embulk-filter-null_string 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 +12 -0
- data/.travis.yml +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +35 -0
- data/build.gradle +99 -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/null_string.rb +3 -0
- data/src/main/java/org/embulk/filter/null_string/NullStringFilterPlugin.java +98 -0
- data/src/main/java/org/embulk/filter/null_string/NullStringVisitorImpl.java +121 -0
- data/src/test/java/org/embulk/filter/null_string/TestNullStringFilterPlugin.java +5 -0
- data/src/test/java/org/embulk/filter/null_string/TestNullStringVisitorImpl.java +271 -0
- metadata +89 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 0fb202cde1e54414f3433e98ed739976bf9a2d7e
|
|
4
|
+
data.tar.gz: 9a8271b90a220fc201e9c48bfc75fcc9dc02e8c6
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 5a6fde482127b0f025a1af8dc606b918b118fff783dfaa32453cf7c0b8616ab2beb63f2c84b07e722c04c02f0b38290e5bfc0e6e80c6c4dc6f1ddc59678185a2
|
|
7
|
+
data.tar.gz: ced6372b1fcbdbe7a3c7ddb847926e317391767ff8423876b3fcbe5319dd23c5dc403e252277d07068311d161d932f3154226933bc4054736fc512997c776d98
|
data/.gitignore
ADDED
data/.travis.yml
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 +1,35 @@
|
|
|
1
|
+
# Null String filter plugin for Embulk
|
|
2
|
+
|
|
3
|
+
An Embulk filter plugin to convert the matching string to NULL.
|
|
4
|
+
|
|
5
|
+
## Overview
|
|
6
|
+
|
|
7
|
+
* **Plugin type**: filter
|
|
8
|
+
|
|
9
|
+
## Configuration
|
|
10
|
+
|
|
11
|
+
- **columns**: name of convert columns
|
|
12
|
+
- **name**: column name (string, required)
|
|
13
|
+
- **null_string**: value of null_string (string, required)
|
|
14
|
+
|
|
15
|
+
## Example
|
|
16
|
+
|
|
17
|
+
```yaml
|
|
18
|
+
- type: null_string
|
|
19
|
+
columns:
|
|
20
|
+
- name: comment
|
|
21
|
+
null_string: ""
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
```yaml
|
|
25
|
+
- type: null_string
|
|
26
|
+
columns:
|
|
27
|
+
- name: comment
|
|
28
|
+
null_string: "\\N"
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
## Build
|
|
32
|
+
|
|
33
|
+
```
|
|
34
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
|
35
|
+
```
|
data/build.gradle
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
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 "findbugs"
|
|
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:0.8.13"
|
|
24
|
+
provided "org.embulk:embulk-core:0.8.13"
|
|
25
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
|
26
|
+
testCompile "junit:junit:4.+"
|
|
27
|
+
|
|
28
|
+
testCompile "org.embulk:embulk-core:0.8.13:tests"
|
|
29
|
+
testCompile "org.embulk:embulk-standards:0.8.13"
|
|
30
|
+
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
|
34
|
+
doFirst { file("classpath").deleteDir() }
|
|
35
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
|
36
|
+
into "classpath"
|
|
37
|
+
}
|
|
38
|
+
clean { delete "classpath" }
|
|
39
|
+
|
|
40
|
+
checkstyle {
|
|
41
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
|
42
|
+
toolVersion = '6.14.1'
|
|
43
|
+
}
|
|
44
|
+
checkstyleMain {
|
|
45
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
46
|
+
ignoreFailures = true
|
|
47
|
+
}
|
|
48
|
+
checkstyleTest {
|
|
49
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
|
50
|
+
ignoreFailures = true
|
|
51
|
+
}
|
|
52
|
+
task checkstyle(type: Checkstyle) {
|
|
53
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
|
54
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
|
55
|
+
}
|
|
56
|
+
|
|
57
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
|
58
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
|
59
|
+
script "${project.name}.gemspec"
|
|
60
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
|
64
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
|
65
|
+
script "pkg/${project.name}-${project.version}.gem"
|
|
66
|
+
}
|
|
67
|
+
|
|
68
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) << {
|
|
69
|
+
println "> Build succeeded."
