def mget(self, uuids, **kwargs):
"""Get source from a list of uuids.
:param uuids: uuids of documents to be retrieved.
:type uuids: list of strings representing uuids
:returns: list of JSON documents
"""
documents = current_search_client.mget(index=self.Meta.index,
doc_type=self.Meta.doc_types,
body={'ids': uuids},
**kwargs)
return [document['_source'] for document in documents['docs']]
def references(self):
"""Reference export for single record in datatables format.
:returns: list
List of lists where every item represents a datatables row.
A row consists of [reference_number, reference, num_citations]
"""
out = []
references = self.record.get('references')
if references:
refs_to_get_from_es = [
ref['recid'] for ref in references if ref.get('recid')
]
records_from_es = []
if refs_to_get_from_es:
records_from_es = es.mget(body={
"ids": refs_to_get_from_es
}, index="records-hep")['docs']
refs_from_es = {
ref['_id']: ref['_source'] for ref in records_from_es if '_source' in ref
}
for reference in references:
row = []
recid = reference.get('recid')
ref_record = refs_from_es.get(str(recid)) if recid else None
if recid and ref_record:
recid = reference['recid']
ref_record = Record(refs_from_es.get(str(recid)))
if ref_record:
row.append(render_template_to_string(
"inspirehep_theme/references.html",
record=ref_record,
reference=reference
))
row.append(ref_record.get('citation_count', ''))
out.append(row)
else:
row.append(render_template_to_string(
"inspirehep_theme/references.html",
reference=reference))
row.append('')
out.append(row)
return out
def mget(self, uuids, **kwargs):
"""Get source from a list of uuids.
:param uuids: uuids of documents to be retrieved.
:type uuids: list of strings representing uuids
:returns: list of JSON documents
"""
documents = current_search_client.mget(
index=self.Meta.index,
doc_type=self.Meta.doc_types,
body={'ids': uuids},
**kwargs
)
return [document['_source'] for document in documents['docs']]
def mget(self, uuids, **kwargs):
"""Get source from a list of uuids.
:param uuids: uuids of documents to be retrieved.
:type uuids: list of strings representing uuids
:returns: list of JSON documents
"""
results = []
try:
documents = es.mget(index=self.alias,
doc_type=self.Meta.doc_types,
body={"ids": uuids},
**kwargs)
results = [document["_source"] for document in documents["docs"]]
except RequestError:
pass
return results
def mget(self, uuids, **kwargs):
"""Get source from a list of uuids.
:param uuids: uuids of documents to be retrieved.
:type uuids: list of strings representing uuids
:returns: list of JSON documents
"""
results = []
try:
documents = es.mget(index=self.Meta.index,
doc_type=self.Meta.doc_types,
body={'ids': uuids},
**kwargs)
results = [document['_source'] for document in documents['docs']]
except RequestError as e:
logger.exception(e)
return results
def mget(self, uuids, **kwargs):
"""Get source from a list of uuids.
:param uuids: uuids of documents to be retrieved.
:type uuids: list of strings representing uuids
:returns: list of JSON documents
"""
results = []
try:
documents = es.mget(
index=self.Meta.index,
doc_type=self.Meta.doc_types,
body={'ids': uuids},
**kwargs
)
results = [document['_source'] for document in documents['docs']]
except RequestError:
pass
return results
def serialize(self, pid, record, links_factory=None):
"""
Serialize a single impact graph from a record.
:param pid: Persistent identifier instance.
:param record: Record instance.
:param links_factory: Factory function for the link generation,
which are added to the response.
"""
out = {}
# Add information about current record
out['inspire_id'] = record['control_number']
out['title'] = get_title(record)
out['year'] = record['earliest_date'].split('-')[0]
# Get citations
citations = []
es_query = Query('refersto:' + record['control_number'])
es_query.body.update(
{
'size': 9999
}
)
record_citations = current_search_client.search(
index='records-hep',
doc_type='hep',
body=es_query.body,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
)['hits']['hits']
for citation in record_citations:
citation = citation['_source']
citations.append({
"inspire_id": citation['control_number'],
"citation_count": citation.get('citation_count', 0),
"title": get_title(citation),
"year": citation['earliest_date'].split('-')[0]
})
out['citations'] = citations
# Get references
record_references = record.get('references', [])
references = []
reference_recids = [
ref['recid'] for ref in record_references if ref.get('recid')
]
if reference_recids:
mget_body = {
"ids": reference_recids
}
record_references = current_search_client.mget(
index='records-hep',
doc_type='hep',
body=mget_body,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
]
)
for reference in record_references["docs"]:
ref_info = reference["_source"]
references.append({
"inspire_id": ref_info['control_number'],
"citation_count": ref_info.get('citation_count', 0),
"title": get_title(ref_info),
"year": ref_info['earliest_date'].split('-')[0]
})
out['references'] = references
return json.dumps(out)
def serialize(self, pid, record, links_factory=None):
"""
Serialize a single impact graph from a record.
:param pid: Persistent identifier instance.
:param record: Record instance.
:param links_factory: Factory function for the link generation,
which are added to the response.
"""
out = {}
# Add information about current record
out['inspire_id'] = record['control_number']
out['title'] = get_title(record)
out['year'] = record['earliest_date'].split('-')[0]
# Get citations
citations = []
es_query = Query('refersto:' + record['control_number'])
es_query.body.update({'size': 9999})
record_citations = current_search_client.search(index='records-hep',
doc_type='hep',
body=es_query.body,
_source=[
'control_number',
'citation_count',
'titles',
'earliest_date'
])['hits']['hits']
for citation in record_citations:
citation = citation['_source']
citations.append({
"inspire_id":
citation['control_number'],
"citation_count":
citation.get('citation_count', 0),
"title":
get_title(citation),
"year":
citation['earliest_date'].split('-')[0]
})
out['citations'] = citations
# Get references
record_references = record.get('references', [])
references = []
reference_recids = [
ref['recid'] for ref in record_references if ref.get('recid')
]
if reference_recids:
mget_body = {"ids": reference_recids}
record_references = current_search_client.mget(
index='records-hep',
doc_type='hep',
body=mget_body,
_source=[
'control_number', 'citation_count', 'titles',
'earliest_date'
])
for reference in record_references["docs"]:
ref_info = reference["_source"]
references.append({
"inspire_id":
ref_info['control_number'],
"citation_count":
ref_info.get('citation_count', 0),
"title":
get_title(ref_info),
"year":
ref_info['earliest_date'].split('-')[0]
})
out['references'] = references
return json.dumps(out)