ci: share extended test commands through xtask

.github/workflows/extended.yml

@@ -15,6 +15,14 @@
 # specific language governing permissions and limitations
 # under the License.
 
+# Each test command below is implemented with `cargo xtask` so developers can
+# run the same suite locally. Append `--explain` to print the underlying
+# `cargo test` invocation without running it. Job setup, the clean working tree
+# check, and `cargo clean` remain in this workflow.
+#
+# See `xtask/README.md` for details about DataFusion's `xtask` tooling.
+# Track progress at https://github.com/apache/datafusion/issues/24487.
+
 name: Datafusion extended tests
 
 concurrency:
@@ -75,22 +83,7 @@ jobs:
         run: |
           df -h
       - name: Run tests (excluding doctests)
-        env:
-          RUST_BACKTRACE: 1
-          # Run more random scenarios of the spill pool fuzzer than the
-          # default suite does (about a minute).
-          DATAFUSION_SPILL_POOL_FUZZ_ITERATIONS: 1000
-        run: |
-          cargo test \
-            --profile ci \
-            --exclude datafusion-examples \
-            --exclude datafusion-benchmarks \
-            --exclude datafusion-cli \
-            --workspace \
-            --lib \
-            --tests \
-            --bins \
-            --features avro,json,backtrace,extended_tests,recursive_protection,parquet_encryption
+        run: cargo xtask ci step test extended
       - parallel:
           - name: Verify Working Directory Clean
             run: git diff --exit-code
@@ -118,8 +111,8 @@ jobs:
           rust-version: stable
       - name: Run tests
         run: |
+          cargo xtask ci step test hash-collisions
           cd datafusion
-          cargo test  --profile ci --exclude datafusion-examples --exclude datafusion-benchmarks --exclude datafusion-sqllogictest --exclude datafusion-cli --workspace --lib --tests --features=force_hash_collisions,avro
           cargo clean
 
   sqllogictest-sqlite:
@@ -142,5 +135,4 @@ jobs:
             run: |
               apt-get update && apt-get install -y protobuf-compiler
       - name: Run sqllogictest
-        run: |
-          cargo test --features backtrace,parquet_encryption --profile ci-optimized --test sqllogictests -- --include-sqlite
+        run: cargo xtask ci step test sqlite

xtask/src/ci_steps.rs

@@ -55,7 +55,7 @@ static CI_STEPS: &[StepInfo] = &[
     },
     StepInfo {
         command: "test",
-        help_usage: "test <workspace|cli|doctest|ffi|benchmark-plan|benchmark-sqllogic|postgres|substrait> [--explain]",
+        help_usage: "test <workspace|cli|doctest|ffi|benchmark-plan|benchmark-sqllogic|postgres|substrait|extended|hash-collisions|sqlite> [--explain]",
         help_examples: &["test cli", "test workspace"],
         help_description: "Run a CI test suite",
         error_message: "Cargo test step failed",
@@ -358,6 +358,70 @@ impl StepContext {
                     "limit.slt",
                 ]);
             }
+            "extended" => {
+                command
+                    .args([
+                        "test",
+                        "--profile",
+                        "ci",
+                        "--exclude",
+                        "datafusion-examples",
+                        "--exclude",
+                        "datafusion-benchmarks",
+                        "--exclude",
+                        "datafusion-cli",
+                        "--workspace",
+                        "--lib",
+                        "--tests",
+                        "--bins",
+                        "--features",
+                        "avro,json,backtrace,extended_tests,recursive_protection,parquet_encryption",
+                    ])
+                    .env("RUST_BACKTRACE", "1")
+                    // Run more random scenarios of the spill pool fuzzer than the
+                    // default suite does (about a minute).
+                    .env("DATAFUSION_SPILL_POOL_FUZZ_ITERATIONS", "1000");
+            }
+            "hash-collisions" => {
+                // Check answers are correct when hash values collide. The CI job
+                // runs from the `datafusion` directory with the builder setup,
+                // which sets `RUST_BACKTRACE=1`.
+                command
+                    .args([
+                        "test",
+                        "--profile",
+                        "ci",
+                        "--exclude",
+                        "datafusion-examples",
+                        "--exclude",
+                        "datafusion-benchmarks",
+                        "--exclude",
+                        "datafusion-sqllogictest",
+                        "--exclude",
+                        "datafusion-cli",
+                        "--workspace",
+                        "--lib",
+                        "--tests",
+                        "--features=force_hash_collisions,avro",
+                    ])
+                    .current_dir(self.root.join("datafusion"))
+                    .env("RUST_BACKTRACE", "1");
+            }
+            "sqlite" => {
+                // The CI job skips the builder setup because backtraces make this
+                // suite expensive, so `RUST_BACKTRACE` is deliberately not set.
+                command.args([
+                    "test",
+                    "--features",
+                    "backtrace,parquet_encryption",
+                    "--profile",
+                    "ci-optimized",
+                    "--test",
+                    "sqllogictests",
+                    "--",
+                    "--include-sqlite",
+                ]);
+            }
             _ => return Err(StepError::Usage),
         }
 
