zsxwing commented on a change in pull request #22282: [SPARK-23539][SS] Add
support for Kafka headers in Structured Streaming
URL: https://github.com/apache/spark/pull/22282#discussion_r316380289
##########
File path:
external/kafka-0-10-sql/src/main/scala/org/apache/spark/sql/kafka010/KafkaOffsetReader.scala
##########
@@ -433,4 +441,42 @@ private[kafka010] object KafkaOffsetReader {
StructField("timestamp", TimestampType),
StructField("timestampType", IntegerType)
))
+
+ val schemaWithHeaders = {
+ new StructType(schemaWithoutHeaders.fields :+ StructField("headers",
headersType))
+ }
+
+ def kafkaSchema(includeHeaders: Boolean): StructType = {
+ if (includeHeaders) schemaWithHeaders else schemaWithoutHeaders
+ }
+
+ def toInternalRowWithoutHeaders: Record => InternalRow =
+ (cr: Record) => InternalRow(
+ cr.key, cr.value, UTF8String.fromString(cr.topic), cr.partition,
cr.offset,
+ DateTimeUtils.fromJavaTimestamp(new java.sql.Timestamp(cr.timestamp)),
cr.timestampType.id
+ )
+
+ def toInternalRowWithHeaders: Record => InternalRow =
+ (cr: Record) => InternalRow(
+ cr.key, cr.value, UTF8String.fromString(cr.topic), cr.partition,
cr.offset,
+ DateTimeUtils.fromJavaTimestamp(new java.sql.Timestamp(cr.timestamp)),
cr.timestampType.id,
+ if (cr.headers.iterator().hasNext) {
+ new GenericArrayData(cr.headers.iterator().asScala
+ .map(header =>
+ InternalRow(UTF8String.fromString(header.key()), header.value())
+ ).toArray)
+ } else {
+ null
+ }
+ )
+
+ def toUnsafeRowWithoutHeadersProjector: Record => UnsafeRow =
+ (cr: Record) =>
UnsafeProjection.create(schemaWithoutHeaders)(toInternalRowWithoutHeaders(cr))
Review comment:
I meant we should create one `UnsafeProjection` and reuse it for all records
in the same task.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
