zhixingheyi-tian commented on code in PR #14353:
URL: https://github.com/apache/arrow/pull/14353#discussion_r1051755382


##########
cpp/src/parquet/column_reader.cc:
##########
@@ -1957,6 +1970,139 @@ class ByteArrayChunkedRecordReader : public 
TypedRecordReader<ByteArrayType>,
   typename EncodingTraits<ByteArrayType>::Accumulator accumulator_;
 };
 
+class ByteArrayChunkedOptRecordReader : public 
TypedRecordReader<ByteArrayType>,
+                                        virtual public BinaryRecordReader {
+ public:
+  ByteArrayChunkedOptRecordReader(const ColumnDescriptor* descr, LevelInfo 
leaf_info,
+                                  ::arrow::MemoryPool* pool)
+      : TypedRecordReader<ByteArrayType>(descr, leaf_info, pool) {
+    DCHECK_EQ(descr_->physical_type(), Type::BYTE_ARRAY);
+    accumulator_.builder.reset(new ::arrow::BinaryBuilder(pool));
+    values_ = AllocateBuffer(pool);
+    offset_ = AllocateBuffer(pool);
+  }
+
+  ::arrow::ArrayVector GetBuilderChunks() override {
+    if (uses_opt_) {
+      std::vector<std::shared_ptr<Buffer>> buffers = {ReleaseIsValid(), 
ReleaseOffsets(),
+                                                      ReleaseValues()};
+      auto data = std::make_shared<::arrow::ArrayData>(
+          ::arrow::binary(), values_written(), buffers, null_count());
+
+      auto chunks = ::arrow::ArrayVector({::arrow::MakeArray(data)});
+      return chunks;
+    } else {
+      ::arrow::ArrayVector result = accumulator_.chunks;
+      if (result.size() == 0 || accumulator_.builder->length() > 0) {
+        std::shared_ptr<::arrow::Array> last_chunk;
+        PARQUET_THROW_NOT_OK(accumulator_.builder->Finish(&last_chunk));
+        result.push_back(std::move(last_chunk));
+      }
+      accumulator_.chunks = {};
+      return result;

Review Comment:
   The optimized RecordReader implementation is ByteArrayChunkedOptRecordReader
   
    
https://github.com/zhixingheyi-tian/arrow/blob/8d611c673d3ed23abfa32f50da3cc4c4e4feb807/cpp/src/parquet/column_reader.cc#L2203-L2206
   
   And is just for  Binary/String/LargeBinary/LargeString types.
   
   



-- 
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]

Reply via email to