[GitHub] [iceberg] rdblue commented on a change in pull request #1407: Hive: HiveIcebergOutputFormat first implementation - WIP

[GitBox <gi...@apache.org>]

rdblue commented on a change in pull request #1407:
URL: https://github.com/apache/iceberg/pull/1407#discussion_r481310443



##########
File path: mr/src/main/java/org/apache/iceberg/mr/hive/HiveIcebergOutputFormat.java
##########
@@ -19,21 +19,216 @@
 
 package org.apache.iceberg.mr.hive;
 
+import java.io.IOException;
+import java.util.Map;
+import java.util.Properties;
+import java.util.UUID;
+import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.ql.exec.FileSinkOperator;
+import org.apache.hadoop.hive.ql.io.HiveOutputFormat;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.io.Writable;
 import org.apache.hadoop.mapred.JobConf;
-import org.apache.hadoop.mapred.OutputFormat;
-import org.apache.hadoop.mapred.RecordWriter;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapreduce.JobContext;
+import org.apache.hadoop.mapreduce.OutputCommitter;
+import org.apache.hadoop.mapreduce.OutputFormat;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
 import org.apache.hadoop.util.Progressable;
+import org.apache.iceberg.AppendFiles;
+import org.apache.iceberg.DataFiles;
+import org.apache.iceberg.FileFormat;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.avro.Avro;
+import org.apache.iceberg.data.Record;
+import org.apache.iceberg.data.avro.DataWriter;
+import org.apache.iceberg.data.orc.GenericOrcWriter;
+import org.apache.iceberg.data.parquet.GenericParquetWriter;
+import org.apache.iceberg.hadoop.HadoopFileIO;
+import org.apache.iceberg.io.FileAppender;
+import org.apache.iceberg.io.FileIO;
+import org.apache.iceberg.io.OutputFile;
+import org.apache.iceberg.mr.Catalogs;
+import org.apache.iceberg.mr.HiveSerDeConfig;
+import org.apache.iceberg.mr.mapreduce.IcebergWritable;
+import org.apache.iceberg.orc.ORC;
+import org.apache.iceberg.parquet.Parquet;
+import org.apache.iceberg.relocated.com.google.common.base.Preconditions;
 
-public class HiveIcebergOutputFormat<T> implements OutputFormat<Void, T> {
+public class HiveIcebergOutputFormat extends OutputFormat<NullWritable, IcebergWritable>
+    implements HiveOutputFormat<NullWritable, IcebergWritable> {
+  private Configuration overlayedConf = null;
+  private Table table = null;
 
   @Override
-  public RecordWriter<Void, T> getRecordWriter(FileSystem ignored, JobConf job, String name, Progressable progress) {
-    throw new UnsupportedOperationException("Writing to an Iceberg table with Hive is not supported");
+  @SuppressWarnings("rawtypes")

Review comment:
       We don't suppress these warnings. Instead we should fix the cases.




----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org