You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by GitBox <gi...@apache.org> on 2022/10/20 09:09:49 UTC

[GitHub] [hudi] xushiyan commented on a diff in pull request #6448: [HUDI-4647] Keep the hive sync settings in spark sql consistent

xushiyan commented on code in PR #6448:
URL: https://github.com/apache/hudi/pull/6448#discussion_r1000360939


##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/spark/sql/hudi/ProvidesHoodieConfig.scala:
##########
@@ -266,21 +281,27 @@ trait ProvidesHoodieConfig extends Logging {
         KEYGENERATOR_CLASS_NAME.key -> classOf[SqlKeyGenerator].getCanonicalName,
         SqlKeyGenerator.ORIGINAL_KEYGEN_CLASS_NAME -> tableConfig.getKeyGeneratorClassName,
         OPERATION.key -> DataSourceWriteOptions.DELETE_OPERATION_OPT_VAL,
-        PARTITIONPATH_FIELD.key -> tableConfig.getPartitionFieldProp,
-        HoodieSyncConfig.META_SYNC_ENABLED.key -> hiveSyncConfig.getString(HoodieSyncConfig.META_SYNC_ENABLED.key),
-        HiveSyncConfigHolder.HIVE_SYNC_ENABLED.key -> hiveSyncConfig.getString(HiveSyncConfigHolder.HIVE_SYNC_ENABLED.key),
-        HiveSyncConfigHolder.HIVE_SYNC_MODE.key -> hiveSyncConfig.getStringOrDefault(HiveSyncConfigHolder.HIVE_SYNC_MODE, HiveSyncMode.HMS.name()),
-        HoodieSyncConfig.META_SYNC_DATABASE_NAME.key -> hiveSyncConfig.getStringOrDefault(HoodieSyncConfig.META_SYNC_DATABASE_NAME),
-        HoodieSyncConfig.META_SYNC_TABLE_NAME.key -> hiveSyncConfig.getStringOrDefault(HoodieSyncConfig.META_SYNC_TABLE_NAME),
-        HiveSyncConfigHolder.HIVE_SUPPORT_TIMESTAMP_TYPE.key -> hiveSyncConfig.getBoolean(HiveSyncConfigHolder.HIVE_SUPPORT_TIMESTAMP_TYPE).toString,
-        HoodieSyncConfig.META_SYNC_PARTITION_FIELDS.key -> partitionFields,
-        HoodieSyncConfig.META_SYNC_PARTITION_EXTRACTOR_CLASS.key -> hiveSyncConfig.getStringOrDefault(HoodieSyncConfig.META_SYNC_PARTITION_EXTRACTOR_CLASS),
+        PARTITIONPATH_FIELD.key -> partitionFields,
         HoodieWriteConfig.DELETE_PARALLELISM_VALUE.key -> hoodieProps.getString(HoodieWriteConfig.DELETE_PARALLELISM_VALUE.key, "200"),
         SqlKeyGenerator.PARTITION_SCHEMA -> partitionSchema.toDDL
-      )
+      ) ++ commonHiveSyncConfig(hiveSyncConfig, partitionFields)
     }
   }
 
+  def commonHiveSyncConfig(hiveSyncConfig: HiveSyncConfig, partitionFields: String): Map[String, String] = {
+    Map(
+      HoodieSyncConfig.META_SYNC_ENABLED.key -> hiveSyncConfig.getString(HoodieSyncConfig.META_SYNC_ENABLED.key),
+      HiveSyncConfigHolder.HIVE_SYNC_ENABLED.key -> hiveSyncConfig.getString(HiveSyncConfigHolder.HIVE_SYNC_ENABLED.key),
+      HiveSyncConfigHolder.HIVE_SYNC_MODE.key -> hiveSyncConfig.getString(HiveSyncConfigHolder.HIVE_SYNC_MODE),

Review Comment:
   since most of sql scenarios have already been using HMS mode, we should ensure the existing sql behavior is not affected. So we need to keep it HMS and only for merge into this is changed. (which is acceptable for consistency reason)



-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@hudi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org