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

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

anjakefala commented on code in PR #14293:
URL: https://github.com/apache/arrow/pull/14293#discussion_r1068857310


##########
cpp/src/parquet/encoding.cc:
##########
@@ -2537,6 +2537,114 @@ class DeltaBitPackDecoder : public DecoderImpl, virtual public TypedDecoder<DTyp
 // ----------------------------------------------------------------------
 // DELTA_LENGTH_BYTE_ARRAY
 
+// ----------------------------------------------------------------------
+// DeltaLengthByteArrayEncoder
+
+class DeltaLengthByteArrayEncoder : public EncoderImpl,
+                                    virtual public TypedEncoder<ByteArrayType> {
+ public:
+  using T = typename ByteArrayType::c_type;
+
+  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},
+        lengths_(0, ::arrow::stl::allocator<int32_t>(pool)) {}
+
+  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:
+  ::arrow::BufferBuilder sink_;
+  DeltaBitPackEncoder<Int32Type> length_encoder_;
+  uint32_t encoded_size_;
+  ArrowPoolVector<int32_t> lengths_;
+};
+
+void DeltaLengthByteArrayEncoder::Put(const ::arrow::Array& values) {
+  const ::arrow::ArrayData& data = *values.data();
+  if (values.type_id() != ::arrow::Type::BINARY) {
+    throw ParquetException("Expected ByteArrayType, got ", values.type()->ToString());
+  }
+  if (data.length > std::numeric_limits<int32_t>::max()) {
+    throw ParquetException("Array cannot be longer than ",
+                           std::numeric_limits<int32_t>::max());
+  }
+  if (values.null_count() == 0) {
+    Put(data.GetValues<ByteArray>(1), static_cast<int>(data.length));

Review Comment:
   > It's not perfect, but it gives you a sort of basic code coverage. :
   
   Oh, cool!



-- 
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