embulk-output-s3_per_record 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 88cdda711509c0f8890ae1dfa9c9720c1067bd0b
4
+ data.tar.gz: 1618f1e1d874773f3edcaa738bd1f4bd4d4c766e
5
+ SHA512:
6
+ metadata.gz: 1b2b9029f619efcb751886b52d755cfd8bf11750a87c6a98c4f9561a539083ec78ece754fe1d2fa19be646fb2d3d677488207b2b1cbb31c4405b181c56bd5c53
7
+ data.tar.gz: 1c39b5d32160d7e2290bba51c376971131f44a5d81159db285340119c1d28970d984d05d5ba2dc8c569189189e242722241136965a8e92c6926cd5143d75d9f6
data/.gitignore ADDED
@@ -0,0 +1,12 @@
1
+ *~
2
+ /pkg/
3
+ /tmp/
4
+ *.gemspec
5
+ .gradle/
6
+ /classpath/
7
+ build/
8
+ .idea
9
+ /.settings/
10
+ /.metadata/
11
+ .classpath
12
+ .project
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 +1,46 @@
1
+ # S3 Per Record output plugin for Embulk
2
+
3
+ This plugin uploads a column's value to S3 as one S3 object per row.
4
+ S3 object key can be composed of another column.
5
+
6
+ ## Overview
7
+
8
+ * **Plugin type**: output
9
+ * **Load all or nothing**: no
10
+ * **Resume supported**: no
11
+
12
+ ## Configuration
13
+
14
+ - **bucket**: S3 bucket name.
15
+ - **key**: S3 object key. `${column}` is replaced by the column's value.
16
+ - **data_column**: Column for object's body.
17
+ - **aws_access_key_id**: (optional) AWS access key id. If not given, [DefaultAWSCredentialsProviderChain](http://docs.aws.amazon.com/AWSJavaSDK/latest/javadoc/com/amazonaws/auth/DefaultAWSCredentialsProviderChain.html) is used to get credentials.
18
+ - **aws_secret_access_key**: (optional) AWS secret access key. Required if `aws_access_key_id` is given.
19
+
20
+ ## Example
21
+
22
+ ```yaml
23
+ out:
24
+ type: s3_per_record
25
+ bucket: your-bucket-name
26
+ key: "sample/${id}.txt"
27
+ data_column: payload
28
+ ```
29
+
30
+ ```
31
+ id | payload
32
+ ------------
33
+ 1 | hello
34
+ 5 | world
35
+ 12 | embulk
36
+ ```
37
+
38
+ This generates `s3://your-bucket-name/sample/1.txt` with its content `hello`,
39
+ `s3://your-bucket-name/sample/5.txt` with its content `world`, and so on.
40
+
41
+
42
+ ## Build
43
+
44
+ ```
45
+ $ ./gradlew gem # -t to watch change of files and rebuild continuously
46
+ ```
data/build.gradle ADDED
@@ -0,0 +1,93 @@
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 = "0.1.0"
17
+
18
+ sourceCompatibility = 1.7
19
+ targetCompatibility = 1.7
20
+
21
+ dependencies {
22
+ compile "org.embulk:embulk-core:0.8.8"
23
+ provided "org.embulk:embulk-core:0.8.8"
24
+ compile 'com.amazonaws:aws-java-sdk-s3:1.10.71'
25
+ testCompile "junit:junit:4.+"
26
+ }
27
+
28
+ task classpath(type: Copy, dependsOn: ["jar"]) {
29
+ doFirst { file("classpath").deleteDir() }
30
+ from (configurations.runtime - configurations.provided + files(jar.archivePath))
31
+ into "classpath"
32
+ }
33
+ clean { delete "classpath" }
34
+
35
+ checkstyle {
36
+ configFile = file("${project.rootDir}/config/checkstyle/checkstyle.xml")
37
+ toolVersion = '6.14.1'
38
+ }
39
+ checkstyleMain {
40
+ configFile = file("${project.rootDir}/config/checkstyle/default.xml")
41
+ ignoreFailures = true
42
+ }
43
+ checkstyleTest {
44
+ configFile = file("${project.rootDir}/config/checkstyle/default.xml")
45
+ ignoreFailures = true
46
+ }
47
+ task checkstyle(type: Checkstyle) {
48
+ classpath = sourceSets.main.output + sourceSets.test.output
49
+ source = sourceSets.main.allJava + sourceSets.test.allJava
50
+ }
51
+
52
+ task gem(type: JRubyExec, dependsOn: ["gemspec", "classpath"]) {
53
+ jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
54
+ script "${project.name}.gemspec"
55
+ doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
56
+ }
57
+
58
+ task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
59
+ jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
60
+ script "pkg/${project.name}-${project.version}.gem"
61
+ }
62
+
63
+ task "package"(dependsOn: ["gemspec", "classpath"]) << {
64
+ println "> Build succeeded."
