| 1 |
39920
|
sandro.lab
|
import json
|
| 2 |
|
|
import pysolr
|
| 3 |
|
|
|
| 4 |
|
|
|
| 5 |
|
|
solr_server = pysolr.Solr("http://node0.d.dli.research-infrastructures.eu:8983/solr/DLIF-index-cleaned_shard1_replica1")
|
| 6 |
|
|
"""
|
| 7 |
|
|
result =solr_server.search(q="localidentifier:'10.5517/ccp8ql7' ", rows=20, **{
|
| 8 |
|
|
'facet':'true',
|
| 9 |
|
|
'start':10,
|
| 10 |
|
|
'facet.field':['entitytype', 'provenance']
|
| 11 |
|
|
});
|
| 12 |
|
|
"""
|
| 13 |
|
|
|
| 14 |
|
|
|
| 15 |
|
|
def getPointingTo(query, type):
|
| 16 |
|
|
result = solr_server.search(q=query, rows=10, **{
|
| 17 |
|
|
'facet':'true',
|
| 18 |
|
|
'facet.field':['relatedobjtype'],
|
| 19 |
|
|
'fq':'entitytype:"%s"'%type,
|
| 20 |
|
|
'fq':'entitytype:"publication"'
|
| 21 |
|
|
|
| 22 |
|
|
})
|
| 23 |
|
|
|
| 24 |
|
|
fields =result.facets['facet_fields']
|
| 25 |
|
|
|
| 26 |
|
|
return {type: [{'key':fields['relatedobjtype'][i], 'value':fields['relatedobjtype'][i+1]} for i in range(0,len(fields['relatedobjtype']),2)]}
|
| 27 |
|
|
|
| 28 |
|
|
|
| 29 |
|
|
def get_stats(self):
|
| 30 |
|
|
stats = {}
|
| 31 |
|
|
response = self.solr_server.search(q='*:*', rows=0, **{
|
| 32 |
|
|
'facet': 'true',
|
| 33 |
|
|
'facet.field': ['provenance']
|
| 34 |
|
|
})
|
| 35 |
|
|
d = response.facets['facet_fields']['provenance']
|
| 36 |
|
|
stats['dataset'] = [[d[i], d[i+1]] for i in range(0, len(d), 2)]
|
| 37 |
|
|
response = self.solr_server.search(q='*:*', rows=0, **{
|
| 38 |
|
|
'facet': 'true',
|
| 39 |
|
|
'facet.field': ['provenance'],
|
| 40 |
|
|
'fq': ['entitytype:"publication"']
|
| 41 |
|
|
})
|
| 42 |
|
|
d = response.facets['facet_fields']['provenance']
|
| 43 |
|
|
stats['publication'] = [[d[i], d[i+1]] for i in range(0, len(d), 2)]
|
| 44 |
|
|
return stats
|
| 45 |
|
|
|
| 46 |
|
|
|
| 47 |
|
|
def get_stats_detail_part2(stat_dict):
|
| 48 |
|
|
response =solr_server.search(q='*:*', rows=0, **{
|
| 49 |
|
|
'facet':'true',
|
| 50 |
|
|
'facet.field':['provenance'],
|
| 51 |
|
|
'fq': ['entitytype:"publication"']
|
| 52 |
|
|
})
|
| 53 |
|
|
res = response.facets['facet_fields']
|
| 54 |
|
|
data= res['provenance']
|
| 55 |
|
|
total_pubs = [(data[i], data[i+1]) for i in range(len(data)) if (i % 2) == 0]
|
| 56 |
|
|
for item in total_pubs:
|
| 57 |
|
|
if item[0] not in stat_dict:
|
| 58 |
|
|
stat_dict[item[0]] = {'totalObject': 0, 'totalPublication': 0, 'totalDatasets': 0, 'totalRelations': 0}
|
| 59 |
|
|
stat_dict[item[0]]['totalPublication'] =item[1]
|
| 60 |
|
|
|
| 61 |
|
|
response =solr_server.search(q='*:*', rows=0, **{
|
| 62 |
|
|
'facet':'true',
|
| 63 |
|
|
'facet.field':['provenance'],
|
| 64 |
|
|
'fq': ['entitytype:"dataset"']
|
| 65 |
|
|
})
|
| 66 |
|
|
res = response.facets['facet_fields']
|
| 67 |
|
|
data= res['provenance']
|
| 68 |
|
|
total_datasets = [(data[i], data[i+1]) for i in range(len(data)) if (i % 2) == 0]
|
| 69 |
|
|
for item in total_datasets:
|
| 70 |
|
|
if item[0] not in stat_dict:
|
| 71 |
|
|
stat_dict[item[0]] ={}
|
| 72 |
|
|
stat_dict[item[0]]['totalDatasets'] =item[1]
|
| 73 |
|
|
|
| 74 |
|
|
|
| 75 |
|
|
|
| 76 |
|
|
|
| 77 |
|
|
def get_stats_detail():
|
| 78 |
|
|
response =solr_server.search(q='*:*', rows=0, **{
|
| 79 |
|
|
'facet':'true',
|
| 80 |
|
|
'facet.field':['provenance', 'relationprovenance']
|
| 81 |
|
|
})
|
| 82 |
|
|
res = response.facets['facet_fields']
|
| 83 |
|
|
data= res['provenance']
|
| 84 |
|
|
repo_name = [data[i] for i in range(len(data)) if (i % 2) == 0]
|
| 85 |
|
|
stat_dict = {}
|
| 86 |
|
|
total_item = [(data[i], data[i+1]) for i in range(len(data)) if (i % 2) == 0]
|
| 87 |
|
|
for repo in repo_name:
|
| 88 |
|
|
stat_dict[repo] ={'totalObject': 0, 'totalPublication': 0, 'totalDatasets': 0, 'totalRelations': 0}
|
| 89 |
|
|
for item in total_item:
|
| 90 |
|
|
stat_dict[item[0]]['totalObject'] =item[1]
|
| 91 |
|
|
data= res['relationprovenance']
|
| 92 |
|
|
total_rels = [(data[i], data[i+1]) for i in range(len(data)) if (i % 2) == 0]
|
| 93 |
|
|
for item in total_rels:
|
| 94 |
|
|
if item[0] not in stat_dict:
|
| 95 |
|
|
stat_dict[item[0]] ={'totalObject': 0, 'totalPublication': 0, 'totalDatasets': 0, 'totalRelations': 0}
|
| 96 |
|
|
stat_dict[item[0]]['totalRelations'] =item[1]
|
| 97 |
|
|
return stat_dict
|
| 98 |
|
|
|
| 99 |
|
|
|
| 100 |
|
|
|
| 101 |
|
|
import urllib2
|
| 102 |
|
|
|
| 103 |
|
|
|
| 104 |
|
|
import re
|
| 105 |
|
|
p = re.compile("((https?):((//)|(\\\\))+([\w\d:#@%/;$()~_?\+-=\\\.&](#!)?)*)")
|
| 106 |
|
|
|
| 107 |
|
|
print p.match("http://data.aims.gov.au/extpubs/do/viewpub.do?articleid=7037")
|
| 108 |
|
|
|
| 109 |
|
|
|
| 110 |
|
|
|
| 111 |
|
|
|
| 112 |
|
|
data =urllib2.urlopen("http://node0.d.dli.research-infrastructures.eu:8080/dli/mvc/ui/stats/getLastStats")
|
| 113 |
|
|
json.loads(data.read())
|
| 114 |
|
|
|