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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
use std::any::Any;
use std::fmt;
use std::sync::Arc;
use super::ColumnarValue;
use crate::error::{DataFusionError, Result};
use crate::physical_plan::PhysicalExpr;
use crate::scalar::ScalarValue;
use arrow::array::BooleanArray;
use arrow::datatypes::{DataType, Schema};
use arrow::record_batch::RecordBatch;
#[derive(Debug)]
pub struct NotExpr {
arg: Arc<dyn PhysicalExpr>,
}
impl NotExpr {
pub fn new(arg: Arc<dyn PhysicalExpr>) -> Self {
Self { arg }
}
pub fn arg(&self) -> &Arc<dyn PhysicalExpr> {
&self.arg
}
}
impl fmt::Display for NotExpr {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "NOT {}", self.arg)
}
}
impl PhysicalExpr for NotExpr {
fn as_any(&self) -> &dyn Any {
self
}
fn data_type(&self, _input_schema: &Schema) -> Result<DataType> {
Ok(DataType::Boolean)
}
fn nullable(&self, input_schema: &Schema) -> Result<bool> {
self.arg.nullable(input_schema)
}
fn evaluate(&self, batch: &RecordBatch) -> Result<ColumnarValue> {
let arg = self.arg.evaluate(batch)?;
match arg {
ColumnarValue::Array(array) => {
let array =
array
.as_any()
.downcast_ref::<BooleanArray>()
.ok_or_else(|| {
DataFusionError::Internal(
"boolean_op failed to downcast array".to_owned(),
)
})?;
Ok(ColumnarValue::Array(Arc::new(
arrow::compute::kernels::boolean::not(array)?,
)))
}
ColumnarValue::Scalar(scalar) => {
use std::convert::TryInto;
let bool_value: bool = scalar.try_into()?;
Ok(ColumnarValue::Scalar(ScalarValue::Boolean(Some(
!bool_value,
))))
}
}
}
}
pub fn not(
arg: Arc<dyn PhysicalExpr>,
input_schema: &Schema,
) -> Result<Arc<dyn PhysicalExpr>> {
let data_type = arg.data_type(input_schema)?;
if data_type != DataType::Boolean {
Err(DataFusionError::Internal(format!(
"NOT '{:?}' can't be evaluated because the expression's type is {:?}, not boolean",
arg, data_type,
)))
} else {
Ok(Arc::new(NotExpr::new(arg)))
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::error::Result;
use crate::physical_plan::expressions::col;
use arrow::datatypes::*;
#[test]
fn neg_op() -> Result<()> {
let schema = Schema::new(vec![Field::new("a", DataType::Boolean, true)]);
let expr = not(col("a"), &schema)?;
assert_eq!(expr.data_type(&schema)?, DataType::Boolean);
assert_eq!(expr.nullable(&schema)?, true);
let input = BooleanArray::from(vec![Some(true), None, Some(false)]);
let expected = &BooleanArray::from(vec![Some(false), None, Some(true)]);
let batch =
RecordBatch::try_new(Arc::new(schema.clone()), vec![Arc::new(input)])?;
let result = expr.evaluate(&batch)?.into_array(batch.num_rows());
let result = result
.as_any()
.downcast_ref::<BooleanArray>()
.expect("failed to downcast to BooleanArray");
assert_eq!(result, expected);
Ok(())
}
#[test]
fn neg_op_not_null() {
let schema = Schema::new(vec![Field::new("a", DataType::Utf8, true)]);
let expr = not(col("a"), &schema);
assert!(expr.is_err());
}
}