embulk-filter-unpivot 0.1.0

Sign up to get free protection for your applications and to get access to all the features.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: c352fdf1a5783a814f232d2f55b2c022773efea0
4
+ data.tar.gz: f35ef1645e26bb9b792ca4d81fc2023517f0d76c
5
+ SHA512:
6
+ metadata.gz: 4ccddd4b316e27a62ab9f9a2791ffe4788983bbbdf61ed3c025fa77e4ed865315c9e703e0ee9ed237e65872b82bb7652055ad9c4fa356fe62cab4504834bda44
7
+ data.tar.gz: 982258ee75bdf68317ecb9fd054450ae1abf1e92a999938332cbad45b7ac509efc466e38d2d7e9ae4a92cfc923169a6eac0ecb1d91848d2837d55de814249c18
@@ -0,0 +1,5 @@
1
+ *~
2
+ /pkg/
3
+ /tmp/
4
+ /.bundle/
5
+ /Gemfile.lock
@@ -0,0 +1 @@
1
+ jruby-9.1.5.0
data/Gemfile ADDED
@@ -0,0 +1,2 @@
1
+ source 'https://rubygems.org/'
2
+ gemspec
@@ -0,0 +1,21 @@
1
+
2
+ MIT License
3
+
4
+ Permission is hereby granted, free of charge, to any person obtaining
5
+ a copy of this software and associated documentation files (the
6
+ "Software"), to deal in the Software without restriction, including
7
+ without limitation the rights to use, copy, modify, merge, publish,
8
+ distribute, sublicense, and/or sell copies of the Software, and to
9
+ permit persons to whom the Software is furnished to do so, subject to
10
+ the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be
13
+ included in all copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16
+ EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18
+ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
19
+ LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
20
+ OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
21
+ WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
@@ -0,0 +1,77 @@
1
+ # Unpivot filter plugin for Embulk
2
+
3
+ [Embulk](https://github.com/embulk/embulk/) filter plugin to nomalize fields.
4
+
5
+ 「横持ち」のテーブル構造から「縦持ち」のテーブルに変換するembulkフィルタ。
6
+
7
+ ## Overview
8
+
9
+ * **Plugin type**: filter
10
+
11
+ 設備が1列に並んでいる不動産物件データを縦持ちに変換する例
12
+
13
+ * 変換元物件データ
14
+
15
+ |物件ID|家賃|ペット可|駐車場付き|バス・トイレ別|エアコン|
16
+ |---|---|---|---|---|---|
17
+ |1|8.5|0|0|1|1|
18
+ |2|5.5|0|0|0|0|
19
+ |3|10.0|1|0|1|1|
20
+ |4|15.5|0|1|1|1|
21
+
22
+ * 設備コード表
23
+
24
+ |設備ID|設備|
25
+ |---|---|
26
+ |1|ペット可|
27
+ |2|駐車場付き|
28
+ |3|バス・トイレ別|
29
+ |4|エアコン|
30
+
31
+ *↓*
32
+
33
+ * 変換後データ
34
+
35
+ |物件ID|設備ID|
36
+ |---|---|
37
+ |1|3|
38
+ |1|4|
39
+ |3|1|
40
+ |3|3|
41
+ |3|4|
42
+ |4|2|
43
+ |4|3|
44
+ |4|4|
45
+
46
+ ## Configuration
47
+
48
+ - **outer_key**: normalization record id field name(string, required)
49
+ - **inner_key**: master id field name (string, required)  
50
+ - **columns**: master key/value set (array, default: [])  
51
+ - **additional**: additional field (array, default: [])
52
+
53
+ ## Example
54
+
55
+ ```
56
+ filters:
57
+ - type: column
58
+ add_columns:
59
+      - {name: 設備ID, type: long, default: 0}
60
+      - {name: created_at, type: timestamp, src: '物件情報入力日'}
61
+ - {name: updated_at, type: timestamp, src: '物件情報更新日'}
62
+ - type: unpivot
63
+    outer_key: 物件ID
64
+    inner_key: 設備ID
65
+ additional: [created_at, updated_at]
66
+ columns:
67
+      - {name: 'ペット可', id: 1}
68
+      - {name: '駐車場付き', id: 2}
69
+      - {name: 'バス・トイレ別', id: 3}
70
+      - {name: 'エアコン', id: 4}
71
+ ```
72
+
73
+ ## Build
74
+
75
+ ```
76
+ $ rake
77
+ ```
@@ -0,0 +1,3 @@
1
+ require "bundler/gem_tasks"
2
+
3
+ task default: :build
@@ -0,0 +1,20 @@
1
+
2
+ Gem::Specification.new do |spec|
3
+ spec.name = "embulk-filter-unpivot"
4
+ spec.version = "0.1.0"
5
+ spec.authors = ["takemi.ohama"]
6
+ spec.summary = "Unpivot filter plugin for Embulk"
7
+ spec.description = "Unpivot"
8
+ spec.email = ["engineer@ietty.co.jp"]
9
+ spec.licenses = ["MIT"]
10
+ # TODO set this: spec.homepage = "https://github.com/YOUR_NAME/embulk-filter-unpivot"
11
+
12
+ spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
13
+ spec.test_files = spec.files.grep(%r{^(test|spec)/})
14
+ spec.require_paths = ["lib"]
15
+
16
+ #spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
