Merge branch 'main' of https://github.com/apache/datafusion into lambda_and_array_transform

Author: gstvg

.asf.yaml

@@ -55,6 +55,7 @@ github:
         contexts:
           - "Check License Header"
           - "Use prettier to check formatting of documents"
+          - "Check Markdown Links"
           - "Validate required_status_checks in .asf.yaml"
           - "Spell Check with Typos"
     # needs to be updated as part of the release process

.github/workflows/audit.yml

@@ -33,9 +33,12 @@ on:
     paths:
       - "**/Cargo.toml"
       - "**/Cargo.lock"
-  
+
   merge_group:
 
+permissions:
+  contents: read
+
 jobs:
   security_audit:
     runs-on: ubuntu-latest

.github/workflows/dependencies.yml

@@ -37,6 +37,9 @@ on:
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   depcheck:
     name: circular dependency check

.github/workflows/dev.yml

@@ -23,6 +23,9 @@ on:
   pull_request:
   merge_group:
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }}
   cancel-in-progress: true
@@ -51,6 +54,22 @@ jobs:
       # if you encounter error, see instructions inside the script
         run: ci/scripts/doc_prettier_check.sh
 
+  markdown-link-check:
+    name: Check Markdown Links
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
+      - name: Load tool versions
+        run: |
+          source ci/scripts/utils/tool_versions.sh
+          echo "LYCHEE_VERSION=${LYCHEE_VERSION}" >> "$GITHUB_ENV"
+      - name: Install lychee
+        uses: taiki-e/install-action@055f5df8c3f65ea01cd41e9dc855becd88953486  # v2.75.18
+        with:
+          tool: lychee@${{ env.LYCHEE_VERSION }}
+      - name: Run markdown link check
+        run: bash ci/scripts/markdown_link_check.sh
+
   asf-yaml-check:
     name: Validate required_status_checks in .asf.yaml
     runs-on: ubuntu-latest
@@ -66,7 +85,7 @@ jobs:
       - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           persist-credentials: false
-      # Version fixed on purpose. It uses heuristics to detect typos, so upgrading 
+      # Version fixed on purpose. It uses heuristics to detect typos, so upgrading
       # it may cause checks to fail more often.
       # We can upgrade it manually once a while.
       - name: Install typos-cli

.github/workflows/docs_pr.yaml

@@ -33,8 +33,10 @@ on:
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
-  
   # Test doc build
   linux-test-doc-build:
     name: Test doc build

.github/workflows/large_files.yml

@@ -25,6 +25,9 @@ on:
   pull_request:
   merge_group:
 
+permissions:
+  contents: read
+
 jobs:
   check-files:
     runs-on: ubuntu-slim
@@ -34,9 +37,9 @@ jobs:
           fetch-depth: 0
       - name: Check size of new Git objects
         env:
-          # 1 MB ought to be enough for anybody.
+          # 1.5 MB ought to be enough for anybody.
           # TODO in case we may want to consciously commit a bigger file to the repo without using Git LFS we may disable the check e.g. with a label
-          MAX_FILE_SIZE_BYTES: 1048576
+          MAX_FILE_SIZE_BYTES: 1572864
         shell: bash
         run: |
           if [ "${{ github.event_name }}" = "merge_group" ]; then

.github/workflows/stale.yml

@@ -37,3 +37,4 @@ jobs:
           days-before-issue-stale: -1
           days-before-issue-close: -1
           repo-token: ${{ secrets.GITHUB_TOKEN }}
+          operations-per-run: 150