tustvold commented on issue #4005:
URL:
https://github.com/apache/arrow-datafusion/issues/4005#issuecomment-1295942182
I can reproduce this with
```
#[test]
fn foo() {
use arrow::datatypes::Int32Type as ArrowInt32Type;
let file =
File::open("/home/raphael/Downloads/data.parquet").unwrap();
let builder =
ParquetRecordBatchReaderBuilder::try_new(file).unwrap();
let container_idx = builder.schema.index_of("container").unwrap();
let projection =
ProjectionMask::leaves(builder.parquet_schema(),
[container_idx]);
let p1 = ArrowPredicateFn::new(projection, |b| {
arrow::compute::eq_dyn_utf8_scalar(
as_dictionary_array::<ArrowInt32Type>(b.column(0)),
"backend_container_0",
)
});
let pod_idx = builder.schema.index_of("pod").unwrap();
let projection = ProjectionMask::leaves(builder.parquet_schema(),
[pod_idx]);
let p2 = ArrowPredicateFn::new(projection, |b| {
arrow::compute::eq_dyn_utf8_scalar(
as_dictionary_array::<ArrowInt32Type>(b.column(0)),
"aqcathnxqsphdhgjtgvxsfyiwbmhlmg",
)
});
let filter = RowFilter::new(vec![Box::new(p1), Box::new(p2)]);
let reader = builder.with_row_filter(filter).build().unwrap();
let count: usize = reader.map(|x| x.unwrap().num_rows()).sum();
assert_eq!(count, 39982)
}
```
--
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]
