embulk-filter-expand_json_array 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +5 -0
- data/.ruby-version +1 -0
- data/Gemfile +2 -0
- data/LICENSE.txt +21 -0
- data/README.md +58 -0
- data/Rakefile +3 -0
- data/embulk-filter-expand_json_array.gemspec +21 -0
- data/example/data.tsv +2 -0
- data/example/embulk.yml +24 -0
- data/lib/embulk/filter/expand_json_array.rb +59 -0
- metadata +110 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 39016765cabb31388f886776716e7c19dcedf13f
|
4
|
+
data.tar.gz: 0ff2be418ab5199de563afa1169f57695c775d1c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: fad74fff4af56f6ee404098ec16f2ed7c75e3b1b8b8aa1b8f4946b2201e732d414eca856649ff8dfaa2de20c610456ad64246c65aefe2d51e85d722fbfcca804
|
7
|
+
data.tar.gz: cec5c1c5f58feac4ec725dcf6057766b9573d9af563d548d4ae0c64845a0647d5be904492d80246ae14e0a22c945c8da00646b0809fb6844212518649b0ba761
|
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
jruby-9.1.2.0
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -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.
|
data/README.md
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
# Expand Json Array filter plugin for Embulk
|
2
|
+
|
3
|
+
## Overview
|
4
|
+
|
5
|
+
* **Plugin type**: filter
|
6
|
+
|
7
|
+
This is a embulk plugin for expanding record which has json column includes `N`-size array to `N` records.
|
8
|
+
|
9
|
+
For example, plugin expands below record which has json column `json_value` includes size-3 array value as `latest_receipt_info` to 3 records.
|
10
|
+
|
11
|
+
Before:
|
12
|
+
|
13
|
+
```
|
14
|
+
+-------------------------+---------+-------------+--------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
15
|
+
| time:timestamp | id:long | name:string | score:double | json_payload:string |
|
16
|
+
+-------------------------+---------+-------------+--------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
17
|
+
| 2015-10-11 00:00:00 UTC | 0 | Avis Lind | -3256.869635206057 | {"phone_numbers":"1-276-220-7263","app_id":0,"point":-1601.6890336884562,"created_at":"2015-10-07 20:23:57 +0900","profile":{"like_words":["maiores","eum","aut"],"anniversary":{"voluptatem":"dolor","et":"ullam"}},"latest_receipt_info":[1,2,3]} |
|
18
|
+
+-------------------------+---------+-------------+--------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|
19
|
+
```
|
20
|
+
|
21
|
+
Filtered:
|
22
|
+
|
23
|
+
```
|
24
|
+
+-------------------------+---------+-------------+--------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------+
|
25
|
+
| time:timestamp | id:long | name:string | score:double | json_payload:string | latest_receipt_info:string |
|
26
|
+
+-------------------------+---------+-------------+--------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------+
|
27
|
+
| 2015-10-11 00:00:00 UTC | 0 | Avis Lind | -3256.869635206057 | {"phone_numbers":"1-276-220-7263","app_id":0,"point":-1601.6890336884562,"created_at":"2015-10-07 20:23:57 +0900","profile":{"like_words":["maiores","eum","aut"],"anniversary":{"voluptatem":"dolor","et":"ullam"}},"latest_receipt_info":[1,2,3]} | 1 |
|
28
|
+
| 2015-10-11 00:00:00 UTC | 0 | Avis Lind | -3256.869635206057 | {"phone_numbers":"1-276-220-7263","app_id":0,"point":-1601.6890336884562,"created_at":"2015-10-07 20:23:57 +0900","profile":{"like_words":["maiores","eum","aut"],"anniversary":{"voluptatem":"dolor","et":"ullam"}},"latest_receipt_info":[1,2,3]} | 2 |
|
29
|
+
| 2015-10-11 00:00:00 UTC | 0 | Avis Lind | -3256.869635206057 | {"phone_numbers":"1-276-220-7263","app_id":0,"point":-1601.6890336884562,"created_at":"2015-10-07 20:23:57 +0900","profile":{"like_words":["maiores","eum","aut"],"anniversary":{"voluptatem":"dolor","et":"ullam"}},"latest_receipt_info":[1,2,3]} | 3 |
