embulk-encoder-commons-compress 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 +7 -0
- data/LICENSE.txt +22 -0
- data/README.md +33 -0
- data/build.gradle +63 -0
- data/classpath/commons-compress-1.9.jar +0 -0
- data/classpath/embulk-encoder-commons-compress-0.1.0.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/encoder/commons-compress.rb +3 -0
- data/src/main/java/org/embulk/encoder/CommonsCompressArchiveProvider.java +139 -0
- data/src/main/java/org/embulk/encoder/CommonsCompressCompressorProvider.java +74 -0
- data/src/main/java/org/embulk/encoder/CommonsCompressEncoderPlugin.java +51 -0
- data/src/test/java/org/embulk/encoder/TestCommonsCompressEncoderPlugin.java +5 -0
- metadata +87 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 23a1109315cf57fbdf2ffde3d4eec038d0dbea18
|
4
|
+
data.tar.gz: 391ee97d553804487bee7e5421dc1cef952bb99d
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 789058ac973dfcb777cf0216bacf107dc27a92dcb2016a2fdc190095b5c5295a0e57ba26f6f7f8b83a4e2a96471a2cba479c497830641d91be0a46f2294dcd2c
|
7
|
+
data.tar.gz: 43e265e8be8e80bccabcf032f964f8cbea0fdeefa1c898730e344ff3e0a9931c57f6310c900bd00e919cc67ce2c8d9089045c40bd91d67351709393666d13c26
|
data/.gitignore
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright(C) 2015 Hiroki Ata
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
# Commons Compress Encoder plugin for Embulk
|
2
|
+
|
3
|
+
This encoder plugin supports to encode a format like bzip2 and gzip.
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: encoder
|
8
|
+
* **Load all or nothing**: yes
|
9
|
+
* **Resume supported**: no
|
10
|
+
|
11
|
+
## Configuration
|
12
|
+
|
13
|
+
- **format**: File format like bzip2, gzip (string, required)
|
14
|
+
|
15
|
+
## Example
|
16
|
+
|
17
|
+
```yaml
|
18
|
+
out:
|
19
|
+
type: file
|
20
|
+
path_prefix: any path
|
21
|
+
file_ext: .csv.bz2
|
22
|
+
formatter:
|
23
|
+
type: csv
|
24
|
+
encoders:
|
25
|
+
- type: commons-compress
|
26
|
+
format: bzip2
|
27
|
+
```
|
28
|
+
|
29
|
+
## Build
|
30
|
+
|
31
|
+
```
|
32
|
+
$ ./gradlew gem
|
33
|
+
```
|
data/build.gradle
ADDED
@@ -0,0 +1,63 @@
|
|
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
|
+
|
8
|
+
sourceCompatibility = '1.7'
|
9
|
+
targetCompatibility = '1.7'
|
10
|
+
|
11
|
+
repositories {
|
12
|
+
mavenCentral()
|
13
|
+
jcenter()
|
14
|
+
}
|
15
|
+
configurations {
|
16
|
+
provided
|
17
|
+
}
|
18
|
+
|
19
|
+
version = "0.1.0"
|
20
|
+
|
21
|
+
dependencies {
|
22
|
+
compile "org.embulk:embulk-core:0.4.6"
|
23
|
+
compile "org.apache.commons:commons-compress:1.9"
|
24
|
+
provided "org.embulk:embulk-core:0.4.6"
|
25
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
26
|
+
testCompile "org.jmockit:jmockit:1.15"
|
27
|
+
testCompile "junit:junit:4.+"
|
28
|
+
}
|
29
|
+
|
30
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
31
|
+
doFirst { file("classpath").deleteDir() }
|
32
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
33
|
+
into "classpath"
|
34
|
+
}
|
35
|
+
clean { delete 'classpath' }
|
36
|
+
|
37
|
+
task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
|
38
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
39
|
+
script "build/gemspec"
|
40
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
41
|
+
}
|
42
|
+
|
43
|
+
task gemspec << { file("build/gemspec").write($/
|
44
|
+
Gem::Specification.new do |spec|
|
45
|
+
spec.name = "${project.name}"
|
46
|
+
spec.version = "${project.version}"
|
47
|
+
spec.authors = ["hata"]
|
48
|
+
spec.summary = %[Commons Compress encoder plugin for Embulk]
|
49
|
+
spec.description = %[Commons Compress encoder plugin is an Embulk plugin that encodes files using Commons Compress so that any file output plugins can store the files. Search the file output plugins by 'embulk-output file' keywords.]
