invenio-vocabularies 7.0.0.dev2__tar.gz → 7.2.0__tar.gz

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/CHANGES.rst

@@ -9,6 +9,22 @@
 Changes
 =======
 
+Version v7.2.0 (released 2025-03-10)
+
+- search: fix too many clauses on affiliation search
+- search: remove redundant fields from affiliation and funders search
+- nvs subjects: fix deprecated subjects skipping (raise skipped)
+
+Version v7.1.0 (released 2025-02-20)
+
+- subjects: renamed bodc to nvs
+- bodc: updated file uri & subject label
+
+Version v7.0.0 (released 2025-02-13)
+
+- Promote to stable release
+- jobs: apply code upgrades
+
 Version v7.0.0.dev2 (released 2025-01-23)
 
 Version v7.0.0.dev1 (released 2024-12-12)

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: invenio-vocabularies
-Version: 7.0.0.dev2
+Version: 7.2.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -15,7 +15,7 @@ License-File: AUTHORS.rst
 Requires-Dist: invenio-i18n<4.0.0,>=3.0.0
 Requires-Dist: invenio-records-resources<8.0.0,>=7.0.0
 Requires-Dist: invenio-administration<4.0.0,>=3.0.0
-Requires-Dist: invenio-jobs<4.0.0,>=3.0.0.dev2
+Requires-Dist: invenio-jobs<4.0.0,>=3.0.0
 Requires-Dist: lxml>=4.5.0
 Requires-Dist: pycountry<23.0.0,>=22.3.5
 Requires-Dist: PyYAML>=5.4.1
@@ -91,6 +91,22 @@ https://invenio-vocabularies.readthedocs.io/
 Changes
 =======
 
+Version v7.2.0 (released 2025-03-10)
+
+- search: fix too many clauses on affiliation search
+- search: remove redundant fields from affiliation and funders search
+- nvs subjects: fix deprecated subjects skipping (raise skipped)
+
+Version v7.1.0 (released 2025-02-20)
+
+- subjects: renamed bodc to nvs
+- bodc: updated file uri & subject label
+
+Version v7.0.0 (released 2025-02-13)
+
+- Promote to stable release
+- jobs: apply code upgrades
+
 Version v7.0.0.dev2 (released 2025-01-23)
 
 Version v7.0.0.dev1 (released 2024-12-12)

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/__init__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2020-2024 CERN.
+# Copyright (C) 2020-2025 CERN.
 # Copyright (C) 2024 Graz University of Technology.
 #
 # Invenio-Vocabularies is free software; you can redistribute it and/or
@@ -11,6 +11,6 @@
 
 from .ext import InvenioVocabularies
 
-__version__ = "7.0.0.dev2"
+__version__ = "7.2.0"
 
 __all__ = ("__version__", "InvenioVocabularies")

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/config.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2020-2024 CERN.
+# Copyright (C) 2020-2025 CERN.
 # Copyright (C) 2021 Northwestern University.
 # Copyright (C) 2024 University of Münster.
 #
@@ -196,8 +196,8 @@ VOCABULARIES_SUBJECTS_GEMET_FILE_URL = (
 )
 """Subject GEMET file download link."""
 
-VOCABULARIES_SUBJECTS_BODC_PUV_FILE_URL = "http://vocab.nerc.ac.uk/collection/P01/current/?_profile=nvs&_mediatype=application/rdf+xml"
-"""Subject BODC-PUV file download link."""
+VOCABULARIES_SUBJECTS_NVS_FILE_URL = "http://vocab.nerc.ac.uk/collection/P02/current/?_profile=nvs&_mediatype=application/rdf+xml"
+"""Subject NVS-P02 file download link."""
 
