def corpus(self):
if self._corpus is None:
self._corpus = get_dual_corpora_by_metadata('docket_id', self.kwargs['docket_id'])
if not self._corpus:
# todo: better error handling
raise Http404("Couldn't find analysis for docket %s" % self.kwargs['docket_id'])
return self._corpus
def delete_analysis(docket):
with transaction.commit_on_success():
c = get_dual_corpora_by_metadata('docket_id', docket.id)
if c:
c.delete_corpus()
print "Deleted docket %s (id=%s)." % (docket.id, c.id)
else:
print "Attempted deletion of %s. Docket not found." % docket.id
Doc.objects(docket_id=docket.id).update(set__in_cluster_db=False)
def corpus(self):
if self._corpus is None:
self._corpus = get_dual_corpora_by_metadata(
'docket_id', self.kwargs['docket_id'])
if not self._corpus:
# todo: better error handling
raise Http404("Couldn't find analysis for docket %s" %
self.kwargs['docket_id'])
return self._corpus
def delete_analysis(docket_id):
with transaction.commit_on_success():
c = get_dual_corpora_by_metadata('docket_id', docket_id)
if c:
c.delete_corpus()
print "Deleted docket %s (id=%s)." % (docket_id, c.id)
else:
print "Attempted deletion of %s. Docket not found." % docket_id
Doc.objects(docket_id=docket_id).update(set__in_cluster_db=False)
def repair_missing_sims(docket):
"""Repair the situation where a docket is correct in Mongo and Postgres,
but the similarity directory is missing."""
with transaction.commit_on_success():
c = get_dual_corpora_by_metadata('docket_id', docket.id)
if c and not bsims.exists(c.id):
print "Docket %s (id=%s) missing similarities. Starting recomputation at %s..." % (docket.id, c.id, datetime.now())
i = DocumentIngester(c)
i.compute_similarities()
def repair_missing_sims(docket_id):
"""Repair the situation where a docket is correct in Mongo and Postgres,
but the similarity directory is missing."""
with transaction.commit_on_success():
c = get_dual_corpora_by_metadata('docket_id', docket_id)
if c and not bsims.exists(c.id):
print "Docket %s (id=%s) missing similarities. Starting recomputation at %s..." % (
docket_id, c.id, datetime.now())
i = DocumentIngester(c)
i.compute_similarities()
