embulk-input-remote 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 +21 -0
- data/README.md +49 -0
- data/build.gradle +57 -0
- data/classpath/bcpkix-jdk15on-1.51.jar +0 -0
- data/classpath/bcprov-jdk15on-1.51.jar +0 -0
- data/classpath/embulk-input-remote-0.1.0.jar +0 -0
- data/classpath/jzlib-1.1.3.jar +0 -0
- data/classpath/sshj-0.11.0.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/input/remote.rb +3 -0
- data/src/main/java/org/embulk/input/RemoteFileInputPlugin.java +315 -0
- data/src/test/java/org/embulk/input/TestRemoteFileInputPlugin.java +5 -0
- metadata +88 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 305d88a19ed8811959b2b5fe1f28ccd0f0c0470f
|
4
|
+
data.tar.gz: 267dcf87dbc85df3abc4d79d04d710a7a894a2a5
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: f45656d575e8801e2b8f10901bdfeb2bfdcd91e1edc58242e4505954b58d96ca1d58b0b3f81b1c803982c9b9519f7539cc41e8dc49d578d8bf494f2003fb608d
|
7
|
+
data.tar.gz: 6126dd4f0f71de003097de04f643d24672ea6ed95490705ff01a81a5c74dc187d63b20703de1542f7fa6cc1d20aa096f0a7a430c34541bdbed0a78963cb6bbfa
|
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 +1,49 @@
|
|
1
|
+
# Remote file input plugin for Embulk
|
2
|
+
|
3
|
+
This plugin load data from Remote hosts by SCP
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: file input
|
8
|
+
* **Resume supported**: yes
|
9
|
+
* **Cleanup supported**: yes
|
10
|
+
|
11
|
+
## Configuration
|
12
|
+
|
13
|
+
- **hosts**: Target hosts (list, default: [])
|
14
|
+
- **hosts_command**: Command to getting hosts(Windows not supported). If given the option, "hosts" is overwritten. (string, default: null)
|
15
|
+
- **hosts_separator**: Separator of "hosts_command" result (string, default: " ")
|
16
|
+
- **path**: Path of remote host (File or Directory) (string, default: "")
|
17
|
+
- **path_command**: Command to getting hosts (Windows not supported). If given the option "path" is overwritten. (string, default: null)
|
18
|
+
- **auth**: SSH authentication setting (map, default: {})
|
19
|
+
- **user**: SSH username (string, default: executing username)
|
20
|
+
- **type**: public_key or password (string, default: public_key)
|
21
|
+
- **key_path**: Path of secret key (If you choose type "public_key") (string, default: "~/.ssh/id_rsa or id_dsa")
|
22
|
+
- **password**: SSH password (If you choose type "password") (string)
|
23
|
+
|
24
|
+
## Example
|
25
|
+
|
26
|
+
```yaml
|
27
|
+
in:
|
28
|
+
type: remote
|
29
|
+
hosts:
|
30
|
+
- host1
|
31
|
+
- host2
|
32
|
+
# hosts_command: echo 'host1,host2'
|
33
|
+
# hosts_separator: ','
|
34
|
+
path: echo /some/path/20150414125923
|
35
|
+
# path_command: echo /some/path/`date "+%Y%m%d%H%M%S"`
|
36
|
+
auth:
|
37
|
+
user: {username}
|
38
|
+
type: public_key
|
39
|
+
key_path: /usr/home/.ssh/id_rsa
|
40
|
+
# type: password
|
41
|
+
# password: {password}
|
42
|
+
```
|
43
|
+
|
44
|
+
|
45
|
+
## Build
|
46
|
+
|
47
|
+
```
|
48
|
+
$ ./gradlew gem
|
49
|
+
```
|
data/build.gradle
ADDED
@@ -0,0 +1,57 @@
|
|
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 "idea"
|
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
|
+
dependencies {
|
19
|
+
compile "org.embulk:embulk-core:0.6.1"
|
20
|
+
compile "com.hierynomus:sshj:0.11.0"
|
21
|
+
provided "org.embulk:embulk-core:0.6.1"
|
22
|
+
testCompile "junit:junit:4.+"
|
23
|
+
}
|
24
|
+
|
25
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
26
|
+
doFirst { file("classpath").deleteDir() }
|
27
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
28
|
+
into "classpath"
|
29
|
+
}
|
30
|
+
clean { delete 'classpath' }
|
31
|
+
|
32
|
+
task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
|
33
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
34
|
+
script "build/gemspec"
|
35
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
36
|
+
}
|
37
|
+
|
38
|
+
task gemspec << { file("build/gemspec").write($/
|
39
|
+
Gem::Specification.new do |spec|
|
40
|
+
spec.name = "${project.name}"
|
41
|
+
spec.version = "${project.version}"
|
42
|
+
spec.authors = ["Shinichi ISHIMURA"]
|
43
|
+
spec.summary = %[Remote file input plugin for Embulk]
|
44
|
+
spec.description = %[Reads files stored on Remote hosts.]
