Merge remote-tracking branch 'origin/main' into use-clap-subcommands

Author: kevinjqliu

.github/workflows/build-py-packages.yml

@@ -82,7 +82,7 @@ jobs:
           manylinux: ${{ matrix.manylinux || '' }}
       - name: Upload wheels
         if: ${{ inputs.upload-artifacts }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: wheels-${{ matrix.os }}-${{ matrix.target }}
           path: tpchgen-cli/dist
@@ -99,7 +99,7 @@ jobs:
           working-directory: tpchgen-cli
       - name: Upload sdist
         if: ${{ inputs.upload-artifacts }}
-        uses: actions/upload-artifact@v6
+        uses: actions/upload-artifact@v7
         with:
           name: wheels-sdist
           path: tpchgen-cli/dist

.github/workflows/ci_typos.yml

@@ -39,4 +39,4 @@ jobs:
     steps:
       - uses: actions/checkout@v6
       - name: Check typos
-        uses: crate-ci/typos@v1.42.1
+        uses: crate-ci/typos@v1.44.0

.github/workflows/tpcdsgen-conformance.yml

@@ -63,7 +63,7 @@ jobs:
 
     - name: Upload test fixtures as artifacts
       if: failure()  # Upload fixtures if tests fail for debugging
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v7
       with:
         name: test-fixtures
         path: tpcdsgen/tests/fixtures/
@@ -107,7 +107,7 @@ jobs:
         time ./target/release/tpcdsgen --scale 1 --directory /tmp/bench
 
     - name: Upload benchmark results
-      uses: actions/upload-artifact@v6
+      uses: actions/upload-artifact@v7
       with:
         name: benchmark-results
         path: /tmp/bench/

.github/workflows/tpchgen-cli-publish-pypi.yml

@@ -24,7 +24,7 @@ jobs:
       attestations: write # Used to generate artifact attestation
     steps:
       - name: Download all build artifacts
-        uses: actions/download-artifact@v7
+        uses: actions/download-artifact@v8
         with:
           pattern: '*'
           merge-multiple: true
@@ -37,7 +37,7 @@ jobs:
         run: python -m twine check --strict dist/*
 
       - name: Generate artifact attestation
-        uses: actions/attest-build-provenance@v3
+        uses: actions/attest-build-provenance@v4
         with:
           subject-path: 'dist/*'
 

Cargo.toml

@@ -14,4 +14,6 @@ repository = "https://github.com/clflushopt/tpchgen-rs"
 version = "2.0.2"
 
 [profile.release]
+codegen-units = 1
+lto = true
 strip = "debuginfo"

tpchgen-arrow/Cargo.toml

@@ -9,9 +9,9 @@ readme = "README.md"
 license = "Apache-2.0"
 
 [dependencies]
-arrow = { version = "57.1", default-features = false, features = ["prettyprint"] }
+arrow = { version = "58", default-features = false, features = ["prettyprint"] }
 tpchgen = { path = "../tpchgen", version = "2.0.2" }
 
 [dev-dependencies]
-arrow-csv = "57.1"
+arrow-csv = "58"
 chrono = "0.4.39"

tpchgen-cli/Cargo.toml

@@ -18,12 +18,12 @@ name = "tpchgen-cli"
 path = "bin/main.rs"
 
 [dependencies]
-arrow = "57.1"
-parquet = "57.1"
+arrow = "58"
+parquet = "58"
 clap = { version = "4.5.32", features = ["derive"] }
-tpchgen = { path = "../tpchgen", version = "2.0.2"}
+tpchgen = { path = "../tpchgen", version = "2.0.2" }
 tpchgen-arrow = { path = "../tpchgen-arrow", version = "2.0.2" }
-tokio = { version = "1.44.1", features = ["full"]}
+tokio = { version = "1.44.1", features = ["full"] }
 futures = "0.3.31"
 num_cpus = "1.0"
 log = "0.4.26"

tpchgen-cli/tests/cli_integration.rs

@@ -1,4 +1,4 @@
-use assert_cmd::Command;
+use assert_cmd::cargo::cargo_bin_cmd;
 use parquet::arrow::arrow_reader::{ArrowReaderOptions, ParquetRecordBatchReaderBuilder};
 use parquet::file::metadata::ParquetMetaDataReader;
 use std::fs;
@@ -16,8 +16,7 @@ fn test_tpchgen_cli_tbl_scale_factor_0_001() {
     let temp_dir = tempdir().expect("Failed to create temporary directory");
 
     // Run the tpchgen-cli command
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--output-dir")
@@ -73,8 +72,7 @@ fn test_tpchgen_cli_tbl_no_overwrite() {
     let expected_file = temp_dir.path().join("part.tbl");
 
     // First run - create the file
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--tables")
@@ -90,8 +88,7 @@ fn test_tpchgen_cli_tbl_no_overwrite() {
 
     // Run the tpchgen-cli command again with the same parameters and expect the
     // file to not be overwritten and a warning to be logged
-    let output = Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    let output = cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--tables")
@@ -128,8 +125,7 @@ fn test_tpchgen_cli_parquet_no_overwrite() {
     let expected_file = temp_dir.path().join("part.parquet");
 
