CHANGELOG.md

@@ -1,3 +1,15 @@
+# 4.4.0 (2025-10-07)
+
+## New features
+
+- Record submission time in stored records.
+
+- Add configuration option for submitter ID-class and the submitter time-class.
+
+- Improve configuration validation. Configurations with unknown keys are now
+  rejected.
+
+
 # 4.3.1 (2025-10-06)
 
 ## Bugfixes

README.md

@@ -439,6 +439,142 @@ A Forgejo authentication source can authenticate Forgejo-tokens that have at lea
 - Repository (only if `repository` is set in the configuration): required to determine a team's access to the repository.
 
 
+#### Submission annotation tag
+
+The service annotates submitted records with a submitter id and a timestamp.
+Annotations consist of an annotation tag, defining the class of the annotation, and an annotation value.
+By default the service will use the class `http://purl.obolibrary.org/obo/NCIT_C54269` for the submitter id and the class `http://semanticscience.org/resource/SIO_001083` for submission time.
+(Both tags will be converted into CURIEs if the schema of the collection defines an appropriate prefix.)
+
+The default annotation tag classes can be overridden in the configuration on a per collection basis.
+To override the defaults tags, add a `submission_tags`-attribute to a collection definition.
+The `submission_tags`-attribute should contain a mapping that maps either `submitter_id_tag`, or `submitter_time_tag` or both to an IRI or a CURIE.
+If the schema defines a matching prefix, IRIs are automatically converted to CURIEs before storing the record.
+The service validates that the prefix of a CURIE is defined in the schema of the collection.
+
+```yaml
+type: collections
+version: 1
+collections:
+  collection_1:
+    default_token: basic_access
+    curated: curated
+    incoming: contributions
+    submission_tags:
+      submitter_id_tag: schema:user_id
+      submission_time_tag: schema:time
+
+  ...
+
+```
+
+The service currently supports the following backends for storing records:
+- `record_dir`: this backend stores records as YAML-files in a directory structure that is defined [here](https://concepts.datalad.org/dump-things-storage-v0/). It reads the backend configuration from a "record collection configuration file" as described [here](https://concepts.datalad.org/dump-things-storage-v0/).
+
+- `sqlite`: this backend stores records in a SQLite database. There is an individual database file, named `__sqlite-records.db`, for each curated area and incoming area.
+
+- `record_dir+stl`: here `stl` stands for "schema-type-layer".
+  This backend stores records in the same format as `record_dir`, but adds special treatment for the `schema_type` attribute in records.
+  It removes `schema_type`-attributes from the top-level mapping of a record before storing it as YAML-file. When records are read from this backend, a `schema_type` attribute is added back into the record, using a schema to determine the correct class-URI.
+  In other words, all records stored with this backend will have no `schema_type`-attribute in the top-level, and all records read with this backend will have a `schema_type` attribute in the top-level.
+
+- `sqlite+stl`: This backend stores records in the same format as `sqlite`, but adds the same special treatment for the `schema_type` attribute as `record_dir+stl`.
+
+Backends can be defined per collection in the configuration file.
+The backend will be used for the curated area and for the incoming areas of the collection.
+If no backend is defined for a collection, the `record_dir+stl`-backend is used by default.
+The `+stl`-backends can be useful if an endpoint returns records of multiple classes, because it allows clients to determine the class of each result record.
+
+The service guarantees that backends of all types can co-exist independently in the same directory, i.e., there are no name collisions in files that are used for different backends (as long as no class name starts with `.` or `_`)).
+
+The following configuration snippet shows how to define a backend for a collection:
+
+```yaml
+...
+collections:
+  collection_with_default_record_dir+stl_backend:
+    # This is a collection with the default backend, i.e. `record_dir+stl` and
+    # the default authentication, i.e. config-based authentication.
+    default_token: anon_read
+    curated: collection_1/curated
+
+  collection_with_forgejo_authentication_source:
+    # This is a collection with the default backend, i.e. `record_dir+stl` and
+    # a forgejo-based authentication source. That means it will use a forgejo
+    # instance to determine the permissions of a token for this collection.
+    # The instance is also used to determine the user-id and the incoming label.
+    # In the case of forgejo, the user-id and the incoming label are the
+    # forgejo login associated with the token.
+
+    # We still need the name of a default token. If the token is defined in this
+    # config file, its properties will be determined by the
+    # config file. If the token is not defined in the config file, its
+    # properties will be determined by the authentication sources. In this
+    # example by the forgejo-instance at `https://forgejo.example.com`.
+    # If there is more than one authentication source, they will be tried
+    # in the order they are defined in the config file.
+    default_token: anon_read    # We still need a default token
+    curated: collection_2/curated
+
+    # Token permissions, user-ids (for record annotations), and incoming
+    # label can be determined by multiple authentication sources.
+    # If no source is defined, `config` will be used, which reads token
+    # information from the config file.
+    # This example explicitly defines `config` and a second authentication
+    # source, a `forgejo` authentication source.
+    auth_sources:
+      - type: forgejo   # requires `user`-read and `organization`-read permissions on token
+        # The API-URL of the forgejo instance that should be used
+        url: https://forgejo.example.com/api/v1
+        # An organization
+        organization: data_handling
+        # A team in the organization. The authorization of the team
+        # determines the permissions of the token
+        team: data_entry_personal
+        # `label_type` determines how an incoming label is created for
+        # a Forgejo token. If `label_type` is `team`, the incoming label
+        # will be `forgejo-team-<organization>-<team>`. If `label_type`
+        # is `user`, the incoming label will be 
+        # `forgejo-user-<user-login>`
+        label_type: team
+        # An optional repository. The token will only be authorized
+        # if the team has access to the repository. Note: if `repo`
+        # is set, the token must have at least repository read
+        # permissions.
+        repo: reference-repository
+
+      # Fallback to the config file.
+      - type: config    # check tokens from the configuration file
+
+      # Multiple authorization sources are allowed. They will be tried in the
+      # order defined in the config file. If an authorization source returns
+      # permissions for a token, those permissions will be used and no other
+      # authorization sources will be queried.
+      # The default authorization source is `config`, which reads the token 
+      # permissions, user-id, and incoming
+  
+  collection_with_explicit_record_dir+stl_backend:
+    default_token: anon_read
+    curated: collection_3/curated
+    backend:
+      # The record_dir-backend is identified by the
+      # type: "record_dir". No more attributes are
+      # defined for this backend.
+      type: record_dir+stl
+
+  collection_with_sqlite_backend:
+    default_token: anon_read
+    curated: collection_4/curated
+    backend:
+      # The sqlite-backend is identified by the
+      # type: "sqlite". It requires a schema attribute
+      # that holds the URL of the schema that should
+      # be used in this backend.
+      type: sqlite
+      schema: https://concepts.inm7.de/s/flat-data/unreleased.yaml
+```
+
+
 ### Command line parameters:
 
