feat: add Arrow and Orc file formats (#169)

BREAKING CHANGE: The `substrait/ReadRel/LocalFiles/format` field is deprecated. This will cause a hard break in compatibility. Newer consumers will not be able to read older files. Older consumers will not be able to read newer files. One should now express format concepts using the file_format oneof field.

Co-authored-by: Jacques Nadeau <[email protected]>

proto/substrait/algebra.proto

@@ -102,7 +102,9 @@ message ReadRel {
         string uri_folder = 4;
       }
 
-      FileFormat format = 5;
+      // Original file format enum, superseded by the file_format oneof.
+      reserved 5;
+      reserved "format";
 
       // the index of the partition this item belongs to
       uint64 partition_index = 6;
@@ -113,9 +115,16 @@ message ReadRel {
       // the length in byte to read from this item
       uint64 length = 8;
 
-      enum FileFormat {
-        FILE_FORMAT_UNSPECIFIED = 0;
-        FILE_FORMAT_PARQUET = 1;
+      message ParquetReadOptions {}
+      message ArrowReadOptions {}
+      message OrcReadOptions {}
+
+      // The format of the files.
+      oneof file_format {
+        ParquetReadOptions parquet = 9;
+        ArrowReadOptions arrow = 10;
+        OrcReadOptions orc = 11;
+        google.protobuf.Any extension = 12;
       }
     }
   }