zhangyue19921010 commented on code in PR #13060:
URL: https://github.com/apache/hudi/pull/13060#discussion_r2026282689
##########
hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/source/FileIndex.java:
##########
@@ -68,25 +69,30 @@ public class FileIndex implements Serializable {
private final org.apache.hadoop.conf.Configuration hadoopConf;
private final PartitionPruners.PartitionPruner partitionPruner; // for
partition pruning
private final ColumnStatsProbe colStatsProbe; // for
probing column stats
- private final int dataBucket; // for
bucket pruning
+ private final int dataBucketHashing; //
for bucket pruning
private List<String> partitionPaths; // cache of
partition paths
private final FileStatsIndex fileStatsIndex; // for data
skipping
+ private final NumBucketsFunction numBucketsFunction;
private FileIndex(
StoragePath path,
Configuration conf,
RowType rowType,
ColumnStatsProbe colStatsProbe,
PartitionPruners.PartitionPruner partitionPruner,
- int dataBucket) {
+ int dataBucketHashing,
+ NumBucketsFunction numBucketsFunction) {
this.path = path;
this.hadoopConf = HadoopConfigurations.getHadoopConf(conf);
this.tableExists = StreamerUtil.tableExists(path.toString(), hadoopConf);
this.metadataConfig = StreamerUtil.metadataConfig(conf);
this.colStatsProbe =
isDataSkippingFeasible(conf.get(FlinkOptions.READ_DATA_SKIPPING_ENABLED)) ?
colStatsProbe : null;
this.partitionPruner = partitionPruner;
- this.dataBucket = dataBucket;
Review Comment:
evolve this dataBucket to a function
--
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]