 VOCABULARIES_AFFILIATIONS_EDMO_COUNTRY_MAPPING = {
     "Cape Verde": "Cabo Verde",

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/contrib/affiliations/config.py

@@ -42,12 +42,9 @@ class AffiliationsSearchOptions(SearchOptions):
             # Aliases can sometimes be shorter, so we boost them a bit.
             "aliases^5",
             localized_title,
-            "id^2",
             # Allow to search identifiers directly (e.g. ROR)
             "identifiers.identifier",
-            "country",
             "country_name",
-            "types",
         ],
     )
 

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/contrib/funders/config.py

@@ -41,13 +41,10 @@ class FundersSearchOptions(SearchOptions):
             # Aliases can sometimes be shorter, so we boost them a bit.
             "aliases^5",
             localized_title,
-            "id^2",
             # Allow to search identifiers directly (e.g. ROR)
             "identifiers.identifier",
-            "country",
             "country_name",
-            "types",
-        ]
+        ],
     )
 
     sort_default = "bestmatch"

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/contrib/subjects/config.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2021-2024 CERN.
+# Copyright (C) 2021-2025 CERN.
 # Copyright (C) 2021 Northwestern University.
 # Copyright (C) 2024 University of Münster.
 #
@@ -36,8 +36,8 @@ euroscivoc_file_url = LocalProxy(
     lambda: current_app.config["VOCABULARIES_SUBJECTS_EUROSCIVOC_FILE_URL"]
 )
 
-bodc_puv_file_url = LocalProxy(
-    lambda: current_app.config["VOCABULARIES_SUBJECTS_BODC_PUV_FILE_URL"]
+nvs_file_url = LocalProxy(
+    lambda: current_app.config["VOCABULARIES_SUBJECTS_NVS_FILE_URL"]
 )
 
 

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/contrib/subjects/datastreams.py

@@ -12,10 +12,10 @@ from invenio_access.permissions import system_identity
 from invenio_i18n import lazy_gettext as _
 
 from ...datastreams.writers import ServiceWriter
-from .bodc import datastreams as bodc_datastreams
 from .euroscivoc import datastreams as euroscivoc_datastreams
 from .gemet import datastreams as gemet_datastreams
 from .mesh import datastreams as mesh_datastreams
+from .nvs import datastreams as nvs_datastreams
 
 
 class SubjectsServiceWriter(ServiceWriter):
@@ -40,7 +40,7 @@ VOCABULARIES_DATASTREAM_TRANSFORMERS = {
     **mesh_datastreams.VOCABULARIES_DATASTREAM_TRANSFORMERS,
     **euroscivoc_datastreams.VOCABULARIES_DATASTREAM_TRANSFORMERS,
     **gemet_datastreams.VOCABULARIES_DATASTREAM_TRANSFORMERS,
-    **bodc_datastreams.VOCABULARIES_DATASTREAM_TRANSFORMERS,
+    **nvs_datastreams.VOCABULARIES_DATASTREAM_TRANSFORMERS,
 }
 """Subjects Data Streams transformers."""
 

invenio_vocabularies-7.2.0/invenio_vocabularies/contrib/subjects/nvs/__init__.py

@@ -0,0 +1,9 @@
+# -*- coding: utf-8 -*-
+#
+# Copyright (C) 2024-2025 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
+# details.
+
+"""NVS Subjects module."""

{invenio_vocabularies-7.0.0.dev2/invenio_vocabularies/contrib/subjects/bodc → invenio_vocabularies-7.2.0/invenio_vocabularies/contrib/subjects/nvs}/datastreams.py

@@ -1,18 +1,18 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2024 CERN.
+# Copyright (C) 2024-2025 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
 # details.
 
-"""BODC subjects datastreams, readers, transformers, and writers."""
+"""NVS subjects datastreams, readers, transformers, and writers."""
 
 from invenio_vocabularies.datastreams.errors import TransformerError
 from invenio_vocabularies.datastreams.readers import RDFReader
 from invenio_vocabularies.datastreams.transformers import RDFTransformer
 
-from ..config import bodc_puv_file_url
+from ..config import nvs_file_url
 
 # Available with the "rdf" extra
 try:
@@ -21,9 +21,9 @@ except ImportError:
     rdflib = None
 
 
-class BODCPUVSubjectsTransformer(RDFTransformer):
+class NVSSubjectsTransformer(RDFTransformer):
     """
-    Transformer class to convert BODC-PUV RDF data to a dictionary format.
+    Transformer class to convert NVS RDF data to a dictionary format.
 
