refactor: use gcc-14 in ubuntu ci

.devcontainer/Dockerfile.template

@@ -26,10 +26,11 @@ RUN apt update && \
     bash-completion \
     build-essential \
     ccache \
+    clangd \
     cmake \
     curl \
-    gcc \
-    g++ \
+    gcc-14 \
+    g++-14 \
     git \
     htop \
     libboost-all-dev \

.github/workflows/cpp-linter.yml

@@ -36,6 +36,9 @@ jobs:
         shell: bash
         run: sudo apt-get update && sudo apt-get install -y libcurl4-openssl-dev
       - name: Run build
+        env:
+          CC: gcc-14
+          CXX: g++-14
         run: |
           mkdir build && cd build
           cmake .. -G Ninja -DCMAKE_EXPORT_COMPILE_COMMANDS=ON
@@ -54,7 +57,8 @@ jobs:
           thread-comments: true
           ignore: 'build|cmake_modules|ci'
           database: build
-          extra-args: '-I$PWD/src -I$PWD/build/src'
+          # need '-fno-builtin-std-forward_like', see https://github.com/llvm/llvm-project/issues/101614
+          extra-args: '-I$PWD/src -I$PWD/build/src -fno-builtin-std-forward_like'
       - name: Fail fast?!
         if: steps.linter.outputs.checks-failed != 0
         run: |

.github/workflows/docs.yml

@@ -17,7 +17,7 @@ permissions:
 
 jobs:
   docs:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
 
     steps:
       - uses: actions/checkout@v6.0.0

.github/workflows/license_check.yml

@@ -22,7 +22,7 @@ on: pull_request
 jobs:
   license-check:
     name: "License Check"
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     steps:
       - name: Checkout repository
         uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0

.github/workflows/rc.yml

@@ -30,7 +30,7 @@ permissions:
 jobs:
   archive:
     name: Archive
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     timeout-minutes: 5
     steps:
       - name: Checkout
@@ -77,6 +77,10 @@ jobs:
           - macos-26
           - ubuntu-24.04
           # - windows-latest
+        include:
+          - os: ubuntu-24.04
+            CC: gcc-14
+            CXX: g++-14
     steps:
       - name: Checkout
         uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v6.0.0
@@ -85,6 +89,12 @@ jobs:
         with:
           name: archive
 
+      - name: Set Ubuntu Compilers
+        if: ${{ startsWith(matrix.runs-on, 'ubuntu') }}
+        run: |
+          echo "CC=${{ matrix.CC }}" >> $GITHUB_ENV
+          echo "CXX=${{ matrix.CXX }}" >> $GITHUB_ENV
+
       - name: Verify
         run: |
           tar_gz=$(echo apache-iceberg-cpp-*.tar.gz)
@@ -109,7 +119,7 @@ jobs:
     if: github.ref_type == 'tag'
     needs:
       - verify
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     permissions:
       contents: write
     steps:

.github/workflows/sanitizer_test.yml

@@ -46,6 +46,9 @@ jobs:
         shell: bash
         run: sudo apt-get update && sudo apt-get install -y libcurl4-openssl-dev
       - name: Configure and Build with ASAN & UBSAN
+        env:
+          CC: gcc-14
+          CXX: g++-14
         run: |
           mkdir build && cd build
           cmake .. -G Ninja -DCMAKE_BUILD_TYPE=Debug -DICEBERG_ENABLE_ASAN=ON -DICEBERG_ENABLE_UBSAN=ON

.github/workflows/test.yml

@@ -51,9 +51,15 @@ jobs:
         run: sudo apt-get update && sudo apt-get install -y libcurl4-openssl-dev
       - name: Build Iceberg
         shell: bash
+        env:
+          CC: gcc-14
+          CXX: g++-14
         run: ci/scripts/build_iceberg.sh $(pwd)
       - name: Build Example
         shell: bash
+        env:
+          CC: gcc-14
+          CXX: g++-14
         run: ci/scripts/build_example.sh $(pwd)/example
   macos:
     name: AArch64 macOS 26
@@ -102,6 +108,8 @@ jobs:
         include:
           - title: AMD64 Ubuntu 24.04
             runs-on: ubuntu-24.04
+            CC: gcc-14
+            CXX: g++-14
           - title: AMD64 Windows 2025
             runs-on: windows-2025
             meson-setup-args: --vsenv
@@ -117,6 +125,11 @@ jobs:
         run: |
           python3 -m pip install --upgrade pip
           python3 -m pip install -r requirements.txt
+      - name: Set Ubuntu Compilers
+        if: ${{ startsWith(matrix.runs-on, 'ubuntu') }}
+        run: |
+          echo "CC=${{ matrix.CC }}" >> $GITHUB_ENV
+          echo "CXX=${{ matrix.CXX }}" >> $GITHUB_ENV
       - name: Build Iceberg
         run: |
           meson setup builddir ${{ matrix.meson-setup-args || '' }}

cmake_modules/IcebergThirdpartyToolchain.cmake

@@ -97,6 +97,7 @@ function(resolve_arrow_dependency)
   set(ARROW_WITH_ZLIB ON)
   set(ZLIB_SOURCE "SYSTEM")
   set(ARROW_VERBOSE_THIRDPARTY_BUILD OFF)
+  set(CMAKE_CXX_STANDARD 17)
 
   fetchcontent_declare(VendoredArrow
                        ${FC_DECLARE_COMMON_OPTIONS}
@@ -323,7 +324,7 @@ function(resolve_croaring_dependency)
     set(CROARING_URL "$ENV{ICEBERG_CROARING_URL}")
   else()
     set(CROARING_URL
-        "https://github.com/RoaringBitmap/CRoaring/archive/refs/tags/v4.3.11.tar.gz")
+        "https://github.com/RoaringBitmap/CRoaring/archive/refs/tags/v4.4.3.tar.gz")
   endif()
 