|
50
|
+
spec.email = ["hiroki.ata@gmail.com"]
|
51
|
+
spec.licenses = ["MIT"]
|
52
|
+
spec.homepage = "https://github.com/hata/embulk-encoder-commons-compress"
|
53
|
+
|
54
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
55
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
56
|
+
spec.require_paths = ["lib"]
|
57
|
+
|
58
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
59
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
60
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
61
|
+
end
|
62
|
+
/$)
|
63
|
+
}
|
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 +1,139 @@
|
|
1
|
+
package org.embulk.encoder;
|
2
|
+
|
3
|
+
import java.io.ByteArrayOutputStream;
|
4
|
+
import java.io.IOException;
|
5
|
+
import java.io.OutputStream;
|
6
|
+
import java.util.concurrent.atomic.AtomicInteger;
|
7
|
+
|
8
|
+
import org.apache.commons.compress.archivers.ArchiveEntry;
|
9
|
+
import org.apache.commons.compress.archivers.ArchiveOutputStream;
|
10
|
+
import org.apache.commons.compress.archivers.cpio.CpioArchiveEntry;
|
11
|
+
import org.apache.commons.compress.archivers.cpio.CpioArchiveOutputStream;
|
12
|
+
import org.apache.commons.compress.archivers.jar.JarArchiveEntry;
|
13
|
+
import org.apache.commons.compress.archivers.jar.JarArchiveOutputStream;
|
14
|
+
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
|
15
|
+
import org.apache.commons.compress.archivers.tar.TarArchiveOutputStream;
|
16
|
+
import org.apache.commons.compress.archivers.zip.ZipArchiveEntry;
|
17
|
+
import org.apache.commons.compress.archivers.zip.ZipArchiveOutputStream;
|
18
|
+
import org.embulk.encoder.CommonsCompressEncoderPlugin.PluginTask;
|
19
|
+
import org.embulk.spi.FileOutput;
|
20
|
+
import org.embulk.spi.util.FileOutputOutputStream;
|
21
|
+
import org.embulk.spi.util.OutputStreamFileOutput;
|
22
|
+
|
23
|
+
class CommonsCompressArchiveProvider implements OutputStreamFileOutput.Provider {
|
24
|
+
private enum ArchiveFormat {
|
25
|
+
CPIO, JAR, TAR, ZIP;
|
26
|
+
|
27
|
+
static ArchiveFormat toArchiveFormat(String format) {
|
28
|
+
return ArchiveFormat.valueOf(format.toUpperCase());
|
29
|
+
}
|
30
|
+
}
|
31
|
+
|
32
|
+
private static final AtomicInteger baseNumSeq = new AtomicInteger(-1);
|
33
|
+
|
34
|
+
private final ArchiveFormat format;
|
35
|
+
private final FileOutput underlyingFileOutput;
|
36
|
+
private final FileOutputOutputStream output;
|
37
|
+
private final String entryNamePrefix;
|
38
|
+
private final int baseNum;
|
39
|
+
private int count;
|
40
|
+
private ArchiveOutputStream archiveOut;
|
41
|
+
|
42
|
+
// NOTE: ArchiveEntry should set size to put data. This may use much memory.
|
43
|
+
// So, this is not good.
|
44
|
+
private ByteArrayOutputStream tmpOut;
|
45
|
+
|
46
|
+
static boolean isArchiveFormat(String format) {
|
47
|
+
try {
|
48
|
+
return ArchiveFormat.toArchiveFormat(format) != null;
|
49
|
+
} catch (Throwable t) {
|
50
|
+
// Any exceptions are false.
