Merge branch 'main' into add-example-arrow-binary-crate

.github/workflows/arrow.yml

@@ -146,11 +146,11 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
         with:
-          target: wasm32-unknown-unknown,wasm32-wasi
+          target: wasm32-unknown-unknown,wasm32-wasip1
       - name: Build wasm32-unknown-unknown
         run: cargo build -p arrow --no-default-features --features=json,csv,ipc,ffi --target wasm32-unknown-unknown
-      - name: Build wasm32-wasi
-        run: cargo build -p arrow --no-default-features --features=json,csv,ipc,ffi --target wasm32-wasi
+      - name: Build wasm32-wasip1
+        run: cargo build -p arrow --no-default-features --features=json,csv,ipc,ffi --target wasm32-wasip1
 
   clippy:
     name: Clippy

.github/workflows/integration.yml

@@ -65,8 +65,7 @@ jobs:
       ARROW_INTEGRATION_JAVA: ON
       ARROW_INTEGRATION_JS: ON
       ARCHERY_INTEGRATION_TARGET_IMPLEMENTATIONS: "rust"
-      # Disable nanoarrow integration, due to https://github.com/apache/arrow-rs/issues/5052
-      ARCHERY_INTEGRATION_WITH_NANOARROW: "0"
+      ARCHERY_INTEGRATION_WITH_NANOARROW: "1"
       # https://github.com/apache/arrow/pull/38403/files#r1371281630
       ARCHERY_INTEGRATION_WITH_RUST: "1"
       # These are necessary because the github runner overrides $HOME

.github/workflows/object_store.yml

@@ -54,6 +54,10 @@ jobs:
       # targets.
       - name: Run clippy with default features
         run: cargo clippy -- -D warnings
+      - name: Run clippy without default features
+        run: cargo clippy --no-default-features -- -D warnings
+      - name: Run clippy with fs features
+        run: cargo clippy --no-default-features --features fs -- -D warnings
       - name: Run clippy with aws feature
         run: cargo clippy --features aws -- -D warnings
       - name: Run clippy with gcp feature
@@ -200,11 +204,11 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
         with:
-          target: wasm32-unknown-unknown,wasm32-wasi
+          target: wasm32-unknown-unknown,wasm32-wasip1
       - name: Build wasm32-unknown-unknown
         run: cargo build --target wasm32-unknown-unknown
-      - name: Build wasm32-wasi
-        run: cargo build --target wasm32-wasi
+      - name: Build wasm32-wasip1
+        run: cargo build --target wasm32-wasip1
 
   windows:
     name: cargo test LocalFileSystem (win64)

.github/workflows/parquet.yml

@@ -97,6 +97,8 @@ jobs:
         run: cargo check -p parquet --no-default-features
       - name: Check compilation --no-default-features --features arrow
         run: cargo check -p parquet --no-default-features --features arrow
+      - name: Check compilation --no-default-features --features simdutf8
+        run: cargo check -p parquet --no-default-features --features simdutf8
       - name: Check compilation --no-default-features --all-features
         run: cargo check -p parquet --all-features
       - name: Check compilation --all-targets
@@ -123,13 +125,13 @@ jobs:
       - name: Setup Rust toolchain
         uses: ./.github/actions/setup-builder
         with:
-          target: wasm32-unknown-unknown,wasm32-wasi
+          target: wasm32-unknown-unknown,wasm32-wasip1
       - name: Install clang # Needed for zlib compilation
         run: apt-get update && apt-get install -y clang gcc-multilib
       - name: Build wasm32-unknown-unknown
         run: cargo build -p parquet --target wasm32-unknown-unknown
-      - name: Build wasm32-wasi
-        run: cargo build -p parquet --target wasm32-wasi
+      - name: Build wasm32-wasip1
+        run: cargo build -p parquet --target wasm32-wasip1
 
   pyspark-integration-test:
     name: PySpark Integration Test

.github/workflows/rust.yml

@@ -123,32 +123,18 @@ jobs:
         uses: ./.github/actions/setup-builder
       - name: Install cargo-msrv
         run: cargo install cargo-msrv
-      - name: Downgrade arrow dependencies
-        run: cargo update -p ahash --precise 0.8.7
-      - name: Check arrow
-        working-directory: arrow
-        run: |
-          # run `cd arrow; cargo msrv verify` to see problematic dependencies
-          cargo msrv verify --output-format=json
-      - name: Check parquet
-        working-directory: parquet
-        run: |
-          # run `cd parquet; cargo msrv verify` to see problematic dependencies
-          cargo msrv verify --output-format=json
-      - name: Check arrow-flight
-        working-directory: arrow-flight
-        run: |
-          # run `cd arrow-flight; cargo msrv verify` to see problematic dependencies
-          cargo msrv verify --output-format=json
       - name: Downgrade object_store dependencies
         working-directory: object_store
         # Necessary because tokio 1.30.0 updates MSRV to 1.63
         # and url 2.5.1, updates to 1.67
         run: |
           cargo update -p tokio --precise 1.29.1
           cargo update -p url --precise 2.5.0
-      - name: Check object_store
-        working-directory: object_store
+      - name: Check all packages
         run: |
-          # run `cd object_store; cargo msrv verify` to see problematic dependencies
-          cargo msrv verify --output-format=json
+          # run `cargo msrv verify --manifest-path "path/to/Cargo.toml"` to see problematic dependencies
+          find . -mindepth 2 -name Cargo.toml | while read -r dir
+          do
+            echo "Checking package '$dir'"
+            cargo msrv verify --manifest-path "$dir" --output-format=json || exit 1
+          done

Cargo.toml

@@ -74,7 +74,7 @@ include = [
     "Cargo.toml",
 ]
 edition = "2021"
-rust-version = "1.62"
+rust-version = "1.70"
 
 [workspace.dependencies]
 arrow = { version = "54.0.0", path = "./arrow", default-features = false }

README.md

@@ -90,6 +90,16 @@ Planned Release Schedule
 | Dec 2024         | `0.11.2` | Minor, NO breaking API changes          |
 | Feb 2025         | `0.12.0` | Major, potentially breaking API changes |
 
+### Guidelines for `panic` vs `Result`
+
+In general, use panics for bad states that are unreachable, unrecoverable or harmful.
+For those caused by invalid user input, however, we prefer to report that invalidity
+gracefully as an error result instead of panicking. In general, invalid input should result
+in an `Error` as soon as possible. It _is_ ok for code paths after validation to assume
+validation has already occurred and panic if not. See [this ticket] for more nuances.
+
+[this ticket]: https://github.com/apache/arrow-rs/issues/6737
+
 ### Deprecation Guidelines
 
 Minor releases may deprecate, but not remove APIs. Deprecating APIs allows