This is an automated email from the ASF dual-hosted git repository. prantogg pushed a commit to branch make-parquet-default in repository https://gitbox.apache.org/repos/asf/sedona-spatialbench.git
commit 9879de9e355736e5c055dd05205817d8e23e9271 Author: Pranav Toggi <[email protected]> AuthorDate: Mon Oct 13 19:28:03 2025 -0700 update default output format to parquet --- spatialbench-cli/README.md | 2 +- spatialbench-cli/src/main.rs | 4 ++-- spatialbench-cli/tests/cli_integration.rs | 12 ++++++------ 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/spatialbench-cli/README.md b/spatialbench-cli/README.md index 98c7f91..84f8cca 100644 --- a/spatialbench-cli/README.md +++ b/spatialbench-cli/README.md @@ -43,7 +43,7 @@ Options: --part <PART> Which part to generate (1-based, only relevant if parts > 1) [default: 1] -f, --format <FORMAT> - Output format: tbl, csv, parquet (default: tbl) [default: tbl] [possible values: tbl, csv, parquet] + Output format: parquet, tbl, csv (default: parquet) [default: parquet] [possible values: parquet, tbl, csv] -n, --num-threads <NUM_THREADS> The number of threads for parallel generation, defaults to the number of CPUs [default: 8] -c, --parquet-compression <PARQUET_COMPRESSION> diff --git a/spatialbench-cli/src/main.rs b/spatialbench-cli/src/main.rs index f94e4b9..8067a45 100644 --- a/spatialbench-cli/src/main.rs +++ b/spatialbench-cli/src/main.rs @@ -13,7 +13,7 @@ //! -V, --version Prints version information //! -s, --scale-factor <FACTOR> Scale factor for the data generation (default: 1) //! -T, --tables <TABLES> Comma-separated list of tables to generate (default: all) -//! -f, --format <FORMAT> Output format: tbl, csv, or parquet (default: tbl) +//! -f, --format <FORMAT> Output format: parquet, tbl or csv (default: parquet) //! -o, --output-dir <DIR> Output directory (default: current directory) //! -p, --parts <N> Number of parts to split generation into (default: 1) //! --part <N> Which part to generate (1-based, default: 1) @@ -109,7 +109,7 @@ struct Cli { part: Option<i32>, /// Output format: tbl, csv, parquet - #[arg(short, long, default_value = "tbl")] + #[arg(short, long, default_value = "parquet")] format: OutputFormat, /// The number of threads for parallel generation, defaults to the number of CPUs diff --git a/spatialbench-cli/tests/cli_integration.rs b/spatialbench-cli/tests/cli_integration.rs index 1786278..5cfaf91 100644 --- a/spatialbench-cli/tests/cli_integration.rs +++ b/spatialbench-cli/tests/cli_integration.rs @@ -22,6 +22,8 @@ fn test_spatialbench_cli_tbl_scale_factor_v1() { .expect("Binary not found") .arg("--scale-factor") .arg("0.51") + .arg("--format") + .arg("tbl") .arg("--output-dir") .arg(temp_dir.path()) .arg("--tables") @@ -34,6 +36,8 @@ fn test_spatialbench_cli_tbl_scale_factor_v1() { .expect("Binary not found") .arg("--scale-factor") .arg("0.001") + .arg("--format") + .arg("tbl") .arg("--output-dir") .arg(temp_dir.path()) .arg("--tables") @@ -100,6 +104,8 @@ fn test_spatialbench_cli_parts() { .expect("Binary not found") .arg("--scale-factor") .arg("0.001") + .arg("--format") + .arg("tbl") .arg("--output-dir") .arg(&part_dir) .arg("--parts") @@ -145,8 +151,6 @@ async fn test_write_parquet_trips() { let output_path = output_dir.path().join("trip.parquet"); Command::cargo_bin("spatialbench-cli") .expect("Binary not found") - .arg("--format") - .arg("parquet") .arg("--tables") .arg("trip") .arg("--scale-factor") @@ -191,8 +195,6 @@ async fn test_write_parquet_row_group_size_default() { let output_dir = tempdir().unwrap(); Command::cargo_bin("spatialbench-cli") .expect("Binary not found") - .arg("--format") - .arg("parquet") .arg("--scale-factor") .arg("1") .arg("--tables") @@ -235,8 +237,6 @@ async fn test_write_parquet_row_group_size_20mb() { let output_dir = tempdir().unwrap(); Command::cargo_bin("spatialbench-cli") .expect("Binary not found") - .arg("--format") - .arg("parquet") .arg("--scale-factor") .arg("1") .arg("--tables")
