embulk-output-s3 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +11 -0
- data/LICENSE.txt +21 -0
- data/README.md +39 -0
- data/build.gradle +56 -0
- data/classpath/aws-java-sdk-core-1.9.24.jar +0 -0
- data/classpath/aws-java-sdk-kms-1.9.24.jar +0 -0
- data/classpath/aws-java-sdk-s3-1.9.24.jar +0 -0
- data/classpath/commons-codec-1.6.jar +0 -0
- data/classpath/commons-logging-1.1.3.jar +0 -0
- data/classpath/embulk-output-s3-0.1.0.jar +0 -0
- data/classpath/httpclient-4.3.4.jar +0 -0
- data/classpath/httpcore-4.3.2.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +164 -0
- data/gradlew.bat +90 -0
- data/lib/embulk/output/s3.rb +3 -0
- data/src/main/java/org/embulk/output/S3FileOutputPlugin.java +258 -0
- data/src/test/java/org/embulk/output/TestS3FileOutputPlugin.java +5 -0
- metadata +91 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: ec5fe08d2ad38fad94f03679479e3653cfac20cb
|
4
|
+
data.tar.gz: 6d363a602b57f9b9315b68a16602ca6a0af294c6
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: bd0d1aa10571f12e130040a5073a5b7fcc649576f81f5bb83f8f32e12aba031fa56061a8c78d1308cf52445921e50754ab4490ffae2cdfa0dd49a3990003247e
|
7
|
+
data.tar.gz: df38d944942edb611ff64ac85a243246a61c31ab03350baa811fd3f91fef77cc3f77b3024860f8ed9c73b4415b12c4aeb8ccf345e93f05db316cf8021de0e6f6
|
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 +1,39 @@
|
|
1
|
+
# S3 file output plugin for Embulk
|
2
|
+
|
3
|
+
## Overview
|
4
|
+
|
5
|
+
* **Plugin type**: file output
|
6
|
+
* **Load all or nothing**: no
|
7
|
+
* **Resume supported**: yes
|
8
|
+
* **Cleanup supported**: yes
|
9
|
+
|
10
|
+
## Configuration
|
11
|
+
|
12
|
+
- **path_prefix**: prefix of target keys (string, required)
|
13
|
+
- **file_ext**: suffix of target keys (string, required)
|
14
|
+
- **sequence_format**: format for sequence part of target keys (string, default: '.%03d.%02d')
|
15
|
+
- **bucket**: S3 bucket name (string, required)
|
16
|
+
- **endpoint**: S3 endpoint login user name (string, optional)
|
17
|
+
- **access_key_id**: AWS access key id (string, required)
|
18
|
+
- **secret_access_key**: AWS secret key (string, required)
|
19
|
+
- **tmp_path_prefix**: prefix of temporary files (string, defualt: 'embulk-output-s3-')
|
20
|
+
|
21
|
+
## Example
|
22
|
+
|
23
|
+
```yaml
|
24
|
+
path_prefix: logs/out
|
25
|
+
file_ext: .csv
|
26
|
+
bucket: my-s3-bucket
|
27
|
+
endpoint: s3-us-west-1.amazonaws.com
|
28
|
+
access_key_id: ABCXYZ123ABCXYZ123
|
29
|
+
secret_access_key: AbCxYz123aBcXyZ123
|
30
|
+
formatter:
|
31
|
+
type: csv
|
32
|
+
```
|
33
|
+
|
34
|
+
|
35
|
+
## Build
|
36
|
+
|
37
|
+
```
|
38
|
+
$ ./gradlew gem
|
39
|
+
```
|
data/build.gradle
ADDED
@@ -0,0 +1,56 @@
|
|
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
|
+
}
|
6
|
+
import com.github.jrubygradle.JRubyExec
|
7
|
+
repositories {
|
8
|
+
mavenCentral()
|
9
|
+
jcenter()
|
10
|
+
}
|
11
|
+
configurations {
|
12
|
+
provided
|
13
|
+
}
|
14
|
+
|
15
|
+
version = "0.1.0"
|
16
|
+
|
17
|
+
dependencies {
|
18
|
+
compile "org.embulk:embulk-core:0.5.2"
|
19
|
+
provided "org.embulk:embulk-core:0.5.2"
|
20
|
+
compile "com.amazonaws:aws-java-sdk-s3:1.9.24"
|
21
|
+
testCompile "junit:junit:4.+"
|
22
|
+
}
|
23
|
+
|
24
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
25
|
+
doFirst { file("classpath").deleteDir() }
|
26
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
27
|
+
into "classpath"
|
28
|
+
}
|
29
|
+
clean { delete 'classpath' }
|
30
|
+
|
31
|
+
task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
|
32
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
33
|
+
script "build/gemspec"
|
34
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
35
|
+
}
|
36
|
+
|
37
|
+
task gemspec << { file("build/gemspec").write($/
|
38
|
+
Gem::Specification.new do |spec|
|
39
|
+
spec.name = "${project.name}"
|
40
|
+
spec.version = "${project.version}"
|
41
|
+
spec.authors = ["Manabu Takayama"]
|
42
|
+
spec.summary = %[S3 file output plugin for Embulk]
|
43
|
+
spec.description = %["Stores files on S3."]
