arkindex-base-worker 0.4.0rc4__tar.gz → 0.4.0rc5__tar.gz

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: arkindex-base-worker
-Version: 0.4.0rc4
+Version: 0.4.0rc5
 Summary: Base Worker to easily build Arkindex ML workflows
 Author-email: Teklia <contact@teklia.com>
 Maintainer-email: Teklia <contact@teklia.com>

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/arkindex_base_worker.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: arkindex-base-worker
-Version: 0.4.0rc4
+Version: 0.4.0rc5
 Summary: Base Worker to easily build Arkindex ML workflows
 Author-email: Teklia <contact@teklia.com>
 Maintainer-email: Teklia <contact@teklia.com>

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/arkindex_worker/worker/__init__.py

@@ -133,8 +133,12 @@ class ElementsWorker(
         Whether or not WorkerActivity support has been enabled on the DataImport
         used to run this worker.
         """
-        if self.is_read_only or self.process_mode == ProcessMode.Dataset:
-            # Worker activities are also disabled when running an ElementsWorker in a Dataset process.
+        if self.is_read_only or self.process_mode in [
+            ProcessMode.Dataset,
+            ProcessMode.Export,
+        ]:
+            # Worker activities are also disabled when running an ElementsWorker in a Dataset process
+            # and when running export processes.
             return False
         assert (
             self.process_information

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/arkindex_worker/worker/entity.py

@@ -16,9 +16,6 @@ from arkindex_worker.cache import (
 )
 from arkindex_worker.models import Element, Transcription
 from arkindex_worker.utils import (
-    DEFAULT_BATCH_SIZE,
-    batch_publication,
-    make_batches,
     pluralize,
 )
 
@@ -219,12 +216,10 @@ class EntityMixin:
         return transcription_ent
 
     @unsupported_cache
-    @batch_publication
     def create_transcription_entities(
         self,
         transcription: Transcription,
         entities: list[Entity],
-        batch_size: int = DEFAULT_BATCH_SIZE,
     ) -> list[dict[str, str]]:
         """
         Create multiple entities attached to a transcription in a single API request.
@@ -247,8 +242,6 @@ class EntityMixin:
             confidence (float or None)
                 Optional confidence score, between 0.0 and 1.0.
 
-        :param batch_size: The size of each batch, which will be used to split the publication to avoid API errors.
-
         :return: List of dicts, with each dict having a two keys, `transcription_entity_id` and `entity_id`, holding the UUID of each created object.
         """
         assert transcription and isinstance(
@@ -300,18 +293,14 @@ class EntityMixin:
             )
             return
 
-        created_entities = [
-            created_entity
-            for batch in make_batches(entities, "entity", batch_size)
-            for created_entity in self.api_client.request(
-                "CreateTranscriptionEntities",
-                id=transcription.id,
-                body={
-                    "worker_run_id": self.worker_run_id,
-                    "entities": batch,
-                },
-            )["entities"]
-        ]
+        created_entities = self.api_client.request(
+            "CreateTranscriptionEntities",
+            id=transcription.id,
+            body={
+                "worker_run_id": self.worker_run_id,
+                "entities": entities,
+            },
+        )["entities"]
 
         return created_entities
 

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/arkindex_worker/worker/process.py

@@ -61,3 +61,8 @@ class ProcessMode(Enum):
     """
     Dataset processes.
     """
+
+    Export = "export"
+    """
+    Export processes.
+    """

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "arkindex-base-worker"
-version = "0.4.0rc4"
+version = "0.4.0rc5"
 description = "Base Worker to easily build Arkindex ML workflows"
 license = { file = "LICENSE" }
 dependencies = [

{arkindex_base_worker-0.4.0rc4 → arkindex_base_worker-0.4.0rc5}/tests/test_elements_worker/test_entity_create.py

@@ -13,7 +13,6 @@ from arkindex_worker.cache import (
     CachedTranscriptionEntity,
 )
 from arkindex_worker.models import Transcription
-from arkindex_worker.utils import DEFAULT_BATCH_SIZE
 from arkindex_worker.worker.transcription import TextOrientation
 from tests import CORPUS_ID
 
@@ -836,89 +835,50 @@ def test_create_transcription_entities_wrong_entity(
         )
 
 
-@pytest.mark.parametrize("batch_size", [DEFAULT_BATCH_SIZE, 1])
-def test_create_transcription_entities(batch_size, responses, mock_elements_worker):
+def test_create_transcription_entities(responses, mock_elements_worker):
     transcription = Transcription(id="transcription-id")
 
