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

GH-3040: DictionaryFilter.canDrop may return false positive result when dict size exceeds 8k #3041

Merged
merged 4 commits into from
Nov 6, 2024
Merged
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
Expand Up @@ -20,12 +20,14 @@

import java.io.ByteArrayOutputStream;
import java.io.DataInputStream;
import java.io.EOFException;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.nio.ByteBuffer;
import java.nio.ByteOrder;
import java.nio.channels.Channels;
import java.nio.channels.ReadableByteChannel;
import java.nio.channels.WritableByteChannel;
import java.util.Arrays;
import java.util.List;
Expand Down Expand Up @@ -376,7 +378,15 @@ void writeInto(ByteBuffer buffer) {
ByteBuffer workBuf = buffer.duplicate();
int pos = buffer.position();
workBuf.limit(pos + byteCount);
Channels.newChannel(in).read(workBuf);
Copy link
Contributor

Choose a reason for hiding this comment

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

Is there any other place that is used like this?

Copy link
Member Author

Choose a reason for hiding this comment

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

I went through the original PR and found nothing else, it would be great if others have a double check.

ReadableByteChannel channel = Channels.newChannel(in);
int remaining = byteCount;
while (remaining > 0) {
int bytesRead = channel.read(workBuf);
if (bytesRead < 0) {
throw new EOFException("Reached the end of stream with " + remaining + " bytes left to read");
}
remaining -= bytesRead;
}
buffer.position(pos + byteCount);
} catch (IOException e) {
new RuntimeException("Exception occurred during reading input stream", e);
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
/*
* 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.parquet.bytes;

import java.io.ByteArrayInputStream;

public class AvailableAgnosticInputStream extends ByteArrayInputStream {

public AvailableAgnosticInputStream(byte[] buf) {
super(buf);
}

// In practice, there are some implementations always return 0 even if they has more data
Copy link
Member Author

Choose a reason for hiding this comment

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

in my case, the underlying IntputStream is H1SeekableInputStream

Copy link
Contributor

Choose a reason for hiding this comment

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

Out of curiosity. Why are you using H1SeekableInputStream? This one is related to Hadoop 1.

Copy link
Member Author

Choose a reason for hiding this comment

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

My test code is
(sorry, the file contains private data so I can not share)

public class MyDictionaryFilterTest {

  private static final Configuration conf = new Configuration();
  List<ColumnChunkMetaData> ccmd;
  ParquetFileReader reader;
  DictionaryPageReadStore dictionaries;
  private Path file = new Path("/Users/chengpan/Temp/part-2bb8404a-f6e5-4e9f-9161-f749c4bf46d0-2-2222");

  @Before
  public void setUp() throws Exception {
    reader = ParquetFileReader.open(conf, file);
    ParquetMetadata meta = reader.getFooter();
    ccmd = meta.getBlocks().get(0).getColumns();
    dictionaries = reader.getDictionaryReader(meta.getBlocks().get(0));
  }

  @After
  public void tearDown() throws Exception {
    reader.close();
  }

  @Test
  public void testEqBinary() throws Exception {
    BinaryColumn b = binaryColumn("source_id");
    FilterPredicate pred = eq(b, Binary.fromString("5059661515"));

    assertFalse(canDrop(pred, ccmd, dictionaries));
  }
}

Copy link
Contributor

Choose a reason for hiding this comment

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

Thanks, this is very helpful!

@Override
public synchronized int available() {
return 0;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,20 @@ public void testFromInputStream() throws IOException {
validate(data, factory);
}

@Test
public void testFromLargeAvailableAgnosticInputStream() throws IOException {
// allocate a bytes that large than
// java.nio.channel.Channels.ReadableByteChannelImpl.TRANSFER_SIZE = 8192
byte[] data = new byte[9 * 1024];
RANDOM.nextBytes(data);
byte[] input = new byte[data.length + 10];
RANDOM.nextBytes(input);
System.arraycopy(data, 0, input, 0, data.length);
Supplier<BytesInput> factory = () -> BytesInput.from(new AvailableAgnosticInputStream(input), 9 * 1024);
Copy link
Member

Choose a reason for hiding this comment

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

What about using an anonymous class here instead of adding a new file?

Copy link
Member Author

Choose a reason for hiding this comment

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

I tend to use a new file as it is a quite common case that needs to be tested, it might be used in other places in the future.


validate(data, factory);
}

@Test
public void testFromByteArrayOutputStream() throws IOException {
byte[] data = new byte[1000];
Expand Down