Skip to content

fix: include per-column details in exportBatch row count mismatch error #4214

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
andygrove wants to merge 1 commit into
base: main
Choose a base branch
from
+10 −6
Draft

fix: include per-column details in exportBatch row count mismatch error #4214

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
16 changes: 10 additions & 6 deletions common/src/main/scala/org/apache/comet/vector/NativeUtil.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@ class NativeUtil {
arrayAddrs: Array[Long],
schemaAddrs: Array[Long],
batch: ColumnarBatch): Int = {
val numRows = mutable.ArrayBuffer.empty[Int]
val numRows = mutable.ArrayBuffer.empty[(Int, Int, String)]

(0 until batch.numCols()).foreach { index =>
batch.column(index) match {
Expand All @@ -122,7 +122,7 @@ class NativeUtil {
val valueVector = valuesVector.getValueVector

// Use the selection vector's logical row count
numRows += selectionVector.numValues()
numRows += ((selectionVector.numValues(), index, selectionVector.getClass.getSimpleName))

val provider = if (valueVector.getField.getDictionary != null) {
valuesVector.getDictionaryProvider
Expand All @@ -143,7 +143,7 @@ class NativeUtil {
case a: CometVector =>
val valueVector = a.getValueVector

numRows += valueVector.getValueCount
numRows += ((valueVector.getValueCount, index, a.getClass.getSimpleName))

val provider = if (valueVector.getField.getDictionary != null) {
a.getDictionaryProvider
Expand All @@ -168,9 +168,13 @@ class NativeUtil {
}
}

if (numRows.distinct.length > 1) {
val distinctRowCounts = numRows.map(_._1).distinct
if (distinctRowCounts.length > 1) {
val details = numRows
.map { case (rows, idx, className) => s"col[$idx]=$rows ($className)" }
.mkString(", ")
throw new SparkException(
s"Number of rows in each column should be the same, but got [${numRows.distinct}]")
s"Number of rows in each column should be the same, but got [$details]")
}

// `ColumnarBatch.numRows` might return a different number than the actual number of rows in
Expand All @@ -179,7 +183,7 @@ class NativeUtil {
// logical number of rows which is less than actual number of rows due to row deletion.
// Similarly, CometSelectionVector represents a different number of logical rows than the
// underlying vector.
numRows.headOption.getOrElse(batch.numRows())
numRows.headOption.map(_._1).getOrElse(batch.numRows())
}

/**
Expand Down
Loading