arkindex-base-worker 0.4.0rc3__py3-none-any.whl → 0.4.0rc5__py3-none-any.whl

tests/test_elements_worker/{test_entities.py → test_entity_create.py}

@@ -13,8 +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.entity import MissingEntityType
 from arkindex_worker.worker.transcription import TextOrientation
 from tests import CORPUS_ID
 
@@ -686,158 +684,6 @@ def test_create_transcription_entity_with_confidence_with_cache(
     ]
 
 
-def test_list_transcription_entities_deprecation(fake_dummy_worker):
-    transcription = Transcription({"id": "fake_transcription_id"})
-    worker_version = "worker_version_id"
-    fake_dummy_worker.api_client.add_response(
-        "ListTranscriptionEntities",
-        id=transcription.id,
-        worker_version=worker_version,
-        response={"id": "entity_id"},
-    )
-    with pytest.deprecated_call(
-        match="`worker_version` usage is deprecated. Consider using `worker_run` instead."
-    ):
-        assert fake_dummy_worker.list_transcription_entities(
-            transcription, worker_version=worker_version
-        ) == {"id": "entity_id"}
-
-    assert len(fake_dummy_worker.api_client.history) == 1
-    assert len(fake_dummy_worker.api_client.responses) == 0
-
-
-def test_list_transcription_entities(fake_dummy_worker):
-    transcription = Transcription({"id": "fake_transcription_id"})
-    worker_run = "worker_run_id"
-    fake_dummy_worker.api_client.add_response(
-        "ListTranscriptionEntities",
-        id=transcription.id,
-        worker_run=worker_run,
-        response={"id": "entity_id"},
-    )
-    assert fake_dummy_worker.list_transcription_entities(
-        transcription, worker_run=worker_run
-    ) == {"id": "entity_id"}
-
-    assert len(fake_dummy_worker.api_client.history) == 1
-    assert len(fake_dummy_worker.api_client.responses) == 0
-
-
-def test_list_corpus_entities(responses, mock_elements_worker):
-    responses.add(
-        responses.GET,
-        f"http://testserver/api/v1/corpus/{CORPUS_ID}/entities/",
-        json={
-            "count": 1,
-            "next": None,
-            "results": [
-                {
-                    "id": "fake_entity_id",
-                }
-            ],
-        },
-    )
-
-    mock_elements_worker.list_corpus_entities()
-
-    assert mock_elements_worker.entities == {
-        "fake_entity_id": {
-            "id": "fake_entity_id",
-        }
-    }
-
-    assert len(responses.calls) == len(BASE_API_CALLS) + 1
-    assert [
-        (call.request.method, call.request.url) for call in responses.calls
-    ] == BASE_API_CALLS + [
-        (
-            "GET",
-            f"http://testserver/api/v1/corpus/{CORPUS_ID}/entities/",
-        ),
-    ]
-
-
-@pytest.mark.parametrize("wrong_name", [1234, 12.5])
-def test_list_corpus_entities_wrong_name(mock_elements_worker, wrong_name):
-    with pytest.raises(AssertionError, match="name should be of type str"):
-        mock_elements_worker.list_corpus_entities(name=wrong_name)
-
-
-@pytest.mark.parametrize("wrong_parent", [{"id": "element_id"}, 12.5, "blabla"])
-def test_list_corpus_entities_wrong_parent(mock_elements_worker, wrong_parent):
-    with pytest.raises(AssertionError, match="parent should be of type Element"):
-        mock_elements_worker.list_corpus_entities(parent=wrong_parent)
-
-
-def test_check_required_entity_types(responses, mock_elements_worker):
-    # Set one entity type
-    mock_elements_worker.entity_types = {"person": "person-entity-type-id"}
-
-    checked_types = ["person", "new-entity"]
-
-    # Call to create new entity type
-    responses.add(
-        responses.POST,
-        "http://testserver/api/v1/entity/types/",
-        status=200,
-        match=[
-            matchers.json_params_matcher(
-                {
-                    "name": "new-entity",
-                    "corpus": CORPUS_ID,
-                }
-            )
-        ],
-        json={
-            "id": "new-entity-id",
-            "corpus": CORPUS_ID,
-            "name": "new-entity",
-            "color": "ffd1b3",
-        },
-    )
-
-    mock_elements_worker.check_required_entity_types(
-        entity_types=checked_types,
-    )
-
-    # Make sure the entity_types entry has been updated
-    assert mock_elements_worker.entity_types == {
-        "person": "person-entity-type-id",
-        "new-entity": "new-entity-id",
-    }
-
-    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/entity/types/",
-        ),
-    ]
-
-
-def test_check_required_entity_types_no_creation_allowed(
-    responses, mock_elements_worker
-):
-    # Set one entity type
-    mock_elements_worker.entity_types = {"person": "person-entity-type-id"}
-
-    checked_types = ["person", "new-entity"]
-
-    with pytest.raises(
-        MissingEntityType, match="Entity type `new-entity` was not in the corpus."
-    ):
-        mock_elements_worker.check_required_entity_types(
-            entity_types=checked_types, create_missing=False
-        )
-
-    assert len(responses.calls) == len(BASE_API_CALLS)
-    assert [
-        (call.request.method, call.request.url) for call in responses.calls
-    ] == BASE_API_CALLS
-
-
 @pytest.mark.parametrize("transcription", [None, "not a transcription", 1])
 def test_create_transcription_entities_wrong_transcription(
     mock_elements_worker, transcription
@@ -989,89 +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 = {
@@ -1095,26 +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