|
44
|
+
spec.email = ["learn.libra@gmail.com"]
|
45
|
+
spec.licenses = ["MIT"]
|
46
|
+
spec.homepage = "https://github.com/llibra/embulk-output-s3"
|
47
|
+
|
48
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
49
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
50
|
+
spec.require_paths = ["lib"]
|
51
|
+
|
52
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
53
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
54
|
+
end
|
55
|
+
/$)
|
56
|
+
}
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
data/gradlew
ADDED
@@ -0,0 +1,164 @@
|
|
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
|
+
# For Cygwin, ensure paths are in UNIX format before anything is touched.
|
46
|
+
if $cygwin ; then
|
47
|
+
[ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
|
48
|
+
fi
|
49
|
+
|
50
|
+
# Attempt to set APP_HOME
|
51
|
+
# Resolve links: $0 may be a link
|
52
|
+
PRG="$0"
|
53
|
+
# Need this for relative symlinks.
|
54
|
+
while [ -h "$PRG" ] ; do
|
55
|
+
ls=`ls -ld "$PRG"`
|
56
|
+
link=`expr "$ls" : '.*-> \(.*\)$'`
|
57
|
+
if expr "$link" : '/.*' > /dev/null; then
|
58
|
+
PRG="$link"
|
59
|
+
else
|
60
|
+
PRG=`dirname "$PRG"`"/$link"
|
61
|
+
fi
|
62
|
+
done
|
63
|
+
SAVED="`pwd`"
|
64
|
+
cd "`dirname \"$PRG\"`/" >&-
|
65
|
+
APP_HOME="`pwd -P`"
|
66
|
+
cd "$SAVED" >&-
|
67
|
+
|
68
|
+
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
|
69
|
+
|
70
|
+
# Determine the Java command to use to start the JVM.
|
71
|
+
if [ -n "$JAVA_HOME" ] ; then
|
72
|
+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
|
73
|
+
# IBM's JDK on AIX uses strange locations for the executables
|
74
|
+
JAVACMD="$JAVA_HOME/jre/sh/java"
|
75
|
+
else
|
76
|
+
JAVACMD="$JAVA_HOME/bin/java"
|
77
|
+
fi
|
78
|
+
if [ ! -x "$JAVACMD" ] ; then
|
79
|
+
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
|
80
|
+
|
81
|
+
Please set the JAVA_HOME variable in your environment to match the
|
82
|
+
location of your Java installation."
|
83
|
+
fi
|
84
|
+
else
|
85
|
+
JAVACMD="java"
|
86
|
+
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
|
87
|
+
|
88
|
+
Please set the JAVA_HOME variable in your environment to match the
|
89
|
+
location of your Java installation."