   fetchcontent_declare(croaring
@@ -542,7 +543,7 @@ function(resolve_cpr_dependency)
             RUNTIME DESTINATION "${ICEBERG_INSTALL_BINDIR}"
             ARCHIVE DESTINATION "${ICEBERG_INSTALL_LIBDIR}"
             LIBRARY DESTINATION "${ICEBERG_INSTALL_LIBDIR}")
-    list(APPEND ICEBERG_SYSTEM_DEPENDENCIES OpenSSL)
+    list(APPEND ICEBERG_SYSTEM_DEPENDENCIES OpenSSL CURL)
   else()
     set(CPR_VENDORED FALSE)
     list(APPEND ICEBERG_SYSTEM_DEPENDENCIES cpr)

src/iceberg/iceberg-config.cmake.in

@@ -72,19 +72,6 @@ endmacro()
 # Find system dependencies
 iceberg_find_dependencies("${ICEBERG_SYSTEM_DEPENDENCIES}")
 
-# Create missing CRoaring targets if they don't exist
-if(NOT TARGET roaring::roaring-headers)
-  add_library(roaring::roaring-headers INTERFACE IMPORTED)
-endif()
-
-if(NOT TARGET roaring::roaring-headers-cpp)
-  add_library(roaring::roaring-headers-cpp INTERFACE IMPORTED)
-endif()
-
-if(NOT TARGET CURL::libcurl)
-  add_library(CURL::libcurl INTERFACE IMPORTED)
-endif()
-
 include("${CMAKE_CURRENT_LIST_DIR}/iceberg-targets.cmake")
 
 if(TARGET iceberg::arrow_static)

src/iceberg/table_metadata.cc

@@ -22,6 +22,7 @@
 #include <algorithm>
 #include <chrono>
 #include <format>
+#include <ranges>
 #include <string>
 
 #include <nlohmann/json.hpp>
@@ -184,51 +185,45 @@ Result<TableMetadataCache::SnapshotsMapRef> TableMetadataCache::GetSnapshotsById
 
 Result<TableMetadataCache::SchemasMap> TableMetadataCache::InitSchemasMap(
     const TableMetadata* metadata) {
-  SchemasMap schemas_map;
-  schemas_map.reserve(metadata->schemas.size());
-  for (const auto& schema : metadata->schemas) {
-    if (schema->schema_id()) {
-      schemas_map.emplace(schema->schema_id().value(), schema);
-    }
-  }
-  return schemas_map;
+  return metadata->schemas | std::views::filter([](const auto& schema) {
+           return schema->schema_id().has_value();
+         }) |
+         std::views::transform([](const auto& schema) {
+           return std::make_pair(schema->schema_id().value(), schema);
+         }) |
+         std::ranges::to<SchemasMap>();
 }
 
 Result<TableMetadataCache::PartitionSpecsMap> TableMetadataCache::InitPartitionSpecsMap(
     const TableMetadata* metadata) {
-  PartitionSpecsMap partition_specs_map;
-  partition_specs_map.reserve(metadata->partition_specs.size());
-  for (const auto& spec : metadata->partition_specs) {
-    partition_specs_map.emplace(spec->spec_id(), spec);
-  }
-  return partition_specs_map;
+  return metadata->partition_specs | std::views::transform([](const auto& spec) {
+           return std::make_pair(spec->spec_id(), spec);
+         }) |
+         std::ranges::to<PartitionSpecsMap>();
 }
 
 Result<TableMetadataCache::SortOrdersMap> TableMetadataCache::InitSortOrdersMap(
     const TableMetadata* metadata) {
-  SortOrdersMap sort_orders_map;
-  sort_orders_map.reserve(metadata->sort_orders.size());
-  for (const auto& order : metadata->sort_orders) {
-    sort_orders_map.emplace(order->order_id(), order);
-  }
-  return sort_orders_map;
+  return metadata->sort_orders | std::views::transform([](const auto& order) {
+           return std::make_pair(order->order_id(), order);
+         }) |
+         std::ranges::to<SortOrdersMap>();
 }
 
 Result<TableMetadataCache::SnapshotsMap> TableMetadataCache::InitSnapshotMap(
     const TableMetadata* metadata) {
-  SnapshotsMap snapshots_map;
-  snapshots_map.reserve(metadata->snapshots.size());
-  for (const auto& snapshot : metadata->snapshots) {
-    snapshots_map.emplace(snapshot->snapshot_id, snapshot);
-  }
-  return snapshots_map;
+  return metadata->snapshots | std::views::transform([](const auto& snapshot) {
+           return std::make_pair(snapshot->snapshot_id, snapshot);
+         }) |
+         std::ranges::to<SnapshotsMap>();
 }
 
 // TableMetadataUtil implementation
 
 Result<MetadataFileCodecType> TableMetadataUtil::CodecFromFileName(
     std::string_view file_name) {
-  if (file_name.find(".metadata.json") == std::string::npos) {
+  auto pos = file_name.find_last_of(".metadata.json");
+  if (pos == std::string::npos) {
     return InvalidArgument("{} is not a valid metadata file", file_name);
   }
 
@@ -237,8 +232,7 @@ Result<MetadataFileCodecType> TableMetadataUtil::CodecFromFileName(
     return MetadataFileCodecType::kGzip;
   }
 
-  std::string_view file_name_without_suffix =
-      file_name.substr(0, file_name.find_last_of(".metadata.json"));
+  std::string_view file_name_without_suffix = file_name.substr(0, pos);
   if (file_name_without_suffix.ends_with(".gz")) {
     return MetadataFileCodecType::kGzip;
   }