     Input:
         - Relevant fields:
@@ -36,8 +36,8 @@ class BODCPUVSubjectsTransformer(RDFTransformer):
     Output:
         - A dictionary with the following structure:
             {
-                "id": "SDN:P01::SAGEMSFM",  # BODC-specific parameter ID (skos:notation).
-                "scheme": "BODC-PUV",  # The scheme name indicating this is a BODC Parameter Usage Vocabulary concept.
+                "id": "SDN:P01::SAGEMSFM",  # NVS-specific parameter ID (skos:notation).
+                "scheme": "NVS-P01",  # The scheme name indicating this is a collection P01 from NERC Vocabulary Server (NVS).
                 "subject": "AMSSedAge",  # The alternative label (skos:altLabel), if available, or None.
                 "title": {
                     "en": "14C age of Foraminiferida"  # English preferred label (skos:prefLabel).
@@ -70,7 +70,7 @@ class BODCPUVSubjectsTransformer(RDFTransformer):
         subject_data = self._get_subject_data(rdf_graph, subject)
         deprecated = subject_data.get(str(rdflib.namespace.OWL.deprecated), [False])
         if deprecated and str(deprecated[0]).lower() == "true":
-            return None  # Skip deprecated subjects
+            raise TransformerError(f"Skipping deprecated subject: {subject_data}")
 
         notation = subject_data.get(str(self.skos_core.notation), [])
         if notation:
@@ -78,13 +78,16 @@ class BODCPUVSubjectsTransformer(RDFTransformer):
         else:
             raise TransformerError(f"No id found for: {subject}")
 
-        alt_labels = [obj for obj in subject_data.get(str(self.skos_core.altLabel), [])]
-        subject_text = str(alt_labels[0]) if alt_labels else ""
+        pref_labels = [
+            obj for obj in subject_data.get(str(self.skos_core.prefLabel), [])
+        ]
+
+        subject_text = str(pref_labels[0]) if pref_labels else labels["en"]
         definition = str(subject_data.get(str(self.skos_core.definition), [None])[0])
 
         return {
             "id": id,
-            "scheme": "BODC-PUV",
+            "scheme": "NVS-P02",
             "subject": subject_text,
             "title": labels,
             "props": {"definition": definition} if definition else {},
@@ -94,18 +97,18 @@ class BODCPUVSubjectsTransformer(RDFTransformer):
 
 # Configuration for datastream
 
-VOCABULARIES_DATASTREAM_TRANSFORMERS = {"bodc-transformer": BODCPUVSubjectsTransformer}
+VOCABULARIES_DATASTREAM_TRANSFORMERS = {"nvs-transformer": NVSSubjectsTransformer}
 
 DATASTREAM_CONFIG = {
     "readers": [
         {
             "type": "http",
             "args": {
-                "origin": bodc_puv_file_url,
+                "origin": nvs_file_url,
             },
         },
         {"type": "rdf"},
     ],
-    "transformers": [{"type": "bodc-transformer"}],
+    "transformers": [{"type": "nvs-transformer"}],
     "writers": [{"args": {"writer": {"type": "subjects-service"}}, "type": "async"}],
 }

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/factories.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2024 CERN.
+# Copyright (C) 2024-2025 CERN.
 # Copyright (C) 2024 KTH Royal Institute of Technology.
 #
 # Invenio-Vocabularies is free software; you can redistribute it and/or
@@ -28,12 +28,12 @@ from .contrib.awards.datastreams import (
 )
 from .contrib.funders.datastreams import DATASTREAM_CONFIG as funders_ds_config
 from .contrib.names.datastreams import DATASTREAM_CONFIG as names_ds_config
-from .contrib.subjects.bodc.datastreams import DATASTREAM_CONFIG as bodc_ds_config
 from .contrib.subjects.datastreams import DATASTREAM_CONFIG as subjects_ds_config
 from .contrib.subjects.euroscivoc.datastreams import (
     DATASTREAM_CONFIG as euroscivoc_ds_config,
 )
 from .contrib.subjects.gemet.datastreams import DATASTREAM_CONFIG as gemet_ds_config
+from .contrib.subjects.nvs.datastreams import DATASTREAM_CONFIG as nvs_ds_config
 
 
 class VocabularyConfig:
@@ -164,15 +164,15 @@ class SubjectsGEMETVocabularyConfig(VocabularyConfig):
         raise NotImplementedError("Service not implemented for GEMET Subjects")
 
 
-class SubjectsBODCVocabularyConfig(VocabularyConfig):
-    """BODC Subjects Vocabulary Config."""
+class SubjectsNVSVocabularyConfig(VocabularyConfig):
+    """NVS Subjects Vocabulary Config."""
 
