Merge remote-tracking branch 'upstream/main' into fix-flaot-round

Author: kazuyukitanimura

.claude/skills/bug-triage/SKILL.md

@@ -65,8 +65,7 @@ For each issue, review the title and body and determine:
 2. **Area labels** (zero or more): from the area table in the guide
    (`area:writer`, `area:shuffle`, `area:aggregation`, `area:scan`,
    `area:expressions`, `area:ffi`, `area:ci`) plus the pre-existing area
-   indicators (`native_datafusion`, `native_iceberg_compat`, `spark 4`,
-   `spark sql tests`).
+   indicators (`spark 4`, `spark sql tests`).
 3. **Escalation note**: if the issue matches an escalation trigger from the
    guide (e.g., a `priority:high` crash that may also produce wrong results),
    note it in the summary.

.claude/skills/wire-datafusion-function/SKILL.md

@@ -29,10 +29,6 @@ inputs:
     description: 'Maven options passed to the mvn command'
     required: false
     default: ''
-  scan_impl:
-    description: 'The default Parquet scan implementation'
-    required: false
-    default: 'auto'
   upload-test-reports:
     description: 'Whether to upload test results including coverage to GitHub'
     required: false
@@ -72,7 +68,6 @@ runs:
       shell: bash
       if: ${{ inputs.suites == '' }}
       env:
-        COMET_PARQUET_SCAN_IMPL: ${{ inputs.scan_impl }}
         SPARK_LOCAL_HOSTNAME: "localhost"
         SPARK_LOCAL_IP: "127.0.0.1"
       run: |
@@ -81,7 +76,6 @@ runs:
       shell: bash
       if: ${{ inputs.suites != '' }}
       env:
-        COMET_PARQUET_SCAN_IMPL: ${{ inputs.scan_impl }}
         SPARK_LOCAL_HOSTNAME: "localhost"
         SPARK_LOCAL_IP: "127.0.0.1"
       run: |

.github/actions/java-test/action.yaml

@@ -51,7 +51,7 @@ runs:
         path: |
           ~/.m2/repository
           /root/.m2/repository
-        key: ${{ runner.os }}-spark-sql-${{ hashFiles('spark/**/pom.xml', 'common/**/pom.xml') }}
+        key: ${{ runner.os }}-spark-sql-${{ hashFiles('common/**/pom.xml', 'spark/**/pom.xml') }}
         restore-keys: |
           ${{ runner.os }}-spark-sql-
 

.github/actions/setup-spark-builder/action.yaml

@@ -49,11 +49,11 @@ jobs:
         persist-credentials: false
 
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4
+      uses: github/codeql-action/init@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4
       with:
         languages: actions
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4
+      uses: github/codeql-action/analyze@9e0d7b8d25671d64c341c19c0152d693099fb5ba # v4
       with:
         category: "/language:actions"

.github/workflows/codeql.yml

@@ -25,29 +25,41 @@ on:
   push:
     branches:
       - main
-    paths-ignore:
-      - "benchmarks/**"
-      - "doc/**"
-      - "docs/**"
-      - "**.md"
-      - "native/core/benches/**"
-      - "native/spark-expr/benches/**"
-      - "spark/src/test/**"
-      - "common/src/test/**"
-      - "spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
-      - "spark-integration/**"
+    paths:
+      - "native/**/src/**"
+      - "native/**/Cargo.toml"
+      - "native/Cargo.lock"
+      - "!native/hdfs/**"
+      - "!native/fs-hdfs/**"
+      - "common/src/main/**"
+      - "common/pom.xml"
+      - "spark/src/main/**"
+      - "!spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
+      - "spark/pom.xml"
+      - "dev/diffs/iceberg/**"
+      - "pom.xml"
+      - "rust-toolchain.toml"
+      - ".github/workflows/iceberg_spark_test.yml"
+      - ".github/actions/setup-builder/**"
+      - ".github/actions/setup-iceberg-builder/**"
   pull_request:
-    paths-ignore:
-      - "benchmarks/**"
-      - "doc/**"
-      - "docs/**"
-      - "**.md"
-      - "native/core/benches/**"
-      - "native/spark-expr/benches/**"
-      - "spark/src/test/**"
-      - "common/src/test/**"
-      - "spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
-      - "spark-integration/**"
+    paths:
+      - "native/**/src/**"
+      - "native/**/Cargo.toml"
+      - "native/Cargo.lock"
+      - "!native/hdfs/**"
+      - "!native/fs-hdfs/**"
+      - "common/src/main/**"
+      - "common/pom.xml"
+      - "spark/src/main/**"
+      - "!spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
+      - "spark/pom.xml"
+      - "dev/diffs/iceberg/**"
+      - "pom.xml"
+      - "rust-toolchain.toml"
+      - ".github/workflows/iceberg_spark_test.yml"
+      - ".github/actions/setup-builder/**"
+      - ".github/actions/setup-iceberg-builder/**"
   # manual trigger
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow
   workflow_dispatch:

.github/workflows/iceberg_spark_test.yml

@@ -22,26 +22,9 @@ concurrency:
   cancel-in-progress: true
 
 on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - "doc/**"
-      - "docs/**"
-      - "**.md"
-      - "native/core/benches/**"
-      - "native/spark-expr/benches/**"
-      - "spark/src/test/scala/org/apache/spark/sql/benchmark/**"
-      - "spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
-  pull_request:
-    paths-ignore:
-      - "doc/**"
-      - "docs/**"
-      - "**.md"
-      - "native/core/benches/**"
-      - "native/spark-expr/benches/**"
-      - "spark/src/test/scala/org/apache/spark/sql/benchmark/**"
-      - "spark/src/main/scala/org/apache/comet/GenerateDocs.scala"
+  # nightly safety check
+  schedule:
+    - cron: '0 4 * * *'
   # manual trigger
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow
   workflow_dispatch: