embulk-filter-google_translate_api 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 +13 -0
- data/LICENSE.txt +21 -0
- data/README.md +120 -0
- data/build.gradle +98 -0
- data/config/checkstyle/checkstyle.xml +128 -0
- data/config/checkstyle/default.xml +108 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +160 -0
- data/gradlew.bat +90 -0
- data/lib/embulk/filter/google_translate_api.rb +3 -0
- data/src/main/java/org/embulk/filter/google_translate_api/GoogleTranslateApiFilterPlugin.java +80 -0
- data/src/main/java/org/embulk/filter/google_translate_api/GoogleTranslateApiPageOutput.java +150 -0
- data/src/test/java/org/embulk/filter/google_translate_api/TestGoogleTranslateApiFilterPlugin.java +5 -0
- metadata +126 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: e0b8b1920af5d5c00f037a3daa8ef8653786571a
|
4
|
+
data.tar.gz: 976ad1852875d994a10d82fb748d2e72f9a7123b
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1f63e182a6633d7e55931b58536466670f5a0e267c0de96c5fef9316f4e4f3f7d777638484a1c9db17aacb6425ff1d1c3663a2d7ebf138787589b22811f8321b
|
7
|
+
data.tar.gz: f941fa3b74cc759329ef5a04220146525715e21d5c929f090270823757da11b1eb7b1c66b5b8d55b13091001c75ccdf9d0fd0c30185e105bbf60798347010b05
|
data/.gitignore
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 +1,120 @@
|
|
1
|
+
# Google Translate Api filter plugin for Embulk
|
2
|
+
|
3
|
+
Google Translate Api filter plugin for Embulk.
|
4
|
+
|
5
|
+
see support language. [Google Language Codes \- tomihasa](https://sites.google.com/site/tomihasa/google-language-codes)
|
6
|
+
|
7
|
+
## Overview
|
8
|
+
|
9
|
+
* **Plugin type**: filter
|
10
|
+
|
11
|
+
## Configuration
|
12
|
+
|
13
|
+
- **key_names**: target key names (array, required)
|
14
|
+
- **out_key_name_suffix**: translated target key names suffix (string, required)
|
15
|
+
- **source_lang**: source language (string, default: `null`)
|
16
|
+
- **target_lang**: target language (string, required)
|
17
|
+
- **sleep**: delay per record, define milliseconds. (string, required)
|
18
|
+
- **google_api_key**: google_api_key. support environment variable. pleaese `export GOOGLE_API_KEY`(string, default: `null`)
|
19
|
+
|
20
|
+
## Example
|
21
|
+
|
22
|
+
#### input
|
23
|
+
```yaml
|
24
|
+
- {
|
25
|
+
sentence1: 'Embulk supports plugins to add functions',
|
26
|
+
sentence2: 'Embulk is a parallel bulk data loader that helps data transfer between various storages, databases, NoSQL and cloud services.',
|
27
|
+
sentence3: 'You can share the plugins to keep your custom scripts readable, maintainable, and reusable.',
|
28
|
+
json_column: ['aaa', 'bbbb', 'cccc']
|
29
|
+
}
|
30
|
+
- {
|
31
|
+
sentence1: 'Automatic guessing of input file formats',
|
32
|
+
sentence2: 'Parallel & distributed execution to deal with big data sets',
|
33
|
+
json_column: ['aaa', 'bbbb', 'cccc']
|
34
|
+
}
|
35
|
+
|
36
|
+
```
|
37
|
+
|
38
|
+
#### setting
|
39
|
+
```yaml
|
40
|
+
filters:
|
41
|
+
- type: google_translate_api
|
42
|
+
key_names:
|
43
|
+
- sentence1
|
44
|
+
- sentence2
|
45
|
+
- sentence3
|
46
|
+
out_key_name_suffix: _translated
|
47
|
+
source_lang: en
|
48
|
+
target_lang: ja
|
49
|
+
sleep: 1000
|
50
|
+
google_api_key: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
51
|
+
```
|
52
|
+
|
53
|
+
#### output
|
54
|
+
```
|
55
|
+
*************************** 1 ***************************
|
56
|
+
sentence1 (string) : Embulk supports plugins to add functions
|
57
|
+
sentence2 (string) : Embulk is a parallel bulk data loader that helps data transfer between various storages, databases, NoSQL and cloud services.
|
58
|
+
sentence3 (string) : You can share the plugins to keep your custom scripts readable, maintainable, and reusable.
|
59
|
+
json_column ( json) : ["aaa","bbbb","cccc"]
|
60
|
+
sentence1_translated (string) : Embulkは、機能を追加するためのプラグインをサポートしています
|
61
|
+
sentence2_translated (string) : Embulkは、さまざまなストレージ、データベース、NoSQLのとクラウドサービス間のデータ転送を助けるパラレル・バルク・データ・ローダーです。
|
62
|
+
sentence3_translated (string) : あなたは、読み込み可能な保守性、および再利用可能なカスタムスクリプトを維持するためのプラグインを共有することができます。
|
63
|
+
*************************** 2 ***************************
|
64
|
+
sentence1 (string) : Automatic guessing of input file formats
|
65
|
+
sentence2 (string) : Parallel & distributed execution to deal with big data sets
|
66
|
+
sentence3 (string) :
|
67
|
+
json_column ( json) : ["aaa","bbbb","cccc"]
|
68
|
+
sentence1_translated (string) : 入力ファイル形式の自動推測
|
69
|
+
sentence2_translated (string) : ビッグデータ・セットに対処するための並列分散実行
|
70
|
+
sentence3_translated (string) :
|
71
|
+
embulk preview -G -b embulk_bundle -I tmp/test_translate.yml.liquid 10.86s user 0.68s system 115% cpu 9.991 total
|
72
|
+
```
|
73
|
+
|
74
|
+
## Example(Multi language combined)
|
75
|
+
|
76
|
+
#### input
|
77
|
+
```yaml
|
78
|
+
- {
|
79
|
+
sentence1: 'Embulk is a Java application.',
|
80
|
+
sentence2: 'Embulk ist eine Java-Anwendung.',
|
81
|
+
sentence3: 'Embulk是Java应用程序。',
|
82
|
+
json_column: ['aaa', 'bbbb', 'cccc']
|
83
|
+
}
|
84
|
+
|
85
|
+
```
|
86
|
+
|
87
|
+
#### setting
|
88
|
+
```yaml
|
89
|
+
filters:
|
90
|
+
- type: google_translate_api
|
91
|
+
key_names:
|
92
|
+
- sentence1
|
93
|
+
- sentence2
|
94
|
+
- sentence3
|
95
|
+
out_key_name_suffix: _translated
|
96
|
+
target_lang: ja
|
97
|
+
sleep: 1000
|
98
|
+
google_api_key: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
99
|
+
```
|
100
|
+
|
101
|
+
* If not define source_lang, auto detect language.
