SourabhBadhya commented on code in PR #5251:
URL: https://github.com/apache/hive/pull/5251#discussion_r1617033067
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/mapreduce/IcebergInputFormat.java:
##########
@@ -312,33 +314,43 @@ private static final class IcebergRecordReader<T> extends
RecordReader<Void, T>
private CloseableIterator<T> currentIterator;
private Table table;
private boolean fetchVirtualColumns;
+ private boolean isMerge = false;
+ private IcebergMergeSplit mergeSplit;
Review Comment:
Created a new record reader impl.
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/mapreduce/IcebergInputFormat.java:
##########
@@ -312,33 +314,43 @@ private static final class IcebergRecordReader<T> extends
RecordReader<Void, T>
private CloseableIterator<T> currentIterator;
private Table table;
private boolean fetchVirtualColumns;
+ private boolean isMerge = false;
+ private IcebergMergeSplit mergeSplit;
@Override
public void initialize(InputSplit split, TaskAttemptContext newContext) {
// For now IcebergInputFormat does its own split planning and does not
accept FileSplit instances
- CombinedScanTask task = ((IcebergSplit) split).task();
this.context = newContext;
this.conf = newContext.getConfiguration();
- this.table = SerializationUtil.deserializeFromBase64(
- conf.get(InputFormatConfig.SERIALIZED_TABLE_PREFIX +
conf.get(InputFormatConfig.TABLE_IDENTIFIER)));
+ this.table = HiveIcebergStorageHandler.table(conf,
conf.get(InputFormatConfig.TABLE_IDENTIFIER));
HiveIcebergStorageHandler.checkAndSetIoConfig(conf, table);
- this.tasks = task.files().iterator();
this.nameMapping =
table.properties().get(TableProperties.DEFAULT_NAME_MAPPING);
this.caseSensitive = conf.getBoolean(InputFormatConfig.CASE_SENSITIVE,
InputFormatConfig.CASE_SENSITIVE_DEFAULT);
this.expectedSchema = readSchema(conf, table, caseSensitive);
this.reuseContainers =
conf.getBoolean(InputFormatConfig.REUSE_CONTAINERS, false);
this.inMemoryDataModel =
conf.getEnum(InputFormatConfig.IN_MEMORY_DATA_MODEL,
InputFormatConfig.InMemoryDataModel.GENERIC);
this.fetchVirtualColumns = InputFormatConfig.fetchVirtualColumns(conf);
+ if (split instanceof IcebergMergeSplit) {
+ this.isMerge = true;
+ this.mergeSplit = (IcebergMergeSplit) split;
+ } else {
+ CombinedScanTask task = ((IcebergSplit) split).task();
+ this.tasks = task.files().iterator();
+ }
Review Comment:
Done.
--
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: gitbox-unsubscr...@hive.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org
For additional commands, e-mail: gitbox-h...@hive.apache.org
