Class: ArrowFormat::Org::Apache::Arrow::Flatbuf::DictionaryEncoding

Inherits:
FlatBuffers::Table
  • Object
show all
Defined in:
lib/arrow-format/org/apache/arrow/flatbuf/dictionary_encoding.rb

Constant Summary collapse

FIELDS = 
{
  id: ::FlatBuffers::Field.new(:id, 0, 4, :long, 0),
  index_type: ::FlatBuffers::Field.new(:index_type, 1, 6, "::ArrowFormat::Org::Apache::Arrow::Flatbuf::Int", 0),
  ordered?: ::FlatBuffers::Field.new(:ordered?, 2, 8, :bool, 0),
  dictionary_kind: ::FlatBuffers::Field.new(:dictionary_kind, 3, 10, :short, 0),
}
Data = 
define_data_class

Instance Method Summary collapse

Instance Method Details

#dictionary_kind ⇒ Object 



26
27
28
29
30
31
32
33
34
 
# File 'lib/arrow-format/org/apache/arrow/flatbuf/dictionary_encoding.rb', line 26

def dictionary_kind
  field_offset = @view.unpack_virtual_offset(10)
  if field_offset.zero?
    enum_value = 0
  else
    enum_value = @view.unpack_short(field_offset)
  end
  ::ArrowFormat::Org::Apache::Arrow::Flatbuf::DictionaryKind.try_convert(enum_value) || enum_value
end

#id ⇒ Object

The known dictionary id in the application where this data is used. In the file or streaming formats, the dictionary ids are found in the DictionaryBatch messages



39
40
41
42
43
44
 
# File 'lib/arrow-format/org/apache/arrow/flatbuf/dictionary_encoding.rb', line 39

def id
  field_offset = @view.unpack_virtual_offset(4)
  return 0 if field_offset.zero?

  @view.unpack_long(field_offset)
end

#index_type ⇒ Object

The dictionary indices are constrained to be non-negative integers. If this field is null, the indices must be signed int32. To maximize cross-language compatibility and performance, implementations are recommended to prefer signed integer types over unsigned integer types and to avoid uint64 indices unless they are required by an application.



51
52
53
54
55
56
 
# File 'lib/arrow-format/org/apache/arrow/flatbuf/dictionary_encoding.rb', line 51

def index_type
  field_offset = @view.unpack_virtual_offset(6)
  return nil if field_offset.zero?

  @view.unpack_table(::ArrowFormat::Org::Apache::Arrow::Flatbuf::Int, field_offset)
end

#ordered? ⇒ Boolean

By default, dictionaries are not ordered, or the order does not have semantic meaning. In some statistical applications, dictionary-encoding is used to represent ordered categorical data, and we provide a way to preserve that metadata here

Returns:

  • (Boolean) 


62
63
64
65
66
67
 
# File 'lib/arrow-format/org/apache/arrow/flatbuf/dictionary_encoding.rb', line 62

def ordered?
  field_offset = @view.unpack_virtual_offset(8)
  return false if field_offset.zero?

  @view.unpack_bool(field_offset)
end