From 0f77cac4b55d83b2cdc1aa50c0c848f0720c3ed6 Mon Sep 17 00:00:00 2001 From: Claudio Atzori Date: Thu, 2 Jul 2020 12:43:51 +0200 Subject: [PATCH] fix: deduper must use queueMaxSize instead of groupMaxSize for the block definition --- .../src/main/java/eu/dnetlib/dhp/oa/dedup/Deduper.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/Deduper.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/Deduper.java index c72940deb..180f9f846 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/Deduper.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/Deduper.java @@ -37,7 +37,7 @@ public class Deduper implements Serializable { public static JavaPairRDD createSortedBlocks( JavaPairRDD mapDocs, DedupConfig config) { final String of = config.getWf().getOrderField(); - final int maxQueueSize = config.getWf().getGroupMaxSize(); + final int maxQueueSize = config.getWf().getQueueMaxSize(); return mapDocs // the reduce is just to be sure that we haven't document with same id