invenio-vocabularies 8.2.0__tar.gz → 8.3.0__tar.gz

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/CHANGES.rst

@@ -9,6 +9,14 @@
 Changes
 =======
 
+Version v8.3.0 (released 2025-07-31)
+
+- subjects: Add search scheme field configuration to enable composite and filter query support in subject search functionality
+
+Version v8.2.1 (released 2025-07-21)
+
+- fix(jobs): remove string casts from since
+
 Version v8.2.0 (released 2025-07-17)
 
 - tasks: fix error name

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: invenio-vocabularies
-Version: 8.2.0
+Version: 8.3.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -89,6 +89,14 @@ Invenio module for managing vocabularies, based on Invenio-Records and Invenio-R
 Changes
 =======
 
+Version v8.3.0 (released 2025-07-31)
+
+- subjects: Add search scheme field configuration to enable composite and filter query support in subject search functionality
+
+Version v8.2.1 (released 2025-07-21)
+
+- fix(jobs): remove string casts from since
+
 Version v8.2.0 (released 2025-07-17)
 
 - tasks: fix error name

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/invenio_vocabularies/__init__.py

@@ -11,6 +11,6 @@
 
 from .ext import InvenioVocabularies
 
-__version__ = "8.2.0"
+__version__ = "8.3.0"
 
 __all__ = ("__version__", "InvenioVocabularies")

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/invenio_vocabularies/contrib/common/ror/datastreams.py

@@ -10,8 +10,8 @@
 """ROR-related Datastreams Readers/Writers/Transformers module."""
 
 import io
+from datetime import datetime
 
-import arrow
 import requests
 from flask import current_app
 from idutils import normalize_ror
@@ -52,9 +52,11 @@ class RORHTTPReader(BaseReader):
                     json_ld_reponse.raise_for_status()
                     json_ld_data = json_ld_reponse.json()
 
-                    last_dump_date = arrow.get(
-                        json_ld_data.get("dateCreated")
-                        or json_ld_data.get("datePublished")
+                    last_dump_date = json_ld_data.get(
+                        "dateCreated"
+                    ) or json_ld_data.get("datePublished")
+                    last_dump_date = datetime.fromisoformat(
+                        last_dump_date.replace("Z", "+00:00")
                     )
                     return last_dump_date
         else:
@@ -93,7 +95,9 @@ class RORHTTPReader(BaseReader):
 
         if self._since and self._since != "None":
             last_dump_date = self._get_last_dump_date(linksets)
-            if last_dump_date < arrow.get(self._since):
+            since = datetime.fromisoformat(self._since)
+
+            if last_dump_date < since:
                 current_app.logger.info(
                     f"Skipping ROR data dump (last dump: {last_dump_date}, since: {self._since})"
                 )

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/invenio_vocabularies/contrib/names/datastreams.py

@@ -11,13 +11,12 @@
 import csv
 import io
 import tarfile
-from concurrent.futures import ThreadPoolExecutor, as_completed
+from concurrent.futures import ThreadPoolExecutor
 from contextvars import copy_context
-from datetime import timedelta
+from datetime import datetime, timedelta
 from itertools import islice
 from pathlib import Path
 
-import arrow
 import regex as re
 from flask import current_app
 from invenio_access.permissions import system_identity
@@ -66,12 +65,16 @@ class OrcidDataSyncReader(BaseReader):
 
         Yield ORCiDs to sync until the last sync date is reached.
         """
-        date_format = "YYYY-MM-DD HH:mm:ss.SSSSSS"
-        date_format_no_millis = "YYYY-MM-DD HH:mm:ss"
-        time_shift = current_app.config["VOCABULARIES_ORCID_SYNC_SINCE"]
+        date_format = "%Y-%m-%d %H:%M:%S.%f"
+        date_format_no_millis = "%Y-%m-%d %H:%M:%S"
+
         if self.since:
-            time_shift = self.since
-        last_sync = arrow.now() - timedelta(**time_shift)
+            last_sync = datetime.now()
+        else:
+            last_sync = datetime.now() - timedelta(
+                **current_app.config["VOCABULARIES_ORCID_SYNC_SINCE"]
+            )
+
         try:
             content = io.TextIOWrapper(fileobj, encoding="utf-8")
             csv_reader = csv.DictReader(content)
@@ -82,9 +85,11 @@ class OrcidDataSyncReader(BaseReader):
                 # Lambda file is ordered by last modified date
                 last_modified_str = row["last_modified"]
                 try:
-                    last_modified_date = arrow.get(last_modified_str, date_format)
-                except arrow.parser.ParserError:
-                    last_modified_date = arrow.get(
+                    last_modified_date = datetime.strptime(
+                        last_modified_str, date_format
+                    )
+                except Exception:
+                    last_modified_date = datetime.strptime(
                         last_modified_str, date_format_no_millis
                     )
 

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/invenio_vocabularies/contrib/subjects/config.py

@@ -45,8 +45,10 @@ class SubjectsSearchOptions(SearchOptions):
     """Search options."""
 
     suggest_parser_cls = CompositeSuggestQueryParser.factory(
+        filter_field="scheme",
         fields=[
             "subject^100",
+            "scheme^20",
             localized_title,
             "synonyms^20",
         ],

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/invenio_vocabularies/jobs.py

@@ -8,8 +8,6 @@
 
 """Jobs module."""
 
-import datetime
-
 from invenio_i18n import lazy_gettext as _
 from invenio_jobs.jobs import JobType
 
@@ -40,7 +38,7 @@ class ProcessRORAffiliationsJob(ProcessDataStreamJob):
             "config": {
                 "readers": [
                     {
-                        "args": {"since": str(since)},
+                        "args": {"since": since},
                         "type": "ror-http",
                     },
                     {"args": {"regex": "_schema_v2\\.json$"}, "type": "zip"},
@@ -78,7 +76,7 @@ class ProcessRORFundersJob(ProcessDataStreamJob):
             "config": {
                 "readers": [
                     {
-                        "args": {"since": str(since)},
+                        "args": {"since": since},
                         "type": "ror-http",
                     },
                     {"args": {"regex": "_schema_v2\\.json$"}, "type": "zip"},
@@ -173,4 +171,9 @@ class ImportORCIDJob(ProcessDataStreamJob):
     @classmethod
     def build_task_arguments(cls, job_obj, since=None, **kwargs):
         """Process ORCID data."""
-        return {"config": {**ORCID_PRESET_DATASTREAM_CONFIG}}
+        task_args = {"config": {**ORCID_PRESET_DATASTREAM_CONFIG}}
+        for reader in task_args["config"]["readers"]:
+            # Assign since to all readers of the ORCID job
+            # It is the responsibility of the reader to handle it or ignore it
+            reader["args"] = {**reader.get("args", {}), "since": str(since)}
+        return task_args

{invenio_vocabularies-8.2.0 → invenio_vocabularies-8.3.0}/invenio_vocabularies.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: invenio-vocabularies
-Version: 8.2.0
+Version: 8.3.0
 Summary: Invenio module for managing vocabularies.
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -89,6 +89,14 @@ Invenio module for managing vocabularies, based on Invenio-Records and Invenio-R
 Changes
 =======
 
+Version v8.3.0 (released 2025-07-31)
+
+- subjects: Add search scheme field configuration to enable composite and filter query support in subject search functionality
+
+Version v8.2.1 (released 2025-07-21)
+
+- fix(jobs): remove string casts from since
+
 Version v8.2.0 (released 2025-07-17)
 
 - tasks: fix error name