embulk-filter-azure_translator_api 0.1.0

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.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: afa13d2b165a2a901773a492d11e0ef786245125
4
+ data.tar.gz: 4b8d2da4781f4bfcb20f66527d69f666522225ef
5
+ SHA512:
6
+ metadata.gz: 0b0da7a63c4d1c61cec6bbec439c1de470c8ad84a662ac384897a91ee0b1ed9a2ea5dfeff24caba3a0fedb3d8a0e8fa33d9810bcb565749c21a8505881ee2105
7
+ data.tar.gz: 598e775bab15d78c62a3f5e8c27521fce63f9b2baf74bbb7b6b42a3780abf6fccb47d2c90af2ac265a1a517346d1c5bd74a9d4c38cd54873525cce8e88509f8d
@@ -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 +1,43 @@
1
+ # Azure Translator Api filter plugin for Embulk
2
+
3
+ Write short description here and embulk-filter-azure_translator_api.gemspec file.
4
+
5
+ ## Documentation
6
+ * [seamlessly](https://www.microsoft.com/cognitive-services/en-us/translator-api/documentation/Text/overview)
7
+ * [Microsoft Cognitive Services](http://docs.microsofttranslator.com/text-translate.html)
8
+
9
+ ## Overview
10
+
11
+ * **Plugin type**: filter
12
+
13
+ ## Configuration
14
+ - **api_type**: api_type (string),
15
+ - **out_key_name_suffix**: out_key_name_suffix (string),
16
+ - **key_names**: key_names (array),
17
+ - **params**: params (hash, default: {}),
18
+ - **delay**: delay (integer, default: 0),
19
+ - **subscription_key**: subscription_key (string),
20
+ - **content_type**: content_type (string, default: nil),
21
+ - **category**: category (string, default: nil),
22
+ - **to**: to (string),
23
+ - **from**: from (string, default: nil)
24
+
25
+ ## Example
26
+
27
+ ```yaml
28
+ filters:
29
+ - type: azure_translator_api
30
+ key_names:
31
+ - string_column
32
+ - string_column2
33
+ out_key_name_suffix: translated
34
+ subscription_key: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
35
+ api_type: Translate
36
+ to: ja
37
+ ```
38
+
39
+ ## Build
40
+
41
+ ```
42
+ $ rake
43
+ ```
@@ -0,0 +1,3 @@
1
+ require "bundler/gem_tasks"
2
+
3
+ task default: :build
@@ -0,0 +1,21 @@
1
+
2
+ Gem::Specification.new do |spec|
3
+ spec.name = "embulk-filter-azure_translator_api"
4
+ spec.version = "0.1.0"
5
+ spec.authors = ["toyama0919"]
6
+ spec.summary = "Azure Translator Api filter plugin for Embulk"
7
+ spec.description = "Azure Translator Api"
8
+ spec.email = ["toyama0919@gmail.com"]
9
+ spec.licenses = ["MIT"]
10
+ spec.homepage = "https://github.com/toyama0919/embulk-filter-azure_translator_api"
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 'rest-client'
17
+ spec.add_dependency 'crack'
18
+ spec.add_development_dependency 'embulk', ['>= 0.8.15']
19
+ spec.add_development_dependency 'bundler', ['>= 1.10.6']
20
+ spec.add_development_dependency 'rake', ['>= 10.0']
21
+ end
@@ -0,0 +1,73 @@
1
+ require_relative 'azure_translator_api/azure_translator_client'
2
+
3
+ module Embulk
4
+ module Filter
5
+
6
+ class AzureTranslatorApi < FilterPlugin
7
+ Plugin.register_filter("azure_translator_api", self)
8
+
9
+ def self.transaction(config, in_schema, &control)
10
+ task = {
11
+ "api_type" => config.param("api_type", :string),
12
+ "out_key_name_suffix" => config.param("out_key_name_suffix", :string),
13
+ "key_names" => config.param("key_names", :array),
14
+ "params" => config.param("params", :hash, default: {}),
15
+ "delay" => config.param("delay", :integer, default: 0),
16
+ "subscription_key" => config.param("subscription_key", :string),
17
+ "content_type" => config.param("content_type", :string, default: nil),
18
+ "category" => config.param("category", :string, default: nil),
19
+ "to" => config.param("to", :string),
20
+ "from" => config.param("from", :string, default: nil)
21
+ }
22
+
23
+ add_columns = task['key_names'].map do |key_name|
24
+ Column.new(nil, key_name + task["out_key_name_suffix"], :string)
25
+ end
26
+
27
+ out_columns = in_schema + add_columns
28
+ task['authorization_token'] = AzureTranslatorClient.get_authorization_token(task["subscription_key"])
29
+
30
+ yield(task, out_columns)
31
+ end
32
+
33
+ def init
34
+ @delay = task['delay']
35
+ @key_names = task['key_names']
36
+ @out_key_name_suffix = task['out_key_name_suffix']
37
+
38
+ params = {
39
+ 'to' => task['to'],
40
+ }
41
+ params['from'] = task['from'] if task['from']
42
+ params['content_type'] = task['content_type'] if task['content_type']
43
+ params['category'] = task['category'] if task['category']
44
+ @client = AzureTranslatorClient.new(
45
+ params: params,
46
+ authorization_token: task['authorization_token'],
47
+ api_type: task['api_type']
48
+ )
49
+ end
50
+
51
+ def close
