Skip to content

Linter for all modules #521

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

Merged
merged 2 commits into from
Nov 30, 2023
Merged

Linter for all modules #521

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e2a131b
Enabling linter for all modules except jdbc
Jolanrensen Nov 28, 2023
d50002b
Linter fixes and slight refactorings in some places for all non-:core…
Jolanrensen Nov 28, 2023
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
27 changes: 27 additions & 0 deletions build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
import org.jetbrains.kotlin.gradle.tasks.KotlinCompile
import org.jetbrains.kotlin.tooling.core.closure
import org.jetbrains.kotlinx.publisher.apache2
import org.jetbrains.kotlinx.publisher.developer
import org.jetbrains.kotlinx.publisher.githubRepo
import org.jmailen.gradle.kotlinter.KotlinterExtension

@Suppress("DSL_SCOPE_VIOLATION", "UnstableApiUsage")
plugins {
Expand Down Expand Up @@ -51,6 +53,31 @@ allprojects {
sourceCompatibility = JavaVersion.VERSION_1_8.toString()
targetCompatibility = JavaVersion.VERSION_1_8.toString()
}

// Attempts to configure kotlinter for each sub-project that uses the plugin
afterEvaluate {
try {
kotlinter {
ignoreFailures = false
reporters = arrayOf("checkstyle", "plain")
experimentalRules = true
disabledRules = arrayOf(
"no-wildcard-imports",
"experimental:spacing-between-declarations-with-annotations",
"experimental:enum-entry-name-case",
"experimental:argument-list-wrapping",
"experimental:annotation",
"max-line-length",
"filename",
"comment-spacing",
"curly-spacing",
"experimental:annotation-spacing"
)
}
} catch (_: UnknownDomainObjectException) {
logger.warn("Could not set kotlinter config on :${this.name}")
}
}
}

koverMerged {
Expand Down
18 changes: 0 additions & 18 deletions core/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -298,24 +298,6 @@ korro {
}
}

kotlinter {
ignoreFailures = false
reporters = arrayOf("checkstyle", "plain")
experimentalRules = true
disabledRules = arrayOf(
"no-wildcard-imports",
"experimental:spacing-between-declarations-with-annotations",
"experimental:enum-entry-name-case",
"experimental:argument-list-wrapping",
"experimental:annotation",
"max-line-length",
"filename",
"comment-spacing",
"curly-spacing",
"experimental:annotation-spacing"
)
}

tasks.withType<KspTaskJvm> {
dependsOn(tasks.generateKeywordsSrc)
}
Expand Down
4 changes: 2 additions & 2 deletions ...ed-sources/src/main/kotlin/org/jetbrains/kotlinx/dataframe/jupyter/JupyterHtmlRenderer.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,9 +50,9 @@ internal inline fun <reified T : Any> JupyterHtmlRenderer.render(
includeCss = true,
).plus(
df.toHTML(
configuration = reifiedDisplayConfiguration,
// is added later to make sure it's put outside of potential iFrames
configuration = reifiedDisplayConfiguration.copy(enableFallbackStaticTables = false),
cellRenderer = contextRenderer,
includeStatic = false, // is added later to make sure it's put outside of potential iFrames
) { footer }
).toJupyterHtmlData()

Expand Down
1 change: 1 addition & 0 deletions dataframe-arrow/build.gradle.kts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@ plugins {
kotlin("jvm")
kotlin("libs.publisher")
id("org.jetbrains.kotlinx.kover")
id("org.jmailen.kotlinter")
}

group = "org.jetbrains.kotlinx"
Expand Down
168 changes: 139 additions & 29 deletions dataframe-arrow/src/main/kotlin/org/jetbrains/kotlinx/dataframe/io/ArrowWriterImpl.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,6 @@ import org.jetbrains.kotlinx.dataframe.exceptions.CellConversionException
import org.jetbrains.kotlinx.dataframe.exceptions.TypeConverterNotFoundException
import org.jetbrains.kotlinx.dataframe.name
import org.jetbrains.kotlinx.dataframe.values
import java.nio.charset.Charset
import kotlin.reflect.full.isSubtypeOf
import kotlin.reflect.typeOf

