embulk-filter-convert_unicode_sequence_to_string 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.
- checksums.yaml +7 -0
- data/.gitignore +12 -0
- data/LICENSE.txt +21 -0
- data/README.md +44 -0
- data/build.gradle +98 -0
- data/config/checkstyle/checkstyle.xml +128 -0
- data/config/checkstyle/default.xml +108 -0
- data/embulk-example/csv/sample.csv +4 -0
- data/embulk-example/seed.yml +18 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +5 -0
- data/gradlew +172 -0
- data/gradlew.bat +84 -0
- data/lib/embulk/filter/convert_unicode_sequence_to_string.rb +3 -0
- data/src/main/java/org/embulk/filter/convert_unicode_sequence_to_string/ConvertUnicodeSequenceToStringFilterPlugin.java +211 -0
- data/src/test/java/org/embulk/filter/convert_unicode_sequence_to_string/TestConvertUnicodeSequenceToStringFilterPlugin.java +5 -0
- metadata +88 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: d3ddd50d18ae0d1001c98f4af3decf4588902d7d
|
|
4
|
+
data.tar.gz: efafc078d2d0f61abbdec691491e105795588db8
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 65d808ee09228e4440f31dd0e37ae7f376f20655cfa1976733fc7bc842442aa27b1c51b080c8cce5d31db6fbf669deb825aa54c64abb831d60256ca994ca917b
|
|
7
|
+
data.tar.gz: 49fb1cd0b9e7263ce3d88282a752f4702b07c1b4493a5f9ca0176da20237c0835e4cf888d95e7ad0160425be14b070330da518fb2e16c2186f6ff6b1a5397e4c
|
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 +1,44 @@
|
|
|
1
|
+
# Convert Unicode Sequence To String filter plugin for Embulk
|
|
2
|
+
|
|
3
|
+
TODO: Write short description here and build.gradle file.
|
|
4
|
+
|
|
5
|
+
## Overview
|
|
6
|
+
|
|
7
|
+
* **Plugin type**: filter
|
|
8
|
+
|
|
9
|
+
## Configuration
|
|
10
|
+
|
|
11
|
+
- **target_columns**: columns to convert (array of string)
|
|
12
|
+
|
|
13
|
+
## Example
|
|
14
|
+
|
|
15
|
+
Say input.csv is as follows:
|
|
16
|
+
```csv
|
|
17
|
+
id,name
|
|
18
|
+
0,hoge\u0000
|
|
19
|
+
1,fuga\u0041
|
|
20
|
+
2,normal_string
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
```yaml
|
|
24
|
+
filters:
|
|
25
|
+
- type: convert_unicode_sequence_to_string
|
|
26
|
+
target_columns:
|
|
27
|
+
- name
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
converts unicode escape sequence like below:
|
|
31
|
+
|
|
32
|
+
```csv
|
|
33
|
+
id,name
|
|
34
|
+
0,hoge
|
|
35
|
+
1,fugaA
|
|
36
|
+
2,normal_string
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
## Build
|
|
41
|
+
|
|
42
|
+
```
|
|
43
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
|
44
|
+
```
|
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 "1.5.0"
|
|
4
|
+
id "java"
|
|
5
|
+
id "checkstyle"
|
|
6
|
+
}
|
|
7
|
+
import com.github.jrubygradle.JRubyExec
|
|
8
|
+
repositories {
|
|
9
|
+
mavenCentral()
|
|
10
|
+
jcenter()
|
|
11
|
+
}
|
|
12
|
+
configurations {
|
|
13
|
+
provided
|
|
14
|
+
}
|
|
15
|
+
|
|
16
|
+
version = "0.1.0"
|
|
17
|
+
|
|
18
|
+
sourceCompatibility = 1.8
|
|
19
|
+
targetCompatibility = 1.8
|
|
20
|
+
|
|
21
|
+
dependencies {
|
|
22
|
+
compile "org.embulk:embulk-core:0.9.23"
|
|
23
|
+
provided "org.embulk:embulk-core:0.9.23"
|
|
24
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
|
25
|
+
testCompile "junit:junit:4.+"
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
|
29
|
+
doFirst { file("classpath").deleteDir() }
|
|
30
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
|
31
|
+
into "classpath"
|
|
32
|
+
}
|
|
33
|
+
clean { delete "classpath" }
|
|
34
|
+
|
|
35
|
+
checkstyle {
|
|
36
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
|
37
|
+
toolVersion = '6.14.1'
|
|
38
|
+
}
|
|
39
|
+
checkstyleMain {
|
|
40
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
41
|
+
ignoreFailures = true
|
|
42
|
+
}
|
|
43
|
+
checkstyleTest {
|
|
44
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
45
|
+
ignoreFailures = true
|
|
46
|
+
}
|
|
47
|
+
task checkstyle(type: Checkstyle) {
|
|
48
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
|
49
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
|
50
|
+
}
|
|
51
|
+
|
|
52
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
|
53
|
+
jrubyArgs "-S"
|
|
54
|
+
script "gem"
|
|
55
|
+
scriptArgs "build", "${project.name}.gemspec"
|
|
56
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
|
60
|
+
jrubyArgs "-S"
|
|
61
|
+
script "gem"
|
|
62
|
+
scriptArgs "push", "pkg/${project.name}-${project.version}.gem"
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) {
|
|
66
|
+
doLast {
|
|
67
|
+
println "> Build succeeded."