52
+ end
53
+
54
+ def add(page)
55
+ records = page.map do |record|
56
+ Hash[in_schema.names.zip(record)]
57
+ end
58
+
59
+ records.each do |record|
60
+ @key_names.each do |key_name|
61
+ record[key_name + @out_key_name_suffix] = @client.translate_text(record[key_name])
62
+ end
63
+ page_builder.add(record.values)
64
+ sleep @delay
65
+ end
66
+ end
67
+
68
+ def finish
69
+ page_builder.finish
70
+ end
71
+ end
72
+ end
73
+ end
@@ -0,0 +1,47 @@
1
+ require 'crack/xml'
2
+ require 'rest-client'
3
+
4
+ module Embulk
5
+ module Filter
6
+ class AzureTranslatorApi < FilterPlugin
7
+ class AzureTranslatorClient
8
+ ENDPOINT_PREFIX = "https://api.microsofttranslator.com/v2/http.svc"
9
+ AUTH_ENDPOINT_PREFIX = "https://api.cognitive.microsoft.com/sts/v1.0/issueToken"
10
+
11
+ def self.get_authorization_token(subscription_key)
12
+ RestClient.post AUTH_ENDPOINT_PREFIX, "", {
13
+ params: { 'Subscription-Key' => subscription_key }
14
+ }
15
+ end
16
+
17
+ def initialize(params: , authorization_token: , api_type:)
18
+ uri_string = "#{ENDPOINT_PREFIX}/#{api_type}"
19
+ @resource = RestClient::Resource.new uri_string
20
+ @params = params
21
+ @authorization_token = authorization_token
22
+ end
23
+
24
+ def translate_text(text)
25
+ translate(text)['string']
26
+ end
27
+
28
+ def translate(text)
29
+ request(text)
30
+ end
31
+
32
+ def request(text)
33
+ request_param = { text: text }.merge(@params)
34
+ Embulk.logger.debug("request_param => #{request_param}")
35
+ ::Crack::XML.parse(
36
+ @resource.get(
37
+ {
38
+ Authorization: "Bearer #{@authorization_token}",
39
+ params: request_param
40
+ }
41
+ )
42
+ )
43
+ end
44
+ end
45
+ end
46
+ end
47
+ end
metadata ADDED
@@ -0,0 +1,123 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-filter-azure_translator_api
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - toyama0919
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2017-01-26 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'
19
+ name: rest-client
20
+ prerelease: false
21
+ type: :runtime
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ">="
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
27
+ - !ruby/object:Gem::Dependency
28
+ requirement: !ruby/object:Gem::Requirement
29
+ requirements:
30
+ - - ">="
31
+ - !ruby/object:Gem::Version
32
+ version: '0'
33
+ name: crack
34
+ prerelease: false
35
+ type: :runtime
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ">="
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ requirement: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - ">="
45
+ - !ruby/object:Gem::Version
46
+ version: 0.8.15
47
+ name: embulk
48
+ prerelease: false
49
+ type: :development
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: 0.8.15
55
+ - !ruby/object:Gem::Dependency
56
+ requirement: !ruby/object:Gem::Requirement
57
+ requirements:
58
+ - - ">="
59
+ - !ruby/object:Gem::Version
60
+ version: 1.10.6
61
+ name: bundler
62
+ prerelease: false
63
+ type: :development
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: 1.10.6
69
+ - !ruby/object:Gem::Dependency
70
+ requirement: !ruby/object:Gem::Requirement
71
+ requirements:
72
+ - - ">="
73
+ - !ruby/object:Gem::Version
74
+ version: '10.0'
75
+ name: rake
76
+ prerelease: false
77
+ type: :development
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - ">="
81
+ - !ruby/object:Gem::Version
82
+ version: '10.0'
83
+ description: Azure Translator Api
84
+ email:
85
+ - toyama0919@gmail.com
86
+ executables: []
87
+ extensions: []
88
+ extra_rdoc_files: []
89
+ files:
90
+ - ".gitignore"
91
+ - ".ruby-version"
92
+ - Gemfile
93
+ - LICENSE.txt
94
+ - README.md
95
+ - Rakefile
96
+ - embulk-filter-azure_translator_api.gemspec
97
+ - lib/embulk/filter/azure_translator_api.rb
98
+ - lib/embulk/filter/azure_translator_api/azure_translator_client.rb
99
+ homepage: https://github.com/toyama0919/embulk-filter-azure_translator_api
100
+ licenses:
101
+ - MIT
102
+ metadata: {}
103
+ post_install_message:
104
+ rdoc_options: []
105
+ require_paths:
106
+ - lib
107
+ required_ruby_version: !ruby/object:Gem::Requirement
108
+ requirements:
109
+ - - ">="
110
+ - !ruby/object:Gem::Version
111
+ version: '0'
112
+ required_rubygems_version: !ruby/object:Gem::Requirement
113
+ requirements:
114
+ - - ">="
115
+ - !ruby/object:Gem::Version
116
+ version: '0'
117
+ requirements: []
118
+ rubyforge_project:
119
+ rubygems_version: 2.6.6
120
+ signing_key:
121
+ specification_version: 4
122
+ summary: Azure Translator Api filter plugin for Embulk
123
+ test_files: []