arrow 59.2.0

Rust implementation of Apache Arrow
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

// 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.

#[macro_use]
extern crate criterion;
use criterion::Criterion;

extern crate arrow;

use arrow::array::*;
use arrow::compute::kernels::substring::*;
use arrow::util::bench_util::*;
use std::hint;

fn bench_substring(arr: &dyn Array, start: i64, length: Option<u64>) {
    substring(hint::black_box(arr), start, length).unwrap();
}

fn bench_substring_by_char<O: OffsetSizeTrait>(
    arr: &GenericStringArray<O>,
    start: i64,
    length: Option<u64>,
) {
    substring_by_char(hint::black_box(arr), start, length).unwrap();
}

/// A non-ASCII variant of [`create_string_array_with_len`]: every fourth char is a
/// multi-byte codepoint, so `substring_by_char` has to decode UTF-8 to find a char index.
fn create_utf8_array_with_len<O: OffsetSizeTrait>(
    size: usize,
    str_len: usize,
) -> GenericStringArray<O> {
    create_string_array_with_len::<O>(size, 0.0, str_len)
        .iter()
        .map(|val| {
            val.map(|val| {
                val.chars()
                    .enumerate()
                    .map(|(i, c)| if i % 4 == 0 { 'é' } else { c })
                    .collect::<String>()
            })
        })
        .collect()
}

fn add_benchmark(c: &mut Criterion) {
    let size = 65536;
    let val_len = 1000;

    let arr_string = create_string_array_with_len::<i32>(size, 0.0, val_len);
    let arr_utf8 = create_utf8_array_with_len::<i32>(size, val_len);
    let arr_fsb = create_fsb_array(size, 0.0, val_len);

    c.bench_function("substring utf8 (start = 0, length = None)", |b| {
        b.iter(|| bench_substring(&arr_string, 0, None))
    });

    c.bench_function("substring utf8 (start = 1, length = str_len - 1)", |b| {
        b.iter(|| bench_substring(&arr_string, 1, Some((val_len - 1) as u64)))
    });

    c.bench_function("substring utf8 by char", |b| {
        b.iter(|| bench_substring_by_char(&arr_string, 1, Some((val_len - 1) as u64)))
    });

    c.bench_function("substring by char (ascii, prefix)", |b| {
        b.iter(|| bench_substring_by_char(&arr_string, 0, Some(10)))
    });

    c.bench_function("substring by char (ascii, tail)", |b| {
        b.iter(|| bench_substring_by_char(&arr_string, -10, None))
    });

    c.bench_function("substring by char (non-ascii, prefix)", |b| {
        b.iter(|| bench_substring_by_char(&arr_utf8, 0, Some(10)))
    });

    c.bench_function("substring by char (non-ascii, tail)", |b| {
        b.iter(|| bench_substring_by_char(&arr_utf8, -10, None))
    });

    c.bench_function("substring fixed size binary array", |b| {
        b.iter(|| bench_substring(&arr_fsb, 1, Some((val_len - 1) as u64)))
    });
}

criterion_group!(benches, add_benchmark);
criterion_main!(benches);