invenio-vocabularies 6.2.1__tar.gz → 6.3.0__tar.gz

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/CHANGES.rst

@@ -8,6 +8,13 @@
 Changes
 =======
 
+Version v6.3.0 (released 2024-10-11)
+
+- awards: get program from CORDIS
+- fix: add 'en' title if missing ROR
+- fix: since not passed to args
+- jobs: add process funders job
+
 Version v6.2.1 (released 2024-10-10)
 
 - webpack: bump react-searchkit due to axios upgrade

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invenio-vocabularies
-Version: 6.2.1
+Version: 6.3.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -50,6 +50,13 @@ Description: ..
         Changes
         =======
         
+        Version v6.3.0 (released 2024-10-11)
+        
+        - awards: get program from CORDIS
+        - fix: add 'en' title if missing ROR
+        - fix: since not passed to args
+        - jobs: add process funders job
+        
         Version v6.2.1 (released 2024-10-10)
         
         - webpack: bump react-searchkit due to axios upgrade

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/invenio_vocabularies/__init__.py

@@ -10,6 +10,6 @@
 
 from .ext import InvenioVocabularies
 
-__version__ = "6.2.1"
+__version__ = "6.3.0"
 
 __all__ = ("__version__", "InvenioVocabularies")

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/invenio_vocabularies/contrib/awards/datastreams.py

@@ -211,6 +211,56 @@ class CORDISProjectTransformer(BaseTransformer):
 
                 award["organizations"].append(organization_data)
 
+        programmes = (
+            record.get("relations", {}).get("associations", {}).get("programme", {})
+        )
+        if programmes:
+            # Projects with a single programme (this is the case of some projects in FP7) are not wrapped in a list,
+            # so we do this here to be able to iterate over it.
+            programmes = programmes if isinstance(programmes, list) else [programmes]
+
+            programmes_related_legal_basis = [
+                {
+                    "code": programme["code"],
+                    "uniqueprogrammepart": programme.get("@uniqueprogrammepart"),
+                }
+                for programme in programmes
+                if programme.get("@type") == "relatedLegalBasis"
+            ]
+
+            if len(programmes_related_legal_basis) == 0:
+                raise TransformerError(
+                    _(
+                        "No related legal basis programme found for project {project_id}".format(
+                            project_id=record["id"]
+                        )
+                    )
+                )
+            elif len(programmes_related_legal_basis) == 1:
+                # FP7 projects have only one related legal basis programme and do not have a 'uniqueprogrammepart' field.
+                unique_programme_related_legal_basis = programmes_related_legal_basis[0]
+            elif len(programmes_related_legal_basis) >= 1:
+                # The entry with the field 'uniqueprogrammepart' == 'true' is the high level programme code,
+                # while the other entry is a more specific sub-programme.
+                unique_programme_related_legal_basis = [
+                    programme_related_legal_basis
+                    # A few H2020 projects have more than one 'uniqueprogrammepart' == 'true',
+                    # for instance https://cordis.europa.eu/project/id/825673 (showing as "main programme" in the page)
+                    # which has one entry with the code 'H2020-EU.1.2.',
+                    # and one with the code 'H2020-EU.1.2.3.'.
+                    # We sort them from the shortest code to the longest code, and take the first item,
+                    # so that it conforms more with other projects which all have the shortest code as the main one.
+                    for programme_related_legal_basis in sorted(
+                        programmes_related_legal_basis, key=lambda d: len(d["code"])
+                    )
+                    if programme_related_legal_basis["uniqueprogrammepart"] == "true"
+                ][0]
+
+            # Store the code of the programme.
+            # For instance the code "HORIZON.1.2" which means "Marie Skłodowska-Curie Actions (MSCA)"
+            # See https://cordis.europa.eu/programme/id/HORIZON.1.2
+            award["program"] = unique_programme_related_legal_basis["code"]
+
         stream_entry.entry = award
         return stream_entry
 
@@ -222,7 +272,7 @@ class CORDISAwardsServiceWriter(ServiceWriter):
         """Constructor."""
         service_or_name = kwargs.pop("service_or_name", "awards")
         # Here we only update and we do not insert, since CORDIS data is used to augment existing awards
-        # (with subjects and organizations information) and is not used to create new awards.
+        # (with subjects, organizations, and program information) and is not used to create new awards.
         super().__init__(
             service_or_name=service_or_name, insert=False, update=True, *args, **kwargs
         )

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/invenio_vocabularies/contrib/common/ror/datastreams.py

@@ -160,6 +160,8 @@ class RORTransformer(BaseTransformer):
                     acronym = name["value"]
                 else:
                     aliases.add(name["value"])
+        if "en" not in ror["title"]:
+            ror["title"]["en"] = ror["name"]
         if acronym:
             ror["acronym"] = acronym
         if aliases:

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/invenio_vocabularies/jobs.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2021-2022 CERN.
+# Copyright (C) 2021-2024 CERN.
 #
 # Invenio-Vocabularies is free software; you can redistribute it and/or
 # modify it under the terms of the MIT License; see LICENSE file for more
@@ -60,8 +60,10 @@ class ProcessRORAffiliationsJob(ProcessDataStreamJob):
         if since is None and job_obj.last_runs["success"]:
             since = job_obj.last_runs["success"].started_at
         else:
-            since = datetime.datetime.now()
+            since = since or datetime.datetime.now()
 
