Merge remote-tracking branch 'apache/main' into worktree-pr-4239-regexp-default

Author: andygrove

.dockerignore

@@ -10,7 +10,6 @@ metastore_db
 target
 common/target
 spark-integration/target
-fuzz-testing/target
 spark/target
 native/target
 core/target

.github/workflows/codeql.yml

@@ -36,7 +36,7 @@ permissions:
 jobs:
   analyze:
     name: Analyze Actions
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     permissions:
       contents: read
       security-events: write

.github/workflows/docker-publish.yml

@@ -36,7 +36,6 @@ on:
       - "spark/src/test/**"
       - "common/src/test/**"
       - "spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
-      - "fuzz-testing/**"
       - "spark-integration/**"
   pull_request:
     paths-ignore:
@@ -50,7 +49,6 @@ on:
       - "spark/src/test/**"
       - "common/src/test/**"
       - "spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
-      - "fuzz-testing/**"
       - "spark-integration/**"
   # manual trigger
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow

.github/workflows/iceberg_spark_test.yml

@@ -51,7 +51,7 @@ on:
 jobs:
   miri:
     name: "Miri"
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/checkout@v6
       - name: Install Build Dependencies

.github/workflows/miri.yml

@@ -46,7 +46,7 @@ env:
 jobs:
   benchmark-check:
     name: Benchmark Compile & Lint Check
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     steps:

.github/workflows/pr_benchmark_check.yml

@@ -63,7 +63,7 @@ jobs:
   # Fast lint check - gates all other jobs
   lint:
     name: Lint
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     steps:
@@ -77,7 +77,7 @@ jobs:
   lint-java:
     needs: lint
     name: Lint Java (${{ matrix.profile.name }})
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
       env:
@@ -103,7 +103,6 @@ jobs:
           # spark-4.2 profiles.
       fail-fast: false
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -154,7 +153,7 @@ jobs:
   build-spark-4-1:
     needs: lint
     name: Build Spark 4.1, JDK 17
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     steps:
@@ -183,11 +182,10 @@ jobs:
   build-native:
     needs: lint
     name: Build Native Library
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=8,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
       - uses: actions/checkout@v6
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
@@ -236,12 +234,10 @@ jobs:
   linux-test-rust:
     needs: lint
     name: ubuntu-latest/rust-test
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -292,11 +288,6 @@ jobs:
             maven_opts: "-Pspark-3.5 -Pscala-2.13"
             scan_impl: "native_iceberg_compat"
 
-          - name: "Spark 4.0, JDK 17"
-            java_version: "17"
-            maven_opts: "-Pspark-4.0"
-            scan_impl: "auto"
-
           - name: "Spark 4.0, JDK 21"
             java_version: "21"
             maven_opts: "-Pspark-4.0"
@@ -342,6 +333,7 @@ jobs:
               org.apache.spark.sql.comet.ParquetEncryptionITCase
               org.apache.comet.exec.CometNativeReaderSuite
               org.apache.comet.CometIcebergNativeSuite
+              org.apache.comet.CometIcebergRewriteActionSuite
               org.apache.comet.iceberg.IcebergReflectionSuite
           - name: "csv"
             value: |
@@ -401,14 +393,13 @@ jobs:
               org.apache.spark.sql.CometCollationSuite
       fail-fast: false
     name: ${{ matrix.profile.name }}/${{ matrix.profile.scan_impl }} [${{ matrix.suite.name }}]
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
       env:
         JAVA_TOOL_OPTIONS: ${{ (matrix.profile.java_version == '17' || matrix.profile.java_version == '21') && '--add-exports=java.base/sun.nio.ch=ALL-UNNAMED --add-exports=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED' || '' }}
 
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -449,14 +440,12 @@ jobs:
   verify-benchmark-results-tpch:
     needs: build-native
     name: Verify TPC-H Results
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     env:
       JAVA_TOOL_OPTIONS: --add-exports=java.base/sun.nio.ch=ALL-UNNAMED --add-exports=java.base/sun.util.calendar=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.lang.invoke=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.concurrent.atomic=ALL-UNNAMED --add-opens=java.base/jdk.internal.ref=ALL-UNNAMED --add-opens=java.base/sun.nio.ch=ALL-UNNAMED --add-opens=java.base/sun.nio.cs=ALL-UNNAMED --add-opens=java.base/sun.security.action=ALL-UNNAMED --add-opens=java.base/sun.util.calendar=ALL-UNNAMED
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -505,7 +494,7 @@ jobs:
   verify-benchmark-results-tpcds:
     needs: build-native
     name: Verify TPC-DS Results (${{ matrix.join }})
-    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a+m7a+c8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
+    runs-on: ubuntu-24.04
     container:
       image: amd64/rust
     env:
@@ -515,8 +504,6 @@ jobs:
         join: [sort_merge, broadcast, hash]
       fail-fast: false
     steps:
-      - uses: runs-on/action@742bf56072eb4845a0f94b3394673e4903c90ff0  # v2.1.0
-
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain

.github/workflows/pr_build_linux.yml

@@ -181,6 +181,7 @@ jobs:
               org.apache.spark.sql.comet.ParquetEncryptionITCase
               org.apache.comet.exec.CometNativeReaderSuite
               org.apache.comet.CometIcebergNativeSuite
+              org.apache.comet.CometIcebergRewriteActionSuite
               org.apache.comet.iceberg.IcebergReflectionSuite
           - name: "csv"
             value: |

.github/workflows/pr_build_macos.yml

@@ -28,7 +28,7 @@ on:
 
 jobs:
   prettier-check:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/checkout@v6
 

.github/workflows/pr_markdown_format.yml

@@ -30,7 +30,7 @@ on:
 
 jobs:
   check-missing-suites:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - uses: actions/checkout@v6
       - name: Check Missing Suites