Skip to content

Minor: use FileScanConfig builder API in some tests #14938

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Mar 3, 2025
Merged

Minor: use FileScanConfig builder API in some tests #14938

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
40fcbe1
Minor: use FileScanConfig builder API
alamb Feb 28, 2025
b8363d9
moar
alamb Feb 28, 2025
9681308
Merge remote-tracking branch 'apache/main' into alamb/try_no_statistics
alamb Mar 3, 2025
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
113 changes: 43 additions & 70 deletions datafusion/proto/tests/cases/roundtrip_physical_plan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,6 @@ use datafusion::arrow::compute::kernels::sort::SortOptions;
use datafusion::arrow::datatypes::{DataType, Field, IntervalUnit, Schema};
use datafusion::datasource::empty::EmptyTable;
use datafusion::datasource::file_format::csv::CsvSink;
use datafusion::datasource::file_format::file_compression_type::FileCompressionType;
use datafusion::datasource::file_format::json::JsonSink;
use datafusion::datasource::file_format::parquet::ParquetSink;
use datafusion::datasource::listing::{ListingTableUrl, PartitionedFile};
Expand Down Expand Up @@ -95,7 +94,7 @@ use datafusion_common::file_options::json_writer::JsonWriterOptions;
use datafusion_common::parsers::CompressionTypeVariant;
use datafusion_common::stats::Precision;
use datafusion_common::{
internal_err, not_impl_err, Constraints, DataFusionError, Result, UnnestOptions,
internal_err, not_impl_err, DataFusionError, Result, UnnestOptions,
};
use datafusion_expr::{
Accumulator, AccumulatorFactoryFunction, AggregateUDF, ColumnarValue, ScalarUDF,
Expand Down Expand Up @@ -738,33 +737,23 @@ fn roundtrip_parquet_exec_with_pruning_predicate() -> Result<()> {
let mut options = TableParquetOptions::new();
options.global.pushdown_filters = true;

let source = Arc::new(
let file_source = Arc::new(
ParquetSource::new(options).with_predicate(Arc::clone(&file_schema), predicate),
);

let scan_config = FileScanConfig {
object_store_url: ObjectStoreUrl::local_filesystem(),
file_schema,
file_groups: vec![vec![PartitionedFile::new(
"/path/to/file.parquet".to_string(),
1024,
)]],
constraints: Constraints::empty(),
statistics: Statistics {
num_rows: Precision::Inexact(100),
total_byte_size: Precision::Inexact(1024),
column_statistics: Statistics::unknown_column(&Arc::new(Schema::new(vec![
Field::new("col", DataType::Utf8, false),
]))),
},
projection: None,
limit: None,
table_partition_cols: vec![],
output_ordering: vec![],
file_compression_type: FileCompressionType::UNCOMPRESSED,
new_lines_in_values: false,
file_source: source,
};
let scan_config =
FileScanConfig::new(ObjectStoreUrl::local_filesystem(), file_schema, file_source)
.with_file_groups(vec![vec![PartitionedFile::new(
"/path/to/file.parquet".to_string(),
1024,
)]])
.with_statistics(Statistics {
num_rows: Precision::Inexact(100),
total_byte_size: Precision::Inexact(1024),
column_statistics: Statistics::unknown_column(&Arc::new(Schema::new(
vec![Field::new("col", DataType::Utf8, false)],
))),
});

roundtrip_test(scan_config.build())
}
Expand All @@ -777,9 +766,9 @@ async fn roundtrip_parquet_exec_with_table_partition_cols() -> Result<()> {
vec![wrap_partition_value_in_dict(ScalarValue::Int64(Some(0)))];
let schema = Arc::new(Schema::new(vec![Field::new("col", DataType::Utf8, false)]));

let source = Arc::new(ParquetSource::default());
let file_source = Arc::new(ParquetSource::default());
let scan_config =
FileScanConfig::new(ObjectStoreUrl::local_filesystem(), schema, source)
FileScanConfig::new(ObjectStoreUrl::local_filesystem(), schema, file_source)
.with_projection(Some(vec![0, 1]))
.with_file_group(vec![file_group])
.with_table_partition_cols(vec![Field::new(
Expand All @@ -801,34 +790,24 @@ fn roundtrip_parquet_exec_with_custom_predicate_expr() -> Result<()> {
inner: Arc::new(Column::new("col", 1)),
});

let source = Arc::new(
let file_source = Arc::new(
ParquetSource::default()
.with_predicate(Arc::clone(&file_schema), custom_predicate_expr),
);

let scan_config = FileScanConfig {
object_store_url: ObjectStoreUrl::local_filesystem(),
file_schema,
file_groups: vec![vec![PartitionedFile::new(
"/path/to/file.parquet".to_string(),
1024,
)]],
constraints: Constraints::empty(),
statistics: Statistics {
num_rows: Precision::Inexact(100),
total_byte_size: Precision::Inexact(1024),
column_statistics: Statistics::unknown_column(&Arc::new(Schema::new(vec![
Field::new("col", DataType::Utf8, false),
]))),
},
projection: None,
limit: None,
table_partition_cols: vec![],
output_ordering: vec![],
file_compression_type: FileCompressionType::UNCOMPRESSED,
new_lines_in_values: false,
file_source: source,
};
let scan_config =
FileScanConfig::new(ObjectStoreUrl::local_filesystem(), file_schema, file_source)
.with_file_groups(vec![vec![PartitionedFile::new(
"/path/to/file.parquet".to_string(),
1024,
)]])
.with_statistics(Statistics {
num_rows: Precision::Inexact(100),
total_byte_size: Precision::Inexact(1024),
column_statistics: Statistics::unknown_column(&Arc::new(Schema::new(
vec![Field::new("col", DataType::Utf8, false)],
))),
});

#[derive(Debug, Clone, Eq)]
struct CustomPredicateExpr {
Expand Down Expand Up @@ -1608,24 +1587,18 @@ async fn roundtrip_projection_source() -> Result<()> {

let statistics = Statistics::new_unknown(&schema);

let source = ParquetSource::default().with_statistics(statistics.clone());
let scan_config = FileScanConfig {
object_store_url: ObjectStoreUrl::local_filesystem(),
file_groups: vec![vec![PartitionedFile::new(
"/path/to/file.parquet".to_string(),
1024,
)]],
constraints: Constraints::empty(),
statistics,
file_schema: schema.clone(),
projection: Some(vec![0, 1, 2]),
limit: None,
table_partition_cols: vec![],
output_ordering: vec![],
file_compression_type: FileCompressionType::UNCOMPRESSED,
new_lines_in_values: false,
file_source: source,
};
let file_source = ParquetSource::default().with_statistics(statistics.clone());
let scan_config = FileScanConfig::new(
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this also makes the non-default fields more clear

ObjectStoreUrl::local_filesystem(),
schema.clone(),
file_source,
)
.with_file_groups(vec![vec![PartitionedFile::new(
"/path/to/file.parquet".to_string(),
1024,
)]])
.with_statistics(statistics)
.with_projection(Some(vec![0, 1, 2]));

let filter = Arc::new(
FilterExec::try_new(
Expand Down