65
+ println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
66
+ }
67
+
68
+ task gemspec {
69
+ ext.gemspecFile = file("${project.name}.gemspec")
70
+ inputs.file "build.gradle"
71
+ outputs.file gemspecFile
72
+ doLast { gemspecFile.write($/
73
+ Gem::Specification.new do |spec|
74
+ spec.name = "${project.name}"
75
+ spec.version = "${project.version}"
76
+ spec.authors = ["tomykaira"]
77
+ spec.summary = %[S3 Per Record output plugin for Embulk]
78
+ spec.description = %[Upload a column's value to S3 as one S3 object per row.]
79
+ spec.email = ["tomykaira@gmail.com"]
80
+ spec.licenses = ["MIT"]
81
+ spec.homepage = "https://github.com/tomykaira/embulk-output-s3_per_record"
82
+
83
+ spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
84
+ spec.test_files = spec.files.grep(%r"^(test|spec)/")
85
+ spec.require_paths = ["lib"]
86
+
87
+ spec.add_development_dependency 'bundler', ['~> 1.0']
88
+ spec.add_development_dependency 'rake', ['>= 10.0']
89
+ end
90
+ /$)
91
+ }
92
+ }
93
+ 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
@@ -0,0 +1,6 @@
1
+ #Wed Jan 13 12:41:02 JST 2016
2
+ distributionBase=GRADLE_USER_HOME
3
+ distributionPath=wrapper/dists
4
+ zipStoreBase=GRADLE_USER_HOME
5
+ zipStorePath=wrapper/dists
6
+ distributionUrl=https\://services.gradle.org/distributions/gradle-2.10-bin.zip
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 +1,3 @@
1
+ Embulk::JavaPlugin.register_output(
2
+ "s3_per_record", "org.embulk.output.s3_per_record.S3PerRecordOutputPlugin",
3
+ File.expand_path('../../../../classpath', __FILE__))
@@ -0,0 +1,246 @@
1
+ package org.embulk.output.s3_per_record;
2
+
3
+ import java.io.ByteArrayInputStream;
4
+ import java.io.IOException;
5
+ import java.io.InputStream;
6
+ import java.util.ArrayList;
7
+ import java.util.List;
8
+
9
+ import javax.validation.constraints.NotNull;
10
+
11
+ import org.embulk.config.Config;
12
+ import org.embulk.config.ConfigDefault;
13
+ import org.embulk.config.ConfigDiff;
14
+ import org.embulk.config.ConfigSource;
15
+ import org.embulk.config.Task;
16
+ import org.embulk.config.TaskReport;
17
+ import org.embulk.config.TaskSource;
18
+ import org.embulk.spi.Column;
19
+ import org.embulk.spi.Exec;
20
+ import org.embulk.spi.OutputPlugin;
21
+ import org.embulk.spi.Page;
22
+ import org.embulk.spi.PageReader;
23
+ import org.embulk.spi.Schema;
24
+ import org.embulk.spi.TransactionalPageOutput;
25
+
26
+ import com.amazonaws.auth.AWSCredentials;
27
+ import com.amazonaws.auth.BasicAWSCredentials;
28
+ import com.amazonaws.auth.DefaultAWSCredentialsProviderChain;
29
+ import com.amazonaws.services.s3.model.ObjectMetadata;
30
+ import com.amazonaws.services.s3.transfer.TransferManager;
31
+ import com.amazonaws.services.s3.transfer.Upload;
32
+ import com.google.common.base.Optional;
33
+
34
+
35
+ public class S3PerRecordOutputPlugin
36
+ implements OutputPlugin
37
+ {
38
+
39
+ public static final String KEY_COLUMN_START_MARKER = "${";
40
+ public static final String KEY_COLUMN_END_MARKER = "}";
41
+
42
+ public interface PluginTask
43
+ extends Task
44
+ {
45
+ // S3 bucket name.
46
+ @Config("bucket")
47
+ String getBucket();
48
+
49
+ // S3 key. {{column}} is expanded to column value in a row.
50
+ @Config("key")
51
+ String getKey();
52
+
53
+ // Column name.
54
+ @Config("data_column")
55
+ String getDataColumn();
56
+
57
+ // AWS access key id.