|
45
|
+
spec.email = ["shiketaudonko41@gmail.com"]
|
46
|
+
spec.licenses = ["MIT"]
|
47
|
+
spec.homepage = "https://github.com/kamatama41/embulk-input-remote"
|
48
|
+
|
49
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
50
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
51
|
+
spec.require_paths = ["lib"]
|
52
|
+
|
53
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
54
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
55
|
+
end
|
56
|
+
/$)
|
57
|
+
}
|
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 +1,315 @@
|
|
1
|
+
package org.embulk.input;
|
2
|
+
|
3
|
+
import java.io.BufferedReader;
|
4
|
+
import java.io.ByteArrayInputStream;
|
5
|
+
import java.io.ByteArrayOutputStream;
|
6
|
+
import java.io.IOException;
|
7
|
+
import java.io.InputStream;
|
8
|
+
import java.io.InputStreamReader;
|
9
|
+
import java.io.OutputStream;
|
10
|
+
import java.util.ArrayList;
|
11
|
+
import java.util.Arrays;
|
12
|
+
import java.util.Collections;
|
13
|
+
import java.util.List;
|
14
|
+
import java.util.Map;
|
15
|
+
|
16
|
+
import com.fasterxml.jackson.annotation.JsonCreator;
|
17
|
+
import com.fasterxml.jackson.annotation.JsonProperty;
|
18
|
+
import com.google.common.base.Optional;
|
19
|
+
import com.google.common.collect.ImmutableList;
|
20
|
+
import net.schmizz.sshj.SSHClient;
|
21
|
+
import net.schmizz.sshj.xfer.InMemoryDestFile;
|
22
|
+
import net.schmizz.sshj.xfer.LocalDestFile;
|
23
|
+
import org.embulk.config.CommitReport;
|
24
|
+
import org.embulk.config.Config;
|
25
|
+
import org.embulk.config.ConfigDefault;
|
26
|
+
import org.embulk.config.ConfigDiff;
|
27
|
+
import org.embulk.config.ConfigInject;
|
28
|
+
import org.embulk.config.ConfigSource;
|
29
|
+
import org.embulk.config.Task;
|
30
|
+
import org.embulk.config.TaskSource;
|
31
|
+
import org.embulk.spi.BufferAllocator;
|
32
|
+
import org.embulk.spi.Exec;
|
33
|
+
import org.embulk.spi.FileInputPlugin;
|
34
|
+
import org.embulk.spi.TransactionalFileInput;
|
35
|
+
import org.embulk.spi.util.InputStreamFileInput;
|
36
|
+
import org.slf4j.Logger;
|
37
|
+
|
38
|
+
import javax.annotation.Nullable;
|
39
|
+
|
40
|
+
public class RemoteFileInputPlugin
|
41
|
+
implements FileInputPlugin {
|
42
|
+
public interface PluginTask
|
43
|
+
extends Task {
|
44
|
+
@Config("hosts")
|
45
|
+
@ConfigDefault("[]")
|
46
|
+
public List<String> getHosts();
|
47
|
+
|
48
|
+
@Config("hosts_command")
|
49
|
+
@ConfigDefault("null")
|
50
|
+
public Optional<String> getHostsCommand();
|
51
|
+
|
52
|
+
@Config("hosts_separator")
|
53
|
+
@ConfigDefault("\" \"")
|
54
|
+
public String getHostsSeparator();
|
55
|
+
|
56
|
+
@Config("path")
|
57
|
+
@ConfigDefault("\"\"")
|
58
|
+
public String getPath();
|
59
|
+
|
60
|
+
@Config("path_command")
|
61
|
+
@ConfigDefault("null")
|
62
|
+
public Optional<String> getPathCommand();
|
63
|
+
|
64
|
+
@Config("auth")
|
65
|
+
@ConfigDefault("{}")
|
66
|
+
public Map<String, String> getAuth();
|
67
|
+
|
68
|
+
@Config("last_target")
|
69
|
+
@ConfigDefault("null")
|
70
|
+
public Optional<Target> getLastTarget();
|
71
|
+
|
72
|
+
public void setLastTarget(Optional<Target> lastTarget);
|
73
|
+
|
74
|
+
public List<Target> getTargets();