|
|
70
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
|
71
|
+
}
|
|
72
|
+
|
|
73
|
+
task gemspec {
|
|
74
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
|
75
|
+
inputs.file "build.gradle"
|
|
76
|
+
outputs.file gemspecFile
|
|
77
|
+
doLast { gemspecFile.write($/
|
|
78
|
+
Gem::Specification.new do |spec|
|
|
79
|
+
spec.name = "${project.name}"
|
|
80
|
+
spec.version = "${project.version}"
|
|
81
|
+
spec.authors = ["Hiroyuki Sato"]
|
|
82
|
+
spec.summary = %[Null String filter plugin for Embulk]
|
|
83
|
+
spec.description = %[An Embulk filter plugin to convert the matching string to NULL.]
|
|
84
|
+
spec.email = ["hiroysato@gmail.com"]
|
|
85
|
+
spec.licenses = ["MIT"]
|
|
86
|
+
spec.homepage = "https://github.com/hiroyuki-sato/embulk-filter-null_string"
|
|
87
|
+
|
|
88
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
|
89
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
|
90
|
+
spec.require_paths = ["lib"]
|
|
91
|
+
|
|
92
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
|
93
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
|
94
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
|
95
|
+
end
|
|
96
|
+
/$)
|
|
97
|
+
}
|
|
98
|
+
}
|
|
99
|
+
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 +1,98 @@
|
|
|
1
|
+
package org.embulk.filter.null_string;
|
|
2
|
+
|
|
3
|
+
import org.embulk.config.Config;
|
|
4
|
+
import org.embulk.config.ConfigSource;
|
|
5
|
+
import org.embulk.config.Task;
|
|
6
|
+
import org.embulk.config.TaskSource;
|
|
7
|
+
import org.embulk.spi.Column;
|
|
8
|
+
import org.embulk.spi.Exec;
|
|
9
|
+
import org.embulk.spi.FilterPlugin;
|
|
10
|
+
import org.embulk.spi.Page;
|
|
11
|
+
import org.embulk.spi.PageBuilder;
|
|
12
|
+
import org.embulk.spi.PageOutput;
|
|
13
|
+
import org.embulk.spi.PageReader;
|
|
14
|
+
import org.embulk.spi.Schema;
|
|
15
|
+
|
|
16
|
+
import java.util.List;
|
|
17
|
+
|
|
18
|
+
public class NullStringFilterPlugin
|
|
19
|
+
implements FilterPlugin
|
|
20
|
+
{
|
|
21
|
+
public interface NullColumnConfig
|
|
22
|
+
extends Task
|
|
23
|
+
{
|
|
24
|
+
@Config("name")
|
|
25
|
+
String getName();
|
|
26
|
+
|
|
27
|
+
@Config("null_string")
|
|
28
|
+
String getNullString();
|
|
29
|
+
}
|
|
30
|
+
|
|
31
|
+
public interface PluginTask
|
|
32
|
+
extends Task
|
|
33
|
+
{
|
|
34
|
+
@Config("columns")
|
|
35
|
+
public List<NullColumnConfig> getNullColumnConfig();
|
|
36
|
+
}
|
|
37
|
+
|
|
38
|
+
@Override
|
|
39
|
+
public void transaction(ConfigSource config, Schema inputSchema,
|
|
40
|
+
FilterPlugin.Control control)
|
|
41
|
+
{
|
|
42
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
|
43
|
+
|
|
44
|
+
Schema outputSchema = inputSchema;
|
|
45
|
+
|
|
46
|
+
for (NullColumnConfig nullConfig : task.getNullColumnConfig()) {
|
|
47
|
+
inputSchema.lookupColumn(nullConfig.getName());
|
|
48
|
+
}
|
|
49
|
+
|
|
50
|
+
control.run(task.dump(), outputSchema);
|
|
51
|
+
}
|
|
52
|
+
|
|
53
|
+
static Schema buildOutputSchema(PluginTask task, Schema inputSchema)
|
|
54
|
+
{
|
|
55
|
+
Schema.Builder builder = Schema.builder();
|
|
56
|
+