 The service supports the following command line parameters:

dump_things_service/__about__.py

@@ -1 +1 @@
-__version__ = '4.3.1'
+__version__ = '4.4.0'

dump_things_service/config.py

@@ -17,6 +17,8 @@ import yaml
 from fastapi import HTTPException
 from pydantic import (
     BaseModel,
+    ConfigDict,
+    Field,
     ValidationError,
 )
 from yaml.scanner import ScannerError
@@ -29,8 +31,12 @@ from dump_things_service.backends.sqlite import (
     record_file_name as sqlite_record_file_name,
 )
 from dump_things_service.converter import get_conversion_objects
-from dump_things_service.exceptions import ConfigError
+from dump_things_service.exceptions import (
+    ConfigError,
+    CurieResolutionError,
+)
 from dump_things_service.model import get_model_for_schema
+from dump_things_service.resolve_curie import resolve_curie
 from dump_things_service.store.model_store import ModelStore
 from dump_things_service.token import (
     TokenPermission,
@@ -51,6 +57,10 @@ ignored_files = {'.', '..', config_file_name}
 _global_config_instance = None
 
 
+class StrictModel(BaseModel):
+    model_config = ConfigDict(extra='forbid')
+
+
 class MappingMethod(enum.Enum):
     digest_md5 = 'digest-md5'
     digest_md5_p3 = 'digest-md5-p3'
@@ -61,7 +71,7 @@ class MappingMethod(enum.Enum):
     after_last_colon = 'after-last-colon'
 
