Skip to content

Implement TimeStampXXXTZVector for parquet isAdjustedToUTC #926 #576 #577 #927

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

Draft
wants to merge 7 commits into
base: master
Choose a base branch
from
Draft

Implement TimeStampXXXTZVector for parquet isAdjustedToUTC #926 #576 #577 #927

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b5c614c
Implement TimeStampMicroTZVector for parquet isAdjustedToUTC timestam…
Oct 17, 2024
d5bd3a2
test for TimeStampMicroTZVector
Oct 18, 2024
330951c
add support for TimeStampNanoTZVector
Oct 18, 2024
7bc05a4
fix precision of TimeStampMicroTZVector (div. 1_000L was wrong)
Oct 18, 2024
bd049d9
add support for TimeStampMilliTZVector
Oct 18, 2024
cbdf8f7
use proper utility method for TimeStampNanoTZVector
Oct 18, 2024
e121232
add support for timeStampSecTZVector
Oct 18, 2024
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
16 changes: 16 additions & 0 deletions dataframe-arrow/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/arrowReadingImpl.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,14 @@
package org.jetbrains.kotlinx.dataframe.io

import kotlinx.datetime.Instant
import kotlinx.datetime.LocalDate
import kotlinx.datetime.LocalDateTime
import kotlinx.datetime.LocalTime
import kotlinx.datetime.TimeZone
import kotlinx.datetime.toKotlinLocalDate
import kotlinx.datetime.toKotlinLocalDateTime
import kotlinx.datetime.toKotlinLocalTime
import kotlinx.datetime.toLocalDateTime
import org.apache.arrow.memory.RootAllocator
import org.apache.arrow.vector.BigIntVector
import org.apache.arrow.vector.BitVector
Expand All @@ -21,6 +24,7 @@ import org.apache.arrow.vector.LargeVarBinaryVector
import org.apache.arrow.vector.LargeVarCharVector
import org.apache.arrow.vector.NullVector
import org.apache.arrow.vector.SmallIntVector
import org.apache.arrow.vector.TimeStampMicroTZVector
import org.apache.arrow.vector.TimeMicroVector
import org.apache.arrow.vector.TimeMilliVector
import org.apache.arrow.vector.TimeNanoVector
Expand Down Expand Up @@ -179,6 +183,16 @@ private fun TimeStampMicroVector.values(range: IntRange): List<LocalDateTime?> =
}
}

private fun TimeStampMicroTZVector.values(range: IntRange): List<LocalDateTime?> =
range.mapIndexed { i, it ->
if (isNull(i)) {
null
} else {
Instant.fromEpochMilliseconds(getObject(it) / 1000)
.toLocalDateTime(TimeZone.of(this.timeZone))
}
}

private fun TimeStampMilliVector.values(range: IntRange): List<LocalDateTime?> =
range.mapIndexed { i, it ->
if (isNull(i)) {
Expand Down Expand Up @@ -345,6 +359,8 @@ private fun readField(root: VectorSchemaRoot, field: Field, nullability: Nullabi

is TimeStampMicroVector -> vector.values(range).withTypeNullable(field.isNullable, nullability)

is TimeStampMicroTZVector -> vector.values(range).withTypeNullable(field.isNullable, nullability)

is TimeStampMilliVector -> vector.values(range).withTypeNullable(field.isNullable, nullability)

is TimeStampSecVector -> vector.values(range).withTypeNullable(field.isNullable, nullability)
Expand Down