def start_task_and_return(self, data):
if data.get('skip_confirmation'):
self.start_task(data)
return self.json_response(self.task_started_message)
sm = ChunkSimilarity()
estimation = sm.estimate_time(**data)
# if estimated task duration is less than 1 hour:
if estimation < SimilarityLimits.WARN_CHUNK_SIMILARITY_SECONDS:
self.start_task(data)
return self.json_response(self.task_started_message)
_min, sec = divmod(estimation, 60)
hour, _min = divmod(_min, 60)
estim_str = "%d:%02d:%02d" % (hour, _min, sec)
return self.json_response({
'message': f'Processing may take about {estim_str}.',
'confirm': True
})
continue
doc_ids_to_values[doc_a_pk].add(doc_b_pk)
doc_ids_to_values[doc_b_pk].add(doc_a_pk)
if x % 100 == 0:
self.log_info('{field}: Checked for similarity {x} documents of {n}'
.format(field=dst_field.code, x=x + 1, n=total_docs))
self.push()
self.push()
self.log_info('{field}: Found {n} similar documents. Storing links into the document fields.'
.format(field=dst_field.code, n=len(doc_ids_to_values)))
doc_ids_to_values = {doc_id: list(v) if v else None for doc_id, v in doc_ids_to_values}
field_repo.store_values_one_field_many_docs_no_ants(field=dst_field, doc_ids_to_values=doc_ids_to_values)
log = CeleryTaskLogger(self)
for doc_id in doc_ids_to_values.keys():
try:
doc = Document.objects.get(pk=doc_id)
signals.fire_document_changed(log=log, document=doc, changed_by_user=None, system_fields_changed=False,
generic_fields_changed=False, user_fields_changed=[dst_field.code])
except Exception as ex:
self.log_error(f'Unable to fire doc id change event for doc #{doc_id}', exc_info=ex)
app.register_task(PreconfiguredDocumentSimilaritySearch())
app.register_task(Similarity())
app.register_task(SimilarityByFeatures())
app.register_task(ChunkSimilarity())
app.register_task(PartySimilarity())