 
-class CollectionDirConfig(BaseModel):
+class CollectionDirConfig(StrictModel):
     type: Literal['records']
     version: Literal[1]
     schema: str
@@ -82,26 +92,27 @@ class TokenModes(enum.Enum):
 
 
 class TokenCollectionConfig(BaseModel):
+    model_config = ConfigDict(extra='forbid')
     mode: TokenModes
-    incoming_label: str
+    incoming_label: str = Field(strict=True)
 
 
-class TokenConfig(BaseModel):
+class TokenConfig(StrictModel):
     user_id: str
     collections: dict[str, TokenCollectionConfig]
     hashed: bool = False
 
 
-class BackendConfigRecordDir(BaseModel):
+class BackendConfigRecordDir(StrictModel):
     type: Literal['record_dir', 'record_dir+stl']
 
 
-class BackendConfigSQLite(BaseModel):
+class BackendConfigSQLite(StrictModel):
     type: Literal['sqlite', 'sqlite+stl']
     schema: str
 
 
-class ForgejoAuthConfig(BaseModel):
+class ForgejoAuthConfig(StrictModel):
     type: Literal['forgejo']
     url: str
     organization: str
@@ -110,19 +121,27 @@ class ForgejoAuthConfig(BaseModel):
     repository: str | None = None
 
 
-class ConfigAuthConfig(BaseModel):
+class ConfigAuthConfig(StrictModel):
     type: Literal['config'] = 'config'
 
 
-class CollectionConfig(BaseModel):
+class TagConfig(StrictModel):
+    submitter_id_tag: str = 'http://purl.obolibrary.org/obo/NCIT_C54269'
+    submission_time_tag: str = 'http://semanticscience.org/resource/SIO_001083'
+
+
+class CollectionConfig(StrictModel):
     default_token: str
     curated: Path
     incoming: Path | None = None
     backend: BackendConfigRecordDir | BackendConfigSQLite | None = None
     auth_sources: list[ForgejoAuthConfig | ConfigAuthConfig] = [ConfigAuthConfig()]
+    submission_tags: TagConfig = TagConfig()
 
 
-class GlobalConfig(BaseModel):
+class GlobalConfig(StrictModel):
+    model_config = ConfigDict(strict=True)
+
     type: Literal['collections']
     version: Literal[1]
     collections: dict[str, CollectionConfig]
@@ -399,6 +418,10 @@ def process_config_object(
         curated_store = ModelStore(
             schema=schema,
             backend=curated_store_backend,
+            tags={
+                'id': collection_info.submission_tags.submitter_id_tag,
+                'time': collection_info.submission_tags.submission_time_tag,
+            }
         )
 
         instance_config.curated_stores[collection_name] = curated_store
@@ -496,6 +519,14 @@ def process_config_object(
         msg = 'plain tokens clash with hashed tokens'
         raise ConfigError(msg)
 
+    # Check tags
+    for collection_name, collection_info in config_object.collections.items():
+        module = instance_config.model_info[collection_name][0]
+        try:
+            resolve_curie(module, collection_info.submission_tags.submission_time_tag)
+        except CurieResolutionError as e:
+            raise ConfigError(str(e)) from e
+
     return instance_config
 
 

dump_things_service/resolve_curie.py

@@ -17,21 +17,30 @@ url_regex = re.compile(url_pattern)
 
 def resolve_curie(
     model: types.ModuleType,
-    curie: str,
+    curie_or_iri: str,
 ) -> str:
-    if ':' not in curie:
+    if ':' not in curie_or_iri:
-        return curie
+        return curie_or_iri
 
-    if url_regex.match(curie):
+    if not is_curie(curie_or_iri):
-        return curie
+        return curie_or_iri
 
-    prefix, identifier = curie.split(':', 1)
+    prefix, identifier = curie_or_iri.split(':', 1)
     prefix_value = model.linkml_meta.root.get('prefixes', {}).get(prefix)
     if prefix_value is None:
         msg = (
-            f'cannot resolve CURIE "{curie}". No such prefix: "{prefix}" in '
+            f'cannot resolve CURIE "{curie_or_iri}". No such prefix: "{prefix}" in '
             f'schema: {model.linkml_meta.root["id"]}'
         )
         raise CurieResolutionError(msg)
 
     return prefix_value['prefix_reference'] + identifier
+
+
+def is_curie(
+    curie_or_iri: str,
+):
+    if ':' not in curie_or_iri:
+        return False
+
+    return url_regex.match(curie_or_iri) is None

dump_things_service/store/model_store.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from datetime import datetime
 from itertools import chain
 from typing import TYPE_CHECKING
 
