invenio-vocabularies 4.2.0__py2.py3-none-any.whl → 4.4.0__py2.py3-none-any.whl

invenio_vocabularies/__init__.py

@@ -10,6 +10,6 @@
 
 from .ext import InvenioVocabularies
 
-__version__ = "4.2.0"
+__version__ = "4.4.0"
 
 __all__ = ("__version__", "InvenioVocabularies")

invenio_vocabularies/cli.py

@@ -142,18 +142,27 @@ def convert(vocabulary, filepath=None, origin=None, target=None, num_samples=Non
     type=click.STRING,
     help="Identifier of the vocabulary item to delete.",
 )
-@click.option("--all", is_flag=True, default=False, help="Not supported yet.")
+@click.option("--all", is_flag=True, default=False)
 @with_appcontext
 def delete(vocabulary, identifier, all):
     """Delete all items or a specific one of the vocabulary."""
-    if not id and not all:
+    if not identifier and not all:
         click.secho("An identifier or the --all flag must be present.", fg="red")
         exit(1)
+
     vc = get_vocabulary_config(vocabulary)
     service = vc.get_service()
     if identifier:
         try:
-            if service.delete(identifier, system_identity):
+            if service.delete(system_identity, identifier):
                 click.secho(f"{identifier} deleted from {vocabulary}.", fg="green")
         except (PIDDeletedError, PIDDoesNotExistError):
             click.secho(f"PID {identifier} not found.")
+    elif all:
+        items = service.scan(system_identity)
+        for item in items.hits:
+            try:
+                if service.delete(system_identity, item["id"]):
+                    click.secho(f"{item['id']} deleted from {vocabulary}.", fg="green")
+            except (PIDDeletedError, PIDDoesNotExistError):
+                click.secho(f"PID {item['id']} not found.")

invenio_vocabularies/config.py

@@ -155,3 +155,16 @@ VOCABULARIES_TYPES_SEARCH = {
     "sort": ["name", "count"],
 }
 """Vocabulary type search configuration."""
+
+VOCABULARIES_ORCID_ACCESS_KEY = "TODO"
+"""ORCID access key to access the s3 bucket."""
+VOCABULARIES_ORCID_SECRET_KEY = "TODO"
+"""ORCID secret key to access the s3 bucket."""
+VOCABULARIES_ORCID_SUMMARIES_BUCKET = "v3.0-summaries"
+"""ORCID summaries bucket name."""
+VOCABULARIES_ORCID_SYNC_MAX_WORKERS = 32
+"""ORCID max number of simultaneous workers/connections."""
+VOCABULARIES_ORCID_SYNC_SINCE = {
+    "days": 1,
+}
+"""ORCID time shift to sync. Parameters accepted are the ones passed to 'datetime.timedelta'."""

invenio_vocabularies/contrib/affiliations/affiliations.py

@@ -8,11 +8,13 @@
 
 """Vocabulary affiliations."""
 
+from flask_resources import JSONSerializer, ResponseHandler
 from invenio_db import db
 from invenio_records.dumpers import SearchDumper
 from invenio_records.dumpers.indexedat import IndexedAtDumperExt
 from invenio_records_resources.factories.factory import RecordTypeFactory
 from invenio_records_resources.records.systemfields import ModelPIDField
+from invenio_records_resources.resources.records.headers import etag_headers
 
 from ...services.permissions import PermissionPolicy
 from .config import AffiliationsSearchOptions, service_components
@@ -46,4 +48,12 @@ record_type = RecordTypeFactory(
     permission_policy_cls=PermissionPolicy,
     # Resource layer
     endpoint_route="/affiliations",
+    resource_cls_attrs={
+        "response_handlers": {
+            "application/json": ResponseHandler(JSONSerializer(), headers=etag_headers),
+            "application/vnd.inveniordm.v1+json": ResponseHandler(
+                JSONSerializer(), headers=etag_headers
+            ),
+        }
+    },
 )

invenio_vocabularies/contrib/affiliations/datastreams.py

@@ -42,7 +42,7 @@ class AffiliationsRORTransformer(RORTransformer):
             *args,
             vocab_schemes=vocab_schemes,
             funder_fundref_doi_prefix=funder_fundref_doi_prefix,
-            **kwargs
+            **kwargs,
         )
 
 

invenio_vocabularies/contrib/funders/datastreams.py

@@ -46,7 +46,7 @@ class FundersRORTransformer(RORTransformer):
             *args,
             vocab_schemes=vocab_schemes,
             funder_fundref_doi_prefix=funder_fundref_doi_prefix,
-            **kwargs
+            **kwargs,
         )
 
 

invenio_vocabularies/contrib/names/datastreams.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
@@ -8,15 +8,123 @@
 
 """Names datastreams, transformers, writers and readers."""
 
+import csv
+import io
+import tarfile
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from datetime import timedelta
+
+import arrow
+import regex as re
+from flask import current_app
 from invenio_access.permissions import system_identity
 from invenio_records.dictutils import dict_lookup
 
+from invenio_vocabularies.contrib.names.s3client import S3OrcidClient
+
 from ...datastreams.errors import TransformerError
-from ...datastreams.readers import SimpleHTTPReader
+from ...datastreams.readers import BaseReader, SimpleHTTPReader
 from ...datastreams.transformers import BaseTransformer
 from ...datastreams.writers import ServiceWriter
 
