def _stats_top_dataset_downloads(self, org_id):
from ckan.lib.search.query import make_connection
datasets_map = jql.downloads_per_organization_per_dataset_last_24_weeks_cached(
).get(org_id, {})
total_downloads = sum(
(item.get('value') for item in datasets_map.values()))
context = {
'model': model,
'user': c.user or c.author,
'auth_user_obj': c.userobj
}
data_dict = {
'q':
'*:*',
'fl':
'id name title',
'fq':
'capacity:"public" id:({})'.format(' OR '.join(
datasets_map.keys())),
'rows':
len(datasets_map),
'start':
0,
}
ret = []
if datasets_map:
try:
conn = make_connection(decode_dates=False)
search_result = conn.search(**data_dict)
dataseta_meta_map = {
d['id']: {
'title': d.get('title'),
'url': h.url_for('dataset_read', id=d.get('name'))
}
for d in search_result.docs
}
ret = [
{
'dataset_id':
d.get('dataset_id'),
'name':
dataseta_meta_map.get(d.get('dataset_id'),
{}).get('title'),
'url':
dataseta_meta_map.get(d.get('dataset_id'),
{}).get('url'),
'value':
d.get('value'),
'total':
total_downloads,
# 'percentage': round(100*d.get('value', 0)/total_downloads, 1)
} for d in itertools.islice((
ds for ds in datasets_map.values()
if ds.get('dataset_id') in dataseta_meta_map), 25)
]
except Exception, e:
log.warn('Error in searching solr {}'.format(str(e)))
def _find_potential_datasets_in_solr(self):
from ckan.lib.search.query import make_connection
dataseta_meta_map = {}
data_dict = {
'q': '*:*',
'fl': 'id pageviews_last_14_days total_res_downloads',
'fq': 'total_res_downloads:[1 TO *] OR pageviews_last_14_days: [1 TO *]',
'start': 0,
'rows': 1000000
}
try:
conn = make_connection(decode_dates=False)
search_result = conn.search(**data_dict)
dataseta_meta_map = {d['id']: {'pageviews': d.get('pageviews_last_14_days', 0),
'downloads': d.get('total_res_downloads', 0)}
for d in search_result.docs}
except Exception, e:
self.log.warn('Error in searching solr {}'.format(str(e)))
def _stats_top_dataset_downloads(self, org_id, org_name):
from ckan.lib.search.query import make_connection
datasets_map = jql.downloads_per_organization_per_dataset_last_24_weeks_cached().get(
org_id, {})
total_downloads = sum((item.get('value') for item in datasets_map.values()))
data_dict = {
'q': '*:*',
'fl': 'id name title',
'fq': 'capacity:"public" organization:{}'.format(org_name),
'rows': 5000, # Just setting a max, we need all public datasets that an org has
'start': 0,
}
ret = []
if datasets_map:
mp_datasets_sorted = sorted(datasets_map.values(), key=lambda item: item.get('value'), reverse=True)
try:
conn = make_connection(decode_dates=False)
search_result = conn.search(**data_dict)
dataseta_meta_map = {
d['id']: {
'title': d.get('title'),
'name': d.get('name'),
}
for d in search_result.docs
}
ret = [
{
'dataset_id': d.get('dataset_id'),
'name': dataseta_meta_map.get(d.get('dataset_id'), {}).get('title'),
'url': h.url_for('dataset_read', id=dataseta_meta_map.get(d.get('dataset_id'), {}).get('name')),
'value': d.get('value'),
'total': total_downloads,
# 'percentage': round(100*d.get('value', 0)/total_downloads, 1)
}
for d in itertools.islice(
(ds for ds in mp_datasets_sorted if ds.get('dataset_id') in dataseta_meta_map), 25
)
]
except Exception, e:
log.warn('Error in searching solr {}'.format(str(e)))