embulk-filter-hash 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 +12 -0
- data/LICENSE.txt +21 -0
- data/README.md +45 -0
- data/build.gradle +73 -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/filter/hash.rb +3 -0
- data/src/main/java/org/embulk/filter/hash/HashFilterPlugin.java +164 -0
- data/src/test/java/org/embulk/filter/hash/TestHashFilterPlugin.java +27 -0
- metadata +84 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 8c2882f03b8798c5a10f69d575c94b1b3f63a0ce
|
4
|
+
data.tar.gz: d7f3149fbcffe1c14d4a7fa6db5d46bb74c91272
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a537c2ab6a7a42c34580166d50f1b8462621bdc62fcd1ddc06daaa2eec70261a9893c4b68139e5a8addd12caabd2615467c6e61be796df8371b038a853365fba
|
7
|
+
data.tar.gz: 4dafd182554a77b880830bc67feb77dba2d0f417135b15e27dd216a1c24cd72666b622ceef6397c0a197b786a8acc563c0e15d5f7ee082d91efe2b51c2ec0898
|
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 +1,45 @@
|
|
1
|
+
# Hash filter plugin for Embulk
|
2
|
+
|
3
|
+
Embulk filter plugin to convert a input to hash.
|
4
|
+
|
5
|
+
## Overview
|
6
|
+
|
7
|
+
* **Plugin type**: filter
|
8
|
+
|
9
|
+
## Configuration
|
10
|
+
|
11
|
+
- **columns**: Columns to hash (array, required)
|
12
|
+
- **name**: Name of input column (string, required)
|
13
|
+
- **algorithm**: A hash algorithm. [See also](#hash_algorithm) (string, default:`"SHA-256"`)
|
14
|
+
- **new_name**: New column name if you want to rename (string, default: `null`)
|
15
|
+
|
16
|
+
## Example
|
17
|
+
|
18
|
+
```yaml
|
19
|
+
filters:
|
20
|
+
- type: hash
|
21
|
+
columns:
|
22
|
+
- { name: username }
|
23
|
+
- { name: email, algorithm: SHA-512, new_name: hashed_email }
|
24
|
+
```
|
25
|
+
|
26
|
+
## Hash Algorithm
|
27
|
+
<a name ="hash_algorithm">
|
28
|
+
This plugin use [MessageDigest](https://docs.oracle.com/javase/7/docs/api/java/security/MessageDigest.html) for hashing.
|
29
|
+
Every implementation of the Java platform supports the following MessageDigest algorithms:
|
30
|
+
- MD5
|
31
|
+
- SHA-1
|
32
|
+
- SHA-256
|
33
|
+
|
34
|
+
If you want to know all algorithms that your platform supports, run the following snippet.
|
35
|
+
```java
|
36
|
+
for (String algorithm : java.security.Security.getAlgorithms("MessageDigest")) {
|
37
|
+
System.out.println(algorithm);
|
38
|
+
}
|
39
|
+
```
|
40
|
+
|
41
|
+
## Build
|
42
|
+
|
43
|
+
```
|
44
|
+
$ ./gradlew gem # -t to watch change of files and rebuild continuously
|
45
|
+
```
|
data/build.gradle
ADDED
@@ -0,0 +1,73 @@
|
|
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:0.7.7"
|
19
|
+
provided "org.embulk:embulk-core:0.7.7"
|
20
|
+
// compile "YOUR_JAR_DEPENDENCY_GROUP:YOUR_JAR_DEPENDENCY_MODULE:YOUR_JAR_DEPENDENCY_VERSION"
|
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: ["gemspec", "classpath"]) {
|
32
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
33
|
+
script "${project.name}.gemspec"
|
34
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
35
|
+
}
|
36
|
+
|
37
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
38
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
39
|
+
script "pkg/${project.name}-${project.version}.gem"
|
40
|
+
}
|
41
|
+
|
42
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) << {
|
43
|
+
println "> Build succeeded."