58
+ @Config("aws_access_key_id")
59
+ @ConfigDefault("null")
60
+ Optional<String> getAwsAccessKeyId();
61
+
62
+ // AWS secret access key
63
+ @Config("aws_secret_access_key")
64
+ @ConfigDefault("null")
65
+ Optional<String> getAwsSecretAccessKey();
66
+ }
67
+
68
+ @Override
69
+ public ConfigDiff transaction(ConfigSource config,
70
+ Schema schema, int taskCount,
71
+ OutputPlugin.Control control)
72
+ {
73
+ PluginTask task = config.loadConfig(PluginTask.class);
74
+ control.run(task.dump());
75
+ return Exec.newConfigDiff();
76
+ }
77
+
78
+ @Override
79
+ public ConfigDiff resume(TaskSource taskSource,
80
+ Schema schema, int taskCount,
81
+ OutputPlugin.Control control)
82
+ {
83
+ throw new UnsupportedOperationException("s3_per_record output plugin does not support resuming");
84
+ }
85
+
86
+ @Override
87
+ public void cleanup(TaskSource taskSource,
88
+ Schema schema, int taskCount,
89
+ List<TaskReport> successTaskReports)
90
+ {
91
+ }
92
+
93
+ @Override
94
+ public TransactionalPageOutput open(TaskSource taskSource, Schema schema, int taskIndex)
95
+ {
96
+ PluginTask task = taskSource.loadTask(PluginTask.class);
97
+ S3PerRecordPageOutput output = new S3PerRecordPageOutput(task, schema);
98
+ output.open();
99
+ return output;
100
+ }
101
+
102
+ private static class S3PerRecordPageOutput implements TransactionalPageOutput {
103
+ private final TransferManager transferManager;
104
+ private PageReader pageReader;
105
+ private final String bucket;
106
+ private final List<KeyPart> keyPattern;
107
+ private final Column dataColumn;
108
+ private final Schema schema;
109
+ private List<Upload> uploads;
110
+
111
+ public S3PerRecordPageOutput(PluginTask task, Schema schema) {
112
+ this.schema = schema;
113
+ bucket = task.getBucket();
114
+ keyPattern = makeKeyPattern(task.getKey());
115
+ dataColumn = schema.lookupColumn(task.getDataColumn());
116
+
117
+ AWSCredentials credentials;
118
+ if (task.getAwsAccessKeyId().isPresent() && task.getAwsSecretAccessKey().isPresent()) {
119
+ credentials = new BasicAWSCredentials(task.getAwsAccessKeyId().get(), task.getAwsSecretAccessKey().get());
120
+ } else {
121
+ credentials = new DefaultAWSCredentialsProviderChain().getCredentials();
122
+ }
123
+ transferManager = new TransferManager(credentials);
124
+
125
+ uploads = new ArrayList<>();
126
+ }
127
+
128
+ private List<KeyPart> makeKeyPattern(final String key) {
129
+ int offset = 0;
130
+ int nextOffset = 0;
131
+ ArrayList<KeyPart> parts = new ArrayList<>();
132
+ while ((nextOffset = key.indexOf(KEY_COLUMN_START_MARKER, offset)) != -1) {
133
+ parts.add(new ConstantStringPart(key.substring(offset, nextOffset)));
134
+ offset = nextOffset + KEY_COLUMN_START_MARKER.length();
135
+ nextOffset = key.indexOf(KEY_COLUMN_END_MARKER, offset);
136
+ if (nextOffset == -1) {
137
+ throw new RuntimeException("Key's column name segment is not closed. Check that {{ and }} are corresponding.");
138
+ }
139
+ parts.add(new ColumnPart(schema.lookupColumn(key.substring(offset, nextOffset))));
140
+ offset = nextOffset + KEY_COLUMN_END_MARKER.length();
141
+ }
142
+ if (offset < key.length()) {
143
+ parts.add(new ConstantStringPart(key.substring(offset, key.length())));
144
+ }
145
+ return parts;
146
+ }
147
+
148
+ void open() {
149
+ pageReader = new PageReader(schema);
150
+ }
151
+
152
+ @Override
153
+ public void add(Page page) {
154
+ pageReader.setPage(page);
155
+
156
+ while (pageReader.nextRecord()) {
157
+ String key = buildKey(pageReader);
158
+
159
+ String payload = pageReader.getString(dataColumn);
160
+ byte[] payloadBytes = payload.getBytes();
161
+ ObjectMetadata metadata = new ObjectMetadata();
162
+ metadata.setContentLength(payloadBytes.length);
163
+
164
+ try (InputStream is = new ByteArrayInputStream(payloadBytes)) {
165
+ Upload upload = transferManager.upload(bucket, key, is, metadata);
166
+ uploads.add(upload);