|
30
|
+
+-------------------------+---------+-------------+--------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+----------------------------+
|
31
|
+
```
|
32
|
+
|
33
|
+
## Configuration
|
34
|
+
|
35
|
+
- **json_column_name**: column name of json value in record (string , required)
|
36
|
+
- **root**: pointer of array value in json, specified as [jsonpath](https://github.com/joshbuddy/jsonpath)(string , required)
|
37
|
+
- **expanded_column_name**: column name after parsing target array value in json (string , required)
|
38
|
+
|
39
|
+
## Example
|
40
|
+
|
41
|
+
```yaml
|
42
|
+
filters:
|
43
|
+
- type: expand_json_array
|
44
|
+
json_column_name: json_payload
|
45
|
+
root: "$.latest_receipt_info"
|
46
|
+
expanded_column_name: latest_receipt_info
|
47
|
+
```
|
48
|
+
|
49
|
+
|
50
|
+
## Build
|
51
|
+
|
52
|
+
```
|
53
|
+
$ rake
|
54
|
+
```
|
55
|
+
|
56
|
+
## Reference
|
57
|
+
|
58
|
+
- [civitaspo/embulk-filter-expand_json](https://github.com/civitaspo/embulk-filter-expand_json)
|
data/Rakefile
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
|
2
|
+
Gem::Specification.new do |spec|
|
3
|
+
spec.name = "embulk-filter-expand_json_array"
|
4
|
+
spec.version = "0.1.0"
|
5
|
+
spec.authors = ["Naoki AINOYA"]
|
6
|
+
spec.summary = "Expand Json Array filter plugin for Embulk"
|
7
|
+
spec.description = "Expand Json Array"
|
8
|
+
spec.email = ["ainonic@gmail.com"]
|
9
|
+
spec.licenses = ["MIT"]
|
10
|
+
# TODO set this: spec.homepage = "https://github.com/ainonic/embulk-filter-expand_json_array"
|
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 'jsonpath', ['>= 0.5.8']
|
17
|
+
|
18
|
+
spec.add_development_dependency 'embulk', ['>= 0.8.13']
|
19
|
+
spec.add_development_dependency 'bundler', ['>= 1.10.6']
|
20
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
21
|
+
end
|
data/example/data.tsv
ADDED
@@ -0,0 +1,2 @@
|
|
1
|
+
time id name score json_payload
|
2
|
+
2015-10-11 08:06:23 +0900 0 Avis Lind -3256.869635206057 {"phone_numbers":"1-276-220-7263","app_id":0,"point":-1601.6890336884562,"created_at":"2015-10-07 20:23:57 +0900","profile":{"like_words":["maiores","eum","aut"],"anniversary":{"voluptatem":"dolor","et":"ullam"}},"latest_receipt_info":[1,2,3]}
|
data/example/embulk.yml
ADDED
@@ -0,0 +1,24 @@
|
|
1
|
+
in:
|
2
|
+
type: file
|
3
|
+
path_prefix: ./data.tsv
|
4
|
+
parser:
|
5
|
+
type: csv
|
6
|
+
delimiter: "\t"
|
7
|
+
charset: UTF-8
|
8
|
+
newline: CRLF
|
9
|
+
null_string: 'NULL'
|
10
|
+
skip_header_lines: 1
|
11
|
+
comment_line_marker: '#'
|
12
|
+
columns:
|
13
|
+
- {name: time, type: timestamp, format: "%Y-%m-%d"}
|
14
|
+
- {name: id, type: long}
|
15
|
+
- {name: name, type: string}
|
16
|
+
- {name: score, type: double}
|
17
|
+
- {name: json_payload, type: string}
|
18
|
+
filters:
|
19
|
+
- type: expand_json_array
|
20
|
+
json_column_name: json_payload
|
21
|
+
root: "$.latest_receipt_info"
|
22
|
+
expanded_column_name: latest_receipt_info
|
23
|
+
out:
|
24
|
+
type: stdout
|
@@ -0,0 +1,59 @@
|
|
1
|
+
require 'jsonpath'
|
2
|
+
|
3
|
+
module Embulk
|
4
|
+
module Filter
|
5
|
+
|
6
|
+
class ExpandJsonArray < FilterPlugin
|
7
|
+
Plugin.register_filter("expand_json_array", self)
|
8
|
+
|
9
|
+
def self.transaction(config, in_schema, &control)
|
10
|
+
# configuration code:
|
11
|
+
task = {
|
12
|
+
"json_column_name" => config.param("json_column_name", :string),
|
13
|
+
"root" => config.param("root", :string),
|
14
|
+
"expanded_column_name" => config.param("expanded_column_name", :string)
|
15
|
+
}
|
16
|
+
|
17
|
+