 
+class OrcidDataSyncReader(BaseReader):
+    """ORCiD Data Sync Reader."""
+
+    def __init__(self, origin=None, mode="r", since=None, *args, **kwargs):
+        """Constructor.
+
+        :param origin: Data source (e.g. filepath).
+                       Can be none in case of piped readers.
+        """
+        super().__init__(origin=origin, mode=mode, *args, **kwargs)
+        self.s3_client = S3OrcidClient()
+        self.since = since
+
+    def _fetch_orcid_data(self, orcid_to_sync, bucket):
+        """Fetches a single ORCiD record from S3."""
+        # The ORCiD file key is located in a folder which name corresponds to the last three digits of the ORCiD
+        suffix = orcid_to_sync[-3:]
+        key = f"{suffix}/{orcid_to_sync}.xml"
+        try:
+            return self.s3_client.read_file(f"s3://{bucket}/{key}")
+        except Exception as e:
+            # TODO: log
+            return None
+
+    def _process_lambda_file(self, fileobj):
+        """Process the ORCiD lambda file and returns a list of ORCiDs to sync.
+
+        The decoded fileobj looks like the following:
+        orcid, path, date_created, last_modified
+        0000-0001-5109-3700, http://orcid.org/0000-0001-5109-3700, 2014-08-02 15:00:00.000,2021-08-02 15:00:00.000
+
+        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"]
+        if self.since:
+            time_shift = self.since
+        last_sync = arrow.now() - timedelta(**time_shift)
+
+        file_content = fileobj.read().decode("utf-8")
+
+        csv_reader = csv.DictReader(file_content.splitlines())
+
+        for row in csv_reader:  # Skip the header line
+            orcid = row["orcid"]
+
+            # 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_str, date_format_no_millis)
+
+            if last_modified_date < last_sync:
+                break
+            yield orcid
+
+    def _iter(self, orcids):
+        """Iterates over the ORCiD records yielding each one."""
+        with ThreadPoolExecutor(
+            max_workers=current_app.config["VOCABULARIES_ORCID_SYNC_MAX_WORKERS"]
+        ) as executor:
+            futures = [
+                executor.submit(
+                    self._fetch_orcid_data,
+                    orcid,
+                    current_app.config["VOCABULARIES_ORCID_SUMMARIES_BUCKET"],
+                )
+                for orcid in orcids
+            ]
+            for future in as_completed(futures):
+                result = future.result()
+                if result is not None:
+                    yield result
+
+    def read(self, item=None, *args, **kwargs):
+        """Streams the ORCiD lambda file, process it to get the ORCiDS to sync and yields it's data."""
+        # Read the file from S3
+        tar_content = self.s3_client.read_file(
+            "s3://orcid-lambda-file/last_modified.csv.tar"
+        )
+
+        orcids_to_sync = []
+        # Opens tar file and process it
+        with tarfile.open(fileobj=io.BytesIO(tar_content)) as tar:
+            # Iterate over each member (file or directory) in the tar file
+            for member in tar.getmembers():
+                # Extract the file
+                extracted_file = tar.extractfile(member)
+                if extracted_file:
+                    # Process the file and get the ORCiDs to sync
+                    orcids_to_sync.extend(self._process_lambda_file(extracted_file))
+
+        yield from self._iter(orcids_to_sync)
+
+
 class OrcidHTTPReader(SimpleHTTPReader):
     """ORCiD HTTP Reader."""
 
@@ -30,9 +138,26 @@ class OrcidHTTPReader(SimpleHTTPReader):
         super().__init__(origin, *args, **kwargs)
 
 
+DEFAULT_NAMES_EXCLUDE_REGEX = r"[\p{P}\p{S}\p{Nd}\p{No}\p{Emoji}--,.()\-']"
+"""Regex to filter out names with punctuations, symbols, decimal numbers and emojis."""
+
+
 class OrcidTransformer(BaseTransformer):
     """Transforms an ORCiD record into a names record."""
 
+    def __init__(
+        self, *args, names_exclude_regex=DEFAULT_NAMES_EXCLUDE_REGEX, **kwargs
+    ) -> None:
+        """Constructor."""
+        self._names_exclude_regex = names_exclude_regex
+        super().__init__()
+
+    def _is_valid_name(self, name):
+        """Check whether the name passes the regex."""
+        if not self._names_exclude_regex:
+            return True
+        return not bool(re.search(self._names_exclude_regex, name, re.UNICODE | re.V1))
+
     def apply(self, stream_entry, **kwargs):
         """Applies the transformation to the stream entry."""
         record = stream_entry.entry
@@ -42,6 +167,11 @@ class OrcidTransformer(BaseTransformer):
         name = person.get("name")
         if name is None:
             raise TransformerError(f"Name not found in ORCiD entry.")
+        if name.get("family-name") is None:
+            raise TransformerError(f"Family name not found in ORCiD entry.")
+
+        if not self._is_valid_name(name["given-names"] + name["family-name"]):
+            raise TransformerError(f"Invalid characters in name.")
 
         entry = {
             "id": orcid_id,
@@ -89,6 +219,7 @@ class NamesServiceWriter(ServiceWriter):
 
 VOCABULARIES_DATASTREAM_READERS = {
     "orcid-http": OrcidHTTPReader,
+    "orcid-data-sync": OrcidDataSyncReader,
 }
 
 
@@ -128,3 +259,30 @@ DATASTREAM_CONFIG = {
 
 An origin is required for the reader.
 """
+
+# TODO: Used on the jobs and should be set as a "PRESET" (naming to be defined)
+ORCID_PRESET_DATASTREAM_CONFIG = {
+    "readers": [
+        {
+            "type": "orcid-data-sync",
+        },
+        {"type": "xml"},
+    ],
+    "transformers": [{"type": "orcid"}],
+    "writers": [
+        {
+            "type": "async",
+            "args": {
+                "writer": {
+                    "type": "names-service",
+                }
+            },
+        }
+    ],
+    "batch_size": 1000,
+    "write_many": True,
+}
+"""ORCiD Data Stream configuration.
+
+An origin is required for the reader.
+"""

invenio_vocabularies/contrib/names/names.py

@@ -8,6 +8,7 @@
 
 """Vocabulary names."""
 