|
|
68
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
|
69
|
+
}
|
|
70
|
+
}
|
|
71
|
+
|
|
72
|
+
task gemspec {
|
|
73
|
+
ext.gemspecFile = file("${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 = "${project.version}"
|
|
80
|
+
spec.authors = ["reizist"]
|
|
81
|
+
spec.summary = %[Convert Unicode Sequence To String filter plugin for Embulk]
|
|
82
|
+
spec.description = %[Convert Unicode Sequence To String]
|
|
83
|
+
spec.email = ["reizist@gmail.com"]
|
|
84
|
+
spec.licenses = ["MIT"]
|
|
85
|
+
# TODO set this: spec.homepage = "https://github.com/reizist/embulk-filter-convert_unicode_sequence_to_string"
|
|
86
|
+
|
|
87
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
|
88
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
|
89
|
+
spec.require_paths = ["lib"]
|
|
90
|
+
|
|
91
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
|
92
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
|
93
|
+
spec.add_development_dependency 'rake', ['~> 12.0']
|
|
94
|
+
end
|
|
95
|
+
/$)
|
|
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>
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
in:
|
|
2
|
+
type: file
|
|
3
|
+
path_prefix: '/Users/reizist/go/src/github.com/reizist/embulk-filter-convert_unicode_sequence_to_string/embulk-example/csv/sample.csv'
|
|
4
|
+
parser:
|
|
5
|
+
charset: UTF-8
|
|
6
|
+
newline: CRLF
|
|
7
|
+
type: csv
|
|
8
|
+
delimiter: ','
|
|
9
|
+
skip_header_lines: 0
|
|
10
|
+
columns:
|
|
11
|
+
- {name: id, type: string}
|
|
12
|
+
- {name: name, type: string}
|
|
13
|
+
filters:
|
|
14
|
+
- type: convert_unicode_sequence_to_string
|
|
15
|
+
target_columns:
|
|
16
|
+
- name
|
|
17
|
+
out:
|
|
18
|
+
type: stdout
|
|
Binary file
|
data/gradlew
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
1
|
+
#!/usr/bin/env sh
|
|
2
|
+
|
|
3
|
+
##############################################################################
|
|
4
|
+
##
|
|
5
|
+
## Gradle start up script for UN*X
|
|
6
|
+
##
|
|
7
|
+
##############################################################################
|
|
8
|
+
|
|
9
|
+
# Attempt to set APP_HOME
|
|
10
|
+
# Resolve links: $0 may be a link
|
|
11
|
+
PRG="$0"
|
|
12
|
+
# Need this for relative symlinks.
|
|
13
|
+
while [ -h "$PRG" ] ; do
|
|
14
|
+
ls=`ls -ld "$PRG"`
|
|
15
|
+
link=`expr "$ls" : '.*-> \(.*\)$'`
|
|
16
|
+
if expr "$link" : '/.*' > /dev/null; then
|
|
17
|
+
PRG="$link"
|
|
18
|
+
else
|
|
19
|
+
PRG=`dirname "$PRG"`"/$link"
|
|
20
|
+
fi
|
|
21
|
+
done
|
|
22
|
+
SAVED="`pwd`"
|
|
23
|
+
cd "`dirname \"$PRG\"`/" >/dev/null
|
|
24
|
+
APP_HOME="`pwd -P`"
|
|
25
|
+
cd "$SAVED" >/dev/null
|
|
26
|
+
|
|
27
|
+
APP_NAME="Gradle"
|
|
28
|
+
APP_BASE_NAME=`basename "$0"`
|
|
29
|
+
|
|
30
|
+
# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
|
|
31
|
+
DEFAULT_JVM_OPTS=""
