[spiceai-48] -> Update to DataFusion 48

.asf.yaml

@@ -50,6 +50,9 @@ github:
     main:
       required_pull_request_reviews:
         required_approving_review_count: 1
+  pull_requests:
+    # enable updating head branches of pull requests
+    allow_update_branch: true
 
 # publishes the content of the `asf-site` branch to
 # https://datafusion.apache.org/

.github/workflows/docs_pr.yaml

@@ -34,26 +34,7 @@ on:
   workflow_dispatch:
 
 jobs:
-  # Run doc tests
-  linux-test-doc:
-    name: cargo doctest (amd64)
-    runs-on: ubuntu-latest
-    container:
-      image: amd64/rust
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          submodules: true
-          fetch-depth: 1
-      - name: Setup Rust toolchain
-        uses: ./.github/actions/setup-builder
-        with:
-          rust-version: stable
-      - name: Run doctests (embedded rust examples)
-        run: cargo test --doc --features avro,json
-      - name: Verify Working Directory Clean
-        run: git diff --exit-code
-
+
   # Test doc build
   linux-test-doc-build:
     name: Test doc build

.github/workflows/extended.yml

@@ -101,7 +101,17 @@ jobs:
       - name: Run tests (excluding doctests)
         env:
           RUST_BACKTRACE: 1
-        run: cargo test --profile ci --exclude datafusion-examples --exclude datafusion-benchmarks --workspace --lib --tests --bins --features avro,json,backtrace,extended_tests,recursive_protection
+        run: |
+          cargo test \
+            --profile ci \
+            --exclude datafusion-examples \
+            --exclude datafusion-benchmarks \
+            --exclude datafusion-cli \
+            --workspace \
+            --lib \
+            --tests \
+            --bins \
+            --features avro,json,backtrace,extended_tests,recursive_protection
       - name: Verify Working Directory Clean
         run: git diff --exit-code
       - name: Cleanup

.github/workflows/dev_pr.yml → .github/workflows/labeler.yml

@@ -49,7 +49,7 @@ jobs:
         uses: actions/[email protected]
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
-          configuration-path: .github/workflows/dev_pr/labeler.yml
+          configuration-path: .github/workflows/labeler/labeler-config.yml
           sync-labels: true
 
       # TODO: Enable this when eps1lon/actions-label-merge-conflict is available.

.github/workflows/dev_pr/labeler.yml → .github/workflows/labeler/labeler-config.yml

@@ -41,7 +41,7 @@ physical-expr:
 
 physical-plan:
   - changed-files:
-      - any-glob-to-any-file: [datafusion/physical-plan/**/*']
+      - any-glob-to-any-file: ['datafusion/physical-plan/**/*']
 
 
 catalog:
@@ -77,6 +77,10 @@ proto:
   - changed-files:
       - any-glob-to-any-file: ['datafusion/proto/**/*', 'datafusion/proto-common/**/*']
 
+spark:
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/spark/**/*']
+
 substrait:
 - changed-files:
   - any-glob-to-any-file: ['datafusion/substrait/**/*']

.github/workflows/rust.yml

@@ -401,8 +401,8 @@ jobs:
       - name: Run tests with headless mode
         working-directory: ./datafusion/wasmtest
         run: |
-          wasm-pack test --headless --firefox
-          wasm-pack test --headless --chrome --chromedriver $CHROMEWEBDRIVER/chromedriver
+          RUSTFLAGS='--cfg getrandom_backend="wasm_js"' wasm-pack test --headless --firefox
+          RUSTFLAGS='--cfg getrandom_backend="wasm_js"' wasm-pack test --headless --chrome --chromedriver $CHROMEWEBDRIVER/chromedriver
 
   # verify that the benchmark queries return the correct results
   verify-benchmark-results:
@@ -476,6 +476,28 @@ jobs:
           POSTGRES_HOST: postgres
           POSTGRES_PORT: ${{ job.services.postgres.ports[5432] }}
 
+  sqllogictest-substrait:
+    name: "Run sqllogictest in Substrait round-trip mode"
+    needs: linux-build-lib
+    runs-on: ubuntu-latest
+    container:
+      image: amd64/rust
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          submodules: true
+          fetch-depth: 1
+      - name: Setup Rust toolchain
+        uses: ./.github/actions/setup-builder
+        with:
+          rust-version: stable
+      - name: Run sqllogictest
+        # TODO: Right now several tests are failing in Substrait round-trip mode, so this
+        #  command cannot be run for all the .slt files. Run it for just one that works (limit.slt)
+        #  until most of the tickets in https://github.com/apache/datafusion/issues/16248 are addressed
+        #  and this command can be run without filters.
+        run: cargo test --test sqllogictests -- --substrait-round-trip limit.slt
+
   #  Temporarily commenting out the Windows flow, the reason is enormously slow running build
   #  Waiting for new Windows 2025 github runner
   #  Details: https://github.com/apache/datafusion/issues/13726
@@ -693,6 +715,11 @@ jobs:
           # If you encounter an error, run './dev/update_function_docs.sh' and commit
           ./dev/update_function_docs.sh
           git diff --exit-code
+      - name: Check if runtime_configs.md has been modified
+        run: |
+          # If you encounter an error, run './dev/update_runtime_config_docs.sh' and commit
+          ./dev/update_runtime_config_docs.sh
+          git diff --exit-code
 
   # Verify MSRV for the crates which are directly used by other projects:
   # - datafusion