def index_after_commit(sender, changes):
"""Index a record in ES after it was committed to the DB.
This cannot happen in an ``after_record_commit`` receiver from Invenio-Records
because, despite the name, at that point we are not yet sure whether the record
has been really committed to the DB.
"""
for model_instance, change in changes:
if isinstance(model_instance, RecordMetadata):
if change in ("insert", "update", "delete"):
LOGGER.debug(f"Record commited",
change=change,
uuid=str(model_instance.id))
pid_type = PidStoreBase.get_pid_type_from_schema(
model_instance.json.get("$schema"))
delete = "delete" in changes
arguments = InspireRecord.get_subclasses(
)[pid_type]._record_index(model_instance.json,
_id=str(model_instance.id),
force_delete=delete)
arguments["record_version"] = model_instance.version_id
LOGGER.debug(
f"Record sending to index",
uuid=str(model_instance.id),
delete=delete,
)
current_celery_app.send_task(
"inspirehep.records.indexer.tasks.index_record",
kwargs=arguments)
else:
raise RuntimeError("Wrong operation `%s` on record %r", change,
model_instance.id)
def assign_to_author(from_author_recid, to_author_recid, literature_recids):
author_record = AuthorsRecord.get_record_by_pid_value(to_author_recid)
num_workers = count_consumers_for_queue("assign")
for batch in chunker(literature_recids, 10, num_workers):
current_celery_app.send_task(
"inspirehep.assign.tasks.assign_papers",
kwargs={
"from_author_recid": from_author_recid,
"to_author_record": author_record,
"author_papers_recids": batch,
},
)
unstub_author_by_recid(to_author_recid)
def push_to_hal(record):
"""If needed, queue the push of the new changes to HAL."""
if not current_app.config["FEATURE_FLAG_ENABLE_HAL_PUSH"]:
LOGGER.info("HAL push feature flag not enabled")
return
# Ensure there is a control number. This is not always the case because of broken store_record.
if "control_number" not in record:
return
if is_hal_set(record):
current_celery_app.send_task(
"inspirehep.hal.tasks.hal_push",
kwargs={"recid": record["control_number"]})
def assign_to_new_stub_author(from_author_recid, literature_recids):
# TODO: differentiate from BEARD created stub author
author_papers = get_literature_records_by_recid(literature_recids)
author_signatures = get_author_signatures(from_author_recid, author_papers)
stub_author_data = update_author_names({"name": {}}, author_signatures)
to_author = create_new_stub_author(**stub_author_data)
num_workers = count_consumers_for_queue("assign")
for batch in chunker(literature_recids, 10, num_workers):
current_celery_app.send_task(
"inspirehep.assign.tasks.assign_papers",
kwargs={
"from_author_recid": from_author_recid,
"to_author_record": to_author,
"author_papers_recids": batch,
"is_stub_author": True,
},
)
return to_author["control_number"]
def index(self, force_delete=None):
"""Index record in ES
This method do not have any important logic.
It just runs self._index() with proper arguments in separate worker.
To properly index data it requires to fully commit the record first!
It won't index outdated record.
Args:
force_delete: set to True if record has to be deleted,
If not set, tries to determine automatically if record should be deleted
Returns:
celery.result.AsyncResult: Task itself
"""
indexing_args = self._record_index(self, force_delete=force_delete)
indexing_args["record_version"] = self.model.version_id
task = current_celery_app.send_task(
"inspirehep.records.indexer.tasks.index_record", kwargs=indexing_args
)
LOGGER.info(
"Record indexing", recid=self.get("control_number"), uuid=str(self.id)
)
return task
def _send_push_task(kwargs):
current_celery_app.send_task("inspirehep.orcid.tasks.orcid_push",
queue="orcid_push",
kwargs=kwargs)