invenio-vocabularies 6.4.0__tar.gz → 6.5.0__tar.gz

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/CHANGES.rst

@@ -8,6 +8,17 @@
 Changes
 =======
 
+Version v6.5.0 (released 2024-10-31)
+
+- subjects: euroscivoc: change default to latest version-less URL
+- Rename patched filters so the normalizer uses the default ones (#409)
+    * rename patched filters so the normalizer uses the default ones
+
+Version v6.4.1 (released 2024-10-15)
+
+- fix: exclude unknown fields when updating awards with subjects
+- fix: revert generic writer and define OpenAIRE awards writer logic
+
 Version v6.4.0 (released 2024-10-15)
 
 - jobs: add import awards OpenAIRE; Update CORDIS

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invenio-vocabularies
-Version: 6.4.0
+Version: 6.5.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -50,6 +50,17 @@ Description: ..
         Changes
         =======
         
+        Version v6.5.0 (released 2024-10-31)
+        
+        - subjects: euroscivoc: change default to latest version-less URL
+        - Rename patched filters so the normalizer uses the default ones (#409)
+            * rename patched filters so the normalizer uses the default ones
+        
+        Version v6.4.1 (released 2024-10-15)
+        
+        - fix: exclude unknown fields when updating awards with subjects
+        - fix: revert generic writer and define OpenAIRE awards writer logic
+        
         Version v6.4.0 (released 2024-10-15)
         
         - jobs: add import awards OpenAIRE; Update CORDIS

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/__init__.py

@@ -10,6 +10,6 @@
 
 from .ext import InvenioVocabularies
 
-__version__ = "6.4.0"
+__version__ = "6.5.0"
 
 __all__ = ("__version__", "InvenioVocabularies")

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/config.py

@@ -172,7 +172,7 @@ VOCABULARIES_TYPES_SEARCH = {
 }
 """Vocabulary type search configuration."""
 
-SUBJECTS_EUROSCIVOC_FILE_URL = "https://op.europa.eu/o/opportal-service/euvoc-download-handler?cellarURI=http%3A%2F%2Fpublications.europa.eu%2Fresource%2Fdistribution%2Feuroscivoc%2F20231115-0%2Frdf%2Fskos_ap_eu%2FEuroSciVoc-skos-ap-eu.rdf&fileName=EuroSciVoc-skos-ap-eu.rdf"
+SUBJECTS_EUROSCIVOC_FILE_URL = "https://publications.europa.eu/resource/distribution/euroscivoc/rdf/skos_ap_eu/EuroSciVoc-skos-ap-eu.rdf"
 """Subject EuroSciVoc file download link."""
 
 VOCABULARIES_ORCID_ACCESS_KEY = "TODO"

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/contrib/affiliations/datastreams.py

@@ -9,8 +9,11 @@
 
 """Affiliations datastreams, transformers, writers and readers."""
 
+from copy import deepcopy
+
 from flask import current_app
 
+from ...datastreams import StreamEntry
 from ...datastreams.errors import TransformerError, WriterError
 from ...datastreams.transformers import BaseTransformer
 from ...datastreams.writers import ServiceWriter
@@ -96,15 +99,24 @@ class OpenAIREAffiliationsServiceWriter(ServiceWriter):
         """Get the id from an entry."""
         return entry["id"]
 
-    def write(self, stream_entry, *args, **kwargs):
-        """Writes the input entry using a given service."""
-        entry = stream_entry.entry
-
-        return super().write(stream_entry, *args, **kwargs)
-
-    def write_many(self, stream_entries, *args, **kwargs):
-        """Writes the input entries using a given service."""
-        return super().write_many(stream_entries, *args, **kwargs)
+    def _do_update(self, entry):
+        vocab_id = self._entry_id(entry)
+        current = self._resolve(vocab_id)
+        updated = deepcopy(current.to_dict())
+
+        if "identifiers" in entry:
+            # For each new identifier
+            for new_identifier in entry["identifiers"]:
+                # Either find an existing identifier with the same scheme and update the "identifier" value
+                for existing_identifier in updated["identifiers"]:
+                    if existing_identifier["scheme"] == new_identifier["scheme"]:
+                        existing_identifier["identifier"] = new_identifier["identifier"]
+                        break
+                # Or add the new identifier to the list of identifiers
+                else:
+                    updated["identifiers"].append(new_identifier)
+
+        return StreamEntry(self._service.update(self._identity, vocab_id, updated))
 
 
 VOCABULARIES_DATASTREAM_READERS = {}

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/contrib/funders/mappings/os-v1/funders/funder-v2.0.0.json

