embulk-filter-woothee 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/.travis.yml +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +69 -0
- data/build.gradle +73 -0
- data/classpath/embulk-filter-woothee-0.1.0.jar +0 -0
- data/classpath/woothee-java-1.2.0.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/filter/woothee.rb +3 -0
- data/src/main/java/org/embulk/filter/WootheeFilterPlugin.java +179 -0
- data/src/test/java/org/embulk/filter/TestWootheeFilterPlugin.java +5 -0
- metadata +87 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 752c7a195247ac302a42c084df1599f689c1cb88
|
4
|
+
data.tar.gz: 6d129efffc8daf764f001fa9924dce6409931f07
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 17e87d45fae472c708eb490c3a09352c9bfb4eadb97eca0f2943368ebc6892bcaeb725b68166b8ea784a47a3b88e83889cd92e66de0f65edaa0c61c8438b98ef
|
7
|
+
data.tar.gz: dab3a5770122bedd72dd15eb5dbd8060d4cf681ed4c3ecada07c032aa5ade35dbcd5551091ba7a4d61c75ddc314c7a129831ca538962173965160d11dbd67ebd
|
data/.gitignore
ADDED
data/.travis.yml
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 +1,69 @@
|
|
1
|
+
# Woothee filter plugin for Embulk
|
2
|
+
|
3
|
+
parse UserAgent strings and to filter/drop specified categories of user terminals.
|
4
|
+
|
5
|
+
see. [woothee/woothee-java](https://github.com/woothee/woothee-java)
|
6
|
+
|
7
|
+
## Overview
|
8
|
+
|
9
|
+
* **Plugin type**: filter
|
10
|
+
|
11
|
+
## Configuration
|
12
|
+
|
13
|
+
- **key_name**: target key name (string, required)
|
14
|
+
- **out_key_name**: out key name (string, default: agent_name)
|
15
|
+
- **out_key_category**: out key category (string, default: agent_category)
|
16
|
+
- **out_key_os**: out key os (string, default: agent_os)
|
17
|
+
- **out_key_version**: out key version (string, default: agent_version)
|
18
|
+
- **out_key_vendor**: out key vendor (string, default: agent_vendor)
|
19
|
+
- **filter_categories**: filter categories (array, default: null)
|
20
|
+
- **drop_categories**: drop categories (array, default: null)
|
21
|
+
- **merge_agent_info**: merge agent info (bool, default: false)
|
22
|
+
|
23
|
+
## Example1(add agent info)
|
24
|
+
|
25
|
+
```yaml
|
26
|
+
filters:
|
27
|
+
- type: woothee
|
28
|
+
key_name: user_agent
|
29
|
+
merge_agent_info: true
|
30
|
+
out:
|
31
|
+
type: stdout
|
32
|
+
```
|
33
|
+
|
34
|
+
## Example2(filter categories)
|
35
|
+
|
36
|
+
```yaml
|
37
|
+
filters:
|
38
|
+
- type: woothee
|
39
|
+
key_name: user_agent
|
40
|
+
merge_agent_info: true
|
41
|
+
filter_categories:
|
42
|
+
- pc
|
43
|
+
- smartphone
|
44
|
+
- mobilephone
|
45
|
+
- appliance
|
46
|
+
out:
|
47
|
+
type: stdout
|
48
|
+
```
|
49
|
+
|
50
|
+
## Example3(drop categories)
|
51
|
+
|
52
|
+
```yaml
|
53
|
+
filters:
|
54
|
+
- type: woothee
|
55
|
+
key_name: user_agent
|
56
|
+
merge_agent_info: true
|
57
|
+
filter_categories:
|
58
|
+
- crawler
|
59
|
+
- UNKNOWN
|
60
|
+
out:
|
61
|
+
type: stdout
|
62
|
+
```
|
63
|
+
|
64
|
+
|
65
|
+
## Build
|
66
|
+
|
67
|
+
```
|
68
|
+
$ ./gradlew gem
|
69
|
+
```
|
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
|
+
id "eclipse"
|
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:0.7.1"
|
20
|
+
provided "org.embulk:embulk-core:0.7.1"
|
21
|
+
compile 'is.tagomor.woothee:woothee-java:1.2.0'
|
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: ["gemspec", "classpath"]) {
|
33
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
34
|
+
script "${project.name}.gemspec"
|
35
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
36
|
+
}
|
37
|
+
|
38
|
+
task gemPush(type: JRubyExec, dependsOn: ["gem"]) {
|
39
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "push"
|
40
|
+
script "pkg/${project.name}-${project.version}.gem"
|
41
|
+
}
|
42
|
+
|
43
|
+
task "package"(dependsOn: ["gemspec", "classpath"]) << {
|
44
|
+
println "> Build succeeded."