|
102
|
+
|
103
|
+
#### output
|
104
|
+
```
|
105
|
+
*************************** 1 ***************************
|
106
|
+
sentence1 (string) : Embulk is a Java application.
|
107
|
+
sentence2 (string) : Embulk ist eine Java-Anwendung.
|
108
|
+
sentence3 (string) : Embulk是Java应用程序。
|
109
|
+
json_column ( json) : ["aaa","bbbb","cccc"]
|
110
|
+
sentence1_translated (string) : Embulkは、Javaアプリケーションです。
|
111
|
+
sentence2_translated (string) : Embulkは、Javaアプリケーションです。
|
112
|
+
sentence3_translated (string) : Embulkは、Javaアプリケーションです。
|
113
|
+
```
|
114
|
+
|
115
|
+
|
116
|
+
## Build
|
117
|
+
|
118
|
+
```
|
119
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
120
|
+
```
|
data/build.gradle
ADDED
@@ -0,0 +1,98 @@
|
|
1
|
+
plugins {
|
2
|
+
id "com.jfrog.bintray" version "1.1"
|
3
|
+
id "com.github.jruby-gradle.base" version "0.1.5"
|
4
|
+
id "java"
|
5
|
+
id "checkstyle"
|
6
|
+
id "eclipse"
|
7
|
+
}
|
8
|
+
import com.github.jrubygradle.JRubyExec
|
9
|
+
repositories {
|
10
|
+
mavenCentral()
|
11
|
+
jcenter()
|
12
|
+
}
|
13
|
+
configurations {
|
14
|
+
provided
|
15
|
+
}
|
16
|
+
|
17
|
+
version = "0.1.0"
|
18
|
+
|
19
|
+
sourceCompatibility = 1.7
|
20
|
+
targetCompatibility = 1.7
|
21
|
+
|
22
|
+
dependencies {
|
23
|
+
compile "org.embulk:embulk-core:0.8.15"
|
24
|
+
provided "org.embulk:embulk-core:0.8.15"
|
25
|
+
// https://mvnrepository.com/artifact/com.google.cloud/google-cloud-translate
|
26
|
+
compile group: 'com.google.cloud', name: 'google-cloud-translate', version: '0.8.0'
|
27
|
+
|
28
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
29
|
+
testCompile "junit:junit:4.+"
|
30
|
+
}
|
31
|
+
|
32
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
33
|
+
doFirst { file("classpath").deleteDir() }
|
34
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
35
|
+
into "classpath"
|
36
|
+
}
|
37
|
+
clean { delete "classpath" }
|
38
|
+
|
39
|
+
checkstyle {
|
40
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
41
|
+
toolVersion = '6.14.1'
|
42
|
+
}
|
43
|
+
checkstyleMain {
|
44
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
45
|
+
ignoreFailures = true
|
46
|
+
}
|
47
|
+
checkstyleTest {
|
48
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
49
|
+
ignoreFailures = true
|
50
|
+
}
|
51
|
+
task checkstyle(type: Checkstyle) {
|
52
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
53
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
54
|
+
}
|
55
|
+
|
56
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
57
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
58
|
+
script "${project.name}.gemspec"
|
59
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
60
|
+
}
|
61
|
+
|
62
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
63
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
64
|
+
script "pkg/${project.name}-${project.version}.gem"
|
65
|
+
}
|
66
|
+
|
67
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) << {
|
68
|
+
println "> Build succeeded."
|
69
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
70
|
+
}
|
71
|
+
|
72
|
+
task gemspec {
|
73
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
74
|
+
inputs.file "build.gradle"
|
75
|
+
outputs.file gemspecFile
|
76
|
+
doLast { gemspecFile.write($/
|
77
|
+
Gem::Specification.new do |spec|
|
78
|
+
spec.name = "${project.name}"
|
79
|
+
spec.version = "${project.version}"
|
80
|
+
spec.authors = ["toyama0919"]
|
81
|
+
spec.summary = %[Google Translate Api filter plugin for Embulk]
|
82
|
+
spec.description = %[Google Translate Api filter plugin for Embulk]
|
83
|
+
spec.email = ["toyama0919@gmail.com"]
|
84
|
+
spec.licenses = ["MIT"]
|
85
|
+
# TODO set this: spec.homepage = "https://github.com/toyama0919/embulk-filter-google_translate_api"
|
86
|
+
|
87
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
88
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
89
|
+
spec.require_paths = ["lib"]
|
90
|
+
|
91
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
92
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
93
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
94
|
+
end
|
95
|
+
/$)
|
96
|
+
}
|
97
|
+
}
|
98
|
+
clean { delete "${project.name}.gemspec" }
|
@@ -0,0 +1,128 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
+
<!DOCTYPE module PUBLIC
|
3
|
+
"-//Puppy Crawl//DTD Check Configuration 1.3//EN"
|
4
|
+
"http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
|
5
|
+
<module name="Checker">
|
6
|
+
<!-- https://github.com/facebook/presto/blob/master/src/checkstyle/checks.xml -->
|
7
|
+
<module name="FileTabCharacter"/>
|
8
|
+
<module name="NewlineAtEndOfFile">
|
9
|
+
<property name="lineSeparator" value="lf"/>
|
10
|
+
</module>
|
11
|
+
<module name="RegexpMultiline">
|
12
|
+
<property name="format" value="\r"/>
|
13
|
+
<property name="message" value="Line contains carriage return"/>
|
14
|
+
</module>
|
15
|
+
<module name="RegexpMultiline">
|
16
|
+
<property name="format" value=" \n"/>
|
17
|
+
<property name="message" value="Line has trailing whitespace"/>
|
18
|
+
</module>
|
19
|
+
<module name="RegexpMultiline">
|
20
|
+
<property name="format" value="\{\n\n"/>
|
21
|
+