@@ -546,6 +610,8 @@ fn required_env(name: &str) -> Result<String> {
 mod tests {
     use super::*;
 
+    const TEST_USAGE: &str = "usage: cargo xtask ci step test <workspace|cli|doctest|ffi|benchmark-plan|benchmark-sqllogic|postgres|substrait|extended|hash-collisions|sqlite> [--explain]";
+
     fn args(args: &[&str]) -> Vec<String> {
         args.iter().map(|arg| (*arg).to_string()).collect()
     }
@@ -590,10 +656,17 @@ mod tests {
             .err()
             .unwrap();
 
-        assert_eq!(
-            error,
-            "usage: cargo xtask ci step test <workspace|cli|doctest|ffi|benchmark-plan|benchmark-sqllogic|postgres|substrait> [--explain]"
-        );
+        assert_eq!(error, TEST_USAGE);
+    }
+
+    #[test]
+    fn unknown_test_variant_is_rejected() {
+        let error = context()
+            .ci_step(&args(&["test", "extended_tests", "--explain"]))
+            .err()
+            .unwrap();
+
+        assert_eq!(error, TEST_USAGE);
     }
 
     // Test all available commands, ensure their executed command is expected
@@ -775,6 +848,58 @@ cargo test \
 --test sqllogictests \
 --features substrait \
 -- --substrait-round-trip limit.slt
+")
+                },
+            },
+            Cmd {
+                command: &["test", "extended"],
+                expected: |actual| {
+                    insta::assert_snapshot!(actual, @r"
+cd /workspace && \
+DATAFUSION_SPILL_POOL_FUZZ_ITERATIONS=1000 \
+RUST_BACKTRACE=1 \
+cargo test \
+--profile ci \
+--exclude datafusion-examples \
+--exclude datafusion-benchmarks \
+--exclude datafusion-cli \
+--workspace \
+--lib \
+--tests \
+--bins \
+--features avro,json,backtrace,extended_tests,recursive_protection,parquet_encryption
+")
+                },
+            },
+            Cmd {
+                command: &["test", "hash-collisions"],
+                expected: |actual| {
+                    insta::assert_snapshot!(actual, @r"
+cd /workspace/datafusion && \
+RUST_BACKTRACE=1 \
+cargo test \
+--profile ci \
+--exclude datafusion-examples \
+--exclude datafusion-benchmarks \
+--exclude datafusion-sqllogictest \
+--exclude datafusion-cli \
+--workspace \
+--lib \
+--tests \
+--features=force_hash_collisions,avro
+")
+                },
+            },
+            Cmd {
+                command: &["test", "sqlite"],
+                expected: |actual| {
+                    insta::assert_snapshot!(actual, @r"
+cd /workspace && \
+cargo test \
+--features backtrace,parquet_encryption \
+--profile ci-optimized \
+--test sqllogictests \
+-- --include-sqlite
 ")
                 },
             },