Skip to content

Spark 3.0: ORC support estimated length for unclosed file. #4420

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
hililiwei wants to merge 1 commit into from
Closed

Spark 3.0: ORC support estimated length for unclosed file. #4420

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 1 addition & 8 deletions spark/v3.0/spark/src/main/java/org/apache/iceberg/spark/source/SparkWrite.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,6 @@
import org.apache.iceberg.SnapshotUpdate;
import org.apache.iceberg.Table;
import org.apache.iceberg.TableProperties;
import org.apache.iceberg.encryption.EncryptedOutputFile;
import org.apache.iceberg.expressions.Expression;
import org.apache.iceberg.expressions.Expressions;
import org.apache.iceberg.io.ClusteredDataWriter;
Expand Down Expand Up @@ -585,13 +584,7 @@ private static class UnpartitionedDataWriter implements DataWriter<InternalRow>

private UnpartitionedDataWriter(SparkFileWriterFactory writerFactory, OutputFileFactory fileFactory,
FileIO io, PartitionSpec spec, FileFormat format, long targetFileSize) {
// TODO: support ORC rolling writers
if (format == FileFormat.ORC) {
EncryptedOutputFile outputFile = fileFactory.newOutputFile();
delegate = writerFactory.newDataWriter(outputFile, spec, null);
} else {
delegate = new RollingDataWriter<>(writerFactory, fileFactory, io, targetFileSize, spec, null);
}
this.delegate = new RollingDataWriter<>(writerFactory, fileFactory, io, targetFileSize, spec, null);
this.io = io;
}

Expand Down
16 changes: 6 additions & 10 deletions spark/v3.0/spark/src/test/java/org/apache/iceberg/spark/source/TestSparkDataWrite.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,11 +365,9 @@ public void testUnpartitionedCreateWithTargetFileSizeViaTableProperties() throws
files.add(file);
}
}
// TODO: ORC file now not support target file size
if (!format.equals(FileFormat.ORC)) {
Assert.assertEquals("Should have 4 DataFiles", 4, files.size());
Assert.assertTrue("All DataFiles contain 1000 rows", files.stream().allMatch(d -> d.recordCount() == 1000));
}

Assert.assertEquals("Should have 4 DataFiles", 4, files.size());
Assert.assertTrue("All DataFiles contain 1000 rows", files.stream().allMatch(d -> d.recordCount() == 1000));
}

@Test
Expand Down Expand Up @@ -585,11 +583,9 @@ public void partitionedCreateWithTargetFileSizeViaOption(IcebergOptionsType opti
files.add(file);
}
}
// TODO: ORC file now not support target file size
if (!format.equals(FileFormat.ORC)) {
Assert.assertEquals("Should have 8 DataFiles", 8, files.size());
Assert.assertTrue("All DataFiles contain 1000 rows", files.stream().allMatch(d -> d.recordCount() == 1000));
}

Assert.assertEquals("Should have 8 DataFiles", 8, files.size());
Assert.assertTrue("All DataFiles contain 1000 rows", files.stream().allMatch(d -> d.recordCount() == 1000));
}

public enum IcebergOptionsType {
Expand Down