JingsongLi commented on a change in pull request #10922:
[FLINK-11899][parquet][table-runtime] Introduce ParquetColumnarRowSplitReader
URL: https://github.com/apache/flink/pull/10922#discussion_r386978811
##########
File path:
flink-connectors/flink-connector-hive/src/main/java/org/apache/flink/connectors/hive/read/HiveTableInputFormat.java
##########
@@ -113,16 +114,74 @@ public void
configure(org.apache.flink.configuration.Configuration parameters) {
@Override
public void open(HiveTableInputSplit split) throws IOException {
- if (!useMapRedReader &&
useOrcVectorizedRead(split.getHiveTablePartition())) {
+ HiveTablePartition partition = split.getHiveTablePartition();
+ if (!useMapRedReader && useOrcVectorizedRead(partition)) {
this.reader = new HiveVectorizedOrcSplitReader(
hiveVersion, jobConf, fieldNames,
fieldTypes, selectedFields, split);
+ } else if (!useMapRedReader &&
useParquetVectorizedRead(partition)) {
+ this.reader = new HiveVectorizedParquetSplitReader(
+ hiveVersion, jobConf, fieldNames,
fieldTypes, selectedFields, split);
} else {
this.reader = new HiveMapredSplitReader(jobConf,
partitionKeys, fieldTypes, selectedFields, split,
HiveShimLoader.loadHiveShim(hiveVersion));
}
currentReadCount = 0L;
}
+ private boolean isComplexType(LogicalType t) {
+ switch (t.getTypeRoot()) {
+ case CHAR:
+ case VARCHAR:
+ case BOOLEAN:
+ case BINARY:
+ case VARBINARY:
+ case DECIMAL:
+ case TINYINT:
+ case SMALLINT:
+ case INTEGER:
+ case BIGINT:
+ case FLOAT:
+ case DOUBLE:
+ case DATE:
+ case TIME_WITHOUT_TIME_ZONE:
+ case TIMESTAMP_WITHOUT_TIME_ZONE:
+ case TIMESTAMP_WITH_LOCAL_TIME_ZONE:
+ return false;
+ case TIMESTAMP_WITH_TIME_ZONE:
+ case INTERVAL_YEAR_MONTH:
+ case INTERVAL_DAY_TIME:
Review comment:
I'll rename to `isVectorizationSupport`
----------------------------------------------------------------
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:
us...@infra.apache.org
With regards,
Apache Git Services
