def fuzzy_match(obj, eng):
"""Return ``True`` if a similar record is found in the system.
Uses a custom configuration for ``inspire-matcher`` to find records
similar to the current workflow object's payload in the system.
Also sets the ``matches.fuzzy`` property in ``extra_data`` to the list of
the brief of first 5 record that matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the system
``False`` otherwise.
"""
if not current_app.config.get('FEATURE_FLAG_ENABLE_FUZZY_MATCHER'):
return False
fuzzy_match_config = current_app.config['FUZZY_MATCH']
matches = dedupe_list(match(obj.data, fuzzy_match_config))
record_ids = [_get_hep_record_brief(el['_source']) for el in matches]
obj.extra_data.setdefault('matches', {})['fuzzy'] = record_ids[0:5]
return bool(record_ids)
def test_match_raises_if_inner_hits_param_has_wrong_config():
config = {
'algorithm': [
{
"queries": [
{
"paths": ["first_name", "last_name"],
"search_paths":
["authors.first_name", "authors.last_name"],
"type": "nested",
"inner_hits": {
"not_existing_argument": ["authors.record"]
}
},
],
},
],
'doc_type':
'hep',
'index':
'records-hep',
}
with pytest.raises(ValueError) as excinfo:
list(match(None, config))
assert 'Malformed query' in str(excinfo.value)
def article_exists(obj, eng):
"""Return ``True`` if the record is already present in the system.
Uses the default configuration of the ``inspire-matcher`` to find
duplicates of the current workflow object in the system.
Also sets the ``record_matches`` property in ``extra_data`` to the list of
control numbers that matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the system
``False`` otherwise.
"""
matches = dedupe_list(match(obj.data))
record_ids = [el['_source']['control_number'] for el in matches]
if record_ids:
obj.extra_data['record_matches'] = record_ids
return True
obj.extra_data['record_matches'] = []
return False
def fuzzy_match(obj, eng):
"""Return ``True`` if a similar record is found in the system.
Uses a custom configuration for ``inspire-matcher`` to find records
similar to the current workflow object's payload in the system.
Also sets the ``matches.fuzzy`` property in ``extra_data`` to the list of
the brief of first 5 record that matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the system
``False`` otherwise.
"""
if not current_app.config.get('FEATURE_FLAG_ENABLE_FUZZY_MATCHER'):
return False
fuzzy_match_config = current_app.config['FUZZY_MATCH']
matches = dedupe_list(match(obj.data, fuzzy_match_config))
record_ids = [_get_hep_record_brief(el['_source']) for el in matches]
obj.extra_data.setdefault('matches', {})['fuzzy'] = record_ids[0:5]
return bool(record_ids)
def match_literature_author_with_config(author_data, matcher_config):
matched_records = [
matched_record for matched_record in match(author_data, matcher_config)
if get_value(matched_record,
"inner_hits.authors.hits.hits[0]._source.record.$ref")
]
return matched_records
def article_exists(obj, eng):
"""Return ``True`` if the record is already present in the system.
Uses the default configuration of the ``inspire-matcher`` to find
duplicates of the current workflow object in the system.
Also sets the ``record_matches`` property in ``extra_data`` to the list of
control numbers that matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the system
``False`` otherwise.
"""
matches = dedupe_list(match(obj.data))
record_ids = [el['_source']['control_number'] for el in matches]
if record_ids:
obj.extra_data['record_matches'] = record_ids
return True
obj.extra_data['record_matches'] = []
return False
def test_match_raises_if_the_configuration_does_not_have_all_the_keys():
config = {
'doc_type': 'hep',
'index': 'records-hep',
}
with pytest.raises(KeyError) as excinfo:
list(match(None, config))
assert 'Malformed configuration' in str(excinfo.value)
def match_author(author):
matched_authors = match(author, current_app.config["AUTHOR_MATCHER_EXACT_CONFIG"])
matched_refs_ids = {
matched_author["_source"]["self"]["$ref"]: matched_author["_source"].get(
"ids", []
)
for matched_author in matched_authors
}
matched_author_data = get_reference_and_bai_if_unambiguous_match(matched_refs_ids)
return matched_author_data
def test_match_raises_if_one_step_of_the_algorithm_has_no_queries():
config = {
'algorithm': [
{'validator': 'inspire_matcher.validators:default_validator'},
],
'doc_type': 'hep',
'index': 'records-hep',
}
with pytest.raises(KeyError) as excinfo:
list(match(None, config))
assert 'Malformed algorithm' in str(excinfo.value)
def pending_in_holding_pen(obj, eng):
"""Return ``True`` if the record is already present in the Holding Pen.
Uses a custom configuration of the ``inspire-matcher`` to find duplicates
of the current workflow object in the Holding Pen.
Also sets ``holdingpen_matches`` in ``extra_data`` to the list of ids that
matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the Holding
Pen, ``False`` otherwise.