17
+ spec.add_development_dependency 'embulk', ['>= 0.8.18']
18
+ spec.add_development_dependency 'bundler', ['>= 1.10.6']
19
+ spec.add_development_dependency 'rake', ['>= 10.0']
20
+ end
@@ -0,0 +1,82 @@
1
+ #require 'pry'
2
+ #require 'pry-nav'
3
+
4
+ module Embulk
5
+ module Filter
6
+
7
+ class Unpivot < FilterPlugin
8
+ Plugin.register_filter("unpivot", self)
9
+
10
+ def self.transaction(config, in_schema, &control)
11
+
12
+ task = {
13
+ "outer_key" => config.param("outer_key", :string),
14
+ "inner_key" => config.param("inner_key", :string),
15
+ "columns" => config.param("columns", :array, default: []),
16
+ "additional" => config.param("additional", :array, default: []),
17
+ }
18
+
19
+ out_columns = [
20
+ Column.new(nil, task["outer_key"], :string),
21
+ Column.new(nil, task["inner_key"], :string),
22
+ ]
23
+
24
+ task["additional"].each do |name|
25
+ col = in_schema.find { |sch| sch.name == name }
26
+ col.index = nil
27
+ out_columns.push(col)
28
+ end
29
+
30
+ yield(task, out_columns)
31
+ end
32
+
33
+ def init
34
+ # initialization code:
35
+ @idx_outer = get_index(task["outer_key"], in_schema)
36
+ @idx_inner = get_index(task["inner_key"], in_schema)
37
+ @indexes = {}
38
+ task["additional"].each do |name|
39
+ @indexes[name] = get_index(name, in_schema)
40
+ end
41
+ task["columns"].each do |target|
42
+ @indexes[target["name"]] = get_index(target["name"], in_schema)
43
+ end
44
+ end
45
+
46
+ def close
47
+ end
48
+
49
+ def add(page)
50
+ page.each do |record|
51
+ new_record = []
52
+ new_record.push(record[@idx_outer])
53
+ new_record.push(record[@idx_inner])
54
+
55
+ task["additional"].each do |name|
56
+ new_record.push(record[@indexes[name]])
57
+ end
58
+
59
+ task["columns"].each do |target|
60
+ index = @indexes[target["name"]]
61
+ next if record[index] == 0 or record[index] == ''
62
+ new_record[1] = target["id"]
63
+ page_builder.add(new_record)
64
+ end
65
+ end
66
+ end
67
+
68
+ def finish
69
+ page_builder.finish
70
+ end
71
+
72
+ private
73
+
74
+ def get_index(name, schema)
75
+ col = schema.select{|c| c.name == name }
76
+ col[0].index
77
+ end
78
+
79
+ end
80
+
81
+ end
82
+ end
metadata ADDED
@@ -0,0 +1,94 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-filter-unpivot
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - takemi.ohama
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2017-05-12 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: embulk
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: 0.8.18
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ">="
25
+ - !ruby/object:Gem::Version
26
+ version: 0.8.18
27
+ - !ruby/object:Gem::Dependency
28
+ name: bundler
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ">="
32
+ - !ruby/object:Gem::Version
33
+ version: 1.10.6
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ">="
39
+ - !ruby/object:Gem::Version
40
+ version: 1.10.6
41
+ - !ruby/object:Gem::Dependency
42
+ name: rake
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '10.0'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '10.0'
55
+ description: Unpivot
56
+ email:
57
+ - engineer@ietty.co.jp
58
+ executables: []
59
+ extensions: []
60
+ extra_rdoc_files: []
61
+ files:
62
+ - ".gitignore"
63
+ - ".ruby-version"
64
+ - Gemfile
65
+ - LICENSE.txt
66
+ - README.md
67
+ - Rakefile
68
+ - embulk-filter-unpivot.gemspec
69
+ - lib/embulk/filter/unpivot.rb
70
+ homepage:
71
+ licenses:
72
+ - MIT
73
+ metadata: {}
74
+ post_install_message:
75
+ rdoc_options: []
76
+ require_paths:
77
+ - lib
78
+ required_ruby_version: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ required_rubygems_version: !ruby/object:Gem::Requirement
84
+ requirements:
85
+ - - ">="
86
+ - !ruby/object:Gem::Version
87
+ version: '0'
88
+ requirements: []
89
+ rubyforge_project:
90
+ rubygems_version: 2.5.1
91
+ signing_key:
92
+ specification_version: 4
93
+ summary: Unpivot filter plugin for Embulk
94
+ test_files: []