use of org.apache.hudi.common.model.BaseAvroPayload in project hudi by apache.
the class BucketAssignFunction method processRecord.
@SuppressWarnings("unchecked")
private void processRecord(HoodieRecord<?> record, Collector<O> out) throws Exception {
// 1. put the record into the BucketAssigner;
// 2. look up the state for location, if the record has a location, just send it out;
// 3. if it is an INSERT, decide the location using the BucketAssigner then send it out.
final HoodieKey hoodieKey = record.getKey();
final String recordKey = hoodieKey.getRecordKey();
final String partitionPath = hoodieKey.getPartitionPath();
final HoodieRecordLocation location;
// Only changing records need looking up the index for the location,
// append only records are always recognized as INSERT.
HoodieRecordGlobalLocation oldLoc = indexState.value();
if (isChangingRecords && oldLoc != null) {
// Set up the instant time as "U" to mark the bucket as an update bucket.
if (!Objects.equals(oldLoc.getPartitionPath(), partitionPath)) {
if (globalIndex) {
// if partition path changes, emit a delete record for old partition path,
// then update the index state using location with new partition path.
HoodieRecord<?> deleteRecord = new HoodieAvroRecord<>(new HoodieKey(recordKey, oldLoc.getPartitionPath()), payloadCreation.createDeletePayload((BaseAvroPayload) record.getData()));
deleteRecord.setCurrentLocation(oldLoc.toLocal("U"));
deleteRecord.seal();
out.collect((O) deleteRecord);
}
location = getNewRecordLocation(partitionPath);
updateIndexState(partitionPath, location);
} else {
location = oldLoc.toLocal("U");
this.bucketAssigner.addUpdate(partitionPath, location.getFileId());
}
} else {
location = getNewRecordLocation(partitionPath);
}
// always refresh the index
if (isChangingRecords) {
updateIndexState(partitionPath, location);
}
record.setCurrentLocation(location);
out.collect((O) record);
}
Aggregations