embulk-filter-strip_html_tags 0.1.0 → 0.2.0
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 +4 -4
- data/.gitignore +11 -0
- data/README.md +1 -1
- data/build.gradle +102 -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 +172 -0
- data/gradlew.bat +84 -0
- data/lib/embulk/filter/strip_html_tags.rb +3 -56
- data/src/main/java/org/embulk/filter/strip_html_tags/ColumnVisitorImpl.java +101 -0
- data/src/main/java/org/embulk/filter/strip_html_tags/PlainTextizer.java +15 -0
- data/src/main/java/org/embulk/filter/strip_html_tags/StripHtmlTagsFilterPlugin.java +69 -0
- data/src/test/java/org/embulk/filter/strip_html_tags/TestStripHtmlTagsFilterPlugin.java +127 -0
- metadata +26 -30
- data/Gemfile +0 -2
- data/Rakefile +0 -3
- data/embulk-filter-strip_html_tags.gemspec +0 -21
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6a7d4ca3b7bde941d8b6d239febb959af549bbd8
|
4
|
+
data.tar.gz: 3b4bbf3b76fb8978cea465891c27557aa3081e84
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8e593cbec8f7eba23f4cc4fd2f0d0563f8f6006cc042e9706ca83290bd8768ce7544a91dd4b7b61ba31794fae4baa8091787632766198c67000be8cb1d0a8ac7
|
7
|
+
data.tar.gz: 041e427dfb03b31c175b0608128b461dc668d3f00cd3f03c9629cea222488093b36f851e5c3cb927d2feb99d3b6f0b1160b94c1ab7197bc068f30f9024627fa5
|
data/.gitignore
CHANGED
data/README.md
CHANGED
data/build.gradle
ADDED
@@ -0,0 +1,102 @@
|
|
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
|
+
import com.github.jrubygradle.JRubyExec
|
8
|
+
repositories {
|
9
|
+
mavenCentral()
|
10
|
+
jcenter()
|
11
|
+
}
|
12
|
+
configurations {
|
13
|
+
provided
|
14
|
+
}
|
15
|
+
|
16
|
+
version = "0.2.0"
|
17
|
+
|
18
|
+
sourceCompatibility = 1.7
|
19
|
+
targetCompatibility = 1.7
|
20
|
+
|
21
|
+
dependencies {
|
22
|
+
compile "org.embulk:embulk-core:0.8.38"
|
23
|
+
provided "org.embulk:embulk-core:0.8.38"
|
24
|
+
compile "org.jsoup:jsoup:1.11.2"
|
25
|
+
runtime "org.jsoup:jsoup:1.11.2"
|
26
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
27
|
+
testCompile "junit:junit:4.12", {
|
28
|
+
transitive = false
|
29
|
+
}
|
30
|
+
testCompile "org.hamcrest:hamcrest-all:1.3"
|
31
|
+
testCompile "org.embulk:embulk-core:0.8.38:tests"
|
32
|
+
}
|
33
|
+
|
34
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
35
|
+
doFirst { file("classpath").deleteDir() }
|
36
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
37
|
+
into "classpath"
|
38
|
+
}
|
39
|
+
clean { delete "classpath" }
|
40
|
+
|
41
|
+
checkstyle {
|
42
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
43
|
+
toolVersion = '6.14.1'
|
44
|
+
}
|
45
|
+
checkstyleMain {
|
46
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
47
|
+
ignoreFailures = true
|
48
|
+
}
|
49
|
+
checkstyleTest {
|
50
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
51
|
+
ignoreFailures = true
|
52
|
+
}
|
53
|
+
task checkstyle(type: Checkstyle) {
|
54
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
55
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
56
|
+
}
|
57
|
+
|
58
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
59
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
60
|
+
script "${project.name}.gemspec"
|
61
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
62
|
+
}
|
63
|
+
|
64
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
65
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
66
|
+
script "pkg/${project.name}-${project.version}.gem"
|
67
|
+
}
|
68
|
+
|
69
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) {
|
70
|
+
doLast {
|
71
|
+
println "> Build succeeded."