|
90
|
+
fi
|
91
|
+
|
92
|
+
# Increase the maximum file descriptors if we can.
|
93
|
+
if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
|
94
|
+
MAX_FD_LIMIT=`ulimit -H -n`
|
95
|
+
if [ $? -eq 0 ] ; then
|
96
|
+
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
|
97
|
+
MAX_FD="$MAX_FD_LIMIT"
|
98
|
+
fi
|
99
|
+
ulimit -n $MAX_FD
|
100
|
+
if [ $? -ne 0 ] ; then
|
101
|
+
warn "Could not set maximum file descriptor limit: $MAX_FD"
|
102
|
+
fi
|
103
|
+
else
|
104
|
+
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
|
105
|
+
fi
|
106
|
+
fi
|
107
|
+
|
108
|
+
# For Darwin, add options to specify how the application appears in the dock
|
109
|
+
if $darwin; then
|
110
|
+
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
|
111
|
+
fi
|
112
|
+
|
113
|
+
# For Cygwin, switch paths to Windows format before running java
|
114
|
+
if $cygwin ; then
|
115
|
+
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
|
116
|
+
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
|
117
|
+
|
118
|
+
# We build the pattern for arguments to be converted via cygpath
|
119
|
+
ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
|
120
|
+
SEP=""
|
121
|
+
for dir in $ROOTDIRSRAW ; do
|
122
|
+
ROOTDIRS="$ROOTDIRS$SEP$dir"
|
123
|
+
SEP="|"
|
124
|
+
done
|
125
|
+
OURCYGPATTERN="(^($ROOTDIRS))"
|
126
|
+
# Add a user-defined pattern to the cygpath arguments
|
127
|
+
if [ "$GRADLE_CYGPATTERN" != "" ] ; then
|
128
|
+
OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
|
129
|
+
fi
|
130
|
+
# Now convert the arguments - kludge to limit ourselves to /bin/sh
|
131
|
+
i=0
|
132
|
+
for arg in "$@" ; do
|
133
|
+
CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
|
134
|
+
CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
|
135
|
+
|
136
|
+
if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
|
137
|
+
eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
|
138
|
+
else
|
139
|
+
eval `echo args$i`="\"$arg\""
|
140
|
+
fi
|
141
|
+
i=$((i+1))
|
142
|
+
done
|
143
|
+
case $i in
|
144
|
+
(0) set -- ;;
|
145
|
+
(1) set -- "$args0" ;;
|
146
|
+
(2) set -- "$args0" "$args1" ;;
|
147
|
+
(3) set -- "$args0" "$args1" "$args2" ;;
|
148
|
+
(4) set -- "$args0" "$args1" "$args2" "$args3" ;;
|
149
|
+
(5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
|
150
|
+
(6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
|
151
|
+
(7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
|
152
|
+
(8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
|
153
|
+
(9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
|
154
|
+
esac
|
155
|
+
fi
|
156
|
+
|
157
|
+
# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
|
158
|
+
function splitJvmOpts() {
|
159
|
+
JVM_OPTS=("$@")
|
160
|
+
}
|
161
|
+
eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
|
162
|
+
JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
|
163
|
+
|
164
|
+
exec "$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 +1,258 @@
|
|
1
|
+
package org.embulk.output;
|
2
|
+
|
3
|
+
import java.io.IOException;
|
4
|
+
import java.io.OutputStream;
|
5
|
+
import java.nio.file.Files;
|
6
|
+
import java.nio.file.Path;
|
7
|
+
import java.util.IllegalFormatException;
|
8
|
+
import java.util.List;
|
9
|
+
