mirror of
https://github.com/NVIDIA-NeMo/DataDesigner
synced 2026-05-24 09:48:29 +00:00
ae0665fa16
* remove old structure * major shuffle * streamline project configs * update make commands * updates to make commands * remove essentials * initialize logger in interface * uv lock * ignore notepad * update workflows * fix e2e project config * generate colab notebooks * resolve default model settings in interface * fix build commands * update perf import make command * cleaning up some slop * update recipes * move conftest files to tests/ * update subpackage readmes * streamline config_logging * use exports * update perf import usage pattern * update for IDE behavior with ruff * remove engine's fixtures file * add note to about lazy imports * update dependencies * update docs * doc fixes * uv lock * updates to catch up with main * clean up makefile * remove package gitignores * define deps only once * isolate tests * add test for protetion rule * create temp dirs for isolated tests * catch up to main * update headers * re apply changes * better result summaries for isolated tests * move exports into top-level init * fix client importlib version syntax * catch up with main
56 lines
2.1 KiB
Python
56 lines
2.1 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
from unittest.mock import MagicMock
|
|
|
|
from data_designer.config.dataset_metadata import DatasetMetadata
|
|
from data_designer.engine.resources.resource_provider import ResourceProvider
|
|
from data_designer.engine.resources.seed_reader import SeedReader
|
|
|
|
|
|
def test_dataset_metadata_defaults() -> None:
|
|
"""Test DatasetMetadata default values."""
|
|
metadata = DatasetMetadata()
|
|
assert metadata.seed_column_names == []
|
|
|
|
|
|
def test_dataset_metadata_with_seed_columns() -> None:
|
|
"""Test DatasetMetadata with seed column names."""
|
|
metadata = DatasetMetadata(seed_column_names=["name", "age", "city"])
|
|
assert metadata.seed_column_names == ["name", "age", "city"]
|
|
|
|
|
|
def test_get_dataset_metadata_with_seed_reader() -> None:
|
|
"""Test creating DatasetMetadata from ResourceProvider with seed reader."""
|
|
seed_reader = MagicMock(spec=SeedReader)
|
|
seed_reader.get_column_names.return_value = ["col1", "col2"]
|
|
|
|
resource_provider = MagicMock(spec=ResourceProvider)
|
|
resource_provider.seed_reader = seed_reader
|
|
|
|
metadata = ResourceProvider.get_dataset_metadata(resource_provider)
|
|
|
|
assert metadata.seed_column_names == ["col1", "col2"]
|
|
seed_reader.get_column_names.assert_called_once()
|
|
|
|
|
|
def test_get_dataset_metadata_without_seed_reader() -> None:
|
|
"""Test creating DatasetMetadata from ResourceProvider without seed reader."""
|
|
resource_provider = MagicMock(spec=ResourceProvider)
|
|
resource_provider.seed_reader = None
|
|
|
|
metadata = ResourceProvider.get_dataset_metadata(resource_provider)
|
|
|
|
assert metadata.seed_column_names == []
|
|
|
|
|
|
def test_dataset_metadata_is_serializable() -> None:
|
|
"""Test that DatasetMetadata can be serialized to JSON."""
|
|
metadata = DatasetMetadata(seed_column_names=["name", "age"])
|
|
|
|
json_data = metadata.model_dump_json()
|
|
assert '"seed_column_names":["name","age"]' in json_data
|
|
|
|
# Can be deserialized back
|
|
restored = DatasetMetadata.model_validate_json(json_data)
|
|
assert restored.seed_column_names == ["name", "age"]
|