task['parse_target_column'] = in_schema.find{|c| c.name == task['json_column_name']}
|
18
|
+
|
19
|
+
columns = [
|
20
|
+
Column.new(nil, task["expanded_column_name"], :string),
|
21
|
+
]
|
22
|
+
|
23
|
+
out_columns = in_schema + columns
|
24
|
+
|
25
|
+
yield(task, out_columns)
|
26
|
+
end
|
27
|
+
|
28
|
+
def init
|
29
|
+
# initialization code:
|
30
|
+
@json_column_name = task["json_column_name"]
|
31
|
+
@root = task["root"]
|
32
|
+
@expanded_column_name = task["expanded_column_name"]
|
33
|
+
|
34
|
+
@parse_target_column = task['parse_target_column']
|
35
|
+
|
36
|
+
@json_path = JsonPath.new(@root)
|
37
|
+
end
|
38
|
+
|
39
|
+
def close
|
40
|
+
end
|
41
|
+
|
42
|
+
def add(page)
|
43
|
+
# filtering code:
|
44
|
+
page.each do |record|
|
45
|
+
expanded_columns = @json_path.on(record[@parse_target_column['index']]).flatten
|
46
|
+
|
47
|
+
expanded_columns.each do |ec|
|
48
|
+
page_builder.add(record + [ec])
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def finish
|
54
|
+
page_builder.finish
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
end
|
59
|
+
end
|
metadata
ADDED
@@ -0,0 +1,110 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-filter-expand_json_array
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Naoki AINOYA
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-10-12 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
requirement: !ruby/object:Gem::Requirement
|
15
|
+
requirements:
|
16
|
+
- - ">="
|
17
|
+
- !ruby/object:Gem::Version
|
18
|
+
version: 0.5.8
|
19
|
+
name: jsonpath
|
20
|
+
prerelease: false
|
21
|
+
type: :runtime
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.5.8
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
requirement: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - ">="
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: 0.8.13
|
33
|
+
name: embulk
|
34
|
+
prerelease: false
|
35
|
+
type: :development
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 0.8.13
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
requirement: !ruby/object:Gem::Requirement
|
43
|
+
requirements:
|
44
|
+
- - ">="
|
45
|
+
- !ruby/object:Gem::Version
|
46
|
+
version: 1.10.6
|
47
|
+
name: bundler
|
48
|
+
prerelease: false
|
49
|
+
type: :development
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: 1.10.6
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
requirement: !ruby/object:Gem::Requirement
|
57
|
+
requirements:
|
58
|
+
- - ">="
|
59
|
+
- !ruby/object:Gem::Version
|
60
|
+
version: '10.0'
|
61
|
+
name: rake
|
62
|
+
prerelease: false
|
63
|
+
type: :development
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '10.0'
|
69
|
+
description: Expand Json Array
|
70
|
+
email:
|
71
|
+
- ainonic@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- ".gitignore"
|
77
|
+
- ".ruby-version"
|
78
|
+
- Gemfile
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- embulk-filter-expand_json_array.gemspec
|
83
|
+
- example/data.tsv
|
84
|
+
- example/embulk.yml
|
85
|
+
- lib/embulk/filter/expand_json_array.rb
|
86
|
+
homepage:
|
87
|
+
licenses:
|
88
|
+
- MIT
|
89
|
+
metadata: {}
|
90
|
+
post_install_message:
|
91
|
+
rdoc_options: []
|
92
|
+
require_paths:
|
93
|
+
- lib
|
94
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
95
|
+
requirements:
|
96
|
+
- - ">="
|
97
|
+
- !ruby/object:Gem::Version
|
98
|
+
version: '0'
|
99
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
requirements: []
|
105
|
+
rubyforge_project:
|
106
|
+
rubygems_version: 2.6.4
|
107
|
+
signing_key:
|
108
|
+
specification_version: 4
|
109
|
+
summary: Expand Json Array filter plugin for Embulk
|
110
|
+
test_files: []
|