|
75
|
+
|
76
|
+
public void setTargets(List<Target> targets);
|
77
|
+
|
78
|
+
@ConfigInject
|
79
|
+
public BufferAllocator getBufferAllocator();
|
80
|
+
}
|
81
|
+
|
82
|
+
private final Logger log = Exec.getLogger(getClass());
|
83
|
+
|
84
|
+
@Override
|
85
|
+
public ConfigDiff transaction(ConfigSource config, FileInputPlugin.Control control) {
|
86
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
87
|
+
|
88
|
+
List<Target> targets = listTargets(task);
|
89
|
+
log.info("Loading targets {}", targets);
|
90
|
+
task.setTargets(targets);
|
91
|
+
|
92
|
+
// number of processors is same with number of targets
|
93
|
+
int taskCount = targets.size();
|
94
|
+
return resume(task.dump(), taskCount, control);
|
95
|
+
}
|
96
|
+
|
97
|
+
private List<Target> listTargets(PluginTask task) {
|
98
|
+
task.getHostsCommand().orNull();
|
99
|
+
|
100
|
+
final List<String> hosts = listHosts(task);
|
101
|
+
final String path = getPath(task);
|
102
|
+
|
103
|
+
final ImmutableList.Builder<Target> builder = ImmutableList.builder();
|
104
|
+
Target lastTarget = task.getLastTarget().orNull();
|
105
|
+
for (String host : hosts) {
|
106
|
+
Target target = new Target(host, path);
|
107
|
+
if (lastTarget == null || target.compareTo(lastTarget) > 0) {
|
108
|
+
builder.add(target);
|
109
|
+
}
|
110
|
+
}
|
111
|
+
return builder.build();
|
112
|
+
}
|
113
|
+
|
114
|
+
private List<String> listHosts(PluginTask task) {
|
115
|
+
final String hostsCommand = task.getHostsCommand().orNull();
|
116
|
+
if (hostsCommand != null) {
|
117
|
+
final String stdout = execCommand(hostsCommand).trim();
|
118
|
+
return Arrays.asList(stdout.split(task.getHostsSeparator()));
|
119
|
+
} else {
|
120
|
+
return task.getHosts();
|
121
|
+
}
|
122
|
+
}
|
123
|
+
|
124
|
+
private String getPath(PluginTask task) {
|
125
|
+
final String pathCommand = task.getPathCommand().orNull();
|
126
|
+
if (pathCommand != null) {
|
127
|
+
return execCommand(pathCommand).trim();
|
128
|
+
} else {
|
129
|
+
return task.getPath();
|
130
|
+
}
|
131
|
+
}
|
132
|
+
|
133
|
+
private String execCommand(String command) {
|
134
|
+
ProcessBuilder pb = new ProcessBuilder("sh", "-c", command); // TODO: windows
|
135
|
+
log.info("Running command {}", command);
|
136
|
+
try {
|
137
|
+
final Process process = pb.start();
|
138
|
+
try (InputStream stream = process.getInputStream();
|
139
|
+
BufferedReader brStdout = new BufferedReader(new InputStreamReader(stream))
|
140
|
+
) {
|
141
|
+
String line;
|
142
|
+
StringBuilder stdout = new StringBuilder();
|
143
|
+
while ((line = brStdout.readLine()) != null) {
|
144
|
+
stdout.append(line);
|
145
|
+
}
|
146
|
+
|
147
|
+
final int code = process.waitFor();
|
148
|
+
if (code != 0) {
|
149
|
+
throw new IOException(String.format(
|
150
|
+
"Command finished with non-zero exit code. Exit code is %d.", code));
|
151
|
+
}
|
152
|
+
|
153
|
+
return stdout.toString();
|
154
|
+
}
|
155
|
+
} catch (IOException | InterruptedException e) {
|
156
|
+
throw new RuntimeException(e);
|
157
|
+
}
|
158
|
+
}
|
159
|
+
|
160
|
+
@Override
|
161
|
+
public ConfigDiff resume(TaskSource taskSource,
|
162
|
+
int taskCount,
|
163
|
+
FileInputPlugin.Control control) {