|
|
32
|
+
|
|
33
|
+
# Use the maximum available, or set MAX_FD != -1 to use that value.
|
|
34
|
+
MAX_FD="maximum"
|
|
35
|
+
|
|
36
|
+
warn () {
|
|
37
|
+
echo "$*"
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
die () {
|
|
41
|
+
echo
|
|
42
|
+
echo "$*"
|
|
43
|
+
echo
|
|
44
|
+
exit 1
|
|
45
|
+
}
|
|
46
|
+
|
|
47
|
+
# OS specific support (must be 'true' or 'false').
|
|
48
|
+
cygwin=false
|
|
49
|
+
msys=false
|
|
50
|
+
darwin=false
|
|
51
|
+
nonstop=false
|
|
52
|
+
case "`uname`" in
|
|
53
|
+
CYGWIN* )
|
|
54
|
+
cygwin=true
|
|
55
|
+
;;
|
|
56
|
+
Darwin* )
|
|
57
|
+
darwin=true
|
|
58
|
+
;;
|
|
59
|
+
MINGW* )
|
|
60
|
+
msys=true
|
|
61
|
+
;;
|
|
62
|
+
NONSTOP* )
|
|
63
|
+
nonstop=true
|
|
64
|
+
;;
|
|
65
|
+
esac
|
|
66
|
+
|
|
67
|
+
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
|
|
68
|
+
|
|
69
|
+
# Determine the Java command to use to start the JVM.
|
|
70
|
+
if [ -n "$JAVA_HOME" ] ; then
|
|
71
|
+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
|
|
72
|
+
# IBM's JDK on AIX uses strange locations for the executables
|
|
73
|
+
JAVACMD="$JAVA_HOME/jre/sh/java"
|
|
74
|
+
else
|
|
75
|
+
JAVACMD="$JAVA_HOME/bin/java"
|
|
76
|
+
fi
|
|
77
|
+
if [ ! -x "$JAVACMD" ] ; then
|
|
78
|
+
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
|
|
79
|
+
|
|
80
|
+
Please set the JAVA_HOME variable in your environment to match the
|
|
81
|
+
location of your Java installation."
|
|
82
|
+
fi
|
|
83
|
+
else
|
|
84
|
+
JAVACMD="java"
|
|
85
|
+
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
|
|
86
|
+
|
|
87
|
+
Please set the JAVA_HOME variable in your environment to match the
|
|
88
|
+
location of your Java installation."
|
|
89
|
+
fi
|
|
90
|
+
|
|
91
|
+
# Increase the maximum file descriptors if we can.
|
|
92
|
+
if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
|
|
93
|
+
MAX_FD_LIMIT=`ulimit -H -n`
|
|
94
|
+
if [ $? -eq 0 ] ; then
|
|
95
|
+
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
|
|
96
|
+
MAX_FD="$MAX_FD_LIMIT"
|
|
97
|
+
fi
|
|
98
|
+
ulimit -n $MAX_FD
|
|
99
|
+
if [ $? -ne 0 ] ; then
|
|
100
|
+
warn "Could not set maximum file descriptor limit: $MAX_FD"
|
|
101
|
+
fi
|
|
102
|
+
else
|
|
103
|
+
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
|
|
104
|
+
fi
|
|
105
|
+
fi
|
|
106
|
+
|
|
107
|
+
# For Darwin, add options to specify how the application appears in the dock
|
|
108
|
+
if $darwin; then
|
|
109
|
+
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
|
|
110
|
+
fi
|
|
111
|
+
|
|
112
|
+
# For Cygwin, switch paths to Windows format before running java
|
|
113
|
+
if $cygwin ; then
|
|
114
|
+
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
|
|
115
|
+
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
|
|
116
|
+
JAVACMD=`cygpath --unix "$JAVACMD"`
|
|
117
|
+
|
|
118
|
+
# We build the pattern for arguments to be converted via cygpath
|
|
119
|
+
ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
|
|
120
|
+
SEP=""
|
|
121
|
+
for dir in $ROOTDIRSRAW ; do
|
|
122
|
+
ROOTDIRS="$ROOTDIRS$SEP$dir"
|
|
123
|
+
SEP="|"
|
|
124
|
+
done
|
|
125
|
+
OURCYGPATTERN="(^($ROOTDIRS))"
|
|
126
|
+
# Add a user-defined pattern to the cygpath arguments
|
|
127
