1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
{
"name": "filter_nested",
"pyspark_version": "3.5.0",
"input": {
"schema": [
{
"name": "id",
"type": "int"
},
{
"name": "age",
"type": "int"
},
{
"name": "score",
"type": "int"
},
{
"name": "vip",
"type": "int"
}
],
"rows": [
[
1,
25,
50,
0
],
[
2,
35,
60,
0
],
[
3,
45,
110,
1
],
[
4,
55,
70,
0
],
[
5,
30,
80,
1
]
]
},
"operations": [
{
"op": "filter",
"expr": "(col('age') > 30 AND (col('score') < 100 OR col('vip') == 1))"
},
{
"op": "orderBy",
"columns": [
"id"
],
"ascending": [
true
]
}
],
"expected": {
"schema": [
{
"name": "id",
"type": "int"
},
{
"name": "age",
"type": "int"
},
{
"name": "score",
"type": "int"
},
{
"name": "vip",
"type": "int"
}
],
"rows": [
[
2,
35,
60,
0
],
[
3,
45,
110,
1
],
[
4,
55,
70,
0
]
]
}
}