Skip to content

GH-48206 Fix Statistics logic to enable Parquet DB support on s390x #48207

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+73 −0
Open

GH-48206 Fix Statistics logic to enable Parquet DB support on s390x #48207

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 73 additions & 0 deletions cpp/src/parquet/statistics.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@
#include "arrow/type_traits.h"
#include "arrow/util/bit_run_reader.h"
#include "arrow/util/checked_cast.h"
#include "arrow/util/endian.h"
#include "arrow/util/float16.h"
#include "arrow/util/logging_internal.h"
#include "arrow/util/ubsan.h"
Expand Down Expand Up @@ -925,22 +926,94 @@ void TypedStatisticsImpl<DType>::UpdateSpaced(const T* values, const uint8_t* va

template <typename DType>
void TypedStatisticsImpl<DType>::PlainEncode(const T& src, std::string* dst) const {
#if ARROW_LITTLE_ENDIAN
auto encoder = MakeTypedEncoder<DType>(Encoding::PLAIN, false, descr_, pool_);
encoder->Put(&src, 1);
auto buffer = encoder->FlushValues();
auto ptr = reinterpret_cast<const char*>(buffer->data());
dst->assign(ptr, static_cast<size_t>(buffer->size()));
#else
// For fixed-width numeric types, write explicit little-endian bytes per spec
if constexpr (std::is_same_v<DType, Int32Type>) {
uint32_t u;
std::memcpy(&u, &src, sizeof(u));
u = ::arrow::bit_util::ToLittleEndian(u);
dst->assign(reinterpret_cast<const char*>(&u), sizeof(u));
return;
} else if constexpr (std::is_same_v<DType, Int64Type>) {
uint64_t u;
std::memcpy(&u, &src, sizeof(u));
u = ::arrow::bit_util::ToLittleEndian(u);
dst->assign(reinterpret_cast<const char*>(&u), sizeof(u));
return;
} else if constexpr (std::is_same_v<DType, FloatType>) {
uint32_t u;
static_assert(sizeof(u) == sizeof(float), "size");
std::memcpy(&u, &src, sizeof(u));
u = ::arrow::bit_util::ToLittleEndian(u);
dst->assign(reinterpret_cast<const char*>(&u), sizeof(u));
return;
} else if constexpr (std::is_same_v<DType, DoubleType>) {
uint64_t u;
static_assert(sizeof(u) == sizeof(double), "size");
std::memcpy(&u, &src, sizeof(u));
u = ::arrow::bit_util::ToLittleEndian(u);
dst->assign(reinterpret_cast<const char*>(&u), sizeof(u));
return;
}
Comment on lines +937 to +963
Copy link
Member

@kou kou Nov 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we do this in XXXEncoder::Put() instead of here?

// Fallback: use encoder for other types
auto encoder = MakeTypedEncoder<DType>(Encoding::PLAIN, false, descr_, pool_);
encoder->Put(&src, 1);
auto buffer = encoder->FlushValues();
dst->assign(reinterpret_cast<const char*>(buffer->data()),
static_cast<size_t>(buffer->size()));
Comment on lines +964 to +969
Copy link
Member

@kou kou Nov 22, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we reuse the implementation in ARROW_LITTLE_ENDIAN for this?

#if !ARROW_LITTLE_ENDIAN
  if constexprt (...) {
    ...
  } else if ... {
    ...
  }
#endif
  auto encoder = MakeTypedEncoder<DType>(Encoding::PLAIN, false, descr_, pool_);
  encoder->Put(&src, 1);
  auto buffer = encoder->FlushValues();
  auto ptr = reinterpret_cast<const char*>(buffer->data());
  dst->assign(ptr, static_cast<size_t>(buffer->size()));

#endif
}

template <typename DType>
void TypedStatisticsImpl<DType>::PlainDecode(const std::string& src, T* dst) const {
#if ARROW_LITTLE_ENDIAN
auto decoder = MakeTypedDecoder<DType>(Encoding::PLAIN, descr_);
decoder->SetData(1, reinterpret_cast<const uint8_t*>(src.c_str()),
static_cast<int>(src.size()));
int decoded_values = decoder->Decode(dst, 1);
if (decoded_values != 1) {
throw ParquetException("Failed to decode statistic value from plain encoded string");
}
#else
if constexpr (std::is_same_v<DType, Int32Type>) {
uint32_t u = 0;
std::memcpy(&u, src.data(), std::min(src.size(), sizeof(u)));
u = ::arrow::bit_util::FromLittleEndian(u);
std::memcpy(dst, &u, sizeof(u));
return;
} else if constexpr (std::is_same_v<DType, Int64Type>) {
uint64_t u = 0;
std::memcpy(&u, src.data(), std::min(src.size(), sizeof(u)));
u = ::arrow::bit_util::FromLittleEndian(u);
std::memcpy(dst, &u, sizeof(u));
return;
} else if constexpr (std::is_same_v<DType, FloatType>) {
uint32_t u = 0;
std::memcpy(&u, src.data(), std::min(src.size(), sizeof(u)));
u = ::arrow::bit_util::FromLittleEndian(u);
std::memcpy(dst, &u, sizeof(u));
return;
} else if constexpr (std::is_same_v<DType, DoubleType>) {
uint64_t u = 0;
std::memcpy(&u, src.data(), std::min(src.size(), sizeof(u)));
u = ::arrow::bit_util::FromLittleEndian(u);
std::memcpy(dst, &u, sizeof(u));
return;
}
auto decoder = MakeTypedDecoder<DType>(Encoding::PLAIN, descr_);
decoder->SetData(1, reinterpret_cast<const uint8_t*>(src.c_str()),
static_cast<int>(src.size()));
int decoded_values = decoder->Decode(dst, 1);
if (decoded_values != 1) {
throw ParquetException("Failed to decode statistic value from plain encoded string");
}
#endif
}

template <>
Expand Down
Loading