def _update_query_with_classification(q: AdvancedQuery, data: MultiDict) \
-> AdvancedQuery:
q.classification = ClassificationList()
archives = [('computer_science', 'cs'), ('economics', 'econ'),
('eess', 'eess'), ('mathematics', 'math'),
('q_biology', 'q-bio'), ('q_finance', 'q-fin'),
('statistics', 'stat')]
for field, archive in archives:
if data.get(field):
# Fix for these typing issues is coming soon!
# See: https://github.com/python/mypy/pull/4397
q.classification.append(
Classification(archive={'id': archive}) # type: ignore
)
if data.get('physics') and 'physics_archives' in data:
if 'all' in data['physics_archives']:
q.classification.append(
Classification(group={'id': 'grp_physics'}) # type: ignore
)
else:
q.classification.append(
Classification( # type: ignore
group={'id': 'grp_physics'},
archive={'id': data['physics_archives']}))
return q
def _update_query_with_classification(q: AdvancedQuery,
data: MultiDict) -> AdvancedQuery:
q.classification = ClassificationList()
archives = [
("computer_science", "cs"),
("economics", "econ"),
("eess", "eess"),
("mathematics", "math"),
("q_biology", "q-bio"),
("q_finance", "q-fin"),
("statistics", "stat"),
]
for field, archive in archives:
if data.get(field):
# Fix for these typing issues is coming soon!
# See: https://github.com/python/mypy/pull/4397
q.classification.append(
Classification(archive={"id": archive}) # type: ignore
)
if data.get("physics") and "physics_archives" in data:
if "all" in data["physics_archives"]:
q.classification.append(
Classification(group={"id": "grp_physics"}) # type: ignore
)
else:
q.classification.append(
Classification( # type: ignore
group={"id": "grp_physics"},
archive={"id": data["physics_archives"]},
))
return q
def _update_with_archives(q: SimpleQuery, archives: List[str]) -> SimpleQuery:
"""
Search within a group or archive.
Parameters
----------
q : :class:`SimpleQuery`
groups_or_archives : str
Returns
-------
:class:`SimpleQuery`
"""
logger.debug('Search within %s', archives)
q.classification = ClassificationList([
Classification(archive={'id': archive}) # type: ignore
for archive in archives
])
return q
def test_advanced_query(self, mock_Elasticsearch, mock_Search):
""":class:`.index.search` supports :class:`AdvancedQuery`."""
mock_results = mock.MagicMock()
mock_results.__getitem__.return_value = {'total': 53}
rdata = dict(authors=[{'full_name': 'N. Ame'}],
owners=[{'full_name': 'N. Ame'}],
submitter={'full_name': 'N. Ame'},
paper_id='1234.56789')
mock_result = mock.MagicMock(_d_=rdata, **rdata)
mock_result.meta.score = 1
mock_results.__iter__.return_value = [mock_result]
mock_Search.execute.return_value = mock_results
# Support the chaining API for py-ES.
mock_Search.return_value = mock_Search
mock_Search.filter.return_value = mock_Search
mock_Search.highlight.return_value = mock_Search
mock_Search.highlight_options.return_value = mock_Search
mock_Search.query.return_value = mock_Search
mock_Search.sort.return_value = mock_Search
mock_Search.__getitem__.return_value = mock_Search
query = AdvancedQuery(
order='relevance',
size=10,
date_range=DateRange(
start_date=datetime.now() - timedelta(days=5),
end_date=datetime.now()
),
classification=ClassificationList([
Classification(
group={'id': 'physics'},
archive={'id': 'physics'},
category={'id': 'hep-th'}
)
]),
terms=FieldedSearchList([
FieldedSearchTerm(operator='AND', field='title', term='foo'),
FieldedSearchTerm(operator='AND', field='author', term='joe'),
FieldedSearchTerm(operator='OR', field='abstract', term='hmm'),
FieldedSearchTerm(operator='NOT', field='comments', term='eh'),
FieldedSearchTerm(operator='AND', field='journal_ref',
term='jref (1999) 1:2-3'),
FieldedSearchTerm(operator='AND', field='acm_class',
term='abc123'),
FieldedSearchTerm(operator='AND', field='msc_class',
term='abc123'),
FieldedSearchTerm(operator='OR', field='report_num',
term='abc123'),
FieldedSearchTerm(operator='OR', field='doi',
term='10.01234/56789'),
FieldedSearchTerm(operator='OR', field='orcid',
term='0000-0000-0000-0000'),
FieldedSearchTerm(operator='OR', field='author_id',
term='Bloggs_J'),
])
)
document_set = index.SearchSession.search(query)
# self.assertIsInstance(document_set, DocumentSet)
self.assertEqual(document_set['metadata']['start'], 0)
self.assertEqual(document_set['metadata']['total'], 53)
self.assertEqual(document_set['metadata']['current_page'], 1)
self.assertEqual(document_set['metadata']['total_pages'], 6)
self.assertEqual(document_set['metadata']['size'], 10)
self.assertEqual(len(document_set['results']), 1)
def test_advanced_query(self, mock_Elasticsearch, mock_Search):
""":class:`.index.search` supports :class:`AdvancedQuery`."""
mock_results = mock.MagicMock()
mock_results.__getitem__.return_value = {"total": 53}
rdata = mock_rdata()
mock_result = mock.MagicMock(_d_=rdata, **rdata)
mock_result.meta.score = 1
mock_results.__iter__.return_value = [mock_result]
mock_Search.execute.return_value = mock_results
# Support the chaining API for py-ES.
mock_Search.return_value = mock_Search
mock_Search.filter.return_value = mock_Search
mock_Search.highlight.return_value = mock_Search
mock_Search.highlight_options.return_value = mock_Search
mock_Search.query.return_value = mock_Search
mock_Search.sort.return_value = mock_Search
mock_Search.__getitem__.return_value = mock_Search
query = AdvancedQuery(
order="relevance",
size=10,
date_range=DateRange(
start_date=datetime.now() - timedelta(days=5),
end_date=datetime.now(),
),
classification=ClassificationList([
Classification(
group={"id": "physics"},
archive={"id": "physics"},
category={"id": "hep-th"},
)
]),
terms=FieldedSearchList([
FieldedSearchTerm(operator="AND", field="title", term="foo"),
FieldedSearchTerm(operator="AND", field="author", term="joe"),
FieldedSearchTerm(operator="OR", field="abstract", term="hmm"),
FieldedSearchTerm(operator="NOT", field="comments", term="eh"),
FieldedSearchTerm(
operator="AND",
field="journal_ref",
term="jref (1999) 1:2-3",
),
FieldedSearchTerm(operator="AND",
field="acm_class",
term="abc123"),
FieldedSearchTerm(operator="AND",
field="msc_class",
term="abc123"),
FieldedSearchTerm(operator="OR",
field="report_num",
term="abc123"),
FieldedSearchTerm(operator="OR",
field="doi",
term="10.01234/56789"),
FieldedSearchTerm(
operator="OR",
field="orcid",
term="0000-0000-0000-0000",
),
FieldedSearchTerm(operator="OR",
field="author_id",
term="Bloggs_J"),
]),
)
document_set = index.SearchSession.search(query)
# self.assertIsInstance(document_set, DocumentSet)
self.assertEqual(document_set["metadata"]["start"], 0)
self.assertEqual(document_set["metadata"]["total_results"], 53)
self.assertEqual(document_set["metadata"]["current_page"], 1)
self.assertEqual(document_set["metadata"]["total_pages"], 6)
self.assertEqual(document_set["metadata"]["size"], 10)
self.assertEqual(len(document_set["results"]), 1)