|
44
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
45
|
+
}
|
46
|
+
|
47
|
+
task gemspec {
|
48
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
49
|
+
inputs.file "build.gradle"
|
50
|
+
outputs.file gemspecFile
|
51
|
+
doLast { gemspecFile.write($/
|
52
|
+
Gem::Specification.new do |spec|
|
53
|
+
spec.name = "${project.name}"
|
54
|
+
spec.version = "${project.version}"
|
55
|
+
spec.authors = ["Shinichi Ishimura"]
|
56
|
+
spec.summary = %[Hash filter plugin for Embulk]
|
57
|
+
spec.description = %[Embulk filter plugin to convert a input to hash.]
|
58
|
+
spec.email = ["shiketaudonko41@gmail.com"]
|
59
|
+
spec.licenses = ["MIT"]
|
60
|
+
# TODO set this: spec.homepage = "https://github.com/kamatama41/embulk-filter-hash"
|
61
|
+
|
62
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
63
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
64
|
+
spec.require_paths = ["lib"]
|
65
|
+
|
66
|
+
#spec.add_dependency 'YOUR_GEM_DEPENDENCY', ['~> YOUR_GEM_DEPENDENCY_VERSION']
|
67
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
68
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
69
|
+
end
|
70
|
+
/$)
|
71
|
+
}
|
72
|
+
}
|
73
|
+
clean { delete "${project.name}.gemspec" }
|
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 +1,164 @@
|
|
1
|
+
package org.embulk.filter.hash;
|
2
|
+
|
3
|
+
import com.google.common.base.Optional;
|
4
|
+
import com.google.common.base.Throwables;
|
5
|
+
import org.embulk.config.*;
|
6
|
+
import org.embulk.spi.*;
|
7
|
+
import org.embulk.spi.time.Timestamp;
|
8
|
+
import org.embulk.spi.type.Types;
|
9
|
+
|
10
|
+
import java.security.MessageDigest;
|
11
|
+
import java.security.NoSuchAlgorithmException;
|
12
|
+
import java.util.HashMap;
|
13
|
+
import java.util.List;
|
14
|
+
import java.util.Map;
|
15
|
+
|
16
|
+
public class HashFilterPlugin implements FilterPlugin {
|
17
|
+
|
18
|
+
public interface PluginTask extends Task {
|
19
|
+
@Config("columns")
|
20
|
+
List<HashColumn> getColumns();
|
21
|
+
}
|
22
|
+
|
23
|
+
public interface HashColumn extends Task {
|
24
|
+
@Config("name")
|
25
|
+
String getName();
|
26
|
+
|
27
|
+
@Config("algorithm")
|
28
|
+
@ConfigDefault("\"SHA-256\"")
|
29
|
+
Optional<String> getAlgorithm();
|
30
|
+
|
31
|
+
@Config("new_name")
|
32
|
+
@ConfigDefault("null")
|
33
|
+
Optional<String> getNewName();
|
34
|
+
}
|
35
|
+
|
36
|
+
@Override
|
37
|
+
public void transaction(ConfigSource config, Schema inputSchema, FilterPlugin.Control control) {
|
38
|
+
|
39
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
40
|
+
Map<String, HashColumn> hashColumnMap = convertHashColumnListToMap(task.getColumns());
|
41
|
+
|
42
|
+
Schema.Builder builder = Schema.builder();
|
43
|
+