+from flask_resources import JSONSerializer, ResponseHandler
 from invenio_db import db
 from invenio_records.dumpers import SearchDumper
 from invenio_records.dumpers.indexedat import IndexedAtDumperExt
@@ -18,6 +19,7 @@ from invenio_records_resources.records.systemfields import (
     ModelPIDField,
     PIDListRelation,
 )
+from invenio_records_resources.resources.records.headers import etag_headers
 
 from ...services.permissions import PermissionPolicy
 from ..affiliations.api import Affiliation
@@ -63,4 +65,12 @@ record_type = RecordTypeFactory(
     permission_policy_cls=PermissionPolicy,
     # Resource layer
     endpoint_route="/names",
+    resource_cls_attrs={
+        "response_handlers": {
+            "application/json": ResponseHandler(JSONSerializer(), headers=etag_headers),
+            "application/vnd.inveniordm.v1+json": ResponseHandler(
+                JSONSerializer(), headers=etag_headers
+            ),
+        }
+    },
 )

invenio_vocabularies/contrib/names/s3client.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+#
+# This file is part of Invenio.
+# Copyright (C) 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
+# details.
+
+"""S3 client."""
+
+from flask import current_app
+
+try:
+    import s3fs
+except ImportError:
+    s3fs = None
+
+
+class S3Client:
+    """S3 client."""
+
+    def __init__(self, access_key, secret_key):
+        """Constructor."""
+        if s3fs is None:
+            raise Exception("s3fs is not installed.")
+
+        self.fs = s3fs.S3FileSystem(key=access_key, secret=secret_key)
+
+    def read_file(self, s3_path):
+        """Reads a file from S3."""
+        with self.fs.open(s3_path, "rb") as f:
+            return f.read()
+
+
+class S3OrcidClient(S3Client):
+    """S3 ORCiD client."""
+
+    def __init__(self):
+        """Constructor."""
+        super().__init__(
+            access_key=current_app.config["VOCABULARIES_ORCID_ACCESS_KEY"],
+            secret_key=current_app.config["VOCABULARIES_ORCID_SECRET_KEY"],
+        )

invenio_vocabularies/contrib/subjects/subjects.py

@@ -9,9 +9,11 @@
 
 """Vocabulary subjects."""
 
+from flask_resources import JSONSerializer, ResponseHandler
 from invenio_records.dumpers import SearchDumper
 from invenio_records.dumpers.indexedat import IndexedAtDumperExt
 from invenio_records_resources.factories.factory import RecordTypeFactory
+from invenio_records_resources.resources.records.headers import etag_headers
 
 from ...records.pidprovider import PIDProviderFactory
 from ...records.systemfields import BaseVocabularyPIDFieldContext
@@ -42,4 +44,12 @@ record_type = RecordTypeFactory(
     permission_policy_cls=PermissionPolicy,
     # Resource layer
     endpoint_route="/subjects",
+    resource_cls_attrs={
+        "response_handlers": {
+            "application/json": ResponseHandler(JSONSerializer(), headers=etag_headers),
+            "application/vnd.inveniordm.v1+json": ResponseHandler(
+                JSONSerializer(), headers=etag_headers
+            ),
+        }
+    },
 )

invenio_vocabularies/datastreams/datastreams.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
@@ -8,17 +8,41 @@
 
 """Base data stream."""
 
+from flask import current_app
+
 from .errors import ReaderError, TransformerError, WriterError
 
 
 class StreamEntry:
     """Object to encapsulate streams processing."""
 
-    def __init__(self, entry, errors=None):
-        """Constructor."""
+    def __init__(self, entry, record=None, errors=None, op_type=None, exc=None):
+        """Constructor for the StreamEntry class.
+
+        :param entry (object): The entry object, usually a record dict.
+        :param record (object): The record object, usually a record class.
+        :param errors (list, optional): List of errors. Defaults to None.
+        :param op_type (str, optional): The operation type. Defaults to None.
+        :param exc (str, optional): The raised unhandled exception. Defaults to None.
+        """
         self.entry = entry
+        self.record = record
         self.filtered = False
         self.errors = errors or []
+        self.op_type = op_type
+        self.exc = exc
+
+    def log_errors(self, logger=None):
+        """Log the errors using the provided logger or the default logger.
+
+        :param logger (logging.Logger, optional): Logger instance to use. Defaults to None.
+        """
+        if logger is None:
+            logger = current_app.logger
+        for error in self.errors:
+            logger.error(f"Error in entry {self.entry}: {error}")
+        if self.exc:
+            logger.error(f"Exception in entry {self.entry}: {self.exc}")
 
 
 class DataStream:
@@ -39,15 +63,10 @@ class DataStream:
         """Checks if an stream_entry should be filtered out (skipped)."""
         return False
 
