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

Jump to bottom

Use new getJsonObject kernel for json_tuple #10635

Merged
merged 9 commits into from
Apr 25, 2024
Merged

Use new getJsonObject kernel for json_tuple #10635

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
e4f8050
Use new getJsonObject kernel for json_tuple
thirtiseven Mar 26, 2024
e242666
fallback change, remove xfails and verify
thirtiseven Mar 27, 2024
3b9e0ac
verify
thirtiseven Apr 1, 2024
d61d339
Merge branch 'branch-24.04' into json-tuple-new-kernel
thirtiseven Apr 1, 2024
5409d58
Add a test case and reverify
thirtiseven Apr 1, 2024
cfb0eeb
Merge branch 'NVIDIA:branch-24.06' into json-tuple-new-kernel
thirtiseven Apr 23, 2024
2da8d5a
disable by default
thirtiseven Apr 24, 2024
40790a1
verify again
thirtiseven Apr 24, 2024
6b74922
add config back after off by default
thirtiseven Apr 25, 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
30 changes: 16 additions & 14 deletions sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuJsonTuple.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,10 +16,10 @@

package com.nvidia.spark.rapids

import ai.rapids.cudf.{GetJsonObjectOptions,Scalar}
import com.nvidia.spark.rapids.Arm._
import com.nvidia.spark.rapids.RapidsPluginImplicits._
import com.nvidia.spark.rapids.RmmRapidsRetryIterator.{splitSpillableInHalfByRows, withRetry}
import com.nvidia.spark.rapids.jni.JSONUtils
import com.nvidia.spark.rapids.shims.ShimExpression

import org.apache.spark.sql.catalyst.analysis.TypeCheckResult
Expand Down Expand Up @@ -59,26 +59,28 @@ case class GpuJsonTuple(children: Seq[Expression]) extends GpuGenerator
val json = inputBatch.column(generatorOffset).asInstanceOf[GpuColumnVector].getBase
val schema = Array.fill[DataType](fieldExpressions.length)(StringType)

val fieldScalars = fieldExpressions.safeMap { field =>
val fieldInstructions = fieldExpressions.map { field =>
withResourceIfAllowed(field.columnarEvalAny(inputBatch)) {
case fieldScalar: GpuScalar =>
// Specials characters like '.', '[', ']' are not supported in field names
Scalar.fromString("$." + fieldScalar.getBase.getJavaString)
val fieldString = fieldScalar.getBase.getJavaString
val key = new JSONUtils.PathInstructionJni(
JSONUtils.PathInstructionType.KEY, "", -1)
val named = new JSONUtils.PathInstructionJni(
JSONUtils.PathInstructionType.NAMED, fieldString, -1)
Array(key, named)
case _ => throw new UnsupportedOperationException(s"JSON field must be a scalar value")
}
}

withResource(fieldScalars) { fieldScalars =>
withResource(fieldScalars.safeMap(field => json.getJSONObject(field,
GetJsonObjectOptions.builder().allowSingleQuotes(true).build()))) { resultCols =>
val generatorCols = resultCols.safeMap(_.incRefCount).zip(schema).safeMap {
case (col, dataType) => GpuColumnVector.from(col, dataType)
}
val nonGeneratorCols = (0 until generatorOffset).safeMap { i =>
inputBatch.column(i).asInstanceOf[GpuColumnVector].incRefCount
}
new ColumnarBatch((nonGeneratorCols ++ generatorCols).toArray, inputBatch.numRows)
withResource(fieldInstructions.safeMap(field => JSONUtils.getJsonObject(json, 2, field))) {
resultCols =>
val generatorCols = resultCols.safeMap(_.incRefCount).zip(schema).safeMap {
case (col, dataType) => GpuColumnVector.from(col, dataType)
}
val nonGeneratorCols = (0 until generatorOffset).safeMap { i =>
inputBatch.column(i).asInstanceOf[GpuColumnVector].incRefCount
}
new ColumnarBatch((nonGeneratorCols ++ generatorCols).toArray, inputBatch.numRows)
}
}
}
Expand Down
Loading