for (Column column : inputSchema.getColumns()) {
|
44
|
+
|
45
|
+
HashColumn hashColumn = hashColumnMap.get(column.getName());
|
46
|
+
|
47
|
+
if (hashColumn != null) {
|
48
|
+
builder.add(hashColumn.getNewName().or(column.getName()), Types.STRING);
|
49
|
+
} else {
|
50
|
+
builder.add(column.getName(), column.getType());
|
51
|
+
}
|
52
|
+
}
|
53
|
+
control.run(task.dump(), builder.build());
|
54
|
+
}
|
55
|
+
|
56
|
+
@Override
|
57
|
+
public PageOutput open(final TaskSource taskSource, final Schema inputSchema,
|
58
|
+
final Schema outputSchema, final PageOutput output) {
|
59
|
+
|
60
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
61
|
+
final Map<String, HashColumn> hashColumnMap = convertHashColumnListToMap(task.getColumns());
|
62
|
+
final Map<String, Column> outputColumnMap = convertColumnListToMap(outputSchema.getColumns());
|
63
|
+
|
64
|
+
return new PageOutput() {
|
65
|
+
private PageReader reader = new PageReader(inputSchema);
|
66
|
+
private PageBuilder builder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output);
|
67
|
+
|
68
|
+
@Override
|
69
|
+
public void add(Page page) {
|
70
|
+
reader.setPage(page);
|
71
|
+
while (reader.nextRecord()) {
|
72
|
+
setValue();
|
73
|
+
builder.addRecord();
|
74
|
+
}
|
75
|
+
}
|
76
|
+
|
77
|
+
private void setValue() {
|
78
|
+
for (Column inputColumn : inputSchema.getColumns()) {
|
79
|
+
if (reader.isNull(inputColumn)) {
|
80
|
+
builder.setNull(inputColumn);
|
81
|
+
continue;
|
82
|
+
}
|
83
|
+
|
84
|
+
// Write the original data
|
85
|
+
Object inputValue;
|
86
|
+
if (Types.STRING.equals(inputColumn.getType())) {
|
87
|
+
final String value = reader.getString(inputColumn);
|
88
|
+
inputValue = value;
|
89
|
+
builder.setString(inputColumn, value);
|
90
|
+
} else if (Types.BOOLEAN.equals(inputColumn.getType())) {
|
91
|
+
final boolean value = reader.getBoolean(inputColumn);
|
92
|
+
inputValue = value;
|
93
|
+
builder.setBoolean(inputColumn, value);
|
94
|
+
} else if (Types.DOUBLE.equals(inputColumn.getType())) {
|
95
|
+
final double value = reader.getDouble(inputColumn);
|
96
|
+
inputValue = value;
|
97
|
+
builder.setDouble(inputColumn, value);
|
98
|
+
} else if (Types.LONG.equals(inputColumn.getType())) {
|
99
|
+
final long value = reader.getLong(inputColumn);
|
100
|
+
inputValue = value;
|
101
|
+
builder.setLong(inputColumn, value);
|
102
|
+
} else if (Types.TIMESTAMP.equals(inputColumn.getType())) {
|
103
|
+
final Timestamp value = reader.getTimestamp(inputColumn);
|
104
|
+
inputValue = value;
|
105
|
+
builder.setTimestamp(inputColumn, value);
|
106
|
+
} else {
|
107
|
+
throw new DataException("Unexpected type:" + inputColumn.getType());
|
108
|
+
}
|
109
|
+
|
110
|
+
// Overwrite the column if it's hash column.
