Skip to content
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.

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

feat: Add DeleteColumnReader and PositionColumnReader #363

Closed
wants to merge 1 commit into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/

package org.apache.comet.parquet;

import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;

/** A column reader for reading delete column */
public class DeleteColumnReader extends MetadataColumnReader {
private boolean[] isDeleted;

public DeleteColumnReader(boolean[] isDeleted) {
super(
DataTypes.BooleanType,
TypeUtil.convertToParquet(
new StructField("deleted", DataTypes.BooleanType, false, Metadata.empty())),
false);
this.isDeleted = isDeleted;
}

@Override
public void readBatch(int total) {
Native.resetBatch(nativeHandle);
Native.setIsDeleted(nativeHandle, isDeleted);

super.readBatch(total);
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,47 @@
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/

package org.apache.comet.parquet;

import org.apache.parquet.column.ColumnDescriptor;
import org.apache.spark.sql.types.DataTypes;

/** A column reader for reading position column */
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would you like to add some more comment explaining why we have these? Especially they are not used in Comet itself.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actually this is common module, and it is odd to have Iceberg code here.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

These are pretty much similar to ConstantColumnReader, so I am thinking of putting them in common.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am OK with leave these in Iceberg.

public class PositionColumnReader extends MetadataColumnReader {
/** The current position value of the column that are used to initialize this column reader. */
private long position;

public PositionColumnReader(ColumnDescriptor descriptor) {
this(descriptor, 0L);
}

PositionColumnReader(ColumnDescriptor descriptor, long position) {
super(DataTypes.LongType, descriptor, false);
this.position = position;
}

@Override
public void readBatch(int total) {
Native.resetBatch(nativeHandle);
Native.setPosition(nativeHandle, position, total);
position += total;

super.readBatch(total);
Comment on lines +42 to +45
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm not familiar with this area of code, but this looks odd to me and maybe just needs a comment to explain. My understanding:

  • we set the position to position
  • we then increase the position by total
  • then we do the read, but shouldn't this be from the original position?

}
}
Loading