Merge branch 'main' into zip-string-view-improv

Author: alamb

.github/pull_request_template.md

@@ -1,28 +1,38 @@
 # Which issue does this PR close?
 
+<!--
 We generally require a GitHub issue to be filed for all bug fixes and enhancements and this helps us generate change logs for our releases. You can link an issue to this PR using the GitHub syntax.
+-->
 
 - Closes #NNN.
 
 # Rationale for this change
 
+<!--
 Why are you proposing this change? If this is already explained clearly in the issue then this section is not needed.
 Explaining clearly why changes are proposed helps reviewers understand your changes and offer better suggestions for fixes.
+-->
 
 # What changes are included in this PR?
 
+<!--
 There is no need to duplicate the description in the issue here but it is sometimes worth providing a summary of the individual changes in this PR.
+-->
 
 # Are these changes tested?
 
+<!--
 We typically require tests for all PRs in order to:
 1. Prevent the code from being accidentally broken by subsequent changes
 2. Serve as another way to document the expected behavior of the code
 
 If tests are not included in your PR, please explain why (for example, are they covered by existing tests)?
+-->
 
 # Are there any user-facing changes?
 
+<!--
 If there are user-facing changes then we may require documentation to be updated before approving the PR.
 
 If there are any breaking changes to public APIs, please call them out.
+-->

.github/workflows/docs.yml

@@ -71,7 +71,7 @@ jobs:
     steps:
       - uses: actions/checkout@v6
       - name: Download crate docs
-        uses: actions/download-artifact@v6
+        uses: actions/download-artifact@v7
         with:
           name: crate-docs
           path: website/build

.github/workflows/integration.yml

@@ -78,58 +78,112 @@ jobs:
       run:
         shell: bash
     steps:
+      - name: Monitor disk usage - Initial
+        run: |
+          echo "=== Initial Disk Usage ==="
+          df -h /
+          echo ""
+
+      - name: Remove unnecessary preinstalled software
+        run: |
+          echo "=== Cleaning up host disk space ==="
+          echo "Disk space before cleanup:"
+          df -h /
+
+          # Clean apt cache
+          apt-get clean || true
+
+          # Remove GitHub Actions tool cache
+          rm -rf /__t/* || true
+
+          # Remove large packages from host filesystem (mounted at /host/)
+          rm -rf /host/usr/share/dotnet || true
+          rm -rf /host/usr/local/lib/android || true
+          rm -rf /host/usr/local/.ghcup || true
+          rm -rf /host/opt/hostedtoolcache/CodeQL || true
+
+          echo ""
+          echo "Disk space after cleanup:"
+          df -h /
+          echo ""
+
       # This is necessary so that actions/checkout can find git
       - name: Export conda path
         run: echo "/opt/conda/envs/arrow/bin" >> $GITHUB_PATH
       # This is necessary so that Rust can find cargo
       - name: Export cargo path
         run: echo "/root/.cargo/bin" >> $GITHUB_PATH
-      - name: Check rustup
-        run: which rustup
-      - name: Check cmake
-        run: which cmake
+
+      # Checkout repos (using shallow clones with fetch-depth: 1)
       - name: Checkout Arrow
         uses: actions/checkout@v6
         with:
           repository: apache/arrow
           submodules: true
-          fetch-depth: 0
+          fetch-depth: 1
       - name: Checkout Arrow Rust
         uses: actions/checkout@v6
         with:
           path: rust
           submodules: true
-          fetch-depth: 0
+          fetch-depth: 1
       - name: Checkout Arrow .NET
         uses: actions/checkout@v6
         with:
           repository: apache/arrow-dotnet
           path: dotnet
+          fetch-depth: 1
       - name: Checkout Arrow Go
         uses: actions/checkout@v6
         with:
           repository: apache/arrow-go
           path: go
+          fetch-depth: 1
       - name: Checkout Arrow Java
         uses: actions/checkout@v6
         with:
           repository: apache/arrow-java
           path: java
+          fetch-depth: 1
       - name: Checkout Arrow JavaScript
         uses: actions/checkout@v6
         with:
           repository: apache/arrow-js
           path: js
+          fetch-depth: 1
       - name: Checkout Arrow nanoarrow
         uses: actions/checkout@v6
         with:
           repository: apache/arrow-nanoarrow
           path: nanoarrow
+          fetch-depth: 1
+
+      - name: Monitor disk usage - After checkouts
+        run: |
+          echo "=== After Checkouts ==="
+          df -h /
+          echo ""
+
       - name: Build
         run: conda run --no-capture-output ci/scripts/integration_arrow_build.sh $PWD /build
+
+      - name: Monitor disk usage - After build
+        if: always()
+        run: |
+          echo "=== After Build ==="
+          df -h /
+          echo ""
+
       - name: Run
         run: conda run --no-capture-output ci/scripts/integration_arrow.sh $PWD /build
 
+      - name: Monitor disk usage - After tests
+        if: always()
+        run: |
+          echo "=== After Tests ==="
+          df -h /
+          echo ""
+
   # test FFI against the C-Data interface exposed by pyarrow
   pyarrow-integration-test:
     name: Pyarrow C Data Interface

arrow-array/benches/union_array.rs

@@ -54,10 +54,10 @@ fn criterion_benchmark(c: &mut Criterion) {
                 |b| {
                     let type_ids = 0..with_nulls+without_nulls;
 
