def doc_count(request):
"""Returns the number of documents returned by a query
"""
logger.info('services/doc_count/ - user: {}'.format(request.user.username))
if settings.DEBUG:
print >> stderr, "doc_count()"
query_id = request.REQUEST.get('queryID')
if query_id:
query, response = get_query_object(query_id)
if not query:
return response
else:
return json_response_message('error', 'Missing query id.')
params = query.get_query_dict()
result = count_search_results(settings.ES_INDEX,
settings.ES_DOCTYPE,
params['query'],
params['dates'],
params['exclude_distributions'],
params['exclude_article_types'],
params['selected_pillars'])
count = result.get('count', 'error')
if not count == 'error':
params = {'doc_count': str(count)}
return json_response_message('ok', 'Retrieved document count.', params)
return json_response_message('error', 'Unable to retrieve document count'
' for query "{query}"' % query)
def cloud(request):
"""Return word cloud data using the terms aggregation approach
This view is currently not used, because it uses the terms aggregation
approach to generate word clouds, and this is not feasible in ES.
Returns word cloud data for a single document word cloud (based on a single
document id) and multiple document word clouds (either based on a list of
document ids (i.e., timeline burst cloud) or a query with metadata).
"""
if settings.DEBUG:
print >> stderr, "cloud()"
result = None
params = get_search_parameters(request.REQUEST)
ids = request.REQUEST.get('ids')
# Cloud by ids
if ids:
ids = ids.split(',')
if len(ids) == 1:
# Word cloud for single document
t_vector = single_document_word_cloud(settings.ES_INDEX,
settings.ES_DOCTYPE,
ids[0])
return json_response_message('ok', 'Word cloud generated', t_vector)
else:
# Word cloud for multiple ids
result = multiple_document_word_cloud(params.get('collection'),
settings.ES_DOCTYPE,
params.get('query'),
params.get('dates'),
params.get('distributions'),
params.get('article_types'),
params.get('pillars'),
ids)
# Cloud by queryID
query_id = request.REQUEST.get('queryID')
if query_id:
query, response = get_query_object(query_id)
if not query:
return response
# for some reason, the collection to be searched is stored in parameter
# 'collections' (with s added) instead of 'collection' as expected by
# get_search_parameters.
coll = request.REQUEST.get('collections', settings.ES_INDEX)
result = multiple_document_word_cloud(coll,
settings.ES_DOCTYPE,
query.query,
params.get('dates'),
params.get('distributions'),
params.get('article_types'),
params.get('pillars'))
if not result:
return json_response_message('error', 'No word cloud generated.')
return json_response_message('success', 'Word cloud generated', result)