for (Column inputColumns : inputSchema.getColumns()) {
|
|
57
|
+
builder.add(inputColumns.getName(), inputColumns.getType());
|
|
58
|
+
}
|
|
59
|
+
return builder.build();
|
|
60
|
+
}
|
|
61
|
+
|
|
62
|
+
@Override
|
|
63
|
+
public PageOutput open(TaskSource taskSource, final Schema inputSchema,
|
|
64
|
+
final Schema outputSchema, final PageOutput output)
|
|
65
|
+
{
|
|
66
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
67
|
+
|
|
68
|
+
return new PageOutput()
|
|
69
|
+
{
|
|
70
|
+
private PageReader pageReader = new PageReader(inputSchema);
|
|
71
|
+
private PageBuilder pageBuilder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
|
|
72
|
+
private NullStringVisitorImpl visitor = new NullStringVisitorImpl(task, inputSchema, outputSchema, pageReader, pageBuilder);
|
|
73
|
+
|
|
74
|
+
@Override
|
|
75
|
+
public void finish()
|
|
76
|
+
{
|
|
77
|
+
pageBuilder.finish();
|
|
78
|
+
}
|
|
79
|
+
|
|
80
|
+
@Override
|
|
81
|
+
public void close()
|
|
82
|
+
{
|
|
83
|
+
pageBuilder.close();
|
|
84
|
+
}
|
|
85
|
+
|
|
86
|
+
@Override
|
|
87
|
+
public void add(Page page)
|
|
88
|
+
{
|
|
89
|
+
pageReader.setPage(page);
|
|
90
|
+
|
|
91
|
+
while (pageReader.nextRecord()) {
|
|
92
|
+
outputSchema.visitColumns(visitor);
|
|
93
|
+
pageBuilder.addRecord();
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
};
|
|
97
|
+
}
|
|
98
|
+
}
|
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
package org.embulk.filter.null_string;
|
|
2
|
+
|
|
3
|
+
import org.embulk.spi.Column;
|
|
4
|
+
import org.embulk.spi.ColumnVisitor;
|
|
5
|
+
import org.embulk.spi.Exec;
|
|
6
|
+
import org.embulk.spi.PageBuilder;
|
|
7
|
+
import org.embulk.spi.PageReader;
|
|
8
|
+
import org.embulk.spi.Schema;
|
|
9
|
+
import org.slf4j.Logger;
|
|
10
|
+
|
|
11
|
+
import java.util.HashMap;
|
|
12
|
+
|
|
13
|
+
import static java.util.Locale.ENGLISH;
|
|
14
|
+
|
|
15
|
+
public class NullStringVisitorImpl
|
|
16
|
+
implements ColumnVisitor
|
|
17
|
+
{
|
|
18
|
+
private static final Logger logger = Exec.getLogger(NullStringFilterPlugin.class);
|
|
19
|
+
private final NullStringFilterPlugin.PluginTask task;
|
|
20
|
+
private final Schema inputSchema;
|
|
21
|
+
private final Schema outputSchema;
|
|
22
|
+
private final PageReader pageReader;
|
|
23
|
+
private final PageBuilder pageBuilder;
|
|
24
|
+
private final HashMap<String, String> nullStringMap = new HashMap<>();
|
|
25
|
+
|
|
26
|
+
NullStringVisitorImpl(NullStringFilterPlugin.PluginTask task, Schema inputSchema, Schema outputSchema, PageReader pageReader, PageBuilder pageBuilder)
|
|
27
|
+
{
|
|
28
|
+
this.task = task;
|
|
29
|
+
this.inputSchema = inputSchema;
|
|
30
|
+
this.outputSchema = outputSchema;
|
|
31
|
+
this.pageReader = pageReader;
|
|
32
|
+
this.pageBuilder = pageBuilder;
|
|
33
|
+
initializeNullStringMap();
|
|
34
|
+
}
|
|
35
|
+
|
|
36
|
+
private void initializeNullStringMap()
|
|
37
|
+
{
|
|
38
|
+
for (NullStringFilterPlugin.NullColumnConfig nullStringConfig : task.getNullColumnConfig()) {
|
|
39
|
+
logger.debug(String.format(ENGLISH, "set null_string %s = \"%s\"", nullStringConfig.getName(), nullStringConfig.getNullString()));