|
164
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
165
|
+
|
166
|
+
control.run(taskSource, taskCount);
|
167
|
+
|
168
|
+
List<Target> targets = new ArrayList<>(task.getTargets());
|
169
|
+
Collections.sort(targets);
|
170
|
+
return Exec.newConfigDiff().set("last_target", targets.get(targets.size() - 1));
|
171
|
+
}
|
172
|
+
|
173
|
+
@Override
|
174
|
+
public void cleanup(TaskSource taskSource,
|
175
|
+
int taskCount,
|
176
|
+
List<CommitReport> successCommitReports) {
|
177
|
+
}
|
178
|
+
|
179
|
+
@Override
|
180
|
+
public TransactionalFileInput open(TaskSource taskSource, int taskIndex) {
|
181
|
+
PluginTask task = taskSource.loadTask(PluginTask.class);
|
182
|
+
final Target target = task.getTargets().get(taskIndex);
|
183
|
+
|
184
|
+
try {
|
185
|
+
return new PluginFileInput(task, download(target, task.getAuth()));
|
186
|
+
} catch (IOException e) {
|
187
|
+
throw new RuntimeException(e);
|
188
|
+
}
|
189
|
+
}
|
190
|
+
|
191
|
+
public static class PluginFileInput
|
192
|
+
extends InputStreamFileInput
|
193
|
+
implements TransactionalFileInput {
|
194
|
+
// TODO create single-file InputStreamFileInput utility
|
195
|
+
private static class RemoteFileProvider
|
196
|
+
implements InputStreamFileInput.Provider {
|
197
|
+
private boolean opened = false;
|
198
|
+
private final InputStream input;
|
199
|
+
|
200
|
+
public RemoteFileProvider(InputStream input) {
|
201
|
+
this.input = input;
|
202
|
+
}
|
203
|
+
|
204
|
+
@Override
|
205
|
+
public InputStream openNext() throws IOException {
|
206
|
+
if (opened) {
|
207
|
+
return null;
|
208
|
+
}
|
209
|
+
opened = true;
|
210
|
+
return input;
|
211
|
+
}
|
212
|
+
|
213
|
+
@Override
|
214
|
+
public void close() {
|
215
|
+
}
|
216
|
+
}
|
217
|
+
|
218
|
+
public PluginFileInput(PluginTask task, InputStream input) {
|
219
|
+
super(task.getBufferAllocator(), new RemoteFileProvider(input));
|
220
|
+
}
|
221
|
+
|
222
|
+
@Override
|
223
|
+
public void abort() {
|
224
|
+
}
|
225
|
+
|
226
|
+
@Override
|
227
|
+
public CommitReport commit() {
|
228
|
+
return Exec.newCommitReport();
|
229
|
+
}
|
230
|
+
|
231
|
+
|
232
|
+
}
|
233
|
+
|
234
|
+
private InputStream download(Target target, Map<String, String> auth) throws IOException {
|
235
|
+
SSHClient client = new SSHClient();
|
236
|
+
client.loadKnownHosts();
|
237
|
+
InMemoryDestFileImpl memoryDestFile = new InMemoryDestFileImpl();
|
238
|
+
try {
|
239
|
+
client.connect(target.getHost());
|
240
|
+
final String type = auth.get("type") != null ? auth.get("type") : "public_key";
|
241
|
+
final String user = auth.get("user") != null ? auth.get("user") : System.getProperty("user.name");
|
242
|
+
|
243
|
+
if ("password".equals(type)) {
|
244
|
+
client.authPassword(auth.get("user"), auth.get("password"));
|
245
|
+
} else if ("public_key".equals(type)) {
|
246
|
+
final String key_path = auth.get("key_path");
|
247
|
+
if (key_path == null) {
|
248
|
+
client.authPublickey(user);
|
249
|
+
} else {
|
250
|
+
client.authPublickey(user, key_path);
|
251
|
+
}
|
252
|
+
} else {
|
253
|
+
throw new UnsupportedOperationException("Unsupported auth type : " + type);
|
254
|
+
}
|
255
|
+
