DecimalArray

.github/workflows/qemu.yaml

@@ -123,6 +123,7 @@ jobs:
               -DUSE_DATE_POLYFILL=${{matrix.target.date-polyfill}} \
               -DBUILD_TESTS=ON \
               -DBUILD_EXAMPLES=ON \
+              -DUSE_LARGE_INT_PLACEHOLDERS=ON \
               -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \
               -DCMAKE_C_COMPILER_LAUNCHER=ccache
             cd build

.github/workflows/windows.yml

@@ -19,10 +19,10 @@ jobs:
       matrix:
         runs-on: [windows-latest]
         toolchain:
-        - {compiler: msvc, date-polyfill: 'ON'}
-        - {compiler: msvc, date-polyfill: 'OFF'}
-        - {compiler: clang, date-polyfill: 'ON', version: 18}
-        - {compiler: clang, date-polyfill: 'OFF', version: 18}
+        - {compiler: msvc, date-polyfill: 'ON', use-large-int-placeholders: 'ON'}
+        - {compiler: msvc, date-polyfill: 'OFF', use-large-int-placeholders: 'ON'}
+        - {compiler: clang, date-polyfill: 'ON', version: 18, use-large-int-placeholders: 'ON'}
+        - {compiler: clang, date-polyfill: 'OFF', version: 18, use-large-int-placeholders: 'ON'}
         target-arch:
         - {
             name: "Win64",
@@ -125,6 +125,7 @@ jobs:
         echo "SPARROW_DEPS_PREFIX=$CONDA_PREFIX" >> $GITHUB_ENV
         echo "SPARROW_INSTALL_PREFIX=$CONDA_PREFIX" >> $GITHUB_ENV
         echo "SPARROW_ADDITIONAL_OPTIONS=-DSPARROW_TARGET_32BIT=OFF" >> $GITHUB_ENV
+
 
     - name: Set dependencies install prefix dir for 32bit
       if: matrix.target-arch.name == 'Win32'
@@ -174,6 +175,7 @@ jobs:
         -DCMAKE_INSTALL_PREFIX=$SPARROW_INSTALL_PREFIX \
         -DBUILD_TESTS=ON \
         -DBUILD_EXAMPLES=ON \
+        -DUSE_LARGE_INT_PLACEHOLDERS=${{matrix.toolchain.use-large-int-placeholders}} \
         -DUSE_DATE_POLYFILL=${{matrix.toolchain.date-polyfill}} \
         $GENERATOR_EXTRA_FLAGS \
         $SPARROW_CHECKS \

.pre-commit-config.yaml

@@ -0,0 +1,5 @@
+repos:
+- repo: https://github.com/pre-commit/mirrors-clang-format
+  rev: v19.1.5
+  hooks:
+  - id: clang-format

CMakeLists.txt

@@ -86,6 +86,7 @@ OPTION(BUILD_TESTS "Build sparrow test suite" OFF)
 OPTION(BUILD_DOCS  "Build sparrow documentation" OFF)
 OPTION(BUILD_EXAMPLES "Build sparrow examples" OFF)
 OPTION(USE_DATE_POLYFILL "Use date polyfill implementation" ON)
+OPTION(USE_LARGE_INT_PLACEHOLDERS "use types without api for big integers" OFF)
 
 OPTION(SPARROW_TARGET_32BIT "Test 32bit support" OFF)
 
@@ -131,6 +132,11 @@ if (USE_DATE_POLYFILL)
     add_compile_definitions(SPARROW_USE_DATE_POLYFILL)
 endif()
 
+if(USE_LARGE_INT_PLACEHOLDERS)
+
+    add_compile_definitions(SPARROW_USE_LARGE_INT_PLACEHOLDERS)
+endif()
+
 # Build
 # =====
 
@@ -230,6 +236,7 @@ else()
         ${SPARROW_SOURCE_DIR}/record_batch.cpp
         ${SPARROW_SOURCE_DIR}/run_encoded_array.cpp
         ${SPARROW_SOURCE_DIR}/struct_value.cpp
+        ${SPARROW_SOURCE_DIR}/types/data_type.cpp
     )
 endif()
 

include/sparrow/arrow_interface/arrow_array.hpp

@@ -56,7 +56,8 @@ namespace sparrow
     SPARROW_API void release_arrow_array(ArrowArray* array);
 
