Merge updates from main

.github/workflows/CI.yml

@@ -1,4 +1,4 @@
-name: CI
+name: Container Build
 
 on:
   # Allow manual triggering of the workflow

.github/workflows/tests.yml

@@ -1,4 +1,4 @@
-name: Run Tests
+name: Tests
 
 on:
   push:
@@ -70,6 +70,8 @@ jobs:
           COMMONS_SEARCH_API_TOKEN: ${{ secrets.TEST_COMMONS_SEARCH_API_TOKEN }}
           INVENIO_SEARCH_DOMAIN: ${{ vars.INVENIO_SEARCH_DOMAIN }}
           INVENIO_ADMIN_EMAIL: ${{ secrets.TEST_INVENIO_ADMIN_EMAIL }}
+          INVENIO_SITE_UI_URL: ${{ vars.INVENIO_SITE_UI_URL }}
+          INVENIO_SITE_API_URL: ${{ vars.INVENIO_SITE_API_URL }}
           SQLALCHEMY_DATABASE_URI: ${{ vars.TEST_SQLALCHEMY_DATABASE_URI }}
           INVENIO_SQLALCHEMY_DATABASE_URI: ${{ vars.TEST_SQLALCHEMY_DATABASE_URI }}
           POSTGRESQL_USER: ${{ vars.POSTGRES_USER }}

README.md

@@ -1,5 +1,9 @@
 # Knowledge Commons Works
 
+![Tests](https://github.com/mesh-research/knowledge-commons-works/actions/workflows/tests.yml/badge.svg)
+![Container build](https://github.com/mesh-research/knowledge-commons-works/actions/workflows/CI.yml/badge.svg)
+
+
 Knowledge Commons Works is a collaborative tool for storing and sharing academic research. It is part of Knowledge Commons and is built on an instance of the InvenioRDM repository system.
 
 Version 0.3.5-beta8

docs/source/in_depth.md

@@ -107,7 +107,7 @@ Using GIT, clone this repository. You should then have a folder called `knowledg
 
 ### Standardized environment variables
 
-This file must include the following variables with these values:
+For local development, this file must include the following variables with these values:
 
 ```
 INVENIO_INSTANCE_PATH=/opt/invenio/var/instance

site/kcworks/api_helpers.py

@@ -66,10 +66,16 @@ def format_commons_search_payload(
     **kwargs,
 ) -> dict:
     """Format payload for external service."""
-    UI_URL_BASE = os.environ.get("INVENIO_SITE_UI_URL", "http://works.kcommons.org")
-    API_URL_BASE = os.environ.get(
-        "INVENIO_SITE_API_URL", "http://works.kcommons.org/api"
-    )
+    UI_URL_BASE = os.environ.get("INVENIO_SITE_UI_URL", "")
+    if not UI_URL_BASE:
+        UI_URL_BASE = current_app.config.get(
+            "SITE_UI_URL", "https://works.kcommons.org"
+        )
+    API_URL_BASE = os.environ.get("INVENIO_SITE_API_URL", "")
+    if not API_URL_BASE:
+        API_URL_BASE = current_app.config.get(
+            "SITE_API_URL", "https://works.kcommons.org/api"
+        )
     PROFILES_URL_BASE = current_app.config.get(
         "KC_PROFILES_URL_BASE", "http://hcommons.org/profiles"
     )

site/tests/api/test_api_import.py

@@ -618,10 +618,14 @@ def test_import_records_loader_load(
         rdm_record = records_service.read(
             system_identity, id_=record_created_id
         ).to_dict()
-        assert rdm_record["files"] == {
-            k: v
-            for k, v in test_metadata.published["files"].items()
-            if k != "default_preview"
+        expected_record_files = copy.deepcopy(test_metadata.published["files"])
+
+        # FIXME: There's an inconsistency in file metadata between test runs
+        # locally and on github. The github run extracts image dimensions.
+        if "sample.jpg" in expected_record_files["entries"].keys():
+            expected_record_files["entries"]["sample.jpg"]["metadata"] = {}
+        assert expected_record_files == {
+            k: v for k, v in expected_record_files.items() if k != "default_preview"
         }
 
         # ensure the files can be downloaded

site/tests/api/test_api_notifications.py

@@ -1501,6 +1501,9 @@ def test_notification_on_first_upload(
     assert "A new user has created their first draft." in email.body
     assert "A new user has created their first draft." in email.html
 
+    # Refresh the index to ensure the draft is indexed
+    RDMDraft.index.refresh()
+
     # Create a second draft work (different work)
     draft2_response = client.post(
         f"{app.config['SITE_API_URL']}/records",

site/tests/api/test_stats.py

@@ -1,3 +1,4 @@
+from pprint import pformat
 import arrow
 from invenio_access.permissions import system_identity
 from invenio_search.proxies import current_search
@@ -37,6 +38,13 @@ def test_stats_backend_processing(
     metadata_record = published.to_dict()
     dt = arrow.utcnow()
 
+    # ensure that the stats queue is empty
+    # before we add any events to it
+    old_view_events = [p for p in current_stats.consume("record-view")]
+    old_download_events = [p for p in current_stats.consume("file-download")]
+    app.logger.debug(f"pre-existing view events: {pformat(old_view_events)}")
+    app.logger.debug(f"pre-existing download events: {pformat(old_download_events)}")
+
     # set previous bookmark to one tz aware
     # to ensure that it is properly handled by the tests
     # file-download aggregation runs with no bookmark
@@ -91,7 +99,27 @@ def test_stats_backend_processing(
             }
         ],
     )
+
+    # put events in search index from queue
     events = process_events(["file-download", "record-view"])
+
+    current_search.flush_and_refresh(index="*")
+    # app.logger.debug(
+    #     f"events: {pformat(current_search_client.indices.get('*record-view*'))}"
+    # )
+    # app.logger.debug(
+    #     f"events: {pformat(current_search_client.indices.get('*file-download*'))}"
+    # )
+    # view_records = current_search_client.search(
+    #     index="events-stats-record-view", body={}
+    # )
+    # app.logger.debug(f"view_records: {pformat(view_records)}")
+    # download_records = current_search_client.search(
+    #     index="events-stats-file-download", body={}
+    # )
+    # app.logger.debug(f"download_records: {pformat(download_records)}")
+
+    # check that events are in search index
     assert len(events) == 2
     assert events == [("file-download", (1, 0)), ("record-view", (1, 0))]
     current_search.flush_and_refresh(index="*")

site/tests/fixtures/records.py

@@ -641,6 +641,11 @@ def compare_published(
                     == expected["files"]["entries"][k]["storage_class"]
                 )
                 if v["metadata"]:
+                    if v["key"] == "sample.jpg":  # meta drawn from file
+                        expected["files"]["entries"][k]["metadata"] = {
+                            "height": 1672,
+                            "width": 1254,
+                        }
                     assert v["metadata"] == expected["files"]["entries"][k]["metadata"]
                 else:
                     assert not expected["files"]["entries"][k]["metadata"]
@@ -719,7 +724,7 @@ def compare_published(
                 assert actual["parent"]["pids"] == {
                     "doi": {
                         "client": "datacite",
-                        "identifier": (f"10.17613/{actual['parent']['id']}"),
+                        "identifier": f"10.17613/{actual['parent']['id']}",
                         "provider": "datacite",
                     },
                 }