|
72
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
73
|
+
}
|
74
|
+
}
|
75
|
+
|
76
|
+
task gemspec {
|
77
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
78
|
+
inputs.file "build.gradle"
|
79
|
+
outputs.file gemspecFile
|
80
|
+
doLast { gemspecFile.write($/
|
81
|
+
Gem::Specification.new do |spec|
|
82
|
+
spec.name = "${project.name}"
|
83
|
+
spec.version = "${project.version}"
|
84
|
+
spec.authors = ["SAWADA Tadashi"]
|
85
|
+
spec.summary = "Strip Html Tags filter plugin for Embulk"
|
86
|
+
spec.description = "Strip Html Tags"
|
87
|
+
spec.email = ["cesare@mayverse.jp"]
|
88
|
+
spec.licenses = ["MIT"]
|
89
|
+
spec.homepage = "https://github.com/cesare/embulk-filter-strip_html_tags"
|
90
|
+
|
91
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
92
|
+
spec.test_files = spec.files.grep(%r{^(test|spec)/})
|
93
|
+
spec.require_paths = ["lib"]
|
94
|
+
|
95
|
+
spec.add_development_dependency 'embulk', ['>= 0.8.30']
|
96
|
+
spec.add_development_dependency 'bundler', ['>= 1.10.6']
|
97
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
98
|
+
end
|
99
|
+
/$)
|
100
|
+
}
|
101
|
+
}
|
102
|
+
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 +1,172 @@
|
|
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
|
@@ -1,56 +1,3 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
module Filter
|
5
|
-
|
6
|
-
class StripHtmlTags < FilterPlugin
|
7
|
-
Plugin.register_filter("strip_html_tags", self)
|
8
|
-
|
9
|
-
def self.transaction(config, in_schema, &control)
|
10
|
-
task = {
|
11
|
-
"columns" => config.param("columns", :array, default: []),
|
12
|
-
}
|
13
|
-
|
14
|
-
out_columns = in_schema
|
15
|
-
|
16
|
-
yield(task, out_columns)
|
17
|
-
end
|
18
|
-
|
19
|
-
attr_reader :target_columns, :target_fields
|
20
|
-
|
21
|
-
def init
|
22
|
-
@target_columns = task["columns"]
|
23
|
-
@target_fields = out_schema.map {|c| @target_columns.include?(c.name) }
|
24
|
-
end
|
25
|
-
|
26
|
-
def close
|
27
|
-
end
|
28
|
-
|
29
|
-
def add(page)
|
30
|
-
page.each do |record|
|
31
|
-
page_builder.add(fix_record(record))
|
32
|
-
end
|
33
|
-
end
|
34
|
-
|
35
|
-
def finish
|
36
|
-
page_builder.finish
|
37
|
-
end
|
38
|
-
|
39
|
-
private
|
40
|
-
|
41
|
-
def fix_record(record)
|
42
|
-
record.zip(target_fields).map do |(value, target)|
|
43
|
-
if target
|
44
|
-
strip_tags(value)
|
45
|
-
else
|
46
|
-
value
|
47
|
-
end
|
48
|
-
end
|
49
|
-
end
|
50
|
-
|
51
|
-
def strip_tags(str)
|
52
|
-
Nokogiri::HTML.parse(str).text
|
53
|
-
end
|
54
|
-
end
|
55
|
-
end
|
56
|
-
end
|
1
|
+
Embulk::JavaPlugin.register_filter(
|
2
|
+
"strip_html_tags", "org.embulk.filter.strip_html_tags.StripHtmlTagsFilterPlugin",
|
3
|
+
File.expand_path('../../../../classpath', __FILE__))
|
@@ -0,0 +1,101 @@
|
|
1
|
+
package org.embulk.filter.strip_html_tags;
|
2
|
+
|
3
|
+
import org.embulk.spi.*;
|
4
|
+
import org.embulk.filter.strip_html_tags.StripHtmlTagsFilterPlugin.PluginTask;
|
5
|
+
|
6
|
+
import java.util.List;
|
7
|
+
|
8
|
+
