embulk-input-sparql 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.github/workflows/build.yml +20 -0
- data/.gitignore +12 -0
- data/LICENSE.txt +21 -0
- data/README.md +47 -0
- data/build.gradle +108 -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 +5 -0
- data/gradlew +172 -0
- data/gradlew.bat +84 -0
- data/lib/embulk/input/sparql.rb +3 -0
- data/src/main/java/org/embulk/input/sparql/SparqlInputPlugin.java +188 -0
- data/src/test/java/org/embulk/input/sparql/TestSparqlInputPlugin.java +134 -0
- data/src/test/resources/org/embulk/input/sparql/test/expect/test_config.yml +10 -0
- data/src/test/resources/org/embulk/input/sparql/test/expect/test_config_attrs.yml +19 -0
- data/src/test/resources/org/embulk/input/sparql/test/expect/test_config_invalid_cols.yml +8 -0
- data/src/test/resources/org/embulk/input/sparql/test/expect/test_expected.csv +7 -0
- data/src/test/resources/org/embulk/input/sparql/test/expect/test_expected_attrs.csv +1 -0
- data/src/test/resources/org/embulk/input/sparql/test/expect/unittest.ttl +14 -0
- metadata +117 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: b6ff6a1c57cfd8cfaedd4ab3106a14f60a112e00
|
4
|
+
data.tar.gz: 1142c395dd8f943c8918db379f8b57e2ccc2dd1f
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: d3155ee26c0da9167d8524f99dde14d6bb42fe31dfc37aad5152d63a2e22cd00b73ce337c26fe6466dcdb6ae288ed554901af6238fe3747bb6fd8d4d3244947b
|
7
|
+
data.tar.gz: 44260271a4535d40693a87543895c9c264839d3530c210434b706e3efd46c4d34fe5fef8f017504215909522d07e0e22639f38712d8ab8ac020dc41f064ae20a
|
@@ -0,0 +1,20 @@
|
|
1
|
+
name: Build and test
|
2
|
+
on: push
|
3
|
+
|
4
|
+
jobs:
|
5
|
+
build:
|
6
|
+
runs-on: ubuntu-latest
|
7
|
+
steps:
|
8
|
+
- uses: actions/checkout@v2
|
9
|
+
- uses: actions/setup-java@v1
|
10
|
+
with:
|
11
|
+
java-version: 1.8
|
12
|
+
- run: chmod +x gradlew
|
13
|
+
- uses: actions/cache@v2
|
14
|
+
with:
|
15
|
+
path: ~/.gradle/caches
|
16
|
+
key: ${{ runner.os }}-gradle-${{ hashFiles('**/*.gradle') }}
|
17
|
+
restore-keys: |
|
18
|
+
${{ runner.os }}-gradle-
|
19
|
+
- name: gradle check
|
20
|
+
run: ./gradlew check
|
data/.gitignore
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
|
2
|
+
MIT License
|
3
|
+
|
4
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
5
|
+
a copy of this software and associated documentation files (the
|
6
|
+
"Software"), to deal in the Software without restriction, including
|
7
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
8
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
9
|
+
permit persons to whom the Software is furnished to do so, subject to
|
10
|
+
the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be
|
13
|
+
included in all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
16
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
17
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
18
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
19
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
20
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
21
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
# SPARQL input plugin for Embulk
|
2
|
+
|
3
|
+
SPARQL input plugin for Embulk loads records by SPARQL from any endpoint.