167
+ } catch (IOException e) {
168
+ throw new RuntimeException(e);
169
+ }
170
+ }
171
+ }
172
+
173
+ private String buildKey(@NotNull PageReader pageReader) {
174
+ StringBuilder sb = new StringBuilder();
175
+ for (KeyPart p : keyPattern) {
176
+ sb.append(p.resolve(pageReader));
177
+ }
178
+ return sb.toString();
179
+ }
180
+
181
+ @Override
182
+ public void finish()
183
+ {
184
+ try {
185
+ for (Upload upload : uploads) {
186
+ upload.waitForUploadResult();
187
+ }
188
+ } catch (InterruptedException e) {
189
+ throw new RuntimeException(e);
190
+ } finally {
191
+ close();
192
+ }
193
+ }
194
+
195
+ @Override
196
+ public void close()
197
+ {
198
+ if (pageReader != null) {
199
+ pageReader.close();
200
+ }
201
+ }
202
+
203
+ @Override
204
+ public void abort() {
205
+ for (Upload upload : uploads) {
206
+ upload.abort();
207
+ }
208
+ }
209
+
210
+ @Override
211
+ public TaskReport commit()
212
+ {
213
+ return Exec.newTaskReport();
214
+ }
215
+ }
216
+
217
+ private interface KeyPart {
218
+ @NotNull String resolve(PageReader reader);
219
+ }
220
+
221
+ private static class ConstantStringPart implements KeyPart {
222
+ @NotNull private final String data;
223
+
224
+ private ConstantStringPart(@NotNull String data) {
225
+ this.data = data;
226
+ }
227
+
228
+ @Override
229
+ public String resolve(@NotNull PageReader reader) {
230
+ return data;
231
+ }
232
+ }
233
+
234
+ private static class ColumnPart implements KeyPart {
235
+ @NotNull private final Column column;
236
+
237
+ private ColumnPart(@NotNull Column column) {
238
+ this.column = column;
239
+ }
240
+
241
+ @Override
242
+ public String resolve(@NotNull PageReader reader) {
243
+ return reader.getString(column);
244
+ }
245
+ }
246
+ }
@@ -0,0 +1,5 @@
1
+ package org.embulk.output.s3_per_record;
2
+
3
+ public class TestS3PerRecordOutputPlugin
4
+ {
5
+ }
metadata ADDED
@@ -0,0 +1,94 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-output-s3_per_record
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - tomykaira
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2016-04-21 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: Upload a column's value to S3 as one S3 object per row.
42
+ email:
43
+ - tomykaira@gmail.com
44
+ executables: []
45
+ extensions: []
46
+ extra_rdoc_files: []
47
+ files:
48
+ - .gitignore
49
+ - LICENSE.txt
50
+ - README.md
51
+ - build.gradle
52
+ - config/checkstyle/checkstyle.xml
53
+ - config/checkstyle/default.xml
54
+ - gradle/wrapper/gradle-wrapper.jar
55
+ - gradle/wrapper/gradle-wrapper.properties
56
+ - gradlew
57
+ - gradlew.bat
58
+ - lib/embulk/output/s3_per_record.rb
59
+ - src/main/java/org/embulk/output/s3_per_record/S3PerRecordOutputPlugin.java
60
+ - src/test/java/org/embulk/output/s3_per_record/TestS3PerRecordOutputPlugin.java
61
+ - classpath/jackson-dataformat-cbor-2.5.3.jar
62
+ - classpath/httpclient-4.3.6.jar
63
+ - classpath/commons-logging-1.1.3.jar
64
+ - classpath/commons-codec-1.6.jar
65
+ - classpath/aws-java-sdk-s3-1.10.71.jar
66
+ - classpath/aws-java-sdk-core-1.10.71.jar
67
+ - classpath/embulk-output-s3_per_record-0.1.0.jar
68
+ - classpath/httpcore-4.3.3.jar
69
+ - classpath/aws-java-sdk-kms-1.10.71.jar
70
+ homepage: https://github.com/tomykaira/embulk-output-s3_per_record
71
+ licenses:
72
+ - MIT
73
+ metadata: {}
74
+ post_install_message:
75
+ rdoc_options: []
76
+ require_paths:
77
+ - lib
78
+ required_ruby_version: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - '>='
81
+ - !ruby/object:Gem::Version
82
+ version: '0'
83
+ required_rubygems_version: !ruby/object:Gem::Requirement
84
+ requirements:
85
+ - - '>='
86
+ - !ruby/object:Gem::Version
87
+ version: '0'
88
+ requirements: []
89
+ rubyforge_project:
90
+ rubygems_version: 2.1.9
91
+ signing_key:
92
+ specification_version: 4
93
+ summary: S3 Per Record output plugin for Embulk
94
+ test_files: []