<property name="message" value="Blank line after opening brace"/>
|
22
|
+
</module>
|
23
|
+
<module name="RegexpMultiline">
|
24
|
+
<property name="format" value="\n\n\s*\}"/>
|
25
|
+
<property name="message" value="Blank line before closing brace"/>
|
26
|
+
</module>
|
27
|
+
<module name="RegexpMultiline">
|
28
|
+
<property name="format" value="\n\n\n"/>
|
29
|
+
<property name="message" value="Multiple consecutive blank lines"/>
|
30
|
+
</module>
|
31
|
+
<module name="RegexpMultiline">
|
32
|
+
<property name="format" value="\n\n\Z"/>
|
33
|
+
<property name="message" value="Blank line before end of file"/>
|
34
|
+
</module>
|
35
|
+
<module name="RegexpMultiline">
|
36
|
+
<property name="format" value="Preconditions\.checkNotNull"/>
|
37
|
+
<property name="message" value="Use of checkNotNull"/>
|
38
|
+
</module>
|
39
|
+
|
40
|
+
<module name="TreeWalker">
|
41
|
+
<module name="EmptyBlock">
|
42
|
+
<property name="option" value="text"/>
|
43
|
+
<property name="tokens" value="
|
44
|
+
LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_IF,
|
45
|
+
LITERAL_FOR, LITERAL_TRY, LITERAL_WHILE, INSTANCE_INIT, STATIC_INIT"/>
|
46
|
+
</module>
|
47
|
+
<module name="EmptyStatement"/>
|
48
|
+
<module name="EmptyForInitializerPad"/>
|
49
|
+
<module name="EmptyForIteratorPad">
|
50
|
+
<property name="option" value="space"/>
|
51
|
+
</module>
|
52
|
+
<module name="MethodParamPad">
|
53
|
+
<property name="allowLineBreaks" value="true"/>
|
54
|
+
<property name="option" value="nospace"/>
|
55
|
+
</module>
|
56
|
+
<module name="ParenPad"/>
|
57
|
+
<module name="TypecastParenPad"/>
|
58
|
+
<module name="NeedBraces"/>
|
59
|
+
<module name="LeftCurly">
|
60
|
+
<property name="option" value="nl"/>
|
61
|
+
<property name="tokens" value="CLASS_DEF, CTOR_DEF, INTERFACE_DEF, METHOD_DEF"/>
|
62
|
+
</module>
|
63
|
+
<module name="LeftCurly">
|
64
|
+
<property name="option" value="eol"/>
|
65
|
+
<property name="tokens" value="
|
66
|
+
LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_FOR,
|
67
|
+
LITERAL_IF, LITERAL_SWITCH, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE"/>
|
68
|
+
</module>
|
69
|
+
<module name="RightCurly">
|
70
|
+
<property name="option" value="alone"/>
|
71
|
+
</module>
|
72
|
+
<module name="GenericWhitespace"/>
|
73
|
+
<module name="WhitespaceAfter"/>
|
74
|
+
<module name="NoWhitespaceBefore"/>
|
75
|
+
|
76
|
+
<module name="UpperEll"/>
|
77
|
+
<module name="DefaultComesLast"/>
|
78
|
+
<module name="ArrayTypeStyle"/>
|
79
|
+
<module name="MultipleVariableDeclarations"/>
|
80
|
+
<module name="ModifierOrder"/>
|
81
|
+
<module name="OneStatementPerLine"/>
|
82
|
+
<module name="StringLiteralEquality"/>
|
83
|
+
<module name="MutableException"/>
|
84
|
+
<module name="EqualsHashCode"/>
|
85
|
+
<module name="InnerAssignment"/>
|
86
|
+
<module name="InterfaceIsType"/>
|
87
|
+
<module name="HideUtilityClassConstructor"/>
|
88
|
+
|
89
|
+
<module name="MemberName"/>
|
90
|
+
<module name="LocalVariableName"/>
|
91
|
+
<module name="LocalFinalVariableName"/>
|
92
|
+
<module name="TypeName"/>
|
93
|
+
<module name="PackageName"/>
|
94
|
+
<module name="ParameterName"/>
|
95
|
+
<module name="StaticVariableName"/>
|
96
|
+
<module name="ClassTypeParameterName">
|
97
|
+
<property name="format" value="^[A-Z][0-9]?$"/>
|
98
|
+
</module>
|
99
|
+
<module name="MethodTypeParameterName">
|
100
|
+
<property name="format" value="^[A-Z][0-9]?$"/>
|
101
|
+
</module>
|
102
|
+
|
103
|
+
<module name="AvoidStarImport"/>
|
104
|
+
<module name="RedundantImport"/>
|
105
|
+
<module name="UnusedImports"/>
|
106
|
+
<module name="ImportOrder">
|
107
|
+
<property name="groups" value="*,javax,java"/>
|
108
|
+
<property name="separated" value="true"/>
|
109
|
+
<property name="option" value="bottom"/>
|
110
|
+
<property name="sortStaticImportsAlphabetically" value="true"/>
|
111
|
+
</module>
|
112
|
+
|
113
|
+
<module name="WhitespaceAround">
|
114
|
+
<property name="allowEmptyConstructors" value="true"/>
|
115
|
+
<property name="allowEmptyMethods" value="true"/>
|
116
|
+
<property name="ignoreEnhancedForColon" value="false"/>
|
117
|
+
<property name="tokens" value="
|
118
|
+
ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN,
|
119
|
+
BXOR, BXOR_ASSIGN, COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LE,
|
120
|
+
LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
|
121
|
+
LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN,
|
122
|
+
LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE,
|
123
|
+
LOR, LT, MINUS, MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL,
|
124
|
+
PLUS, PLUS_ASSIGN, QUESTION, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN,
|
125
|
+
STAR, STAR_ASSIGN, TYPE_EXTENSION_AND"/>
|
126
|
+
</module>
|
127
|
+
</module>
|
128
|
+
</module>
|
@@ -0,0 +1,108 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
+
<!DOCTYPE module PUBLIC
|
3
|
+
"-//Puppy Crawl//DTD Check Configuration 1.3//EN"
|
4
|
+
"http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
|
5
|
+
<!--
|
6
|
+
This is a subset of ./checkstyle.xml which allows some loose styles
|
7
|
+
-->
|
8
|
+
<module name="Checker">
