|
| 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 | +use arrow::array::{ |
| 19 | + BooleanBuilder, Int16Builder, Int32Builder, Int64Builder, Int8Builder, StringBuilder, |
| 20 | + StructArray, StructBuilder, |
| 21 | +}; |
| 22 | +use arrow::datatypes::{DataType, Field}; |
| 23 | +use criterion::{criterion_group, criterion_main, Criterion}; |
| 24 | +use datafusion_comet_spark_expr::{to_csv_inner, CsvWriteOptions, EvalMode, SparkCastOptions}; |
| 25 | +use std::hint::black_box; |
| 26 | + |
| 27 | +fn create_struct_array(array_size: usize) -> StructArray { |
| 28 | + let fields = vec![ |
| 29 | + Field::new("f1", DataType::Boolean, true), |
| 30 | + Field::new("f2", DataType::Int8, true), |
| 31 | + Field::new("f3", DataType::Int16, true), |
| 32 | + Field::new("f4", DataType::Int32, true), |
| 33 | + Field::new("f5", DataType::Int64, true), |
| 34 | + Field::new("f6", DataType::Utf8, true), |
| 35 | + ]; |
| 36 | + let mut struct_builder = StructBuilder::from_fields(fields, array_size); |
| 37 | + for i in 0..array_size { |
| 38 | + struct_builder |
| 39 | + .field_builder::<BooleanBuilder>(0) |
| 40 | + .unwrap() |
| 41 | + .append_option(if i % 10 == 0 { None } else { Some(i % 2 == 0) }); |
| 42 | + |
| 43 | + struct_builder |
| 44 | + .field_builder::<Int8Builder>(1) |
| 45 | + .unwrap() |
| 46 | + .append_option(if i % 10 == 0 { |
| 47 | + None |
| 48 | + } else { |
| 49 | + Some((i % 128) as i8) |
| 50 | + }); |
| 51 | + |
| 52 | + struct_builder |
| 53 | + .field_builder::<Int16Builder>(2) |
| 54 | + .unwrap() |
| 55 | + .append_option(if i % 10 == 0 { None } else { Some(i as i16) }); |
| 56 | + |
| 57 | + struct_builder |
| 58 | + .field_builder::<Int32Builder>(3) |
| 59 | + .unwrap() |
| 60 | + .append_option(if i % 10 == 0 { None } else { Some(i as i32) }); |
| 61 | + |
| 62 | + struct_builder |
| 63 | + .field_builder::<Int64Builder>(4) |
| 64 | + .unwrap() |
| 65 | + .append_option(if i % 10 == 0 { None } else { Some(i as i64) }); |
| 66 | + |
| 67 | + struct_builder |
| 68 | + .field_builder::<StringBuilder>(5) |
| 69 | + .unwrap() |
| 70 | + .append_option(if i % 10 == 0 { |
| 71 | + None |
| 72 | + } else { |
| 73 | + Some(format!("string_{}", i)) |
| 74 | + }); |
| 75 | + |
| 76 | + struct_builder.append(true); |
| 77 | + } |
| 78 | + struct_builder.finish() |
| 79 | +} |
| 80 | + |
| 81 | +fn criterion_benchmark(c: &mut Criterion) { |
| 82 | + let array_size = 8192; |
| 83 | + let timezone = "UTC"; |
| 84 | + let struct_array = create_struct_array(array_size); |
| 85 | + let default_delimiter = ","; |
| 86 | + let default_null_value = ""; |
| 87 | + let default_quote = "\""; |
| 88 | + let default_escape = "\\"; |
| 89 | + let mut cast_options = SparkCastOptions::new(EvalMode::Legacy, timezone, false); |
| 90 | + cast_options.null_string = default_null_value.to_string(); |
| 91 | + let csv_write_options = CsvWriteOptions::new( |
| 92 | + default_delimiter.to_string(), |
| 93 | + default_quote.to_string(), |
| 94 | + default_escape.to_string(), |
| 95 | + default_null_value.to_string(), |
| 96 | + false, |
| 97 | + true, |
| 98 | + true, |
| 99 | + ); |
| 100 | + c.bench_function("to_csv", |b| { |
| 101 | + b.iter(|| { |
| 102 | + black_box(to_csv_inner(&struct_array, &cast_options, &csv_write_options).unwrap()) |
| 103 | + }) |
| 104 | + }); |
| 105 | +} |
| 106 | + |
| 107 | +criterion_group!(benches, criterion_benchmark); |
| 108 | +criterion_main!(benches); |
0 commit comments