Class: DeltaSharing::Schema

Inherits:
Object
  • Object
show all
Defined in:
lib/delta_sharing/schema.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(schema_string) ⇒ Schema

Returns a new instance of Schema.



7
8
9
10
11
# File 'lib/delta_sharing/schema.rb', line 7

def initialize(schema_string)
  schema_json = JSON.parse(schema_string)
  @fields = schema_json['fields'] || []
  @arrow_schema = build_arrow_schema
end

Instance Attribute Details

#arrow_schemaObject (readonly)

Returns the value of attribute arrow_schema.



5
6
7
# File 'lib/delta_sharing/schema.rb', line 5

def arrow_schema
  @arrow_schema
end

#fieldsObject (readonly)

Returns the value of attribute fields.



5
6
7
# File 'lib/delta_sharing/schema.rb', line 5

def fields
  @fields
end

Instance Method Details

#build_arrow_schemaObject



21
22
23
24
25
26
27
28
# File 'lib/delta_sharing/schema.rb', line 21

def build_arrow_schema
  fields = @fields.map do |field|
    arrow_type = delta_type_to_arrow_type(field['type'])
    Arrow::Field.new(field['name'], arrow_type, field['nullable'])
  end

  Arrow::Schema.new(fields)
end

#delta_type_to_arrow_type(delta_type) ⇒ Object



30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
# File 'lib/delta_sharing/schema.rb', line 30

def delta_type_to_arrow_type(delta_type)
  case delta_type
  when 'boolean'
    Arrow::BooleanDataType.new
  when 'byte'
    Arrow::Int8DataType.new
  when 'short'
    Arrow::Int16DataType.new
  when 'integer'
    Arrow::Int32DataType.new
  when 'long'
    Arrow::Int64DataType.new
  when 'float'
    Arrow::FloatDataType.new
  when 'double'
    Arrow::DoubleDataType.new
  when 'string'
    Arrow::StringDataType.new
  when 'binary'
    Arrow::BinaryDataType.new
  when 'date'
    Arrow::Date32DataType.new
  when 'timestamp'
    Arrow::TimestampDataType.new(:micro)
  else
    if delta_type.is_a?(Hash)
      case delta_type['type']
      when 'decimal'
        Arrow::DecimalDataType.new(delta_type['precision'], delta_type['scale'])
      when 'array'
        element_type = delta_type_to_arrow_type(delta_type['elementType'])
        Arrow::ListDataType.new(element_type)
      when 'map'
        key_type = delta_type_to_arrow_type(delta_type['keyType'])
        value_type = delta_type_to_arrow_type(delta_type['valueType'])
        Arrow::MapDataType.new(key_type, value_type)
      when 'struct'
        fields = delta_type['fields'].map do |field|
          field_type = delta_type_to_arrow_type(field['type'])
          Arrow::Field.new(field['name'], field_type, field['nullable'])
        end
        Arrow::StructDataType.new(fields)
      else
        Arrow::StringDataType.new # Fallback to string
      end
    else
      Arrow::StringDataType.new # Fallback to string
    end
  end
end

#field_index(name) ⇒ Object



17
18
19
# File 'lib/delta_sharing/schema.rb', line 17

def field_index(name)
  @fields.find_index { |f| f['name'] == name }
end

#field_namesObject



13
14
15
# File 'lib/delta_sharing/schema.rb', line 13

def field_names
  @fields.map { |f| f['name'] }
end