Merge branch 'main' into feature/array-position

Author: andygrove

.github/dependabot.yml

@@ -37,6 +37,22 @@ updates:
         patterns:
           - "prost*"
           - "pbjson*"
+      # Catch-all: group only minor/patch into a single PR,
+      # excluding deps we want always separate (and excluding arrow/parquet which have their own group)
+      all-other-cargo-deps:
+        applies-to: version-updates
+        patterns:
+          - "*"
+        exclude-patterns:
+          - "arrow*"
+          - "parquet"
+          - "object_store"
+          - "sqlparser"
+          - "prost*"
+          - "pbjson*"
+        update-types:
+          - "minor"
+          - "patch"
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:

.github/workflows/iceberg_spark_test.yml

@@ -26,6 +26,7 @@ on:
     branches:
       - main
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"
@@ -34,6 +35,7 @@ on:
       - "spark/src/test/scala/org/apache/spark/sql/benchmark/**"
   pull_request:
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"

.github/workflows/pr_build_linux.yml

@@ -26,6 +26,7 @@ on:
     branches:
       - main
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"
@@ -34,6 +35,7 @@ on:
       - "spark/src/test/scala/org/apache/spark/sql/benchmark/**"
   pull_request:
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"
@@ -67,12 +69,12 @@ jobs:
   build-native:
     needs: lint
     name: Build Native Library
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a,cpu=8,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
     steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
       - uses: actions/checkout@v6
-
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
         with:
@@ -120,10 +122,12 @@ jobs:
   linux-test-rust:
     needs: lint
     name: ubuntu-latest/rust-test
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
     steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -161,7 +165,6 @@ jobs:
     needs: build-native
     strategy:
       matrix:
-        os: [ubuntu-latest]
         # the goal with these profiles is to get coverage of all Java, Scala, and Spark
         # versions without testing all possible combinations, which would be overkill
         profile:
@@ -273,14 +276,15 @@ jobs:
             value: |
               org.apache.spark.sql.CometToPrettyStringSuite
       fail-fast: false
-    name: ${{ matrix.os }}/${{ matrix.profile.name }}/${{ matrix.profile.scan_impl }} [${{ matrix.suite.name }}]
-    runs-on: ${{ matrix.os }}
+    name: ${{ matrix.profile.name }}/${{ matrix.profile.scan_impl }} [${{ matrix.suite.name }}]
+    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
       env:
         JAVA_TOOL_OPTIONS: ${{ matrix.profile.java_version == '17' && '--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@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -310,7 +314,7 @@ jobs:
       - name: Java test steps
         uses: ./.github/actions/java-test
         with:
-          artifact_name: ${{ matrix.os }}-${{ matrix.profile.name }}-${{ matrix.suite.name }}-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}
+          artifact_name: ${{ matrix.profile.name }}-${{ matrix.suite.name }}-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}
           suites: ${{ matrix.suite.name == 'sql' && matrix.profile.name == 'Spark 3.4, JDK 11, Scala 2.12' && '' || matrix.suite.value }}
           maven_opts: ${{ matrix.profile.maven_opts }}
           scan_impl: ${{ matrix.profile.scan_impl }}
@@ -321,10 +325,12 @@ jobs:
   verify-benchmark-results-tpch:
     needs: build-native
     name: Verify TPC-H Results
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
     steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain
@@ -373,14 +379,16 @@ jobs:
   verify-benchmark-results-tpcds:
     needs: build-native
     name: Verify TPC-DS Results (${{ matrix.join }})
-    runs-on: ubuntu-latest
+    runs-on: ${{ github.repository_owner == 'apache' && format('runs-on={0},family=m8a,cpu=16,image=ubuntu24-full-x64,extras=s3-cache,disk=large,tag=datafusion-comet', github.run_id) || 'ubuntu-latest' }}
     container:
       image: amd64/rust
     strategy:
       matrix:
         join: [sort_merge, broadcast, hash]
       fail-fast: false
     steps:
+      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e  # v2.0.3
+
       - uses: actions/checkout@v6
 
       - name: Setup Rust & Java toolchain

.github/workflows/pr_build_macos.yml

@@ -26,6 +26,7 @@ on:
     branches:
       - main
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"
@@ -34,6 +35,7 @@ on:
       - "spark/src/test/scala/org/apache/spark/sql/benchmark/**"
   pull_request:
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"

.github/workflows/spark_sql_test.yml

@@ -26,6 +26,7 @@ on:
     branches:
       - main
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"
@@ -34,6 +35,7 @@ on:
       - "spark/src/test/scala/org/apache/spark/sql/benchmark/**"
   pull_request:
     paths-ignore:
+      - "benchmarks/**"
       - "doc/**"
       - "docs/**"
       - "**.md"

.github/workflows/stale.yml

@@ -27,7 +27,7 @@ jobs:
       issues: write
       pull-requests: write
     steps:
-      - uses: actions/stale@997185467fa4f803885201cee163a9f38240193d  # v10.1.1
+      - uses: actions/stale@b5d41d4e1d5dceea10e7104786b73624c18a190f  # v10.2.0
         with:
           stale-pr-message: "Thank you for your contribution. Unfortunately, this pull request is stale because it has been open 60 days with no activity. Please remove the stale label or comment or this will be closed in 7 days."
           days-before-pr-stale: 60

.gitignore

@@ -17,8 +17,10 @@ filtered_rat.txt
 dev/dist
 apache-rat-*.jar
 venv
+.venv
 dev/release/comet-rm/workdir
 spark/benchmarks
 .DS_Store
 comet-event-trace.json
 __pycache__
+output