-                    let fields = UnionFields::new(
+                    let fields = UnionFields::try_new(
                         type_ids.clone(),
                         type_ids.clone().map(|i| Field::new(format!("f{i}"), DataType::Int32, true)),
-                    );
+                    ).unwrap();
 
                     let array = UnionArray::try_new(
                         fields,

arrow-array/src/array/boolean_array.rs

@@ -829,4 +829,32 @@ mod tests {
         assert_eq!(values.values(), &[0b1000_0000]);
         assert!(nulls.is_none());
     }
+
+    #[test]
+    fn test_new_null_array() {
+        let arr = BooleanArray::new_null(5);
+
+        assert_eq!(arr.len(), 5);
+        assert_eq!(arr.null_count(), 5);
+        assert_eq!(arr.true_count(), 0);
+        assert_eq!(arr.false_count(), 0);
+
+        for i in 0..5 {
+            assert!(arr.is_null(i));
+            assert!(!arr.is_valid(i));
+        }
+    }
+
+    #[test]
+    fn test_slice_with_nulls() {
+        let arr = BooleanArray::from(vec![Some(true), None, Some(false)]);
+        let sliced = arr.slice(1, 2);
+
+        assert_eq!(sliced.len(), 2);
+        assert_eq!(sliced.null_count(), 1);
+
+        assert!(sliced.is_null(0));
+        assert!(sliced.is_valid(1));
+        assert!(!sliced.value(1));
+    }
 }

arrow-array/src/array/list_view_array.rs

@@ -26,8 +26,8 @@ use crate::array::{make_array, print_long_array};
 use crate::builder::{GenericListViewBuilder, PrimitiveBuilder};
 use crate::iterator::GenericListViewArrayIter;
 use crate::{
-    Array, ArrayAccessor, ArrayRef, ArrowPrimitiveType, FixedSizeListArray, OffsetSizeTrait,
-    new_empty_array,
+    Array, ArrayAccessor, ArrayRef, ArrowPrimitiveType, FixedSizeListArray, GenericListArray,
+    OffsetSizeTrait, new_empty_array,
 };
 
 /// A [`GenericListViewArray`] of variable size lists, storing offsets as `i32`.
@@ -498,6 +498,29 @@ impl<OffsetSize: OffsetSizeTrait> std::fmt::Debug for GenericListViewArray<Offse
     }
 }
 
+impl<OffsetSize: OffsetSizeTrait> From<GenericListArray<OffsetSize>>
+    for GenericListViewArray<OffsetSize>
+{
+    fn from(value: GenericListArray<OffsetSize>) -> Self {
+        let (field, offsets, values, nulls) = value.into_parts();
+        let len = offsets.len() - 1;
+        let mut sizes = Vec::with_capacity(len);
+        let mut view_offsets = Vec::with_capacity(len);
+        for (i, offset) in offsets.iter().enumerate().take(len) {
+            view_offsets.push(*offset);
+            sizes.push(offsets[i + 1] - offsets[i]);
+        }
+
+        Self::new(
+            field,
+            ScalarBuffer::from(view_offsets),
+            ScalarBuffer::from(sizes),
+            values,
+            nulls,
+        )
+    }
+}
+
 impl<OffsetSize: OffsetSizeTrait> From<GenericListViewArray<OffsetSize>> for ArrayData {
     fn from(array: GenericListViewArray<OffsetSize>) -> Self {
         let len = array.len();

arrow-array/src/array/mod.rs

@@ -620,10 +620,11 @@ impl<'a> StringArrayType<'a> for &'a StringViewArray {
     }
 }
 
-/// A trait for Arrow String Arrays, currently three types are supported:
+/// A trait for Arrow Binary Arrays, currently four types are supported:
 /// - `BinaryArray`
 /// - `LargeBinaryArray`
 /// - `BinaryViewArray`
+/// - `FixedSizeBinaryArray`
 ///
 /// This trait helps to abstract over the different types of binary arrays
 /// so that we don't need to duplicate the implementation for each type.
@@ -642,6 +643,11 @@ impl<'a> BinaryArrayType<'a> for &'a BinaryViewArray {
         BinaryViewArray::iter(self)
     }
 }
+impl<'a> BinaryArrayType<'a> for &'a FixedSizeBinaryArray {
+    fn iter(&self) -> ArrayIter<Self> {
+        FixedSizeBinaryArray::iter(self)
+    }
+}
 
 impl PartialEq for dyn Array + '_ {
     fn eq(&self, other: &Self) -> bool {
@@ -1067,13 +1073,14 @@ mod tests {
     fn test_null_union() {
         for mode in [UnionMode::Sparse, UnionMode::Dense] {
             let data_type = DataType::Union(
-                UnionFields::new(
+                UnionFields::try_new(
                     vec![2, 1],
                     vec![
                         Field::new("foo", DataType::Int32, true),
                         Field::new("bar", DataType::Int64, true),
                     ],
-                ),
+                )
+                .unwrap(),
                 mode,
             );
             let array = new_null_array(&data_type, 4);