import java.util.Locale;
|
10
|
+
|
11
|
+
import org.embulk.config.CommitReport;
|
12
|
+
import org.embulk.config.Config;
|
13
|
+
import org.embulk.config.ConfigDefault;
|
14
|
+
import org.embulk.config.ConfigDiff;
|
15
|
+
import org.embulk.config.ConfigException;
|
16
|
+
import org.embulk.config.ConfigSource;
|
17
|
+
import org.embulk.config.Task;
|
18
|
+
import org.embulk.config.TaskSource;
|
19
|
+
import org.embulk.spi.Buffer;
|
20
|
+
import org.embulk.spi.Exec;
|
21
|
+
import org.embulk.spi.FileOutput;
|
22
|
+
import org.embulk.spi.FileOutputPlugin;
|
23
|
+
import org.embulk.spi.TransactionalFileOutput;
|
24
|
+
import org.slf4j.Logger;
|
25
|
+
|
26
|
+
import com.amazonaws.ClientConfiguration;
|
27
|
+
import com.amazonaws.auth.AWSCredentials;
|
28
|
+
import com.amazonaws.auth.AWSCredentialsProvider;
|
29
|
+
import com.amazonaws.auth.BasicAWSCredentials;
|
30
|
+
import com.amazonaws.services.s3.AmazonS3Client;
|
31
|
+
import com.amazonaws.services.s3.model.PutObjectRequest;
|
32
|
+
|
33
|
+
public class S3FileOutputPlugin implements FileOutputPlugin {
|
34
|
+
public interface PluginTask extends Task {
|
35
|
+
@Config("path_prefix")
|
36
|
+
public String getPathPrefix();
|
37
|
+
|
38
|
+
@Config("file_ext")
|
39
|
+
public String getFileNameExtension();
|
40
|
+
|
41
|
+
@Config("sequence_format")
|
42
|
+
@ConfigDefault("\".%03d.%02d\"")
|
43
|
+
public String getSequenceFormat();
|
44
|
+
|
45
|
+
@Config("bucket")
|
46
|
+
public String getBucket();
|
47
|
+
|
48
|
+
@Config("endpoint")
|
49
|
+
public String getEndpoint();
|
50
|
+
|
51
|
+
@Config("access_key_id")
|
52
|
+
public String getAccessKeyId();
|
53
|
+
|
54
|
+
@Config("secret_access_key")
|
55
|
+
public String getSecretAccessKey();
|
56
|
+
|
57
|
+
@Config("tmp_path_prefix")
|
58
|
+
@ConfigDefault("\"embulk-output-s3-\"")
|
59
|
+
public String getTempPathPrefix();
|
60
|
+
}
|
61
|
+
|
62
|
+
public static class S3FileOutput implements FileOutput,
|
63
|
+
TransactionalFileOutput {
|
64
|
+
private final Logger log = Exec.getLogger(S3FileOutputPlugin.class);
|
65
|
+
|
66
|
+
private final String bucket;
|
67
|
+
private final String pathPrefix;
|
68
|
+
private final String sequenceFormat;
|
69
|
+
private final String fileNameExtension;
|
70
|
+
private final String tempPathPrefix;
|
71
|
+
|
72
|
+
private int taskIndex;
|
73
|
+
private int fileIndex;
|
74
|
+
private AmazonS3Client client;
|
75
|
+
private OutputStream current;
|
76
|
+
private Path tempFilePath;
|
77
|
+
|
78
|
+
public static AWSCredentialsProvider getCredentialsProvider(
|
79
|
+
PluginTask task) {
|
80
|
+
final AWSCredentials cred = new BasicAWSCredentials(
|
81
|
+
task.getAccessKeyId(), task.getSecretAccessKey());
|
82
|
+
return new AWSCredentialsProvider() {
|
83
|
+
@Override
|
84
|
+
public AWSCredentials getCredentials() {
|
85
|
+
return cred;
|
86
|
+
}
|
87
|
+
|
88
|
+
@Override
|
89
|
+
public void refresh() {
|
90
|
+
}
|
91
|
+
};
|
92
|
+
}
|
93
|
+
|
94
|
+
private static AmazonS3Client newS3Client(PluginTask task) {
|
95
|
+
AWSCredentialsProvider credentials = getCredentialsProvider(task);
|
96
|
+
|
97
|
+
ClientConfiguration config = new ClientConfiguration();
|
98
|
+
// TODO: Support more configurations.