Expand Down Expand Up @@ -85,15 +84,21 @@ internal class ArrowWriterImpl(
private fun countTotalBytes(column: AnyCol): Long? {
val columnType = column.type()
return when {
columnType.isSubtypeOf(typeOf<String?>()) -> column.values.fold(0L) {totalBytes, value -> totalBytes + value.toString().length * 4}
columnType.isSubtypeOf(typeOf<String?>()) -> column.values.fold(0L) { totalBytes, value -> totalBytes + value.toString().length * 4 }
else -> null
}
}

private fun infillWithNulls(vector: FieldVector, size: Int) {
when (vector) {
is BaseFixedWidthVector -> for (i in 0 until size) { vector.setNull(i) }
is BaseVariableWidthVector -> for (i in 0 until size) { vector.setNull(i) }
is BaseFixedWidthVector -> for (i in 0 until size) {
vector.setNull(i)
}

is BaseVariableWidthVector -> for (i in 0 until size) {
vector.setNull(i)
}

else -> throw IllegalArgumentException("Can not infill ${vector.javaClass.canonicalName}")
}
vector.valueCount = size
Expand All @@ -110,7 +115,8 @@ internal class ArrowWriterImpl(
ArrowType.Int(32, true) -> column.convertToInt()
ArrowType.Int(64, true) -> column.convertToLong()
is ArrowType.Decimal -> column.convertToBigDecimal()
ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE) -> column.convertToDouble().convertToFloat() // Use [convertToDouble] as locale logic step
ArrowType.FloatingPoint(FloatingPointPrecision.SINGLE) -> column.convertToDouble()
.convertToFloat() // Use [convertToDouble] as locale logic step
ArrowType.FloatingPoint(FloatingPointPrecision.DOUBLE) -> column.convertToDouble()
ArrowType.Date(DateUnit.DAY) -> column.convertToLocalDate()
ArrowType.Date(DateUnit.MILLISECOND) -> column.convertToLocalDateTime()
Expand All @@ -123,25 +129,108 @@ internal class ArrowWriterImpl(

private fun infillVector(vector: FieldVector, column: AnyCol) {
when (vector) {
is VarCharVector -> column.convertToString().forEachIndexed { i, value -> value?.let { vector.set(i, Text(value)); value } ?: vector.setNull(i) }
is LargeVarCharVector -> column.convertToString().forEachIndexed { i, value -> value?.let { vector.set(i, Text(value)); value } ?: vector.setNull(i) }
is BitVector -> column.convertToBoolean().forEachIndexed { i, value -> value?.let { vector.set(i, value.compareTo(false)); value } ?: vector.setNull(i) }
is TinyIntVector -> column.convertToInt().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is SmallIntVector -> column.convertToInt().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is IntVector -> column.convertToInt().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is BigIntVector -> column.convertToLong().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is DecimalVector -> column.convertToBigDecimal().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is Decimal256Vector -> column.convertToBigDecimal().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is Float8Vector -> column.convertToDouble().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }
is Float4Vector -> column.convertToFloat().forEachIndexed { i, value -> value?.let { vector.set(i, value); value } ?: vector.setNull(i) }

is DateDayVector -> column.convertToLocalDate().forEachIndexed { i, value -> value?.let { vector.set(i, (value.toJavaLocalDate().toEpochDay()).toInt()); value } ?: vector.setNull(i) }
is DateMilliVector -> column.convertToLocalDateTime().forEachIndexed { i, value -> value?.let { vector.set(i, value.toInstant(
TimeZone.UTC).toEpochMilliseconds()); value } ?: vector.setNull(i) }
is TimeNanoVector -> column.convertToLocalTime().forEachIndexed { i, value -> value?.let { vector.set(i, value.toNanoOfDay()); value } ?: vector.setNull(i) }
is TimeMicroVector -> column.convertToLocalTime().forEachIndexed { i, value -> value?.let { vector.set(i, value.toNanoOfDay() / 1000); value } ?: vector.setNull(i) }
is TimeMilliVector -> column.convertToLocalTime().forEachIndexed { i, value -> value?.let { vector.set(i, (value.toNanoOfDay() / 1000 / 1000).toInt()); value } ?: vector.setNull(i) }
is TimeSecVector -> column.convertToLocalTime().forEachIndexed { i, value -> value?.let { vector.set(i, (value.toNanoOfDay() / 1000 / 1000 / 1000).toInt()); value } ?: vector.setNull(i) }
is VarCharVector -> column.convertToString()
.forEachIndexed { i, value ->
value?.also { vector.set(i, Text(value)) }
?: vector.setNull(i)
}

is LargeVarCharVector -> column.convertToString()
Copy link
Collaborator

Choose a reason for hiding this comment

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

This is became more readable!