|
51
|
+
return false;
|
52
|
+
}
|
53
|
+
}
|
54
|
+
|
55
|
+
CommonsCompressArchiveProvider(PluginTask task, FileOutput fileOutput) {
|
56
|
+
this.format = ArchiveFormat.toArchiveFormat(task.getFormat());
|
57
|
+
this.underlyingFileOutput = fileOutput;
|
58
|
+
this.output = new FileOutputOutputStream(fileOutput, task.getBufferAllocator(), FileOutputOutputStream.CloseMode.FLUSH);
|
59
|
+
this.entryNamePrefix = task.getPrefix();
|
60
|
+
this.baseNum = baseNumSeq.incrementAndGet();
|
61
|
+
}
|
62
|
+
|
63
|
+
@Override
|
64
|
+
public OutputStream openNext() throws IOException {
|
65
|
+
output.nextFile();
|
66
|
+
return tmpOut = new ByteArrayOutputStream();
|
67
|
+
}
|
68
|
+
|
69
|
+
@Override
|
70
|
+
public void finish() throws IOException {
|
71
|
+
if (tmpOut != null) {
|
72
|
+
archiveOut = createArchiveOutputStream();
|
73
|
+
archiveOut.putArchiveEntry(createEntry(tmpOut.size()));
|
74
|
+
archiveOut.write(tmpOut.toByteArray());
|
75
|
+
archiveOut.closeArchiveEntry();
|
76
|
+
archiveOut.finish();
|
77
|
+
tmpOut = null;
|
78
|
+
}
|
79
|
+
}
|
80
|
+
|
81
|
+
@Override
|
82
|
+
public void close() throws IOException {
|
83
|
+
if (tmpOut != null) {
|
84
|
+
finish();
|
85
|
+
}
|
86
|
+
if (archiveOut != null) {
|
87
|
+
archiveOut.close();
|
88
|
+
archiveOut = null;
|
89
|
+
}
|
90
|
+
underlyingFileOutput.close();
|
91
|
+
}
|
92
|
+
|
93
|
+
ArchiveOutputStream createArchiveOutputStream() throws IOException {
|
94
|
+
switch (format) {
|
95
|
+
case CPIO:
|
96
|
+
return new CpioArchiveOutputStream(output);
|
97
|
+
case JAR:
|
98
|
+
return new JarArchiveOutputStream(output);
|
99
|
+
case TAR:
|
100
|
+
return new TarArchiveOutputStream(output);
|
101
|
+
case ZIP:
|
102
|
+
return new ZipArchiveOutputStream(output);
|
103
|
+
}
|
104
|
+
|
105
|
+
// Normally, this code is not called because of the above switch.
|
106
|
+
throw new IOException("Format is configured.");
|
107
|
+
}
|
108
|
+
|
109
|
+
ArchiveEntry createEntry(long size) throws IOException {
|
110
|
+
// TODO: How to set entry name and indexes.
|
111
|
+
String name = String.format(entryNamePrefix, baseNum, count++);
|
112
|
+
|
113
|
+
switch (format) {
|
114
|
+
case CPIO:
|
115
|
+
CpioArchiveEntry cpioEntry = new CpioArchiveEntry(name);
|
116
|
+
cpioEntry.setSize(size);
|
117
|
+
cpioEntry.setTime(System.currentTimeMillis());
|
118
|
+
return cpioEntry;
|
119
|
+
case JAR:
|
120
|
+
JarArchiveEntry jarEntry = new JarArchiveEntry(name);
|
121
|
+
jarEntry.setSize(size);
|
122
|
+
jarEntry.setTime(System.currentTimeMillis());
|
123
|
+
return jarEntry;
|
124
|
+
case TAR:
|
125
|
+
TarArchiveEntry tarEntry = new TarArchiveEntry(name);
|
126
|
+
tarEntry.setSize(size);
|
127
|
+
tarEntry.setModTime(System.currentTimeMillis());
|
128
|
+
return tarEntry;
|
129
|
+
case ZIP:
|
130
|
+
ZipArchiveEntry zipEntry = new ZipArchiveEntry(name);
|
131
|
+
zipEntry.setSize(size);
|
132
|
+
zipEntry.setTime(System.currentTimeMillis());
|
133
|
+
return zipEntry;
|
134
|
+
}
|
135
|
+
|
136
|
+
// Normally, this code is not called because of the above switch.