|
+
if [ "$GRADLE_CYGPATTERN" != "" ] ; then
|
|
128
|
+
OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
|
|
129
|
+
fi
|
|
130
|
+
# Now convert the arguments - kludge to limit ourselves to /bin/sh
|
|
131
|
+
i=0
|
|
132
|
+
for arg in "$@" ; do
|
|
133
|
+
CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
|
|
134
|
+
CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
|
|
135
|
+
|
|
136
|
+
if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
|
|
137
|
+
eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
|
|
138
|
+
else
|
|
139
|
+
eval `echo args$i`="\"$arg\""
|
|
140
|
+
fi
|
|
141
|
+
i=$((i+1))
|
|
142
|
+
done
|
|
143
|
+
case $i in
|
|
144
|
+
(0) set -- ;;
|
|
145
|
+
(1) set -- "$args0" ;;
|
|
146
|
+
(2) set -- "$args0" "$args1" ;;
|
|
147
|
+
(3) set -- "$args0" "$args1" "$args2" ;;
|
|
148
|
+
(4) set -- "$args0" "$args1" "$args2" "$args3" ;;
|
|
149
|
+
(5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
|
|
150
|
+
(6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
|
|
151
|
+
(7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
|
|
152
|
+
(8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
|
|
153
|
+
(9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
|
|
154
|
+
esac
|
|
155
|
+
fi
|
|
156
|
+
|
|
157
|
+
# Escape application args
|
|
158
|
+
save () {
|
|
159
|
+
for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
|
|
160
|
+
echo " "
|
|
161
|
+
}
|
|
162
|
+
APP_ARGS=$(save "$@")
|
|
163
|
+
|
|
164
|
+
# Collect all arguments for the java command, following the shell quoting and substitution rules
|
|
165
|
+
eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
|
|
166
|
+
|
|
167
|
+
# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
|
|
168
|
+
if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
|
|
169
|
+
cd "$(dirname "$0")"
|
|
170
|
+
fi
|
|
171
|
+
|
|
172
|
+
exec "$JAVACMD" "$@"
|
data/gradlew.bat
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
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
|
+
set DIRNAME=%~dp0
|
|
12
|
+
if "%DIRNAME%" == "" set DIRNAME=.
|
|
13
|
+
set APP_BASE_NAME=%~n0
|
|
14
|
+
set APP_HOME=%DIRNAME%
|
|
15
|
+
|
|
16
|
+
@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
|
|
17
|
+
set DEFAULT_JVM_OPTS=
|
|
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 Windows variants
|
|
50
|
+
|
|
51
|
+
if not "%OS%" == "Windows_NT" goto win9xME_args
|
|
52
|
+
|
|
53
|
+
:win9xME_args
|
|
54
|
+
@rem Slurp the command line arguments.
|
|
55
|
+
set CMD_LINE_ARGS=
|
|
56
|
+
set _SKIP=2
|
|
57
|
+
|
|
58
|
+
:win9xME_args_slurp
|
|
59
|
+
if "x%~1" == "x" goto execute
|
|
60
|
+
|
|
61
|
+
set CMD_LINE_ARGS=%*
|
|
62
|
+
|
|
63
|
+
:execute
|
|
64
|
+
@rem Setup the command line
|
|
65
|
+
|
|
66
|
+
set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
|
|
67
|
+
|
|
68
|
+
@rem Execute Gradle
|
|
69
|
+
"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
|
|
70
|
+
|
|
71
|
+
:end
|
|
72
|
+
@rem End local scope for the variables with windows NT shell
|
|
73
|
+
if "%ERRORLEVEL%"=="0" goto mainEnd
|
|
74
|
+
|
|
75
|
+
:fail
|
|
76
|
+
rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
|
|
77
|
+
rem the _cmd.exe /c_ return code!