-    def process(self, *args, **kwargs):
-        """Iterates over the entries.
-
-        Uses the reader to get the raw entries and transforms them.
-        It will iterate over the `StreamEntry` objects returned by
-        the reader, apply the transformations and yield the result of
-        writing it.
-        """
-        for stream_entry in self.read():
+    def process_batch(self, batch, write_many=False):
+        """Process a batch of entries."""
+        transformed_entries = []
+        for stream_entry in batch:
             if stream_entry.errors:
                 yield stream_entry  # reading errors
             else:
@@ -58,7 +77,31 @@ class DataStream:
                     transformed_entry.filtered = True
                     yield transformed_entry
                 else:
-                    yield self.write(transformed_entry)
+                    transformed_entries.append(transformed_entry)
+        if transformed_entries:
+            if write_many:
+                yield from self.batch_write(transformed_entries)
+            else:
+                yield from (self.write(entry) for entry in transformed_entries)
+
+    def process(self, batch_size=100, write_many=False, *args, **kwargs):
+        """Iterates over the entries.
+
+        Uses the reader to get the raw entries and transforms them.
+        It will iterate over the `StreamEntry` objects returned by
+        the reader, apply the transformations and yield the result of
+        writing it.
+        """
+        batch = []
+        for stream_entry in self.read():
+            batch.append(stream_entry)
+            if len(batch) >= batch_size:
+                yield from self.process_batch(batch, write_many=write_many)
+                batch = []
+
+        # Process any remaining entries in the last batch
+        if batch:
+            yield from self.process_batch(batch, write_many=write_many)
 
     def read(self):
         """Recursively read the entries."""
@@ -107,6 +150,11 @@ class DataStream:
 
         return stream_entry
 
+    def batch_write(self, stream_entries, *args, **kwargs):
+        """Apply the transformations to an stream_entry. Errors are handler in the service layer."""
+        for writer in self._writers:
+            yield from writer.write_many(stream_entries)
+
     def total(self, *args, **kwargs):
         """The total of entries obtained from the origin."""
         raise NotImplementedError()

invenio_vocabularies/datastreams/readers.py

@@ -21,6 +21,7 @@ from json.decoder import JSONDecodeError
 import requests
 import yaml
 from lxml import etree
+from lxml.html import fromstring
 from lxml.html import parse as html_parse
 
 from .errors import ReaderError
@@ -226,8 +227,13 @@ class XMLReader(BaseReader):
     def _iter(self, fp, *args, **kwargs):
         """Read and parse an XML file to dict."""
         # NOTE: We parse HTML, to skip XML validation and strip XML namespaces
-        xml_tree = html_parse(fp).getroot()
-        record = etree_to_dict(xml_tree)["html"]["body"].get("record")
+        record = None
+        try:
+            xml_tree = fromstring(fp)
+            record = etree_to_dict(xml_tree).get("record")
+        except Exception as e:
+            xml_tree = html_parse(fp).getroot()
+            record = etree_to_dict(xml_tree)["html"]["body"].get("record")
 
         if not record:
             raise ReaderError(f"Record not found in XML entry.")

invenio_vocabularies/datastreams/tasks.py

@@ -15,11 +15,23 @@ from ..datastreams.factories import WriterFactory
 
 
 @shared_task(ignore_result=True)
-def write_entry(writer, entry):
+def write_entry(writer_config, entry):
     """Write an entry.
 
     :param writer: writer configuration as accepted by the WriterFactory.
     :param entry: dictionary, StreamEntry is not serializable.
     """
-    writer = WriterFactory.create(config=writer)
+    writer = WriterFactory.create(config=writer_config)
     writer.write(StreamEntry(entry))
+
+
+@shared_task(ignore_result=True)
+def write_many_entry(writer_config, entries):
+    """Write many entries.
+
+    :param writer: writer configuration as accepted by the WriterFactory.
+    :param entry: lisf ot dictionaries, StreamEntry is not serializable.
+    """
+    writer = WriterFactory.create(config=writer_config)
+    stream_entries = [StreamEntry(entry) for entry in entries]
+    writer.write_many(stream_entries)

invenio_vocabularies/datastreams/writers.py

@@ -20,12 +20,17 @@ from marshmallow import ValidationError
 
 from .datastreams import StreamEntry
 from .errors import WriterError
-from .tasks import write_entry
+from .tasks import write_entry, write_many_entry
 
 
 class BaseWriter(ABC):
     """Base writer."""
 
+    def __init__(self, *args, **kwargs):
+        """Base initialization logic."""
+        # Add any base initialization here if needed
+        pass
+
     @abstractmethod
     def write(self, stream_entry, *args, **kwargs):
         """Writes the input stream entry to the target output.
@@ -36,6 +41,16 @@ class BaseWriter(ABC):
         """
         pass
 
+    @abstractmethod
+    def write_many(self, stream_entries, *args, **kwargs):
+        """Writes the input streams entry to the target output.
+
+        :returns: A List of StreamEntry. The result of writing the entry.
+                  Raises WriterException in case of errors.
+
+        """
+        pass
+
 
 class ServiceWriter(BaseWriter):
     """Writes the entries to an RDM instance using a Service object."""
@@ -86,6 +101,25 @@ class ServiceWriter(BaseWriter):
             # TODO: Check if we can get the error message easier
             raise WriterError([{"InvalidRelationValue": err.args[0]}])
 
+    def write_many(self, stream_entries, *args, **kwargs):
+        """Writes the input entries using a given service."""
+        entries = [entry.entry for entry in stream_entries]
+        entries_with_id = [(self._entry_id(entry), entry) for entry in entries]
+        results = self._service.create_or_update_many(self._identity, entries_with_id)
+        stream_entries_processed = []
+        for entry, result in zip(entries, results):
+            processed_stream_entry = StreamEntry(
+                entry=entry,
+                record=result.record,
+                errors=result.errors,
+                op_type=result.op_type,
+                exc=result.exc,
+            )
+            processed_stream_entry.log_errors()
+            stream_entries_processed.append(processed_stream_entry)
+
+        return stream_entries_processed
+
 
 class YamlWriter(BaseWriter):
     """Writes the entries to a YAML file."""
@@ -108,6 +142,15 @@ class YamlWriter(BaseWriter):
 
         return stream_entry
 
+    def write_many(self, stream_entries, *args, **kwargs):
+        """Writes the yaml input entries."""
+        with open(self._filepath, "a") as file:
+            yaml.safe_dump(
+                [stream_entry.entry for stream_entry in stream_entries],
+                file,
+                allow_unicode=True,
+            )
+
 
 class AsyncWriter(BaseWriter):
     """Writes the entries asynchronously (celery task)."""
@@ -117,11 +160,19 @@ class AsyncWriter(BaseWriter):
 