|
9
|
+
<module name="FileTabCharacter"/>
|
10
|
+
<module name="NewlineAtEndOfFile">
|
11
|
+
<property name="lineSeparator" value="lf"/>
|
12
|
+
</module>
|
13
|
+
<module name="RegexpMultiline">
|
14
|
+
<property name="format" value="\r"/>
|
15
|
+
<property name="message" value="Line contains carriage return"/>
|
16
|
+
</module>
|
17
|
+
<module name="RegexpMultiline">
|
18
|
+
<property name="format" value=" \n"/>
|
19
|
+
<property name="message" value="Line has trailing whitespace"/>
|
20
|
+
</module>
|
21
|
+
<module name="RegexpMultiline">
|
22
|
+
<property name="format" value="\n\n\n"/>
|
23
|
+
<property name="message" value="Multiple consecutive blank lines"/>
|
24
|
+
</module>
|
25
|
+
<module name="RegexpMultiline">
|
26
|
+
<property name="format" value="\n\n\Z"/>
|
27
|
+
<property name="message" value="Blank line before end of file"/>
|
28
|
+
</module>
|
29
|
+
|
30
|
+
<module name="TreeWalker">
|
31
|
+
<module name="EmptyBlock">
|
32
|
+
<property name="option" value="text"/>
|
33
|
+
<property name="tokens" value="
|
34
|
+
LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_IF,
|
35
|
+
LITERAL_FOR, LITERAL_TRY, LITERAL_WHILE, INSTANCE_INIT, STATIC_INIT"/>
|
36
|
+
</module>
|
37
|
+
<module name="EmptyStatement"/>
|
38
|
+
<module name="EmptyForInitializerPad"/>
|
39
|
+
<module name="EmptyForIteratorPad">
|
40
|
+
<property name="option" value="space"/>
|
41
|
+
</module>
|
42
|
+
<module name="MethodParamPad">
|
43
|
+
<property name="allowLineBreaks" value="true"/>
|
44
|
+
<property name="option" value="nospace"/>
|
45
|
+
</module>
|
46
|
+
<module name="ParenPad"/>
|
47
|
+
<module name="TypecastParenPad"/>
|
48
|
+
<module name="NeedBraces"/>
|
49
|
+
<module name="LeftCurly">
|
50
|
+
<property name="option" value="nl"/>
|
51
|
+
<property name="tokens" value="CLASS_DEF, CTOR_DEF, INTERFACE_DEF, METHOD_DEF"/>
|
52
|
+
</module>
|
53
|
+
<module name="LeftCurly">
|
54
|
+
<property name="option" value="eol"/>
|
55
|
+
<property name="tokens" value="
|
56
|
+
LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE, LITERAL_FINALLY, LITERAL_FOR,
|
57
|
+
LITERAL_IF, LITERAL_SWITCH, LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE"/>
|
58
|
+
</module>
|
59
|
+
<module name="RightCurly">
|
60
|
+
<property name="option" value="alone"/>
|
61
|
+
</module>
|
62
|
+
<module name="GenericWhitespace"/>
|
63
|
+
<module name="WhitespaceAfter"/>
|
64
|
+
<module name="NoWhitespaceBefore"/>
|
65
|
+
|
66
|
+
<module name="UpperEll"/>
|
67
|
+
<module name="DefaultComesLast"/>
|
68
|
+
<module name="ArrayTypeStyle"/>
|
69
|
+
<module name="MultipleVariableDeclarations"/>
|
70
|
+
<module name="ModifierOrder"/>
|
71
|
+
<module name="OneStatementPerLine"/>
|
72
|
+
<module name="StringLiteralEquality"/>
|
73
|
+
<module name="MutableException"/>
|
74
|
+
<module name="EqualsHashCode"/>
|
75
|
+
<module name="InnerAssignment"/>
|
76
|
+
<module name="InterfaceIsType"/>
|
77
|
+
<module name="HideUtilityClassConstructor"/>
|
78
|
+
|
79
|
+
<module name="MemberName"/>
|
80
|
+
<module name="LocalVariableName"/>
|
81
|
+
<module name="LocalFinalVariableName"/>
|
82
|
+
<module name="TypeName"/>
|
83
|
+
<module name="PackageName"/>
|
84
|
+
<module name="ParameterName"/>
|
85
|
+
<module name="StaticVariableName"/>
|
86
|
+
<module name="ClassTypeParameterName">
|
87
|
+
<property name="format" value="^[A-Z][0-9]?$"/>
|
88
|
+
</module>
|
89
|
+
<module name="MethodTypeParameterName">
|
90
|
+
<property name="format" value="^[A-Z][0-9]?$"/>
|
91
|
+
</module>
|
92
|
+
|
93
|
+
<module name="WhitespaceAround">
|
94
|
+
<property name="allowEmptyConstructors" value="true"/>
|
95
|
+
<property name="allowEmptyMethods" value="true"/>
|
96
|
+
<property name="ignoreEnhancedForColon" value="false"/>
|
97
|
+
<property name="tokens" value="
|
98
|
+
ASSIGN, BAND, BAND_ASSIGN, BOR, BOR_ASSIGN, BSR, BSR_ASSIGN,
|
99
|
+
BXOR, BXOR_ASSIGN, COLON, DIV, DIV_ASSIGN, EQUAL, GE, GT, LAND, LE,
|
100
|
+
LITERAL_ASSERT, LITERAL_CATCH, LITERAL_DO, LITERAL_ELSE,
|
101
|
+
LITERAL_FINALLY, LITERAL_FOR, LITERAL_IF, LITERAL_RETURN,
|
102
|
+
LITERAL_SYNCHRONIZED, LITERAL_TRY, LITERAL_WHILE,
|
103
|
+
LOR, LT, MINUS, MINUS_ASSIGN, MOD, MOD_ASSIGN, NOT_EQUAL,
|
104
|
+
PLUS, PLUS_ASSIGN, QUESTION, SL, SLIST, SL_ASSIGN, SR, SR_ASSIGN,
|
105
|
+
STAR, STAR_ASSIGN, TYPE_EXTENSION_AND"/>
|
106
|
+
</module>
|
107
|
+
</module>
|
108
|
+
</module>
|
Binary file
|
data/gradlew
ADDED
@@ -0,0 +1,160 @@
|
|
1
|
+
#!/usr/bin/env bash
|
2
|
+
|
3
|
+
##############################################################################
|
4
|
+
##
|
5
|
+
## Gradle start up script for UN*X
|
6
|
+
##
|
7
|
+
##############################################################################
|
8
|
+
|
9
|
+
# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
|
10
|
+
DEFAULT_JVM_OPTS=""
|
11
|
+
|
12
|
+
APP_NAME="Gradle"
|
13
|
+
APP_BASE_NAME=`basename "$0"`
|
14
|
+
|
15
|
+
# Use the maximum available, or set MAX_FD != -1 to use that value.
|
16
|
+
MAX_FD="maximum"
|
17
|
+
|
18
|
+
warn ( ) {
|
19
|
+
echo "$*"
|
20
|
+
}
|
21
|
+
|
22
|
+
die ( ) {
|
23
|
+
echo
|
24
|
+
echo "$*"