|
|
40
|
+
nullStringMap.put(nullStringConfig.getName(), nullStringConfig.getNullString());
|
|
41
|
+
}
|
|
42
|
+
}
|
|
43
|
+
|
|
44
|
+
@Override
|
|
45
|
+
public void booleanColumn(Column outputColumn)
|
|
46
|
+
{
|
|
47
|
+
Column inputColumn = inputSchema.lookupColumn(outputColumn.getName());
|
|
48
|
+
pageBuilder.setBoolean(outputColumn, pageReader.getBoolean(inputColumn));
|
|
49
|
+
}
|
|
50
|
+
|
|
51
|
+
@Override
|
|
52
|
+
public void longColumn(Column outputColumn)
|
|
53
|
+
{
|
|
54
|
+
Column inputColumn = inputSchema.lookupColumn(outputColumn.getName());
|
|
55
|
+
if (pageReader.isNull(inputColumn)) {
|
|
56
|
+
pageBuilder.setNull(outputColumn);
|
|
57
|
+
}
|
|
58
|
+
else {
|
|
59
|
+
pageBuilder.setLong(outputColumn, pageReader.getLong(inputColumn));
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
|
|
63
|
+
@Override
|
|
64
|
+
public void doubleColumn(Column outputColumn)
|
|
65
|
+
{
|
|
66
|
+
Column inputColumn = inputSchema.lookupColumn(outputColumn.getName());
|
|
67
|
+
if (pageReader.isNull(inputColumn)) {
|
|
68
|
+
pageBuilder.setNull(outputColumn);
|
|
69
|
+
}
|
|
70
|
+
else {
|
|
71
|
+
pageBuilder.setDouble(outputColumn, pageReader.getDouble(inputColumn));
|
|
72
|
+
}
|
|
73
|
+
}
|
|
74
|
+
|
|
75
|
+
@Override
|
|
76
|
+
public void stringColumn(Column outputColumn)
|
|
77
|
+
{
|
|
78
|
+
Column inputColumn = inputSchema.lookupColumn(outputColumn.getName());
|
|
79
|
+
if (pageReader.isNull(inputColumn)) {
|
|
80
|
+
pageBuilder.setNull(outputColumn);
|
|
81
|
+
}
|
|
82
|
+
else {
|
|
83
|
+
String nullString = nullStringMap.get(outputColumn.getName());
|
|
84
|
+
String value = pageReader.getString(inputColumn);
|
|
85
|
+
|
|
86
|
+
logger.debug(String.format(ENGLISH, "value = \"%s\", null_string = \"%s\"", value, nullString));
|
|
87
|
+
|
|
88
|
+
if (nullString != null && nullString.equals(value)) {
|
|
89
|
+
pageBuilder.setNull(outputColumn);
|
|
90
|
+
}
|
|
91
|
+
else {
|
|
92
|
+
pageBuilder.setString(outputColumn, pageReader.getString(inputColumn));
|
|
93
|
+
}
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
@Override
|
|
98
|
+
public void jsonColumn(Column outputColumn)
|
|
99
|
+
{
|
|
100
|
+
Column inputColumn = inputSchema.lookupColumn(outputColumn.getName());
|
|
101
|
+
if (pageReader.isNull(inputColumn)) {
|
|
102
|
+
pageBuilder.setNull(outputColumn);
|
|
103
|
+
}
|
|
104
|
+
else {
|
|
105
|
+
pageBuilder.setJson(outputColumn, pageReader.getJson(inputColumn));
|
|
106
|
+
}
|
|
107
|
+
;
|
|
108
|
+
}
|
|
109
|
+
|
|
110
|
+
@Override
|
|
111
|
+
public void timestampColumn(Column outputColumn)
|
|
112
|
+
{
|
|
113
|
+
Column inputColumn = inputSchema.lookupColumn(outputColumn.getName());
|
|
114
|
+
if (pageReader.isNull(inputColumn)) {
|
|
115
|
+
pageBuilder.setNull(outputColumn);
|
|
116
|
+
}
|
|
117
|
+
else {
|
|
118
|
+
pageBuilder.setTimestamp(outputColumn, pageReader.getTimestamp(inputColumn));
|
|
119
|
+
}
|
|
120
|
+
}
|
|
121
|
+
}
|
|
@@ -0,0 +1,271 @@
|
|
|
1
|
+
package org.embulk.filter.null_string;
|
|
2
|
+
|
|
3
|
+