public class ColumnVisitorImpl implements ColumnVisitor{
|
9
|
+
|
10
|
+
private final PluginTask task;
|
11
|
+
private final Schema inputSchema;
|
12
|
+
private final Schema outputSchema;
|
13
|
+
private final PageReader pageReader;
|
14
|
+
private final PageBuilder pageBuilder;
|
15
|
+
private final PlainTextizer plainTextizer;
|
16
|
+
|
17
|
+
ColumnVisitorImpl(PluginTask task, Schema inputSchema, Schema outputSchema, PageReader pageReader, PageBuilder pageBuilder) {
|
18
|
+
this.task = task;
|
19
|
+
this.inputSchema = inputSchema;
|
20
|
+
this.outputSchema = outputSchema;
|
21
|
+
this.pageReader = pageReader;
|
22
|
+
this.pageBuilder = pageBuilder;
|
23
|
+
this.plainTextizer = new PlainTextizer();
|
24
|
+
}
|
25
|
+
|
26
|
+
@Override
|
27
|
+
public void booleanColumn(Column column) {
|
28
|
+
if (pageReader.isNull(column)) {
|
29
|
+
pageBuilder.setNull(column);
|
30
|
+
}
|
31
|
+
else {
|
32
|
+
pageBuilder.setBoolean(column, pageReader.getBoolean(column));
|
33
|
+
}
|
34
|
+
}
|
35
|
+
|
36
|
+
@Override
|
37
|
+
public void longColumn(Column column) {
|
38
|
+
if (pageReader.isNull(column)) {
|
39
|
+
pageBuilder.setNull(column);
|
40
|
+
}
|
41
|
+
else {
|
42
|
+
pageBuilder.setLong(column, pageReader.getLong(column));
|
43
|
+
}
|
44
|
+
}
|
45
|
+
|
46
|
+
@Override
|
47
|
+
public void doubleColumn(Column column) {
|
48
|
+
if (pageReader.isNull(column)) {
|
49
|
+
pageBuilder.setNull(column);
|
50
|
+
}
|
51
|
+
else {
|
52
|
+
pageBuilder.setDouble(column, pageReader.getDouble(column));
|
53
|
+
}
|
54
|
+
}
|
55
|
+
|
56
|
+
@Override
|
57
|
+
public void stringColumn(Column column) {
|
58
|
+
if (pageReader.isNull(column)) {
|
59
|
+
pageBuilder.setNull(column);
|
60
|
+
return;
|
61
|
+
}
|
62
|
+
|
63
|
+
String value = pageReader.getString(column);
|
64
|
+
if (isTargetColumn(column)) {
|
65
|
+
pageBuilder.setString(column, stripTags(value));
|
66
|
+
}
|
67
|
+
else {
|
68
|
+
pageBuilder.setString(column, value);
|
69
|
+
}
|
70
|
+
}
|
71
|
+
|
72
|
+
@Override
|
73
|
+
public void timestampColumn(Column column) {
|
74
|
+
if (pageReader.isNull(column)) {
|
75
|
+
pageBuilder.setNull(column);
|
76
|
+
}
|
77
|
+
else {
|
78
|
+
pageBuilder.setTimestamp(column, pageReader.getTimestamp(column));
|
79
|
+
}
|
80
|
+
}
|
81
|
+
|
82
|
+
@Override
|
83
|
+
public void jsonColumn(Column column) {
|
84
|
+
if (pageReader.isNull(column)) {
|
85
|
+
pageBuilder.setNull(column);
|
86
|
+
}
|
87
|
+
else {
|
88
|
+
pageBuilder.setJson(column, pageReader.getJson(column));
|
89
|
+
}
|
90
|
+
}
|
91
|
+
|
92
|
+
private boolean isTargetColumn(Column column) {
|
93
|
+
List<String> targetColumns = task.getColumns();
|
94
|
+
String columnName = column.getName();
|
95
|
+
return targetColumns.contains(columnName);
|
96
|
+
}
|
97
|
+
|
98
|
+
private String stripTags(String str) {
|
99
|
+
return plainTextizer.execute(str);
|
100
|
+
}
|
101
|
+
}
|
@@ -0,0 +1,15 @@
|
|
1
|
+
package org.embulk.filter.strip_html_tags;
|
2
|
+
|
3
|
+
import org.jsoup.Jsoup;
|
4
|
+