|
45
|
+
println "> You can run embulk with '-L ${file(".").absolutePath}' argument."
|
46
|
+
}
|
47
|
+
|
48
|
+
task gemspec {
|
49
|
+
ext.gemspecFile = file("${project.name}.gemspec")
|
50
|
+
inputs.file "build.gradle"
|
51
|
+
outputs.file gemspecFile
|
52
|
+
doLast { gemspecFile.write($/
|
53
|
+
Gem::Specification.new do |spec|
|
54
|
+
spec.name = "${project.name}"
|
55
|
+
spec.version = "${project.version}"
|
56
|
+
spec.authors = ["toyama-h"]
|
57
|
+
spec.summary = %[Woothee filter plugin for Embulk]
|
58
|
+
spec.description = %[Woothee]
|
59
|
+
spec.email = ["toyama0919@gmail.com"]
|
60
|
+
spec.licenses = ["MIT"]
|
61
|
+
spec.homepage = "https://github.com/toyama0919/embulk-filter-woothee"
|
62
|
+
|
63
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
64
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
65
|
+
spec.require_paths = ["lib"]
|
66
|
+
|
67
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
68
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
69
|
+
end
|
70
|
+
/$)
|
71
|
+
}
|
72
|
+
}
|
73
|
+
clean { delete "${project.name}.gemspec" }
|
Binary file
|
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 +1,179 @@
|
|
1
|
+
package org.embulk.filter;
|
2
|
+
|
3
|
+
import is.tagomor.woothee.Classifier;
|
4
|
+
|
5
|
+
import java.util.List;
|
6
|
+
import java.util.Map;
|
7
|
+
|
8
|
+
import org.embulk.config.Config;
|
9
|
+
import org.embulk.config.ConfigDefault;
|
10
|
+
import org.embulk.config.ConfigSource;
|
11
|
+
import org.embulk.config.Task;
|
12
|
+
import org.embulk.config.TaskSource;
|
13
|
+
import org.embulk.spi.Column;
|
14
|
+
import org.embulk.spi.Exec;
|
15
|
+
import org.embulk.spi.FilterPlugin;
|
16
|
+
import org.embulk.spi.Page;
|
17
|
+
import org.embulk.spi.PageBuilder;
|
18
|
+
import org.embulk.spi.PageOutput;
|
19
|
+
import org.embulk.spi.PageReader;
|
20
|
+
import org.embulk.spi.Schema;
|
21
|
+
import org.embulk.spi.type.Types;
|
22
|
+
|
23
|
+
import com.google.common.base.Optional;
|
24
|
+
import com.google.common.collect.ImmutableList;
|
25
|
+
import com.google.common.collect.Maps;
|
26
|
+
|
27
|
+
public class WootheeFilterPlugin implements FilterPlugin
|
28
|
+
{
|
29
|
+
public interface PluginTask extends Task
|
30
|
+
{
|
31
|
+
@Config("key_name")
|
32
|
+
public String getKeyName();
|
33
|
+
|
34
|
+
@Config("out_key_name")
|
35
|
+
@ConfigDefault("\"agent_name\"")
|
36
|
+
public String getOutKeyName();
|
37
|
+
|
38
|
+
@Config("out_key_category")
|
39
|
+
@ConfigDefault("\"agent_category\"")
|
40
|
+
public String getOutKeyCategory();
|
41
|
+
|
42
|
+
@Config("out_key_os")
|
43
|
+
@ConfigDefault("\"agent_os\"")
|
44
|
+
public String getOutKeyOs();
|
45
|
+
|
46
|
+
@Config("out_key_version")
|
47
|
+
@ConfigDefault("\"agent_version\"")
|
48
|
+
public String getOutKeyVersion();
|
49
|
+
|
50
|
+
@Config("out_key_vendor")
|
51
|
+
@ConfigDefault("\"agent_vendor\"")
|
52
|
+
public String getOutKeyVendor();
|
53
|
+
|
54
|
+
@Config("filter_categories")
|
55
|
+
@ConfigDefault("null")
|
56
|
+