|
137
|
+
throw new IOException("Format is configured.");
|
138
|
+
}
|
139
|
+
}
|
@@ -0,0 +1,74 @@
|
|
1
|
+
package org.embulk.encoder;
|
2
|
+
|
3
|
+
import java.io.IOException;
|
4
|
+
import java.io.OutputStream;
|
5
|
+
|
6
|
+
import org.apache.commons.compress.compressors.CompressorOutputStream;
|
7
|
+
import org.apache.commons.compress.compressors.bzip2.BZip2CompressorOutputStream;
|
8
|
+
import org.apache.commons.compress.compressors.deflate.DeflateCompressorOutputStream;
|
9
|
+
import org.apache.commons.compress.compressors.gzip.GzipCompressorOutputStream;
|
10
|
+
import org.embulk.encoder.CommonsCompressEncoderPlugin.PluginTask;
|
11
|
+
import org.embulk.spi.FileOutput;
|
12
|
+
import org.embulk.spi.util.FileOutputOutputStream;
|
13
|
+
import org.embulk.spi.util.OutputStreamFileOutput;
|
14
|
+
|
15
|
+
|
16
|
+
class CommonsCompressCompressorProvider implements OutputStreamFileOutput.Provider {
|
17
|
+
private enum CompressorFormat {
|
18
|
+
BZIP2, DEFLATE, GZIP;
|
19
|
+
|
20
|
+
static CompressorFormat toCompressorFormat(String format) {
|
21
|
+
return CompressorFormat.valueOf(format.toUpperCase());
|
22
|
+
}
|
23
|
+
}
|
24
|
+
|
25
|
+
private final CompressorFormat format;
|
26
|
+
private final FileOutput underlyingFileOutput;
|
27
|
+
private final FileOutputOutputStream output;
|
28
|
+
|
29
|
+
static boolean isCompressorFormat(String format) {
|
30
|
+
try {
|
31
|
+
return CompressorFormat.toCompressorFormat(format) != null;
|
32
|
+
} catch (Throwable ignore) {
|
33
|
+
// All exceptions are not compressor format.
|
34
|
+
return false;
|
35
|
+
}
|
36
|
+
}
|
37
|
+
|
38
|
+
CommonsCompressCompressorProvider(PluginTask task, FileOutput fileOutput) {
|
39
|
+
this.format = CompressorFormat.toCompressorFormat(task.getFormat());
|
40
|
+
this.underlyingFileOutput = fileOutput;
|
41
|
+
this.output = new FileOutputOutputStream(fileOutput, task.getBufferAllocator(), FileOutputOutputStream.CloseMode.FLUSH);
|
42
|
+
}
|
43
|
+
|
44
|
+
@Override
|
45
|
+
public OutputStream openNext() throws IOException {
|
46
|
+
output.nextFile();
|
47
|
+
return createCompressorOutputStream();
|
48
|
+
}
|
49
|
+
|
50
|
+
@Override
|
51
|
+
public void finish() throws IOException {
|
52
|
+
output.finish();
|
53
|
+
}
|
54
|
+
|
55
|
+
@Override
|
56
|
+
public void close() throws IOException {
|
57
|
+
output.close();
|
58
|
+
underlyingFileOutput.close();
|
59
|
+
}
|
60
|
+
|
61
|
+
CompressorOutputStream createCompressorOutputStream() throws IOException {
|
62
|
+
switch (format) {
|
63
|
+
case BZIP2:
|
64
|
+
return new BZip2CompressorOutputStream(output);
|
65
|
+
case DEFLATE:
|
66
|
+
return new DeflateCompressorOutputStream(output);
|
67
|
+
case GZIP:
|
68
|
+
return new GzipCompressorOutputStream(output);
|
69
|
+
}
|
70
|
+
|
71
|
+
// Normally, this exception is not thrown.
