Skip to content

jmat(update): SVS-1112 add wdf column name to input of custom fields script #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
janmatzek merged 1 commit into from
Jul 9, 2025
Merged

jmat(update): SVS-1112 add wdf column name to input of custom fields script #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 6 additions & 5 deletions docs/CUSTOM_FIELDS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,9 +23,9 @@ Multiple datasets and fields can be defined in the files. However, the files nee

The first contains the definitions of the datasets you want to create. It should have following structure:

| workspace_id | dataset_id | dataset_name | dataset_datasource_id | dataset_source_table | dataset_source_sql | parent_dataset_reference | parent_dataset_reference_attribute_id | dataset_reference_source_colum | wdf_id |
| -------------------- | ----------------- | -------------------- | --------------------- | -------------------- | ------------------ | ------------------------ | ------------------------------------- | ------------------------------ | ------ |
| child_workspace_id_1 | custom_dataset_id | Custom Dataset Title | datasource_id | dataset_source_table | | parent_dataset_id | parent_dataset.reference_field | custom_dataset.reference_field | wdf_id |
| workspace_id | dataset_id | dataset_name | dataset_datasource_id | dataset_source_table | dataset_source_sql | parent_dataset_reference | parent_dataset_reference_attribute_id | dataset_reference_source_column | wdf_id | wdf_column_name |
| -------------------- | ----------------- | -------------------- | --------------------- | -------------------- | ------------------ | ------------------------ | ------------------------------------- | ------------------------------- | ------ | --------------- |
| child_workspace_id_1 | custom_dataset_id | Custom Dataset Title | datasource_id | dataset_source_table | | parent_dataset_id | parent_dataset.reference_field | custom_dataset.reference_field | wdf_id | wdf_column_name |

#### Validity constraints

Expand All @@ -47,8 +47,9 @@ For readability, here is the data structure in JSON format with comments. Howeve
"dataset_source_sql": null, // SQL query defining the dataset
"parent_dataset_reference": "products", // ID of the parent dataset to which the custom one will be connected
"parent_dataset_reference_attribute_id": "products.product_id", // parent dataset column name used fot the "join"
"dataset_reference_source_colum": "product_id", // custom dataset column name used for the "join"
"wdf_id": "x__client_id" // workspace data filter id
"dataset_reference_source_column": "product_id", // custom dataset column name used for the "join"
"wdf_id": "x__client_id", // workspace data filter id
"wdf_column_name": "client_id" // name of the column used for filtering
}
```

Expand Down
4 changes: 2 additions & 2 deletions scripts/custom_fields/input_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,7 +221,7 @@ def datasets_to_ldm(
multivalue=True,
sources=[
CatalogDeclarativeReferenceSource(
column=dataset.definition.dataset_reference_source_colum,
column=dataset.definition.dataset_reference_source_column,
target=CatalogGrainIdentifier(
id=dataset.definition.parent_dataset_reference_attribute_id,
type=CustomFieldType.ATTRIBUTE.value,
Expand All @@ -247,7 +247,7 @@ def datasets_to_ldm(
filter_id=CatalogDatasetWorkspaceDataFilterIdentifier(
id=dataset.definition.wdf_id
),
filter_column=dataset.definition.wdf_id,
filter_column=dataset.definition.wdf_column_name,
filter_column_data_type=ColumnDataType.STRING.value,
)
],
Expand Down
3 changes: 2 additions & 1 deletion scripts/custom_fields/models/custom_data_object.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,8 +62,9 @@ class CustomDatasetDefinition(BaseModel):
dataset_source_sql: str | None
parent_dataset_reference: str
parent_dataset_reference_attribute_id: str
dataset_reference_source_colum: str
dataset_reference_source_column: str
wdf_id: str
wdf_column_name: str

@model_validator(mode="after")
def check_source(self) -> "CustomDatasetDefinition":
Expand Down
3 changes: 2 additions & 1 deletion tests/test_custom_fields/test_input_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,8 +68,9 @@ def mock_dataset_definition():
dataset_source_sql=None,
parent_dataset_reference="parent_ds",
parent_dataset_reference_attribute_id="parent_attr",
dataset_reference_source_colum="ref_col",
dataset_reference_source_column="ref_col",
wdf_id="wdf1",
wdf_column_name="col1",
)


Expand Down
12 changes: 6 additions & 6 deletions tests/test_custom_fields/test_input_validator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,9 +28,9 @@ def valid_dataset_definitions():
"dataset_source_sql": None,
"parent_dataset_reference": "parent1",
"parent_dataset_reference_attribute_id": "parent1.id",
"dataset_reference_source_colum": "id",
"dataset_reference_source_column": "id",
"wdf_id": "wdf1",
"wdf_value": "val1",
"wdf_column_name": "id",
},
{
"workspace_id": "ws2",
Expand All @@ -41,9 +41,9 @@ def valid_dataset_definitions():
"dataset_source_sql": None,
"parent_dataset_reference": "parent2",
"parent_dataset_reference_attribute_id": "parent2.id",
"dataset_reference_source_colum": "id",
"dataset_reference_source_column": "id",
"wdf_id": "wdf2",
"wdf_value": "val2",
"wdf_column_name": "id",
},
]

Expand Down Expand Up @@ -107,9 +107,9 @@ def test_duplicate_dataset_raises(valid_dataset_definitions):
"dataset_source_sql": None,
"parent_dataset_reference": "parent1",
"parent_dataset_reference_attribute_id": "parent1.id",
"dataset_reference_source_colum": "id",
"dataset_reference_source_column": "id",
"wdf_id": "wdf1",
"wdf_value": "val1",
"wdf_column_name": "id",
}
]
validator = CustomFieldsDataValidator()
Expand Down
4 changes: 2 additions & 2 deletions tests/test_custom_fields/test_models/test_custom_data_object.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,9 @@ def make_valid_dataset_def(**kwargs):
"dataset_source_sql": None,
"parent_dataset_reference": "parent_ds",
"parent_dataset_reference_attribute_id": "parent_attr",
"dataset_reference_source_colum": "src_col",
"dataset_reference_source_column": "src_col",
"wdf_id": "wdf1",
"wdf_value": "val1",
"wdf_column_name": "col1",
}
data.update(kwargs)
return data
Expand Down