alamb commented on code in PR #5433:
URL: https://github.com/apache/arrow-datafusion/pull/5433#discussion_r1124346116
##########
benchmarks/README.md:
##########
@@ -176,3 +181,13 @@ Iteration 1 returned 1781686 rows in 1986 ms
Iteration 2 returned 1781686 rows in 1947 ms
...
```
+
+Similarly, to run sorting benchmarks, run:
+
+```base
+cargo run --release --bin parquet -- sort --path ./data --scale-factor 1.0
Review Comment:
I tried this out and it works great!
```
cargo run --bin parquet -- sort --path ./data --scale-factor 0.1
```
##########
parquet-test-utils/src/lib.rs:
##########
@@ -148,25 +155,26 @@ impl TestParquetFile {
// run coercion on the filters to coerce types etc.
let props = ExecutionProps::new();
let context =
SimplifyContext::new(&props).with_schema(df_schema.clone());
- let simplifier = ExprSimplifier::new(context);
- let filter = simplifier.coerce(filter, df_schema.clone()).unwrap();
-
- let physical_filter_expr = create_physical_expr(
- &filter,
- &df_schema,
- self.schema.as_ref(),
- &ExecutionProps::default(),
- )?;
-
- let parquet_exec = Arc::new(ParquetExec::new(
- scan_config,
- Some(physical_filter_expr.clone()),
- None,
- ));
-
- let exec = Arc::new(FilterExec::try_new(physical_filter_expr,
parquet_exec)?);
-
- Ok(exec)
+ if let Some(filter) = maybe_filter {
Review Comment:
👍
--
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]
