embulk-decoder-remove_nonstandard_utf8_bytes 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 +15 -0
- data/LICENSE.txt +21 -0
- data/README.md +27 -0
- data/build.gradle +98 -0
- data/config/checkstyle/checkstyle.xml +128 -0
- data/config/checkstyle/default.xml +108 -0
- data/example.yml +11 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +169 -0
- data/gradlew.bat +84 -0
- data/lib/embulk/decoder/remove_nonstandard_utf8_bytes.rb +3 -0
- data/src/main/java/org/embulk/decoder/remove_nonstandard_utf8_bytes/IgnoreMalformedUTF8InputStream.java +28 -0
- data/src/main/java/org/embulk/decoder/remove_nonstandard_utf8_bytes/RemoveNonstandardUtf8BytesDecoderPlugin.java +73 -0
- data/src/test/java/org/embulk/decoder/remove_nonstandard_utf8_bytes/IgnoreMalformedUTF8InputStreamTest.java +42 -0
- metadata +88 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: c65e313f89eb2a1719e220afc4c2af649fe76dc3
|
|
4
|
+
data.tar.gz: a6b44f615755571da33b9e621f16b92d9390ee58
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 8b545c6158cd639a8baf05fe6909af4bb8a6abbcb780f4e9033bb412a4ba6e6fc62c0adfc0736a5adf268306aee91f5f56a7d2bc2e46cfb6cbfe5cd13293e295
|
|
7
|
+
data.tar.gz: 052984ce6f755670f24980b18474ccd55eff5f8a643aff8d6b826e7c36b383a29a9f14bab6e99a4cdc2326a9052be0e54eb637d2b0d550a9dfeeab5c6a247f79
|
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 +1,27 @@
|
|
|
1
|
+
# Remove nonstandard UTF-8 Bytes decoder plugin for Embulk.
|
|
2
|
+
|
|
3
|
+
Remove broken encoding of UTF-8 plugin for the Embulk.
|
|
4
|
+
|
|
5
|
+
- Ignoring malformed input.
|
|
6
|
+
- Ignoring unmappable character.
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
## Overview
|
|
10
|
+
|
|
11
|
+
* **Plugin type**: decoder
|
|
12
|
+
* **Guess supported**: no
|
|
13
|
+
|
|
14
|
+
## Example
|
|
15
|
+
|
|
16
|
+
```yaml
|
|
17
|
+
in:
|
|
18
|
+
type: any output input plugin type
|
|
19
|
+
decoders:
|
|
20
|
+
- type: remove_nonstandard_utf8_bytes
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
## Build
|
|
24
|
+
|
|
25
|
+
```
|
|
26
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
|
27
|
+
```
|
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
|
+
}
|
|
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:0.8.22"
|
|
24
|
+
compile "com.google.guava:guava:18.0"
|
|
25
|
+
provided "org.embulk:embulk-core:0.8.22"
|
|
26
|
+
testCompile "junit:junit:4.+"
|
|
27
|
+
testCompile "org.embulk:embulk-core:0.8.+:tests"
|
|
28
|
+
}
|
|
29
|
+
|
|
30
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
|
31
|
+
doFirst { file("classpath").deleteDir() }
|
|
32
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
|
33
|
+
into "classpath"
|
|
34
|
+
}
|
|
35
|
+
clean { delete "classpath" }
|
|
36
|
+
|
|
37
|
+
checkstyle {
|
|
38
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
|
39
|
+
toolVersion = '6.14.1'
|
|
40
|
+
}
|
|
41
|
+
checkstyleMain {
|
|
42
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
43
|
+
ignoreFailures = true
|
|
44
|
+
}
|
|
45
|
+
checkstyleTest {
|
|
46
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
47
|
+
ignoreFailures = true
|
|
48
|
+
}
|
|
49
|
+
task checkstyle(type: Checkstyle) {
|
|
50
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
|
51
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
|
52
|
+
}
|
|
53
|
+
|
|
54
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
|
55
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
|
56
|
+
script "${project.name}.gemspec"
|
|
57
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
|
58
|
+
}
|
|
59
|
+
|
|
60
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
|
61
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
|
62
|
+
script "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 = "${project.version}"
|
|
80
|
+
spec.authors = ["smdmts"]
|
|
81
|
+
spec.summary = %[Remove Nonstandard Utf8 Bytes decoder plugin for Embulk]
|
|
82
|
+
spec.description = %[Decodes Remove Nonstandard Utf8 Bytes-encoded files read by other file input plugins.]
