{
"test_id": "encode",
"pyspark_version": "3.5",
"generated_at": "2025-10-27T14:13:23.327161",
"input_data": [
{
"id": 1,
"name": "Alice",
"text": "Hello World",
"email": "alice@example.com"
},
{
"id": 2,
"name": "Bob",
"text": "Test String",
"email": "bob@test.com"
},
{
"id": 3,
"name": "Charlie",
"text": "Python Data",
"email": "charlie@company.org"
}
],
"operation": "DataFrame operation: encode",
"expected_output": {
"schema": {
"field_count": 1,
"field_names": [
"encode(name, UTF-8)"
],
"field_types": [
"binary"
],
"fields": [
{
"name": "encode(name, UTF-8)",
"type": "binary",
"nullable": true
}
]
},
"data": [
{
"encode(name, UTF-8)": "bytearray(b'Alice')"
},
{
"encode(name, UTF-8)": "bytearray(b'Bob')"
},
{
"encode(name, UTF-8)": "bytearray(b'Charlie')"
}
],
"row_count": 3
}
}