|
99
|
+
|
100
|
+
AmazonS3Client client = new AmazonS3Client(credentials, config);
|
101
|
+
client.setEndpoint(task.getEndpoint());
|
102
|
+
|
103
|
+
return client;
|
104
|
+
}
|
105
|
+
|
106
|
+
public S3FileOutput(PluginTask task, int taskIndex) {
|
107
|
+
this.taskIndex = taskIndex;
|
108
|
+
this.client = newS3Client(task);
|
109
|
+
this.bucket = task.getBucket();
|
110
|
+
this.pathPrefix = task.getPathPrefix();
|
111
|
+
this.sequenceFormat = task.getSequenceFormat();
|
112
|
+
this.fileNameExtension = task.getFileNameExtension();
|
113
|
+
this.tempPathPrefix = task.getTempPathPrefix();
|
114
|
+
}
|
115
|
+
|
116
|
+
private static Path newTempFile(String prefix) throws IOException {
|
117
|
+
return Files.createTempFile(prefix, null);
|
118
|
+
}
|
119
|
+
|
120
|
+
private void deleteTempFile() {
|
121
|
+
if (tempFilePath == null) {
|
122
|
+
return;
|
123
|
+
}
|
124
|
+
|
125
|
+
try {
|
126
|
+
Files.delete(tempFilePath);
|
127
|
+
tempFilePath = null;
|
128
|
+
} catch (IOException e) {
|
129
|
+
throw new RuntimeException(e);
|
130
|
+
}
|
131
|
+
}
|
132
|
+
|
133
|
+
private String buildCurrentKey() {
|
134
|
+
String sequence = String.format(sequenceFormat, taskIndex,
|
135
|
+
fileIndex);
|
136
|
+
return pathPrefix + sequence + fileNameExtension;
|
137
|
+
}
|
138
|
+
|
139
|
+
private void putFile(Path from, String key) {
|
140
|
+
PutObjectRequest request = new PutObjectRequest(bucket, key,
|
141
|
+
from.toFile());
|
142
|
+
client.putObject(request);
|
143
|
+
}
|
144
|
+
|
145
|
+
private void closeCurrent() {
|
146
|
+
if (current == null) {
|
147
|
+
return;
|
148
|
+
}
|
149
|
+
|
150
|
+
try {
|
151
|
+
putFile(tempFilePath, buildCurrentKey());
|
152
|
+
fileIndex++;
|
153
|
+
} finally {
|
154
|
+
try {
|
155
|
+
current.close();
|
156
|
+
current = null;
|
157
|
+
} catch (IOException e) {
|
158
|
+
throw new RuntimeException(e);
|
159
|
+
} finally {
|
160
|
+
deleteTempFile();
|
161
|
+
}
|
162
|
+
}
|
163
|
+
}
|
164
|
+
|
165
|
+
@Override
|
166
|
+
public void nextFile() {
|
167
|
+
closeCurrent();
|
168
|
+
|
169
|
+
try {
|
170
|
+
tempFilePath = newTempFile(tempPathPrefix);
|
171
|
+
|
172
|
+
log.info("Writing S3 file '{}'", buildCurrentKey());
|
173
|
+
|
174
|
+
current = Files.newOutputStream(tempFilePath);
|
175
|
+
} catch (IOException e) {
|
176
|
+
throw new RuntimeException(e);
|
177
|
+
}
|
178
|
+
}
|
179
|
+
|
180
|
+
@Override
|
181
|
+
public void add(Buffer buffer) {
|
182
|
+
if (current == null) {
|
183
|
+
throw new IllegalStateException(
|
184
|
+
"nextFile() must be called before poll()");
|
185
|
+
}
|
186
|
+
|
187
|
+
try {
|
188
|
+
current.write(buffer.array(), buffer.offset(), buffer.limit());
|
189
|
+
} catch (IOException ex) {
|
190
|
+
throw new RuntimeException(ex);
|
191
|
+
} finally {
|
192
|
+
buffer.release();
|
193
|
+
}
|
194
|
+
}
|
195
|
+
|
196
|
+
@Override
|
197
|
+
public void finish() {
|
198
|
+
closeCurrent();
|
199
|
+
}
|
200
|
+
|
201
|
+
@Override
|
202
|
+
public void close() {
|
203
|
+
closeCurrent();
|
204
|
+
}
|
205
|
+
|
206
|
+
@Override
|
207
|
+
public void abort() {
|
208
|
+
deleteTempFile();
|
209
|
+
}
|
210
|
+
|
211
|
+
@Override
|
212
|
+
public CommitReport commit() {
|
213
|
+
CommitReport report = Exec.newCommitReport();
|
214
|
+
return report;
|
215
|
+
}
|
216
|
+
}
|
217
|
+
|
218
|
+
private void validateSequenceFormat(PluginTask task) {
|
219
|
+
try {
|
220
|
+
@SuppressWarnings("unused")
|
221
|
+
String dontCare = String.format(Locale.ENGLISH,
|
222
|
+
