osipovartem commented on code in PR #11411:
URL: https://github.com/apache/arrow-rs/pull/11411#discussion_r4211644009
##########
parquet-variant-compute/benches/variant_kernels.rs:
##########
@@ -42,6 +42,58 @@ const VARIANT_GET_UNSHREDDED_OBJECT_ROWS: usize = 262_144;
const VARIANT_ARRAY_BUILD_ROWS: usize = 262_144;
const SHRED_VARIANT_OBJECT_ROWS: usize = 8_192;
+fn benchmark_json_to_variant_inputs(c: &mut Criterion) {
+ let large_array = format!(
+ "[{}]",
+ (0..1024)
+ .map(|number| number.to_string())
+ .collect::<Vec<_>>()
+ .join(",")
+ );
+ let large_string = format!(r#"{{"payload":"{}","id":42}}"#,
"x".repeat(8192));
+ let duplicate_large = format!(r#"{{"a":"{}","a":0}}"#,
"x".repeat(100_000));
+ let inputs = [
+ (
+ "integers",
+ r#"{"id":123456789,"values":[1,2,3,4,5],"active":true}"#,
+ ),
+ (
+ "decimals",
+
r#"{"small":1.23,"medium":999999999.0,"large":0.9999999999999999999}"#,
+ ),
+ (
+ "strings",
+ r#"{"first":"alpha","second":"beta","third":"gamma"}"#,
+ ),
+ (
+ "escaped_strings",
+ r#"{"line":"one\ntwo","quote":"\"value\"","unicode":"\u2764"}"#,
+ ),
+ (
+ "nested",
+
r#"{"outer":[{"id":1,"values":[1.25,2.50]},{"id":2,"values":[3.75,4.00]}]}"#,
+ ),
+ ("large_array_1024", large_array.as_str()),
+ ("large_string_8k", large_string.as_str()),
+ ("duplicate_key_100k", duplicate_large.as_str()),
+ ];
+
+ let mut group = c.benchmark_group("json_to_variant_inputs");
Review Comment:
Updated to the existing `bench_function` format with no separate Criterion
group or throughput setting. Each new benchmark name includes bytes per
document and row count, as in the surrounding suite.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
