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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements. See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership. The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License. You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied. See the License for the
// specific language governing permissions and limitations
// under the License.
//! Values execution plan
use super::expressions::PhysicalSortExpr;
use super::{common, SendableRecordBatchStream, Statistics};
use crate::physical_plan::{
memory::MemoryStream, ColumnarValue, DisplayFormatType, ExecutionPlan, Partitioning,
PhysicalExpr,
};
use arrow::array::new_null_array;
use arrow::datatypes::SchemaRef;
use arrow::record_batch::RecordBatch;
use datafusion_common::ScalarValue;
use datafusion_common::{DataFusionError, Result};
use datafusion_execution::TaskContext;
use std::any::Any;
use std::sync::Arc;
/// Execution plan for values list based relation (produces constant rows)
#[derive(Debug)]
pub struct ValuesExec {
/// The schema
schema: SchemaRef,
/// The data
data: Vec<RecordBatch>,
}
impl ValuesExec {
/// create a new values exec from data as expr
pub fn try_new(
schema: SchemaRef,
data: Vec<Vec<Arc<dyn PhysicalExpr>>>,
) -> Result<Self> {
if data.is_empty() {
return Err(DataFusionError::Plan("Values list cannot be empty".into()));
}
let n_row = data.len();
let n_col = schema.fields().len();
// we have this single row, null, typed batch as a placeholder to satisfy evaluation argument
let batch = RecordBatch::try_new(
schema.clone(),
schema
.fields()
.iter()
.map(|field| new_null_array(field.data_type(), 1))
.collect::<Vec<_>>(),
)?;
let arr = (0..n_col)
.map(|j| {
(0..n_row)
.map(|i| {
let r = data[i][j].evaluate(&batch);
match r {
Ok(ColumnarValue::Scalar(scalar)) => Ok(scalar),
Ok(ColumnarValue::Array(a)) if a.len() == 1 => {
ScalarValue::try_from_array(&a, 0)
}
Ok(ColumnarValue::Array(a)) => {
Err(DataFusionError::Plan(format!(
"Cannot have array values {a:?} in a values list"
)))
}
Err(err) => Err(err),
}
})
.collect::<Result<Vec<_>>>()
.and_then(ScalarValue::iter_to_array)
})
.collect::<Result<Vec<_>>>()?;
let batch = RecordBatch::try_new(schema.clone(), arr)?;
let data: Vec<RecordBatch> = vec![batch];
Ok(Self { schema, data })
}
/// provides the data
fn data(&self) -> Vec<RecordBatch> {
self.data.clone()
}
}
impl ExecutionPlan for ValuesExec {
/// Return a reference to Any that can be used for downcasting
fn as_any(&self) -> &dyn Any {
self
}
fn schema(&self) -> SchemaRef {
self.schema.clone()
}
fn children(&self) -> Vec<Arc<dyn ExecutionPlan>> {
vec![]
}
/// Get the output partitioning of this plan
fn output_partitioning(&self) -> Partitioning {
Partitioning::UnknownPartitioning(1)
}
fn output_ordering(&self) -> Option<&[PhysicalSortExpr]> {
None
}
fn with_new_children(
self: Arc<Self>,
_: Vec<Arc<dyn ExecutionPlan>>,
) -> Result<Arc<dyn ExecutionPlan>> {
Ok(Arc::new(ValuesExec {
schema: self.schema.clone(),
data: self.data.clone(),
}))
}
fn execute(
&self,
partition: usize,
_context: Arc<TaskContext>,
) -> Result<SendableRecordBatchStream> {
// GlobalLimitExec has a single output partition
if 0 != partition {
return Err(DataFusionError::Internal(format!(
"ValuesExec invalid partition {partition} (expected 0)"
)));
}
Ok(Box::pin(MemoryStream::try_new(
self.data(),
self.schema.clone(),
None,
)?))
}
fn fmt_as(
&self,
t: DisplayFormatType,
f: &mut std::fmt::Formatter,
) -> std::fmt::Result {
match t {
DisplayFormatType::Default | DisplayFormatType::Verbose => {
write!(f, "ValuesExec")
}
}
}
fn statistics(&self) -> Statistics {
let batch = self.data();
common::compute_record_batch_statistics(&[batch], &self.schema, None)
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::test_util;
#[tokio::test]
async fn values_empty_case() -> Result<()> {
let schema = test_util::aggr_test_schema();
let empty = ValuesExec::try_new(schema, vec![]);
assert!(empty.is_err());
Ok(())
}
}