-    config = bodc_ds_config
-    vocabulary_name = "subjects:bodc-puv"
+    config = nvs_ds_config
+    vocabulary_name = "subjects:nvs"
 
     def get_service(self):
         """Get the service for the vocabulary."""
-        raise NotImplementedError("Service not implemented for BODC Subjects")
+        raise NotImplementedError("Service not implemented for NVS Subjects")
 
 
 def get_vocabulary_config(vocabulary):
@@ -187,7 +187,7 @@ def get_vocabulary_config(vocabulary):
         "affiliations:edmo": AffiliationsEDMOVocabularyConfig,
         "subjects": SubjectsVocabularyConfig,
         "subjects:gemet": SubjectsGEMETVocabularyConfig,
-        "subjects:bodc": SubjectsBODCVocabularyConfig,
+        "subjects:nvs": SubjectsNVSVocabularyConfig,
         "subjects:euroscivoc": SubjectsEuroSciVocVocabularyConfig,
     }
     return vocab_config.get(vocabulary, VocabularyConfig)()

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies/jobs.py

@@ -9,44 +9,19 @@
 """Jobs module."""
 
 import datetime
-from datetime import timezone
 
 from invenio_i18n import gettext as _
 from invenio_jobs.jobs import JobType
-from marshmallow import Schema, fields
-from marshmallow_utils.fields import TZDateTime
 
 from invenio_vocabularies.services.tasks import process_datastream
 
 from .contrib.names.datastreams import ORCID_PRESET_DATASTREAM_CONFIG
 
 
-class ArgsSchema(Schema):
-    """Schema of task input arguments."""
-
-    since = TZDateTime(
-        timezone=timezone.utc,
-        format="iso",
-        metadata={
-            "description": _(
-                "YYYY-MM-DD HH:mm format. "
-                "Leave field empty if it should continue since last successful run."
-            )
-        },
-    )
-    job_arg_schema = fields.String(
-        metadata={"type": "hidden"},
-        dump_default="ArgsSchema",
-        load_default="ArgsSchema",
-    )
-
-
 class ProcessDataStreamJob(JobType):
     """Generic process data stream job type."""
 
-    arguments_schema = ArgsSchema
     task = process_datastream
-    id = None
 
 
 class ProcessRORAffiliationsJob(ProcessDataStreamJob):
@@ -57,13 +32,8 @@ class ProcessRORAffiliationsJob(ProcessDataStreamJob):
     id = "process_ror_affiliations"
 
     @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()
-
+    def build_task_arguments(cls, job_obj, since=None, **kwargs):
+        """Process ROR affiliations."""
         # 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 {
@@ -100,13 +70,8 @@ class ProcessRORFundersJob(ProcessDataStreamJob):
     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()
-
+    def build_task_arguments(cls, job_obj, since=None, **kwargs):
+        """Process ROR funders."""
         # 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 {
@@ -143,8 +108,8 @@ class ImportAwardsOpenAIREJob(ProcessDataStreamJob):
     id = "import_awards_openaire"
 
     @classmethod
-    def default_args(cls, job_obj, **kwargs):
-        """Generate default job arguments."""
+    def build_task_arguments(cls, job_obj, since=None, **kwargs):
+        """Process awards OpenAIRE."""
         return {
             "config": {
                 "readers": [
@@ -178,8 +143,8 @@ class UpdateAwardsCordisJob(ProcessDataStreamJob):
     id = "update_awards_cordis"
 
     @classmethod
-    def default_args(cls, job_obj, **kwargs):
-        """Generate default job arguments."""
+    def build_task_arguments(cls, job_obj, since=None, **kwargs):
+        """Process awards Cordis."""
         return {
             "config": {
                 "readers": [
@@ -206,6 +171,6 @@ class ImportORCIDJob(ProcessDataStreamJob):
     id = "import_orcid"
 
     @classmethod
-    def default_args(cls, job_obj, **kwargs):
-        """Generate default job arguments."""
+    def build_task_arguments(cls, job_obj, since=None, **kwargs):
+        """Process ORCID data."""
         return {"config": {**ORCID_PRESET_DATASTREAM_CONFIG}}

