danny0405 commented on code in PR #8102:
URL: https://github.com/apache/hudi/pull/8102#discussion_r1157165945
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/source/FileIndex.java:
##########
@@ -60,23 +61,29 @@ public class FileIndex {
private final Path path;
private final RowType rowType;
+ private final boolean tableExists;
private final HoodieMetadataConfig metadataConfig;
+ private final PartitionPruners.PartitionPruner partitionPruner;
private final boolean dataSkippingEnabled;
+ private final DataPruner dataPruner;
private List<String> partitionPaths; // cache of partition paths
- private List<ResolvedExpression> filters; // push down filters
- private final boolean tableExists;
- private DataPruner dataPruner;
- private FileIndex(Path path, Configuration conf, RowType rowType) {
+ private FileIndex(Path path, Configuration conf, RowType rowType, DataPruner
dataPruner, PartitionPruners.PartitionPruner partitionPruner) {
this.path = path;
this.rowType = rowType;
+ this.tableExists = StreamerUtil.tableExists(path.toString(),
HadoopConfigurations.getHadoopConf(conf));
this.metadataConfig = metadataConfig(conf);
this.dataSkippingEnabled =
conf.getBoolean(FlinkOptions.READ_DATA_SKIPPING_ENABLED);
- this.tableExists = StreamerUtil.tableExists(path.toString(),
HadoopConfigurations.getHadoopConf(conf));
+ this.dataPruner = initializeDataPruner(dataPruner);
Review Comment:
this.dataPruner = isDataSkippingFeasible() ? dataPruner : null;
--
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]
