def jobs_similar(id):
out = ''
es_query = RecordsSearch(index='records-jobs', doc_type='jobs')
es_query = es_query.query(
{
"more_like_this": {
"docs": [
{
"_id": id
}
],
"min_term_freq": 0,
"min_doc_freq": 0,
}
}
)[0:2]
similar_jobs = es_query.execute()
for job in similar_jobs:
out = out + (render_template_to_string(
"inspirehep_theme/similar_jobs.html",
record=job))
return out
def get_experiment_publications(experiment_name):
"""
Get paper count for a given experiment.
:param experiment_name: canonical name of the experiment.
:type experiment_name: string
"""
query = {
"term": {"accelerator_experiments.experiment": experiment_name}
}
search = RecordsSearch(index="records-hep").query(query)
search = search.params(search_type="count")
return search.execute().hits.total
def directly_list_v2_record_ids():
size = 100
page = 1
while True:
search = RecordsSearch().params(version=True)
search = search[(page - 1) * size:page * size]
search_result = search.execute()
for record in search_result.hits.hits:
if record.get('_index') == 'records-records':
yield record
if size * page < search_result.hits.total:
page += 1
else:
break
def get_institution_experiments_from_es(icn):
"""
Get experiments from a given institution.
To avoid killing ElasticSearch the number of experiments is limited.
:param icn: Institution canonical name.
:type icn: string
"""
query = {
"term": {"affiliation": icn}
}
search = RecordsSearch(index="records-experiments").query(query)[:100]
search = search.sort('-earliest_date')
return search.execute().hits