|
|
78
|
+
if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
|
|
79
|
+
exit /b 1
|
|
80
|
+
|
|
81
|
+
:mainEnd
|
|
82
|
+
if "%OS%"=="Windows_NT" endlocal
|
|
83
|
+
|
|
84
|
+
:omega
|
|
@@ -0,0 +1,211 @@
|
|
|
1
|
+
package org.embulk.filter.convert_unicode_sequence_to_string;
|
|
2
|
+
|
|
3
|
+
import org.embulk.config.Config;
|
|
4
|
+
import org.embulk.config.ConfigDefault;
|
|
5
|
+
import org.embulk.config.ConfigException;
|
|
6
|
+
import org.embulk.config.ConfigSource;
|
|
7
|
+
import org.embulk.config.Task;
|
|
8
|
+
import org.embulk.config.TaskSource;
|
|
9
|
+
import org.embulk.spi.Column;
|
|
10
|
+
import org.embulk.spi.FilterPlugin;
|
|
11
|
+
import org.embulk.spi.PageOutput;
|
|
12
|
+
import org.embulk.spi.Schema;
|
|
13
|
+
import org.embulk.spi.Page;
|
|
14
|
+
import org.embulk.spi.PageReader;
|
|
15
|
+
import org.embulk.spi.PageBuilder;
|
|
16
|
+
import org.embulk.spi.Exec;
|
|
17
|
+
import org.embulk.spi.ColumnVisitor;
|
|
18
|
+
|
|
19
|
+
import java.util.List;
|
|
20
|
+
import java.io.BufferedReader;
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
public class ConvertUnicodeSequenceToStringFilterPlugin
|
|
24
|
+
implements FilterPlugin
|
|
25
|
+
{
|
|
26
|
+
public interface PluginTask
|
|
27
|
+
extends Task
|
|
28
|
+
{
|
|
29
|
+
// configuration option 1 (required integer)
|
|
30
|
+
@Config("target_columns")
|
|
31
|
+
@ConfigDefault("[]")
|
|
32
|
+
public List<String> getTargetColumns();
|
|
33
|
+
}
|
|
34
|
+
|
|
35
|
+
public class StringConverterVisitorImpl implements ColumnVisitor {
|
|
36
|
+
private final PluginTask task;
|
|
37
|
+
private final PageReader pageReader;
|
|
38
|
+
private final PageBuilder pageBuilder;
|
|
39
|
+
|
|
40
|
+
StringConverterVisitorImpl(PluginTask task, PageReader pageReader, PageBuilder pageBuilder)
|
|
41
|
+
{
|
|
42
|
+
this.task = task;
|
|
43
|
+
this.pageReader = pageReader;
|
|
44
|
+
this.pageBuilder = pageBuilder;
|
|
45
|
+
}
|
|
46
|
+
|
|
47
|
+
public boolean visitColumns(Schema inputSchema) {
|
|
48
|
+
return false;
|
|
49
|
+
}
|
|
50
|
+
|
|
51
|
+
@Override
|
|
52
|
+
public void booleanColumn(Column column)
|
|
53
|
+
{
|
|
54
|
+
if (pageReader.isNull(column)) {
|
|
55
|
+
pageBuilder.setNull(column);
|
|
56
|
+
}
|
|
57
|
+
else {
|
|
58
|
+
pageBuilder.setBoolean(column, pageReader.getBoolean(column));
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
|
|
62
|
+
@Override
|
|
63
|
+
public void longColumn(Column column)
|
|
64
|
+
{
|
|
65
|
+
if (pageReader.isNull(column)) {
|
|
66
|
+
pageBuilder.setNull(column);
|
|
67
|
+
}
|
|
68
|
+
else {
|
|
69
|
+
pageBuilder.setLong(column, pageReader.getLong(column));
|
|
70
|
+
}
|
|
71
|
+
}
|
|
72
|
+
|
|
73
|
+
@Override
|
|
74
|
+
public void doubleColumn(Column column)
|
|
75
|
+
{
|
|
76
|
+
if (pageReader.isNull(column)) {
|
|
77
|
+
pageBuilder.setNull(column);
|
|
78
|
+
}
|
|
79
|
+
else {
|
|
80
|
+
pageBuilder.setDouble(column, pageReader.getDouble(column));
|
|
81
|
+
}
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
@Override
|
|
85
|
+
public void stringColumn(Column column)
|
|
86
|
+
{
|
|
87
|
+
if (pageReader.isNull(column)) {
|
|
88
|
+