|
25
|
+
echo
|
26
|
+
exit 1
|
27
|
+
}
|
28
|
+
|
29
|
+
# OS specific support (must be 'true' or 'false').
|
30
|
+
cygwin=false
|
31
|
+
msys=false
|
32
|
+
darwin=false
|
33
|
+
case "`uname`" in
|
34
|
+
CYGWIN* )
|
35
|
+
cygwin=true
|
36
|
+
;;
|
37
|
+
Darwin* )
|
38
|
+
darwin=true
|
39
|
+
;;
|
40
|
+
MINGW* )
|
41
|
+
msys=true
|
42
|
+
;;
|
43
|
+
esac
|
44
|
+
|
45
|
+
# Attempt to set APP_HOME
|
46
|
+
# Resolve links: $0 may be a link
|
47
|
+
PRG="$0"
|
48
|
+
# Need this for relative symlinks.
|
49
|
+
while [ -h "$PRG" ] ; do
|
50
|
+
ls=`ls -ld "$PRG"`
|
51
|
+
link=`expr "$ls" : '.*-> \(.*\)$'`
|
52
|
+
if expr "$link" : '/.*' > /dev/null; then
|
53
|
+
PRG="$link"
|
54
|
+
else
|
55
|
+
PRG=`dirname "$PRG"`"/$link"
|
56
|
+
fi
|
57
|
+
done
|
58
|
+
SAVED="`pwd`"
|
59
|
+
cd "`dirname \"$PRG\"`/" >/dev/null
|
60
|
+
APP_HOME="`pwd -P`"
|
61
|
+
cd "$SAVED" >/dev/null
|
62
|
+
|
63
|
+
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
|
64
|
+
|
65
|
+
# Determine the Java command to use to start the JVM.
|
66
|
+
if [ -n "$JAVA_HOME" ] ; then
|
67
|
+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
|
68
|
+
# IBM's JDK on AIX uses strange locations for the executables
|
69
|
+
JAVACMD="$JAVA_HOME/jre/sh/java"
|
70
|
+
else
|
71
|
+
JAVACMD="$JAVA_HOME/bin/java"
|
72
|
+
fi
|
73
|
+
if [ ! -x "$JAVACMD" ] ; then
|
74
|
+
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
|
75
|
+
|
76
|
+
Please set the JAVA_HOME variable in your environment to match the
|
77
|
+
location of your Java installation."
|
78
|
+
fi
|
79
|
+
else
|
80
|
+
JAVACMD="java"
|
81
|
+
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
|
82
|
+
|
83
|
+
Please set the JAVA_HOME variable in your environment to match the
|
84
|
+
location of your Java installation."
|
85
|
+
fi
|
86
|
+
|
87
|
+
# Increase the maximum file descriptors if we can.
|
88
|
+
if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
|
89
|
+
MAX_FD_LIMIT=`ulimit -H -n`
|
90
|
+
if [ $? -eq 0 ] ; then
|
91
|
+
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
|
92
|
+
MAX_FD="$MAX_FD_LIMIT"
|
93
|
+
fi
|
94
|
+
ulimit -n $MAX_FD
|
95
|
+
if [ $? -ne 0 ] ; then
|
96
|
+
warn "Could not set maximum file descriptor limit: $MAX_FD"
|
97
|
+
fi
|
98
|
+
else
|
99
|
+
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
|
100
|
+
fi
|
101
|
+
fi
|
102
|
+
|
103
|
+
# For Darwin, add options to specify how the application appears in the dock
|
104
|
+
if $darwin; then
|
105
|
+
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
|
106
|
+
fi
|
107
|
+
|
108
|
+
# For Cygwin, switch paths to Windows format before running java
|
109
|
+
if $cygwin ; then
|
110
|
+
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
|
111
|
+
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
|
112
|
+
JAVACMD=`cygpath --unix "$JAVACMD"`
|
113
|
+
|
114
|
+
# We build the pattern for arguments to be converted via cygpath
|
115
|
+
ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
|
116
|
+
SEP=""
|
117
|
+
for dir in $ROOTDIRSRAW ; do
|
118
|
+
ROOTDIRS="$ROOTDIRS$SEP$dir"
|
119
|
+
SEP="|"
|
120
|
+
done
|
121
|
+
OURCYGPATTERN="(^($ROOTDIRS))"
|
122
|
+
# Add a user-defined pattern to the cygpath arguments
|
123
|
+
if [ "$GRADLE_CYGPATTERN" != "" ] ; then
|
124
|
+
OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
|
125
|
+
fi
|
126
|
+
# Now convert the arguments - kludge to limit ourselves to /bin/sh
|
127
|
+
i=0
|
128
|
+
for arg in "$@" ; do
|
129
|
+
CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
|
130
|
+
CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
|
131
|
+
|
132
|
+
if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
|
133
|
+
eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
|
134
|
+
else
|
135
|
+
eval `echo args$i`="\"$arg\""
|
136
|
+
fi
|
137
|
+
i=$((i+1))
|
138
|
+
done
|
139
|
+
case $i in
|
140
|
+
(0) set -- ;;
|
141
|
+
(1) set -- "$args0" ;;
|
142
|
+
(2) set -- "$args0" "$args1" ;;
|
143
|
+
(3) set -- "$args0" "$args1" "$args2" ;;
|
144
|
+
(4) set -- "$args0" "$args1" "$args2" "$args3" ;;
|
145
|
+
(5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
|
146
|
+
(6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
|
147
|
+
(7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
|
148
|
+
(8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
|
149
|
+
(9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
|
150
|
+
esac
|
151
|
+
fi
|
152
|
+
|
153
|
+
# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
|
154
|
+
function splitJvmOpts() {
|
155
|
+
JVM_OPTS=("$@")
|
156
|
+
}
|
157
|
+
eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
|
158
|
+
JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
|
159
|
+
|
160
|
+
exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"
|
data/gradlew.bat
ADDED
@@ -0,0 +1,90 @@
|
|
1
|
+
@if "%DEBUG%" == "" @echo off
|
2
|
+
@rem ##########################################################################
|
3
|
+
@rem
|
4
|
+
@rem Gradle startup script for Windows
|
5
|
+
@rem
|
6
|
+
@rem ##########################################################################
|
7
|
+
|
8
|
+
@rem Set local scope for the variables with windows NT shell
|
9
|
+
if "%OS%"=="Windows_NT" setlocal
|
10
|
+
|
11
|
+
@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
|
12
|
+
set DEFAULT_JVM_OPTS=
|
13
|
+
|
14
|
+
set DIRNAME=%~dp0
|
15
|
+
if "%DIRNAME%" == "" set DIRNAME=.
|
16
|
+
set APP_BASE_NAME=%~n0
|
17
|
+
set APP_HOME=%DIRNAME%
|
18
|
+
|
19
|
+
@rem Find java.exe
|
20
|
+
if defined JAVA_HOME goto findJavaFromJavaHome
|
21
|
+
|
22
|
+
set JAVA_EXE=java.exe
|
23
|
+
%JAVA_EXE% -version >NUL 2>&1
|
24
|
+
if "%ERRORLEVEL%" == "0" goto init
|
25
|
+
|
26
|
+
echo.
