Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/266#discussion_r11319296
--- Diff:
streaming/src/main/scala/org/apache/spark/streaming/util/RawTextHelper.scala ---
@@ -19,40 +19,22 @@ package org.apache.spark.streaming.util
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
-import it.unimi.dsi.fastutil.objects.{Object2LongOpenHashMap => OLMap}
+import org.apache.spark.util.collection.OpenHashMap
import scala.collection.JavaConversions.mapAsScalaMap
private[streaming]
object RawTextHelper {
/**
- * Splits lines and counts the words in them using specialized
object-to-long hashmap
- * (to avoid boxing-unboxing overhead of Long in java/scala HashMap)
+ * Splits lines and counts the words.
*/
def splitAndCountPartitions(iter: Iterator[String]): Iterator[(String,
Long)] = {
- val map = new OLMap[String]
- var i = 0
- var j = 0
- while (iter.hasNext) {
- val s = iter.next()
- i = 0
- while (i < s.length) {
- j = i
- while (j < s.length && s.charAt(j) != ' ') {
- j += 1
- }
- if (j > i) {
- val w = s.substring(i, j)
- val c = map.getLong(w)
- map.put(w, c + 1)
- }
- i = j
- while (i < s.length && s.charAt(i) == ' ') {
- i += 1
- }
- }
+ val map = new OpenHashMap[String,Long]
+ val tokenized = iter.flatMap(_.split(" ").filterNot(_.isEmpty))
+ tokenized.foreach{ s =>
+ map.changeValue(s, 1L, _ + 1L)
}
- map.toIterator.map{case (k, v) => (k, v)}
+ map.iterator
--- End diff --
Keep this code the way it was before, I think it was there for some stress
tests that passed in lots of data, to make sure the parsing is not the
bottleneck. Just switch the map over.
---
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.
---
