def match_reference_control_numbers_with_relaxed_journal_titles(reference):
"""Match reference and return the `control_number`.
Args:
reference (dict): the metadata of a reference.
Returns:
list: list of matched recids or None.
"""
if reference.get("curated_relation"):
try:
return [get_recid_from_ref(reference["record"])]
except KeyError:
return None
configs = match_reference_config(reference,
use_relaxed_titles_matching=True)
matches = set()
for config in configs:
matched_recids = [
matched_record["_source"]["control_number"]
for matched_record in match(reference, config)
]
matches.update(matched_recids)
matches = list(matches)[0:5]
return matches
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 match_reference_with_config(reference,
config,
previous_matched_recid=None):
"""Match a reference using inspire-matcher given the config.
Args:
reference (dict): the metadata of the reference.
config (dict): the list of inspire-matcher configurations for queries.
previous_matched_recid (int): the record id of the last matched
reference from the list of references.
Returns:
dict: the matched reference.
"""
# XXX: avoid this type casting.
try:
reference['reference']['publication_info']['year'] = str(
reference['reference']['publication_info']['year'])
except KeyError:
pass
matched_recids = [
matched_record['_source']['control_number']
for matched_record in match(reference, config)
]
matched_recids = dedupe_list(matched_recids)
same_as_previous = any(matched_recid == previous_matched_recid
for matched_recid in matched_recids)
if len(matched_recids) == 1:
_add_match_to_reference(reference, matched_recids[0], config['index'])
elif same_as_previous:
_add_match_to_reference(reference, previous_matched_recid,
config['index'])
# XXX: avoid this type casting.
try:
reference['reference']['publication_info']['year'] = int(
reference['reference']['publication_info']['year'])
except KeyError:
pass
return reference
def match_reference_with_config(reference, config, previous_matched_recid=None):
"""Match a reference using inspire-matcher given the config.
Args:
reference (dict): the metadata of the reference.
config (dict): the list of inspire-matcher configurations for queries.
previous_matched_recid (int): the record id of the last matched
reference from the list of references.
Returns:
dict: the matched reference.
"""
# XXX: avoid this type casting.
try:
reference['reference']['publication_info']['year'] = str(
reference['reference']['publication_info']['year'])
except KeyError:
pass
matched_recids = [matched_record['_source']['control_number'] for matched_record in match(reference, config)]
matched_recids = dedupe_list(matched_recids)
same_as_previous = any(matched_recid == previous_matched_recid for matched_recid in matched_recids)
if len(matched_recids) == 1:
_add_match_to_reference(reference, matched_recids[0], config['index'])
elif same_as_previous:
_add_match_to_reference(reference, previous_matched_recid, config['index'])
# XXX: avoid this type casting.
try:
reference['reference']['publication_info']['year'] = int(
reference['reference']['publication_info']['year'])
except KeyError:
pass
return reference