cloud-fan commented on a change in pull request #29342:
URL: https://github.com/apache/spark/pull/29342#discussion_r469060087
##########
File path: core/src/main/java/org/apache/spark/unsafe/map/BytesToBytesMap.java
##########
@@ -428,6 +428,61 @@ public MapIterator destructiveIterator() {
return new MapIterator(numValues, new Location(), true);
}
+ /**
+ * Iterator for the entries of this map. This is to first iterate over key
index array
+ * `longArray` then accessing values in `dataPages`. NOTE: this is different
from `MapIterator`
+ * in the sense that key index is preserved here (See `UnsafeHashedRelation`
for example of usage).
+ */
+ public final class MapIteratorWithKeyIndex implements Iterator<Location> {
+
+ private int keyIndex = 0;
+ private int numRecords;
+ private final Location loc;
+
+ private MapIteratorWithKeyIndex(int numRecords, Location loc) {
+ this.numRecords = numRecords;
+ this.loc = loc;
+ }
+
+ @Override
+ public boolean hasNext() {
+ return numRecords > 0;
+ }
+
+ @Override
+ public Location next() {
+ if (!loc.isDefined() || !loc.nextValue()) {
+ while (longArray.get(keyIndex * 2) == 0) {
+ keyIndex++;
+ }
+ loc.with(keyIndex, (int) longArray.get(keyIndex * 2 + 1), true);
+ keyIndex++;
+ }
+ numRecords--;
+ return loc;
+ }
+ }
+
+ /**
+ * Returns an iterator for iterating over the entries of this map,
+ * by first iterating over the key index inside hash map's `longArray`.
+ *
+ * For efficiency, all calls to `next()` will return the same {@link
Location} object.
+ *
+ * The returned iterator is NOT thread-safe. If the map is modified while
iterating over it,
+ * the behavior of the returned iterator is undefined.
+ */
+ public MapIteratorWithKeyIndex iteratorWithKeyIndex() {
+ return new MapIteratorWithKeyIndex(numValues, new Location());
+ }
+
+ /**
+ * Number of allowed keys index.
Review comment:
is it the `max key index`?
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