+        # NOTE: Update is set to False for now given we don't have the logic to re-index dependent records yet.
+        # Since jobs support custom args, update true can be passed via that.
         return {
             "config": {
                 "readers": [
@@ -77,7 +79,7 @@ class ProcessRORAffiliationsJob(ProcessDataStreamJob):
                         "args": {
                             "writer": {
                                 "type": "affiliations-service",
-                                "args": {"update": True},
+                                "args": {"update": False},
                             }
                         },
                         "type": "async",
@@ -86,3 +88,46 @@ class ProcessRORAffiliationsJob(ProcessDataStreamJob):
                 "transformers": [{"type": "ror-affiliations"}],
             }
         }
+
+
+class ProcessRORFundersJob(ProcessDataStreamJob):
+    """Process ROR funders datastream registered task."""
+
+    description = "Process ROR funders"
+    title = "Load ROR funders"
+    id = "process_ror_funders"
+
+    @classmethod
+    def default_args(cls, job_obj, since=None, **kwargs):
+        """Generate default job arguments here."""
+        if since is None and job_obj.last_runs["success"]:
+            since = job_obj.last_runs["success"].started_at
+        else:
+            since = since or datetime.datetime.now()
+
+        # NOTE: Update is set to False for now given we don't have the logic to re-index dependent records yet.
+        # Since jobs support custom args, update true can be passed via that.
+        return {
+            "config": {
+                "readers": [
+                    {
+                        "args": {"since": since},
+                        "type": "ror-http",
+                    },
+                    {"args": {"regex": "_schema_v2\\.json$"}, "type": "zip"},
+                    {"type": "json"},
+                ],
+                "writers": [
+                    {
+                        "args": {
+                            "writer": {
+                                "type": "funders-service",
+                                "args": {"update": False},
+                            }
+                        },
+                        "type": "async",
+                    }
+                ],
+                "transformers": [{"type": "ror-funders"}],
+            }
+        }

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/invenio_vocabularies.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invenio-vocabularies
-Version: 6.2.1
+Version: 6.3.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -50,6 +50,13 @@ Description: ..
         Changes
         =======
         
+        Version v6.3.0 (released 2024-10-11)
+        
+        - awards: get program from CORDIS
+        - fix: add 'en' title if missing ROR
+        - fix: since not passed to args
+        - jobs: add process funders job
+        
         Version v6.2.1 (released 2024-10-10)
         
         - webpack: bump react-searchkit due to axios upgrade

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/invenio_vocabularies.egg-info/entry_points.txt

@@ -51,6 +51,7 @@ invenio_vocabularies = invenio_vocabularies
 
 [invenio_jobs.jobs]
 process_ror_affiliations = invenio_vocabularies.jobs:ProcessRORAffiliationsJob
+process_ror_funders = invenio_vocabularies.jobs:ProcessRORFundersJob
 
 [invenio_jsonschemas.schemas]
 affiliations = invenio_vocabularies.contrib.affiliations.jsonschemas

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/setup.cfg

@@ -104,6 +104,7 @@ invenio_celery.tasks =
 	invenio_vocabularies_services = invenio_vocabularies.services.tasks
 invenio_jobs.jobs = 
 	process_ror_affiliations = invenio_vocabularies.jobs:ProcessRORAffiliationsJob
+	process_ror_funders = invenio_vocabularies.jobs:ProcessRORFundersJob
 
 [build_sphinx]
 source-dir = docs/

{invenio-vocabularies-6.2.1 → invenio-vocabularies-6.3.0}/tests/contrib/awards/test_awards_datastreams.py

@@ -115,7 +115,7 @@ def expected_from_award_json_ec():
 
 
 CORDIS_PROJECT_XML = bytes(
-    """      
+    """
 <project
 	xmlns="http://cordis.europa.eu">
 	<language>en</language>
@@ -148,6 +148,16 @@ CORDIS_PROJECT_XML = bytes(
 					</categories>
 				</relations>
 			</organization>
+			<programme source="corda" uniqueProgrammePart="true" type="relatedLegalBasis">
+				<code>HORIZON.1.1</code>
+			</programme>
+			<programme source="corda" type="relatedLegalBasis">
+				<code>ANOTHER.CODE.WHICH.IS.NOT.THE.UNIQUE.PROGRAMME.PART</code>
+			</programme>
+			<programme source="corda" type="relatedTopic">
+				<code>ERC-2023-STG</code>
+				<frameworkProgramme>HORIZON</frameworkProgramme>
+			</programme>
 		</associations>
 		<categories>
 			<category classification="euroSciVoc" type="isInFieldOfScience">
@@ -169,6 +179,7 @@ CORDIS_PROJECT_XML = bytes(
 def expected_from_cordis_project_xml():
     return {
         "id": "00k4n6c32::101117736",
+        "program": "HORIZON.1.1",
         "subjects": [{"id": "euroscivoc:225"}],
         "organizations": [
             {