         :param writer: writer to use.
         """
-        self._writer = writer
         super().__init__(*args, **kwargs)
+        self._writer = writer
 
     def write(self, stream_entry, *args, **kwargs):
         """Launches a celery task to write an entry."""
         write_entry.delay(self._writer, stream_entry.entry)
 
         return stream_entry
+
+    def write_many(self, stream_entries, *args, **kwargs):
+        """Launches a celery task to write an entry."""
+        write_many_entry.delay(
+            self._writer, [stream_entry.entry for stream_entry in stream_entries]
+        )
+
+        return stream_entries

invenio_vocabularies/services/custom_fields/subject.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 #
-# Copyright (C) 2024-2024 CERN.
+# Copyright (C) 2024 CERN.
 #
 # Invenio-RDM-Records is free software; you can redistribute it and/or modify
 # it under the terms of the MIT License; see LICENSE file for more details.

invenio_vocabularies/templates/semantic-ui/invenio_vocabularies/subjects.html

@@ -1,5 +1,5 @@
 {#
-  Copyright (C) 2024-2024 CERN.
+  Copyright (C) 2024 CERN.
 
   Invenio RDM Records is free software; you can redistribute it and/or modify
   it under the terms of the MIT License; see LICENSE file for more details.

{invenio_vocabularies-4.2.0.dist-info → invenio_vocabularies-4.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invenio-vocabularies
-Version: 4.2.0
+Version: 4.4.0
 Summary: "Invenio module for managing vocabularies."
 Home-page: https://github.com/inveniosoftware/invenio-vocabularies
 Author: CERN
@@ -15,6 +15,7 @@ Requires-Dist: invenio-records-resources <7.0.0,>=6.0.0
 Requires-Dist: invenio-administration <3.0.0,>=2.0.0
 Requires-Dist: lxml >=4.5.0
 Requires-Dist: PyYAML >=5.4.1
+Requires-Dist: regex >=2024.7.24
 Provides-Extra: elasticsearch7
 Requires-Dist: invenio-search[elasticsearch7] <3.0.0,>=2.1.0 ; extra == 'elasticsearch7'
 Provides-Extra: mysql
@@ -25,6 +26,8 @@ Requires-Dist: invenio-search[opensearch1] <3.0.0,>=2.1.0 ; extra == 'opensearch
 Provides-Extra: opensearch2
 Requires-Dist: invenio-search[opensearch2] <3.0.0,>=2.1.0 ; extra == 'opensearch2'
 Provides-Extra: postgresql
+Provides-Extra: s3fs
+Requires-Dist: s3fs >=2024.6.1 ; extra == 's3fs'
 Provides-Extra: sqlite
 Provides-Extra: tests
 Requires-Dist: pytest-black-ng >=0.4.0 ; extra == 'tests'
@@ -78,6 +81,16 @@ https://invenio-vocabularies.readthedocs.io/
 Changes
 =======
 
+Version v4.4.0 (released 2024-08-09)
+
+- services: use and adjust vnd.inveniordm.v1+json http accept header
+
+Version v4.3.0 (released 2024-08-05)
+
+- names: make names_exclude_regex configurable
+- names: validate entry full names
+- names: add orcid public data sync
+
 Version v4.2.0 (released 2024-07-24)
 
 - ror: check last update; use ld+json for metadata (#367)