     // First run - create the file
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("parquet")
         .arg("--scale-factor")
         .arg("0.001")
@@ -146,8 +142,7 @@ fn test_tpchgen_cli_parquet_no_overwrite() {
 
     // Run the tpchgen-cli command again with the same parameters and expect the
     // file to not be overwritten and a warning to be logged
-    let output = Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    let output = cargo_bin_cmd!("tpchgen-cli")
         .arg("parquet")
         .arg("--scale-factor")
         .arg("0.001")
@@ -185,8 +180,7 @@ fn test_tpchgen_cli_quiet_flag() {
     let expected_file = temp_dir.path().join("part.tbl");
 
     // First run - create the file
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--tables")
@@ -202,8 +196,7 @@ fn test_tpchgen_cli_quiet_flag() {
 
     // Run the tpchgen-cli command again with --quiet flag
     // Expect the file to not be overwritten and NO warning even though warnings show by default
-    let output = Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    let output = cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--tables")
@@ -245,8 +238,7 @@ fn test_tpchgen_cli_parts() {
 
     let num_parts = 4;
     let output_dir = temp_dir.path().to_path_buf();
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--output-dir")
@@ -276,8 +268,7 @@ fn test_tpchgen_cli_parts_explicit() {
         threads.push(std::thread::spawn(move || {
             // Run the tpchgen-cli command for each part
             // output goes into `output_dir/orders/orders.{part}.tbl`
-            Command::cargo_bin("tpchgen-cli")
-                .expect("Binary not found")
+            cargo_bin_cmd!("tpchgen-cli")
                 .arg("--scale-factor")
                 .arg("0.001")
                 .arg("--output-dir")
@@ -306,8 +297,7 @@ fn test_tpchgen_cli_parts_all_tables() {
 
     let num_parts = 8;
     let output_dir = temp_dir.path().to_path_buf();
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--scale-factor")
         .arg("0.001")
         .arg("--output-dir")
@@ -358,8 +348,7 @@ async fn test_write_parquet_orders() {
     // Run the CLI command to generate parquet data
     let output_dir = tempdir().unwrap();
     let output_path = output_dir.path().join("orders.parquet");
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("parquet")
         .arg("--tables")
         .arg("orders")
@@ -403,8 +392,7 @@ async fn test_write_parquet_orders() {
 async fn test_write_parquet_row_group_size_default() {
     // Run the CLI command to generate parquet data with default settings
     let output_dir = tempdir().unwrap();
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("parquet")
         .arg("--scale-factor")
         .arg("1")
@@ -470,8 +458,7 @@ async fn test_write_parquet_row_group_size_default() {
 async fn test_write_parquet_row_group_size_20mb() {
     // Run the CLI command to generate parquet data with larger row group size
     let output_dir = tempdir().unwrap();
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("parquet")
         .arg("--scale-factor")
         .arg("1")
@@ -530,8 +517,7 @@ fn test_tpchgen_cli_part_no_parts() {
     let temp_dir = tempdir().expect("Failed to create temporary directory");
 
     // CLI Error test --part and but not --parts
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--output-dir")
         .arg(temp_dir.path())
         .arg("--part")
@@ -548,8 +534,7 @@ fn test_tpchgen_cli_too_many_parts() {
     let temp_dir = tempdir().expect("Failed to create temporary directory");
 
     // This should fail because --part is 42 which is more than the --parts 10
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--output-dir")
         .arg(temp_dir.path())
         .arg("--part")
@@ -567,8 +552,7 @@ fn test_tpchgen_cli_too_many_parts() {
 fn test_tpchgen_cli_zero_part() {
     let temp_dir = tempdir().expect("Failed to create temporary directory");
 
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--output-dir")
         .arg(temp_dir.path())
         .arg("--part")
@@ -585,8 +569,7 @@ fn test_tpchgen_cli_zero_part() {
 fn test_tpchgen_cli_zero_part_zero_parts() {
     let temp_dir = tempdir().expect("Failed to create temporary directory");
 
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--output-dir")
         .arg(temp_dir.path())
         .arg("--part")
@@ -604,8 +587,7 @@ fn test_tpchgen_cli_zero_part_zero_parts() {
 #[tokio::test]
 async fn test_incompatible_options_warnings() {
     let output_dir = tempdir().unwrap();
-    Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    cargo_bin_cmd!("tpchgen-cli")
         .arg("--format")
         .arg("csv")
         .arg("--tables")
@@ -634,8 +616,7 @@ async fn test_incompatible_options_warnings() {
 #[tokio::test]
 async fn test_quiet_flag_suppresses_warnings() {
     let output_dir = tempdir().unwrap();
-    let output = Command::cargo_bin("tpchgen-cli")
-        .expect("Binary not found")
+    let output = cargo_bin_cmd!("tpchgen-cli")
         .env("RUST_LOG", "warn")
         .arg("--format")
         .arg("csv")