Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/12102#discussion_r58289639
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
---
@@ -523,44 +497,32 @@ private[joins] object LongHashedRelation {
}
}
- if (keyIsUnique) {
- if (hashTable.size() > (maxKey - minKey) * DENSE_FACTOR) {
- // The keys are dense enough, so use LongArrayRelation
- val length = (maxKey - minKey).toInt + 1
- val sizes = new Array[Int](length)
- val offsets = new Array[Int](length)
- var offset = 0
- var i = 0
- while (i < length) {
- val rows = hashTable.get(i + minKey)
- if (rows != null) {
- offsets(i) = offset
- sizes(i) = rows(0).getSizeInBytes
- offset += sizes(i)
- }
- i += 1
- }
- val bytes = new Array[Byte](offset)
- i = 0
- while (i < length) {
- val rows = hashTable.get(i + minKey)
- if (rows != null) {
- rows(0).writeToMemory(bytes, Platform.BYTE_ARRAY_OFFSET +
offsets(i))
- }
- i += 1
+ if (keyIsUnique && hashTable.size() > (maxKey - minKey) *
DENSE_FACTOR) {
+ // The keys are dense enough, so use LongArrayRelation
+ val length = (maxKey - minKey).toInt + 1
+ val sizes = new Array[Int](length)
+ val offsets = new Array[Int](length)
+ var offset = 0
+ var i = 0
+ while (i < length) {
+ val rows = hashTable.get(i + minKey)
+ if (rows != null) {
+ offsets(i) = offset
+ sizes(i) = rows(0).getSizeInBytes
+ offset += sizes(i)
}
- new LongArrayRelation(numFields, minKey, offsets, sizes, bytes)
-
- } else {
- // all the keys are unique, one row per key.
- val uniqHashTable = new JavaHashMap[Long,
UnsafeRow](hashTable.size)
- val iter = hashTable.entrySet().iterator()
- while (iter.hasNext) {
- val entry = iter.next()
- uniqHashTable.put(entry.getKey, entry.getValue()(0))
+ i += 1
+ }
+ val bytes = new Array[Byte](offset)
+ i = 0
+ while (i < length) {
+ val rows = hashTable.get(i + minKey)
+ if (rows != null) {
+ rows(0).writeToMemory(bytes, Platform.BYTE_ARRAY_OFFSET +
offsets(i))
}
- new UniqueLongHashedRelation(uniqHashTable)
+ i += 1
}
+ new LongArrayRelation(numFields, minKey, offsets, sizes, bytes)
--- End diff --
These will be replaced by LongBytesMap soon
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
