red-arrow-activerecord 0.1.1 → 0.1.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +2 -1
- data/Rakefile +11 -1
- data/doc/text/news.md +12 -0
- data/lib/arrow-activerecord/arrowable.rb +26 -11
- data/lib/arrow-activerecord/version.rb +1 -1
- metadata +3 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: e8d253180a9bf6653d4034c162efd4b092e4ea9e44f983c2f4cb8ea2aa95c8e1
|
|
4
|
+
data.tar.gz: d5d7ea4de22c17357d4eefa6518fadc8c88420e161be91df946e85dfdf7964c9
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 90502eefb44fd4d6d6ffa6e66ce9864b5c6e0b384885ff5f5512f640629b19100a3d708af5b2644711bb6a25988f26bda90ee88c3f5adaad698288bda81a2f6c
|
|
7
|
+
data.tar.gz: 38f2b95f2da0f994ee554edeedaff59d5a5ec19a344c2c0957b74647f78c0bb20538d8d0119766f728356bd9e54850c95212a13160a8a64e61c914791eb73029
|
data/README.md
CHANGED
data/Rakefile
CHANGED
|
@@ -12,7 +12,17 @@ helper.install
|
|
|
12
12
|
|
|
13
13
|
desc "Run tests"
|
|
14
14
|
task :test do
|
|
15
|
-
ruby("test/run
|
|
15
|
+
ruby("test/run.rb")
|
|
16
16
|
end
|
|
17
17
|
|
|
18
18
|
task default: :test
|
|
19
|
+
|
|
20
|
+
release_task = Rake.application["release"]
|
|
21
|
+
# We use Trusted Publishing.
|
|
22
|
+
release_task.prerequisites.delete("build")
|
|
23
|
+
release_task.prerequisites.delete("release:rubygem_push")
|
|
24
|
+
release_task_comment = release_task.comment
|
|
25
|
+
if release_task_comment
|
|
26
|
+
release_task.clear_comments
|
|
27
|
+
release_task.comment = release_task_comment.gsub(/ and build.*$/, "")
|
|
28
|
+
end
|
data/doc/text/news.md
CHANGED
|
@@ -3,6 +3,31 @@ require 'arrow'
|
|
|
3
3
|
module ArrowActiveRecord
|
|
4
4
|
module Arrowable
|
|
5
5
|
def to_arrow(batch_size: 10000)
|
|
6
|
+
record_batches = each_record_batch(batch_size:).to_a
|
|
7
|
+
Arrow::Table.new(record_batches.first.schema, record_batches)
|
|
8
|
+
end
|
|
9
|
+
|
|
10
|
+
def each_record_batch(batch_size: 10000, &block)
|
|
11
|
+
return to_enum(__method__, batch_size:) unless block_given?
|
|
12
|
+
|
|
13
|
+
schema = build_arrow_schema
|
|
14
|
+
target_column_names = schema.fields.collect(&:name)
|
|
15
|
+
record_batch_builder = Arrow::RecordBatchBuilder.new(schema)
|
|
16
|
+
in_batches(of: batch_size).each do |relation|
|
|
17
|
+
records = relation.pluck(*target_column_names)
|
|
18
|
+
if target_column_names.size == 1
|
|
19
|
+
# [1, 2, 3] ->
|
|
20
|
+
# [[1], [2], [3]]
|
|
21
|
+
record_batch_builder.append(records.collect {|value| [value]})
|
|
22
|
+
else
|
|
23
|
+
record_batch_builder.append(records)
|
|
24
|
+
end
|
|
25
|
+
yield(record_batch_builder.flush)
|
|
26
|
+
end
|
|
27
|
+
end
|
|
28
|
+
|
|
29
|
+
private
|
|
30
|
+
def build_arrow_schema
|
|
6
31
|
target_column_names = select_values
|
|
7
32
|
target_column_names = column_names if select_values.empty?
|
|
8
33
|
|
|
@@ -14,19 +39,9 @@ module ArrowActiveRecord
|
|
|
14
39
|
end
|
|
15
40
|
fields << {name: name, data_type: extract_arrow_data_type(target_column)}
|
|
16
41
|
end
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
record_batches = []
|
|
20
|
-
record_batch_builder = Arrow::RecordBatchBuilder.new(schema)
|
|
21
|
-
in_batches(of: batch_size).each do |relation|
|
|
22
|
-
records = relation.pluck(*target_column_names)
|
|
23
|
-
record_batch_builder.append(records)
|
|
24
|
-
record_batches << record_batch_builder.flush
|
|
25
|
-
end
|
|
26
|
-
Arrow::Table.new(schema, record_batches)
|
|
42
|
+
Arrow::Schema.new(fields)
|
|
27
43
|
end
|
|
28
44
|
|
|
29
|
-
private
|
|
30
45
|
def extract_arrow_data_type(column)
|
|
31
46
|
type = nil
|
|
32
47
|
if column
|
metadata
CHANGED
|
@@ -1,15 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: red-arrow-activerecord
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.3
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- hatappi
|
|
8
8
|
- Kouhei Sutou
|
|
9
|
-
autorequire:
|
|
10
9
|
bindir: bin
|
|
11
10
|
cert_chain: []
|
|
12
|
-
date:
|
|
11
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
13
12
|
dependencies:
|
|
14
13
|
- !ruby/object:Gem::Dependency
|
|
15
14
|
name: activerecord
|
|
@@ -113,7 +112,6 @@ homepage: https://github.com/red-data-tools/red-arrow-activerecord
|
|
|
113
112
|
licenses:
|
|
114
113
|
- MIT
|
|
115
114
|
metadata: {}
|
|
116
|
-
post_install_message:
|
|
117
115
|
rdoc_options: []
|
|
118
116
|
require_paths:
|
|
119
117
|
- lib
|
|
@@ -128,9 +126,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
128
126
|
- !ruby/object:Gem::Version
|
|
129
127
|
version: '0'
|
|
130
128
|
requirements: []
|
|
131
|
-
|
|
132
|
-
rubygems_version: 2.7.6
|
|
133
|
-
signing_key:
|
|
129
|
+
rubygems_version: 4.0.10
|
|
134
130
|
specification_version: 4
|
|
135
131
|
summary: A library that provides conversion method between Apache Arrow and ActiveRecord
|
|
136
132
|
test_files: []
|