@@ -7,7 +8,7 @@ from dump_things_service.model import (
     get_model_for_schema,
     get_subclasses,
 )
-from dump_things_service.resolve_curie import resolve_curie
+from dump_things_service.resolve_curie import resolve_curie, is_curie
 from dump_things_service.utils import cleaned_json
 
 if TYPE_CHECKING:
@@ -31,10 +32,12 @@ class _ModelStore:
         self,
         schema: str,
         backend: StorageBackend,
+        tags: dict[str, str]
     ):
         self.schema = schema
         self.model = get_model_for_schema(self.schema)[0]
         self.backend = backend
+        self.tags = tags
 
     def get_uri(self) -> str:
         return self.backend.get_uri()
@@ -95,25 +98,30 @@ class _ModelStore:
         submitter: str,
     ) -> None:
         """Add submitter IRI to the record annotations, use CURIE if possible"""
-        submitter_iri = self.get_curie(
-            submitter_namespace,
-            submitter_class,
-        )
         if 'annotations' not in json_object:
             json_object['annotations'] = {}
-        json_object['annotations'][submitter_iri] = submitter
+        submitter_curie_or_iri = self.get_curie(self.tags['id'])
+        time_curie_or_iri = self.get_curie(self.tags['time'])
+        json_object['annotations'][submitter_curie_or_iri] = submitter
+        json_object['annotations'][time_curie_or_iri] = datetime.now().isoformat()
 
     def get_curie(
         self,
-        name_space: str,
+        curie_or_iri: str,
-        class_name: str,
     ) -> str:
+        if is_curie(curie_or_iri):
+            return curie_or_iri
         prefixes = self.model.linkml_meta.root.get('prefixes')
         if prefixes:
             for prefix_info in prefixes.values():
-                if prefix_info['prefix_reference'] == name_space:
+                reference = prefix_info['prefix_reference']
-                    return f'{prefix_info["prefix_prefix"]}:{class_name}'
+                if curie_or_iri.startswith(reference):
-        return f'{name_space}{class_name}'
+                    return curie_or_iri.replace(
+                        reference,
+                        prefix_info['prefix_prefix'] + ':',
+                        1,
+                    )
+        return curie_or_iri
 
     def extract_inlined(
         self,
@@ -206,6 +214,7 @@ _existing_model_stores = {}
 def ModelStore(  # noqa: N802
     schema: str,
     backend: StorageBackend,
+    tags: dict[str, str],
 ) -> _ModelStore:
     """
     Create a unique model store for the given schema and backend.
@@ -216,7 +225,7 @@ def ModelStore(  # noqa: N802
     """
     existing_model_store, _ = _existing_model_stores.get(id(backend), (None, None))
     if not existing_model_store:
-        existing_model_store = _ModelStore(schema, backend)
+        existing_model_store = _ModelStore(schema, backend, tags)
         # We store a pointer to the backend in the value to ensure that the
         # backend object exists while we use its `id` as a key.
         _existing_model_stores[id(backend)] = existing_model_store, backend

