[PLT-1611] Vb/placeholder datarows (#1851)

Author: vbrodsky

libs/labelbox/src/labelbox/schema/dataset.py

@@ -1,57 +1,43 @@
-from datetime import datetime
-from typing import Dict, Generator, List, Optional, Any, Final, Tuple, Union
-import os
 import json
 import logging
-from collections.abc import Iterable
-from string import Template
-import time
+import os
 import warnings
-
-from labelbox import parser
-from itertools import islice
-
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from io import StringIO
-import requests
+from itertools import islice
+from string import Template
+from typing import Any, Dict, List, Optional, Tuple, Union
 
+import labelbox.schema.internal.data_row_uploader as data_row_uploader
 from labelbox.exceptions import (
     InvalidQueryError,
     LabelboxError,
-    ResourceNotFoundError,
     ResourceCreationError,
+    ResourceNotFoundError,
 )
+from labelbox.orm import query
 from labelbox.orm.comparison import Comparison
-from labelbox.orm.db_object import DbObject, Updateable, Deletable, experimental
+from labelbox.orm.db_object import DbObject, Deletable, Updateable
 from labelbox.orm.model import Entity, Field, Relationship
-from labelbox.orm import query
-from labelbox.exceptions import MalformedQueryException
 from labelbox.pagination import PaginatedCollection
 from labelbox.schema.data_row import DataRow
-from labelbox.schema.embedding import EmbeddingVector
 from labelbox.schema.export_filters import DatasetExportFilters, build_filters
 from labelbox.schema.export_params import (
     CatalogExportParams,
     validate_catalog_export_params,
 )
 from labelbox.schema.export_task import ExportTask
-from labelbox.schema.identifiable import UniqueId, GlobalKey
-from labelbox.schema.task import Task, DataUpsertTask
-from labelbox.schema.user import User
 from labelbox.schema.iam_integration import IAMIntegration
+from labelbox.schema.identifiable import GlobalKey, UniqueId
 from labelbox.schema.internal.data_row_upsert_item import (
+    DataRowCreateItem,
     DataRowItemBase,
     DataRowUpsertItem,
-    DataRowCreateItem,
-)
-import labelbox.schema.internal.data_row_uploader as data_row_uploader
-from labelbox.schema.internal.descriptor_file_creator import (
-    DescriptorFileCreator,
 )
 from labelbox.schema.internal.datarow_upload_constants import (
     FILE_UPLOAD_THREAD_COUNT,
     UPSERT_CHUNK_SIZE_BYTES,
 )
+from labelbox.schema.task import DataUpsertTask, Task
 
 logger = logging.getLogger(__name__)
 
@@ -359,7 +345,7 @@ def data_row_for_external_id(self, external_id) -> "DataRow":
         )
         if len(data_rows) > 1:
             logger.warning(
-                f"More than one data_row has the provided external_id : `%s`. Use function data_rows_for_external_id to fetch all",
+                "More than one data_row has the provided external_id : `%s`. Use function data_rows_for_external_id to fetch all",
                 external_id,
             )
         return data_rows[0]

libs/labelbox/tests/integration/conftest.py

@@ -1,42 +1,53 @@
-from collections import defaultdict
-from itertools import islice
-import json
 import os
 import sys
-import re
 import time
-import uuid
-import requests
-from types import SimpleNamespace
-from typing import Type, List
-from enum import Enum
-from typing import Tuple
+from collections import defaultdict
+from datetime import datetime, timezone
+from itertools import islice
+from typing import Type
 
 import pytest
-import requests
 
-from labelbox import Dataset, DataRow
-from labelbox import LabelingFrontend
 from labelbox import (
-    OntologyBuilder,
-    Tool,
-    Option,
     Classification,
+    Client,
+    Dataset,
+    LabelingFrontend,
     MediaType,
+    OntologyBuilder,
+    Option,
     PromptResponseClassification,
     ResponseOption,
+    Tool,
 )
-from labelbox.orm import query
-from labelbox.pagination import PaginatedCollection
-from labelbox.schema.annotation_import import LabelImport
-from labelbox.schema.catalog import Catalog
-from labelbox.schema.enums import AnnotationImportState
-from labelbox.schema.invite import Invite
-from labelbox.schema.quality_mode import QualityMode
+from labelbox.schema.data_row import DataRowMetadataField
+from labelbox.schema.ontology_kind import OntologyKind
 from labelbox.schema.queue_mode import QueueMode
 from labelbox.schema.user import User
-from labelbox import Client
-from labelbox.schema.ontology_kind import OntologyKind
+
+
+@pytest.fixture
+def constants():
+    SPLIT_SCHEMA_ID = "cko8sbczn0002h2dkdaxb5kal"
+    TEST_SPLIT_ID = "cko8scbz70005h2dkastwhgqt"
+    TEXT_SCHEMA_ID = "cko8s9r5v0001h2dk9elqdidh"
+    CAPTURE_DT_SCHEMA_ID = "cko8sdzv70006h2dk8jg64zvb"
+    EXPECTED_METADATA_SCHEMA_IDS = [
+        SPLIT_SCHEMA_ID,
+        TEST_SPLIT_ID,
+        TEXT_SCHEMA_ID,
+        CAPTURE_DT_SCHEMA_ID,
+    ]
+    CUSTOM_TEXT_SCHEMA_NAME = "custom_text"
+
+    return {
+        "SPLIT_SCHEMA_ID": SPLIT_SCHEMA_ID,
+        "TEST_SPLIT_ID": TEST_SPLIT_ID,
+        "TEXT_SCHEMA_ID": TEXT_SCHEMA_ID,
+        "CAPTURE_DT_SCHEMA_ID": CAPTURE_DT_SCHEMA_ID,
+        "EXPECTED_METADATA_SCHEMA_IDS": EXPECTED_METADATA_SCHEMA_IDS,
+        "CUSTOM_TEXT_SCHEMA_NAME": CUSTOM_TEXT_SCHEMA_NAME,
+    }
 
 
 @pytest.fixture
@@ -835,3 +846,21 @@ def print_perf_summary():
             for aaa in islice(sorted_dict, num_of_entries)
         ]
         print("\nTop slowest fixtures:\n", slowest_fixtures, file=sys.stderr)
+
+
+@pytest.fixture
+def make_metadata_fields(constants):
+    msg = "A message"
+    time = datetime.now(timezone.utc)
+
+    fields = [
+        DataRowMetadataField(
+            schema_id=constants["SPLIT_SCHEMA_ID"],
+            value=constants["TEST_SPLIT_ID"],
+        ),
+        DataRowMetadataField(
+            schema_id=constants["CAPTURE_DT_SCHEMA_ID"], value=time
+        ),
+        DataRowMetadataField(schema_id=constants["TEXT_SCHEMA_ID"], value=msg),
+    ]
+    return fields