import org.embulk.EmbulkTestRuntime;
|
|
4
|
+
import org.embulk.config.ConfigLoader;
|
|
5
|
+
import org.embulk.config.ConfigSource;
|
|
6
|
+
import org.embulk.filter.null_string.NullStringFilterPlugin.PluginTask;
|
|
7
|
+
import org.embulk.spi.Exec;
|
|
8
|
+
import org.embulk.spi.Page;
|
|
9
|
+
import org.embulk.spi.PageBuilder;
|
|
10
|
+
import org.embulk.spi.PageReader;
|
|
11
|
+
import org.embulk.spi.PageTestUtils;
|
|
12
|
+
import org.embulk.spi.Schema;
|
|
13
|
+
import org.embulk.spi.TestPageBuilderReader;
|
|
14
|
+
import org.embulk.spi.time.Timestamp;
|
|
15
|
+
import org.embulk.spi.util.Pages;
|
|
16
|
+
import org.junit.Before;
|
|
17
|
+
import org.junit.Rule;
|
|
18
|
+
import org.junit.Test;
|
|
19
|
+
import org.msgpack.value.ValueFactory;
|
|
20
|
+
|
|
21
|
+
import java.util.List;
|
|
22
|
+
|
|
23
|
+
import static org.embulk.spi.type.Types.BOOLEAN;
|
|
24
|
+
import static org.embulk.spi.type.Types.DOUBLE;
|
|
25
|
+
import static org.embulk.spi.type.Types.JSON;
|
|
26
|
+
import static org.embulk.spi.type.Types.LONG;
|
|
27
|
+
import static org.embulk.spi.type.Types.STRING;
|
|
28
|
+
import static org.embulk.spi.type.Types.TIMESTAMP;
|
|
29
|
+
import static org.junit.Assert.assertEquals;
|
|
30
|
+
|
|
31
|
+
public class TestNullStringVisitorImpl
|
|
32
|
+
{
|
|
33
|
+
@Rule
|
|
34
|
+
public EmbulkTestRuntime runtime = new EmbulkTestRuntime();
|
|
35
|
+
|
|
36
|
+
@Before
|
|
37
|
+
public void createResource()
|
|
38
|
+
{
|
|
39
|
+
}
|
|
40
|
+
|
|
41
|
+
private ConfigSource config()
|
|
42
|
+
{
|
|
43
|
+
return runtime.getExec().newConfigSource();
|
|
44
|
+
}
|
|
45
|
+
|
|
46
|
+
private PluginTask taskFromYamlString(String... lines)
|
|
47
|
+
{
|
|
48
|
+
StringBuilder builder = new StringBuilder();
|
|
49
|
+
for (String line : lines) {
|
|
50
|
+
builder.append(line).append("\n");
|
|
51
|
+
}
|
|
52
|
+
String yamlString = builder.toString();
|
|
53
|
+
|
|
54
|
+
ConfigLoader loader = new ConfigLoader(Exec.getModelManager());
|
|
55
|
+
ConfigSource config = loader.fromYamlString(yamlString);
|
|
56
|
+
return config.loadConfig(PluginTask.class);
|
|
57
|
+
}
|
|
58
|
+
|
|
59
|
+
private List<Object[]> filter(PluginTask task, Schema inputSchema, Object... objects)
|
|
60
|
+
{
|
|
61
|
+
TestPageBuilderReader.MockPageOutput output = new TestPageBuilderReader.MockPageOutput();
|
|
62
|
+
Schema outputSchema = NullStringFilterPlugin.buildOutputSchema(task, inputSchema);
|
|
63
|
+
PageBuilder pageBuilder = new PageBuilder(runtime.getBufferAllocator(), outputSchema, output);
|
|
64
|
+
PageReader pageReader = new PageReader(inputSchema);
|
|
65
|
+
NullStringVisitorImpl visitor = new NullStringVisitorImpl(task, inputSchema, outputSchema, pageReader, pageBuilder);
|
|
66
|
+
|
|
67
|
+
List<Page> pages = PageTestUtils.buildPage(runtime.getBufferAllocator(), inputSchema, objects);
|
|
68
|
+
for (Page page : pages) {
|
|
69
|
+
pageReader.setPage(page);
|
|
70
|
+
|
|
71
|
+
while (pageReader.nextRecord()) {
|
|
72
|
+
outputSchema.visitColumns(visitor);
|
|
73
|
+
pageBuilder.addRecord();
|
|
74
|
+
}
|
|
75
|
+
}
|
|
76
|
+
pageBuilder.finish();
