[GitHub] [arrow] rok commented on a diff in pull request #14293: ARROW-17799: [C++][Parquet] Add DELTA_LENGTH_BYTE_ARRAY encoder to Parquet writer

["rok (via GitHub)" <gi...@apache.org>]

rok commented on code in PR #14293:
URL: https://github.com/apache/arrow/pull/14293#discussion_r1093452943


##########
cpp/src/parquet/encoding.cc:
##########
@@ -2572,6 +2605,131 @@ class DeltaBitPackDecoder : public DecoderImpl, virtual public TypedDecoder<DTyp
 // ----------------------------------------------------------------------
 // DELTA_LENGTH_BYTE_ARRAY
 
+// ----------------------------------------------------------------------
+// DeltaLengthByteArrayEncoder
+
+template <typename DType>
+class DeltaLengthByteArrayEncoder : public EncoderImpl,
+                                    virtual public TypedEncoder<ByteArrayType> {
+ public:
+  explicit DeltaLengthByteArrayEncoder(const ColumnDescriptor* descr, MemoryPool* pool)
+      : EncoderImpl(descr, Encoding::DELTA_LENGTH_BYTE_ARRAY,
+                    pool = ::arrow::default_memory_pool()),
+        sink_(pool),
+        length_encoder_(nullptr, pool),
+        encoded_size_{0} {}
+
+  std::shared_ptr<Buffer> FlushValues() override;
+
+  int64_t EstimatedDataEncodedSize() override {
+    return encoded_size_ + length_encoder_.EstimatedDataEncodedSize();
+  }
+
+  using TypedEncoder<ByteArrayType>::Put;
+
+  void Put(const ::arrow::Array& values) override;
+
+  void Put(const T* buffer, int num_values) override;
+
+  void PutSpaced(const T* src, int num_values, const uint8_t* valid_bits,
+                 int64_t valid_bits_offset) override;
+
+ protected:
+  template <typename ArrayType>
+  void PutBinaryArray(const ArrayType& array) {
+    PARQUET_THROW_NOT_OK(::arrow::VisitArraySpanInline<typename ArrayType::TypeClass>(
+        *array.data(),
+        [&](::std::string_view view) {
+          if (ARROW_PREDICT_FALSE(view.size() > kMaxByteArraySize)) {
+            return Status::Invalid("Parquet cannot store strings with size 2GB or more");
+          }
+          length_encoder_.Put({static_cast<int32_t>(view.length())}, 1);
+          PARQUET_THROW_NOT_OK(sink_.Append(view.data(), view.length()));

Review Comment:
   I'll give it another try and report back.



-- 
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