Last active
March 6, 2018 18:52
-
-
Save niqbal/3e293e2bcb800d6912a250d914c9d478 to your computer and use it in GitHub Desktop.
Experiment with the distribution of documents using Solr composite key router
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import com.niqbal.shard.ShardHash.{c, getShardNumber, router, s} | |
import org.apache.solr.common.cloud.{DocCollection, DocRouter, Slice} | |
import scala.collection.JavaConverters._ | |
import scala.collection.mutable | |
import scala.io.Source | |
class ShardHash { | |
def createCollection(nSlices: Integer, router: DocRouter): DocCollection = { | |
val ranges = router.partitionRange(nSlices, router.fullRange).asScala | |
val slices: Map[String, Slice] = | |
ranges.zipWithIndex | |
.map(x => new Slice(s"${x._2}", null, Map("range" -> x._1.asInstanceOf[AnyRef]).asJava)) | |
.map(y => (y.getName, y)).toMap | |
new DocCollection("collection1", slices.asJava, null, router) | |
} | |
} | |
object ShardHash extends App { | |
val s = new ShardHash | |
val c = s.createCollection(117, DocRouter.DEFAULT) | |
val router = c.getRouter | |
// System.out.println(c.getSlices.asScala.toList.sortBy(_.getRange).map(x => s"${x.getName} -> ${x.getRange}\n")) | |
private def getShardNumber(x: String) = { | |
router.getTargetSlice(x, null, null, null, c).getName | |
} | |
val compositeIds = Range(0, 117).map(_.toString).map(x => (getShardNumber(x), x)) | |
val shardGroups = compositeIds.groupBy(x => x._1) | |
val shardGroupSizes = shardGroups.map(shardMap => (shardMap._1, shardMap._2.size, shardMap._2.map(x=>x._2).toList)) | |
val sortedShardGroupsBySize = shardGroupSizes.toList.sortBy(x => x._2) | |
val mapOutput = sortedShardGroupsBySize.map(x => s"${x._1}:${x._3}\n") | |
System.out.println(compositeIds) | |
System.out.println(shardGroups) | |
System.out.println(shardGroupSizes) | |
System.out.println(sortedShardGroupsBySize) | |
System.out.println(mapOutput) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment