emkornfield commented on code in PR #14142:
URL: https://github.com/apache/arrow/pull/14142#discussion_r974509120
##########
cpp/src/parquet/column_reader.cc:
##########
@@ -1328,6 +1329,156 @@ class TypedRecordReader : public
ColumnReaderImplBase<DType>,
return records_read;
}
+
+ // Skip records that we have in our buffer. This function is only for
+ // non-repeated fields.
+ int64_t SkipRecordsInBufferNonRepeated(int64_t num_records) {
+ ARROW_DCHECK(this->max_rep_level_ == 0);
+ ARROW_DCHECK(this->has_values_to_process());
+
+ int64_t remaining_records = levels_written_ - levels_position_;
+ int64_t skipped_records = std::min(num_records, remaining_records);
+ int64_t start_levels_position = levels_position_;
+ // Since there is no repetition, number of levels equals number of records.
+ levels_position_ += skipped_records;
+ // We skipped the levels by incrementing 'levels_position_'. For values
+ // we do not have a buffer, so we need to read them and throw them away.
+ // First we need to figure out how many present/not-null values there are.
+ std::shared_ptr<::arrow::ResizableBuffer> valid_bits;
+ valid_bits = AllocateBuffer(this->pool_);
+ PARQUET_THROW_NOT_OK(
+ valid_bits->Resize(bit_util::BytesForBits(skipped_records), true));
+ ValidityBitmapInputOutput validity_io;
+ validity_io.values_read_upper_bound = skipped_records;
+ validity_io.valid_bits = valid_bits->mutable_data();
+ validity_io.valid_bits_offset = 0;
+ DefLevelsToBitmap(def_levels() + start_levels_position,
+ levels_position_ - start_levels_position,
+ this->leaf_info_, &validity_io);
+ int64_t values_to_read = validity_io.values_read - validity_io.null_count;
+ ReadAndThrowAway(values_to_read);
+ // Mark the levels as read in the underlying column reader.
+ this->ConsumeBufferedValues(skipped_records);
+ return skipped_records;
+ }
+
+ // Skip records for repeated fields. Returns number of skipped records.
+ // Skip records for repeated fields. Returns number of skipped records.
+ int64_t SkipRecordsRepeated(int64_t num_records) {
+ ARROW_DCHECK_GT(this->max_rep_level_, 0);
+
+ // For repeated fields, we are technically reading and throwing away the
+ // levels and values since we do not know the record boundaries in advance.
+ // Keep filling the buffer and skipping until we reach the desired number
+ // of records or we run out of values in the column chunk.
+ int64_t skipped_records = 0;
+ int64_t level_batch_size = std::max<int>(kMinLevelBatchSize, num_records);
Review Comment:
int64_t for max?
--
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