{invenio_vocabularies-4.2.0.dist-info → invenio_vocabularies-4.4.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
-invenio_vocabularies/__init__.py,sha256=fOsOa6766lKWONOkvvx15eYhnKovuRiq9tWwrXh_5HI,377
-invenio_vocabularies/cli.py,sha256=0PpQttop3lTXxM29IpY70MXFFPhb9apbiutdb7WDBvw,5356
-invenio_vocabularies/config.py,sha256=f3J658yL7E0ShFN99Jq2q1b5AJF1lDeiDyzijDmh8qA,4497
+invenio_vocabularies/__init__.py,sha256=scEcGFp9kWsXCw3wlDVG1nWWpWSVo6szcsMw-T-RcjY,377
+invenio_vocabularies/cli.py,sha256=ToGc5dcGarDwNUgUXGqHIRT-3Uv1rleyFLKenwZdyBw,5719
+invenio_vocabularies/config.py,sha256=hhlwenD5MDajCqmz2EmS7J5hVd2QPD2v5l_MjxM_56s,5011
 invenio_vocabularies/ext.py,sha256=GujJ4UARd4Fxf4z7zznRk9JAgHamZuYCOdrKU5czg00,5987
 invenio_vocabularies/factories.py,sha256=JBvvhg5f47Cy9cJZ1-OBalh750ErycwstLj1e9Gn4W8,2903
 invenio_vocabularies/fixtures.py,sha256=nNWwH04HFASjfj1oy5kMdcQGKmVjzUuA5wSw-ER1QAg,1585
@@ -43,10 +43,10 @@ invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/script
 invenio_vocabularies/assets/semantic-ui/translations/invenio_vocabularies/scripts/initCatalog.js,sha256=ghTi5iOIhT8AJoFGlxnBrHWiw2ts21dKwY_vWxmkiCE,682
 invenio_vocabularies/contrib/__init__.py,sha256=C5eDia6tAVBCrbb5hd_KnxmczyBoF87NIBUCLID-Tzc,240
 invenio_vocabularies/contrib/affiliations/__init__.py,sha256=rV8YAzBRoSKsBYcVjCNJh6j7ITuPRfurwj9HJHRjkN8,565
-invenio_vocabularies/contrib/affiliations/affiliations.py,sha256=Ph0z7bT_tudsWDKFaiksCBngsG-eO6Xpbe3KdejfLXI,1591
+invenio_vocabularies/contrib/affiliations/affiliations.py,sha256=PCWBF9O7ba2yU3LftEt5pxJf14S-HymqnN4GqKhp-Mc,2027
 invenio_vocabularies/contrib/affiliations/api.py,sha256=5nIOvpfcseuAAg2XgblHc8jb7TAdfU79XOBRpL-p398,326
 invenio_vocabularies/contrib/affiliations/config.py,sha256=u1sHeihy0B0e6w5e3HsbrC9e8A4WTLKCYPXUdcX-ZTs,1605
-invenio_vocabularies/contrib/affiliations/datastreams.py,sha256=oojLIh9jCE8zr0dj8KFepxPqsOn2SBSXQsX8L3XwFxs,2383
+invenio_vocabularies/contrib/affiliations/datastreams.py,sha256=Mn62EBBkGwO09qjrXY71qDIrS2mNgarb89ez69Vw4Yk,2384
 invenio_vocabularies/contrib/affiliations/facets.py,sha256=w316MGvtdyTpRCPOpCEmMxxLraRkbFFb1VvLkFlEc9o,1229
 invenio_vocabularies/contrib/affiliations/models.py,sha256=JUcj-1ydc2Cw2Rsc24JwXE3TFBJ_6fivhUYhGq4rT8A,329
 invenio_vocabularies/contrib/affiliations/resources.py,sha256=DBEbRxQmp-o-PeZlgFG588Q4sGcruuwIL8L9O-SzCes,435
@@ -86,7 +86,7 @@ invenio_vocabularies/contrib/common/ror/datastreams.py,sha256=joEiJwYawEaUggOZAQ
 invenio_vocabularies/contrib/funders/__init__.py,sha256=YxFXBDnT7NM8rFwxT_Ge3xXR2n17EM0alknQq7r_Bt8,478
 invenio_vocabularies/contrib/funders/api.py,sha256=QKGGeSnPHSoBfucvpaVruXT_txYidofZ080G3IxFkIo,306
 invenio_vocabularies/contrib/funders/config.py,sha256=BbzCRIcPxSwDllhjnGmdec5A126Zs1I4ZyVUCGi3jRA,1756
-invenio_vocabularies/contrib/funders/datastreams.py,sha256=G3UBT_kXei08zAKD44oaeERbkCVkJ9q9pFUoXpk3yiQ,2480
+invenio_vocabularies/contrib/funders/datastreams.py,sha256=3tOwcN1mK5AVqtdU6KdguouGSUurPTO-FDWTKzK1eRo,2481
 invenio_vocabularies/contrib/funders/facets.py,sha256=a068TVtt74Ncu0latb177LFK8EdnpbMOWecAKozA04M,1245
 invenio_vocabularies/contrib/funders/funders.py,sha256=KtUydQzQZPKtT1YMbBSIRcGc2eBmdkk5Zqavo54zK1E,2298
 invenio_vocabularies/contrib/funders/models.py,sha256=RAU-_YVOUNVCn03_XGJ2czcVwXTaZPk5w7X_bMAgMOk,314
@@ -106,10 +106,11 @@ invenio_vocabularies/contrib/funders/mappings/v7/funders/funder-v1.0.0.json,sha2
 invenio_vocabularies/contrib/names/__init__.py,sha256=DBfsM7JMETZGaV5QmXEwE7zhCaAXvc2SZN6uXnW_V-c,451
 invenio_vocabularies/contrib/names/api.py,sha256=sEPn_jFX3gyoxgbdEUSIvOoPCUI8pocI6qCZO6mzCgQ,300