tests/test_elements_worker/test_entity_list_and_check.py

@@ -0,0 +1,160 @@
+import pytest
+from responses import matchers
+
+from arkindex_worker.models import Transcription
+from arkindex_worker.worker.entity import MissingEntityType
+from tests import CORPUS_ID
+
+from . import BASE_API_CALLS
+
+
+def test_check_required_entity_types(responses, mock_elements_worker):
+    # Set one entity type
+    mock_elements_worker.entity_types = {"person": "person-entity-type-id"}
+
+    checked_types = ["person", "new-entity"]
+
+    # Call to create new entity type
+    responses.add(
+        responses.POST,
+        "http://testserver/api/v1/entity/types/",
+        status=200,
+        match=[
+            matchers.json_params_matcher(
+                {
+                    "name": "new-entity",
+                    "corpus": CORPUS_ID,
+                }
+            )
+        ],
+        json={
+            "id": "new-entity-id",
+            "corpus": CORPUS_ID,
+            "name": "new-entity",
+            "color": "ffd1b3",
+        },
+    )
+
+    mock_elements_worker.check_required_entity_types(
+        entity_types=checked_types,
+    )
+
+    # Make sure the entity_types entry has been updated
+    assert mock_elements_worker.entity_types == {
+        "person": "person-entity-type-id",
+        "new-entity": "new-entity-id",
+    }
+
+    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/entity/types/",
+        ),
+    ]
+
+
+def test_check_required_entity_types_no_creation_allowed(
+    responses, mock_elements_worker
+):
+    # Set one entity type
+    mock_elements_worker.entity_types = {"person": "person-entity-type-id"}
+
+    checked_types = ["person", "new-entity"]
+
+    with pytest.raises(
+        MissingEntityType, match="Entity type `new-entity` was not in the corpus."
+    ):
+        mock_elements_worker.check_required_entity_types(
+            entity_types=checked_types, create_missing=False
+        )
+
+    assert len(responses.calls) == len(BASE_API_CALLS)
+    assert [
+        (call.request.method, call.request.url) for call in responses.calls
+    ] == BASE_API_CALLS
+
+
+def test_list_transcription_entities_deprecation(fake_dummy_worker):
+    transcription = Transcription({"id": "fake_transcription_id"})
+    worker_version = "worker_version_id"
+    fake_dummy_worker.api_client.add_response(
+        "ListTranscriptionEntities",
+        id=transcription.id,
+        worker_version=worker_version,
+        response={"id": "entity_id"},
+    )
+    with pytest.deprecated_call(
+        match="`worker_version` usage is deprecated. Consider using `worker_run` instead."
+    ):
+        assert fake_dummy_worker.list_transcription_entities(
+            transcription, worker_version=worker_version
+        ) == {"id": "entity_id"}
+
+    assert len(fake_dummy_worker.api_client.history) == 1
+    assert len(fake_dummy_worker.api_client.responses) == 0
+
+
+def test_list_transcription_entities(fake_dummy_worker):
+    transcription = Transcription({"id": "fake_transcription_id"})
+    worker_run = "worker_run_id"
+    fake_dummy_worker.api_client.add_response(
+        "ListTranscriptionEntities",
+        id=transcription.id,
+        worker_run=worker_run,
+        response={"id": "entity_id"},
+    )
+    assert fake_dummy_worker.list_transcription_entities(
+        transcription, worker_run=worker_run
+    ) == {"id": "entity_id"}
+
+    assert len(fake_dummy_worker.api_client.history) == 1
+    assert len(fake_dummy_worker.api_client.responses) == 0
+
+
+def test_list_corpus_entities(responses, mock_elements_worker):
+    responses.add(
+        responses.GET,
+        f"http://testserver/api/v1/corpus/{CORPUS_ID}/entities/",
+        json={
+            "count": 1,
+            "next": None,
+            "results": [
+                {
+                    "id": "fake_entity_id",
+                }
+            ],
+        },
+    )
+
+    mock_elements_worker.list_corpus_entities()
+
+    assert mock_elements_worker.entities == {
+        "fake_entity_id": {
+            "id": "fake_entity_id",
+        }
+    }
+
+    assert len(responses.calls) == len(BASE_API_CALLS) + 1
+    assert [
+        (call.request.method, call.request.url) for call in responses.calls
+    ] == BASE_API_CALLS + [
+        (
+            "GET",
+            f"http://testserver/api/v1/corpus/{CORPUS_ID}/entities/",
+        ),
+    ]
+
+
+@pytest.mark.parametrize("wrong_name", [1234, 12.5])
+def test_list_corpus_entities_wrong_name(mock_elements_worker, wrong_name):
+    with pytest.raises(AssertionError, match="name should be of type str"):
+        mock_elements_worker.list_corpus_entities(name=wrong_name)
+
+
+@pytest.mark.parametrize("wrong_parent", [{"id": "element_id"}, 12.5, "blabla"])
+def test_list_corpus_entities_wrong_parent(mock_elements_worker, wrong_parent):
+    with pytest.raises(AssertionError, match="parent should be of type Element"):
+        mock_elements_worker.list_corpus_entities(parent=wrong_parent)