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: input
|
8
|
+
* **Resume supported**: no
|
9
|
+
* **Cleanup supported**: no
|
10
|
+
* **Guess supported**: no
|
11
|
+
|
12
|
+
## Configuration
|
13
|
+
|
14
|
+
- **endpoint**: SPARQL endpoint url (string, required)
|
15
|
+
- **query**: SPARQL query (string, required)
|
16
|
+
- **columns**: Output columns list (list, required)
|
17
|
+
|
18
|
+
## Example
|
19
|
+
|
20
|
+
```yaml
|
21
|
+
in:
|
22
|
+
type: sparql
|
23
|
+
endpoint: https://data.e-stat.go.jp/lod/sparql/alldata/query
|
24
|
+
query: |
|
25
|
+
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
|
26
|
+
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
|
27
|
+
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
|
28
|
+
PREFIX dcterms: <http://purl.org/dc/terms/>
|
29
|
+
SELECT ?publisher ?label ?homepage
|
30
|
+
WHERE {
|
31
|
+
?s rdf:type <http://data.e-stat.go.jp/lod/otherSurvey/Concept>;
|
32
|
+
rdfs:label ?label;
|
33
|
+
foaf:homepage ?homepage;
|
34
|
+
dcterms:publisher ?publisher
|
35
|
+
}
|
36
|
+
order by ?publisher
|
37
|
+
columns:
|
38
|
+
- { name: publisher, type: string }
|
39
|
+
- { name: label, type: string }
|
40
|
+
- { name: homepage, type: string }
|
41
|
+
```
|
42
|
+
|
43
|
+
## Build
|
44
|
+
|
45
|
+
```
|
46
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
47
|
+
```
|
data/build.gradle
ADDED
@@ -0,0 +1,108 @@
|
|
1
|
+
plugins {
|
2
|
+
id "com.jfrog.bintray" version "1.1"
|
3
|
+
id "com.github.jruby-gradle.base" version "1.5.0"
|
4
|
+
id "java"
|
5
|
+
id "checkstyle"
|
6
|
+
}
|
7
|
+
import com.github.jrubygradle.JRubyExec
|
8
|
+
|
9
|
+
repositories {
|
10
|
+
mavenCentral()
|
11
|
+
jcenter()
|
12
|
+
}
|
13
|
+
configurations {
|
14
|
+
provided
|
15
|
+
}
|
16
|
+
|
17
|
+
version = "0.0.1"
|
18
|
+
|
19
|
+
sourceCompatibility = 1.8
|
20
|
+
targetCompatibility = 1.8
|
21
|
+
|
22
|
+
dependencies {
|
23
|
+
compile "org.embulk:embulk-core:0.9.23"
|
24
|
+
provided "org.embulk:embulk-core:0.9.23"
|
25
|
+
|
26
|
+
compile "org.apache.jena:jena-arq:3.16.0"
|
27
|
+
|
28
|
+
testCompile "junit:junit:4.+"
|
29
|
+
testCompile 'org.hamcrest:hamcrest-core:2.2'
|
30
|
+
testCompile "org.embulk:embulk-core:0.9.23"
|
31
|
+
testCompile "org.embulk:embulk-test:0.9.23"
|
32
|
+
testCompile "org.embulk:embulk-deps-buffer:0.9.23"
|
33
|
+
testCompile "org.embulk:embulk-deps-config:0.9.23"
|
34
|
+
testCompile 'org.embulk:embulk-standards:0.9.23'
|
35
|
+
testCompile 'org.apache.jena:jena-fuseki-main:3.16.0'
|
36
|
+
}
|
37
|
+
|
38
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
39
|
+
doFirst { file("classpath").deleteDir() }
|
40
|
+
from(configurations.runtime - configurations.provided + files(jar.archivePath))
|
41
|
+
into "classpath"
|
42
|
+
}
|
43
|
+
clean { delete "classpath" }
|
44
|
+
|
45
|
+
checkstyle {
|
46
|
+
configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
|
47
|
+
toolVersion = '6.14.1'
|
48
|
+
}
|
49
|
+
checkstyleMain {
|
50
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
51
|
+
}
|
52
|
+
checkstyleTest {
|
53
|
+
configFile = file("${project.rootDir}/config/checkstyle/default.xml")
|
54
|
+
ignoreFailures = true
|
55
|
+
}
|
56
|
+
task checkstyle(type: Checkstyle) {
|
57
|
+
classpath = sourceSets.main.output + sourceSets.test.output
|
58
|
+
source = sourceSets.main.allJava + sourceSets.test.allJava
|
59
|
+
}
|
60
|
+
|
61
|
+
task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
|
62
|
+
jrubyArgs "-S"
|
63
|
+
script "gem"
|
64
|
+
scriptArgs "build", "${project.name}.gemspec"
|
65
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
66
|
+
}
|
67
|
+
|
68
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
69
|
+
jrubyArgs "-S"
|
70
|
+
script "gem"
|
71
|
+
scriptArgs "push", "pkg/${project.name}-${project.version}.gem"
|
72
|
+
}
|
73
|
+
|
74
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) {
|
75
|
+
doLast {
|
76
|
+
println "> Build succeeded."
