pqarrow/arrowutils: Support sorting structs within lists #949
+94
−33
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
metalmatze
commented
Feb 14, 2025
Comment on lines
+279
to
+328
| case *array.StructBuilder: | ||
| defer valueBuilder.Release() | ||
|
|
||
| structArray := a.ListValues().(*array.Struct) | ||
|
|
||
| // expand the indices from the list to each row in the struct. | ||
| structIndicesBuilder := array.NewInt32Builder(mem) | ||
| structIndicesBuilder.Reserve(structArray.Len()) | ||
| for _, i := range indices.Int32Values() { | ||
| start, end := a.ValueOffsets(int(i)) | ||
| for j := start; j < end; j++ { | ||
| structIndicesBuilder.Append(int32(j)) | ||
| } | ||
| } | ||
| structIndices := structIndicesBuilder.NewInt32Array() | ||
|
|
||
| r.Append(true) | ||
| start, end := a.ValueOffsets(int(i)) | ||
| for j := start; j < end; j++ { | ||
| idxBuilder.Append(listValues.GetValueIndex(int(j))) | ||
| arrays := []arrow.Array{structArray} | ||
| err := TakeStructColumn(ctx, structArray, 0, arrays, structIndices) | ||
| if err != nil { | ||
| return err | ||
| } | ||
| // Resize is necessary here for the correct offsets to be appended to | ||
| // the list builder. Otherwise length will remain at 0. | ||
| valueBuilder.Resize(idxBuilder.Len()) | ||
| } | ||
|
|
||
| arr[idx] = r.NewArray() | ||
| return nil | ||
| newOffsetBuilder := array.NewInt32Builder(mem) | ||
| newOffsetBuilder.Append(0) | ||
| newOffsetPrevious := int32(0) | ||
| for _, i := range indices.Int32Values() { | ||
| if a.IsNull(int(i)) { | ||
| newOffsetBuilder.AppendNull() | ||
| continue | ||
| } | ||
|
|
||
| start, end := a.ValueOffsets(int(i)) | ||
| // calculate the length of the current list element and add it to the offsets | ||
| newOffsetPrevious += int32(end - start) | ||
| newOffsetBuilder.Append(newOffsetPrevious) | ||
| } | ||
| newOffsets := newOffsetBuilder.NewInt32Array() | ||
|
|
||
| data := array.NewData( | ||
| arrow.ListOf(structArray.DataType()), | ||
| a.Len(), | ||
| []*memory.Buffer{nil, newOffsets.Data().Buffers()[1]}, | ||
| []arrow.ArrayData{arrays[0].Data()}, | ||
| newOffsets.NullN(), | ||
| 0, | ||
| ) | ||
| defer data.Release() | ||
| arr[idx] = array.NewListData(data) | ||
|
|
||
| return nil |
There was a problem hiding this comment.
This part is the important change.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.