public Optional<List<String>> getFilterCategories();
|
57
|
+
|
58
|
+
@Config("drop_categories")
|
59
|
+
@ConfigDefault("null")
|
60
|
+
public Optional<List<String>> getDropCategories();
|
61
|
+
|
62
|
+
@Config("merge_agent_info")
|
63
|
+
@ConfigDefault("false")
|
64
|
+
public Boolean getMergeAgentInfo();
|
65
|
+
}
|
66
|
+
|
67
|
+
@Override
|
68
|
+
public void transaction(ConfigSource config, Schema inputSchema,
|
69
|
+
FilterPlugin.Control control)
|
70
|
+
{
|
71
|
+
PluginTask task = config.loadConfig(PluginTask.class);
|
72
|
+
|
73
|
+
ImmutableList.Builder<Column> builder = ImmutableList.builder();
|
74
|
+
int i = 0;
|
75
|
+
for (Column inputColumn: inputSchema.getColumns()) {
|
76
|
+
Column outputColumn = new Column(i++, inputColumn.getName(), inputColumn.getType());
|
77
|
+
builder.add(outputColumn);
|
78
|
+
}
|
79
|
+
if (task.getMergeAgentInfo()) {
|
80
|
+
builder.add(new Column(i++, task.getOutKeyOs(), Types.STRING));
|
81
|
+
builder.add(new Column(i++, task.getOutKeyName(), Types.STRING));
|
82
|
+
builder.add(new Column(i++, task.getOutKeyCategory(), Types.STRING));
|
83
|
+
builder.add(new Column(i++, task.getOutKeyVersion(), Types.STRING));
|
84
|
+
builder.add(new Column(i++, task.getOutKeyVendor(), Types.STRING));
|
85
|
+
}
|
86
|
+
Schema outputSchema = new Schema(builder.build());
|
87
|
+
|
88
|
+
control.run(task.dump(), outputSchema);
|
89
|
+
}
|
90
|
+
|
91
|
+
@Override
|
92
|
+
public PageOutput open(TaskSource taskSource, final Schema inputSchema, final Schema outputSchema, final PageOutput output)
|
93
|
+
{
|
94
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
95
|
+
|
96
|
+
final List<Column> outputColumns = outputSchema.getColumns();
|
97
|
+
final List<Column> inputColumns = inputSchema.getColumns();
|
98
|
+
Map<String, Column> inputColumnMap = Maps.newHashMap();
|
99
|
+
final Map<String, Column> wootheeColumnMap = Maps.newHashMap();
|
100
|
+
for (Column column : outputColumns) {
|
101
|
+
if (!inputColumns.contains(column)) {
|
102
|
+
wootheeColumnMap.put(column.getName(), column);
|
103
|
+
} else {
|
104
|
+
inputColumnMap.put(column.getName(), column);
|
105
|
+
}
|
106
|
+
}
|
107
|
+
final Column keyNameColumn = inputColumnMap.get(task.getKeyName());
|
108
|
+
|
109
|
+
return new PageOutput() {
|
110
|
+
private PageReader reader = new PageReader(inputSchema);
|
111
|
+
|
112
|
+
@Override
|
113
|
+
public void finish() {
|
114
|
+
output.finish();
|
115
|
+
}
|
116
|
+
|
117
|
+
@Override
|
118
|
+
public void close() {
|
119
|
+
output.close();
|
120
|
+
}
|
121
|
+
|
122
|
+
@Override
|
123
|
+
public void add(Page page) {
|
124
|
+
reader.setPage(page);
|
125
|
+
|
126
|
+
try (final PageBuilder builder = new PageBuilder(Exec.getBufferAllocator(), outputSchema, output)) {
|
127
|
+
while (reader.nextRecord()) {
|
128
|
+
String userAgentString = reader.isNull(keyNameColumn) ? null : reader.getString(keyNameColumn);
|
129
|
+
Map<String, String> ua = Classifier.parse(userAgentString);
|
130
|
+
setValue(builder, ua);
|
131
|
+