|
27
|
+
echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
|
28
|
+
echo.
|
29
|
+
echo Please set the JAVA_HOME variable in your environment to match the
|
30
|
+
echo location of your Java installation.
|
31
|
+
|
32
|
+
goto fail
|
33
|
+
|
34
|
+
:findJavaFromJavaHome
|
35
|
+
set JAVA_HOME=%JAVA_HOME:"=%
|
36
|
+
set JAVA_EXE=%JAVA_HOME%/bin/java.exe
|
37
|
+
|
38
|
+
if exist "%JAVA_EXE%" goto init
|
39
|
+
|
40
|
+
echo.
|
41
|
+
echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
|
42
|
+
echo.
|
43
|
+
echo Please set the JAVA_HOME variable in your environment to match the
|
44
|
+
echo location of your Java installation.
|
45
|
+
|
46
|
+
goto fail
|
47
|
+
|
48
|
+
:init
|
49
|
+
@rem Get command-line arguments, handling Windowz variants
|
50
|
+
|
51
|
+
if not "%OS%" == "Windows_NT" goto win9xME_args
|
52
|
+
if "%@eval[2+2]" == "4" goto 4NT_args
|
53
|
+
|
54
|
+
:win9xME_args
|
55
|
+
@rem Slurp the command line arguments.
|
56
|
+
set CMD_LINE_ARGS=
|
57
|
+
set _SKIP=2
|
58
|
+
|
59
|
+
:win9xME_args_slurp
|
60
|
+
if "x%~1" == "x" goto execute
|
61
|
+
|
62
|
+
set CMD_LINE_ARGS=%*
|
63
|
+
goto execute
|
64
|
+
|
65
|
+
:4NT_args
|
66
|
+
@rem Get arguments from the 4NT Shell from JP Software
|
67
|
+
set CMD_LINE_ARGS=%$
|
68
|
+
|
69
|
+
:execute
|
70
|
+
@rem Setup the command line
|
71
|
+
|
72
|
+
set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
|
73
|
+
|
74
|
+
@rem Execute Gradle
|
75
|
+
"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
|
76
|
+
|
77
|
+
:end
|
78
|
+
@rem End local scope for the variables with windows NT shell
|
79
|
+
if "%ERRORLEVEL%"=="0" goto mainEnd
|
80
|
+
|
81
|
+
:fail
|
82
|
+
rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
|
83
|
+
rem the _cmd.exe /c_ return code!
|
84
|
+
if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
|
85
|
+
exit /b 1
|
86
|
+
|
87
|
+
:mainEnd
|
88
|
+
if "%OS%"=="Windows_NT" endlocal
|
89
|
+
|
90
|
+
:omega
|
@@ -0,0 +1,80 @@
|
|
1
|
+
package org.embulk.filter.google_translate_api;
|
2
|
+
|
3
|
+
import java.util.List;
|
4
|
+
|
5
|
+
import org.embulk.config.Config;
|
6
|
+
import org.embulk.config.ConfigDefault;
|
7
|
+
import org.embulk.config.ConfigSource;
|
8
|
+
import org.embulk.config.Task;
|
9
|
+
import org.embulk.config.TaskSource;
|
10
|
+
import org.embulk.spi.Column;
|
11
|
+
import org.embulk.spi.FilterPlugin;
|
12
|
+
import org.embulk.spi.PageOutput;
|
13
|
+
import org.embulk.spi.Schema;
|
14
|
+
import org.embulk.spi.type.Types;
|
15
|
+
|
16
|
+
import com.google.common.base.Optional;
|
17
|
+
import com.google.common.collect.ImmutableList;
|
18
|
+
|
19
|
+
public class GoogleTranslateApiFilterPlugin implements FilterPlugin
|
20
|
+
{
|
21
|
+
public interface PluginTask extends Task
|
22
|
+
{
|
23
|
+
@Config("key_names")
|
24
|
+
public List<String> getKeyNames();
|
25
|
+
|
26
|
+
@Config("out_key_name_suffix")
|
27
|
+
public String getOutKeyNameSuffix();
|
28
|
+
|
29
|
+
@Config("source_lang")
|
30
|
+
@ConfigDefault("null")
|
31
|
+
public Optional<String> getSourceLang();
|
32
|
+
|
33
|
+
@Config("target_lang")
|
34
|
+
public String getTargetLang();
|
35
|
+
|
36
|
+
@Config("google_api_key")
|
37
|
+
@ConfigDefault("null")
|
38
|
+
public Optional<String> getGoogleApiKey();
|
39
|
+
|
40
|
+
@Config("sleep")
|
41
|
+
@ConfigDefault("0")
|
42
|
+
public Optional<Integer> getSleep();
|
43
|
+
}
|
44
|
+
|
45
|
+
@Override
|
46
|
+
public void transaction(ConfigSource config, Schema inputSchema,
|
47
|
+
FilterPlugin.Control control)
|
48
|
+
{
|
49
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
50
|
+
|
51
|
+
Schema outputSchema = buildOutputSchema(task, inputSchema);
|
52
|
+
|
53
|
+
control.run(task.dump(), outputSchema);
|
54
|
+
}
|
55
|
+
|
56
|
+
@Override
|
57
|
+
public PageOutput open(TaskSource taskSource, final Schema inputSchema, final Schema outputSchema, final PageOutput output)
|
58
|
+
{
|
59
|
+
return new GoogleTranslateApiPageOutput(taskSource, inputSchema, outputSchema, output);
|
60
|
+
}
|
61
|
+
|
62
|
+
/**
|
63
|
+
* @param task
|
64
|
+
* @param inputSchema
|
65
|
+
* @return
|
66
|
+
*/
|
67
|
+
private Schema buildOutputSchema(PluginTask task, Schema inputSchema) {
|
68
|
+
ImmutableList.Builder<Column> builder = ImmutableList.builder();
|
69
|
+
int i = 0;
|
70
|
+
for (Column inputColumn: inputSchema.getColumns()) {
|
71
|
+
Column outputColumn = new Column(i++, inputColumn.getName(), inputColumn.getType());
|
72
|
+
builder.add(outputColumn);
|
73
|
+
}
|
74
|
+
for (String keyName : task.getKeyNames()) {
|
75
|
+
builder.add(new Column(i++, keyName + task.getOutKeyNameSuffix(), Types.STRING));
|
76
|
+
}
|
77
|
+
Schema outputSchema = new Schema(builder.build());
|
78
|
+
return outputSchema;
|
79
|
+
}
|
80
|
+
}
|
@@ -0,0 +1,150 @@
|
|
1
|
+
package org.embulk.filter.google_translate_api;
|
2
|
+
|
3
|
+
import java.util.List;
|
4
|
+
|
5
|
+