dump_things_service/tests/fixtures.py

@@ -37,58 +37,47 @@ collections:
     incoming: {incoming}
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
     auth_sources:
       - type: config
+    submission_tags:
+      submitter_id_tag: oxo:NCIT_C54269
+      submission_time_tag: https://time
   collection_2:
     default_token: basic_access
     curated: {curated}/collection_2
     incoming: incoming_2
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
   collection_3:
     default_token: basic_access
     curated: {curated}/collection_3
     incoming: incoming_3
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
   collection_4:
     default_token: basic_access
     curated: {curated}/collection_4
     incoming: incoming_4
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
   collection_5:
     default_token: basic_access
     curated: {curated}/collection_5
     incoming: incoming_5
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
   collection_6:
     default_token: basic_access
     curated: {curated}/collection_6
     incoming: incoming_6
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
   collection_7:
     default_token: basic_access
     curated: {curated}/collection_7
     incoming: incoming_7
     backend:
       type: record_dir+stl
-      schema: {schema_path}
-      idfx: digest_md5
   collection_8:
     default_token: basic_access
     curated: {curated}/collection_8
@@ -102,8 +91,6 @@ collections:
     incoming: {incoming}/collection_dlflatsocial-1
     backend:
       type: record_dir+stl
-      schema: https://concepts.datalad.org/s/flat-social/unreleased.yaml
-      idfx: digest_md5
   collection_dlflatsocial-2:
     default_token: basic_access
     curated: {curated}/collection_dlflatsocial-2

dump_things_service/tests/test_config.py

@@ -8,7 +8,7 @@ from dump_things_service.config import (
     ConfigError,
     GlobalConfig,
     process_config,
-    process_config_object,
+    process_config_object, get_config,
 )
 
 
@@ -56,3 +56,133 @@ tokens:
     global_dict = {}
     with pytest.raises(ConfigError):
         process_config_object(tmp_path, config_object, [], global_dict)
+
+
+def test_submission_tags_handling(dump_stores_simple):
+    config_object = GlobalConfig(
+        **yaml.load(
+            """
+type: collections
+version: 1
+collections:
+  collection_1:
+    default_token: basic_access
+    curated: curated/in_token_1
+    incoming: contributions
+    submission_tags:
+      submitter_id_tag: no_default_id_tag
+      submission_time_tag: no_default_time_tag
+  collection_2:
+    default_token: basic_access
+    curated: curated/collection_2
+    incoming: contributions
+tokens:
+  basic_access:
+    user_id: anonymous
+    collections:
+      collection_1:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+      collection_2:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+    """,
+            Loader=yaml.SafeLoader,
+        )
+    )
+
+    global_dict = {}
+    config = process_config_object(dump_stores_simple, config_object, [], global_dict)
+    # Check for specified tags in collection `collection_1`
+    assert config.collections['collection_1'].submission_tags.submission_time_tag == 'no_default_time_tag'
+    assert config.collections['collection_1'].submission_tags.submitter_id_tag == 'no_default_id_tag'
+    # Check for default tags in collection `collection_2`
+    assert config.collections['collection_2'].submission_tags.submission_time_tag == 'http://semanticscience.org/resource/SIO_001083'
+    assert config.collections['collection_2'].submission_tags.submitter_id_tag == 'http://purl.obolibrary.org/obo/NCIT_C54269'
+
+
+def test_submission_tags_resolving(dump_stores_simple):
+    config_object = GlobalConfig(
+        **yaml.load(
+            """
+type: collections
+version: 1
+collections:
+  collection_1:
+    default_token: basic_access
+    curated: curated/in_token_1
+    incoming: contributions
+    submission_tags:
+      submitter_id_tag: abc:id
+      submission_time_tag: abc:time
+tokens:
+  basic_access:
+    user_id: anonymous
+    collections:
+      collection_1:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+    """,
+            Loader=yaml.SafeLoader,
+        )
+    )
+
+    global_dict = {}
+    process_config_object(dump_stores_simple, config_object, [], global_dict)
+
+
+def test_submission_tags_resolving_error(dump_stores_simple):
+    config_object = GlobalConfig(
+        **yaml.load(
+            """
+type: collections
+version: 1
+collections:
+  collection_1:
+    default_token: basic_access
+    curated: curated/in_token_1
+    incoming: contributions
+    submission_tags:
+      submitter_id_tag: non-existing:id
+  collection_2:
+    default_token: basic_access
+    curated: curated/in_token_1
+    incoming: contributions
+    submission_tags:
+      submission_time_tag: non-existing:time
+  collection_3:
+    default_token: basic_access
+    curated: curated/in_token_1
+    incoming: contributions
+    submission_tags:
+      submitter_id_tag: http://something/non-existing
+  collection_4:
+    default_token: basic_access
+    curated: curated/in_token_1
+    incoming: contributions
+    submission_tags:
+      submission_time_tag: http://something/non-existing
+tokens:
+  basic_access:
+    user_id: anonymous
+    collections:
+      collection_1:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+      collection_2:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+      collection_3:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+      collection_4:
+        mode: WRITE_COLLECTION
+        incoming_label: incoming_anonymous
+    """,
+            Loader=yaml.SafeLoader,
+        )
+    )
+
+    global_dict = {}
+    with pytest.raises(ConfigError) as e:
+        process_config_object(dump_stores_simple, config_object, [], global_dict)

