search: remove useless translated facets

Independently of Elasticsearch tuning, we need to remove the unnecessary translated facets
to increase the search performance.

* Adds i18n facets factory.
* Updates search factory.
* Adapts config.py.
* Removes duplicate tests on items rest.
* Renames contribution facet to author.

Co-Authored-by: Lauren-D <[email protected]>

Author: lauren-d

rero_ils/config.py

@@ -1340,29 +1340,33 @@ def _(x):
     'documents', RERO_ILS_DEFAULT_AGGREGATION_SIZE)
 RECORDS_REST_FACETS = dict(
     documents=dict(
+        i18n_aggs=dict(
+            author=dict(
+                en=dict(
+                    terms=dict(field='facet_contribution_en',
+                               size=DOCUMENTS_AGGREGATION_SIZE)
+                ),
+                fr=dict(
+                    terms=dict(field='facet_contribution_fr',
+                               size=DOCUMENTS_AGGREGATION_SIZE)
+                ),
+                de=dict(
+                    terms=dict(field='facet_contribution_de',
+                               size=DOCUMENTS_AGGREGATION_SIZE)
+                ),
+                it=dict(
+                    terms=dict(field='facet_contribution_it',
+                               size=DOCUMENTS_AGGREGATION_SIZE)
+                ),
+            ),
+        ),
         aggs=dict(
             # The organisation or library facet is defined
             # dynamically during the query (query.py)
             document_type=dict(
                 terms=dict(field='type',
                            size=DOCUMENTS_AGGREGATION_SIZE)
             ),
-            contribution__en=dict(
-                terms=dict(field='facet_contribution_en',
-                           size=DOCUMENTS_AGGREGATION_SIZE)
-            ),
-            contribution__fr=dict(
-                terms=dict(field='facet_contribution_fr',
-                           size=DOCUMENTS_AGGREGATION_SIZE)
-            ),
-            contribution__de=dict(
-                terms=dict(field='facet_contribution_de',
-                           size=DOCUMENTS_AGGREGATION_SIZE)
-            ),
-            contribution__it=dict(
-                terms=dict(field='facet_contribution_it',
-                           size=DOCUMENTS_AGGREGATION_SIZE)
-            ),
             language=dict(
                 terms=dict(field='language.value',
                            size=DOCUMENTS_AGGREGATION_SIZE)

rero_ils/facets.py

@@ -0,0 +1,46 @@
+# -*- coding: utf-8 -*-
+#
+# RERO ILS
+# Copyright (C) 2019 RERO
+# Copyright (C) 2020 UCLOUVAIN
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, version 3 of the License.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+"""Facets and factories for result aggregation."""
+
+from __future__ import absolute_import, print_function
+
+from flask import current_app, request
+from invenio_i18n.ext import current_i18n
+
+
+def i18n_facets_factory(search, index):
+    """Add a i18n facets to search query.
+
+    It's possible to select facets which should be added to query
+    by passing their name in `facets` parameter.
+
+    :param search: Basic search object.
+    :param index: Index name.
+    :returns: the new search object.
+    """
+    facets_config = current_app.config['RECORDS_REST_FACETS'].get(index, {})
+    # i18n Aggregations.
+    for name, agg in facets_config.get("i18n_aggs", {}).items():
+        i18n_agg = agg.get(
+            request.args.get("lang", current_i18n.language),
+            agg.get(current_app.config.get('BABEL_DEFAULT_LANGUAGE'))
+        )
+        search.aggs[name] = i18n_agg if not callable(i18n_agg) \
+            else i18n_agg()
+    return search

rero_ils/query.py

@@ -2,6 +2,7 @@
 #
 # RERO ILS
 # Copyright (C) 2019 RERO
+# Copyright (C) 2020 UCLOUVAIN
 #
 # This program is free software: you can redistribute it and/or modify
 # it under the terms of the GNU Affero General Public License as published by
@@ -25,6 +26,7 @@
 from flask import current_app, request
 from invenio_records_rest.errors import InvalidQueryRESTError
 
+from .facets import i18n_facets_factory
 from .modules.organisations.api import Organisation, current_organisation
 from .modules.patrons.api import current_patron
 
@@ -270,6 +272,8 @@ def _boosting_parser(query_boosting, search_index):
         raise InvalidQueryRESTError()
 
     search, urlkwargs = default_facets_factory(search, search_index)
+    # i18n translated facets
+    search = i18n_facets_factory(search, search_index)
     search, sortkwargs = default_sorter_factory(search, search_index)
     for key, value in sortkwargs.items():
         urlkwargs.add(key, value)

tests/api/documents/test_documents_rest.py

@@ -173,8 +173,7 @@ def test_documents_facets(
     aggs = data['aggregations']
     # check all facets are present
     for facet in [
-        'document_type', 'contribution__en', 'contribution__fr',
-        'contribution__de', 'contribution__it', 'language', 'subject', 'status'
+        'document_type', 'author', 'language', 'subject', 'status'
     ]:
         assert aggs[facet]