invenio-vocabularies 8.1.0__py2.py3-none-any.whl → 8.2.1__py2.py3-none-any.whl

invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/messages/zh_CN/translations.json

@@ -1,28 +1,28 @@
 {
-  "Search for a funder by name": "",
-  "Funder": "",
-  "Search for funder...": "",
+  "Search for a funder by name": "按姓名搜索资助者",
+  "Funder": "资助机构",
+  "Search for funder...": "搜索资助机构…",
   "Additional information": "",
-  "optional": "",
-  "Number": "",
+  "optional": "可选择的",
+  "Number": "编号",
   "Award/Grant number": "",
-  "Title": "",
+  "Title": "标题",
   "Award/Grant Title": "",
-  "URL": "",
+  "URL": "统一资源定位系统",
   "Award/Grant URL": "",
-  "Add": "",
-  "Add custom": "",
-  "Edit": "",
-  "Remove": "",
-  "Open external link": "",
+  "Add": "添加",
+  "Add custom": "添加自定义",
+  "Edit": "编辑",
+  "Remove": "移除",
+  "Open external link": "打开外部链接",
   "Funder is required.": "",
   "URL must be valid.": "",
   "URL must be set alongside title or number.": "",
   "Add standard award/grant": "",
   "Add custom funding": "",
   "Search for awards/grants": "",
-  "Cancel": "",
-  "Change": "",
+  "Cancel": "取消",
+  "Change": "更改",
   "Did not find your award/grant? ": "",
   "Add a custom award/grant.": ""
 }

invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/messages/zh_TW/messages.po

@@ -0,0 +1,94 @@
+# 
+# Translators:
+# Tibor Simko <tibor.simko@cern.ch>, 2025
+# 
+msgid ""
+msgstr ""
+"Project-Id-Version: i18next-conv\n"
+"POT-Creation-Date: 2025-07-08T15:47:17.169Z\n"
+"PO-Revision-Date: 2025-05-13 21:01+0000\n"
+"Last-Translator: Tibor Simko <tibor.simko@cern.ch>, 2025\n"
+"Language-Team: Chinese (Taiwan) (https://app.transifex.com/inveniosoftware/teams/23537/zh_TW/)\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Language: zh_TW\n"
+"Plural-Forms: nplurals=1; plural=0;\n"
+"mime-version: 1.0\n"
+
+msgid "Search for a funder by name"
+msgstr ""
+
+msgid "Funder"
+msgstr ""
+
+msgid "Search for funder..."
+msgstr ""
+
+msgid "Additional information"
+msgstr ""
+
+msgid "optional"
+msgstr "可選擇的"
+
+msgid "Number"
+msgstr ""
+
+msgid "Award/Grant number"
+msgstr ""
+
+msgid "Title"
+msgstr "標題"
+
+msgid "Award/Grant Title"
+msgstr ""
+
+msgid "URL"
+msgstr ""
+
+msgid "Award/Grant URL"
+msgstr ""
+
+msgid "Add"
+msgstr ""
+
+msgid "Add custom"
+msgstr ""
+
+msgid "Edit"
+msgstr "編輯"
+
+msgid "Remove"
+msgstr "移除"
+
+msgid "Open external link"
+msgstr ""
+
+msgid "Funder is required."
+msgstr ""
+
+msgid "URL must be valid."
+msgstr ""
+
+msgid "URL must be set alongside title or number."
+msgstr ""
+
+msgid "Add standard award/grant"
+msgstr ""
+
+msgid "Add custom funding"
+msgstr ""
+
+msgid "Search for awards/grants"
+msgstr ""
+
+msgid "Cancel"
+msgstr "取消"
+
+msgid "Change"
+msgstr ""
+
+msgid "Did not find your award/grant? "
+msgstr ""
+
+msgid "Add a custom award/grant."
+msgstr ""

invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/messages/zh_TW/translations.json

@@ -3,17 +3,17 @@
   "Funder": "",
   "Search for funder...": "",
   "Additional information": "",
-  "optional": "",
+  "optional": "可選擇的",
   "Number": "",
   "Award/Grant number": "",
-  "Title": "",
+  "Title": "標題",
   "Award/Grant Title": "",
   "URL": "",
   "Award/Grant URL": "",
   "Add": "",
   "Add custom": "",
-  "Edit": "",
-  "Remove": "",
+  "Edit": "編輯",
+  "Remove": "移除",
   "Open external link": "",
   "Funder is required.": "",
   "URL must be valid.": "",
@@ -21,7 +21,7 @@
   "Add standard award/grant": "",
   "Add custom funding": "",
   "Search for awards/grants": "",
-  "Cancel": "",
+  "Cancel": "取消",
   "Change": "",
   "Did not find your award/grant? ": "",
   "Add a custom award/grant.": ""

invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/package.json

@@ -1,37 +1,7 @@
 {
   "name": "invenio-vocabularies-ui",
   "config": {
-    "languages": [
-      "ar",
-      "bg",
-      "ca",
-      "cs",
-      "da",
-      "de",
-      "el",
-      "en",
-      "es",
-      "et",
-      "fa",
-      "fr",
-      "hr",
-      "hu",
-      "it",
-      "ja",
-      "ka",
-      "lt",
-      "no",
-      "pl",
-      "pt",
-      "ro",
-      "ru",
-      "sk",
-      "sv",
-      "tr",
-      "uk",
-      "zh_CN",
-      "zh_TW"
-    ]
+    "languages": ["en"]
   },
   "devDependencies": {
     "i18next-conv": "^10.2.0",
@@ -41,9 +11,9 @@
     "i18next-browser-languagedetector": "^6.1.0"
   },
   "scripts": {
-    "extract_messages": "i18next-scanner --config i18next-scanner.config.js '../../js/**/*.{js,jsx}'",
-    "postextract_messages": "i18next-conv -l en -s ./messages/en/translations.json -t ./translations.pot",
+    "extract_messages": "i18next-scanner --config i18next-scanner.config.js '../../js/**/*.{js,jsx}' '!../../js/**/node_modules/**'",
+    "postextract_messages": "node ./scripts/postExtractMessages.js",
     "compile_catalog": "node ./scripts/compileCatalog.js",
-    "init_catalog": "node ./scripts/initCatalog"
+    "init_catalog": "node ./scripts/initCatalog.js"
   }
 }

invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/translations.pot

@@ -5,8 +5,8 @@ msgstr ""
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
 "Plural-Forms: nplurals=2; plural=(n != 1)\n"
-"POT-Creation-Date: 2025-05-13T09:10:50.615Z\n"
-"PO-Revision-Date: 2025-05-13T09:10:50.616Z\n"
+"POT-Creation-Date: 2025-07-08T15:47:17.169Z\n"
+"PO-Revision-Date: 2025-07-08T15:47:17.170Z\n"
 "Language: en\n"
 
 msgid "Search for a funder by name"
@@ -85,4 +85,4 @@ msgid "Did not find your award/grant? "
 msgstr "Did not find your award/grant? "
 
 msgid "Add a custom award/grant."
-msgstr "Add a custom award/grant."
+msgstr "Add a custom award/grant."

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/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
                     )
 
@@ -262,26 +267,43 @@ class OrcidTransformer(BaseTransformer):
         record = stream_entry.entry
         person = record["person"]
         orcid_id = record["orcid-identifier"]["path"]
+        errors = []
+
+        name = person.get("name", None)
+        family_name = name.get("family-name", None) if name else None
+        given_names = name.get("given-names", None) if name else None
 
-        name = person.get("name")
         if name is None:
-            raise TransformerError(
-                f"Name not found in ORCiD entry for ORCiD ID: {orcid_id}."
+            errors.append(
+                TransformerError(
+                    f"Name not found in ORCiD entry for ORCiD ID: {orcid_id}."
+                )
             )
-        if name.get("family-name") is None:
-            raise TransformerError(
-                f"Family name not found in ORCiD entry for ORCiD ID: {orcid_id}."
+        if family_name is None:
+            errors.append(
+                TransformerError(
+                    f"Family name not found in ORCiD entry for ORCiD ID: {orcid_id}."
+                )
+            )
+        if not self._is_valid_name(given_names + family_name):
+            errors.append(
+                TransformerError(
+                    f"Invalid characters in name for ORCiD ID: {orcid_id}."
+                )
             )
 
-        if not self._is_valid_name(name["given-names"] + name["family-name"]):
-            raise TransformerError(
-                f"Invalid characters in name for ORCiD ID: {orcid_id}."
+        if errors:
+            all_errors = "\n".join(str(e) for e in errors)
+            error_message = (
+                f"ORCiD entry with ORCiD ID: #{orcid_id} failed transformation. "
+                f"See errors:\n{all_errors}"
             )
+            stream_entry.errors.append(error_message)
 
         entry = {
             "id": orcid_id,
-            "given_name": name.get("given-names"),
-            "family_name": name.get("family-name"),
+            "given_name": given_names,
+            "family_name": family_name,
             "identifiers": [{"scheme": "orcid", "identifier": orcid_id}],
             "affiliations": self._extract_affiliations(record),
         }
@@ -292,6 +314,8 @@ class OrcidTransformer(BaseTransformer):
 
     def _is_valid_name(self, name):
         """Check whether the name passes the regex."""
+        if not name:
+            return False
         if not self._names_exclude_regex:
             return True
         return not bool(re.search(self._names_exclude_regex, name, re.UNICODE | re.V1))

invenio_vocabularies/datastreams/datastreams.py

@@ -79,6 +79,7 @@ class DataStream:
         """Process a batch of entries."""
         current_app.logger.info(f"Processing batch of size: {len(batch)}")
         transformed_entries = []
+        transformed_entries_with_errors = []
         for stream_entry in batch:
             if stream_entry.errors:
                 current_app.logger.warning(
@@ -88,12 +89,17 @@ class DataStream:
             else:
                 transformed_entry = self.transform(stream_entry)
                 if transformed_entry.errors:
+                    transformed_entries_with_errors.append(transformed_entry)
                     yield transformed_entry
                 elif self.filter(transformed_entry):
                     transformed_entry.filtered = True
                     yield transformed_entry
                 else:
                     transformed_entries.append(transformed_entry)
+        if transformed_entries_with_errors:
+            current_app.logger.warning(
+                f"Skipping {len(transformed_entries_with_errors)} transformed entries with errors."
+            )
         if transformed_entries:
             if self.write_many:
                 yield from self.batch_write(transformed_entries)

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/services/tasks.py

@@ -9,7 +9,7 @@
 
 from celery import shared_task
 from flask import current_app
-from invenio_jobs.errors import TaskExecutionError
+from invenio_jobs.errors import TaskExecutionPartialError
 
 from ..datastreams.factories import DataStreamFactory
 
@@ -31,6 +31,6 @@ def process_datastream(config):
                 current_app.logger.error(err)
             entries_with_errors += 1
     if entries_with_errors:
-        raise TaskExecutionError(
+        raise TaskExecutionPartialError(
             message=f"Task execution succeeded with {entries_with_errors} entries with errors."
         )