Merge branch 'main' into dict-decoder-regression-fix

.github/workflows/comment_bot.yml

@@ -182,7 +182,7 @@ jobs:
     if: github.event.comment.body == 'take'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/github-script@d7906e4ad0b1822421a7e6a35d5ca353c962f410 # v6.4.1
+      - uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |

.github/workflows/dev_pr.yml

@@ -53,7 +53,7 @@ jobs:
         if: |
           (github.event.action == 'opened' ||
            github.event.action == 'edited')
-        uses: actions/github-script@d7906e4ad0b1822421a7e6a35d5ca353c962f410 # v6.4.1
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -64,7 +64,7 @@ jobs:
         if: |
           (github.event.action == 'opened' ||
            github.event.action == 'edited')
-        uses: actions/github-script@d7906e4ad0b1822421a7e6a35d5ca353c962f410 # v6.4.1
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -75,7 +75,7 @@ jobs:
         if: |
           (github.event.action == 'opened' ||
            github.event.action == 'edited')
-        uses: actions/github-script@d7906e4ad0b1822421a7e6a35d5ca353c962f410 # v6.4.1
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           debug: true
           github-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/issue_bot.yml

@@ -33,7 +33,7 @@ jobs:
     if: github.event.issue.pull_request == null
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/github-script@d7906e4ad0b1822421a7e6a35d5ca353c962f410 # v6.4.1
+      - uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           script: |
             let split_body = context.payload.issue.body.split('### Component(s)');

.github/workflows/java.yml

@@ -48,7 +48,6 @@ env:
   DOCKER_VOLUME_PREFIX: ".docker/"
 
 jobs:
-
   ubuntu:
     name: AMD64 Ubuntu 22.04 Java JDK ${{ matrix.jdk }} Maven ${{ matrix.maven }}
     runs-on: ubuntu-latest

.github/workflows/java_jni.yml

@@ -48,7 +48,6 @@ env:
   DOCKER_VOLUME_PREFIX: ".docker/"
 
 jobs:
-
   docker:
     name: AMD64 manylinux2014 Java JNI
     runs-on: ubuntu-latest

.github/workflows/pr_bot.yml

@@ -40,7 +40,7 @@ jobs:
       - name: 'Download PR review payload'
         id: 'download'
         if: github.event_name == 'workflow_run'
-        uses: actions/github-script@d7906e4ad0b1822421a7e6a35d5ca353c962f410 # v6.4.1
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
         with:
           script: |
             const run_id = "${{ github.event.workflow_run.id }}";

ci/scripts/integration_arrow.sh

@@ -43,6 +43,12 @@ fi
 # Get more detailed context on crashes
 export PYTHONFAULTHANDLER=1
 
+# Due to how Go reads environment variables, we have to set them from the calling
+# process, or they would get ignored.
+# (see https://forum.golangbridge.org/t/are-godebug-and-other-env-vars-ignored-when-loading-a-go-dll-from-foreign-code/33694)
+export GOMEMLIMIT=200MiB
+export GODEBUG=gctrace=1,clobberfree=1
+
 # Rust can be enabled by exporting ARCHERY_INTEGRATION_WITH_RUST=1
 time archery integration \
     --run-c-data \

ci/scripts/java_build.sh

@@ -77,20 +77,20 @@ mvn="${mvn} -T 2C"
 
 pushd ${source_dir}
 
-${mvn} install
-
 if [ "${ARROW_JAVA_SHADE_FLATBUFFERS}" == "ON" ]; then
-  ${mvn} -Pshade-flatbuffers install
+  mvn="${mvn} -Pshade-flatbuffers"
 fi
 
 if [ "${ARROW_JAVA_CDATA}" = "ON" ]; then
-  ${mvn} -Darrow.c.jni.dist.dir=${java_jni_dist_dir} -Parrow-c-data install
+  mvn="${mvn} -Darrow.c.jni.dist.dir=${java_jni_dist_dir} -Parrow-c-data"
 fi
 
 if [ "${ARROW_JAVA_JNI}" = "ON" ]; then
-  ${mvn} -Darrow.cpp.build.dir=${java_jni_dist_dir} -Parrow-jni install
+  mvn="${mvn} -Darrow.cpp.build.dir=${java_jni_dist_dir} -Parrow-jni"
 fi
 
+${mvn} install
+
 if [ "${BUILD_DOCS_JAVA}" == "ON" ]; then
   # HTTP pooling is turned of to avoid download issues https://issues.apache.org/jira/browse/ARROW-11633
   mkdir -p ${build_dir}/docs/java/reference

ci/scripts/rust_build.sh

@@ -21,6 +21,7 @@ set -e
 
 arrow_dir=${1}
 source_dir=${1}/rust
+build_dir=${2}/rust
 
 # This file is used to build the rust binaries needed for the archery
 # integration tests. Testing of the rust implementation in normal CI is handled
@@ -54,7 +55,7 @@ rustup show
 pushd ${source_dir}
 
 # build only the integration testing binaries
-cargo build -p arrow-integration-testing
+cargo build -p arrow-integration-testing --target-dir ${build_dir}
 
 # Save disk space by removing large temporary build products
 rm -rf target/debug/deps

cpp/src/arrow/CMakeLists.txt

@@ -229,6 +229,7 @@ set(ARROW_SRCS
     util/hashing.cc
     util/int_util.cc
     util/io_util.cc
+    util/list_util.cc
     util/logging.cc
     util/key_value_metadata.cc
     util/memory.cc
@@ -790,6 +791,7 @@ add_arrow_test(array_test
                array/array_binary_test.cc
                array/array_dict_test.cc
                array/array_list_test.cc
+               array/array_list_view_test.cc
                array/array_run_end_test.cc
                array/array_struct_test.cc
                array/array_union_test.cc

cpp/src/arrow/array/array_base.cc

@@ -95,7 +95,7 @@ struct ScalarFromArraySlotImpl {
   Status Visit(const MonthDayNanoIntervalArray& a) { return Finish(a.Value(index_)); }
 
   template <typename T>
-  Status Visit(const BaseListArray<T>& a) {
+  Status Visit(const VarLengthListLikeArray<T>& a) {
     return Finish(a.value_slice(index_));
   }