|
|
83
|
+
spec.email = ["smdmts@every.tv"]
|
|
84
|
+
spec.licenses = ["MIT"]
|
|
85
|
+
spec.homepage = "https://github.com/smdmts/embulk-decoder-remove_nonstandard_utf8_bytes"
|
|
86
|
+
|
|
87
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
|
88
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
|
89
|
+
spec.require_paths = ["lib"]
|
|
90
|
+
|
|
91
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
|
92
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
|
93
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
|
94
|
+
end
|
|
95
|
+
/$)
|
|
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>
|
data/example.yml
ADDED
|
Binary file
|
data/gradlew
ADDED
|
@@ -0,0 +1,169 @@
|
|
|
1
|
+
#!/usr/bin/env bash
|
|
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
|
+
# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
|
|
158
|
+
function splitJvmOpts() {
|
|
159
|
+
JVM_OPTS=("$@")
|
|
160
|
+
}
|
|
161
|
+
eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
|
|
162
|
+
JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
|
|
163
|
+
|
|
164
|
+
# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
|
|
165
|
+
if [[ "$(uname)" == "Darwin" ]] && [[ "$HOME" == "$PWD" ]]; then
|
|
166
|
+
cd "$(dirname "$0")"
|
|
167
|
+
fi
|
|
168
|
+
|
|
169
|
+
exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"
|
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 +1,28 @@
|
|
|
1
|
+
package org.embulk.decoder.remove_nonstandard_utf8_bytes;
|
|
2
|
+
|
|
3
|
+
import com.google.common.base.Charsets;
|
|
4
|
+
import com.google.common.io.CharStreams;
|
|
5
|
+
|
|
6
|
+
import java.io.BufferedReader;
|
|
7
|
+
import java.io.ByteArrayInputStream;
|
|
8
|
+
import java.io.IOException;
|
|
9
|
+
import java.io.InputStream;
|
|
10
|
+
import java.io.InputStreamReader;
|
|
11
|
+
import java.io.Reader;
|
|
12
|
+
import java.nio.charset.CharsetDecoder;
|
|
13
|
+
import java.nio.charset.CodingErrorAction;
|
|
14
|
+
import java.nio.charset.StandardCharsets;
|
|
15
|
+
|
|
16
|
+
public class IgnoreMalformedUTF8InputStream {
|
|
17
|
+
|
|
18
|
+
static InputStream get(InputStream is)
|
|
19
|
+
throws IOException
|
|
20
|
+
{
|
|
21
|
+
final CharsetDecoder charsetDecoder = StandardCharsets.UTF_8.newDecoder();
|
|
22
|
+
charsetDecoder.onMalformedInput(CodingErrorAction.IGNORE);
|
|
23
|
+
charsetDecoder.onUnmappableCharacter(CodingErrorAction.IGNORE);
|
|
24
|
+
|
|
25
|
+
Reader reader = new BufferedReader(new InputStreamReader(is, charsetDecoder));
|
|
26
|
+
return new ByteArrayInputStream(CharStreams.toString(reader).getBytes(Charsets.UTF_8));
|
|
27
|
+
}
|
|
28
|
+
}
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
package org.embulk.decoder.remove_nonstandard_utf8_bytes;
|
|
2
|
+
|
|
3
|
+
import com.google.common.base.Charsets;
|
|
4
|
+
import com.google.common.io.CharStreams;
|
|
5
|
+
import org.embulk.config.ConfigInject;
|
|
6
|
+
import org.embulk.config.ConfigSource;
|
|
7
|
+
import org.embulk.config.Task;
|
|
8
|
+
import org.embulk.config.TaskSource;
|
|
9
|
+
import org.embulk.spi.BufferAllocator;
|
|
10
|
+
import org.embulk.spi.DecoderPlugin;
|
|
11
|
+
import org.embulk.spi.FileInput;
|
|
12
|
+
import org.embulk.spi.util.FileInputInputStream;
|
|
13
|
+
import org.embulk.spi.util.InputStreamFileInput;
|
|
14
|
+
|
|
15
|
+
import java.io.BufferedReader;
|
|
16
|
+
import java.io.ByteArrayInputStream;
|
|
17
|
+
import java.io.IOException;
|
|
18
|
+
import java.io.InputStream;
|
|
19
|
+
import java.io.InputStreamReader;
|
|
20
|
+
import java.io.Reader;
|
|
21
|
+
import java.nio.charset.CharsetDecoder;
|
|
22
|
+
import java.nio.charset.CodingErrorAction;
|
|
23
|
+
import java.nio.charset.StandardCharsets;
|
|
24
|
+
|
|
25
|
+
public class RemoveNonstandardUtf8BytesDecoderPlugin
|
|
26
|
+
implements DecoderPlugin
|
|
27
|
+
{
|
|
28
|
+
interface PluginTask
|
|
29
|
+
extends Task
|
|
30
|
+
{
|
|
31
|
+
@ConfigInject
|
|
32
|
+
BufferAllocator getBufferAllocator();
|
|
33
|
+
}
|
|
34
|
+
|
|
35
|
+
@Override
|
|
36
|
+
public void transaction(ConfigSource config, DecoderPlugin.Control control)
|
|
