feat(gooddata-pipelines): make workspace data filter fields optional

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: benkeanna

packages/gooddata-pipelines/src/gooddata_pipelines/ldm_extension/input_processor.py

@@ -253,6 +253,34 @@ def datasets_to_ldm(
             # Get the data source info
             dataset_source_table_id, dataset_sql = self._get_sources(dataset)
 
+            # Workspace data filter fields are optional and must be set together
+            # (validated on the input model). Emit columns/references only when
+            # both are provided.
+            wdf_columns: list[CatalogDeclarativeWorkspaceDataFilterColumn] = []
+            wdf_references: list[
+                CatalogDeclarativeWorkspaceDataFilterReferences
+            ] = []
+            if (
+                dataset.definition.workspace_data_filter_id is not None
+                and dataset.definition.workspace_data_filter_column_name
+                is not None
+            ):
+                wdf_columns.append(
+                    CatalogDeclarativeWorkspaceDataFilterColumn(
+                        name=dataset.definition.workspace_data_filter_column_name,
+                        data_type=ColumnDataType.STRING.value,
+                    )
+                )
+                wdf_references.append(
+                    CatalogDeclarativeWorkspaceDataFilterReferences(
+                        filter_id=CatalogDatasetWorkspaceDataFilterIdentifier(
+                            id=dataset.definition.workspace_data_filter_id
+                        ),
+                        filter_column=dataset.definition.workspace_data_filter_column_name,
+                        filter_column_data_type=ColumnDataType.STRING.value,
+                    )
+                )
+
             # Construct the declarative dataset object and append it to the list.
             declarative_datasets.append(
                 CatalogDeclarativeDataset(
@@ -283,21 +311,8 @@ def datasets_to_ldm(
                     facts=facts,
                     data_source_table_id=dataset_source_table_id,
                     sql=dataset_sql,
-                    workspace_data_filter_columns=[
-                        CatalogDeclarativeWorkspaceDataFilterColumn(
-                            name=dataset.definition.workspace_data_filter_column_name,
-                            data_type=ColumnDataType.STRING.value,
-                        )
-                    ],
-                    workspace_data_filter_references=[
-                        CatalogDeclarativeWorkspaceDataFilterReferences(
-                            filter_id=CatalogDatasetWorkspaceDataFilterIdentifier(
-                                id=dataset.definition.workspace_data_filter_id
-                            ),
-                            filter_column=dataset.definition.workspace_data_filter_column_name,
-                            filter_column_data_type=ColumnDataType.STRING.value,
-                        )
-                    ],
+                    workspace_data_filter_columns=wdf_columns or None,
+                    workspace_data_filter_references=wdf_references or None,
                     tags=_effective_dataset_tags(dataset.definition),
                 )
             )

packages/gooddata-pipelines/src/gooddata_pipelines/ldm_extension/models/custom_data_object.py

@@ -62,7 +62,12 @@ def check_ids_not_equal(self) -> "CustomFieldDefinition":
 
 
 class CustomDatasetDefinition(BaseModel):
-    """Input model for custom dataset definition."""
+    """Input model for custom dataset definition.
+
+    Workspace data filter fields are optional. Both must be set together or
+    both left unset; when set, a single-column WDF binding is emitted on the
+    declarative dataset.
+    """
 
     workspace_id: str
     dataset_id: str
@@ -74,8 +79,8 @@ class CustomDatasetDefinition(BaseModel):
     parent_dataset_reference_attribute_id: str
     dataset_reference_source_column: str
     dataset_reference_source_column_data_type: ColumnDataType
-    workspace_data_filter_id: str
-    workspace_data_filter_column_name: str
+    workspace_data_filter_id: str | None = None
+    workspace_data_filter_column_name: str | None = None
     dataset_description: str | None = Field(
         default=None,
         description="Declarative description on the custom dataset.",
@@ -98,6 +103,18 @@ def check_source(self) -> "CustomDatasetDefinition":
             )
         return self
 
+    @model_validator(mode="after")
+    def check_wdf_pair(self) -> "CustomDatasetDefinition":
+        """Workspace data filter id and column name must be provided together or both omitted."""
+        has_id = self.workspace_data_filter_id is not None
+        has_col = self.workspace_data_filter_column_name is not None
+        if has_id != has_col:
+            raise ValueError(
+                "workspace_data_filter_id and workspace_data_filter_column_name "
+                "must both be set or both be omitted"
+            )
+        return self
+
 
 class CustomDataset(BaseModel):
     """Custom dataset with its definition and custom fields."""

packages/gooddata-pipelines/tests/test_ldm_extension/test_models/test_custom_data_object.py

@@ -100,3 +100,30 @@ def test_custom_dataset_model():
     assert dataset.definition.dataset_id == "ds1"
     assert len(dataset.custom_fields) == 1
     assert dataset.custom_fields[0].custom_field_id == "cf1"
+
+
+def test_custom_dataset_definition_wdf_optional_both_none():
+    data = make_valid_dataset_def(
+        workspace_data_filter_id=None, workspace_data_filter_column_name=None
+    )
+    ds = CustomDatasetDefinition(**data)
+    assert ds.workspace_data_filter_id is None
+    assert ds.workspace_data_filter_column_name is None
+
+
+def test_custom_dataset_definition_wdf_only_id_raises():
+    data = make_valid_dataset_def(
+        workspace_data_filter_id="wdf1", workspace_data_filter_column_name=None
+    )
+    with pytest.raises(ValidationError) as exc:
+        CustomDatasetDefinition(**data)
+    assert "both be set or both be omitted" in str(exc.value)
+
+
+def test_custom_dataset_definition_wdf_only_column_raises():
+    data = make_valid_dataset_def(
+        workspace_data_filter_id=None, workspace_data_filter_column_name="col1"
+    )
+    with pytest.raises(ValidationError) as exc:
+        CustomDatasetDefinition(**data)
+    assert "both be set or both be omitted" in str(exc.value)