pageBuilder.setNull(column);
|
|
89
|
+
}
|
|
90
|
+
else {
|
|
91
|
+
for (String targetColumnName: task.getTargetColumns()) {
|
|
92
|
+
if (column.getName().equals(targetColumnName)) {
|
|
93
|
+
pageBuilder.setString(column, convert(pageReader.getString(column)));
|
|
94
|
+
} else {
|
|
95
|
+
pageBuilder.setString(column, pageReader.getString(column));
|
|
96
|
+
}
|
|
97
|
+
}
|
|
98
|
+
}
|
|
99
|
+
}
|
|
100
|
+
|
|
101
|
+
@Override
|
|
102
|
+
public void timestampColumn(Column column)
|
|
103
|
+
{
|
|
104
|
+
if (pageReader.isNull(column)) {
|
|
105
|
+
pageBuilder.setNull(column);
|
|
106
|
+
}
|
|
107
|
+
else {
|
|
108
|
+
pageBuilder.setTimestamp(column, pageReader.getTimestamp(column));
|
|
109
|
+
}
|
|
110
|
+
}
|
|
111
|
+
|
|
112
|
+
@Override
|
|
113
|
+
public void jsonColumn(Column column)
|
|
114
|
+
{
|
|
115
|
+
if (pageReader.isNull(column)) {
|
|
116
|
+
pageBuilder.setNull(column);
|
|
117
|
+
}
|
|
118
|
+
else {
|
|
119
|
+
pageBuilder.setJson(column, pageReader.getJson(column));
|
|
120
|
+
}
|
|
121
|
+
}
|
|
122
|
+
|
|
123
|
+
private String convert(String text) {
|
|
124
|
+
text = text.replace("\\","//");
|
|
125
|
+
String[] arr = text.split("//u");
|
|
126
|
+
String output = "";
|
|
127
|
+
for(int i = 0; i < arr.length; i++){
|
|
128
|
+
try {
|
|
129
|
+
int hexVal = Integer.parseInt(arr[i], 16);
|
|
130
|
+
output += Character.toString((char)hexVal);
|
|
131
|
+
} catch (NumberFormatException e) {
|
|
132
|
+
output += arr[i];
|
|
133
|
+
}
|
|
134
|
+
}
|
|
135
|
+
return output;
|
|
136
|
+
}
|
|
137
|
+
}
|
|
138
|
+
|
|
139
|
+
@Override
|
|
140
|
+
public void transaction(ConfigSource config, Schema inputSchema,
|
|
141
|
+
FilterPlugin.Control control)
|
|
142
|
+
{
|
|
143
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
|
144
|
+
|
|
145
|
+
configure(task);
|
|
146
|
+
|
|
147
|
+
Schema outputSchema = inputSchema;
|
|
148
|
+
|
|
149
|
+
control.run(task.dump(), outputSchema);
|
|
150
|
+
}
|
|
151
|
+
|
|
152
|
+
private void configure(PluginTask task)
|
|
153
|
+
{
|
|
154
|
+
if (task.getTargetColumns().size() < 1) {
|
|
155
|
+
throw new ConfigException("\"target_columns\" can be specified.");
|
|
156
|
+
}
|
|
157
|
+
}
|
|
158
|
+
|
|
159
|
+
@Override
|
|
160
|
+
public PageOutput open(TaskSource taskSource, Schema inputSchema,
|
|
161
|
+
Schema outputSchema, PageOutput output)
|
|
162
|
+
{
|
|
163
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
164
|
+
PageReader pageReader = new PageReader(inputSchema);
|
|
165
|
+
PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
|
|
166
|
+
StringConverterVisitorImpl visitor = new StringConverterVisitorImpl(task, pageReader, pageBuilder);
|
|
167
|
+
|
|
168
|
+
return new PageOutputImpl(task, pageReader, pageBuilder, outputSchema, visitor, inputSchema);
|
|
169
|
+
}
|
|
170
|
+
|
|
171
|
+
public static class PageOutputImpl implements PageOutput
|
|
172
|
+
{
|
|
173
|
+
private PluginTask task;
|
|
174
|
+
private PageReader pageReader;
|
|
175
|
+
private PageBuilder pageBuilder;
|
|
176
|
+
private Schema outputSchema;
|
|
177
|
+
private Schema inputSchema;
|
|
178
|
+
private StringConverterVisitorImpl visitor;
|
|
