kgyrtkirk commented on a change in pull request #1400:
URL: https://github.com/apache/hive/pull/1400#discussion_r514195755
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/optimizer/correlation/ReduceSinkDeDuplicationUtils.java
##########
@@ -181,6 +183,23 @@ public static boolean merge(HiveConf hiveConf,
ReduceSinkOperator cRS, ReduceSin
TableDesc keyTable = PlanUtils.getReduceKeyTableDesc(new
ArrayList<FieldSchema>(), pRS
.getConf().getOrder(), pRS.getConf().getNullOrder());
pRS.getConf().setKeySerializeInfo(keyTable);
+ } else if (cRS.getConf().getKeyCols() != null &&
cRS.getConf().getKeyCols().size() > 0) {
+ ArrayList<String> keyColNames = Lists.newArrayList();
+ for (ExprNodeDesc keyCol : pRS.getConf().getKeyCols()) {
+ String keyColName = keyCol.getExprString();
+ keyColNames.add(keyColName);
+ }
+ List<FieldSchema> fields =
PlanUtils.getFieldSchemasFromColumnList(pRS.getConf().getKeyCols(),
+ keyColNames, 0, "");
+ TableDesc keyTable = PlanUtils.getReduceKeyTableDesc(fields,
pRS.getConf().getOrder(),
+ pRS.getConf().getNullOrder());
+ ArrayList<String> outputKeyCols = Lists.newArrayList();
+ for (int i = 0; i < fields.size(); i++) {
+ outputKeyCols.add(fields.get(i).getName());
+ }
+ pRS.getConf().setOutputKeyColumnNames(outputKeyCols);
+ pRS.getConf().setKeySerializeInfo(keyTable);
+
pRS.getConf().setNumDistributionKeys(cRS.getConf().getNumDistributionKeys());
}
Review comment:
yes; you are correct
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
