Merge remote-tracking branch 'upstream/main' into feat/try_parse_url

Author: rafafrdz

.asf.yaml

@@ -50,8 +50,36 @@ github:
     main:
       required_pull_request_reviews:
         required_approving_review_count: 1
+      required_status_checks:
+        contexts:
+          - "Check License Header"
+          - "cargo doc"
+          - "build and run with wasm-pack"
+          - "linux build test"
+          - "cargo test (macos-aarch64)"
+          - "Verify Vendored Code"
+          - "Check cargo fmt"
+          - "Verify MSRV (Min Supported Rust Version)"
+          - "cargo check datafusion-common features"
+          - "cargo check datafusion-substrait features"
+          - "cargo check datafusion-proto features"
+          - "cargo check datafusion features"
+          - "cargo check datafusion-functions features"
+          - "cargo test (amd64)"
+          - "cargo examples (amd64)"
+          - "cargo test doc (amd64)"
+          - "verify benchmark results (amd64)"
+          - "Run sqllogictest with Postgres runner"
+          - "Run sqllogictest in Substrait round-trip mode"
+          - "cargo test pyarrow (amd64)"
+          - "clippy"
+          - "check Cargo.toml formatting"
+          - "Use prettier to check formatting of documents"
+          - "check-files"
+          - "cargo test datafusion-cli (amd64)"
+          - "check configs.md and ***_functions.md is up-to-date"
     # needs to be updated as part of the release process
-    # Github doesn't support wildcard branch protection rules, only exact branch names
+    # .asf.yaml doesn't support wildcard branch protection rules, only exact branch names
     # https://github.com/apache/infrastructure-asfyaml?tab=readme-ov-file#branch-protection
     # Keeping set of protected branches for future releases
     # Meanwhile creating a prerelease script that will update the branch protection names
@@ -122,6 +150,7 @@ github:
   pull_requests:
     # enable updating head branches of pull requests
     allow_update_branch: true
+    allow_auto_merge: true
 
 # publishes the content of the `asf-site` branch to
 # https://datafusion.apache.org/

.github/workflows/audit.yml

@@ -23,16 +23,18 @@ concurrency:
 
 on:
   push:
+    branches:
+      - main
     paths:
       - "**/Cargo.toml"
       - "**/Cargo.lock"
-    branches:
-      - main
 
   pull_request:
     paths:
       - "**/Cargo.toml"
       - "**/Cargo.lock"
+  
+  merge_group:
 
 jobs:
   security_audit:

.github/workflows/dependencies.yml

@@ -23,13 +23,16 @@ concurrency:
 
 on:
   push:
+    branches-ignore:
+      - 'gh-readonly-queue/**'
     paths:
       - "**/Cargo.toml"
       - "**/Cargo.lock"
   pull_request:
     paths:
       - "**/Cargo.toml"
       - "**/Cargo.lock"
+  merge_group:
   # manual trigger
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow
   workflow_dispatch:

.github/workflows/dev.yml

@@ -16,7 +16,12 @@
 # under the License.
 
 name: Dev
-on: [push, pull_request]
+on:
+  push:
+    branches-ignore:
+      - 'gh-readonly-queue/**'
+  pull_request:
+  merge_group:
 
 concurrency:
   group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }}

.github/workflows/large_files.yml

@@ -23,6 +23,7 @@ concurrency:
 
 on:
   pull_request:
+  merge_group:
 
 jobs:
   check-files:
@@ -38,7 +39,16 @@ jobs:
           MAX_FILE_SIZE_BYTES: 1048576
         shell: bash
         run: |
-          git rev-list --objects ${{ github.event.pull_request.base.sha }}..${{ github.event.pull_request.head.sha }} \
+          if [ "${{ github.event_name }}" = "merge_group" ]; then
+            # For merge queue, compare against the base branch
+            base_sha="${{ github.event.merge_group.base_sha }}"
+            head_sha="${{ github.event.merge_group.head_sha }}"
+          else
+            # For pull requests
+            base_sha="${{ github.event.pull_request.base.sha }}"
+            head_sha="${{ github.event.pull_request.head.sha }}"
+          fi
+          git rev-list --objects ${base_sha}..${head_sha} \
             > pull-request-objects.txt
           exit_code=0
           while read -r id path; do

.github/workflows/rust.yml

@@ -23,6 +23,8 @@ concurrency:
 
 on:
   push:
+    branches-ignore:
+      - 'gh-readonly-queue/**'
     paths-ignore:
       - "docs/**"
       - "**.md"
@@ -34,6 +36,7 @@ on:
       - "**.md"
       - ".github/ISSUE_TEMPLATE/**"
       - ".github/pull_request_template.md"
+  merge_group:
   # manual trigger
   # https://docs.github.com/en/actions/managing-workflow-runs/manually-running-a-workflow
   workflow_dispatch:

Cargo.lock

@@ -29,7 +29,7 @@ cargo test
 
 ## Running Storage Integration Tests
 
-By default, storage integration tests are not run. These test use the `testcontainers` crate to start up a local MinIO server using docker on port 9000.
+By default, storage integration tests are not run. These tests use the `testcontainers` crate to start up a local MinIO server using Docker on port 9000.
 
 To run them you will need to set `TEST_STORAGE_INTEGRATION`:
 
@@ -49,6 +49,6 @@ If you see an error mentioning "failed to load IMDS session token" such as
 > ---- object_storage::tests::s3_object_store_builder_resolves_region_when_none_provided stdout ----
 > Error: ObjectStore(Generic { store: "S3", source: "Error getting credentials from provider: an error occurred while loading credentials: failed to load IMDS session token" })
 
-You my need to disable trying to fetch S3 credentials from the environment using the `AWS_EC2_METADATA_DISABLED`, for example:
+You may need to disable trying to fetch S3 credentials from the environment using the `AWS_EC2_METADATA_DISABLED`, for example:
 
 > $ AWS_EC2_METADATA_DISABLED=true TEST_STORAGE_INTEGRATION=1 cargo test