Skip to content

GH-48208: [C++][Parquet] Fix Types logic to enable Parquet DB support on s390x #48209

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
Vishwanatha-HD wants to merge 1 commit into
base: main
Choose a base branch
from
Open

GH-48208: [C++][Parquet] Fix Types logic to enable Parquet DB support on s390x #48209

Show file tree
Hide file tree
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
19 changes: 16 additions & 3 deletions cpp/src/parquet/types.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
#include "arrow/util/checked_cast.h"
#include "arrow/util/compression.h"
#include "arrow/util/decimal.h"
#include "arrow/util/endian.h"
#include "arrow/util/float16.h"
#include "arrow/util/logging_internal.h"

Expand Down Expand Up @@ -112,6 +113,15 @@ std::enable_if_t<std::is_arithmetic_v<T>, std::string> FormatNumericValue(
std::stringstream result;
T value{};
std::memcpy(&value, val.data(), sizeof(T));

#if !ARROW_LITTLE_ENDIAN
// Parquet stores numeric stats in little-endian. Convert to native-endian
// before printing to avoid endianness mismatches on big-endian platforms.
if constexpr (std::is_integral_v<T> && sizeof(T) > 1) {
value = ::arrow::bit_util::FromLittleEndian(value);
}
#endif

result << value;
return result.str();
}
Expand Down Expand Up @@ -212,9 +222,12 @@ std::string FormatStatValue(Type::type parquet_type, ::std::string_view val,
return FormatNumericValue<float>(val);
}
case Type::INT96: {
std::array<int32_t, 3> values{};
std::memcpy(values.data(), bytes, 3 * sizeof(int32_t));
result << values[0] << " " << values[1] << " " << values[2];
std::array<uint32_t, 3> values{};
std::memcpy(values.data(), bytes, 3 * sizeof(uint32_t));
// INT96 values are stored in little-endian format
result << ::arrow::bit_util::FromLittleEndian(values[0]) << " "
<< ::arrow::bit_util::FromLittleEndian(values[1]) << " "
<< ::arrow::bit_util::FromLittleEndian(values[2]);
break;
}
case Type::BYTE_ARRAY:
Expand Down
11 changes: 11 additions & 0 deletions cpp/src/parquet/types.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
#include <string>
#include <string_view>

#include "arrow/util/endian.h"
#include "parquet/platform.h"
#include "parquet/type_fwd.h"
#include "parquet/windows_fixup.h" // for OPTIONAL
Expand Down Expand Up @@ -705,7 +706,12 @@ static inline std::string ByteArrayToString(const ByteArray& a) {
}

static inline void Int96SetNanoSeconds(parquet::Int96& i96, int64_t nanoseconds) {
#if ARROW_LITTLE_ENDIAN
std::memcpy(&i96.value, &nanoseconds, sizeof(nanoseconds));
#else
i96.value[0] = static_cast<uint32_t>(nanoseconds);
i96.value[1] = static_cast<uint32_t>(nanoseconds >> 32);
#endif
}

struct DecodedInt96 {
Expand All @@ -720,7 +726,12 @@ static inline DecodedInt96 DecodeInt96Timestamp(const parquet::Int96& i96) {
result.days_since_epoch = i96.value[2] - static_cast<uint64_t>(kJulianToUnixEpochDays);
result.nanoseconds = 0;

#if ARROW_LITTLE_ENDIAN
memcpy(&result.nanoseconds, &i96.value, sizeof(uint64_t));
#else
result.nanoseconds =
static_cast<uint64_t>(i96.value[0]) | (static_cast<uint64_t>(i96.value[1]) << 32);
#endif
return result;
}

Expand Down
Loading