Merge remote-tracking branch 'origin/main' into arrow-avro

# Conflicts:
#	Cargo.lock
#	Cargo.toml
#	datafusion/core/src/datasource/file_format/avro.rs
#	datafusion/datasource-avro/src/avro_to_arrow/schema.rs
#	datafusion/datasource-avro/src/source.rs

Author: getChan

.asf.yaml

@@ -62,6 +62,9 @@ github:
     branch-51:
       required_pull_request_reviews:
         required_approving_review_count: 1
+    branch-52:
+      required_pull_request_reviews:
+        required_approving_review_count: 1
   pull_requests:
     # enable updating head branches of pull requests
     allow_update_branch: true

.github/dependabot.yml

@@ -23,6 +23,7 @@ updates:
       interval: weekly
     target-branch: main
     labels: [auto-dependencies]
+    open-pull-requests-limit: 15
     ignore:
       # major version bumps of arrow* and parquet are handled manually
       - dependency-name: "arrow*"

.github/workflows/audit.yml

@@ -42,8 +42,10 @@ jobs:
     steps:
       - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8  # v6.0.1
       - name: Install cargo-audit
-        uses: taiki-e/install-action@d850aa816998e5cf15f67a78c7b933f2a5033f8a  # v2.63.3
+        uses: taiki-e/install-action@2e9d707ef49c9b094d45955b60c7e5c0dfedeb14  # v2.66.5
         with:
           tool: cargo-audit
       - name: Run audit check
+        # Note: you can ignore specific RUSTSEC issues using the `--ignore` flag ,for example:
+        # run: cargo audit --ignore RUSTSEC-2026-0001
         run: cargo audit

.github/workflows/dependencies.yml

@@ -66,4 +66,4 @@ jobs:
       - name: Install cargo-machete
         run: cargo install cargo-machete --version ^0.9 --locked
       - name: Detect unused dependencies
-        run: cargo machete --with-metadata
+        run: cargo machete --with-metadata

.github/workflows/dev.yml

@@ -44,7 +44,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8  # v6.0.1
-      - uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f  # v6.1.0
+      - uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238  # v6.2.0
         with:
           node-version: "20"
       - name: Prettier check

.github/workflows/docs.yaml

@@ -51,6 +51,12 @@ jobs:
           python3 -m venv venv
           source venv/bin/activate
           pip install -r docs/requirements.txt
+      - name: Install dependency graph tooling
+        run: |
+          set -x
+          sudo apt-get update
+          sudo apt-get install -y graphviz
+          cargo install cargo-depgraph --version ^1.6 --locked
 
       - name: Build docs
         run: |

.github/workflows/docs_pr.yaml

@@ -54,10 +54,15 @@ jobs:
           python3 -m venv venv
           source venv/bin/activate
           pip install -r docs/requirements.txt
+      - name: Install dependency graph tooling
+        run: |
+          set -x
+          sudo apt-get update
+          sudo apt-get install -y graphviz
+          cargo install cargo-depgraph --version ^1.6 --locked
       - name: Build docs html and check for warnings
         run: |
           set -x
           source venv/bin/activate
           cd docs
           ./build.sh # fails on errors
-

.github/workflows/rust.yml

@@ -421,7 +421,7 @@ jobs:
           sudo apt-get update -qq
           sudo apt-get install -y -qq clang
       - name: Setup wasm-pack
-        uses: taiki-e/install-action@d850aa816998e5cf15f67a78c7b933f2a5033f8a  # v2.63.3
+        uses: taiki-e/install-action@2e9d707ef49c9b094d45955b60c7e5c0dfedeb14  # v2.66.5
         with:
           tool: wasm-pack
       - name: Run tests with headless mode
@@ -695,7 +695,7 @@ jobs:
         uses: ./.github/actions/setup-builder
         with:
           rust-version: stable
-      - uses: actions/setup-node@395ad3262231945c25e8478fd5baf05154b1d79f  # v6.1.0
+      - uses: actions/setup-node@6044e13b5dc448c55e2357c09f80417699197238  # v6.2.0
         with:
           node-version: "20"
       - name: Check if configs.md has been modified
@@ -709,6 +709,23 @@ jobs:
           ./dev/update_function_docs.sh
           git diff --exit-code
 
+  examples-docs-check:
+    name: check example README is up-to-date
+    needs: linux-build-lib
+    runs-on: ubuntu-latest
+    container:
+      image: amd64/rust
+
+    steps:
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
+        with:
+          submodules: true
+          fetch-depth: 1
+
+      - name: Run examples docs check script
+        run: |
+          bash ci/scripts/check_examples_docs.sh
+
   # Verify MSRV for the crates which are directly used by other projects:
   # - datafusion
   # - datafusion-substrait
@@ -724,7 +741,7 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
       - name: Install cargo-msrv
-        uses: taiki-e/install-action@d850aa816998e5cf15f67a78c7b933f2a5033f8a  # v2.63.3
+        uses: taiki-e/install-action@2e9d707ef49c9b094d45955b60c7e5c0dfedeb14  # v2.66.5
         with:
           tool: cargo-msrv
 

NOTICE.txt

@@ -1,5 +1,5 @@
 Apache DataFusion
-Copyright 2019-2025 The Apache Software Foundation
+Copyright 2019-2026 The Apache Software Foundation
 
 This product includes software developed at
 The Apache Software Foundation (http://www.apache.org/).

benchmarks/Cargo.toml

@@ -40,6 +40,7 @@ mimalloc_extended = ["libmimalloc-sys/extended"]
 
 [dependencies]
 arrow = { workspace = true }
+clap = { version = "4.5.53", features = ["derive"] }
 datafusion = { workspace = true, default-features = true }
 datafusion-common = { workspace = true, default-features = true }
 env_logger = { workspace = true }
@@ -54,7 +55,6 @@ regex.workspace = true
 serde = { version = "1.0.228", features = ["derive"] }
 serde_json = { workspace = true }
 snmalloc-rs = { version = "0.3", optional = true }
-structopt = { version = "0.3", default-features = false }
 tokio = { workspace = true, features = ["rt-multi-thread", "parking_lot"] }
 tokio-util = { version = "0.7.17" }