{
"test_id": "basic_select",
"pyspark_version": "3.5",
"generated_at": "2025-10-27T14:13:15.387169",
"input_data": [
{
"id": 1,
"name": "Alice",
"age": 25,
"salary": 50000.0
},
{
"id": 2,
"name": "Bob",
"age": 30,
"salary": 60000.0
},
{
"id": 3,
"name": "Charlie",
"age": 35,
"salary": 70000.0
}
],
"operation": "SELECT id, name, age FROM employees",
"expected_output": {
"schema": {
"field_count": 3,
"field_names": [
"id",
"name",
"age"
],
"field_types": [
"long",
"string",
"long"
],
"fields": [
{
"name": "id",
"type": "long",
"nullable": true
},
{
"name": "name",
"type": "string",
"nullable": true
},
{
"name": "age",
"type": "long",
"nullable": true
}
]
},
"data": [
{
"id": 1,
"name": "Alice",
"age": 25
},
{
"id": 2,
"name": "Bob",
"age": 30
},
{
"id": 3,
"name": "Charlie",
"age": 35
}
],
"row_count": 3
}
}