     /**
-     * Empty release function to use for the `ArrowArray.release` member. Should be used for view of ArrowArray.
+     * Empty release function to use for the `ArrowArray.release` member. Should be used for view of
+     * ArrowArray.
      */
     SPARROW_API void empty_release_arrow_array(ArrowArray* array);
 

include/sparrow/arrow_interface/arrow_array_schema_info_utils.hpp

@@ -50,7 +50,10 @@ namespace sparrow
             case data_type::FLOAT:
             case data_type::DOUBLE:
             case data_type::TIMESTAMP:
-            case data_type::DECIMAL:
+            case data_type::DECIMAL32:
+            case data_type::DECIMAL64:
+            case data_type::DECIMAL128:
+            case data_type::DECIMAL256:
             case data_type::LIST:
             case data_type::STRUCT:
             case data_type::STRING:

include/sparrow/details/3rdparty/large_integers/COPYING

@@ -0,0 +1,24 @@
+BSD 2-Clause License
+
+Copyright (c) 2016 - 2019, Kim Walisch.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

include/sparrow/details/3rdparty/large_integers/int128_t.hpp

@@ -0,0 +1,139 @@
+////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+// SPARROW: THIS HAS BEEN COPY-PASTED FROM https://github.com/kimwalisch/primesum/blob/master/include/int128_t.hpp
+// PLEASE UPDATE THIS COMMENT IF YOU REPLACE THIS
+// SEE README.md for rational
+////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+// Modification from the original:
+// * disabled io operators
+////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////////
+///
+/// @file   int128_t.hpp
+/// @brief  Support for int128_t, uint128_t types.
+///
+/// Copyright (C) 2018 Kim Walisch, <[email protected]>
+///
+/// This file is distributed under the BSD License. See the COPYING
+/// file in the top level directory.
+///
+
+#ifndef INT128_T_HPP
+#define INT128_T_HPP
+
+#include <stdint.h>
+#include <limits>
+#include <type_traits>
+
+/// The __int128_t type (GCC/Clang) is not well supported by
+/// the C++ standard library (in 2016) so we have to define
+/// some functions ourselves. We also define typedefs so we
+/// can use int128_t instead of __int128_t. Once this is done
+/// int128_t can be used like a regular integer type.
+///
+#if !defined(INT128_MAX) && \
+     defined(__SIZEOF_INT128__)
+
+#include <ostream>
+#include <string>
+
+namespace primesum {
+
+using int128_t = __int128_t;
+using uint128_t = __uint128_t;
+
+// inline std::ostream& operator<<(std::ostream& stream, uint128_t n)
+// {
+//   std::string str;
+
+//   while (n > 0)
+//   {
+//     str += '0' + n % 10;
+//     n /= 10;
+//   }
+//   if (str.empty())
+//     str = "0";
+
+//   stream << std::string(str.rbegin(), str.rend());
+//   return stream;
+// }
+
+// inline std::ostream& operator<<(std::ostream& stream, int128_t n)
+// {
+//   if (n < 0)
+//   {
+//     stream << "-";
+//     n = -n;
+//   }
+//   stream << (uint128_t) n;
+//   return stream;
+// }
+
+} // namespace
+
+#endif
+
+namespace primesum {
+
+/// Portable namespace, includes functions which (unlike the versions
+/// form the C++ standard library) work with the int128_t and
+/// uint128_t types (2014).
+///
+namespace prt {
+
+template <typename T>
+struct numeric_limits
+{
+  static constexpr T max()
+  {
+    return std::numeric_limits<T>::max();
+  }
+};
+
+template <>
+struct numeric_limits<int128_t>
+{
+  static constexpr int128_t min() { return ((int128_t) 1) << 127; }
+  static constexpr int128_t max() { return ~min(); }
+};
+
+template <>
+struct numeric_limits<uint128_t>
+{
+  static constexpr uint128_t min() { return 0; }
+  static constexpr uint128_t max() { return ~min(); }
+};
+
+template <typename T>
+struct is_integral
+{
+  enum
+  {
+    value = std::is_integral<T>::value ||
+            std::is_same<T, int128_t>::value ||
+            std::is_same<T, uint128_t>::value
+  };
+};
+
+template <typename T>
+struct is_signed
+{
+  enum
+  {
+    value = std::is_signed<T>::value ||
+            std::is_same<T, int128_t>::value
+  };
+};
+
+template <typename T>
+struct is_unsigned
+{
+  enum
+  {
+    value = std::is_unsigned<T>::value ||
+            std::is_same<T, uint128_t>::value
+  };
+};
+
+} // namespace prt
+} // namespace primesum
+
+#endif