import org.jsoup.nodes.Document;
|
5
|
+
|
6
|
+
public class PlainTextizer {
|
7
|
+
public String execute(String str) {
|
8
|
+
if (str == null) {
|
9
|
+
return null;
|
10
|
+
}
|
11
|
+
|
12
|
+
Document doc = Jsoup.parseBodyFragment(str);
|
13
|
+
return doc.body().text();
|
14
|
+
}
|
15
|
+
}
|
@@ -0,0 +1,69 @@
|
|
1
|
+
package org.embulk.filter.strip_html_tags;
|
2
|
+
|
3
|
+
import com.google.common.base.Optional;
|
4
|
+
|
5
|
+
import org.embulk.config.Config;
|
6
|
+
import org.embulk.config.ConfigDefault;
|
7
|
+
import org.embulk.config.ConfigDiff;
|
8
|
+
import org.embulk.config.ConfigSource;
|
9
|
+
import org.embulk.config.Task;
|
10
|
+
import org.embulk.config.TaskSource;
|
11
|
+
import org.embulk.spi.*;
|
12
|
+
|
13
|
+
import java.util.List;
|
14
|
+
|
15
|
+
public class StripHtmlTagsFilterPlugin
|
16
|
+
implements FilterPlugin
|
17
|
+
{
|
18
|
+
public interface PluginTask
|
19
|
+
extends Task
|
20
|
+
{
|
21
|
+
@Config("columns")
|
22
|
+
@ConfigDefault("[]")
|
23
|
+
public List<String> getColumns();
|
24
|
+
}
|
25
|
+
|
26
|
+
@Override
|
27
|
+
public void transaction(ConfigSource config, Schema inputSchema,
|
28
|
+
FilterPlugin.Control control)
|
29
|
+
{
|
30
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
31
|
+
|
32
|
+
Schema outputSchema = inputSchema;
|
33
|
+
|
34
|
+
control.run(task.dump(), outputSchema);
|
35
|
+
}
|
36
|
+
|
37
|
+
@Override
|
38
|
+
public PageOutput open(TaskSource taskSource, final Schema inputSchema,
|
39
|
+
final Schema outputSchema, final PageOutput output)
|
40
|
+
{
|
41
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
42
|
+
|
43
|
+
return new PageOutput() {
|
44
|
+
private PageReader reader = new PageReader(inputSchema);
|
45
|
+
private PageBuilder builder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
|
46
|
+
private ColumnVisitorImpl visitor = new ColumnVisitorImpl(task, inputSchema, outputSchema, reader, builder);
|
47
|
+
|
48
|
+
@Override
|
49
|
+
public void add(Page page) {
|
50
|
+
reader.setPage(page);
|
51
|
+
|
52
|
+
while (reader.nextRecord()) {
|
53
|
+
inputSchema.visitColumns(visitor);
|
54
|
+
builder.addRecord();
|
55
|
+
}
|
56
|
+
}
|
57
|
+
|
58
|
+
@Override
|
59
|
+
public void finish() {
|
60
|
+
builder.finish();
|
61
|
+
}
|
62
|
+
|
63
|
+
@Override
|
64
|
+
public void close() {
|
65
|
+
builder.close();
|
66
|
+
}
|
67
|
+
};
|
68
|
+
}
|
69
|
+
}
|
@@ -0,0 +1,127 @@
|
|
1
|
+
package org.embulk.filter.strip_html_tags;
|
2
|
+
|
3
|
+
import com.fasterxml.jackson.core.JsonProcessingException;
|
4
|
+
import com.fasterxml.jackson.databind.ObjectMapper;
|
5
|
+
import com.google.common.base.Throwables;
|
6
|
+
import org.embulk.EmbulkTestRuntime;
|
7
|
+
import org.embulk.config.ConfigLoader;
|
8
|
+
import org.embulk.config.ConfigSource;
|
9
|
+
import org.embulk.config.TaskSource;
|
10
|
+
import org.embulk.spi.*;
|
11
|
+
import org.embulk.spi.util.Pages;
|
12
|
+
import org.junit.Assert;
|
13
|
+
import org.junit.Rule;
|
14
|
+
import org.junit.Test;