dump_things_service/tests/test_extract_inline.py

@@ -165,6 +165,10 @@ def test_inline_extraction_locally():
     store = ModelStore(
         schema=str(schema_path),
         backend=None,
+        tags = {
+            'id': 'abc:id',
+            'time': 'abc:time',
+        }
     )
     store.model = MockedModule()
     records = store.extract_inlined(inlined_object)
@@ -193,6 +197,10 @@ def test_dont_extract_empty_things_locally():
     store = ModelStore(
         schema=str(schema_path),
         backend=None,
+        tags={
+            'id': 'https://id',
+            'time': 'https://time',
+        }
     )
     store.model = MockedModule()
     records = store.extract_inlined(empty_inlined_object)

dump_things_service/tests/test_roundtrip.py

@@ -1,3 +1,4 @@
+import freezegun
 import pytest  # noqa F401
 
 from .. import HTTP_200_OK
@@ -19,14 +20,32 @@ xyz:HenryAdams a abc:Person ;
     abc:schema_type "abc:Person" .
 """
 
-ttl_result_record = """@prefix abc: <http://example.org/person-schema/abc/> .
+ttl_result_record_a = """@prefix abc: <http://example.org/person-schema/abc/> .
+@prefix oxo: <http://purl.obolibrary.org/obo/> .
+@prefix xyz: <http://example.org/person-schema/xyz/> .
+
+xyz:HenryAdams a abc:Person ;
+    abc:annotations [ a abc:Annotation ;
+            abc:annotation_tag <https://time> ;
+            abc:annotation_value "1970-01-01T00:00:00" ],
+        [ a abc:Annotation ;
+            abc:annotation_tag oxo:NCIT_C54269 ;
+            abc:annotation_value "test_user_1" ] ;
+    abc:given_name "Henryöäß" ;
+    abc:schema_type "abc:Person" .
+"""
+
+ttl_result_record_b = """@prefix abc: <http://example.org/person-schema/abc/> .
 @prefix oxo: <http://purl.obolibrary.org/obo/> .
 @prefix xyz: <http://example.org/person-schema/xyz/> .
 
 xyz:HenryAdams a abc:Person ;
     abc:annotations [ a abc:Annotation ;
             abc:annotation_tag oxo:NCIT_C54269 ;
-            abc:annotation_value "test_user_1" ] ;
+            abc:annotation_value "test_user_1" ],
+        [ a abc:Annotation ;
+            abc:annotation_tag <https://time> ;
+            abc:annotation_value "1970-01-01T00:00:00" ] ;
     abc:given_name "Henryöäß" ;
     abc:schema_type "abc:Person" .
 """
@@ -75,6 +94,7 @@ def test_json_ttl_json(fastapi_client_simple):
     assert json_object == json_record_out
 
 
+@freezegun.freeze_time('1970-01-01')
 def test_ttl_json_ttl(fastapi_client_simple):
     test_client, _ = fastapi_client_simple
 
@@ -115,5 +135,8 @@ def test_ttl_json_ttl(fastapi_client_simple):
     assert response.status_code == HTTP_200_OK
     assert (
         response.text.strip()
-        == ttl_result_record.replace('xyz:HenryAdams', new_json_pid).strip()
+        == ttl_result_record_a.replace('xyz:HenryAdams', new_json_pid).strip()
+    ) or (
+        response.text.strip()
+        == ttl_result_record_b.replace('xyz:HenryAdams', new_json_pid).strip()
     )

dump_things_service/tests/test_roundtrip_flatsocial.py

@@ -1,5 +1,10 @@
+import datetime
+from datetime import datetime as datetime_object
+
 import pytest  # noqa F401
 
+import freezegun
+
 from .. import HTTP_200_OK
 from ..utils import cleaned_json
 
