deniskuzZ commented on code in PR #6074:
URL: https://github.com/apache/hive/pull/6074#discussion_r2355768525
##########
iceberg/iceberg-handler/src/main/java/org/apache/iceberg/mr/hive/writer/HiveIcebergRecordWriter.java:
##########
@@ -20,34 +20,131 @@
package org.apache.iceberg.mr.hive.writer;
import java.io.IOException;
+import java.util.Arrays;
+import java.util.HashSet;
import java.util.List;
+import java.util.Optional;
+import java.util.Set;
+import java.util.stream.Collectors;
import org.apache.hadoop.io.Writable;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.Table;
+import org.apache.iceberg.data.GenericRecord;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.io.DataWriteResult;
import org.apache.iceberg.io.OutputFileFactory;
import org.apache.iceberg.mr.hive.FilesForCommit;
import org.apache.iceberg.mr.hive.writer.WriterBuilder.Context;
import org.apache.iceberg.mr.mapred.Container;
+import org.apache.iceberg.relocated.com.google.common.collect.Sets;
+import org.apache.iceberg.types.Type;
+import org.apache.iceberg.types.Types;
+import org.apache.iceberg.util.DateTimeUtil;
class HiveIcebergRecordWriter extends HiveIcebergWriterBase {
private final int currentSpecId;
+ private final Set<String> missingColumns;
HiveIcebergRecordWriter(Table table, HiveFileWriterFactory fileWriterFactory,
- OutputFileFactory dataFileFactory, Context context) {
+ OutputFileFactory dataFileFactory, Context context, String
missingColumns) {
super(table, newDataWriter(table, fileWriterFactory, dataFileFactory,
context));
this.currentSpecId = table.spec().specId();
+ this.missingColumns = Optional.ofNullable(missingColumns)
+ .map(columns ->
Arrays.stream(columns.split(",")).collect(Collectors.toCollection(HashSet::new)))
+ .orElse(Sets.newHashSet());
}
@Override
public void write(Writable row) throws IOException {
Record record = ((Container<Record>) row).get();
+ setDefault(specs.get(currentSpecId).schema().asStruct().fields(), record,
missingColumns);
Review Comment:
should it be applied to every row?
--
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
