def build(self, q=None, **options):
"""
Build a query according to q and options.
This is the public method called by API handlers.
Regarding scopes:
scopes: [str] nonempty, match query.
scopes: NoneType, or [], no scope, so query string query.
Additionally support these options:
explain: include es scoring information
userquery: customized function to interpret q
* additional keywords are passed through as es keywords
for example: 'explain', 'version' ...
* multi-search is supported when q is a list. all queries
are built individually and then sent in one request.
"""
options = dotdict(options)
if options.scroll_id:
# bypass all query building stages
return ESScrollID(options.scroll_id)
if options.fetch_all:
# clean up conflicting parameters
options.pop('sort', None)
options.pop('size', None)
try:
# process single q vs list of q(s).
# dispatch 'val' vs 'key:val' to corresponding functions.
if isinstance(q, list):
search = MultiSearch()
for _q in q:
_search = self._build_one(_q, options)
search = search.add(_search)
else: # str, int ...
search = self._build_one(q, options)
except IllegalOperation as exc:
raise ValueError(str(exc)) # ex. sorting by -_score
if options.get('rawquery'):
raise RawQueryInterrupt(search.to_dict())
return search
def _data(self, request, cleaned, *args, explain=None, **kwargs):
m_search = MultiSearch()
search = Search(using=connection,
index=settings.ELASTICSEARCH_COMMON_ALIAS_NAME,
extra={'size': 0})
search.aggs.bucket(
'documents_by_type',
TermsFacet(field='model').get_aggregation()).bucket(
'by_month',
DateHistogramFacet(field='created',
interval='month',
min_doc_count=0).get_aggregation())
d_search = DatasetDocument().search().extra(size=0).filter(
'match', status='published')
r_search = ResourceDocument().search().extra(size=0).filter(
'match', status='published')
d_search.aggs.bucket(
'datasets_by_institution',
NestedFacet(
'institution',
TermsFacet(field='institution.id')).get_aggregation())
d_search.aggs.bucket(
'datasets_by_categories',
NestedFacet(
'categories',
TermsFacet(field='categories.id', min_doc_count=1,
size=50)).get_aggregation())
d_search.aggs.bucket(
'datasets_by_category',
NestedFacet(
'category',
TermsFacet(field='category.id', min_doc_count=1,
size=50)).get_aggregation())
d_search.aggs.bucket('datasets_by_tag',
TermsFacet(field='tags').get_aggregation())
d_search.aggs.bucket(
'datasets_by_keyword',
Nested(aggs={
'inner':
Filter(
aggs={'inner': Terms(field='keywords.name')},
term={'keywords.language': get_language()},
)
},
path='keywords'))
d_search.aggs.bucket('datasets_by_formats',
TermsFacet(field='formats').get_aggregation())
d_search.aggs.bucket(
'datasets_by_openness_scores',
TermsFacet(field='openness_scores').get_aggregation())
r_search.aggs.bucket('resources_by_type',
TermsFacet(field='type').get_aggregation())
m_search = m_search.add(search)
m_search = m_search.add(d_search)
m_search = m_search.add(r_search)
if explain == '1':
return m_search.to_dict()
try:
resp1, resp2, resp3 = m_search.execute()
# TODO: how to concatenate two responses in more elegant way?
resp1.aggregations.datasets_by_institution = resp2.aggregations.datasets_by_institution
resp1.aggregations.datasets_by_categories = resp2.aggregations.datasets_by_categories
resp1.aggregations.datasets_by_category = resp2.aggregations.datasets_by_category
resp1.aggregations.datasets_by_tag = resp2.aggregations.datasets_by_tag
resp1.aggregations.datasets_by_keyword = resp2.aggregations.datasets_by_keyword
resp1.aggregations.datasets_by_formats = resp2.aggregations.datasets_by_formats
resp1.aggregations.datasets_by_openness_scores = resp2.aggregations.datasets_by_openness_scores
resp1.aggregations.resources_by_type = resp3.aggregations.resources_by_type
return resp1
except TransportError as err:
try:
description = err.info['error']['reason']
except KeyError:
description = err.error
raise falcon.HTTPBadRequest(description=description)
