Skip to content

fix(array): retain dictionary before replacement #926

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
zeroshade merged 2 commits into from
Jul 13, 2026
+67 −6
Merged

fix(array): retain dictionary before replacement #926

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
a91822e
fix(array): retain dictionary before replacement
fallintoplace Jul 11, 2026
7fbe942
test(array): cover clearing dictionary data
fallintoplace Jul 13, 2026
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
21 changes: 15 additions & 6 deletions arrow/array/data.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,13 +187,22 @@ func (d *Data) Dictionary() arrow.ArrayData { return d.dictionary }

// SetDictionary allows replacing the dictionary for this particular Data object
func (d *Data) SetDictionary(dict arrow.ArrayData) {
if d.dictionary != nil {
d.dictionary.Release()
d.dictionary = nil
var newDict *Data
if dict != nil {
var ok bool
newDict, ok = dict.(*Data)
if !ok {
panic("arrow/array: dictionary data must be *array.Data")
}
}
if dict.(*Data) != nil {
dict.Retain()
d.dictionary = dict.(*Data)

if newDict != nil {
newDict.Retain()

@zeroshade zeroshade Jul 12, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Retain-before-release ordering is correct. Please add a SetDictionary(nil) test (clearing is now supported per the PR description but untested), and optionally one asserting the explicit panic for a non-*array.Data implementation.

}
oldDict := d.dictionary
d.dictionary = newDict
if oldDict != nil {
oldDict.Release()
}
}

Expand Down
52 changes: 52 additions & 0 deletions arrow/array/data_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@ import (
"github.com/apache/arrow-go/v18/arrow/memory"
"github.com/apache/arrow-go/v18/internal/utils/maphash"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)

func TestDataReset(t *testing.T) {
Expand Down Expand Up @@ -101,6 +102,57 @@ func TestDataResetClearsDictionary(t *testing.T) {
mem.AssertSize(t, 0)
}

func TestDataSetDictionaryWithSamePointerRetainsDictionary(t *testing.T) {
mem := memory.NewCheckedAllocator(memory.DefaultAllocator)
defer mem.AssertSize(t, 0)

values := memory.NewResizableBuffer(mem)
values.Resize(4)
copy(values.Bytes(), arrow.Int32Traits.CastToBytes([]int32{42}))
dictData := NewData(arrow.PrimitiveTypes.Int32, 1, []*memory.Buffer{nil, values}, nil, 0, 0)
values.Release()

dictType := &arrow.DictionaryType{
IndexType: arrow.PrimitiveTypes.Int8,
ValueType: arrow.PrimitiveTypes.Int32,
}
data := NewDataWithDictionary(dictType, 1, []*memory.Buffer{nil, memory.NewBufferBytes([]byte{0})}, 0, 0, dictData)
defer data.Release()
dictData.Release()

data.SetDictionary(dictData)
require.Same(t, dictData, data.Dictionary())
require.NotNil(t, dictData.Buffers()[1])

valuesArray := NewInt32Data(dictData)
defer valuesArray.Release()
require.Equal(t, int32(42), valuesArray.Value(0))
}

func TestDataSetDictionaryNilClearsDictionary(t *testing.T) {
mem := memory.NewCheckedAllocator(memory.DefaultAllocator)
defer mem.AssertSize(t, 0)

values := memory.NewResizableBuffer(mem)
values.Resize(4)
dictData := NewData(arrow.PrimitiveTypes.Int32, 1, []*memory.Buffer{nil, values}, nil, 0, 0)
values.Release()

dictType := &arrow.DictionaryType{
IndexType: arrow.PrimitiveTypes.Int8,
ValueType: arrow.PrimitiveTypes.Int32,
}
data := NewDataWithDictionary(dictType, 1, []*memory.Buffer{nil, memory.NewBufferBytes([]byte{0})}, 0, 0, dictData)
defer data.Release()
dictData.Release()

require.NotNil(t, data.Dictionary())

data.SetDictionary(nil)

require.Nil(t, data.Dictionary())
}

func TestHashIncludesDataMetadataAndBuffers(t *testing.T) {
seed := maphash.MakeSeed()
hash := func(data arrow.ArrayData) uint64 {
Expand Down
Loading