Skip to content

[SPARK-53973][Avro] Classify errors for AvroOptions boolean casting failure #52686

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

Closed
siying wants to merge 2 commits into from
Closed

[SPARK-53973][Avro] Classify errors for AvroOptions boolean casting failure #52686

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
f572393
[SPARK-53973][Avro] Classify errors for AvroOptions boolean casting f…
siying Oct 21, 2025
704e5f5
consolidate code
siying Oct 21, 2025
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
20 changes: 20 additions & 0 deletions connector/avro/src/test/scala/org/apache/spark/sql/avro/AvroSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3094,6 +3094,26 @@ abstract class AvroSuite
assert(AvroOptions.isValidOption("recursiveFieldMaxDepth"))
}

test("SPARK-53973: boolean Avro options reject non-boolean values") {
Seq(
AvroOptions.STABLE_ID_FOR_UNION_TYPE,
AvroOptions.POSITIONAL_FIELD_MATCHING,
AvroOptions.IGNORE_EXTENSION
).foreach { opt =>
val e = intercept[AnalysisException] {
AvroOptions(Map(opt -> "not_bool"))
}
checkError(
exception = e,
condition = "STDS_INVALID_OPTION_VALUE.WITH_MESSAGE",
parameters = Map(
"optionName" -> opt,
"message" -> "Cannot cast value 'not_bool' to Boolean."
)
)
}
}

test("SPARK-46633: read file with empty blocks") {
for (maxPartitionBytes <- Seq(100, 100000, 100000000)) {
withSQLConf(SQLConf.FILES_MAX_PARTITION_BYTES.key -> s"$maxPartitionBytes") {
Expand Down
25 changes: 18 additions & 7 deletions sql/core/src/main/scala/org/apache/spark/sql/avro/AvroOptions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,21 @@ private[sql] class AvroOptions(

import AvroOptions._

private def parseBoolean(optionName: String, value: String): Boolean = {
try {
value.toBoolean
} catch {
case _: IllegalArgumentException =>
throw QueryCompilationErrors.avroOptionsException(
optionName,
s"Cannot cast value '$value' to Boolean.")
}
}

private def getBoolean(optionName: String, defaultValue: => Boolean): Boolean = {
parameters.get(optionName).map(v => parseBoolean(optionName, v)).getOrElse(defaultValue)
}

def this(parameters: Map[String, String], conf: Configuration) = {
this(CaseInsensitiveMap(parameters), conf)
}
Expand Down Expand Up @@ -78,8 +93,7 @@ private[sql] class AvroOptions(
* name. This allows for a structurally equivalent Catalyst schema to be used with an Avro schema
* whose field names do not match. Defaults to false.
*/
val positionalFieldMatching: Boolean =
parameters.get(POSITIONAL_FIELD_MATCHING).exists(_.toBoolean)
val positionalFieldMatching: Boolean = getBoolean(POSITIONAL_FIELD_MATCHING, defaultValue = false)

/**
* Top level record name in write result, which is required in Avro spec.
Expand Down Expand Up @@ -107,10 +121,7 @@ private[sql] class AvroOptions(
AvroFileFormat.IgnoreFilesWithoutExtensionProperty,
ignoreFilesWithoutExtensionByDefault)

parameters
.get(IGNORE_EXTENSION)
.map(_.toBoolean)
.getOrElse(!ignoreFilesWithoutExtension)
getBoolean(IGNORE_EXTENSION, defaultValue = !ignoreFilesWithoutExtension)
}

/**
Expand All @@ -134,7 +145,7 @@ private[sql] class AvroOptions(
.getOrElse(SQLConf.get.getConf(SQLConf.AVRO_REBASE_MODE_IN_READ).toString)

val useStableIdForUnionType: Boolean =
parameters.get(STABLE_ID_FOR_UNION_TYPE).map(_.toBoolean).getOrElse(false)
getBoolean(STABLE_ID_FOR_UNION_TYPE, defaultValue = false)

val stableIdPrefixForUnionType: String = parameters
.getOrElse(STABLE_ID_PREFIX_FOR_UNION_TYPE, "member_")
Expand Down