task.getSequenceFormat(), 0, 0);
|
223
|
+
} catch (IllegalFormatException ex) {
|
224
|
+
throw new ConfigException(
|
225
|
+
"Invalid sequence_format: parameter for file output plugin",
|
226
|
+
ex);
|
227
|
+
}
|
228
|
+
}
|
229
|
+
|
230
|
+
@Override
|
231
|
+
public ConfigDiff transaction(ConfigSource config, int taskCount,
|
232
|
+
Control control) {
|
233
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
234
|
+
|
235
|
+
validateSequenceFormat(task);
|
236
|
+
|
237
|
+
return resume(task.dump(), taskCount, control);
|
238
|
+
}
|
239
|
+
|
240
|
+
@Override
|
241
|
+
public ConfigDiff resume(TaskSource taskSource, int taskCount,
|
242
|
+
Control control) {
|
243
|
+
control.run(taskSource);
|
244
|
+
return Exec.newConfigDiff();
|
245
|
+
}
|
246
|
+
|
247
|
+
@Override
|
248
|
+
public void cleanup(TaskSource taskSource, int taskCount,
|
249
|
+
List<CommitReport> successCommitReports) {
|
250
|
+
}
|
251
|
+
|
252
|
+
@Override
|
253
|
+
public TransactionalFileOutput open(TaskSource taskSource, int taskIndex) {
|
254
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
255
|
+
|
256
|
+
return new S3FileOutput(task, taskIndex);
|
257
|
+
}
|
258
|
+
}
|
metadata
ADDED
@@ -0,0 +1,91 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-output-s3
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Manabu Takayama
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-03-15 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
version_requirements: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.0'
|
20
|
+
requirement: !ruby/object:Gem::Requirement
|
21
|
+
requirements:
|
22
|
+
- - ~>
|
23
|
+
- !ruby/object:Gem::Version
|
24
|
+
version: '1.0'
|
25
|
+
prerelease: false
|
26
|
+
type: :development
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
requirement: !ruby/object:Gem::Requirement
|
35
|
+
requirements:
|
36
|
+
- - '>='
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '10.0'
|
39
|
+
prerelease: false
|
40
|
+
type: :development
|
41
|
+
description: '"Stores files on S3."'
|
42
|
+
email:
|
43
|
+
- learn.libra@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- .gitignore
|
49
|
+
- LICENSE.txt
|
50
|
+
- README.md
|
51
|
+
- build.gradle
|
52
|
+
- gradle/wrapper/gradle-wrapper.jar
|
53
|
+
- gradle/wrapper/gradle-wrapper.properties
|
54
|
+
- gradlew
|
55
|
+
- gradlew.bat
|
56
|
+
- lib/embulk/output/s3.rb
|
57
|
+
- src/main/java/org/embulk/output/S3FileOutputPlugin.java
|
58
|
+
- src/test/java/org/embulk/output/TestS3FileOutputPlugin.java
|
59
|
+
- classpath/aws-java-sdk-core-1.9.24.jar
|
60
|
+
- classpath/aws-java-sdk-kms-1.9.24.jar
|
61
|
+
- classpath/aws-java-sdk-s3-1.9.24.jar
|
62
|
+
- classpath/commons-codec-1.6.jar
|
63
|
+
- classpath/commons-logging-1.1.3.jar
|
64
|
+
- classpath/embulk-output-s3-0.1.0.jar
|
65
|
+
- classpath/httpclient-4.3.4.jar
|
66
|
+
- classpath/httpcore-4.3.2.jar
|
67
|
+
homepage: https://github.com/llibra/embulk-output-s3
|
68
|
+
licenses:
|
69
|
+
- MIT
|
70
|
+
metadata: {}
|
71
|
+
post_install_message:
|
72
|
+
rdoc_options: []
|
73
|
+
require_paths:
|
74
|
+
- lib
|
75
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
76
|
+
requirements:
|
77
|
+
- - '>='
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - '>='
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
requirements: []
|
86
|
+
rubyforge_project:
|
87
|
+
rubygems_version: 2.1.9
|
88
|
+
signing_key:
|
89
|
+
specification_version: 4
|
90
|
+
summary: S3 file output plugin for Embulk
|
91
|
+
test_files: []
|