@@ -33,7 +38,22 @@ dlflatsocial:test_john_ttl a dlflatsocial:Person ;
     dlsocialmx:given_name "Johnöüß" .
 """
 
-ttl_output_record = """@prefix dlflatsocial: <https://concepts.datalad.org/s/flat-social/unreleased/> .
+ttl_output_record_a = """@prefix dlflatsocial: <https://concepts.datalad.org/s/flat-social/unreleased/> .
+@prefix dlsocialmx: <https://concepts.datalad.org/s/social-mixin/unreleased/> .
+@prefix dlthings: <https://concepts.datalad.org/s/things/v1/> .
+@prefix obo: <http://purl.obolibrary.org/obo/> .
+
+dlflatsocial:test_john_ttl a dlflatsocial:Person ;
+    dlsocialmx:given_name "Johnöüß" ;
+    dlthings:annotations [ a dlthings:Annotation ;
+            dlthings:annotation_tag <http://semanticscience.org/resource/SIO_001083> ;
+            dlthings:annotation_value "1970-01-01T00:00:00" ],
+        [ a dlthings:Annotation ;
+            dlthings:annotation_tag obo:NCIT_C54269 ;
+            dlthings:annotation_value "test_user_1" ] .
+"""
+
+ttl_output_record_b = """@prefix dlflatsocial: <https://concepts.datalad.org/s/flat-social/unreleased/> .
 @prefix dlsocialmx: <https://concepts.datalad.org/s/social-mixin/unreleased/> .
 @prefix dlthings: <https://concepts.datalad.org/s/things/v1/> .
 @prefix obo: <http://purl.obolibrary.org/obo/> .
@@ -42,7 +62,10 @@ dlflatsocial:test_john_ttl a dlflatsocial:Person ;
     dlsocialmx:given_name "Johnöüß" ;
     dlthings:annotations [ a dlthings:Annotation ;
             dlthings:annotation_tag obo:NCIT_C54269 ;
-            dlthings:annotation_value "test_user_1" ] .
+            dlthings:annotation_value "test_user_1" ],
+        [ a dlthings:Annotation ;
+            dlthings:annotation_tag <http://semanticscience.org/resource/SIO_001083> ;
+            dlthings:annotation_value "1970-01-01T00:00:00" ] .
 """
 
 new_json_pid = 'dlflatsocial:another_john_ttl'
@@ -90,6 +113,7 @@ def test_json_ttl_json_dlflatsocial(fastapi_client_simple):
         assert json_object == json_record_out
 
 
+@freezegun.freeze_time('1970-01-01')
 def test_ttl_json_ttl_dlflatsocial(fastapi_client_simple):
     test_client, _ = fastapi_client_simple
 
@@ -131,5 +155,8 @@ def test_ttl_json_ttl_dlflatsocial(fastapi_client_simple):
         assert response.status_code == HTTP_200_OK
         assert (
             response.text.strip()
-            == ttl_output_record.replace('dlflatsocial:test_john_ttl', new_json_pid).strip()
+            == ttl_output_record_a.replace('dlflatsocial:test_john_ttl', new_json_pid).strip()
+        ) or (
+            response.text.strip()
+            == ttl_output_record_b.replace('dlflatsocial:test_john_ttl', new_json_pid).strip()
         )

dump_things_service/utils.py

@@ -385,7 +385,12 @@ def create_token_store(
     if extension == 'stl':
         token_store = SchemaTypeLayer(backend=token_store, schema=schema_uri)
 
-    model_store = ModelStore(backend=token_store, schema=schema_uri)
+    submission_tags = instance_config.collections[collection_name].submission_tags
+    tags = {
+        'id': submission_tags.submitter_id_tag,
+        'time': submission_tags.submission_time_tag,
+    }
+    model_store = ModelStore(backend=token_store, schema=schema_uri, tags=tags)
     instance_config.all_stores[store_dir] = (collection_name, model_store)
 
     return model_store

pyproject.toml

@@ -102,6 +102,7 @@ run = "python -m dump_things_service.main {args}"
 default-args = ["dump_things_service"]
 extra-dependencies = [
     "dump_things_service",
+    "freezegun",
     "httpx",
     "pytest",
     "pytest-cov",