Skip to content
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

refactor(parquet): Int96 timestamp column reader #11719

Closed
wants to merge 1 commit into from
Closed

refactor(parquet): Int96 timestamp column reader #11719

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
34 changes: 10 additions & 24 deletions velox/dwio/parquet/reader/TimestampColumnReader.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,13 @@
namespace facebook::velox::parquet {
namespace {

Timestamp toInt96Timestamp(const int128_t& value) {
// Convert int128_t to Int96 Timestamp by extracting days and nanos.
const int32_t days = static_cast<int32_t>(value >> 64);
const uint64_t nanos = value & ((((1ULL << 63) - 1ULL) << 1) + 1);
return Timestamp::fromDaysAndNanos(days, nanos);
}

// Range filter for Parquet Int96 Timestamp.
class ParquetInt96TimestampRange final : public common::TimestampRange {
public:
Expand All @@ -34,12 +41,8 @@ class ParquetInt96TimestampRange final : public common::TimestampRange {
bool nullAllowed)
: TimestampRange(lower, upper, nullAllowed) {}

// Int96 is read as int128_t value and converted to Timestamp by extracting
// days and nanos.
bool testInt128(const int128_t& value) const final {
const int32_t days = static_cast<int32_t>(value >> 64);
const uint64_t nanos = value & ((((1ULL << 63) - 1ULL) << 1) + 1);
const auto ts = Timestamp::fromDaysAndNanos(days, nanos);
const auto ts = toInt96Timestamp(value);
return ts >= this->lower() && ts <= this->upper();
}
};
Expand Down Expand Up @@ -75,24 +78,8 @@ class TimestampColumnReader : public IntegerColumnReader {
continue;
}

// Convert int128_t to Timestamp by extracting days and nanos.
const int128_t encoded = reinterpret_cast<int128_t&>(rawValues[i]);
const int32_t days = static_cast<int32_t>(encoded >> 64);
uint64_t nanos = encoded & ((((1ULL << 63) - 1ULL) << 1) + 1);
const auto timestamp = Timestamp::fromDaysAndNanos(days, nanos);

nanos = timestamp.getNanos();
switch (timestampPrecision_) {
case TimestampPrecision::kMilliseconds:
nanos = nanos / 1'000'000 * 1'000'000;
break;
case TimestampPrecision::kMicroseconds:
nanos = nanos / 1'000 * 1'000;
break;
case TimestampPrecision::kNanoseconds:
break;
}
rawValues[i] = Timestamp(timestamp.getSeconds(), nanos);
rawValues[i] = toInt96Timestamp(encoded).toPrecision(timestampPrecision_);
}
}

Expand Down Expand Up @@ -126,7 +113,6 @@ class TimestampColumnReader : public IntegerColumnReader {
rows,
extractValues));
}
return;
}

void read(
Expand All @@ -143,7 +129,7 @@ class TimestampColumnReader : public IntegerColumnReader {
private:
// The requested precision can be specified from HiveConfig to read timestamp
// from Parquet.
TimestampPrecision timestampPrecision_;
const TimestampPrecision timestampPrecision_;
};

} // namespace facebook::velox::parquet
15 changes: 15 additions & 0 deletions velox/type/Timestamp.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,6 +198,21 @@ struct Timestamp {
}
}

Timestamp toPrecision(const TimestampPrecision& precision) const {
uint64_t nanos = nanos_;
switch (precision) {
case TimestampPrecision::kMilliseconds:
nanos = nanos / 1'000'000 * 1'000'000;
break;
case TimestampPrecision::kMicroseconds:
nanos = nanos / 1'000 * 1'000;
break;
case TimestampPrecision::kNanoseconds:
break;
}
return Timestamp(seconds_, nanos);
}

/// Exports the current timestamp as a std::chrono::time_point of millisecond
/// precision. Note that the conversion may overflow since the internal
/// `seconds_` value will need to be multiplied by 1000.
Expand Down
Loading