move endianness to Schema

cpp/src/arrow/ipc/metadata-internal.cc

@@ -246,6 +246,16 @@ Status FieldFromFlatbuffer(const flatbuf::Field* field, std::shared_ptr<Field>*
 
 // Implement MessageBuilder
 
+// will return the endianness of the system we are running on
+flatbuf::Endianness endianness() {
+  union {
+    uint32_t i;
+    char c[4];
+  } bint = {0x01020304};
+
+  return bint.c[0] == 1 ? flatbuf::Endianness_Big : flatbuf::Endianness_Little;
+}
+
 Status MessageBuilder::SetSchema(const Schema* schema) {
   header_type_ = flatbuf::MessageHeader_Schema;
 
@@ -257,26 +267,16 @@ Status MessageBuilder::SetSchema(const Schema* schema) {
     field_offsets.push_back(offset);
   }
 
-  header_ = flatbuf::CreateSchema(fbb_, fbb_.CreateVector(field_offsets)).Union();
+  header_ = flatbuf::CreateSchema(fbb_, endianness(), fbb_.CreateVector(field_offsets)).Union();
   body_length_ = 0;
   return Status::OK();
 }
 
-// will return the endianness of the system we are running on
-flatbuf::Endianness endianness(void) {
-  union {
-    uint32_t i;
-    char c[4];
-  } bint = {0x01020304};
-
-  return bint.c[0] == 1 ? flatbuf::Endianness_Big : flatbuf::Endianness_Little;
-}
-
 Status MessageBuilder::SetRecordBatch(int32_t length, int64_t body_length,
     const std::vector<flatbuf::FieldNode>& nodes,
     const std::vector<flatbuf::Buffer>& buffers) {
   header_type_ = flatbuf::MessageHeader_RecordBatch;
-  header_ = flatbuf::CreateRecordBatch(fbb_, length, endianness(),
+  header_ = flatbuf::CreateRecordBatch(fbb_, length,
                 fbb_.CreateVectorOfStructs(nodes),
                 fbb_.CreateVectorOfStructs(buffers))
                 .Union();

format/Layout.md

@@ -79,12 +79,12 @@ Base requirements
 ## Byte Order ([Endianness][3])
 
 The Arrow format is little endian by default.
-The RecordBatch metadata has an endianness field labelling the RecordBatch accordingly.
+The Schema metadata has an endianness field indicating endiannmess of RecordBatches.
 Typically this is the endianness of the system where the RecordBatch was generated.
 The main use case is exchanging RecordBatches between systems with the same Endianness.
 At first we will return an error when trying to read a RecordBatch with an endianness
 that does not match the underlying system. The reference implementation is focused on
-Little Endian and provides test for it. Eventually we may provide automatic conversion
+Little Endian and provides tests for it. Eventually we may provide automatic conversion
 via byte swapping.
 
 ## Alignment and Padding

format/Message.fbs

@@ -91,10 +91,21 @@ table Field {
   children: [Field];
 }
 
+/// ----------------------------------------------------------------------
+/// Endianness of the platform that produces the RecordBatch
+
+enum Endianness:int { Little, Big }
+
 /// ----------------------------------------------------------------------
 /// A Schema describes the columns in a row batch
 
 table Schema {
+
+  /// endianness of the buffer
+  /// it is Little Endian by default
+  /// if endianness doesn't match the underlying system then the vectors need to be converted
+  endianness: Endianness=Little;
+
   fields: [Field];
 }
 
@@ -134,8 +145,6 @@ struct FieldNode {
   null_count: int;
 }
 
-enum Endianness:int { Little, Big }
-
 /// A data header describing the shared memory layout of a "record" or "row"
 /// batch. Some systems call this a "row batch" internally and others a "record
 /// batch".
@@ -144,11 +153,6 @@ table RecordBatch {
   /// length
   length: int;
 
-  /// endianness of the buffer
-  /// it is Little Endian by default
-  /// if endianness doesn't match the underlying system then the vectors need to be converted
-  endianness: Endianness=Little;
-
   /// Nodes correspond to the pre-ordered flattened logical schema
   nodes: [FieldNode];