|
15
|
+
|
16
|
+
import static org.embulk.spi.type.Types.*;
|
17
|
+
import static org.hamcrest.Matchers.*;
|
18
|
+
|
19
|
+
import org.embulk.filter.strip_html_tags.StripHtmlTagsFilterPlugin.PluginTask;
|
20
|
+
|
21
|
+
import java.util.List;
|
22
|
+
|
23
|
+
public class TestStripHtmlTagsFilterPlugin
|
24
|
+
{
|
25
|
+
@Rule
|
26
|
+
public EmbulkTestRuntime runtime = new EmbulkTestRuntime();
|
27
|
+
|
28
|
+
@Test
|
29
|
+
public void testDefaultConfig() {
|
30
|
+
String configYaml = "type: strip_html_tags\n";
|
31
|
+
ConfigSource config = getConfigFromYaml(configYaml);
|
32
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
33
|
+
|
34
|
+
Assert.assertThat(task.getColumns(), is(empty()));
|
35
|
+
}
|
36
|
+
|
37
|
+
@Test
|
38
|
+
public void testConfig() {
|
39
|
+
String configYaml = ""
|
40
|
+
+ "type: strip_html_tags\n"
|
41
|
+
+ "columns:\n"
|
42
|
+
+ " - foo\n"
|
43
|
+
+ " - bar\n"
|
44
|
+
;
|
45
|
+
ConfigSource config = getConfigFromYaml(configYaml);
|
46
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
47
|
+
|
48
|
+
Assert.assertThat(task.getColumns(), is(contains("foo", "bar")));
|
49
|
+
}
|
50
|
+
|
51
|
+
@Test
|
52
|
+
public void testStringColumns() {
|
53
|
+
String configYaml =""
|
54
|
+
+ "type: strip_html_tags\n"
|
55
|
+
+ "columns:\n"
|
56
|
+
+ " - foo\n"
|
57
|
+
;
|
58
|
+
ConfigSource config = getConfigFromYaml(configYaml);
|
59
|
+
|
60
|
+
final Schema inputSchema = Schema.builder()
|
61
|
+
.add("foo", STRING)
|
62
|
+
.add("bar", STRING)
|
63
|
+
.build();
|
64
|
+
|
65
|
+
final StripHtmlTagsFilterPlugin plugin = new StripHtmlTagsFilterPlugin();
|
66
|
+
plugin.transaction(config, inputSchema, new FilterPlugin.Control() {
|
67
|
+
@Override
|
68
|
+
public void run(TaskSource taskSource, Schema outputSchema) {
|
69
|
+
TestPageBuilderReader.MockPageOutput mockPageOutput = new TestPageBuilderReader.MockPageOutput();
|
70
|
+
PageOutput pageOutput = plugin.open(taskSource, inputSchema, outputSchema, mockPageOutput);
|
71
|
+
|
72
|
+
String foo = "<p>test foo</p>";
|
73
|
+
String bar = "<div>test bar</div>";
|
74
|
+
for (Page page : PageTestUtils.buildPage(runtime.getBufferAllocator(), inputSchema, foo, bar)) {
|
75
|
+
pageOutput.add(page);
|
76
|
+
}
|
77
|
+
pageOutput.finish();
|
78
|
+
pageOutput.close();
|
79
|
+
|
80
|
+
List<Object[]> records = Pages.toObjects(outputSchema, mockPageOutput.pages);
|
81
|
+
Object[] record = records.get(0);
|
82
|
+
Assert.assertEquals("test foo", record[0]);
|
83
|
+
Assert.assertEquals("<div>test bar</div>", record[1]);
|
84
|
+
}
|
85
|
+
});
|
86
|
+
}
|
87
|
+
|
88
|
+
@Test
|
89
|
+
public void testNullColumns() {
|
90
|
+
String configYaml =""
|
91
|
+
+ "type: strip_html_tags\n"
|
92
|
+
+ "columns:\n"
|
93
|
+
+ " - foo\n"
|
94
|
+
;
|
95
|
+
ConfigSource config = getConfigFromYaml(configYaml);
|
96
|
+
|
97
|
+
final Schema inputSchema = Schema.builder()
|
98
|
+
.add("foo", STRING)
|
99
|
+
.add("bar", STRING)
|
100
|
+
.build();
|
101
|
+
|
102
|
+