|
|
77
|
+
pageBuilder.close();
|
|
78
|
+
return Pages.toObjects(outputSchema, output.pages);
|
|
79
|
+
}
|
|
80
|
+
|
|
81
|
+
@Test
|
|
82
|
+
public void visit_nullString_NoConvert()
|
|
83
|
+
{
|
|
84
|
+
PluginTask task = taskFromYamlString(
|
|
85
|
+
"type: null_string",
|
|
86
|
+
"columns: []");
|
|
87
|
+
Schema inputSchema = Schema.builder()
|
|
88
|
+
.add("timestamp", TIMESTAMP)
|
|
89
|
+
.add("string", STRING)
|
|
90
|
+
.add("boolean", BOOLEAN)
|
|
91
|
+
.add("long", LONG)
|
|
92
|
+
.add("double", DOUBLE)
|
|
93
|
+
.add("json", JSON)
|
|
94
|
+
.build();
|
|
95
|
+
List<Object[]> records = filter(task, inputSchema,
|
|
96
|
+
// row1
|
|
97
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"),
|
|
98
|
+
// row2
|
|
99
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"));
|
|
100
|
+
|
|
101
|
+
assertEquals(2, records.size());
|
|
102
|
+
|
|
103
|
+
Object[] record;
|
|
104
|
+
{
|
|
105
|
+
record = records.get(0);
|
|
106
|
+
assertEquals(6, record.length);
|
|
107
|
+
assertEquals(Timestamp.ofEpochSecond(1436745600), record[0]);
|
|
108
|
+
assertEquals("string", record[1]);
|
|
109
|
+
assertEquals(new Boolean(true), record[2]);
|
|
110
|
+
assertEquals(new Long(0), record[3]);
|
|
111
|
+
assertEquals(new Double(0.5), record[4]);
|
|
112
|
+
assertEquals(ValueFactory.newString("json"), record[5]);
|
|
113
|
+
}
|
|
114
|
+
}
|
|
115
|
+
|
|
116
|
+
@Test
|
|
117
|
+
public void visit_nullString_BasicConvert()
|
|
118
|
+
{
|
|
119
|
+
PluginTask task = taskFromYamlString(
|
|
120
|
+
"type: null_string",
|
|
121
|
+
"columns:",
|
|
122
|
+
" - name: null_string",
|
|
123
|
+
" null_string: \"\"");
|
|
124
|
+
Schema inputSchema = Schema.builder()
|
|
125
|
+
.add("timestamp", TIMESTAMP)
|
|
126
|
+
.add("string", STRING)
|
|
127
|
+
.add("boolean", BOOLEAN)
|
|
128
|
+
.add("long", LONG)
|
|
129
|
+
.add("double", DOUBLE)
|
|
130
|
+
.add("json", JSON)
|
|
131
|
+
.add("null_string", STRING)
|
|
132
|
+
.build();
|
|
133
|
+
List<Object[]> records = filter(task, inputSchema,
|
|
134
|
+
// row1
|
|
135
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "",
|
|
136
|
+
// row2
|
|
137
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "");
|
|
138
|
+
|
|
139
|
+
assertEquals(2, records.size());
|
|
140
|
+
|
|
141
|
+
Object[] record;
|
|
142
|
+
{
|
|
143
|
+
record = records.get(0);
|
|
144
|
+
assertEquals(7, record.length);
|
|
145
|
+
assertEquals(Timestamp.ofEpochSecond(1436745600), record[0]);
|
|
146
|
+
assertEquals("string", record[1]);
|
|
147
|
+
assertEquals(new Boolean(true), record[2]);
|
|
148
|
+
assertEquals(new Long(0), record[3]);
|
|
149
|
+
assertEquals(new Double(0.5), record[4]);
|
|
150
|
+
assertEquals(ValueFactory.newString("json"), record[5]);
|
|
151
|
+
assertEquals(null, record[6]);
|
|
152
|
+
}
|
|
153
|
+
}
|
|
154
|
+
|
|
155
|
+
@Test
|
|
156
|
+
public void visit_nullString_NoMatchConvert()
|
|
157
|
+
{
|
|
158
|
+
PluginTask task = taskFromYamlString(
|
|
159
|
+
"type: null_string",
|
|
160
|
+
"columns:",
|
|
161
|
+
" - name: null_string",
|
|
162
|
+
" null_string: \"\"");
|
|
163
|
+