|
77
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
78
|
+
}
|
79
|
+
}
|
80
|
+
|
81
|
+
task gemspec {
|
82
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
83
|
+
inputs.file "build.gradle"
|
84
|
+
outputs.file gemspecFile
|
85
|
+
doLast {
|
86
|
+
gemspecFile.write($/
|
87
|
+
Gem::Specification.new do |spec|
|
88
|
+
spec.name = "${project.name}"
|
89
|
+
spec.version = "${project.version}"
|
90
|
+
spec.authors = ["Mikami, Takeshi"]
|
91
|
+
spec.summary = %[Sparql input plugin for Embulk]
|
92
|
+
spec.description = %[Loads records by Sparql.]
|
93
|
+
spec.email = ["takeshi.mikami@gmail.com"]
|
94
|
+
spec.licenses = ["MIT"]
|
95
|
+
spec.homepage = "https://github.com/takemikami/embulk-input-sparql"
|
96
|
+
|
97
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
98
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
99
|
+
spec.require_paths = ["lib"]
|
100
|
+
|
101
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
102
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
103
|
+
spec.add_development_dependency 'rake', ['~> 12.0']
|
104
|
+
end
|
105
|
+
/$)
|
106
|
+
}
|
107
|
+
}
|
108
|
+
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
|
@@ -0,0 +1,188 @@
|
|
1
|
+
package org.embulk.input.sparql;
|
2
|
+
|
3
|
+
import java.math.BigDecimal;
|
4
|
+
import java.math.BigInteger;
|
5
|
+
import java.util.List;
|
6
|
+
import java.util.NoSuchElementException;
|
7
|
+
import java.util.Optional;
|
8
|
+
import java.util.logging.Logger;
|
9
|
+
|
10
|
+
import org.apache.jena.query.*;
|
11
|
+
|
12
|
+
import org.apache.jena.rdf.model.Literal;
|
13
|
+
import org.embulk.config.Config;
|
14
|
+
import org.embulk.config.ConfigDiff;
|
15
|
+
import org.embulk.config.ConfigSource;
|
16
|
+
import org.embulk.config.Task;
|
17
|
+
import org.embulk.config.TaskReport;
|
18
|
+
import org.embulk.config.TaskSource;
|
19
|
+
import org.embulk.spi.*;
|
20
|
+
import org.embulk.spi.type.Type;
|
21
|
+
import org.embulk.spi.type.Types;
|
22
|
+
import org.joda.time.DateTime;
|
23
|
+
import org.joda.time.DateTimeZone;
|
24
|
+
|
25
|
+
public class SparqlInputPlugin
|
26
|
+
implements InputPlugin
|
27
|
+
{
|
28
|
+
private static final Logger logger = Logger.getLogger(SparqlInputPlugin.class.getName());
|
29
|
+
|
30
|
+
public interface PluginTask
|
31
|
+
extends Task
|
32
|
+
{
|
33
|
+
// endpoint: sparql endpoint (required)
|
34
|
+
@Config("endpoint")
|
35
|
+
public String getEndpoint();
|
36
|
+
|
37
|
+
// query: sparql query (required)
|
38
|
+
@Config("query")
|
39
|
+
public String getQuery();
|
40
|
+
|
41
|
+
// if you get schema from config
|
42
|
+
@Config("columns")
|
43
|
+
public SchemaConfig getColumns();
|
44
|
+
}
|
45
|
+
|
46
|
+
@Override
|
47
|
+
public ConfigDiff transaction(ConfigSource config,
|
48
|
+
InputPlugin.Control control)
|
49
|
+
{
|
50
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
51
|
+
|
52
|
+
Schema schema = task.getColumns().toSchema();
|
53
|
+
int taskCount = 1;
|
54
|
+
|
55
|
+
return resume(task.dump(), schema, taskCount, control);
|
56
|
+
}
|
57
|
+
|
58
|
+
@Override
|
59
|
+
public ConfigDiff resume(TaskSource taskSource,
