Skip to content

Add shardId to kinesis Row #68

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add shardId to kinesis Row #68

Show file tree
Hide file tree
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
1 change: 1 addition & 0 deletions src/main/scala/org/apache/spark/sql/connector/kinesis/KinesisV2PartitionReader.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,6 +294,7 @@ class KinesisV2PartitionReader (schema: StructType,
case "subSequenceNumber" => UTF8String.fromString(record.sequenceNumber.subSequenceNumber.toString)
case "approximateArrivalTimestamp" => ChronoUnit.MICROS.between(Instant.EPOCH, record.approximateArrivalTimestamp)
case "data" => record.data
case "shardId" => UTF8String.fromString(kinesisShardId)
case name =>
throw new UnsupportedOperationException("Unsupported field name in schema " + name)
}.toSeq)
Expand Down
3 changes: 2 additions & 1 deletion src/main/scala/org/apache/spark/sql/connector/kinesis/client/KinesisClientFactory.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,8 @@ object KinesisClientFactory {
StructField("streamName", StringType),
StructField("partitionKey", StringType),
StructField("sequenceNumber", StringType),
StructField("approximateArrivalTimestamp", TimestampType))
StructField("approximateArrivalTimestamp", TimestampType),
StructField("shardId", StringType))
)

def createConsumer(options: KinesisOptions, streamName: String, endpointUrl: String): KinesisClientConsumer = {
Expand Down
5 changes: 3 additions & 2 deletions src/test/scala/org/apache/spark/sql/connector/kinesis/it/KinesisSourceItSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -801,8 +801,8 @@ abstract class KinesisSourceItSuite(aggregateTestData: Boolean,
assert(kinesis.schema == KinesisClientFactory.kinesisSchema)

val result = kinesis.selectExpr("CAST(data AS STRING)", "streamName",
"partitionKey", "sequenceNumber", "CAST(approximateArrivalTimestamp AS TIMESTAMP)")
.as[(String, String, String, String, Long)]
"partitionKey", "sequenceNumber", "CAST(approximateArrivalTimestamp AS TIMESTAMP)", "shardId")
.as[(String, String, String, String, Long, String)]

val query = result.writeStream
.format("memory")
Expand All @@ -823,6 +823,7 @@ abstract class KinesisSourceItSuite(aggregateTestData: Boolean,

assert(row.getAs[String]("streamName") === localTestUtils.streamName, s"Unexpected results: $row")
assert(row.getAs[String]("partitionKey") === "1", s"Unexpected results: $row")
assert(localTestUtils.getShards.map(_.getShardId).contains(row.getAs[String]("shardId")), s"Unexpected results: $row")
query.stop()
} finally {
localTestUtils.deleteStream()
Expand Down