 invenio_vocabularies/contrib/names/config.py,sha256=hKDTEEBYGYOY6sMOArZjjkq2HJ6MJtRZp1geGLAFgRg,1735
-invenio_vocabularies/contrib/names/datastreams.py,sha256=iyXhm5dYOjjx5oTqkso1ymRnJWyjG3MsGb-j2Dfc5KY,3663
+invenio_vocabularies/contrib/names/datastreams.py,sha256=PgCUwK0qpw_r0NTA17w7eqCDhgL2xd0tIXZ9-GjOT2M,9301
 invenio_vocabularies/contrib/names/models.py,sha256=SYdtDDG-y5Wq_d06YhiVO5n8gfxPW_mx-tECsIcv5H8,308
-invenio_vocabularies/contrib/names/names.py,sha256=fRNZW3yTmIE3FBB8zAcTdt1CXH6O8p6Ggz_7k9e8QTk,1987
+invenio_vocabularies/contrib/names/names.py,sha256=NlCyc2n7vUSGN8vA5PmgkNk8GpSF9v7OjBSBhRSQjYI,2423
 invenio_vocabularies/contrib/names/resources.py,sha256=Z8XqLKfFKE69zdTTvcTDmpEZ6wqiqjIH5tp0LzXTSwQ,1588
+invenio_vocabularies/contrib/names/s3client.py,sha256=c7B9_NbnXCfE4pE_yMTsT6uQ2hgbcRU-KY6nbWFuFzU,1063
 invenio_vocabularies/contrib/names/schema.py,sha256=eKhpNwBaACMEY0JWNrSUhr-40lXhkiHDRmM42KsLrYg,3354
 invenio_vocabularies/contrib/names/services.py,sha256=1viM-L8VEojmQWMisIOhDyl8KInPPCZEIf6tU8G07As,1763
 invenio_vocabularies/contrib/names/jsonschemas/__init__.py,sha256=pdDZdyoxqWbAQ6ngiclhYoDUsGKgRDRPXlIDy0U5Jzg,241
@@ -129,7 +130,7 @@ invenio_vocabularies/contrib/subjects/models.py,sha256=8XgbVRxDDvhWPjMWsoCriNlOK
 invenio_vocabularies/contrib/subjects/resources.py,sha256=0KRfUMizwgIziZybk4HnIjiSsXbrCv_XmguNPwnxoo8,506
 invenio_vocabularies/contrib/subjects/schema.py,sha256=jWPhpCDoScf8fRs7T15kcXnprWw31OuGBKJUziQ3t8A,1120
 invenio_vocabularies/contrib/subjects/services.py,sha256=s1U6HMmpjuz7rrgR0DtT9C28TC6sZEeDTsa4Jh1TXQk,864
-invenio_vocabularies/contrib/subjects/subjects.py,sha256=y5IidPbmYV3zs5aEp7CFzijYoVwWZ5GIMwl1kD0e0Eg,1441
+invenio_vocabularies/contrib/subjects/subjects.py,sha256=NwZycExLyV8l7ikGStH4GOecVuDSxFT70KoNv6qC78I,1877
 invenio_vocabularies/contrib/subjects/jsonschemas/__init__.py,sha256=WowVUST1JoEDS3-xeHhCJvIgC9nzMkFs8XRks9zgzaM,292
 invenio_vocabularies/contrib/subjects/jsonschemas/subjects/subject-v1.0.0.json,sha256=jlKAY_0oZH2zMlK8F4oNI2Xbq0ENYhHrM_w5nM9d0Fc,914
 invenio_vocabularies/contrib/subjects/mappings/__init__.py,sha256=Qk-yj1ENsTmijO8ImWuDYGzXi6QQ2VjP4DbjrpRfDk8,243
@@ -140,13 +141,13 @@ invenio_vocabularies/contrib/subjects/mappings/os-v2/subjects/subject-v1.0.0.jso
 invenio_vocabularies/contrib/subjects/mappings/v7/__init__.py,sha256=QK__a1749g2UN3fBqOr9jx8ccZHWAuvd6DSN4B1jJW4,258
 invenio_vocabularies/contrib/subjects/mappings/v7/subjects/subject-v1.0.0.json,sha256=Gr2dnAiqKgOISW2zhv4RZsssIGQPBNtPpgSu_ysHGDs,1166
 invenio_vocabularies/datastreams/__init__.py,sha256=VPefh6k4Q3eYxKIW8I5zXUGucntp7VHxaOR5Vhgkfmg,412
-invenio_vocabularies/datastreams/datastreams.py,sha256=_jSXv2yAvSjt8btMoLJlqXOkqBzYb3Xe9m2GH50Nwag,3987
+invenio_vocabularies/datastreams/datastreams.py,sha256=SpI6ivmf2LIDS2JSkxoM2v5kRmrPoRDtAG5fuzZO4oQ,6078
 invenio_vocabularies/datastreams/errors.py,sha256=IDUZ3gNtYGrhcOgApHCms1gNNJTyJzoMPmG5JtIeYNU,678
 invenio_vocabularies/datastreams/factories.py,sha256=H8a2gAy7KNImtdCdtqpVKC5gIvE3ON6U1Wn1_zaMlQ4,2181
-invenio_vocabularies/datastreams/readers.py,sha256=9WypPQFGWEIKcrra6oC8yxdGzVG3utd3CtrGx-AUxLM,10834
-invenio_vocabularies/datastreams/tasks.py,sha256=V3bm8ebdaB1tkrZWR1DuCscxSzP-O5maZecPkOF3Dyw,694
+invenio_vocabularies/datastreams/readers.py,sha256=JT76oKeD1N2u-0zWlyI7GZ5tR1aGc9IZe7pdTtNaSaM,11038
+invenio_vocabularies/datastreams/tasks.py,sha256=0fuH_PRt9Ncv6WHM4pkYmfheRVGDKkERZiMPvgV4bZU,1129
 invenio_vocabularies/datastreams/transformers.py,sha256=wspny-kazYMRHjkkyFfRVNIYzJxbjAqokRCBQ_-gXcY,1357
-invenio_vocabularies/datastreams/writers.py,sha256=UkrPOKyAOu8SsNyxBgdxYelCtPcBab6kbaIw-swVxlw,4153