client.newSCPFileTransfer().download(target.getPath(), memoryDestFile);
|
256
|
+
return new ByteArrayInputStream(memoryDestFile.outputStream.toByteArray());
|
257
|
+
|
258
|
+
} finally {
|
259
|
+
client.disconnect();
|
260
|
+
}
|
261
|
+
}
|
262
|
+
|
263
|
+
public static class InMemoryDestFileImpl extends InMemoryDestFile {
|
264
|
+
|
265
|
+
private ByteArrayOutputStream outputStream;
|
266
|
+
|
267
|
+
public InMemoryDestFileImpl() {
|
268
|
+
this.outputStream = new ByteArrayOutputStream();
|
269
|
+
}
|
270
|
+
|
271
|
+
@Override
|
272
|
+
public OutputStream getOutputStream() throws IOException {
|
273
|
+
return outputStream;
|
274
|
+
}
|
275
|
+
|
276
|
+
@Override
|
277
|
+
public LocalDestFile getTargetDirectory(String dirname) throws IOException {
|
278
|
+
return this;
|
279
|
+
}
|
280
|
+
}
|
281
|
+
|
282
|
+
public static class Target implements Comparable<Target> {
|
283
|
+
private final String host;
|
284
|
+
private final String path;
|
285
|
+
|
286
|
+
@JsonCreator
|
287
|
+
public Target(
|
288
|
+
@JsonProperty("host") String host,
|
289
|
+
@JsonProperty("path") String path) {
|
290
|
+
this.host = host;
|
291
|
+
this.path = path;
|
292
|
+
}
|
293
|
+
|
294
|
+
public String getHost() {
|
295
|
+
return host;
|
296
|
+
}
|
297
|
+
|
298
|
+
public String getPath() {
|
299
|
+
return path;
|
300
|
+
}
|
301
|
+
|
302
|
+
@Override
|
303
|
+
public int compareTo(@Nullable Target other) {
|
304
|
+
if (other == null) {
|
305
|
+
throw new NullPointerException();
|
306
|
+
}
|
307
|
+
return this.toString().compareTo(other.toString());
|
308
|
+
}
|
309
|
+
|
310
|
+
@Override
|
311
|
+
public String toString() {
|
312
|
+
return host + ":" + path;
|
313
|
+
}
|
314
|
+
}
|
315
|
+
}
|
metadata
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-input-remote
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Shinichi ISHIMURA
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-04-14 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: Reads files stored on Remote hosts.
|
42
|
+
email:
|
43
|
+
- shiketaudonko41@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/input/remote.rb
|
57
|
+
- src/main/java/org/embulk/input/RemoteFileInputPlugin.java
|
58
|
+
- src/test/java/org/embulk/input/TestRemoteFileInputPlugin.java
|
59
|
+
- classpath/bcpkix-jdk15on-1.51.jar
|
60
|
+
- classpath/bcprov-jdk15on-1.51.jar
|
61
|
+
- classpath/embulk-input-remote-0.1.0.jar
|
62
|
+
- classpath/jzlib-1.1.3.jar
|
63
|
+
- classpath/sshj-0.11.0.jar
|
64
|
+
homepage: https://github.com/kamatama41/embulk-input-remote
|
65
|
+
licenses:
|
66
|
+
- MIT
|
67
|
+
metadata: {}
|
68
|
+
post_install_message:
|
69
|
+
rdoc_options: []
|
70
|
+
require_paths:
|
71
|
+
- lib
|
72
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
73
|
+
requirements:
|
74
|
+
- - '>='
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '0'
|
77
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - '>='
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: '0'
|
82
|
+
requirements: []
|
83
|
+
rubyforge_project:
|
84
|
+
rubygems_version: 2.1.9
|
85
|
+
signing_key:
|
86
|
+
specification_version: 4
|
87
|
+
summary: Remote file input plugin for Embulk
|
88
|
+
test_files: []
|