|
111
|
+
HashColumn hashColumn = hashColumnMap.get(inputColumn.getName());
|
112
|
+
if (hashColumn != null) {
|
113
|
+
final Column outputColumn = outputColumnMap.get(hashColumn.getNewName().or(inputColumn.getName()));
|
114
|
+
final String hashedValue = generateHash(inputValue.toString(), hashColumn.getAlgorithm().get());
|
115
|
+
builder.setString(outputColumn, hashedValue);
|
116
|
+
}
|
117
|
+
}
|
118
|
+
}
|
119
|
+
|
120
|
+
private String generateHash(String value, String algorithm) {
|
121
|
+
String result = null;
|
122
|
+
try {
|
123
|
+
MessageDigest md = MessageDigest.getInstance(algorithm);
|
124
|
+
md.update(value.getBytes());
|
125
|
+
|
126
|
+
StringBuilder sb = new StringBuilder();
|
127
|
+
for (byte b : md.digest()) {
|
128
|
+
sb.append(String.format("%02x", b));
|
129
|
+
}
|
130
|
+
result = sb.toString();
|
131
|
+
} catch (NoSuchAlgorithmException e) {
|
132
|
+
Throwables.propagate(e);
|
133
|
+
}
|
134
|
+
return result;
|
135
|
+
}
|
136
|
+
|
137
|
+
@Override
|
138
|
+
public void finish() {
|
139
|
+
builder.finish();
|
140
|
+
}
|
141
|
+
|
142
|
+
@Override
|
143
|
+
public void close() {
|
144
|
+
builder.close();
|
145
|
+
}
|
146
|
+
};
|
147
|
+
}
|
148
|
+
|
149
|
+
private static Map<String, HashColumn> convertHashColumnListToMap(List<HashColumn> hashColumns) {
|
150
|
+
Map<String, HashColumn> result = new HashMap<>();
|
151
|
+
for (HashColumn hashColumn : hashColumns) {
|
152
|
+
result.put(hashColumn.getName(), hashColumn);
|
153
|
+
}
|
154
|
+
return result;
|
155
|
+
}
|
156
|
+
|
157
|
+
private static Map<String, Column> convertColumnListToMap(List<Column> columns) {
|
158
|
+
Map<String, Column> result = new HashMap<>();
|
159
|
+
for (Column column : columns) {
|
160
|
+
result.put(column.getName(), column);
|
161
|
+
}
|
162
|
+
return result;
|
163
|
+
}
|
164
|
+
}
|
@@ -0,0 +1,27 @@
|
|
1
|
+
package org.embulk.filter.hash;
|
2
|
+
|
3
|
+
//import com.fasterxml.jackson.databind.ObjectMapper;
|
4
|
+
//import com.google.inject.AbstractModule;
|
5
|
+
//import com.google.inject.Guice;
|
6
|
+
//import org.embulk.EmbulkEmbed;
|
7
|
+
//import org.embulk.config.ConfigLoader;
|
8
|
+
//import org.embulk.config.ModelManager;
|
9
|
+
//import org.junit.Test;
|
10
|
+
//
|
11
|
+
//import java.io.File;
|
12
|
+
//import java.io.IOException;
|
13
|
+
|
14
|
+
public class TestHashFilterPlugin
|
15
|
+
{
|
16
|
+
// @Test
|
17
|
+
// public void test() throws IOException {
|
18
|
+
// EmbulkEmbed embed = new EmbulkEmbed.Bootstrap().initialize();
|
19
|
+
// ConfigLoader loader = new ConfigLoader(new ModelManager(Guice.createInjector(new AbstractModule() {
|
20
|
+
// @Override
|
21
|
+
// protected void configure() {}
|
22
|
+
// }),
|
23
|
+
// new ObjectMapper()
|
24
|
+
// ));
|
25
|
+
// embed.run(loader.fromYamlFile(new File("./test.yml")));
|
26
|
+
// }
|
27
|
+
}
|
metadata
ADDED
@@ -0,0 +1,84 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-filter-hash
|
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: 2015-11-17 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: Embulk filter plugin to convert a input to hash.
|
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/filter/hash.rb
|
57
|
+
- src/main/java/org/embulk/filter/hash/HashFilterPlugin.java
|
58
|
+
- src/test/java/org/embulk/filter/hash/TestHashFilterPlugin.java
|
59
|
+
- classpath/embulk-filter-hash-0.1.0.jar
|
60
|
+
homepage:
|
61
|
+
licenses:
|
62
|
+
- MIT
|
63
|
+
metadata: {}
|
64
|
+
post_install_message:
|
65
|
+
rdoc_options: []
|
66
|
+
require_paths:
|
67
|
+
- lib
|
68
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
69
|
+
requirements:
|
70
|
+
- - '>='
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
version: '0'
|
73
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
74
|
+
requirements:
|
75
|
+
- - '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
requirements: []
|
79
|
+
rubyforge_project:
|
80
|
+
rubygems_version: 2.1.9
|
81
|
+
signing_key:
|
82
|
+
specification_version: 4
|
83
|
+
summary: Hash filter plugin for Embulk
|
84
|
+
test_files: []
|