Skip to content

bug: Support read_parquet glob file paths #34

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
jiayuasu merged 3 commits into from
Sep 6, 2025
Merged

bug: Support read_parquet glob file paths #34

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e8eb3f1
Add 'test_read_parquet_local_glob' python test
petern48 Sep 5, 2025
39fbfee
Fix glob behavior by only converting to globs once
petern48 Sep 5, 2025
563ef8b
Clean up
petern48 Sep 5, 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
14 changes: 14 additions & 0 deletions python/sedonadb/tests/test_context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,20 @@ def test_read_parquet(con, geoarrow_data):
assert len(tab) == 244


def test_read_parquet_local_glob(con, geoarrow_data):
# The above test uses .glob() method, this test uses the raw string
tab = con.read_parquet(
geoarrow_data / "example/files/*_geo.parquet"
).to_arrow_table()
assert tab["geometry"].type.extension_name == "geoarrow.wkb"
assert len(tab) == 244

tab = con.read_parquet(
geoarrow_data / "example/files/example_polygon-*geo.parquet"
).to_arrow_table()
assert len(tab) == 12


def test_read_parquet_error(con):
with pytest.raises(sedonadb._lib.SedonaError, match="No table paths were provided"):
con.read_parquet([])
Expand Down
24 changes: 14 additions & 10 deletions rust/sedona-geoparquet/src/provider.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ use datafusion::{
file_format::parquet::ParquetFormat,
listing::{ListingOptions, ListingTable, ListingTableConfig, ListingTableUrl},
},
execution::{context::DataFilePaths, options::ReadOptions, SessionState},
execution::{options::ReadOptions, SessionState},
prelude::{ParquetReadOptions, SessionConfig, SessionContext},
};
use datafusion_common::{exec_err, Result};
Expand All @@ -36,12 +36,11 @@ use crate::format::GeoParquetFormat;
/// Because [ListingTable] implements `TableProvider`, this can be used to
/// implement geo-aware Parquet reading with interfaces that are otherwise
/// hard-coded to the built-in Parquet reader.
pub async fn geoparquet_listing_table<P: DataFilePaths>(
pub async fn geoparquet_listing_table(
context: &SessionContext,
table_paths: P,
table_paths: Vec<ListingTableUrl>,
options: GeoParquetReadOptions<'_>,
) -> Result<ListingTable> {
let table_paths = table_paths.to_urls()?;
let session_config = context.copied_config();
let listing_options =
options.to_listing_options(&session_config, context.copied_table_options());
Expand Down Expand Up @@ -134,7 +133,9 @@ mod test {
let data_dir = geoarrow_data_dir().unwrap();
let tab = geoparquet_listing_table(
&ctx,
format!("{data_dir}/example/files/*_geo.parquet"),
vec![
ListingTableUrl::parse(format!("{data_dir}/example/files/*_geo.parquet")).unwrap(),
],
GeoParquetReadOptions::default(),
)
.await
Expand Down Expand Up @@ -169,15 +170,18 @@ mod test {
#[tokio::test]
async fn listing_table_errors() {
let ctx = SessionContext::new();
let err =
geoparquet_listing_table(&ctx, Vec::<String>::new(), GeoParquetReadOptions::default())
.await
.unwrap_err();
let err = geoparquet_listing_table(
&ctx,
Vec::<ListingTableUrl>::new(),
GeoParquetReadOptions::default(),
)
.await
.unwrap_err();
assert_eq!(err.message(), "No table paths were provided");

let err = geoparquet_listing_table(
&ctx,
"foofy.wrongextension",
vec![ListingTableUrl::parse("foofy.wrongextension").unwrap()],
GeoParquetReadOptions::default(),
)
.await
Expand Down