import org.embulk.config.TaskSource;
|
6
|
+
import org.embulk.filter.google_translate_api.GoogleTranslateApiFilterPlugin.PluginTask;
|
7
|
+
import org.embulk.spi.Column;
|
8
|
+
import org.embulk.spi.Exec;
|
9
|
+
import org.embulk.spi.Page;
|
10
|
+
import org.embulk.spi.PageBuilder;
|
11
|
+
import org.embulk.spi.PageOutput;
|
12
|
+
import org.embulk.spi.PageReader;
|
13
|
+
import org.embulk.spi.Schema;
|
14
|
+
import org.embulk.spi.type.Types;
|
15
|
+
import org.slf4j.Logger;
|
16
|
+
|
17
|
+
import com.google.cloud.RetryParams;
|
18
|
+
import com.google.cloud.translate.Translate;
|
19
|
+
import com.google.cloud.translate.Translate.TranslateOption;
|
20
|
+
import com.google.cloud.translate.TranslateOptions;
|
21
|
+
import com.google.cloud.translate.TranslateOptions.Builder;
|
22
|
+
import com.google.cloud.translate.Translation;
|
23
|
+
import com.google.common.collect.Lists;
|
24
|
+
|
25
|
+
public class GoogleTranslateApiPageOutput implements PageOutput
|
26
|
+
{
|
27
|
+
private final PluginTask task;
|
28
|
+
private final Schema outputSchema;
|
29
|
+
private final List<Column> inputColumns;
|
30
|
+
private final List<Column> keyNameColumns;
|
31
|
+
private final PageReader reader;
|
32
|
+
private final PageBuilder builder;
|
33
|
+
private final Translate translate;
|
34
|
+
private final TranslateOption srcLang;
|
35
|
+
|
36
|
+
private static final Logger logger = Exec.getLogger(GoogleTranslateApiFilterPlugin.class);
|
37
|
+
|
38
|
+
public GoogleTranslateApiPageOutput(TaskSource taskSource, Schema inputSchema, Schema outputSchema, PageOutput output) {
|
39
|
+
this.task = taskSource.loadTask(PluginTask.class);
|
40
|
+
this.outputSchema = outputSchema;
|
41
|
+
this.inputColumns = inputSchema.getColumns();
|
42
|
+
this.reader = new PageReader(inputSchema);
|
43
|
+
this.builder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
|
44
|
+
this.keyNameColumns = Lists.newArrayList();
|
45
|
+
for (String keyName : task.getKeyNames()) {
|
46
|
+
this.keyNameColumns.add(outputSchema.lookupColumn(keyName));
|
47
|
+
}
|
48
|
+
this.translate = createTranslateService();
|
49
|
+
|
50
|
+
this.srcLang = task.getSourceLang().isPresent() ? TranslateOption.sourceLanguage(task.getSourceLang().get()) : null;
|
51
|
+
}
|
52
|
+
|
53
|
+
@Override
|
54
|
+
public void finish() {
|
55
|
+
builder.finish();
|
56
|
+
}
|
57
|
+
|
58
|
+
@Override
|
59
|
+
public void close() {
|
60
|
+
builder.close();
|
61
|
+
}
|
62
|
+
|
63
|
+
@Override
|
64
|
+
public void add(Page page) {
|
65
|
+
reader.setPage(page);
|
66
|
+
|
67
|
+
try {
|
68
|
+
while (reader.nextRecord()) {
|
69
|
+
List<String> sourceTexts = Lists.newArrayList();
|
70
|
+
for (Column keyNameColumn : keyNameColumns) {
|
71
|
+
String text = reader.isNull(keyNameColumn) ? "" : reader.getString(keyNameColumn);
|
72
|
+
logger.debug(text);
|
73
|
+
sourceTexts.add(text);
|
74
|
+
}
|
75
|
+
List<Translation> translations = translate(sourceTexts);
|
76
|
+
for (int i = 0; i < keyNameColumns.size(); i++) {
|
77
|
+
builder.setString(outputSchema.lookupColumn(keyNameColumns.get(i).getName() + task.getOutKeyNameSuffix()), translations.get(i).getTranslatedText());
|
78
|
+
}
|
79
|
+
setValue(builder);
|
80
|
+
builder.addRecord();
|
81
|
+
Thread.sleep(task.getSleep().get());
|
82
|
+
}
|
83
|
+
} catch (Exception e) {
|
84
|
+
throw new RuntimeException(e);
|
85
|
+
}
|
86
|
+
}
|
87
|
+
|
88
|
+
/**
|
89
|
+
* @param texts
|
90
|
+
* @return
|
91
|
+
*/
|
92
|
+
private List<Translation> translate(List<String> texts) {
|
93
|
+
return (srcLang == null) ? translate.translate(texts) : translate.translate(texts, srcLang);
|
94
|
+
}
|
95
|
+
|
96
|
+
/**
|
97
|
+
* @param builder
|
98
|
+
*/
|
99
|
+
private void setValue(PageBuilder builder) {
|
100
|
+
for (Column inputColumn: inputColumns) {
|
101
|
+
if (reader.isNull(inputColumn)) {
|
102
|
+
builder.setNull(inputColumn);
|
103
|
+
continue;
|
104
|
+
}
|
105
|
+
if (Types.STRING.equals(inputColumn.getType())) {
|
106
|
+
builder.setString(inputColumn, reader.getString(inputColumn));
|
107
|
+
} else if (Types.BOOLEAN.equals(inputColumn.getType())) {
|
108
|
+
builder.setBoolean(inputColumn, reader.getBoolean(inputColumn));
|
109
|
+
} else if (Types.DOUBLE.equals(inputColumn.getType())) {
|
110
|
+
builder.setDouble(inputColumn, reader.getDouble(inputColumn));
|
111
|
+
} else if (Types.LONG.equals(inputColumn.getType())) {
|
112
|
+
builder.setLong(inputColumn, reader.getLong(inputColumn));
|
113
|
+
} else if (Types.TIMESTAMP.equals(inputColumn.getType())) {
|
114
|
+
builder.setTimestamp(inputColumn, reader.getTimestamp(inputColumn));
|
115
|
+
} else if (Types.JSON.equals(inputColumn.getType())) {
|
116
|
+
builder.setJson(inputColumn, reader.getJson(inputColumn));
|
117
|
+
}
|
118
|
+
}
|
119
|
+
}
|
120
|
+
|
121
|
+
/**
|
122
|
+
* @return
|
123
|
+
*/
|
124
|
+
private Translate createTranslateService() {
|
125
|
+