179
|
+
|
|
180
|
+
PageOutputImpl(PluginTask task, PageReader pageReader, PageBuilder pageBuilder, Schema outputSchema, StringConverterVisitorImpl visitor, Schema inputSchema)
|
|
181
|
+
{
|
|
182
|
+
this.task = task;
|
|
183
|
+
this.pageReader = pageReader;
|
|
184
|
+
this.pageBuilder = pageBuilder;
|
|
185
|
+
this.outputSchema = outputSchema;
|
|
186
|
+
this.visitor = visitor;
|
|
187
|
+
this.inputSchema = inputSchema;
|
|
188
|
+
}
|
|
189
|
+
|
|
190
|
+
|
|
191
|
+
@Override
|
|
192
|
+
public void finish() {
|
|
193
|
+
pageBuilder.finish();
|
|
194
|
+
}
|
|
195
|
+
|
|
196
|
+
@Override
|
|
197
|
+
public void close() {
|
|
198
|
+
pageBuilder.close();
|
|
199
|
+
}
|
|
200
|
+
|
|
201
|
+
@Override
|
|
202
|
+
public void add(Page page) {
|
|
203
|
+
pageReader.setPage(page);
|
|
204
|
+
|
|
205
|
+
while (pageReader.nextRecord()) {
|
|
206
|
+
outputSchema.visitColumns(visitor);
|
|
207
|
+
pageBuilder.addRecord();
|
|
208
|
+
}
|
|
209
|
+
}
|
|
210
|
+
};
|
|
211
|
+
}
|
metadata
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: embulk-filter-convert_unicode_sequence_to_string
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- reizist
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2020-04-23 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: '12.0'
|
|
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: '12.0'
|
|
41
|
+
description: Convert Unicode Sequence To String
|
|
42
|
+
email:
|
|
43
|
+
- reizist@gmail.com
|
|
44
|
+
executables: []
|
|
45
|
+
extensions: []
|
|
46
|
+
extra_rdoc_files: []
|
|
47
|
+
files:
|
|
48
|
+
- ".gitignore"
|
|
49
|
+
- LICENSE.txt
|
|
50
|
+
- README.md
|
|
51
|
+
- build.gradle
|
|
52
|
+
- classpath/embulk-filter-convert_unicode_sequence_to_string-0.1.0.jar
|
|
53
|
+
- config/checkstyle/checkstyle.xml
|
|
54
|
+
- config/checkstyle/default.xml
|
|
55
|
+
- embulk-example/csv/sample.csv
|
|
56
|
+
- embulk-example/seed.yml
|
|
57
|
+
- gradle/wrapper/gradle-wrapper.jar
|
|
58
|
+
- gradle/wrapper/gradle-wrapper.properties
|
|
59
|
+
- gradlew
|
|
60
|
+
- gradlew.bat
|
|
61
|
+
- lib/embulk/filter/convert_unicode_sequence_to_string.rb
|
|
62
|
+
- src/main/java/org/embulk/filter/convert_unicode_sequence_to_string/ConvertUnicodeSequenceToStringFilterPlugin.java
|
|
63
|
+
- src/test/java/org/embulk/filter/convert_unicode_sequence_to_string/TestConvertUnicodeSequenceToStringFilterPlugin.java
|
|
64
|
+
homepage:
|
|
65
|
+
licenses:
|
|
66
|
+
- MIT
|
|
67
|
+
metadata: {}
|
|
68
|
+
post_install_message:
|
|
69
|
+
rdoc_options: []
|
|
70
|
+
require_paths:
|
|
71
|
+
- lib
|
|
72
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
73
|
+
requirements:
|
|
74
|
+
- - ">="
|
|
75
|
+
- !ruby/object:Gem::Version
|
|
76
|
+
version: '0'
|
|
77
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
78
|
+
requirements:
|
|
79
|
+
- - ">="
|
|
80
|
+
- !ruby/object:Gem::Version
|
|
81
|
+
version: '0'
|
|
82
|
+
requirements: []
|
|
83
|
+
rubyforge_project:
|
|
84
|
+
rubygems_version: 2.6.8
|
|
85
|
+
signing_key:
|
|
86
|
+
specification_version: 4
|
|
87
|
+
summary: Convert Unicode Sequence To String filter plugin for Embulk
|
|
88
|
+
test_files: []
|