builtin -> default; move adding plugins to registry

Author: johnnygreco

src/data_designer/engine/analysis/column_profilers/registry.py

@@ -14,7 +14,7 @@
 class ColumnProfilerRegistry(TaskRegistry[ColumnProfilerType, ColumnProfiler, ConfigBase]): ...
 
 
-def create_builtin_column_profiler_registry() -> ColumnProfilerRegistry:
+def create_default_column_profiler_registry() -> ColumnProfilerRegistry:
     registry = ColumnProfilerRegistry()
     registry.register(ColumnProfilerType.JUDGE_SCORE, JudgeScoreProfiler, JudgeScoreProfilerConfig, False)
     return registry

src/data_designer/engine/column_generators/registry.py

@@ -27,12 +27,14 @@
     SeedDatasetMultiColumnConfig,
 )
 from data_designer.engine.registry.base import TaskRegistry
+from data_designer.plugins.plugin import PluginType
+from data_designer.plugins.registry import PluginRegistry
 
 
 class ColumnGeneratorRegistry(TaskRegistry[DataDesignerColumnType, ColumnGenerator, ConfigBase]): ...
 
 
-def create_builtin_column_generator_registry() -> ColumnGeneratorRegistry:
+def create_default_column_generator_registry(with_plugins: bool = True) -> ColumnGeneratorRegistry:
     registry = ColumnGeneratorRegistry()
     registry.register(DataDesignerColumnType.LLM_TEXT, LLMTextCellGenerator, LLMTextColumnConfig)
     registry.register(DataDesignerColumnType.LLM_CODE, LLMCodeCellGenerator, LLMCodeColumnConfig)
@@ -42,4 +44,13 @@ def create_builtin_column_generator_registry() -> ColumnGeneratorRegistry:
     registry.register(DataDesignerColumnType.SEED_DATASET, SeedDatasetColumnGenerator, SeedDatasetMultiColumnConfig)
     registry.register(DataDesignerColumnType.VALIDATION, ValidationColumnGenerator, ValidationColumnConfig)
     registry.register(DataDesignerColumnType.LLM_STRUCTURED, LLMStructuredCellGenerator, LLMStructuredColumnConfig)
+
+    if with_plugins:
+        for plugin in PluginRegistry().get_plugins(PluginType.COLUMN_GENERATOR):
+            registry.register(
+                DataDesignerColumnType(plugin.name),
+                plugin.task_cls,
+                plugin.config_cls,
+            )
+
     return registry

src/data_designer/engine/processing/processors/registry.py

@@ -14,7 +14,7 @@
 class ProcessorRegistry(TaskRegistry[str, Processor, ConfigBase]): ...
 
 
-def create_builtin_processor_registry() -> ProcessorRegistry:
+def create_default_processor_registry() -> ProcessorRegistry:
     registry = ProcessorRegistry()
     registry.register(ProcessorType.DROP_COLUMNS, DropColumnsProcessor, DropColumnsProcessorConfig, False)
     return registry

src/data_designer/engine/registry/data_designer_registry.py

@@ -1,18 +1,15 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from data_designer.config.column_types import DataDesignerColumnType
 from data_designer.engine.analysis.column_profilers.registry import (
     ColumnProfilerRegistry,
-    create_builtin_column_profiler_registry,
+    create_default_column_profiler_registry,
 )
 from data_designer.engine.column_generators.registry import (
     ColumnGeneratorRegistry,
-    create_builtin_column_generator_registry,
+    create_default_column_generator_registry,
 )
-from data_designer.engine.processing.processors.registry import ProcessorRegistry, create_builtin_processor_registry
-from data_designer.plugins.plugin import PluginType
-from data_designer.plugins.registry import PluginRegistry
+from data_designer.engine.processing.processors.registry import ProcessorRegistry, create_default_processor_registry
 
 
 class DataDesignerRegistry:
@@ -23,16 +20,9 @@ def __init__(
         column_profiler_registry: ColumnProfilerRegistry | None = None,
         processor_registry: ProcessorRegistry | None = None,
     ):
-        self._column_generator_registry = column_generator_registry or create_builtin_column_generator_registry()
-        self._column_profiler_registry = column_profiler_registry or create_builtin_column_profiler_registry()
-        self._processor_registry = processor_registry or create_builtin_processor_registry()
-
-        for plugin in PluginRegistry().get_plugins(PluginType.COLUMN_GENERATOR):
-            self._column_generator_registry.register(
-                DataDesignerColumnType(plugin.name),
-                plugin.task_cls,
-                plugin.config_cls,
-            )
+        self._column_generator_registry = column_generator_registry or create_default_column_generator_registry()
+        self._column_profiler_registry = column_profiler_registry or create_default_column_profiler_registry()
+        self._processor_registry = processor_registry or create_default_processor_registry()
 
     @property
     def column_generators(self) -> ColumnGeneratorRegistry:

tests/engine/analysis/test_errors.py

@@ -10,7 +10,7 @@
 )
 from data_designer.engine.analysis.column_profilers.registry import (
     ColumnProfilerRegistry,
-    create_builtin_column_profiler_registry,
+    create_default_column_profiler_registry,
 )
 from data_designer.engine.registry.errors import NotFoundInRegistryError
 
@@ -52,7 +52,7 @@ def test_get_nonexistent_profiler():
 
 
 def test_create_default_registry():
-    registry = create_builtin_column_profiler_registry()
+    registry = create_default_column_profiler_registry()
 
     assert isinstance(registry, ColumnProfilerRegistry)
     assert ColumnProfilerType.JUDGE_SCORE in ColumnProfilerRegistry._registry

tests/engine/column_generators/test_registry.py

@@ -14,12 +14,12 @@
 from data_designer.engine.column_generators.generators.validation import ValidationColumnGenerator
 from data_designer.engine.column_generators.registry import (
     ColumnGeneratorRegistry,
-    create_builtin_column_generator_registry,
+    create_default_column_generator_registry,
 )
 
 
 def test_column_generator_registry_create_default_registry_with_generators():
-    registry = create_builtin_column_generator_registry()
+    registry = create_default_column_generator_registry()
 
     assert isinstance(registry, ColumnGeneratorRegistry)
 

tests/engine/processing/processors/test_registry.py

@@ -5,12 +5,12 @@
 from data_designer.engine.processing.processors.drop_columns import DropColumnsProcessor
 from data_designer.engine.processing.processors.registry import (
     ProcessorRegistry,
-    create_builtin_processor_registry,
+    create_default_processor_registry,
 )
 
 
 def test_create_default_processor_registry():
-    registry = create_builtin_processor_registry()
+    registry = create_default_processor_registry()
 
     assert isinstance(registry, ProcessorRegistry)
     assert ProcessorType.DROP_COLUMNS in ProcessorRegistry._registry

tests/engine/registry/test_data_designer_registry.py

@@ -21,10 +21,10 @@ def stub_column_profiler_registry():
 @pytest.fixture
 def stub_default_registries():
     with patch(
-        "data_designer.engine.registry.data_designer_registry.create_builtin_column_generator_registry"
+        "data_designer.engine.registry.data_designer_registry.create_default_column_generator_registry"
     ) as mock_gen:
         with patch(
-            "data_designer.engine.registry.data_designer_registry.create_builtin_column_profiler_registry"
+            "data_designer.engine.registry.data_designer_registry.create_default_column_profiler_registry"
         ) as mock_prof:
             mock_gen_registry = Mock()
             mock_prof_registry = Mock()