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

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

Author: benkeanna

docs/content/en/latest/pipelines/ldm_extension/_index.md

@@ -43,15 +43,17 @@ The custom dataset represents a new dataset appended to the child LDM. It is def
 | parent_dataset_reference_attribute_id | string | ID of the attribute used for creating the relationship in the parent dataset. |
 | dataset_reference_source_column | string | Name of the column used for creating the relationship in the custom dataset. |
 | dataset_reference_source_column_data_type | [ColumnDataType](#columndatatype) | Column data type. |
-| workspace_data_filter_id | string | ID of the workspace data filter to use. |
-| workspace_data_filter_column_name | string | Name of the column in custom dataset used for filtering. |
+| workspace_data_filter_id | string \| None | ID of the workspace data filter to use. Optional; when omitted the dataset participates in no workspace data filter. |
+| workspace_data_filter_column_name | string \| None | Name of the column in custom dataset used for filtering. Optional; must be set whenever `workspace_data_filter_id` is set. |
 | dataset_description | string \| None | Optional declarative description on the custom dataset. |
 | dataset_tags | string[] \| None | Optional tag list; when omitted, defaults to a single tag derived from the dataset display name. |
 
 #### Validity constraints
 
 Either `dataset_source_table` or `dataset_source_sql` must be specified with a truthy value, but not both. An exception will be raised if both parameters are falsy or if both have truthy values.
 
+`workspace_data_filter_id` and `workspace_data_filter_column_name` must be provided together or both left unset. Setting only one of them raises a `ValidationError`. When both are unset, the resulting dataset is emitted without a workspace data filter binding.
+
 ### Custom Field Definitions
 
 The custom fields define the individual fields in the custom datasets defined above. Each custom field needs to be specified with the following parameters:

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

@@ -253,6 +253,35 @@ def datasets_to_ldm(
             # Get the data source info
             dataset_source_table_id, dataset_sql = self._get_sources(dataset)
 
+            wdf_columns: (
+                list[CatalogDeclarativeWorkspaceDataFilterColumn] | None
+            ) = None
+            wdf_references: (
+                list[CatalogDeclarativeWorkspaceDataFilterReferences] | None
+            ) = None
+            wdf_id = dataset.definition.workspace_data_filter_id
+            wdf_column_name = (
+                dataset.definition.workspace_data_filter_column_name
+            )
+            # `check_wdf_pair` on the model guarantees both fields are set
+            # together or both omitted.
+            if wdf_id is not None and wdf_column_name is not None:
+                wdf_columns = [
+                    CatalogDeclarativeWorkspaceDataFilterColumn(
+                        name=wdf_column_name,
+                        data_type=ColumnDataType.STRING.value,
+                    )
+                ]
+                wdf_references = [
+                    CatalogDeclarativeWorkspaceDataFilterReferences(
+                        filter_id=CatalogDatasetWorkspaceDataFilterIdentifier(
+                            id=wdf_id
+                        ),
+                        filter_column=wdf_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 +312,8 @@ 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,
+                    workspace_data_filter_references=wdf_references,
                     tags=_effective_dataset_tags(dataset.definition),
                 )
             )

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

@@ -74,8 +74,8 @@ 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 +98,18 @@ 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)