{
"name": "read_json",
"pyspark_version": "3.5.0",
"input": {
"schema": [
{
"name": "age",
"type": "bigint"
},
{
"name": "id",
"type": "bigint"
},
{
"name": "name",
"type": "string"
}
],
"rows": [
[
25,
1,
"Alice"
],
[
30,
2,
"Bob"
],
[
35,
3,
"Charlie"
]
],
"file_source": {
"format": "json",
"content": "{\"id\":1,\"age\":25,\"name\":\"Alice\"}\n{\"id\":2,\"age\":30,\"name\":\"Bob\"}\n{\"id\":3,\"age\":35,\"name\":\"Charlie\"}\n"
}
},
"operations": [
{
"op": "filter",
"expr": "col('age') > 30"
},
{
"op": "select",
"columns": [
"name",
"age"
]
},
{
"op": "orderBy",
"columns": [
"name"
],
"ascending": [
true
]
}
],
"expected": {
"schema": [
{
"name": "name",
"type": "string"
},
{
"name": "age",
"type": "bigint"
}
],
"rows": [
[
"Charlie",
35
]
]
}
}