kszucs commented on code in PR #45360:
URL: https://github.com/apache/arrow/pull/45360#discussion_r1985561762
##########
cpp/src/parquet/column_writer.cc:
##########
@@ -1332,13 +1337,38 @@ class TypedColumnWriterImpl : public ColumnWriterImpl,
public TypedColumnWriter<
bits_buffer_->ZeroPadding();
}
- if (leaf_array.type()->id() == ::arrow::Type::DICTIONARY) {
- return WriteArrowDictionary(def_levels, rep_levels, num_levels,
leaf_array, ctx,
- maybe_parent_nulls);
+ if (this->properties_->cdc_enabled()) {
+ ARROW_ASSIGN_OR_RAISE(auto boundaries,
+ content_defined_chunker_.GetBoundaries(
+ def_levels, rep_levels, num_levels,
leaf_array));
+ for (auto chunk : boundaries) {
+ auto chunk_array = leaf_array.Slice(chunk.value_offset);
+ auto chunk_def_levels = AddIfNotNull(def_levels, chunk.level_offset);
+ auto chunk_rep_levels = AddIfNotNull(rep_levels, chunk.level_offset);
+ if (leaf_array.type()->id() == ::arrow::Type::DICTIONARY) {
+ ARROW_CHECK_OK(WriteArrowDictionary(chunk_def_levels,
chunk_rep_levels,
+ chunk.levels_to_write,
*chunk_array, ctx,
+ maybe_parent_nulls));
+ } else {
+ ARROW_CHECK_OK(WriteArrowDense(chunk_def_levels, chunk_rep_levels,
+ chunk.levels_to_write, *chunk_array,
ctx,
+ maybe_parent_nulls));
+ }
+ if (num_buffered_values_ > 0) {
+ AddDataPage();
+ }
+ }
+ return Status::OK();
} else {
- return WriteArrowDense(def_levels, rep_levels, num_levels, leaf_array,
ctx,
- maybe_parent_nulls);
+ if (leaf_array.type()->id() == ::arrow::Type::DICTIONARY) {
+ return WriteArrowDictionary(def_levels, rep_levels, num_levels,
leaf_array, ctx,
+ maybe_parent_nulls);
+ } else {
+ return WriteArrowDense(def_levels, rep_levels, num_levels, leaf_array,
ctx,
+ maybe_parent_nulls);
+ }
Review Comment:
No, this is the original non-CDC code path.
--
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-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