Schema inputSchema = Schema.builder()
|
|
164
|
+
.add("timestamp", TIMESTAMP)
|
|
165
|
+
.add("string", STRING)
|
|
166
|
+
.add("boolean", BOOLEAN)
|
|
167
|
+
.add("long", LONG)
|
|
168
|
+
.add("double", DOUBLE)
|
|
169
|
+
.add("json", JSON)
|
|
170
|
+
.add("null_string", STRING)
|
|
171
|
+
.build();
|
|
172
|
+
List<Object[]> records = filter(task, inputSchema,
|
|
173
|
+
// row1
|
|
174
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "test",
|
|
175
|
+
// row2
|
|
176
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "test");
|
|
177
|
+
|
|
178
|
+
assertEquals(2, records.size());
|
|
179
|
+
|
|
180
|
+
Object[] record;
|
|
181
|
+
{
|
|
182
|
+
record = records.get(0);
|
|
183
|
+
assertEquals(7, record.length);
|
|
184
|
+
assertEquals(Timestamp.ofEpochSecond(1436745600), record[0]);
|
|
185
|
+
assertEquals("string", record[1]);
|
|
186
|
+
assertEquals(new Boolean(true), record[2]);
|
|
187
|
+
assertEquals(new Long(0), record[3]);
|
|
188
|
+
assertEquals(new Double(0.5), record[4]);
|
|
189
|
+
assertEquals(ValueFactory.newString("json"), record[5]);
|
|
190
|
+
assertEquals("test", record[6]);
|
|
191
|
+
}
|
|
192
|
+
}
|
|
193
|
+
|
|
194
|
+
@Test
|
|
195
|
+
public void visit_nullString_StringConvert()
|
|
196
|
+
{
|
|
197
|
+
PluginTask task = taskFromYamlString(
|
|
198
|
+
"type: null_string",
|
|
199
|
+
"columns:",
|
|
200
|
+
" - name: null_string",
|
|
201
|
+
" null_string: \"_NULL_\"");
|
|
202
|
+
Schema inputSchema = Schema.builder()
|
|
203
|
+
.add("timestamp", TIMESTAMP)
|
|
204
|
+
.add("string", STRING)
|
|
205
|
+
.add("boolean", BOOLEAN)
|
|
206
|
+
.add("long", LONG)
|
|
207
|
+
.add("double", DOUBLE)
|
|
208
|
+
.add("json", JSON)
|
|
209
|
+
.add("null_string", STRING)
|
|
210
|
+
.build();
|
|
211
|
+
List<Object[]> records = filter(task, inputSchema,
|
|
212
|
+
// row1
|
|
213
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "_NULL_",
|
|
214
|
+
// row2
|
|
215
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "_NULL_");
|
|
216
|
+
|
|
217
|
+
assertEquals(2, records.size());
|
|
218
|
+
|
|
219
|
+
Object[] record;
|
|
220
|
+
{
|
|
221
|
+
record = records.get(0);
|
|
222
|
+
assertEquals(7, record.length);
|
|
223
|
+
assertEquals(Timestamp.ofEpochSecond(1436745600), record[0]);
|
|
224
|
+
assertEquals("string", record[1]);
|
|
225
|
+
assertEquals(new Boolean(true), record[2]);
|
|
226
|
+
assertEquals(new Long(0), record[3]);
|
|
227
|
+
assertEquals(new Double(0.5), record[4]);
|
|
228
|
+
assertEquals(ValueFactory.newString("json"), record[5]);
|
|
229
|
+
assertEquals(null, record[6]);
|
|
230
|
+
}
|
|
231
|
+
}
|
|
232
|
+
@Test
|
|
233
|
+
public void visit_nullString_StringConvert2()
|
|
234
|
+
{
|
|
235
|
+
PluginTask task = taskFromYamlString(
|
|
236
|
+
"type: null_string",
|
|
237
|
+
"columns:",
|
|
238
|
+
" - name: null_string",
|
|
239
|
+
" null_string: \"\\\\N\"");
|
|
240
|
+
Schema inputSchema = Schema.builder()
|
|
241
|
+
.add("timestamp", TIMESTAMP)
|
|
242
|
+
.add("string", STRING)
|
|
243
|
+
.add("boolean", BOOLEAN)
|
|
244
|
+
.add("long", LONG)
|
|
245
|
+
.add("double", DOUBLE)
