nssalian commented on code in PR #2002:
URL: https://github.com/apache/iceberg-go/pull/2002#discussion_r4051816714
##########
table/variant_residual.go:
##########
@@ -91,18 +201,142 @@ func buildExtractColumn(col iceberg.VariantExtractColumn,
rec arrow.RecordBatch,
}
if aerr := appendExtractLiteral(bldr, lit); aerr != nil {
- return nil, arrow.Field{}, aerr
+ return nil, aerr
}
}
- field := arrow.Field{
- Name: col.Name,
- Type: dt,
- Nullable: true,
- Metadata: arrow.NewMetadata([]string{ArrowParquetFieldIDKey},
[]string{strconv.Itoa(col.FieldID)}),
+ return bldr.NewArray(), nil
+}
+
+// tryShreddedTypedColumn returns the field's typed leaf column when it is
shredded to exactly dt, else nil.
+func tryShreddedTypedColumn(varr *extensions.VariantArray, path
variant.VariantPath, dt arrow.DataType, mem memory.Allocator) arrow.Array {
+ if path.Len() == 0 || varr.Data().Offset() != 0 {
+ return nil
+ }
+ tv := varr.Shredded()
+ if tv == nil || rootResidualHidesRows(varr, tv) {
+ return nil
+ }
+ n := varr.Len()
+
+ var mask *memory.Buffer
+ badOffset := false
+ mergeValidity := func(arr arrow.Array) {
+ if arr.Data().Offset() != 0 {
+ badOffset = true // child at a non-zero offset: our
offset-0 bit indexing would be wrong
+
+ return
+ }
+ if arr.NullN() == 0 {
+ return
+ }
+ vb := arr.Data().Buffers()[0]
+ if vb == nil {
Review Comment:
`mergeValidity` now bails on a nil validity buffer with `NullN()>0`,
matching `rootResidualHidesRows`. Renamed the flag `badOffset` -> `shouldBail`
since it now covers this case too.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