     # Call to Transcription entities creation in bulk
-    if batch_size > 1:
-        responses.add(
-            responses.POST,
-            "http://testserver/api/v1/transcription/transcription-id/entities/bulk/",
-            status=201,
-            match=[
-                matchers.json_params_matcher(
-                    {
-                        "worker_run_id": "56785678-5678-5678-5678-567856785678",
-                        "entities": [
-                            {
-                                "name": "Teklia",
-                                "type_id": "22222222-2222-2222-2222-222222222222",
-                                "offset": 0,
-                                "length": 6,
-                                "confidence": 1.0,
-                            },
-                            {
-                                "name": "Team Rocket",
-                                "type_id": "22222222-2222-2222-2222-222222222222",
-                                "offset": 7,
-                                "length": 11,
-                                "confidence": 1.0,
-                            },
-                        ],
-                    }
-                )
-            ],
-            json={
-                "entities": [
-                    {
-                        "transcription_entity_id": "transc-entity-id",
-                        "entity_id": "entity-id1",
-                    },
-                    {
-                        "transcription_entity_id": "transc-entity-id",
-                        "entity_id": "entity-id2",
-                    },
-                ]
-            },
-        )
-    else:
-        for idx, (name, offset, length) in enumerate(
-            [
-                ("Teklia", 0, 6),
-                ("Team Rocket", 7, 11),
-            ],
-            start=1,
-        ):
-            responses.add(
-                responses.POST,
-                "http://testserver/api/v1/transcription/transcription-id/entities/bulk/",
-                status=201,
-                match=[
-                    matchers.json_params_matcher(
-                        {
-                            "worker_run_id": "56785678-5678-5678-5678-567856785678",
-                            "entities": [
-                                {
-                                    "name": name,
-                                    "type_id": "22222222-2222-2222-2222-222222222222",
-                                    "offset": offset,
-                                    "length": length,
-                                    "confidence": 1.0,
-                                }
-                            ],
-                        }
-                    )
-                ],
-                json={
+    responses.add(
+        responses.POST,
+        "http://testserver/api/v1/transcription/transcription-id/entities/bulk/",
+        status=201,
+        match=[
+            matchers.json_params_matcher(
+                {
+                    "worker_run_id": "56785678-5678-5678-5678-567856785678",
                     "entities": [
                         {
-                            "transcription_entity_id": "transc-entity-id",
-                            "entity_id": f"entity-id{idx}",
-                        }
-                    ]
-                },
+                            "name": "Teklia",
+                            "type_id": "22222222-2222-2222-2222-222222222222",
+                            "offset": 0,
+                            "length": 6,
+                            "confidence": 1.0,
+                        },
+                        {
+                            "name": "Team Rocket",
+                            "type_id": "22222222-2222-2222-2222-222222222222",
+                            "offset": 7,
+                            "length": 11,
+                            "confidence": 1.0,
+                        },
+                    ],
+                }
             )
+        ],
+        json={
+            "entities": [
+                {
+                    "transcription_entity_id": "transc-entity-id",
+                    "entity_id": "entity-id1",
+                },
+                {
+                    "transcription_entity_id": "transc-entity-id",
+                    "entity_id": "entity-id2",
+                },
+            ]
+        },
+    )
 
     # Store entity type/slug correspondence on the worker
     mock_elements_worker.entity_types = {
@@ -942,26 +902,16 @@ def test_create_transcription_entities(batch_size, responses, mock_elements_work
                 "confidence": 1.0,
             },
         ],
-        batch_size=batch_size,
     )
 
     assert len(created_objects) == 2
 
-    bulk_api_calls = [
+    assert len(responses.calls) == len(BASE_API_CALLS) + 1
+    assert [
+        (call.request.method, call.request.url) for call in responses.calls
+    ] == BASE_API_CALLS + [
         (
             "POST",
             "http://testserver/api/v1/transcription/transcription-id/entities/bulk/",
         )
     ]
-    if batch_size != DEFAULT_BATCH_SIZE:
-        bulk_api_calls.append(
-            (
-                "POST",
-                "http://testserver/api/v1/transcription/transcription-id/entities/bulk/",
-            )
-        )
-
-    assert len(responses.calls) == len(BASE_API_CALLS) + len(bulk_api_calls)
-    assert [
-        (call.request.method, call.request.url) for call in responses.calls
-    ] == BASE_API_CALLS + bulk_api_calls