|
60
|
+
Schema schema, int taskCount,
|
61
|
+
InputPlugin.Control control)
|
62
|
+
{
|
63
|
+
control.run(taskSource, schema, taskCount);
|
64
|
+
return Exec.newConfigDiff();
|
65
|
+
}
|
66
|
+
|
67
|
+
@Override
|
68
|
+
public void cleanup(TaskSource taskSource,
|
69
|
+
Schema schema, int taskCount,
|
70
|
+
List<TaskReport> successTaskReports)
|
71
|
+
{
|
72
|
+
}
|
73
|
+
|
74
|
+
@Override
|
75
|
+
public TaskReport run(TaskSource taskSource,
|
76
|
+
Schema schema, int taskIndex,
|
77
|
+
PageOutput output)
|
78
|
+
{
|
79
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
80
|
+
|
81
|
+
BufferAllocator allocator = Exec.getBufferAllocator();
|
82
|
+
PageBuilder pageBuilder = new PageBuilder(allocator, schema, output);
|
83
|
+
|
84
|
+
// execute query
|
85
|
+
QueryExecution qexec = null;
|
86
|
+
try {
|
87
|
+
Query query = QueryFactory.create(task.getQuery());
|
88
|
+
qexec = QueryExecutionFactory.sparqlService(task.getEndpoint(), query);
|
89
|
+
ResultSet results = qexec.execSelect();
|
90
|
+
|
91
|
+
// return columns should be subset of query result columns.
|
92
|
+
List<String> cols = results.getResultVars();
|
93
|
+
Optional<Column> ngCol = schema.getColumns().stream()
|
94
|
+
.filter(col -> !cols.contains(col.getName()))
|
95
|
+
.findFirst();
|
96
|
+
if (ngCol.isPresent()) {
|
97
|
+
throw new NoSuchElementException(String.format("Sparql query do not return column %s", ngCol.get().getName()));
|
98
|
+
}
|
99
|
+
|
100
|
+
// result set loop
|
101
|
+
while (results.hasNext()) {
|
102
|
+
QuerySolution solution = results.next();
|
103
|
+
|
104
|
+
for (Column col : schema.getColumns()) {
|
105
|
+
String colName = col.getName();
|
106
|
+
Type colType = col.getType();
|
107
|
+
int colIndex = col.getIndex();
|
108
|
+
if (colType.equals(Types.LONG)) {
|
109
|
+
pageBuilder.setLong(colIndex, getLongValue(solution, colName));
|
110
|
+
}
|
111
|
+
else if (colType.equals(Types.DOUBLE)) {
|
112
|
+
pageBuilder.setDouble(colIndex, getDoubleValue(solution, colName));
|
113
|
+
}
|
114
|
+
else if (colType.equals(Types.TIMESTAMP)) {
|
115
|
+
pageBuilder.setTimestamp(colIndex, getTimestampValue(solution, colName));
|
116
|
+
}
|
117
|
+
else {
|
118
|
+
pageBuilder.setString(colIndex, getStringValue(solution, colName));
|
119
|
+
}
|
120
|
+
}
|
121
|
+
pageBuilder.addRecord();
|
122
|
+
}
|
123
|
+
}
|
124
|
+
finally {
|
125
|
+
if (qexec != null) {
|
126
|
+
qexec.close();
|
127
|
+
}
|
128
|
+
}
|
129
|
+
|
130
|
+
pageBuilder.finish();
|
131
|
+
return Exec.newTaskReport();
|
132
|
+
}
|
133
|
+
|
134
|
+
@Override
|
135
|
+
public ConfigDiff guess(ConfigSource config)
|
136
|
+
{
|
137
|
+
return Exec.newConfigDiff();
|
138
|
+
}
|
139
|
+
|
140
|
+
// parse values by RDFDataTypes
|
141
|
+
private String getStringValue(QuerySolution solution, String column)
|
142
|
+
{
|
143
|
+
if (solution.get(column).isLiteral()) {
|
144
|
+
Literal literal = solution.getLiteral(column);
|
145
|
+
return literal.getString();
|
146
|
+
}
|
147
|
+
return solution.get(column).toString();
|
148
|
+
}
|
149
|
+
|
150
|
+
private long getLongValue(QuerySolution solution, String column)