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: invenio-vocabularies
-Version: 7.0.0.dev2
+Version: 7.2.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -15,7 +15,7 @@ License-File: AUTHORS.rst
 Requires-Dist: invenio-i18n<4.0.0,>=3.0.0
 Requires-Dist: invenio-records-resources<8.0.0,>=7.0.0
 Requires-Dist: invenio-administration<4.0.0,>=3.0.0
-Requires-Dist: invenio-jobs<4.0.0,>=3.0.0.dev2
+Requires-Dist: invenio-jobs<4.0.0,>=3.0.0
 Requires-Dist: lxml>=4.5.0
 Requires-Dist: pycountry<23.0.0,>=22.3.5
 Requires-Dist: PyYAML>=5.4.1
@@ -91,6 +91,22 @@ https://invenio-vocabularies.readthedocs.io/
 Changes
 =======
 
+Version v7.2.0 (released 2025-03-10)
+
+- search: fix too many clauses on affiliation search
+- search: remove redundant fields from affiliation and funders search
+- nvs subjects: fix deprecated subjects skipping (raise skipped)
+
+Version v7.1.0 (released 2025-02-20)
+
+- subjects: renamed bodc to nvs
+- bodc: updated file uri & subject label
+
+Version v7.0.0 (released 2025-02-13)
+
+- Promote to stable release
+- jobs: apply code upgrades
+
 Version v7.0.0.dev2 (released 2025-01-23)
 
 Version v7.0.0.dev1 (released 2024-12-12)

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies.egg-info/SOURCES.txt

@@ -188,8 +188,6 @@ invenio_vocabularies/contrib/subjects/resources.py
 invenio_vocabularies/contrib/subjects/schema.py
 invenio_vocabularies/contrib/subjects/services.py
 invenio_vocabularies/contrib/subjects/subjects.py
-invenio_vocabularies/contrib/subjects/bodc/__init__.py
-invenio_vocabularies/contrib/subjects/bodc/datastreams.py
 invenio_vocabularies/contrib/subjects/euroscivoc/__init__.py
 invenio_vocabularies/contrib/subjects/euroscivoc/datastreams.py
 invenio_vocabularies/contrib/subjects/gemet/__init__.py
@@ -205,6 +203,8 @@ invenio_vocabularies/contrib/subjects/mappings/v7/__init__.py
 invenio_vocabularies/contrib/subjects/mappings/v7/subjects/subject-v1.0.0.json
 invenio_vocabularies/contrib/subjects/mesh/__init__.py
 invenio_vocabularies/contrib/subjects/mesh/datastreams.py
+invenio_vocabularies/contrib/subjects/nvs/__init__.py
+invenio_vocabularies/contrib/subjects/nvs/datastreams.py
 invenio_vocabularies/datastreams/__init__.py
 invenio_vocabularies/datastreams/datastreams.py
 invenio_vocabularies/datastreams/errors.py
@@ -392,9 +392,9 @@ tests/contrib/subjects/test_subjects_jsonschema.py
 tests/contrib/subjects/test_subjects_resource.py
 tests/contrib/subjects/test_subjects_schema.py
 tests/contrib/subjects/test_subjects_service.py
-tests/contrib/subjects/bodc/test_subjects_bodc_datastream.py
 tests/contrib/subjects/euroscivoc/test_subjects_euroscivoc_datastream.py
 tests/contrib/subjects/gemet/test_subjects_gemet_datastream.py
+tests/contrib/subjects/nvs/test_subjects_nvs_datastream.py
 tests/custom_fields/test_custom_fields.py
 tests/datastreams/conftest.py
 tests/datastreams/test_datastreams.py

{invenio_vocabularies-7.0.0.dev2 → invenio_vocabularies-7.2.0}/invenio_vocabularies.egg-info/requires.txt

@@ -1,7 +1,7 @@
 invenio-i18n<4.0.0,>=3.0.0
 invenio-records-resources<8.0.0,>=7.0.0
 invenio-administration<4.0.0,>=3.0.0
-invenio-jobs<4.0.0,>=3.0.0.dev2
+invenio-jobs<4.0.0,>=3.0.0
 lxml>=4.5.0
 pycountry<23.0.0,>=22.3.5
 PyYAML>=5.4.1