def _gather_wd_data(catalog, entity, works, people):
# Works IDs
data_gathering.gather_target_ids(
target_database.get_work_type(catalog, entity),
catalog,
target_database.get_work_pid(catalog),
works,
)
# People IDs
data_gathering.gather_target_ids(entity, catalog,
target_database.get_person_pid(catalog),
people)
def add_people_statements(catalog: str, statements: Iterable, criterion: str,
sandbox: bool) -> None:
"""Add statements to existing Wikidata people.
Statements typically come from validation criteria 2 or 3
as per :func:`soweego.validator.checks.links` and
:func:`soweego.validator.checks.bio`.
:param catalog: ``{'discogs', 'imdb', 'musicbrainz', 'twitter'}``.
A supported catalog
:param statements: iterable of
(subject, predicate, value, catalog ID) tuples
:param criterion: ``{'links', 'bio'}``. A supported validation criterion
:param sandbox: whether to perform edits on the Wikidata `sandbox 2`_ item
"""
if criterion == 'links':
edit_summary = LINKS_VALIDATION_SUMMARY
elif criterion == 'bio':
edit_summary = BIO_VALIDATION_SUMMARY
else:
raise ValueError(f"Invalid criterion: '{criterion}'. "
"Please use either 'links' or 'bio'")
sandbox_item = vocabulary.SANDBOX_2
catalog_qid = target_database.get_catalog_qid(catalog)
person_pid = target_database.get_person_pid(catalog)
heuristic = vocabulary.RECORD_LINKAGE
if sandbox:
LOGGER.info('Running on the Wikidata sandbox item %s ...',
sandbox_item)
for subject, predicate, value, catalog_id in statements:
LOGGER.info(
'Processing (%s, %s, %s, %s) statement ...',
subject,
predicate,
value,
catalog_id,
)
actual_subject = subject if not sandbox else sandbox_item
_add_or_reference(
(actual_subject, predicate, value),
heuristic,
catalog_qid=catalog_qid,
catalog_pid=person_pid,
catalog_id=catalog_id,
edit_summary=edit_summary,
)
def people_cli(catalog, statements, criterion, sandbox):
"""Add statements to Wikidata people.
STATEMENTS must be a CSV file.
Format: person_QID, PID, value, person_catalog_ID
If the claim already exists, just add a reference.
Example:
$ echo Q312387,P463,Q483407,264375 > joey.csv
$ python -m soweego ingester people discogs joey.csv
Result:
claim (Joey Ramone, member of, Ramones)
reference (based on heuristic, record linkage), (stated in, Discogs), (Discogs artist ID, 264375), (retrieved, today)
"""
sandbox_item = vocabulary.SANDBOX_2
# See https://www.wikidata.org/wiki/Wikidata:Project_chat/Archive/2021/07#URLs_statistics_for_Discogs_(Q504063)_and_MusicBrainz_(Q14005)
heuristic = vocabulary.RECORD_LINKAGE
catalog_qid = target_database.get_catalog_qid(catalog)
catalog_pid = target_database.get_person_pid(catalog)
if criterion == 'links':
edit_summary = LINKS_VALIDATION_SUMMARY
elif criterion == 'bio':
edit_summary = BIO_VALIDATION_SUMMARY
else:
edit_summary = None
if sandbox:
LOGGER.info('Running on the Wikidata sandbox item %s ...',
sandbox_item)
stmt_reader = csv.reader(statements)
for person, predicate, value, catalog_id in stmt_reader:
subject = person if not sandbox else sandbox_item
_add_or_reference(
(subject, predicate, value),
heuristic,
catalog_qid=catalog_qid,
catalog_pid=catalog_pid,
catalog_id=catalog_id,
edit_summary=edit_summary,
)
def _get_works_args(catalog):
# Boolean to run IMDb-specific checks
is_imdb = catalog == IMDB
catalog_qid = target_database.get_catalog_qid(catalog)
person_pid = target_database.get_person_pid(catalog)
return catalog_qid, is_imdb, person_pid