Skip to content

DataFrame incorrectly sets column value for index higher than Buffer.MaxCapacity #6849

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

Merged
merged 2 commits into from
Oct 2, 2023
Merged

DataFrame incorrectly sets column value for index higher than Buffer.MaxCapacity #6849

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0ccca6a
Fix DataFrame incorrectly sets column value for index higher than Buf…
asmirnov82 Oct 1, 2023
607bc8c
Revert renaming
asmirnov82 Oct 1, 2023
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
10 changes: 5 additions & 5 deletions src/Microsoft.Data.Analysis/PrimitiveColumnContainer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -457,25 +457,25 @@ public T? this[long rowIndex]
return null;
}
int arrayIndex = GetArrayContainingRowIndex(rowIndex);
rowIndex = rowIndex - arrayIndex * ReadOnlyDataFrameBuffer<T>.MaxCapacity;
return Buffers[arrayIndex][(int)rowIndex];
var bufferOffset = (int)(rowIndex % ReadOnlyDataFrameBuffer<T>.MaxCapacity);
return Buffers[arrayIndex][bufferOffset];
}
set
{
int arrayIndex = GetArrayContainingRowIndex(rowIndex);
rowIndex = rowIndex - arrayIndex * ReadOnlyDataFrameBuffer<T>.MaxCapacity;
var bufferOffset = (int)(rowIndex % ReadOnlyDataFrameBuffer<T>.MaxCapacity);

Buffers.GetOrCreateMutable(arrayIndex);
NullBitMapBuffers.GetOrCreateMutable(arrayIndex);

if (value.HasValue)
{
Buffers[arrayIndex][(int)rowIndex] = value.Value;
Buffers[arrayIndex][bufferOffset] = value.Value;
SetValidityBit(rowIndex, true);
}
else
{
Buffers[arrayIndex][(int)rowIndex] = default;
Buffers[arrayIndex][bufferOffset] = default;
SetValidityBit(rowIndex, false);
}
}
Expand Down
19 changes: 17 additions & 2 deletions test/Microsoft.Data.Analysis.Tests/BufferTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,27 @@
using System.Text;
using Apache.Arrow;
using Microsoft.ML.TestFramework.Attributes;
using Newtonsoft.Json.Linq;
using Xunit;

namespace Microsoft.Data.Analysis.Tests
{
public class BufferTests
{
[X64Fact("32-bit doesn't allow to allocate more than 2 Gb")]
public void TestGetterAndSetterForColumnsGreaterThanMaxCapacity()
{
const int MaxCapacityInBytes = 2147483591;

var length = MaxCapacityInBytes + 5;
var column = new PrimitiveDataFrameColumn<byte>("LargeColumn", length);
var index = length - 1;
column[index] = 33;

Assert.Equal((byte)33, column[index]);
Assert.Null(column[index % MaxCapacityInBytes]);
}

[Fact]
public void TestNullCounts()
{
Expand Down Expand Up @@ -446,15 +461,15 @@ public void TestArrowStringColumnClone()
Assert.Null(clone[i]);
}

[X64Fact("32-bit dosn't allow to allocate more than 2 Gb")]
[X64Fact("32-bit doesn't allow to allocate more than 2 Gb")]
public void TestAppend_SizeMoreThanMaxBufferCapacity()
{
//Check appending value, than can increase buffer size over MaxCapacity (default strategy is to double buffer capacity)
PrimitiveDataFrameColumn<byte> intColumn = new PrimitiveDataFrameColumn<byte>("Byte1", int.MaxValue / 2 - 1);
intColumn.Append(10);
}

[X64Fact("32-bit dosn't allow to allocate more than 2 Gb")]
[X64Fact("32-bit doesn't allow to allocate more than 2 Gb")]
public void TestAppendMany_SizeMoreThanMaxBufferCapacity()
{
const int MaxCapacityInBytes = 2147483591;
Expand Down