Revision 50035
Added by Sandro La Bruzzo over 6 years ago
| es_connector.py | ||
|---|---|---|
| 8 | 8 |
from os import path |
| 9 | 9 |
|
| 10 | 10 |
|
| 11 |
def get_property(): |
|
| 11 |
pid_resolver = {
|
|
| 12 |
"pdb": "http://www.rcsb.org/pdb/explore/explore.do?structureId=%s", |
|
| 13 |
"ncbi-n": "http://www.ncbi.nlm.nih.gov/gquery/?term=%s", |
|
| 14 |
"pmid": "http://www.ncbi.nlm.nih.gov/pubmed/%s", |
|
| 15 |
"pmcid": "http://www.ncbi.nlm.nih.gov/pmc/articles/%s", |
|
| 16 |
"pubmedid": "http://www.ncbi.nlm.nih.gov/pubmed/%s", |
|
| 17 |
"doi": "http://dx.doi.org/%s", |
|
| 18 |
"genbank": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 19 |
"nuccore": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 20 |
"swiss-prot": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 21 |
"arrayexpress": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 22 |
"biomodels": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 23 |
"bmrb": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 24 |
"ena": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 25 |
"geo": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 26 |
"ensembl": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 27 |
"mgi": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 28 |
"bind": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 29 |
"pride": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 30 |
"ddbj": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 31 |
"bioproject": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 32 |
"embl": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 33 |
"sra": "http://www.ncbi.nlm.nih.gov/nucest/%s?report=genbank", |
|
| 34 |
} |
|
| 12 | 35 |
|
| 13 | 36 |
|
| 37 |
def resolveIdentifier(pid, pid_type): |
|
| 38 |
if pid_type!= None: |
|
| 39 |
if pid_type.lower() in pid_resolver: |
|
| 40 |
return pid_resolver[pid_type.lower()] % pid |
|
| 41 |
else: |
|
| 42 |
if pid_type.lower() == 'openaire': |
|
| 43 |
return "https://www.openaire.eu/search/publication?articleId=%s"%pid.replace('oai:dnet:','')
|
|
| 44 |
else: |
|
| 45 |
return "http://identifiers.org/%s:%s" % (pid_type, pid) |
|
| 46 |
return "" |
|
| 47 |
|
|
| 48 |
def get_property(): |
|
| 14 | 49 |
f = open(path.join(os.path.dirname(os.path.realpath(__file__)), '../../api.properties')) |
| 15 | 50 |
p = {}
|
| 16 | 51 |
for line in f: |
| ... | ... | |
| 97 | 132 |
hits = [] |
| 98 | 133 |
|
| 99 | 134 |
for index_result in response.hits: |
| 100 |
hits.append(index_result.__dict__['_d_']) |
|
| 135 |
input_source = index_result.__dict__['_d_'] |
|
| 136 |
fixed_titles = [] |
|
| 101 | 137 |
|
| 138 |
for ids in input_source.get('localIdentifier',[]):
|
|
| 139 |
ds = resolveIdentifier(ids['id'], ids['type']) |
|
| 140 |
ids['url'] = ds |
|
| 141 |
for t in input_source.get('title',[]):
|
|
| 142 |
if len(t) > 0 and t[0] == '"' and t[-1] == '"': |
|
| 143 |
fixed_titles.append(t[1:-1]) |
|
| 144 |
else: |
|
| 145 |
fixed_titles.append(t) |
|
| 146 |
input_source['title'] = fixed_titles |
|
| 147 |
hits.append(input_source) |
|
| 148 |
|
|
| 102 | 149 |
pid_types = [] |
| 103 | 150 |
for tag in response.aggs.all_pids.all_types.buckets: |
| 104 | 151 |
pid_types.append(dict(key=tag.key, count=tag.doc_count)) |
| ... | ... | |
| 138 | 185 |
return hits |
| 139 | 186 |
|
| 140 | 187 |
def fix_collectedFrom(self, source, relation): |
| 188 |
if relation is None: |
|
| 189 |
return |
|
| 141 | 190 |
relSource = relation.get('source')
|
| 142 | 191 |
collectedFrom = relSource['collectedFrom'] |
| 143 | 192 |
for coll in collectedFrom: |
| ... | ... | |
| 151 | 200 |
res = self.client.get(index=self.index_name, doc_type='object', id=id) |
| 152 | 201 |
hits = [] |
| 153 | 202 |
input_source = res['_source'] |
| 203 |
fixed_titles = [] |
|
| 204 |
for t in input_source.get('title'):
|
|
| 205 |
if len(t) >0 and t[0]=='"' and t[-1]=='"': |
|
| 206 |
fixed_titles.append(t[1:-1]) |
|
| 207 |
else: |
|
| 208 |
fixed_titles.append(t) |
|
| 209 |
input_source['title'] = fixed_titles |
|
| 210 |
|
|
| 211 |
for ids in input_source.get('localIdentifier',[]):
|
|
| 212 |
ds = resolveIdentifier(ids['id'], ids['type']) |
|
| 213 |
ids['url'] = ds |
|
| 154 | 214 |
related_publications = [] |
| 155 | 215 |
related_dataset = [] |
| 156 | 216 |
related_unknown = [] |
| ... | ... | |
| 161 | 221 |
related_publications = self.related_type(id, 'publication', start) |
| 162 | 222 |
else: |
| 163 | 223 |
related_publications = self.related_type(id, 'publication') |
| 164 |
rel_source = related_publications[0] |
|
| 224 |
if len(related_publications) >0 : |
|
| 225 |
rel_source = related_publications[0] |
|
| 226 |
else: |
|
| 227 |
rel_source = {}
|
|
| 165 | 228 |
if input_source.get('relatedDatasets') > 0:
|
| 166 | 229 |
if 'dataset' == type: |
| 167 | 230 |
related_dataset = self.related_type(id, 'dataset', start) |
Also available in: Unified diff
made a new look