Change the image

Dockerfile

@@ -22,47 +22,8 @@
 # waive the privileges and immunities granted to it by virtue of its status
 # as an Intergovernmental Organization or submit itself to any jurisdiction.
 
-# Use Invenio's alma image with Python-3.9
-FROM registry.cern.ch/inveniosoftware/almalinux:1
-
-# Use XRootD 5.6.9
-ENV XROOTD_VERSION=5.6.9
-
-# Install CERN Open Data Portal web node pre-requisites
-# hadolint ignore=DL3033
-RUN yum install -y \
-        ca-certificates \
-        cmake3 \
-        epel-release \
-        libuuid-devel \
-        rlwrap \
-        vim && \
-    yum groupinstall -y "Development Tools" && \
-    yum clean -y all
-
-RUN echo "Will install xrootd version: $XROOTD_VERSION (latest if empty)" && \
-    yum install -y xrootd-"$XROOTD_VERSION" python3-xrootd-"$XROOTD_VERSION" && \
-    yum clean -y all
-
-RUN pip uninstall pipenv -y && pip install --upgrade pip==20.2.4 setuptools==68.2.2 wheel==0.36.2 && \
-    npm install -g --unsafe-perm node-sass@6.0.1 clean-css@3.4.24 requirejs@2.3.6 uglify-js@3.12.1 jsonlint@1.6.3 d3@6.3.1
-
-# Change group to root to support OpenShift runtime
-RUN chgrp -R 0 "${INVENIO_INSTANCE_PATH}" && \
-    chmod -R g=u "${INVENIO_INSTANCE_PATH}"
-
-# Create `code` dir and set Invenio user as owner
-ENV CODE_DIR=/code
-RUN mkdir ${CODE_DIR} && chown invenio:root ${CODE_DIR}
-
-# Run application as Invenio user
-USER ${INVENIO_USER_ID}
-
-# Set default Invenio user Python base for site-packages
-ENV PYTHONUSERBASE=${INVENIO_INSTANCE_PATH}/python
-
-# Add Invenio user Python base to global PATH
-ENV PATH=$PATH:${INVENIO_INSTANCE_PATH}/python/bin
+# hadolint ignore=DL3007
+FROM registry.cern.ch/cernopendata/cernopendata-portal:latest
 
 # Add CERN Open Data Portal sources to `code` and work there
 WORKDIR ${CODE_DIR}

cernopendata/config.py

@@ -231,11 +231,17 @@ def _query_parser_and(qstr=None):
     """Parser that uses the Q() with AND from search engine dsl."""
     if qstr:
         _query = dsl.Q(
-            "query_string", query=qstr.replace("/", "\\/"), default_operator="AND"
+            "query_string",
+            query=qstr.replace("/", "\\/"),
+            default_operator="AND",
+            fields=["title.tokens^2", "*"],
         )
     else:
         _query = dsl.Q()
-    if request.values.get("ondemand") != "true" and request.values.get("ondemand") != "ondemand":
+    if (
+        request.values.get("ondemand") != "true"
+        and request.values.get("ondemand") != "ondemand"
+    ):
         _query = _query & ~dsl.Q("match", **{"distribution.availability": "ondemand"})
     return _query
 

scripts/create-instance.sh

@@ -28,6 +28,9 @@ set -o nounset
 mkdir -p "${INVENIO_INSTANCE_PATH}"
 cd "${INVENIO_INSTANCE_PATH}"/static
 
+# cleanup the previous installation
+rm -rf "${INVENIO_INSTANCE_PATH}"/static/*
+
 npm install git+https://github.com/cernopendata/demobbed-viewer.git --prefix $INVENIO_INSTANCE_PATH/static
 npm install ispy-webgl@0.9.8-COD3.11 --prefix $INVENIO_INSTANCE_PATH/static
 

tests/conftest.py

@@ -71,3 +71,74 @@ def app(env_config, default_config, instance_path):
 
     with app.app_context():
         yield app
+
+
+@pytest.fixture(scope="module")
+def database(app):
+    """Setup database.
+
+    Scope: module
+
+    Normally, tests should use the function-scoped :py:data:`db` fixture
+    instead. This fixture takes care of creating the database/tables and
+    removing the tables once tests are done.
+    """
+    from invenio_db import db as db_
+    from sqlalchemy_utils.functions import create_database, database_exists
+
+    if not database_exists(str(db_.engine.url)):
+        create_database(str(db_.engine.url))
+
+    # Use unlogged tables for PostgreSQL (see https://github.com/sqlalchemy/alembic/discussions/1108)
+    if db_.engine.name == "postgresql":
+        from sqlalchemy.ext.compiler import compiles
+        from sqlalchemy.schema import CreateTable
+
+        @compiles(CreateTable)
+        def _compile_unlogged(element, compiler, **kwargs):
+            return compiler.visit_create_table(element).replace(
+                "CREATE TABLE ",
+                "CREATE UNLOGGED TABLE ",
+            )
+
+    db_.create_all()
+
+    yield db_
+
+    db_.session.remove()
+    db_.drop_all()
+
+
+def _search_create_indexes(current_search, current_search_client):
+    """Create all registered search indexes."""
+    from invenio_search.engine import search
+
+    try:
+        list(current_search.create())
+    except search.RequestError:
+        list(current_search.delete(ignore=[404]))
+        list(current_search.create())
+    current_search_client.indices.refresh()
+
+
+def _search_delete_indexes(current_search):
+    """Delete all registered search indexes."""
+    list(current_search.delete(ignore=[404]))
+
+
+@pytest.fixture(scope="module")
+def search(app):
+    """Setup and teardown all registered search indices.
+
+    Scope: module
+
+    This fixture will create all registered indexes in search and remove
+    once done. Fixtures that perform changes (e.g. index or remove documents),
+    should used the function-scoped :py:data:`search_clear` fixture to leave the
+    indexes clean for the following tests.
+    """
+    from invenio_search import current_search, current_search_client
+
+    _search_create_indexes(current_search, current_search_client)
+    yield current_search_client
+    _search_delete_indexes(current_search)