|
151
|
+
{
|
152
|
+
if (solution.get(column).isLiteral()) {
|
153
|
+
Literal literal = solution.getLiteral(column);
|
154
|
+
if (literal.getDatatype().getJavaClass() == BigInteger.class) {
|
155
|
+
return literal.getInt();
|
156
|
+
}
|
157
|
+
else {
|
158
|
+
return Long.parseLong(literal.toString());
|
159
|
+
}
|
160
|
+
}
|
161
|
+
return Long.parseLong(solution.get(column).toString());
|
162
|
+
}
|
163
|
+
|
164
|
+
private double getDoubleValue(QuerySolution solution, String column)
|
165
|
+
{
|
166
|
+
if (solution.get(column).isLiteral()) {
|
167
|
+
Literal literal = solution.getLiteral(column);
|
168
|
+
if (literal.getDatatype().getJavaClass() == BigDecimal.class) {
|
169
|
+
return literal.getDouble();
|
170
|
+
}
|
171
|
+
else {
|
172
|
+
return Double.parseDouble(literal.toString());
|
173
|
+
}
|
174
|
+
}
|
175
|
+
return Double.parseDouble(solution.get(column).toString());
|
176
|
+
}
|
177
|
+
|
178
|
+
private org.embulk.spi.time.Timestamp getTimestampValue(QuerySolution solution, String column)
|
179
|
+
{
|
180
|
+
String stringValue = getStringValue(solution, column);
|
181
|
+
DateTimeZone defaultTZ = DateTimeZone.getDefault();
|
182
|
+
DateTimeZone.setDefault(DateTimeZone.UTC);
|
183
|
+
DateTime dt = DateTime.parse(stringValue);
|
184
|
+
org.embulk.spi.time.Timestamp ts = org.embulk.spi.time.Timestamp.ofEpochMilli(dt.getMillis());
|
185
|
+
DateTimeZone.setDefault(defaultTZ);
|
186
|
+
return ts;
|
187
|
+
}
|
188
|
+
}
|
@@ -0,0 +1,134 @@
|
|
1
|
+
package org.embulk.input.sparql;
|
2
|
+
|
3
|
+
import org.apache.jena.fuseki.main.FusekiServer;
|
4
|
+
import org.apache.jena.graph.Factory;
|
5
|
+
import org.apache.jena.graph.Graph;
|
6
|
+
import org.apache.jena.query.Dataset;
|
7
|
+
import org.apache.jena.query.DatasetFactory;
|
8
|
+
import org.apache.jena.rdf.model.ModelFactory;
|
9
|
+
import org.apache.jena.riot.RDFParser;
|
10
|
+
import org.embulk.config.ConfigSource;
|
11
|
+
import org.embulk.spi.InputPlugin;
|
12
|
+
import org.embulk.test.EmbulkTests;
|
13
|
+
import org.embulk.test.TestingEmbulk;
|
14
|
+
import org.junit.AfterClass;
|
15
|
+
import org.junit.Before;
|
16
|
+
import org.junit.BeforeClass;
|
17
|
+
import org.junit.Rule;
|
18
|
+
import org.junit.Test;
|
19
|
+
|
20
|
+
import java.io.IOException;
|
21
|
+
import java.net.InetAddress;
|
22
|
+
import java.net.ServerSocket;
|
23
|
+
import java.net.URL;
|
24
|
+
import java.nio.file.Path;
|
25
|
+
import java.util.logging.Logger;
|
26
|
+
|
27
|
+
import static org.embulk.test.EmbulkTests.readSortedFile;
|
28
|
+
import static org.hamcrest.MatcherAssert.assertThat;
|
29
|
+
import static org.hamcrest.core.Is.is;
|
30
|
+
import static org.junit.Assert.assertNotNull;
|
31
|
+
import static org.junit.Assert.fail;
|
32
|
+
|
33
|
+
public class TestSparqlInputPlugin
|
34
|
+
{
|
35
|
+
private static final Logger logger = Logger.getLogger(TestSparqlInputPlugin.class.getName());
|
36
|
+
|
37
|
+
private static final String BASIC_RESOURCE_PATH = "org/embulk/input/sparql/test/expect/";
|
38
|
+
|
39
|
+
private static ConfigSource loadYamlResource(TestingEmbulk embulk, String fileName)