37
|
+
{
|
|
38
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
|
39
|
+
|
|
40
|
+
control.run(task.dump());
|
|
41
|
+
}
|
|
42
|
+
|
|
43
|
+
@Override
|
|
44
|
+
public FileInput open(TaskSource taskSource, FileInput fileInput)
|
|
45
|
+
{
|
|
46
|
+
|
|
47
|
+
final FileInputInputStream files = new FileInputInputStream(fileInput);
|
|
48
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
49
|
+
|
|
50
|
+
return new InputStreamFileInput(
|
|
51
|
+
task.getBufferAllocator(),
|
|
52
|
+
new InputStreamFileInput.Provider()
|
|
53
|
+
{
|
|
54
|
+
public InputStream openNext()
|
|
55
|
+
throws IOException
|
|
56
|
+
{
|
|
57
|
+
if (!files.nextFile()) {
|
|
58
|
+
return null;
|
|
59
|
+
}
|
|
60
|
+
return IgnoreMalformedUTF8InputStream.get(files);
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
public void close()
|
|
64
|
+
throws IOException
|
|
65
|
+
{
|
|
66
|
+
files.close();
|
|
67
|
+
}
|
|
68
|
+
});
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
|
|
72
|
+
|
|
73
|
+
}
|
|
@@ -0,0 +1,42 @@
|
|
|
1
|
+
package org.embulk.decoder.remove_nonstandard_utf8_bytes;
|
|
2
|
+
|
|
3
|
+
import org.junit.Test;
|
|
4
|
+
|
|
5
|
+
import java.io.ByteArrayInputStream;
|
|
6
|
+
import java.io.ByteArrayOutputStream;
|
|
7
|
+
import java.io.IOException;
|
|
8
|
+
import java.io.InputStream;
|
|
9
|
+
import java.nio.charset.StandardCharsets;
|
|
10
|
+
|
|
11
|
+
import static org.hamcrest.core.Is.is;
|
|
12
|
+
import static org.junit.Assert.*;
|
|
13
|
+
|
|
14
|
+
public class IgnoreMalformedUTF8InputStreamTest
|
|
15
|
+
{
|
|
16
|
+
|
|
17
|
+
@Test
|
|
18
|
+
public void spec()
|
|
19
|
+
throws Exception {
|
|
20
|
+
InputStream in = IgnoreMalformedUTF8InputStream.get(createMelformedStream());
|
|
21
|
+
int n = in.available();
|
|
22
|
+
byte[] bytes = new byte[n];
|
|
23
|
+
in.read(bytes, 0, n);
|
|
24
|
+
String s = new String(bytes, StandardCharsets.UTF_8);
|
|
25
|
+
assertThat(s.getBytes() , is("ab".getBytes()));
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
private ByteArrayInputStream createMelformedStream() throws IOException
|
|
29
|
+
{
|
|
30
|
+
// out of utf-8 range's byte.
|
|
31
|
+
// 0xF0 is backslash.
|
|
32
|
+
byte[] brokenBytes = { Integer.valueOf(0xF0).byteValue() };
|
|
33
|
+
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
|
|
34
|
+
// contain illegal char record
|
|
35
|
+
outputStream.write("a".getBytes("UTF-8"));
|
|
36
|
+
outputStream.write(brokenBytes); // append dust bytes.
|
|
37
|
+
outputStream.write("b".getBytes("UTF-8"));
|
|
38
|
+
|
|
39
|
+
return new ByteArrayInputStream(outputStream.toByteArray());
|
|
40
|
+
}
|
|
41
|
+
|
|
42
|
+
}
|
metadata
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: embulk-decoder-remove_nonstandard_utf8_bytes
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- smdmts
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2017-06-02 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: Decodes Remove Nonstandard Utf8 Bytes-encoded files read by other file input plugins.
|
|
42
|
+
email:
|
|
43
|
+
- smdmts@every.tv
|
|
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
|
+
- example.yml
|
|
55
|
+
- gradle/wrapper/gradle-wrapper.jar
|
|
56
|
+
- gradle/wrapper/gradle-wrapper.properties
|
|
57
|
+
- gradlew
|
|
58
|
+
- gradlew.bat
|
|
59
|
+
- lib/embulk/decoder/remove_nonstandard_utf8_bytes.rb
|
|
60
|
+
- src/main/java/org/embulk/decoder/remove_nonstandard_utf8_bytes/IgnoreMalformedUTF8InputStream.java
|
|
61
|
+
- src/main/java/org/embulk/decoder/remove_nonstandard_utf8_bytes/RemoveNonstandardUtf8BytesDecoderPlugin.java
|
|
62
|
+
- src/test/java/org/embulk/decoder/remove_nonstandard_utf8_bytes/IgnoreMalformedUTF8InputStreamTest.java
|
|
63
|
+
- classpath/embulk-decoder-remove_nonstandard_utf8_bytes-0.1.0.jar
|
|
64
|
+
homepage: https://github.com/smdmts/embulk-decoder-remove_nonstandard_utf8_bytes
|
|
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: 2.1.9
|
|
85
|
+
signing_key:
|
|
86
|
+
specification_version: 4
|
|
87
|
+
summary: Remove Nonstandard Utf8 Bytes decoder plugin for Embulk
|
|
88
|
+
test_files: []
|