@@ -14,8 +14,8 @@
           "type": "custom",
           "char_filter": ["strip_special_chars"],
           "filter": [
-            "lowercase",
-            "asciifolding",
+            "lowercasepreserveoriginal",
+            "asciifoldingpreserveoriginal",
             "edgegrams"
           ]
         },
@@ -24,8 +24,8 @@
           "type": "custom",
           "char_filter": ["strip_special_chars"],
           "filter": [
-            "lowercase",
-            "asciifolding"
+            "lowercasepreserveoriginal",
+            "asciifoldingpreserveoriginal"
           ]
         }
       },
@@ -40,11 +40,11 @@
         }
       },
       "filter": {
-        "lowercase": {
+        "lowercasepreserveoriginal": {
           "type": "lowercase",
           "preserve_original": true
         },
-        "asciifolding": {
+        "asciifoldingpreserveoriginal": {
           "type": "asciifolding",
           "preserve_original": true
         },

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/contrib/funders/mappings/os-v2/funders/funder-v2.0.0.json

@@ -14,8 +14,8 @@
           "type": "custom",
           "char_filter": ["strip_special_chars"],
           "filter": [
-            "lowercase",
-            "asciifolding",
+            "lowercasepreserveoriginal",
+            "asciifoldingpreserveoriginal",
             "edgegrams"
           ]
         },
@@ -24,8 +24,8 @@
           "type": "custom",
           "char_filter": ["strip_special_chars"],
           "filter": [
-            "lowercase",
-            "asciifolding"
+            "lowercasepreserveoriginal",
+            "asciifoldingpreserveoriginal"
           ]
         }
       },
@@ -40,11 +40,11 @@
         }
       },
       "filter": {
-        "lowercase": {
+        "lowercasepreserveoriginal": {
           "type": "lowercase",
           "preserve_original": true
         },
-        "asciifolding": {
+        "asciifoldingpreserveoriginal": {
           "type": "asciifolding",
           "preserve_original": true
         },

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/contrib/subjects/schema.py

@@ -13,7 +13,7 @@
 from functools import partial
 
 from invenio_i18n import get_locale
-from marshmallow import Schema, fields, pre_load
+from marshmallow import EXCLUDE, Schema, fields, pre_load
 from marshmallow_utils.fields import IdentifierSet, SanitizedUnicode
 from marshmallow_utils.schemas import IdentifierSchema
 
@@ -59,6 +59,14 @@ class SubjectSchema(BaseVocabularySchema):
 class SubjectRelationSchema(ContribVocabularyRelationSchema):
     """Schema to define an optional subject relation in another schema."""
 
+    # If re-running an OpenAIRE awards update on existing awards which already have subjects,
+    # the subject entries will contains `scheme` and `props`, which are unknown since they are `dump_only`.
+    # This makes the update exclude unknown field and go through with the update.
+    class Meta:
+        """Metadata class."""
+
+        unknown = EXCLUDE
+
     ftf_name = "subject"
     parent_field_name = "subjects"
     subject = SanitizedUnicode()

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies/datastreams/writers.py

@@ -87,23 +87,8 @@ class ServiceWriter(BaseWriter):
     def _do_update(self, entry):
         vocab_id = self._entry_id(entry)
         current = self._resolve(vocab_id)
-        combined_dict = current.to_dict()
-
-        # Update fields from entry
-        for key, value in entry.items():
-            if key in combined_dict:
-                if isinstance(combined_dict[key], list) and isinstance(value, list):
-                    combined_dict[key].extend(
-                        item for item in value if item not in combined_dict[key]
-                    )
-                else:
-                    combined_dict[key] = value
-            else:
-                combined_dict[key] = value
-
-        return StreamEntry(
-            self._service.update(self._identity, vocab_id, combined_dict)
-        )
+        updated = dict(current.to_dict(), **entry)
+        return StreamEntry(self._service.update(self._identity, vocab_id, updated))
 
     def write(self, stream_entry, *args, **kwargs):
         """Writes the input entry using a given service."""

{invenio-vocabularies-6.4.0 → invenio-vocabularies-6.5.0}/invenio_vocabularies.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invenio-vocabularies
-Version: 6.4.0
+Version: 6.5.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -50,6 +50,17 @@ Description: ..
         Changes
         =======
         
+        Version v6.5.0 (released 2024-10-31)
+        
+        - subjects: euroscivoc: change default to latest version-less URL
+        - Rename patched filters so the normalizer uses the default ones (#409)
+            * rename patched filters so the normalizer uses the default ones
+        
+        Version v6.4.1 (released 2024-10-15)
+        
+        - fix: exclude unknown fields when updating awards with subjects
+        - fix: revert generic writer and define OpenAIRE awards writer logic
+        
         Version v6.4.0 (released 2024-10-15)
         
         - jobs: add import awards OpenAIRE; Update CORDIS