sahnib commented on code in PR #44961:
URL: https://github.com/apache/spark/pull/44961#discussion_r1473574772
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/RocksDBStateStoreProvider.scala:
##########
@@ -65,6 +65,43 @@ private[sql] class RocksDBStateStoreProvider
value
}
+ override def valuesIterator(key: UnsafeRow, colFamilyName: String):
Iterator[UnsafeRow] = {
+ verify(key != null, "Key cannot be null")
+ verify(encoder.supportsMultipleValuesPerKey, "valuesIterator requires a
encoder " +
+ "that supports multiple values for a single key.")
+ val valueIterator =
encoder.decodeValues(rocksDB.get(encoder.encodeKey(key), colFamilyName))
+
+ if (!isValidated && valueIterator.nonEmpty) {
+ new Iterator[UnsafeRow] {
+ override def hasNext: Boolean = {
+ valueIterator.hasNext
+ }
+
+ override def next(): UnsafeRow = {
+ val value = valueIterator.next()
+ if (!isValidated && value != null) {
+ StateStoreProvider.validateStateRowFormat(
+ key, keySchema, value, valueSchema, storeConf)
+ isValidated = true
+ }
+ value
+ }
+ }
+ } else {
+ valueIterator
+ }
+ }
+
+ override def merge(key: UnsafeRow, value: UnsafeRow,
+ colFamilyName: String =
StateStore.DEFAULT_COL_FAMILY_NAME): Unit = {
Review Comment:
Fixed,
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala:
##########
@@ -67,6 +67,16 @@ trait ReadStateStore {
def get(key: UnsafeRow,
colFamilyName: String = StateStore.DEFAULT_COL_FAMILY_NAME): UnsafeRow
+ /**
+ * Provides an iterator containing all values for a particular key. The
values are merged
+ * together and stored as a byte Array in the underlying state store. This
operation relies
+ * on state store encoder to be able to split the single array into multiple
values.
+ *
+ * Also see [[MultiValuedStateEncoder]] which supports encoding/decoding
multiple values per key.
+ */
+ def valuesIterator(key: UnsafeRow,
+ colFamilyName: String = StateStore.DEFAULT_COL_FAMILY_NAME):
Iterator[UnsafeRow]
Review Comment:
Fixed.
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStore.scala:
##########
@@ -121,6 +131,9 @@ trait StateStore extends ReadStateStore {
def remove(key: UnsafeRow,
colFamilyName: String = StateStore.DEFAULT_COL_FAMILY_NAME): Unit
+ def merge(key: UnsafeRow, value: UnsafeRow,
+ colFamilyName: String = StateStore.DEFAULT_COL_FAMILY_NAME): Unit
Review Comment:
Fixed.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
