Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 58 additions & 1 deletion datafusion/functions/benches/translate.rs
Original file line number Diff line number Diff line change
Expand Up @@ -15,18 +15,45 @@
// specific language governing permissions and limitations
// under the License.

use arrow::array::OffsetSizeTrait;
use arrow::array::{GenericStringArray, OffsetSizeTrait};
use arrow::datatypes::{DataType, Field};
use arrow::util::bench_util::create_string_array_with_len;
use criterion::{Criterion, SamplingMode, criterion_group, criterion_main};
use datafusion_common::config::ConfigOptions;
use datafusion_common::{DataFusionError, ScalarValue};
use datafusion_expr::{ColumnarValue, ScalarFunctionArgs};
use datafusion_functions::unicode;
use rand::SeedableRng;
use rand::prelude::IndexedRandom;
use rand::rngs::StdRng;
use std::hint::black_box;
use std::sync::Arc;
use std::time::Duration;

// Mix of 2-byte (Greek) and 3-byte (CJK/Hangul) UTF-8 to exercise
// variable-width char paths in translate.
const NON_ASCII_ALPHABET: &[char] = &[
'α', 'β', 'γ', 'δ', 'ε', 'ζ', 'η', 'θ', 'ι', 'κ', 'λ', 'μ', 'ν', 'ξ', 'ο', 'π', 'ρ',
'σ', 'τ', 'υ', 'φ', 'χ', 'ψ', 'ω', '日', '本', '語', '中', '文', '한', '국', '어',
];

fn create_non_ascii_string_array<O: OffsetSizeTrait>(
size: usize,
char_count: usize,
seed: u64,
) -> GenericStringArray<O> {
let mut rng = StdRng::seed_from_u64(seed);
(0..size)
.map(|_| {
Some(
(0..char_count)
.map(|_| *NON_ASCII_ALPHABET.choose(&mut rng).unwrap())
.collect::<String>(),
)
})
.collect()
}

fn create_args_array_from_to<O: OffsetSizeTrait>(
size: usize,
str_len: usize,
Expand All @@ -42,6 +69,25 @@ fn create_args_array_from_to<O: OffsetSizeTrait>(
]
}

fn create_args_array_from_to_non_ascii<O: OffsetSizeTrait>(
size: usize,
str_len: usize,
) -> Vec<ColumnarValue> {
let string_array = Arc::new(create_non_ascii_string_array::<O>(
size,
str_len,
0xA110_AAAA,
));
let from_array = Arc::new(create_non_ascii_string_array::<O>(size, 3, 0xA110_BBBB));
let to_array = Arc::new(create_non_ascii_string_array::<O>(size, 2, 0xA110_CCCC));

vec![
ColumnarValue::Array(string_array),
ColumnarValue::Array(from_array),
ColumnarValue::Array(to_array),
]
}

fn create_args_scalar_from_to<O: OffsetSizeTrait>(
size: usize,
str_len: usize,
Expand Down Expand Up @@ -91,6 +137,17 @@ fn criterion_benchmark(c: &mut Criterion) {
})
});

let args = create_args_array_from_to_non_ascii::<i32>(size, str_len);
group.bench_function(
format!("array_from_to_non_ascii [str_len={str_len}]"),
|b| {
b.iter(|| {
let args_cloned = args.clone();
black_box(invoke_translate_with_args(args_cloned, size))
})
},
);

let args = create_args_scalar_from_to::<i32>(size, str_len);
group.bench_function(format!("scalar_from_to [str_len={str_len}]"), |b| {
b.iter(|| {
Expand Down
Loading
Loading