|
40
|
+
{
|
41
|
+
return embulk.loadYamlResource(BASIC_RESOURCE_PATH + fileName);
|
42
|
+
}
|
43
|
+
|
44
|
+
private static String readResource(String fileName)
|
45
|
+
{
|
46
|
+
return EmbulkTests.readResource(BASIC_RESOURCE_PATH + fileName);
|
47
|
+
}
|
48
|
+
|
49
|
+
@Rule
|
50
|
+
public TestingEmbulk embulk = TestingEmbulk.builder()
|
51
|
+
.registerPlugin(InputPlugin.class, "sparql", SparqlInputPlugin.class)
|
52
|
+
.build();
|
53
|
+
|
54
|
+
private static FusekiServer fusekiServer = null;
|
55
|
+
|
56
|
+
@BeforeClass
|
57
|
+
public static void setup()
|
58
|
+
{
|
59
|
+
// detect available port
|
60
|
+
int availablePort = -1;
|
61
|
+
for (int i = 1025; i < 65535; i++) {
|
62
|
+
try (ServerSocket socket = new ServerSocket(i, 1, InetAddress.getByName("localhost"))) {
|
63
|
+
availablePort = socket.getLocalPort();
|
64
|
+
break;
|
65
|
+
}
|
66
|
+
catch (IOException e) {
|
67
|
+
// skip, try next port number
|
68
|
+
}
|
69
|
+
}
|
70
|
+
if (availablePort == -1) {
|
71
|
+
fail("cannot find available port.");
|
72
|
+
}
|
73
|
+
|
74
|
+
// start fuseki server
|
75
|
+
URL rootUrl = TestSparqlInputPlugin.class.getClassLoader().getResource(BASIC_RESOURCE_PATH + "unittest.ttl");
|
76
|
+
assertNotNull("testValidatorsImpl not found", rootUrl);
|
77
|
+
String ttlPath = rootUrl.getPath();
|
78
|
+
|
79
|
+
Graph g = Factory.createGraphMem();
|
80
|
+
RDFParser.source(ttlPath).parse(g);
|
81
|
+
Dataset ds = DatasetFactory.create(ModelFactory.createModelForGraph(g));
|
82
|
+
fusekiServer = FusekiServer.create()
|
83
|
+
.add("/dataset", ds)
|
84
|
+
.port(availablePort)
|
85
|
+
.build();
|
86
|
+
fusekiServer.start();
|
87
|
+
logger.info("start fuseki server for unittest.");
|
88
|
+
}
|
89
|
+
|
90
|
+
@AfterClass
|
91
|
+
public static void tearDown()
|
92
|
+
{
|
93
|
+
// stop fuseki server
|
94
|
+
fusekiServer.stop();
|
95
|
+
logger.info("stop fuseki server for unittest.");
|
96
|
+
}
|
97
|
+
|
98
|
+
private ConfigSource baseConfig;
|
99
|
+
|
100
|
+
@Before
|
101
|
+
public void init()
|
102
|
+
{
|
103
|
+
// init config
|
104
|
+
baseConfig = embulk.newConfig();
|
105
|
+
baseConfig.set("type", "sparql");
|
106
|
+
baseConfig.set("endpoint", String.format("http://localhost:%d/dataset", fusekiServer.getPort()));
|
107
|
+
}
|
108
|
+
|
109
|
+
@Test
|
110
|
+
public void testBasic()
|
111
|
+
throws Exception
|
112
|
+
{
|
113
|
+
Path out1 = embulk.createTempFile("csv");
|
114
|
+
embulk.runInput(baseConfig.merge(loadYamlResource(embulk, "test_config.yml")), out1);
|
115
|
+
assertThat(readSortedFile(out1), is(readResource("test_expected.csv")));
|
116
|
+
}
|
117
|
+
|
118
|
+
@Test
|
119
|
+
public void testAttrs()
|
120
|
+
throws Exception
|
121
|
+
{
|
122
|
+
Path out1 = embulk.createTempFile("csv");
|
123
|
+
embulk.runInput(baseConfig.merge(loadYamlResource(embulk, "test_config_attrs.yml")), out1);
|
124
|
+
assertThat(readSortedFile(out1), is(readResource("test_expected_attrs.csv")));
|
125
|
+
}
|
126
|
+
|
127
|
+
@Test(expected = org.embulk.exec.PartialExecutionException.class)
|
128
|
+
public void testInvalidCols()
|
129
|
+
throws Exception
|
130