final StripHtmlTagsFilterPlugin plugin = new StripHtmlTagsFilterPlugin();
|
103
|
+
plugin.transaction(config, inputSchema, new FilterPlugin.Control() {
|
104
|
+
@Override
|
105
|
+
public void run(TaskSource taskSource, Schema outputSchema) {
|
106
|
+
TestPageBuilderReader.MockPageOutput mockPageOutput = new TestPageBuilderReader.MockPageOutput();
|
107
|
+
PageOutput pageOutput = plugin.open(taskSource, inputSchema, outputSchema, mockPageOutput);
|
108
|
+
|
109
|
+
for (Page page : PageTestUtils.buildPage(runtime.getBufferAllocator(), inputSchema, null, null)) {
|
110
|
+
pageOutput.add(page);
|
111
|
+
}
|
112
|
+
pageOutput.finish();
|
113
|
+
pageOutput.close();
|
114
|
+
|
115
|
+
List<Object[]> records = Pages.toObjects(outputSchema, mockPageOutput.pages);
|
116
|
+
Object[] record = records.get(0);
|
117
|
+
Assert.assertNull(record[0]);
|
118
|
+
Assert.assertNull(record[1]);
|
119
|
+
}
|
120
|
+
});
|
121
|
+
}
|
122
|
+
|
123
|
+
private ConfigSource getConfigFromYaml(String yaml) {
|
124
|
+
ConfigLoader loader = new ConfigLoader(Exec.getModelManager());
|
125
|
+
return loader.fromYamlString(yaml);
|
126
|
+
}
|
127
|
+
}
|
metadata
CHANGED
@@ -1,33 +1,19 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: embulk-filter-strip_html_tags
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- SAWADA Tadashi
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2018-01-04 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
requirement: !ruby/object:Gem::Requirement
|
15
15
|
requirements:
|
16
|
-
- -
|
17
|
-
- !ruby/object:Gem::Version
|
18
|
-
version: 1.8.0
|
19
|
-
name: nokogiri
|
20
|
-
prerelease: false
|
21
|
-
type: :runtime
|
22
|
-
version_requirements: !ruby/object:Gem::Requirement
|
23
|
-
requirements:
|
24
|
-
- - "~>"
|
25
|
-
- !ruby/object:Gem::Version
|
26
|
-
version: 1.8.0
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
requirement: !ruby/object:Gem::Requirement
|
29
|
-
requirements:
|
30
|
-
- - ">="
|
16
|
+
- - '>='
|
31
17
|
- !ruby/object:Gem::Version
|
32
18
|
version: 0.8.30
|
33
19
|
name: embulk
|
@@ -35,13 +21,13 @@ dependencies:
|
|
35
21
|
type: :development
|
36
22
|
version_requirements: !ruby/object:Gem::Requirement
|
37
23
|
requirements:
|
38
|
-
- -
|
24
|
+
- - '>='
|
39
25
|
- !ruby/object:Gem::Version
|
40
26
|
version: 0.8.30
|
41
27
|
- !ruby/object:Gem::Dependency
|
42
28
|
requirement: !ruby/object:Gem::Requirement
|
43
29
|
requirements:
|
44
|
-
- -
|
30
|
+
- - '>='
|
45
31
|
- !ruby/object:Gem::Version
|
46
32
|
version: 1.10.6
|
47
33
|
name: bundler
|
@@ -49,13 +35,13 @@ dependencies:
|
|
49
35
|
type: :development
|
50
36
|
version_requirements: !ruby/object:Gem::Requirement
|
51
37
|
requirements:
|
52
|
-
- -
|
38
|
+
- - '>='
|
53
39
|
- !ruby/object:Gem::Version
|
54
40
|
version: 1.10.6
|
55
41
|
- !ruby/object:Gem::Dependency
|
56
42
|
requirement: !ruby/object:Gem::Requirement
|
57
43
|
requirements:
|
58
|
-
- -
|
44
|
+
- - '>='
|
59
45
|
- !ruby/object:Gem::Version
|
60
46
|
version: '10.0'
|
61
47
|
