ref(update_control_number, 'literature')
head.setdefault('deleted_records', []).append(update_ref)
head.commit()
update.commit()
db.session.commit()
def assign_papers(
from_author_recid, to_author_record, author_papers, is_stub_author=False
):
author_bai = get_values_for_schema(to_author_record["ids"], "INSPIRE BAI")[0]
for record in author_papers:
lit_author = get_author_by_recid(record, from_author_recid)
lit_author["record"] = get_record_ref(
to_author_record["control_number"], endpoint="authors"
)
if not is_stub_author:
lit_author["curated_relation"] = True
lit_author["ids"] = update_author_bai(author_bai, lit_author)
record.update(dict(record))
def store_records(obj, eng):
"""Store the records involved in the manual merge.
Update the head with the deleted record and send it to hep.
Args:
obj: a workflow object.
eng: a workflow engine.
Returns:
None
"""
head_control_number = obj.extra_data['head_control_number']
update_control_number = obj.extra_data['update_control_number']
head = dict(obj.data)
update_ref = get_record_ref(update_control_number, 'literature')
head.setdefault('deleted_records', []).append(update_ref)
put_record_to_hep('lit', head_control_number, data=obj.data)
def assign_papers(
self,
from_author_recid,
to_author_record,
author_papers_recids,
is_stub_author=False,
):
author_bai = get_values_for_schema(to_author_record["ids"],
"INSPIRE BAI")[0]
for recid in author_papers_recids:
record = LiteratureRecord.get_record_by_pid_value(recid)
lit_author = get_author_by_recid(record, from_author_recid)
lit_author["record"] = get_record_ref(
to_author_record["control_number"], endpoint="authors")
if not is_stub_author:
lit_author["curated_relation"] = True
lit_author["ids"] = update_author_bai(author_bai, lit_author)
record.update(dict(record))
db.session.commit()
def _add_match_to_reference(reference, matched_recid, es_index):
"""Modifies a reference to include its record id."""
if es_index == "records-data":
reference["record"] = get_record_ref(matched_recid, "data")
elif es_index == "records-hep":
reference["record"] = get_record_ref(matched_recid, "literature")
def create_author(profile):
"""Create a new author profile based on a given signature.
The method receives a dictionary representing an author.
Based on the values, it creates a dictionary in the invenio_records format.
After all the fields are processed, the method calls create_record
from invenio_records.api to put the new record.
:param profile:
A signature representing an author's to be created as a profile.
Example:
profile = {u'affiliations': [{u'value': u'Yerevan Phys. Inst.'}],
u'alternative_name': None,
u'curated_relation': False,
u'email': None,
u'full_name': u'Chatrchyan, Serguei',
u'inspire_id': None,
u'orcid': None,
u'profile': u'',
u'recid': None,
u'role': None,
u'uuid': u'd63537a8-1df4-4436-b5ed-224da5b5028c'}
:return:
A recid, where the new profile can be accessed.
Example:
"1234"
"""
name = profile.get('full_name')
# Template of an initial record.
record = {
'$schema': _get_author_schema(),
'_collections': ['Authors'],
'name': {
'value': name
},
}
# The author's email address.
# Unfortunately the method will not correlate a given e-mail address
# with an affiliation.
if 'email' in profile:
email = profile.get('email')
record['positions'] = []
record['positions'].append({'email': email})
# The author can be a member of more than one affiliation.
if 'affiliations' in profile:
affiliations = profile.get('affiliations')
if 'positions' not in record:
record['positions'] = []
for affiliation in affiliations:
name = affiliation.get('value')
recid = affiliation.get('recid', None)
if recid:
record['positions'].append(
{'institution': {
'name': name,
'recid': recid
}})
else:
record['positions'].append({'institution': {'name': name}})
# FIXME: The method should also collect the useful data
# from the publication, like category field, subject,
# etc.
# Disconnect the signal on insert of a new record.
after_record_insert.disconnect(append_new_record_to_queue)
# Create a new author profile.
record = InspireRecord.create(record, id_=None)
# Create Inspire recid.
record_pid = inspire_recid_minter(record.id, record)
# Extend the new record with Inspire recid and self key.
record['control_number'] = record_pid.pid_value
record['self'] = inspire_dojson_utils.get_record_ref(
record_pid.pid_value, 'authors')
# Apply the changes.
record.commit()
db.session.commit()
# Reconnect the disconnected signal.
after_record_insert.connect(append_new_record_to_queue)
# Report.
logger.info("Created profile: %s", record_pid.pid_value)
# Return the recid of new profile to which signatures will point to.
return record_pid.pid_value
def _add_match_to_reference(reference, matched_recid, es_index):
"""Modifies a reference to include its record id."""
if es_index == 'records-data':
reference['record'] = get_record_ref(matched_recid, 'data')
elif es_index == 'records-hep':
reference['record'] = get_record_ref(matched_recid, 'literature')
def test_get_record_ref_without_recid_returns_none():
assert get_record_ref(None, 'endpoint') is None
def _add_match_to_reference(reference, matched_recid, es_index):
"""Modifies a reference to include its record id."""
if es_index == 'records-data':
reference['record'] = get_record_ref(matched_recid, 'data')
elif es_index == 'records-hep':
reference['record'] = get_record_ref(matched_recid, 'literature')
def get_ref_from_pid(pid_type, pid_value):
"""Return full $ref for record with pid_type and pid_value"""
return get_record_ref(pid_value,
PidStoreBase.get_endpoint_from_pid_type(pid_type))