|
+
{
|
131
|
+
Path out1 = embulk.createTempFile("csv");
|
132
|
+
embulk.runInput(baseConfig.merge(loadYamlResource(embulk, "test_config_invalid_cols.yml")), out1);
|
133
|
+
}
|
134
|
+
}
|
@@ -0,0 +1,19 @@
|
|
1
|
+
query: |
|
2
|
+
select ?s ?name ?birth ?position ?height ?url ?knows
|
3
|
+
where {
|
4
|
+
?s <http://schema.org/name> ?name ;
|
5
|
+
<http://schema.org/birthDate> ?birth ;
|
6
|
+
<http://schema.org/position> ?position ;
|
7
|
+
<http://schema.org/height> ?height ;
|
8
|
+
<http://schema.org/url> ?url ;
|
9
|
+
<http://schema.org/knows> ?knows .
|
10
|
+
filter(?s = <http://example.com/something>)
|
11
|
+
}
|
12
|
+
columns:
|
13
|
+
- { name: s, type: string }
|
14
|
+
- { name: name, type: string }
|
15
|
+
- { name: birth, type: timestamp }
|
16
|
+
- { name: position, type: long }
|
17
|
+
- { name: height, type: double }
|
18
|
+
- { name: url, type: string }
|
19
|
+
- { name: knows, type: string }
|
@@ -0,0 +1,7 @@
|
|
1
|
+
http://example.com/something,http://schema.org/birthDate,2000-01-01
|
2
|
+
http://example.com/something,http://schema.org/height,170.0
|
3
|
+
http://example.com/something,http://schema.org/knows,http://example.com/anotherthing
|
4
|
+
http://example.com/something,http://schema.org/name,familyName
|
5
|
+
http://example.com/something,http://schema.org/position,1
|
6
|
+
http://example.com/something,http://schema.org/url,http://example.com/something
|
7
|
+
http://example.com/something,http://www.w3.org/1999/02/22-rdf-syntax-ns#type,http://schema.org/Person
|
@@ -0,0 +1 @@
|
|
1
|
+
http://example.com/something,familyName,2000-01-01 00:00:00.000000 +0000,1,170.0,http://example.com/something,http://example.com/anotherthing
|
@@ -0,0 +1,14 @@
|
|
1
|
+
@base <http://example.com/rdflint#> .
|
2
|
+
@prefix schema: <http://schema.org/> .
|
3
|
+
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
|
4
|
+
@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
|
5
|
+
|
6
|
+
<something> a schema:Person ;
|
7
|
+
schema:name "familyName" ;
|
8
|
+
schema:url <http://example.com/something> ;
|
9
|
+
schema:position 1 ;
|
10
|
+
schema:height 170.0 ;
|
11
|
+
schema:birthDate "2000-01-01"^^xsd:date ;
|
12
|
+
schema:knows <anotherthing>.
|
13
|
+
|
14
|
+
<anotherthing> a schema:Person.
|
metadata
ADDED
@@ -0,0 +1,117 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-input-sparql
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Mikami, Takeshi
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2020-10-15 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
requirement: !ruby/object:Gem::Requirement
|
15
|
+
requirements:
|
16
|
+
- - "~>"
|
17
|
+
- !ruby/object:Gem::Version
|
18
|
+
version: '1.0'
|
19
|
+
name: bundler
|
20
|
+
prerelease: false
|
21
|
+
type: :development
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
requirement: !ruby/object:Gem::Requirement
|
29
|
+
requirements:
|
30
|
+
- - "~>"
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '12.0'
|
33
|
+
name: rake
|
34
|
+
prerelease: false
|
35
|
+
type: :development
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '12.0'
|
41
|
+
description: Loads records by Sparql.
