yihua commented on code in PR #14335:
URL: https://github.com/apache/hudi/pull/14335#discussion_r2561488063
##########
hudi-spark-datasource/hudi-spark3.4.x/src/main/scala/org/apache/spark/sql/adapter/Spark3_4Adapter.scala:
##########
@@ -171,7 +173,15 @@ class Spark3_4Adapter extends BaseSpark3Adapter {
RebaseDateTime.RebaseSpec(LegacyBehaviorPolicy.withName(policy))
}
- override def enableParquetFilterPushDownStringPredicate(conf: SQLConf):
Boolean = {
- conf.parquetFilterPushDownStringPredicate
+ override def createParquetFilters(schema: MessageType, storageConf:
StorageConfiguration[_], sqlConf: SQLConf): ParquetFilters = {
+ new ParquetFilters(
+ schema,
+ storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_DATE_ENABLED.key,
sqlConf.parquetFilterPushDownDate),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_TIMESTAMP_ENABLED.key,
sqlConf.parquetFilterPushDownTimestamp),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_DECIMAL_ENABLED.key,
sqlConf.parquetFilterPushDownDecimal),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_STRING_PREDICATE_ENABLED.key,
sqlConf.parquetFilterPushDownStringPredicate),
Review Comment:
Same question on the changes for higher Spark versions
##########
hudi-spark-datasource/hudi-spark3.4.x/src/main/scala/org/apache/spark/sql/adapter/Spark3_4Adapter.scala:
##########
@@ -171,7 +173,15 @@ class Spark3_4Adapter extends BaseSpark3Adapter {
RebaseDateTime.RebaseSpec(LegacyBehaviorPolicy.withName(policy))
}
- override def enableParquetFilterPushDownStringPredicate(conf: SQLConf):
Boolean = {
- conf.parquetFilterPushDownStringPredicate
+ override def createParquetFilters(schema: MessageType, storageConf:
StorageConfiguration[_], sqlConf: SQLConf): ParquetFilters = {
+ new ParquetFilters(
+ schema,
+ storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_DATE_ENABLED.key,
sqlConf.parquetFilterPushDownDate),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_TIMESTAMP_ENABLED.key,
sqlConf.parquetFilterPushDownTimestamp),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_DECIMAL_ENABLED.key,
sqlConf.parquetFilterPushDownDecimal),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_STRING_PREDICATE_ENABLED.key,
sqlConf.parquetFilterPushDownStringPredicate),
Review Comment:
Or is it a bug that the config is assigned improperly?
##########
hudi-spark-datasource/hudi-spark3.4.x/src/main/scala/org/apache/spark/sql/adapter/Spark3_4Adapter.scala:
##########
@@ -171,7 +173,15 @@ class Spark3_4Adapter extends BaseSpark3Adapter {
RebaseDateTime.RebaseSpec(LegacyBehaviorPolicy.withName(policy))
}
- override def enableParquetFilterPushDownStringPredicate(conf: SQLConf):
Boolean = {
- conf.parquetFilterPushDownStringPredicate
+ override def createParquetFilters(schema: MessageType, storageConf:
StorageConfiguration[_], sqlConf: SQLConf): ParquetFilters = {
+ new ParquetFilters(
+ schema,
+ storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_DATE_ENABLED.key,
sqlConf.parquetFilterPushDownDate),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_TIMESTAMP_ENABLED.key,
sqlConf.parquetFilterPushDownTimestamp),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_DECIMAL_ENABLED.key,
sqlConf.parquetFilterPushDownDecimal),
+
storageConf.getBoolean(SQLConf.PARQUET_FILTER_PUSHDOWN_STRING_PREDICATE_ENABLED.key,
sqlConf.parquetFilterPushDownStringPredicate),
Review Comment:
The original config key used in `HoodieSParkParquetReader` is
`SQLConf.PARQUET_FILTER_PUSHDOWN_STRING_STARTSWITH_ENABLED`. Is there a reason
to change it?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]