datafusion 20.0.0

DataFusion is an in-memory query engine that uses Apache Arrow as the memory model
Documentation 
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

// 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.

//! Collection of testing utility functions that are leveraged by the query optimizer rules

use crate::error::Result;
use crate::prelude::{CsvReadOptions, SessionContext};
use async_trait::async_trait;
use std::sync::Arc;

async fn register_current_csv(
    ctx: &SessionContext,
    table_name: &str,
    infinite: bool,
) -> Result<()> {
    let testdata = crate::test_util::arrow_test_data();
    let schema = crate::test_util::aggr_test_schema();
    ctx.register_csv(
        table_name,
        &format!("{testdata}/csv/aggregate_test_100.csv"),
        CsvReadOptions::new()
            .schema(&schema)
            .mark_infinite(infinite),
    )
    .await?;
    Ok(())
}

#[derive(Eq, PartialEq, Debug)]
pub enum SourceType {
    Unbounded,
    Bounded,
}

#[async_trait]
pub trait SqlTestCase {
    async fn register_table(&self, ctx: &SessionContext) -> Result<()>;
    fn expect_fail(&self) -> bool;
}

/// [UnaryTestCase] is designed for single input [ExecutionPlan]s.
pub struct UnaryTestCase {
    pub(crate) source_type: SourceType,
    pub(crate) expect_fail: bool,
}

#[async_trait]
impl SqlTestCase for UnaryTestCase {
    async fn register_table(&self, ctx: &SessionContext) -> Result<()> {
        let table_is_infinite = self.source_type == SourceType::Unbounded;
        register_current_csv(ctx, "test", table_is_infinite).await?;
        Ok(())
    }

    fn expect_fail(&self) -> bool {
        self.expect_fail
    }
}
/// [BinaryTestCase] is designed for binary input [ExecutionPlan]s.
pub struct BinaryTestCase {
    pub(crate) source_types: (SourceType, SourceType),
    pub(crate) expect_fail: bool,
}

#[async_trait]
impl SqlTestCase for BinaryTestCase {
    async fn register_table(&self, ctx: &SessionContext) -> Result<()> {
        let left_table_is_infinite = self.source_types.0 == SourceType::Unbounded;
        let right_table_is_infinite = self.source_types.1 == SourceType::Unbounded;
        register_current_csv(ctx, "left", left_table_is_infinite).await?;
        register_current_csv(ctx, "right", right_table_is_infinite).await?;
        Ok(())
    }

    fn expect_fail(&self) -> bool {
        self.expect_fail
    }
}

pub struct QueryCase {
    pub(crate) sql: String,
    pub(crate) cases: Vec<Arc<dyn SqlTestCase>>,
    pub(crate) error_operator: String,
}

impl QueryCase {
    /// Run the test cases
    pub(crate) async fn run(&self) -> Result<()> {
        for case in &self.cases {
            let ctx = SessionContext::new();
            case.register_table(&ctx).await?;
            let error = if case.expect_fail() {
                Some(&self.error_operator)
            } else {
                None
            };
            self.run_case(ctx, error).await?;
        }
        Ok(())
    }
    async fn run_case(&self, ctx: SessionContext, error: Option<&String>) -> Result<()> {
        let dataframe = ctx.sql(self.sql.as_str()).await?;
        let plan = dataframe.create_physical_plan().await;
        if error.is_some() {
            let plan_error = plan.unwrap_err();
            let initial = error.unwrap().to_string();
            assert!(
                plan_error.to_string().contains(initial.as_str()),
                "plan_error: {:?} doesn't contain message: {:?}",
                plan_error,
                initial.as_str()
            );
        } else {
            assert!(plan.is_ok())
        }
        Ok(())
    }
}