|
42
|
+
email:
|
43
|
+
- takeshi.mikami@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- ".github/workflows/build.yml"
|
49
|
+
- ".gitignore"
|
50
|
+
- LICENSE.txt
|
51
|
+
- README.md
|
52
|
+
- build.gradle
|
53
|
+
- classpath/collection-0.7.jar
|
54
|
+
- classpath/commons-cli-1.4.jar
|
55
|
+
- classpath/commons-codec-1.14.jar
|
56
|
+
- classpath/commons-compress-1.20.jar
|
57
|
+
- classpath/commons-csv-1.8.jar
|
58
|
+
- classpath/commons-io-2.6.jar
|
59
|
+
- classpath/commons-lang3-3.10.jar
|
60
|
+
- classpath/commons-logging-1.2.jar
|
61
|
+
- classpath/embulk-input-sparql-0.0.1.jar
|
62
|
+
- classpath/httpclient-4.5.10.jar
|
63
|
+
- classpath/httpclient-cache-4.5.10.jar
|
64
|
+
- classpath/httpcore-4.4.12.jar
|
65
|
+
- classpath/jackson-annotations-2.10.1.jar
|
66
|
+
- classpath/jackson-core-2.10.1.jar
|
67
|
+
- classpath/jackson-databind-2.10.1.jar
|
68
|
+
- classpath/javax.annotation-api-1.3.2.jar
|
69
|
+
- classpath/jcl-over-slf4j-1.7.30.jar
|
70
|
+
- classpath/jena-arq-3.16.0.jar
|
71
|
+
- classpath/jena-base-3.16.0.jar
|
72
|
+
- classpath/jena-core-3.16.0.jar
|
73
|
+
- classpath/jena-iri-3.16.0.jar
|
74
|
+
- classpath/jena-shaded-guava-3.16.0.jar
|
75
|
+
- classpath/jsonld-java-0.12.5.jar
|
76
|
+
- classpath/libthrift-0.13.0.jar
|
77
|
+
- classpath/slf4j-api-1.7.30.jar
|
78
|
+
- config/checkstyle/checkstyle.xml
|
79
|
+
- config/checkstyle/default.xml
|
80
|
+
- gradle/wrapper/gradle-wrapper.jar
|
81
|
+
- gradle/wrapper/gradle-wrapper.properties
|
82
|
+
- gradlew
|
83
|
+
- gradlew.bat
|
84
|
+
- lib/embulk/input/sparql.rb
|
85
|
+
- src/main/java/org/embulk/input/sparql/SparqlInputPlugin.java
|
86
|
+
- src/test/java/org/embulk/input/sparql/TestSparqlInputPlugin.java
|
87
|
+
- src/test/resources/org/embulk/input/sparql/test/expect/test_config.yml
|
88
|
+
- src/test/resources/org/embulk/input/sparql/test/expect/test_config_attrs.yml
|
89
|
+
- src/test/resources/org/embulk/input/sparql/test/expect/test_config_invalid_cols.yml
|
90
|
+
- src/test/resources/org/embulk/input/sparql/test/expect/test_expected.csv
|
91
|
+
- src/test/resources/org/embulk/input/sparql/test/expect/test_expected_attrs.csv
|
92
|
+
- src/test/resources/org/embulk/input/sparql/test/expect/unittest.ttl
|
93
|
+
homepage: https://github.com/takemikami/embulk-input-sparql
|
94
|
+
licenses:
|
95
|
+
- MIT
|
96
|
+
metadata: {}
|
97
|
+
post_install_message:
|
98
|
+
rdoc_options: []
|
99
|
+
require_paths:
|
100
|
+
- lib
|
101
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - ">="
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0'
|
106
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
requirements: []
|
112
|
+
rubyforge_project:
|
113
|
+
rubygems_version: 2.6.8
|
114
|
+
signing_key:
|
115
|
+
specification_version: 4
|
116
|
+
summary: Sparql input plugin for Embulk
|
117
|
+
test_files: []
|