tests/test_cernopendata_query_parser.py

@@ -28,35 +28,31 @@
 from cernopendata.config import _query_parser_and
 
 
+def _create_query(term):
+    # Defines the skeleton of a query
+    return dsl.query.Bool(
+        must=[
+            dsl.query.QueryString(
+                default_operator="AND", fields=["title.tokens^2", "*"], query=term
+            )
+        ],
+        must_not=[dsl.query.Match(distribution__availability="ondemand")],
+    )
+
+
 def test_cernopendata_query_parser(app):
     with app.test_request_context("/"):
-        assert _query_parser_and("/Btau") == dsl.query.Bool(
-            must=[dsl.query.QueryString(default_operator="AND", query="\\/Btau")],
-            must_not=[dsl.query.Match(distribution__availability="ondemand")],
-        )
-        assert _query_parser_and('"/Btau"') == dsl.query.Bool(
-            must=[dsl.query.QueryString(default_operator="AND", query='"\\/Btau"')],
-            must_not=[dsl.query.Match(distribution__availability="ondemand")],
-        )
-        assert _query_parser_and("/btau AND CMS") == dsl.query.Bool(
-            must=[
-                dsl.query.QueryString(default_operator="AND", query="\\/btau AND CMS")
-            ],
-            must_not=[dsl.query.Match(distribution__availability="ondemand")],
-        )
-        assert _query_parser_and('"/btau" AND CMS') == dsl.query.Bool(
-            must=[
-                dsl.query.QueryString(default_operator="AND", query='"\\/btau" AND CMS')
-            ],
-            must_not=[dsl.query.Match(distribution__availability="ondemand")],
-        )
-        assert _query_parser_and("CMS AND /btau") == dsl.query.Bool(
-            must=[
-                dsl.query.QueryString(default_operator="AND", query="CMS AND \\/btau")
-            ],
-            must_not=[dsl.query.Match(distribution__availability="ondemand")],
+        assert _query_parser_and("/Btau") == _create_query("\\/Btau")
+        assert _query_parser_and('"/Btau"') == _create_query('"\\/Btau"')
+        assert _query_parser_and("/btau AND CMS") == _create_query("\\/btau AND CMS")
+        assert _query_parser_and('"/btau" AND CMS') == _create_query(
+            '"\\/btau" AND CMS'
         )
+        assert _query_parser_and("CMS AND /btau") == _create_query("CMS AND \\/btau")
+
     with app.test_request_context("/?ondemand=true"):
         assert _query_parser_and("CMS AND /btau") == dsl.query.QueryString(
-            default_operator="AND", query="CMS AND \\/btau"
+            default_operator="AND",
+            fields=["title.tokens^2", "*"],
+            query="CMS AND \\/btau",
         )

tests/test_insert.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+#
+# This file is part of CERN Open Data Portal.
+# Copyright (C) 2021 CERN.
+#
+# CERN Open Data Portal is free software; you can redistribute it
+# and/or modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation; either version 2 of the
+# License, or (at your option) any later version.
+#
+# CERN Open Data Portal 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
+# General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with CERN Open Data Portal; if not, write to the
+# Free Software Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+# MA 02111-1307, USA.
+#
+# In applying this license, CERN does not
+# waive the privileges and immunities granted to it by virtue of its status
+# as an Intergovernmental Organization or submit itself to any jurisdiction.
+
+import re
+
+from invenio_indexer.api import RecordIndexer
+
+from cernopendata.modules.fixtures.cli import create_glossary_term
+
+
+def test_insert(app, database, search):
+    """Checking that records can be inserted"""
+    data = {
+        "anchor": "dummy_test",
+    }
+    schema = app.extensions["invenio-jsonschemas"].path_to_url(
+        "records/glossary-term-v1.0.0.json"
+    )
+    record = create_glossary_term(data, schema)
+
+    indexer = RecordIndexer()
+    done = indexer.index(record)
+
+    assert re.sub("-[^-]*$", "", done["_index"]) == "records-glossary-term-v1.0.0"