|
72
|
+
throw new IOException("Unknown format found.");
|
73
|
+
}
|
74
|
+
}
|
@@ -0,0 +1,51 @@
|
|
1
|
+
package org.embulk.encoder;
|
2
|
+
|
3
|
+
import org.embulk.config.Config;
|
4
|
+
import org.embulk.config.ConfigDefault;
|
5
|
+
import org.embulk.config.ConfigInject;
|
6
|
+
import org.embulk.config.ConfigSource;
|
7
|
+
import org.embulk.config.Task;
|
8
|
+
import org.embulk.config.TaskSource;
|
9
|
+
import org.embulk.spi.BufferAllocator;
|
10
|
+
import org.embulk.spi.EncoderPlugin;
|
11
|
+
import org.embulk.spi.FileOutput;
|
12
|
+
import org.embulk.spi.util.OutputStreamFileOutput;
|
13
|
+
|
14
|
+
public class CommonsCompressEncoderPlugin
|
15
|
+
implements EncoderPlugin
|
16
|
+
{
|
17
|
+
public interface PluginTask extends Task {
|
18
|
+
@Config("format")
|
19
|
+
public String getFormat();
|
20
|
+
|
21
|
+
@Config("prefix")
|
22
|
+
@ConfigDefault("\"result.%1$03d.%1$03d\"")
|
23
|
+
public String getPrefix();
|
24
|
+
|
25
|
+
@ConfigInject
|
26
|
+
public BufferAllocator getBufferAllocator();
|
27
|
+
}
|
28
|
+
|
29
|
+
@Override
|
30
|
+
public void transaction(ConfigSource config, EncoderPlugin.Control control) {
|
31
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
32
|
+
control.run(task.dump());
|
33
|
+
}
|
34
|
+
|
35
|
+
@Override
|
36
|
+
public FileOutput open(TaskSource taskSource, final FileOutput fileOutput) {
|
37
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
38
|
+
return new OutputStreamFileOutput(createProvider(task, fileOutput));
|
39
|
+
}
|
40
|
+
|
41
|
+
OutputStreamFileOutput.Provider createProvider(PluginTask task, FileOutput output) {
|
42
|
+
String format = task.getFormat();
|
43
|
+
if (CommonsCompressCompressorProvider.isCompressorFormat(format)) {
|
44
|
+
return new CommonsCompressCompressorProvider(task, output);
|
45
|
+
} else if (CommonsCompressArchiveProvider.isArchiveFormat(format)) {
|
46
|
+
return new CommonsCompressArchiveProvider(task, output);
|
47
|
+
} else {
|
48
|
+
throw new RuntimeException("Unknown format is set format:" + format);
|
49
|
+
}
|
50
|
+
}
|
51
|
+
}
|
metadata
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-encoder-commons-compress
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- hata
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-10-16 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: Commons Compress encoder plugin is an Embulk plugin that encodes files using Commons Compress so that any file output plugins can store the files. Search the file output plugins by 'embulk-output file' keywords.
|
42
|
+
email:
|
43
|
+
- hiroki.ata@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/encoder/commons-compress.rb
|
57
|
+
- src/main/java/org/embulk/encoder/CommonsCompressArchiveProvider.java
|
58
|
+
- src/main/java/org/embulk/encoder/CommonsCompressCompressorProvider.java
|
59
|
+
- src/main/java/org/embulk/encoder/CommonsCompressEncoderPlugin.java
|
60
|
+
- src/test/java/org/embulk/encoder/TestCommonsCompressEncoderPlugin.java
|
61
|
+
- classpath/commons-compress-1.9.jar
|
62
|
+
- classpath/embulk-encoder-commons-compress-0.1.0.jar
|
63
|
+
homepage: https://github.com/hata/embulk-encoder-commons-compress
|
64
|
+
licenses:
|
65
|
+
- MIT
|
66
|
+
metadata: {}
|
67
|
+
post_install_message:
|
68
|
+
rdoc_options: []
|
69
|
+
require_paths:
|
70
|
+
- lib
|
71
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
77
|
+
requirements:
|
78
|
+
- - '>='
|
79
|
+
- !ruby/object:Gem::Version
|
80
|
+
version: '0'
|
81
|
+
requirements: []
|
82
|
+
rubyforge_project:
|
83
|
+
rubygems_version: 2.1.9
|
84
|
+
signing_key:
|
85
|
+
specification_version: 4
|
86
|
+
summary: Commons Compress encoder plugin for Embulk
|
87
|
+
test_files: []
|