Skip to content

GH-48553: [Ruby] Add support for reading timestamp array #48554

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kou merged 3 commits into from
Dec 17, 2025
Merged

GH-48553: [Ruby] Add support for reading timestamp array #48554

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
3cafd6a
GH-48553: [Ruby] Add support for reading timestamp array
kou Dec 16, 2025
3511322
Fix name
kou Dec 16, 2025
45b0241
Fix unit
kou Dec 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions ruby/red-arrow-format/lib/arrow-format/array.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,6 +183,12 @@ def to_a
end
end

class TimestampArray < TemporalArray
def to_a
apply_validity(@values_buffer.values(:s64, 0, @size))
end
end

class VariableSizeBinaryLayoutArray < Array
def initialize(type, size, validity_buffer, offsets_buffer, values_buffer)
super(type, size, validity_buffer)
Expand Down
4 changes: 4 additions & 0 deletions ruby/red-arrow-format/lib/arrow-format/file-reader.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
require_relative "org/apache/arrow/flatbuf/schema"
require_relative "org/apache/arrow/flatbuf/struct_"
require_relative "org/apache/arrow/flatbuf/time"
require_relative "org/apache/arrow/flatbuf/timestamp"
require_relative "org/apache/arrow/flatbuf/time_unit"
require_relative "org/apache/arrow/flatbuf/union"
require_relative "org/apache/arrow/flatbuf/union_mode"
Expand Down Expand Up @@ -208,6 +209,9 @@ def read_field(fb_field)
type = Time64Type.new(:nanosecond)
end
end
when Org::Apache::Arrow::Flatbuf::Timestamp
unit = fb_type.unit.name.downcase.to_sym
type = TimestampType.new(unit, fb_type.timezone)
when Org::Apache::Arrow::Flatbuf::List
type = ListType.new(read_field(fb_field.children[0]))
when Org::Apache::Arrow::Flatbuf::LargeList
Expand Down
25 changes: 21 additions & 4 deletions ruby/red-arrow-format/lib/arrow-format/type.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -274,12 +274,16 @@ def build_array(size, validity_buffer, values_buffer)
end

class TimeType < TemporalType
attr_reader :unit
def initialize(name, unit)
super(name)
@unit = unit
end
end

class Time32Type < TimeType
def initialize(unit)
super("Time32")
@unit = unit
super("Time32", unit)
end

def build_array(size, validity_buffer, values_buffer)
Expand All @@ -289,15 +293,28 @@ def build_array(size, validity_buffer, values_buffer)

class Time64Type < TimeType
def initialize(unit)
super("Time64")
@unit = unit
super("Time64", unit)
end

def build_array(size, validity_buffer, values_buffer)
Time64Array.new(self, size, validity_buffer, values_buffer)
end
end

class TimestampType < TemporalType
attr_reader :unit
attr_reader :timezone
def initialize(unit, timezone)
super("Timestamp")
@unit = unit
@timezone = timezone
end

def build_array(size, validity_buffer, values_buffer)
TimestampArray.new(self, size, validity_buffer, values_buffer)
end
end

class VariableSizeBinaryType < Type
end

Expand Down
164 changes: 164 additions & 0 deletions ruby/red-arrow-format/test/test-file-reader.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,10 @@ def read
end
end

def type
@type ||= @reader.first.schema.fields[0].type
end

sub_test_case("Null") do
def build_array
Arrow::NullArray.new(3)
Expand Down Expand Up @@ -245,6 +249,10 @@ def test_read
assert_equal([{"value" => [@time_00_00_10, nil, @time_00_01_10]}],
read)
end

def test_type
assert_equal(:second, type.unit)
end
end

sub_test_case("Time32(:millisecond)") do
Expand All @@ -263,6 +271,10 @@ def test_read
assert_equal([{"value" => [@time_00_00_10_000, nil, @time_00_01_10_000]}],
read)
end

def test_type
assert_equal(:millisecond, type.unit)
end
end

sub_test_case("Time64(:microsecond)") do
Expand Down Expand Up @@ -293,6 +305,10 @@ def test_read
],
read)
end

def test_type
assert_equal(:microsecond, type.unit)
end
end

sub_test_case("Time64(:nanosecond)") do
Expand Down Expand Up @@ -323,6 +339,154 @@ def test_read
],
read)
end

def test_type
assert_equal(:nanosecond, type.unit)
end
end

sub_test_case("Timestamp(:second)") do
def setup(&block)
@timestamp_2019_11_18_00_09_11 = 1574003351
@timestamp_2025_12_16_05_33_58 = 1765863238
Copy link
Collaborator

