|
| 1 | +// Licensed to the Apache Software Foundation (ASF) under one |
| 2 | +// or more contributor license agreements. See the NOTICE file |
| 3 | +// distributed with this work for additional information |
| 4 | +// regarding copyright ownership. The ASF licenses this file |
| 5 | +// to you under the Apache License, Version 2.0 (the |
| 6 | +// "License"); you may not use this file except in compliance |
| 7 | +// with the License. You may obtain a copy of the License at |
| 8 | +// |
| 9 | +// http://www.apache.org/licenses/LICENSE-2.0 |
| 10 | +// |
| 11 | +// Unless required by applicable law or agreed to in writing, |
| 12 | +// software distributed under the License is distributed on an |
| 13 | +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 14 | +// KIND, either express or implied. See the License for the |
| 15 | +// specific language governing permissions and limitations |
| 16 | +// under the License. |
| 17 | + |
| 18 | +//! Integration tests for register_arrow API |
| 19 | +
|
| 20 | +use datafusion::{execution::options::ArrowReadOptions, prelude::*}; |
| 21 | +use datafusion_common::Result; |
| 22 | + |
| 23 | +#[tokio::test] |
| 24 | +async fn test_register_arrow_auto_detects_format() -> Result<()> { |
| 25 | + let ctx = SessionContext::new(); |
| 26 | + |
| 27 | + ctx.register_arrow( |
| 28 | + "file_format", |
| 29 | + "../../datafusion/datasource-arrow/tests/data/example.arrow", |
| 30 | + ArrowReadOptions::default(), |
| 31 | + ) |
| 32 | + .await?; |
| 33 | + |
| 34 | + ctx.register_arrow( |
| 35 | + "stream_format", |
| 36 | + "../../datafusion/datasource-arrow/tests/data/example_stream.arrow", |
| 37 | + ArrowReadOptions::default(), |
| 38 | + ) |
| 39 | + .await?; |
| 40 | + |
| 41 | + let file_result = ctx.sql("SELECT * FROM file_format ORDER BY f0").await?; |
| 42 | + let stream_result = ctx.sql("SELECT * FROM stream_format ORDER BY f0").await?; |
| 43 | + |
| 44 | + let file_batches = file_result.collect().await?; |
| 45 | + let stream_batches = stream_result.collect().await?; |
| 46 | + |
| 47 | + assert_eq!(file_batches.len(), stream_batches.len()); |
| 48 | + assert_eq!(file_batches[0].schema(), stream_batches[0].schema()); |
| 49 | + |
| 50 | + let file_rows: usize = file_batches.iter().map(|b| b.num_rows()).sum(); |
| 51 | + let stream_rows: usize = stream_batches.iter().map(|b| b.num_rows()).sum(); |
| 52 | + assert_eq!(file_rows, stream_rows); |
| 53 | + |
| 54 | + Ok(()) |
| 55 | +} |
| 56 | + |
| 57 | +#[tokio::test] |
| 58 | +async fn test_register_arrow_join_file_and_stream() -> Result<()> { |
| 59 | + let ctx = SessionContext::new(); |
| 60 | + |
| 61 | + ctx.register_arrow( |
| 62 | + "file_table", |
| 63 | + "../../datafusion/datasource-arrow/tests/data/example.arrow", |
| 64 | + ArrowReadOptions::default(), |
| 65 | + ) |
| 66 | + .await?; |
| 67 | + |
| 68 | + ctx.register_arrow( |
| 69 | + "stream_table", |
| 70 | + "../../datafusion/datasource-arrow/tests/data/example_stream.arrow", |
| 71 | + ArrowReadOptions::default(), |
| 72 | + ) |
| 73 | + .await?; |
| 74 | + |
| 75 | + let result = ctx |
| 76 | + .sql( |
| 77 | + "SELECT a.f0, a.f1, b.f0, b.f1 |
| 78 | + FROM file_table a |
| 79 | + JOIN stream_table b ON a.f0 = b.f0 |
| 80 | + WHERE a.f0 <= 2 |
| 81 | + ORDER BY a.f0", |
| 82 | + ) |
| 83 | + .await?; |
| 84 | + let batches = result.collect().await?; |
| 85 | + |
| 86 | + let total_rows: usize = batches.iter().map(|b| b.num_rows()).sum(); |
| 87 | + assert_eq!(total_rows, 2); |
| 88 | + |
| 89 | + Ok(()) |
| 90 | +} |
0 commit comments