"""
config = {
'algorithm': [
{
'queries': [
{
'path': 'arxiv_eprints.value',
'search_path': 'metadata.arxiv_eprints.value.raw',
'type': 'exact',
},
{
'path': 'dois.value',
'search_path': 'metadata.dois.value.raw',
'type': 'exact',
},
],
},
],
'doc_type':
'hep',
'index':
'holdingpen-hep',
}
matches = dedupe_list(match(obj.data, config))
holdingpen_ids = [
int(el['_id']) for el in matches if int(el['_id']) != obj.id
]
if holdingpen_ids:
obj.extra_data['holdingpen_matches'] = holdingpen_ids
return True
return False
def duplicated_validator(property_name, property_value):
def _is_not_deleted(base_record, match_result):
return not get_value(match_result, '_source.deleted', default=False)
config = {
'algorithm': [
{
'queries': [
{
'path': 'arxiv_id',
'search_path': 'arxiv_eprints.value.raw',
'type': 'exact',
},
{
'path': 'doi',
'search_path': 'dois.value.raw',
'type': 'exact',
},
],
'validator':
_is_not_deleted,
},
],
'doc_type':
'hep',
'index':
'records-hep',
}
if property_name == 'arXiv ID':
data = {
'arxiv_id': property_value,
}
if property_name == 'DOI':
data = {
'doi': property_value,
}
matches = dedupe_list(match(data, config))
matched_ids = [int(el['_source']['control_number']) for el in matches]
if matched_ids:
url = url_for(
'invenio_records_ui.literature',
pid_value=matched_ids[0],
)
raise ValidationError(
'There exists already an item with the same %s. '
'<a target="_blank" href="%s">See the record.</a>' %
(property_name, url))
def test_match_raises_if_one_query_does_not_have_a_type():
config = {
'algorithm': [
{
'queries': [
{},
],
},
],
'doc_type': 'hep',
'index': 'records-hep',
}
with pytest.raises(ValueError) as excinfo:
list(match(None, config))
assert 'Malformed query' in str(excinfo.value)
def test_match_raises_if_one_query_type_is_not_supported():
config = {
'algorithm': [
{
'queries': [
{'type': 'not-supported'},
],
},
],
'doc_type': 'records',
'index': 'records-hep',
}
with pytest.raises(ValueError) as excinfo:
list(match(None, config))
assert 'Malformed query. Query 0 of step 0 does not compile: type "not-supported" is not supported.' in str(excinfo.value)
def duplicated_validator(property_name, property_value):
def _is_not_deleted(base_record, match_result):
return not get_value(match_result, '_source.deleted', default=False)
config = {
'algorithm': [
{
'queries': [
{
'path': 'arxiv_id',
'search_path': 'arxiv_eprints.value.raw',
'type': 'exact',
},
{
'path': 'doi',
'search_path': 'dois.value.raw',
'type': 'exact',
},
],
'validator': _is_not_deleted,
},
],
'doc_type': 'hep',
'index': 'records-hep',
}
if property_name == 'arXiv ID':
data = {
'arxiv_id': property_value,
}
if property_name == 'DOI':
data = {
'doi': property_value,
}
matches = dedupe_list(match(data, config))
matched_ids = [int(el['_source']['control_number']) for el in matches]
if matched_ids:
url = url_for(
'invenio_records_ui.literature',
pid_value=matched_ids[0],
)
raise ValidationError(
'There exists already an item with the same %s. '
'<a target="_blank" href="%s">See the record.</a>'
% (property_name, url)
)
def update_references_pointing_to_merged_record(refs_to_schema,
merged_record_uri,
new_record_uri):
for index, path in refs_to_schema:
config = get_config_for_given_path(index, path)
matched_records = match({"$ref": merged_record_uri}, config)
for matched_record in matched_records:
matched_inspire_record = InspireRecord.get_record(
matched_record["_id"], with_deleted=True)
referenced_records_in_path = flatten_list(
get_value(matched_inspire_record, path[:-len(".$ref")], []))
for referenced_record in referenced_records_in_path:
update_reference_if_reference_uri_matches(
referenced_record, merged_record_uri, new_record_uri)
matched_inspire_record.update(dict(matched_inspire_record))
LOGGER.info("Updated reference for record",
uuid=str(matched_inspire_record.id))
db.session.commit()
def test_validator_list(es_mock):
es_mock.search.return_value = {
'hits': {
'hits': {
'dummy result',
}
}
}
dummy_validator_1 = mock.Mock()
dummy_validator_1.return_value = True
dummy_validator_2 = mock.Mock()
dummy_validator_2.return_value = True
config = {
'algorithm': [
{
'queries': [
{
'type': 'exact',
'path': 'dummy.path',
'search_path': 'dummy.search.path',
},
],
'validator': [dummy_validator_1, dummy_validator_2],
},
],
'doc_type':
'hep',
'index':
'records-hep',
}
record = {
'dummy': {
'path': 'Non empty value',
},
}
result = list(match(record, config))
assert 'dummy result' in result
dummy_validator_1.assert_called_with(record, 'dummy result')
dummy_validator_2.assert_called_with(record, 'dummy result')
def test_match_raises_if_an_exact_query_does_not_have_all_the_keys():
config = {
'algorithm': [
{
'queries': [
{
'search_path': 'arxiv_eprints.value.raw',
'type': 'exact',
},
],
},
],
'doc_type': 'hep',
'index': 'records-hep',
}
with pytest.raises(ValueError) as excinfo:
list(match(None, config))
assert 'Malformed query' in str(excinfo.value)
def _pending_in_holding_pen(obj, validation_func):
"""Return the list of matching workflows in the holdingpen.