Builder builder = TranslateOptions.newBuilder()
|
126
|
+
.setRetryParams(retryParams())
|
127
|
+
.setConnectTimeout(60000)
|
128
|
+
.setReadTimeout(60000)
|
129
|
+
.setTargetLanguage(task.getTargetLang());
|
130
|
+
|
131
|
+
if (task.getGoogleApiKey().isPresent()) {
|
132
|
+
builder.setApiKey(task.getGoogleApiKey().get());
|
133
|
+
}
|
134
|
+
|
135
|
+
TranslateOptions translateOptions = builder.build();
|
136
|
+
return translateOptions.getService();
|
137
|
+
}
|
138
|
+
|
139
|
+
/**
|
140
|
+
* @return
|
141
|
+
*/
|
142
|
+
private RetryParams retryParams() {
|
143
|
+
return RetryParams.newBuilder()
|
144
|
+
.setRetryMaxAttempts(3)
|
145
|
+
.setMaxRetryDelayMillis(30000)
|
146
|
+
.setTotalRetryPeriodMillis(120000)
|
147
|
+
.setInitialRetryDelayMillis(250)
|
148
|
+
.build();
|
149
|
+
}
|
150
|
+
}
|
metadata
ADDED
@@ -0,0 +1,126 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-filter-google_translate_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: 2016-12-28 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: '1.0'
|
19
|
+
name: bundler
|
20
|
+
prerelease: false
|
21
|
+
type: :development
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
requirement: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '10.0'
|
33
|
+
name: rake
|
34
|
+
prerelease: false
|
35
|
+
type: :development
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
description: Google Translate Api filter plugin for Embulk
|
42
|
+
email:
|
43
|
+
- toyama0919@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- .gitignore
|
49
|
+
- LICENSE.txt
|
50
|
+
- README.md
|
51
|
+
- build.gradle
|
52
|
+
- config/checkstyle/checkstyle.xml
|
53
|
+
- config/checkstyle/default.xml
|
54
|
+
- gradle/wrapper/gradle-wrapper.jar
|
55
|
+
- gradle/wrapper/gradle-wrapper.properties
|
56
|
+
- gradlew
|
57
|
+
- gradlew.bat
|
58
|
+
- lib/embulk/filter/google_translate_api.rb
|
59
|
+
- src/main/java/org/embulk/filter/google_translate_api/GoogleTranslateApiFilterPlugin.java
|
60
|
+
- src/main/java/org/embulk/filter/google_translate_api/GoogleTranslateApiPageOutput.java
|
61
|
+
- src/test/java/org/embulk/filter/google_translate_api/TestGoogleTranslateApiFilterPlugin.java
|
62
|
+
- classpath/api-common-0.0.2.jar
|
63
|
+
- classpath/auto-value-1.2.jar
|
64
|
+
- classpath/commons-codec-1.3.jar
|
65
|
+
- classpath/commons-logging-1.1.1.jar
|
66
|
+
- classpath/embulk-filter-google_translate_api-0.1.0.jar
|
67
|
+
- classpath/gax-0.0.25.jar
|
68
|
+
- classpath/google-api-client-1.21.0.jar
|
69
|
+
- classpath/google-api-client-appengine-1.21.0.jar
|
70
|
+
- classpath/google-api-client-servlet-1.21.0.jar
|
71
|
+
- classpath/google-api-services-translate-v2-rev47-1.22.0.jar
|
72
|
+
- classpath/google-auth-library-credentials-0.6.0.jar
|
73
|
+
- classpath/google-auth-library-oauth2-http-0.6.0.jar
|
74
|
+
- classpath/google-cloud-core-0.8.0.jar
|
75
|
+
- classpath/google-cloud-translate-0.8.0.jar
|
76
|
+
- classpath/google-http-client-1.21.0.jar
|
77
|
+
- classpath/google-http-client-appengine-1.21.0.jar
|
78
|
+
- classpath/google-http-client-jackson-1.21.0.jar
|
79
|
+
- classpath/google-http-client-jackson2-1.21.0.jar
|
80
|
+
- classpath/google-http-client-jdo-1.21.0.jar
|
81
|
+
- classpath/google-oauth-client-1.21.0.jar
|
82
|
+
- classpath/google-oauth-client-appengine-1.21.0.jar
|
83
|
+
- classpath/google-oauth-client-servlet-1.21.0.jar
|
84
|
+
- classpath/grpc-context-1.0.1.jar
|
85
|
+
- classpath/grpc-core-1.0.1.jar
|
86
|
+
- classpath/grpc-google-common-protos-0.1.3.jar
|
87
|
+
- classpath/grpc-google-iam-v1-0.1.3.jar
|
88
|
+
- classpath/grpc-protobuf-1.0.1.jar
|
89
|
+
- classpath/grpc-protobuf-lite-1.0.1.jar
|
90
|
+
- classpath/gson-2.3.jar
|
91
|
+
- classpath/guava-19.0.jar
|
92
|
+
- classpath/httpclient-4.0.1.jar
|
93
|
+
- classpath/httpcore-4.0.1.jar
|
94
|
+
- classpath/jackson-core-asl-1.9.11.jar
|
95
|
+
- classpath/jdo2-api-2.3-eb.jar
|
96
|
+
- classpath/json-20151123.jar
|
97
|
+
- classpath/jsr305-3.0.0.jar
|
98
|
+
- classpath/protobuf-java-3.0.0.jar
|
99
|
+
- classpath/protobuf-java-util-3.0.0.jar
|
100
|
+
- classpath/servlet-api-2.5.jar
|
101
|
+
- classpath/transaction-api-1.1.jar
|
102
|
+
homepage:
|
103
|
+
licenses:
|
104
|
+
- MIT
|
105
|
+
metadata: {}
|
106
|
+
post_install_message:
|
107
|
+
rdoc_options: []
|
108
|
+
require_paths:
|
109
|
+
- lib
|
110
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
111
|
+
requirements:
|
112
|
+
- - '>='
|
113
|
+
- !ruby/object:Gem::Version
|
114
|
+
version: '0'
|
115
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
116
|
+
requirements:
|
117
|
+
- - '>='
|
118
|
+
- !ruby/object:Gem::Version
|
119
|
+
version: '0'
|
120
|
+
requirements: []
|
121
|
+
rubyforge_project:
|
122
|
+
rubygems_version: 2.1.9
|
123
|
+
signing_key:
|
124
|
+
specification_version: 4
|
125
|
+
summary: Google Translate Api filter plugin for Embulk
|
126
|
+
test_files: []
|