Skip to content

Minor: consolidate test data #6217

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 4 commits into from
May 5, 2023
Merged

Minor: consolidate test data #6217

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b6c7c92
Minor: consolidate test data directories
alamb May 3, 2023
3fa1455
move json data
alamb May 3, 2023
f6b859a
move parquet data
alamb May 3, 2023
5e212bd
Merge remote-tracking branch 'apache/main' into alamb/move_data
alamb May 5, 2023
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
4 changes: 2 additions & 2 deletions datafusion/core/src/datasource/file_format/json.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,7 +256,7 @@ mod tests {
projection: Option<Vec<usize>>,
limit: Option<usize>,
) -> Result<Arc<dyn ExecutionPlan>> {
let filename = "tests/jsons/2.json";
let filename = "tests/data/2.json";
let format = JsonFormat::default();
scan_format(state, &format, ".", filename, projection, limit).await
}
Expand All @@ -266,7 +266,7 @@ mod tests {
let session = SessionContext::new();
let ctx = session.state();
let store = Arc::new(LocalFileSystem::new()) as _;
let filename = "tests/jsons/schema_infer_limit.json";
let filename = "tests/data/schema_infer_limit.json";
let format = JsonFormat::default().with_schema_infer_max_rec(Some(3));

let file_schema = format
Expand Down
2 changes: 1 addition & 1 deletion datafusion/core/src/physical_plan/file_format/csv.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -785,7 +785,7 @@ mod tests {
let options = CsvReadOptions::default()
.schema_infer_max_records(2)
.has_header(true);
let df = ctx.read_csv("tests/csv/corrupt.csv", options).await?;
let df = ctx.read_csv("tests/data/corrupt.csv", options).await?;
let tmp_dir = TempDir::new()?;
let out_dir = tmp_dir.as_ref().to_str().unwrap().to_string() + "/out";
let e = df
Expand Down
4 changes: 2 additions & 2 deletions datafusion/core/src/physical_plan/file_format/json.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -309,7 +309,7 @@ mod tests {

use super::*;

const TEST_DATA_BASE: &str = "tests/jsons";
const TEST_DATA_BASE: &str = "tests/data";

async fn prepare_store(
state: &SessionState,
Expand Down Expand Up @@ -707,7 +707,7 @@ mod tests {
let options = CsvReadOptions::default()
.schema_infer_max_records(2)
.has_header(true);
let df = ctx.read_csv("tests/csv/corrupt.csv", options).await?;
let df = ctx.read_csv("tests/data/corrupt.csv", options).await?;
let tmp_dir = TempDir::new()?;
let out_dir = tmp_dir.as_ref().to_str().unwrap().to_string() + "/out";
let e = df
Expand Down
2 changes: 1 addition & 1 deletion datafusion/core/src/physical_plan/file_format/parquet.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -940,7 +940,7 @@ mod tests {
let options = CsvReadOptions::default()
.schema_infer_max_records(2)
.has_header(true);
let df = ctx.read_csv("tests/csv/corrupt.csv", options).await?;
let df = ctx.read_csv("tests/data/corrupt.csv", options).await?;
let tmp_dir = TempDir::new()?;
let out_dir = tmp_dir.as_ref().to_str().unwrap().to_string() + "/out";
let e = df
Expand Down
0 datafusion/core/tests/jsons/1.json → datafusion/core/tests/data/1.json
View file
Open in desktop
File renamed without changes.
0 datafusion/core/tests/jsons/2.json → datafusion/core/tests/data/2.json
View file
Open in desktop
File renamed without changes.
0 datafusion/core/tests/jsons/3.json → datafusion/core/tests/data/3.json
View file
Open in desktop
File renamed without changes.
0 datafusion/core/tests/csv/corrupt.csv → datafusion/core/tests/data/corrupt.csv
View file
Open in desktop
File renamed without changes.
0 ...s/parquet/data/repeat_much.snappy.parquet → ...ore/tests/data/repeat_much.snappy.parquet
View file
Open in desktop
File renamed without changes.
0 .../core/tests/jsons/schema_infer_limit.json → ...n/core/tests/data/schema_infer_limit.json
View file
Open in desktop
File renamed without changes.
0 ...re/tests/parquet/data/test_binary.parquet → ...usion/core/tests/data/test_binary.parquet
View file
Open in desktop
File renamed without changes.
0 ...ts/parquet/data/timestamp_with_tz.parquet → ...core/tests/data/timestamp_with_tz.parquet
View file
Open in desktop
File renamed without changes.
4 changes: 2 additions & 2 deletions datafusion/core/tests/sql/json.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

use super::*;

const TEST_DATA_BASE: &str = "tests/jsons";
const TEST_DATA_BASE: &str = "tests/data";

#[tokio::test]
async fn json_query() {
Expand Down Expand Up @@ -92,7 +92,7 @@ async fn json_explain() {
\n CoalescePartitionsExec\
\n AggregateExec: mode=Partial, gby=[], aggr=[COUNT(UInt8(1))]\
\n RepartitionExec: partitioning=RoundRobinBatch(NUM_CORES), input_partitions=1\
\n JsonExec: file_groups={1 group: [[WORKING_DIR/tests/jsons/2.json]]}, projection=[a]\n",
\n JsonExec: file_groups={1 group: [[WORKING_DIR/tests/data/2.json]]}, projection=[a]\n",
],
];
assert_eq!(expected, actual);
Expand Down
2 changes: 1 addition & 1 deletion datafusion/core/tests/sql/order.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ use test_utils::{batches_to_vec, partitions_to_sorted_vec};
#[tokio::test]
async fn sort_with_lots_of_repetition_values() -> Result<()> {
let ctx = SessionContext::new();
let filename = "tests/parquet/data/repeat_much.snappy.parquet";
Copy link
Contributor Author

@alamb alamb May 3, 2023

Choose a reason for hiding this comment

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

the parquet one was particularly confusing because tests/parquet also has a bunch of rust code as well

let filename = "tests/data/repeat_much.snappy.parquet";

ctx.register_parquet("rep", filename, ParquetReadOptions::default())
.await?;
Expand Down
4 changes: 2 additions & 2 deletions datafusion/core/tests/sql/parquet.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@ async fn fixed_size_binary_columns() {
let ctx = SessionContext::new();
ctx.register_parquet(
"t0",
"tests/parquet/data/test_binary.parquet",
"tests/data/test_binary.parquet",
ParquetReadOptions::default(),
)
.await
Expand All @@ -170,7 +170,7 @@ async fn window_fn_timestamp_tz() {
let ctx = SessionContext::new();
ctx.register_parquet(
"t0",
"tests/parquet/data/timestamp_with_tz.parquet",
"tests/data/timestamp_with_tz.parquet",
ParquetReadOptions::default(),
)
.await
Expand Down