@hiroyuki-sato hiroyuki-sato Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
@timestamp_2025_12_16_05_33_58 = 1765863238
@timestamp_2025_12_16_05_33_58 = 1765830838 
[6] pry(main)> Time.new(2025,12,16,5,33,58).to_i
=> 1765830838

super(&block)
end

def build_array
Arrow::TimestampArray.new(:second,
[
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
])
end

def test_read
assert_equal([
{
"value" => [
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
],
},
],
read)
end
end

sub_test_case("Timestamp(:millisecond)") do
def setup(&block)
@timestamp_2019_11_18_00_09_11 = 1574003351 * 1_000
@timestamp_2025_12_16_05_33_58 = 1765863238 * 1_000
Copy link
Collaborator

@hiroyuki-sato hiroyuki-sato Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
@timestamp_2025_12_16_05_33_58 = 1765863238 * 1_000
@timestamp_2025_12_16_05_33_58 = 1765830838 * 1_000 
[6] pry(main)> Time.new(2025,12,16,5,33,58).to_i
=> 1765830838

super(&block)
end

def build_array
Arrow::TimestampArray.new(:milli,
[
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
])
end

def test_read
assert_equal([
{
"value" => [
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
],
},
],
read)
end
end

sub_test_case("Timestamp(:microsecond)") do
def setup(&block)
@timestamp_2019_11_18_00_09_11 = 1574003351 * 1_000_000
@timestamp_2025_12_16_05_33_58 = 1765863238 * 1_000_000
Copy link
Collaborator

@hiroyuki-sato hiroyuki-sato Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
@timestamp_2025_12_16_05_33_58 = 1765863238 * 1_000_000
@timestamp_2025_12_16_05_33_58 = 1765830838 * 1_000_000 
[6] pry(main)> Time.new(2025,12,16,5,33,58).to_i
=> 1765830838

super(&block)
end

def build_array
Arrow::TimestampArray.new(:micro,
[
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
])
end

def test_read
assert_equal([
{
"value" => [
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
],
},
],
read)
end
end

sub_test_case("Timestamp(:nanosecond)") do
def setup(&block)
@timestamp_2019_11_18_00_09_11 = 1574003351 * 1_000_000_000
@timestamp_2025_12_16_05_33_58 = 1765863238 * 1_000_000_000
Copy link
Collaborator

@hiroyuki-sato hiroyuki-sato Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
@timestamp_2025_12_16_05_33_58 = 1765863238 * 1_000_000_000
@timestamp_2025_12_16_05_33_58 = 1765830838 * 1_000_000_000 
[6] pry(main)> Time.new(2025,12,16,5,33,58).to_i
=> 1765830838

super(&block)
end

def build_array
Arrow::TimestampArray.new(:nano,
[
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
])
end

def test_read
assert_equal([
{
"value" => [
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
],
},
],
read)
end
end

sub_test_case("Timestamp(timezone)") do
def setup(&block)
@timezone = "UTC"
@timestamp_2019_11_18_00_09_11 = 1574003351
@timestamp_2025_12_16_05_33_58 = 1765863238
Copy link
Collaborator

@hiroyuki-sato hiroyuki-sato Dec 16, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
@timestamp_2025_12_16_05_33_58 = 1765863238
@timestamp_2025_12_16_05_33_58 = 1765830838 
[6] pry(main)> Time.new(2025,12,16,5,33,58).to_i
=> 1765830838

super(&block)
end

def build_array
data_type = Arrow::TimestampDataType.new(:second, @timezone)
Arrow::TimestampArray.new(data_type,
[
@timestamp_2019_11_18_00_09_11,
nil,
@timestamp_2025_12_16_05_33_58,
])
end

def test_type
assert_equal([:second, @timezone],
[type.unit, type.timezone])
end
end

sub_test_case("Binary") do
Expand Down
Loading