|
|
246
|
+
.add("json", JSON)
|
|
247
|
+
.add("null_string", STRING)
|
|
248
|
+
.build();
|
|
249
|
+
List<Object[]> records = filter(task, inputSchema,
|
|
250
|
+
// row1
|
|
251
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "\\N",
|
|
252
|
+
// row2
|
|
253
|
+
Timestamp.ofEpochSecond(1436745600), "string", new Boolean(true), new Long(0), new Double(0.5), ValueFactory.newString("json"), "\\N");
|
|
254
|
+
|
|
255
|
+
assertEquals(2, records.size());
|
|
256
|
+
|
|
257
|
+
Object[] record;
|
|
258
|
+
{
|
|
259
|
+
record = records.get(0);
|
|
260
|
+
assertEquals(7, record.length);
|
|
261
|
+
assertEquals(Timestamp.ofEpochSecond(1436745600), record[0]);
|
|
262
|
+
assertEquals("string", record[1]);
|
|
263
|
+
assertEquals(new Boolean(true), record[2]);
|
|
264
|
+
assertEquals(new Long(0), record[3]);
|
|
265
|
+
assertEquals(new Double(0.5), record[4]);
|
|
266
|
+
assertEquals(ValueFactory.newString("json"), record[5]);
|
|
267
|
+
assertEquals(null, record[6]);
|
|
268
|
+
}
|
|
269
|
+
}
|
|
270
|
+
}
|
|
271
|
+
|
metadata
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: embulk-filter-null_string
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Hiroyuki Sato
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2016-08-19 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: An Embulk filter plugin to convert the matching string to NULL.
|
|
42
|
+
email:
|
|
43
|
+
- hiroysato@gmail.com
|
|
44
|
+
executables: []
|
|
45
|
+
extensions: []
|
|
46
|
+
extra_rdoc_files: []
|
|
47
|
+
files:
|
|
48
|
+
- .gitignore
|
|
49
|
+
- .travis.yml
|
|
50
|
+
- LICENSE.txt
|
|
51
|
+
- README.md
|
|
52
|
+
- build.gradle
|
|
53
|
+
- config/checkstyle/checkstyle.xml
|
|
54
|
+
- config/checkstyle/default.xml
|
|
55
|
+
- gradle/wrapper/gradle-wrapper.jar
|
|
56
|
+
- gradle/wrapper/gradle-wrapper.properties
|
|
57
|
+
- gradlew
|
|
58
|
+
- gradlew.bat
|
|
59
|
+
- lib/embulk/filter/null_string.rb
|
|
60
|
+
- src/main/java/org/embulk/filter/null_string/NullStringFilterPlugin.java
|
|
61
|
+
- src/main/java/org/embulk/filter/null_string/NullStringVisitorImpl.java
|
|
62
|
+
- src/test/java/org/embulk/filter/null_string/TestNullStringFilterPlugin.java
|
|
63
|
+
- src/test/java/org/embulk/filter/null_string/TestNullStringVisitorImpl.java
|
|
64
|
+
- classpath/embulk-filter-null_string-0.1.0.jar
|
|
65
|
+
homepage: https://github.com/hiroyuki-sato/embulk-filter-null_string
|
|
66
|
+
licenses:
|
|
67
|
+
- MIT
|
|
68
|
+
metadata: {}
|
|
69
|
+
post_install_message:
|
|
70
|
+
rdoc_options: []
|
|
71
|
+
require_paths:
|
|
72
|
+
- lib
|
|
73
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
74
|
+
requirements:
|
|
75
|
+
- - '>='
|
|
76
|
+
- !ruby/object:Gem::Version
|
|
77
|
+
version: '0'
|
|
78
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - '>='
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '0'
|
|
83
|
+
requirements: []
|
|
84
|
+
rubyforge_project:
|
|
85
|
+
rubygems_version: 2.1.9
|
|
86
|
+
signing_key:
|
|
87
|
+
specification_version: 4
|
|
88
|
+
summary: Null String filter plugin for Embulk
|
|
89
|
+
test_files: []
|