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

yeah, someone didn't know also did exactly what they attempted to do with let. Honestly, I'd replace them with if (value == null) if I wrote it myself, for readability, but at least it's better now :)

.forEachIndexed { i, value ->
value?.also { vector.set(i, Text(value)) }
?: vector.setNull(i)
}

is BitVector -> column.convertToBoolean()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value.compareTo(false)) }
?: vector.setNull(i)
}

is TinyIntVector -> column.convertToInt()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is SmallIntVector -> column.convertToInt()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is IntVector -> column.convertToInt()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is BigIntVector -> column.convertToLong()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is DecimalVector -> column.convertToBigDecimal()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is Decimal256Vector -> column.convertToBigDecimal()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is Float8Vector -> column.convertToDouble()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is Float4Vector -> column.convertToFloat()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value) }
?: vector.setNull(i)
}

is DateDayVector -> column.convertToLocalDate()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value.toJavaLocalDate().toEpochDay().toInt()) }
?: vector.setNull(i)
}

is DateMilliVector -> column.convertToLocalDateTime()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value.toInstant(TimeZone.UTC).toEpochMilliseconds()) }
?: vector.setNull(i)
}

is TimeNanoVector -> column.convertToLocalTime()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value.toNanoOfDay()) }
?: vector.setNull(i)
}

is TimeMicroVector -> column.convertToLocalTime()
.forEachIndexed { i, value ->
value?.also { vector.set(i, value.toNanoOfDay() / 1000) }
?: vector.setNull(i)
}

is TimeMilliVector -> column.convertToLocalTime()
.forEachIndexed { i, value ->
value?.also { vector.set(i, (value.toNanoOfDay() / 1000 / 1000).toInt()) }
?: vector.setNull(i)
}

is TimeSecVector -> column.convertToLocalTime()
.forEachIndexed { i, value ->
value?.also { vector.set(i, (value.toNanoOfDay() / 1000 / 1000 / 1000).toInt()) }
?: vector.setNull(i)
}

else -> {
// TODO implement other vector types from [readField] (VarBinaryVector, UIntVector, DurationVector, StructVector) and may be others (ListVector, FixedSizeListVector etc)
throw NotImplementedError("Saving to ${vector.javaClass.canonicalName} is currently not implemented")
Expand All @@ -154,7 +243,12 @@ internal class ArrowWriterImpl(
/**
* Create Arrow FieldVector with [column] content cast to [field] type according to [strictType] and [strictNullable] settings.
*/
private fun allocateVectorAndInfill(field: Field, column: AnyCol?, strictType: Boolean, strictNullable: Boolean): FieldVector {
private fun allocateVectorAndInfill(
field: Field,
column: AnyCol?,
strictType: Boolean,
strictNullable: Boolean,
): FieldVector {
val containNulls = (column == null || column.hasNulls())
// Convert the column to type specified in field. (If we already have target type, convertTo will do nothing)

Expand All @@ -163,12 +257,19 @@ internal class ArrowWriterImpl(
} catch (e: CellConversionException) {
if (strictType) {
// If conversion failed but strictType is enabled, throw the exception
val mismatch = ConvertingMismatch.TypeConversionFail.ConversionFailError(e.column?.name() ?: "", e.row, e)
val mismatch =
ConvertingMismatch.TypeConversionFail.ConversionFailError(e.column?.name() ?: "", e.row, e)
mismatchSubscriber(mismatch)
throw ConvertingException(mismatch)
} else {
// If strictType is not enabled, use original data with its type. Target nullable is saved at this step.
mismatchSubscriber(ConvertingMismatch.TypeConversionFail.ConversionFailIgnored(e.column?.name() ?: "", e.row, e))
mismatchSubscriber(
ConvertingMismatch.TypeConversionFail.ConversionFailIgnored(
e.column?.name() ?: "",
e.row,
e
)
)
column to column!!.toArrowField(mismatchSubscriber)
}
} catch (e: TypeConverterNotFoundException) {
Expand Down Expand Up @@ -197,8 +298,17 @@ internal class ArrowWriterImpl(
mismatchSubscriber(mismatch)
throw ConvertingException(mismatch)
} else {
mismatchSubscriber(ConvertingMismatch.NullableMismatch.NullValueIgnored(actualField.name, firstNullValue))
Field(actualField.name, FieldType(true, actualField.fieldType.type, actualField.fieldType.dictionary), actualField.children).createVector(allocator)!!
mismatchSubscriber(
ConvertingMismatch.NullableMismatch.NullValueIgnored(
actualField.name,
firstNullValue
)
)
Field(
actualField.name,
FieldType(true, actualField.fieldType.type, actualField.fieldType.dictionary),
actualField.children
).createVector(allocator)!!
}
} else {
actualField.createVector(allocator)!!
Expand Down
Loading