Matches the holdingpen records by their ``arxiv_eprint``, their ``doi``,
and by a custom validator function.
Args:
obj: a workflow object.
validation_func: a function used to filter the matched records.
Returns:
(list): the ids matching the current ``obj`` that satisfy
``validation_func``.
"""
config = {
'algorithm': [
{
'queries': [
{
'path': 'arxiv_eprints.value',
'search_path': 'metadata.arxiv_eprints.value.raw',
'type': 'exact',
},
{
'path': 'dois.value',
'search_path': 'metadata.dois.value.raw',
'type': 'exact',
},
],
'validator':
validation_func,
},
],
'doc_type':
'hep',
'index':
'holdingpen-hep',
}
matches = dedupe_list(match(obj.data, config))
return [int(el['_id']) for el in matches if int(el['_id']) != obj.id]
def test_match_raises_on_invalid_collections():
config = {
'algorithm': [
{
'queries': [
{
'search_path': 'arxiv_eprints.value.raw',
'path': 'arxiv_eprints.value',
'type': 'exact',
},
],
},
],
'doc_type': 'hep',
'index': 'records-hep',
'collections': 'Literature',
}
with pytest.raises(ValueError) as excinfo:
list(match(None, config))
assert 'Malformed collections' in str(excinfo.value)
def test_match_uses_the_given_validator_callable(es_mock):
es_mock.search.return_value = {
'hits': {
'hits': {
'dummy result',
}
}
}
dummy_validator = mock.Mock()
dummy_validator.return_value = False
config = {
'algorithm': [
{
'queries': [
{
'type': 'exact',
'path': 'dummy.path',
'search_path': 'dummy.search.path',
},
],
'validator':
dummy_validator,
},
],
'doc_type':
'hep',
'index':
'records-hep',
}
record = {
'dummy': {
'path': 'Non empty value',
},
}
result = list(match(record, config))
assert not result
dummy_validator.assert_called_with(record, 'dummy result')
def _pending_in_holding_pen(obj, validation_func):
"""Return the list of matching workflows in the holdingpen.
Matches the holdingpen records by their ``arxiv_eprint``, their ``doi``,
and by a custom validator function.
Args:
obj: a workflow object.
validation_func: a function used to filter the matched records.
Returns:
(list): the ids matching the current ``obj`` that satisfy
``validation_func``.
"""
config = {
'algorithm': [
{
'queries': [
{
'path': 'arxiv_eprints.value',
'search_path': 'metadata.arxiv_eprints.value.raw',
'type': 'exact',
},
{
'path': 'dois.value',
'search_path': 'metadata.dois.value.raw',
'type': 'exact',
},
],
'validator': validation_func,
},
],
'doc_type': 'hep',
'index': 'holdingpen-hep',
}
matches = dedupe_list(match(obj.data, config))
return [int(el['_id']) for el in matches if int(el['_id']) != obj.id]
def exact_match(obj, eng):
"""Return ``True`` if the record is already present in the system.
Uses the default configuration of the ``inspire-matcher`` to find
duplicates of the current workflow object in the system.
Also sets the ``matches.exact`` property in ``extra_data`` to the list of
control numbers that matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the system
``False`` otherwise.
"""
exact_match_config = current_app.config['EXACT_MATCH']
matches = dedupe_list(match(obj.data, exact_match_config))
record_ids = [el['_source']['control_number'] for el in matches]
obj.extra_data.setdefault('matches', {})['exact'] = record_ids
return bool(record_ids)
def exact_match(obj, eng):
"""Return ``True`` if the record is already present in the system.
Uses the default configuration of the ``inspire-matcher`` to find
duplicates of the current workflow object in the system.
Also sets the ``matches.exact`` property in ``extra_data`` to the list of
control numbers that matched.
Arguments:
obj: a workflow object.
eng: a workflow engine.
Returns:
bool: ``True`` if the workflow object has a duplicate in the system
``False`` otherwise.
"""
exact_match_config = current_app.config['EXACT_MATCH']
matches = dedupe_list(match(obj.data, exact_match_config))
record_ids = [el['_source']['control_number'] for el in matches]
obj.extra_data.setdefault('matches', {})['exact'] = record_ids
return bool(record_ids)