name: rake
|
@@ -63,7 +49,7 @@ dependencies:
|
|
63
49
|
type: :development
|
64
50
|
version_requirements: !ruby/object:Gem::Requirement
|
65
51
|
requirements:
|
66
|
-
- -
|
52
|
+
- - '>='
|
67
53
|
- !ruby/object:Gem::Version
|
68
54
|
version: '10.0'
|
69
55
|
description: Strip Html Tags
|
@@ -73,14 +59,24 @@ executables: []
|
|
73
59
|
extensions: []
|
74
60
|
extra_rdoc_files: []
|
75
61
|
files:
|
76
|
-
-
|
77
|
-
-
|
78
|
-
- Gemfile
|
62
|
+
- .gitignore
|
63
|
+
- .ruby-version
|
79
64
|
- LICENSE.txt
|
80
65
|
- README.md
|
81
|
-
-
|
82
|
-
-
|
66
|
+
- build.gradle
|
67
|
+
- config/checkstyle/checkstyle.xml
|
68
|
+
- config/checkstyle/default.xml
|
69
|
+
- gradle/wrapper/gradle-wrapper.jar
|
70
|
+
- gradle/wrapper/gradle-wrapper.properties
|
71
|
+
- gradlew
|
72
|
+
- gradlew.bat
|
83
73
|
- lib/embulk/filter/strip_html_tags.rb
|
74
|
+
- src/main/java/org/embulk/filter/strip_html_tags/ColumnVisitorImpl.java
|
75
|
+
- src/main/java/org/embulk/filter/strip_html_tags/PlainTextizer.java
|
76
|
+
- src/main/java/org/embulk/filter/strip_html_tags/StripHtmlTagsFilterPlugin.java
|
77
|
+
- src/test/java/org/embulk/filter/strip_html_tags/TestStripHtmlTagsFilterPlugin.java
|
78
|
+
- classpath/embulk-filter-strip_html_tags-0.2.0.jar
|
79
|
+
- classpath/jsoup-1.11.2.jar
|
84
80
|
homepage: https://github.com/cesare/embulk-filter-strip_html_tags
|
85
81
|
licenses:
|
86
82
|
- MIT
|
@@ -91,17 +87,17 @@ require_paths:
|
|
91
87
|
- lib
|
92
88
|
required_ruby_version: !ruby/object:Gem::Requirement
|
93
89
|
requirements:
|
94
|
-
- -
|
90
|
+
- - '>='
|
95
91
|
- !ruby/object:Gem::Version
|
96
92
|
version: '0'
|
97
93
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
98
94
|
requirements:
|
99
|
-
- -
|
95
|
+
- - '>='
|
100
96
|
- !ruby/object:Gem::Version
|
101
97
|
version: '0'
|
102
98
|
requirements: []
|
103
99
|
rubyforge_project:
|
104
|
-
rubygems_version: 2.
|
100
|
+
rubygems_version: 2.1.9
|
105
101
|
signing_key:
|
106
102
|
specification_version: 4
|
107
103
|
summary: Strip Html Tags filter plugin for Embulk
|
data/Gemfile
DELETED
data/Rakefile
DELETED
@@ -1,21 +0,0 @@
|
|
1
|
-
|
2
|
-
Gem::Specification.new do |spec|
|
3
|
-
spec.name = "embulk-filter-strip_html_tags"
|
4
|
-
spec.version = "0.1.0"
|
5
|
-
spec.authors = ["SAWADA Tadashi"]
|
6
|
-
spec.summary = "Strip Html Tags filter plugin for Embulk"
|
7
|
-
spec.description = "Strip Html Tags"
|
8
|
-
spec.email = ["cesare@mayverse.jp"]
|
9
|
-
spec.licenses = ["MIT"]
|
10
|
-
spec.homepage = "https://github.com/cesare/embulk-filter-strip_html_tags"
|
11
|
-
|
12
|
-
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
13
|
-
spec.test_files = spec.files.grep(%r{^(test|spec)/})
|
14
|
-
spec.require_paths = ["lib"]
|
15
|
-
|
16
|
-
spec.add_dependency "nokogiri", ["~> 1.8.0"]
|
17
|
-
|
18
|
-
spec.add_development_dependency 'embulk', ['>= 0.8.30']
|
19
|
-
spec.add_development_dependency 'bundler', ['>= 1.10.6']
|
20
|
-
spec.add_development_dependency 'rake', ['>= 10.0']
|
21
|
-
end
|