[GitHub] [arrow] pitrou commented on a change in pull request #10606: ARROW-13005: [C++] Add support for take implementation on dense union type

[GitBox <gi...@apache.org>]

pitrou commented on a change in pull request #10606:
URL: https://github.com/apache/arrow/pull/10606#discussion_r663466643



##########
File path: cpp/src/arrow/compute/kernels/vector_selection.cc
##########
@@ -1668,6 +1668,66 @@ struct ListImpl : public Selection<ListImpl<Type>, Type> {
   }
 };
 
+struct DenseUnionImpl : public Selection<DenseUnionImpl, DenseUnionType> {
+  using Base = Selection<DenseUnionImpl, DenseUnionType>;
+  LIFT_BASE_MEMBERS();
+
+  typename TypeTraits<DenseUnionType>::ValueOffsetBuilderType value_offset_builder;
+  typename TypeTraits<DenseUnionType>::ChildIdBuilderType child_id_builder;
+  std::vector<int8_t> type_codes;
+
+  DenseUnionImpl(KernelContext* ctx, const ExecBatch& batch, int64_t output_length,
+                 Datum* out)
+      : Base(ctx, batch, output_length, out),
+        value_offset_builder(ctx->memory_pool()),
+        child_id_builder(ctx->memory_pool()) {
+    DenseUnionArray typed_values(this->values);
+    type_codes = typed_values.union_type()->type_codes();
+  }
+
+  template <typename Adapter>
+  Status GenerateOutput() {
+    DenseUnionArray typed_values(this->values);
+    Adapter adapter(this);
+    RETURN_NOT_OK(adapter.Generate(
+        [&](int64_t index) {
+          auto child_id = typed_values.child_id(index);
+          child_id_builder.UnsafeAppend(type_codes[child_id]);
+          auto value_offset = typed_values.value_offset(index);
+          value_offset_builder.UnsafeAppend(value_offset);
+          return Status::OK();
+        },
+        // TODO: not able to handle null case
+        VisitNoop));
+    return Status::OK();
+  }
+
+  Status Init() override {
+    RETURN_NOT_OK(child_id_builder.Reserve(output_length));
+    RETURN_NOT_OK(value_offset_builder.Reserve(output_length));
+    return Status::OK();
+  }
+
+  Status Finish() override {
+    std::shared_ptr<Array> child_ids;
+    std::shared_ptr<Array> value_offsets;
+    RETURN_NOT_OK(child_id_builder.Finish(&child_ids));
+    RETURN_NOT_OK(value_offset_builder.Finish(&value_offsets));
+
+    DenseUnionArray typed_values(this->values);
+    auto num_fields = typed_values.num_fields();
+    ArrayVector child_arrays;
+    child_arrays.reserve(num_fields);
+    BufferVector buffers = {nullptr, checked_cast<const Int8Array&>(*child_ids).values(),
+                            checked_cast<const Int32Array&>(*value_offsets).values()};
+    *out = ArrayData(typed_values.type(), child_ids->length(), std::move(buffers), 0);
+    for (int i = 0; i < typed_values.num_fields(); i++) {
+      out->child_data.push_back(typed_values.field(i)->data());

Review comment:
       I don't think you need to use any child builders. Instead, you should be able to call `Take` on each of the child arrays; you just have to construct the indices carefully for each child array.




-- 
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: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org