+invenio_vocabularies/datastreams/writers.py,sha256=gFJ-NVbpIuR2aw4v5TyxR5roS-qVnETyqEVY1o8rYKk,6059
 invenio_vocabularies/datastreams/xml.py,sha256=HFa-lfxj7kFrr2IjeN1jxSLDfcvpBwO9nZLZF2-BryE,997
 invenio_vocabularies/records/__init__.py,sha256=Uj7O6fYdAtLOkLXUGSAYPADBB7aqP4yVs9b6OAjA158,243
 invenio_vocabularies/records/api.py,sha256=Lynt6Sz4BVN1orh0zgJ5ljhnUobEtcq8c22PmSeUo2U,1494
@@ -181,9 +182,9 @@ invenio_vocabularies/services/schema.py,sha256=mwIBFylpQlWw1M6h_axc-z4Yd7X3Z1S0P
 invenio_vocabularies/services/service.py,sha256=rUPeb86Jv2WXzRp-RZDHLWsouCmJcqHpCmgrpLm2Vs4,6387
 invenio_vocabularies/services/tasks.py,sha256=AH0XifkOypsEdh8LyjmlHnPLQK5qqUJC8cNVWGkbqks,788
 invenio_vocabularies/services/custom_fields/__init__.py,sha256=QgvSsn-S1xLzbZ57pjjGTt5oI3HqzXHVjwGTtuPgzN8,421
-invenio_vocabularies/services/custom_fields/subject.py,sha256=TrtmRgk3Vj_NxmDhC_7sM8MAIje4AGXBxYIk7nIgt0o,2236
+invenio_vocabularies/services/custom_fields/subject.py,sha256=ZM-ZkaxoouF9lL62smOtLxsjQQZwiQs0jG3qGruP6nY,2231
 invenio_vocabularies/services/custom_fields/vocabulary.py,sha256=oQwI8Aoi2Nr9k3eWKnde5H7RXc7qdlATSeI6coy8UR0,3020
-invenio_vocabularies/templates/semantic-ui/invenio_vocabularies/subjects.html,sha256=h9syHkwZ6ltgjWw_0M5UoR6h6Re2imJ7uQ6M6peOyhk,686
+invenio_vocabularies/templates/semantic-ui/invenio_vocabularies/subjects.html,sha256=Fr8xRfKYiytuTfbtH7gfasNXwFIcjPFnXV4F5oGNUkM,681
 invenio_vocabularies/templates/semantic-ui/invenio_vocabularies/vocabularies-list.html,sha256=-gDwRctqIkSzh9ial8zfbA4o41ARM-Mq-THkcJ87U00,359
 invenio_vocabularies/templates/semantic-ui/invenio_vocabularies/vocabulary-details.html,sha256=2dfQzRFl5RwUwle245sxWGnObwJQXr-e_bBzpe_PkkA,2684
 invenio_vocabularies/translations/messages.pot,sha256=IzTTWdWknzmKKtl1UNUxPOwHjfBB_iidm_eeEY2kV-M,3907
@@ -281,10 +282,10 @@ invenio_vocabularies/translations/zh_CN/LC_MESSAGES/messages.mo,sha256=g1I5aNO8r
 invenio_vocabularies/translations/zh_CN/LC_MESSAGES/messages.po,sha256=vg8qC8ofpAdJ3mQz7mWM1ylKDpiNWXFs7rlMdSPkgKk,4629
 invenio_vocabularies/translations/zh_TW/LC_MESSAGES/messages.mo,sha256=cqSm8NtMAwrP9O6qbmtkDtRT1e9D93qpsJN5X9_PPVw,600
 invenio_vocabularies/translations/zh_TW/LC_MESSAGES/messages.po,sha256=9ACePz_EpB-LfcIJajZ2kp8Q04tcdrQLOtug162ZUss,4115
-invenio_vocabularies-4.2.0.dist-info/AUTHORS.rst,sha256=8d0p_WWE1r9DavvzMDi2D4YIGBHiMYcN3LYxqQOj8sY,291
-invenio_vocabularies-4.2.0.dist-info/LICENSE,sha256=UvI8pR8jGWqe0sTkb_hRG6eIrozzWwWzyCGEpuXX4KE,1062
-invenio_vocabularies-4.2.0.dist-info/METADATA,sha256=2pdaEFZ5Z35PmaNmdeuq-TDu0P1X8KCeyUhZh6NvW-0,8167
-invenio_vocabularies-4.2.0.dist-info/WHEEL,sha256=-G_t0oGuE7UD0DrSpVZnq1hHMBV9DD2XkS5v7XpmTnk,110
-invenio_vocabularies-4.2.0.dist-info/entry_points.txt,sha256=qHHFkyU3r0COsKm5gCYuhP8tfsioBggxKAiEXNAbbjM,2803
-invenio_vocabularies-4.2.0.dist-info/top_level.txt,sha256=x1gRNbaODF_bCD0SBLM3nVOFPGi06cmGX5X94WKrFKk,21
-invenio_vocabularies-4.2.0.dist-info/RECORD,,
+invenio_vocabularies-4.4.0.dist-info/AUTHORS.rst,sha256=8d0p_WWE1r9DavvzMDi2D4YIGBHiMYcN3LYxqQOj8sY,291
+invenio_vocabularies-4.4.0.dist-info/LICENSE,sha256=UvI8pR8jGWqe0sTkb_hRG6eIrozzWwWzyCGEpuXX4KE,1062
+invenio_vocabularies-4.4.0.dist-info/METADATA,sha256=hYz0Gy3C37wuawLdd36nJ9_RZiS130E4bhKN8tlZa9E,8535
+invenio_vocabularies-4.4.0.dist-info/WHEEL,sha256=-G_t0oGuE7UD0DrSpVZnq1hHMBV9DD2XkS5v7XpmTnk,110
+invenio_vocabularies-4.4.0.dist-info/entry_points.txt,sha256=qHHFkyU3r0COsKm5gCYuhP8tfsioBggxKAiEXNAbbjM,2803
+invenio_vocabularies-4.4.0.dist-info/top_level.txt,sha256=x1gRNbaODF_bCD0SBLM3nVOFPGi06cmGX5X94WKrFKk,21
+invenio_vocabularies-4.4.0.dist-info/RECORD,,