if (task.getFilterCategories().isPresent()) {
|
132
|
+
if (task.getFilterCategories().orNull().contains(ua.get("category"))) {
|
133
|
+
builder.addRecord();
|
134
|
+
}
|
135
|
+
} else if (task.getDropCategories().isPresent()) {
|
136
|
+
if (!task.getDropCategories().orNull().contains(ua.get("category"))) {
|
137
|
+
builder.addRecord();
|
138
|
+
}
|
139
|
+
} else {
|
140
|
+
builder.addRecord();
|
141
|
+
}
|
142
|
+
}
|
143
|
+
builder.finish();
|
144
|
+
}
|
145
|
+
}
|
146
|
+
|
147
|
+
/**
|
148
|
+
* @param builder
|
149
|
+
*/
|
150
|
+
private void setValue(PageBuilder builder, Map<String, String> ua) {
|
151
|
+
if (task.getMergeAgentInfo()) {
|
152
|
+
builder.setString(wootheeColumnMap.get(task.getOutKeyOs()), ua.get("os"));
|
153
|
+
builder.setString(wootheeColumnMap.get(task.getOutKeyName()), ua.get("name"));
|
154
|
+
builder.setString(wootheeColumnMap.get(task.getOutKeyCategory()), ua.get("category"));
|
155
|
+
builder.setString(wootheeColumnMap.get(task.getOutKeyVersion()), ua.get("version"));
|
156
|
+
builder.setString(wootheeColumnMap.get(task.getOutKeyVendor()), ua.get("vendor"));
|
157
|
+
}
|
158
|
+
|
159
|
+
for (Column inputColumn: inputColumns) {
|
160
|
+
if (reader.isNull(inputColumn)) {
|
161
|
+
builder.setNull(inputColumn);
|
162
|
+
continue;
|
163
|
+
}
|
164
|
+
if (Types.STRING.equals(inputColumn.getType())) {
|
165
|
+
builder.setString(inputColumn, reader.getString(inputColumn));
|
166
|
+
} else if (Types.BOOLEAN.equals(inputColumn.getType())) {
|
167
|
+
builder.setBoolean(inputColumn, reader.getBoolean(inputColumn));
|
168
|
+
} else if (Types.DOUBLE.equals(inputColumn.getType())) {
|
169
|
+
builder.setDouble(inputColumn, reader.getDouble(inputColumn));
|
170
|
+
} else if (Types.LONG.equals(inputColumn.getType())) {
|
171
|
+
builder.setLong(inputColumn, reader.getLong(inputColumn));
|
172
|
+
} else if (Types.TIMESTAMP.equals(inputColumn.getType())) {
|
173
|
+
builder.setTimestamp(inputColumn, reader.getTimestamp(inputColumn));
|
174
|
+
}
|
175
|
+
}
|
176
|
+
}
|
177
|
+
};
|
178
|
+
}
|
179
|
+
}
|
metadata
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: embulk-filter-woothee
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- toyama-h
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-08-24 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: Woothee
|
42
|
+
email:
|
43
|
+
- toyama0919@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions: []
|
46
|
+
extra_rdoc_files: []
|
47
|
+
files:
|
48
|
+
- .gitignore
|
49
|
+
- .travis.yml
|
50
|
+
- LICENSE.txt
|
51
|
+
- README.md
|
52
|
+
- build.gradle
|
53
|
+
- gradle/wrapper/gradle-wrapper.jar
|
54
|
+
- gradle/wrapper/gradle-wrapper.properties
|
55
|
+
- gradlew
|
56
|
+
- gradlew.bat
|
57
|
+
- lib/embulk/filter/woothee.rb
|
58
|
+
- src/main/java/org/embulk/filter/WootheeFilterPlugin.java
|
59
|
+
- src/test/java/org/embulk/filter/TestWootheeFilterPlugin.java
|
60
|
+
- classpath/embulk-filter-woothee-0.1.0.jar
|
61
|
+
- classpath/woothee-java-1.2.0.jar
|
62
|
+
homepage: https://github.com/toyama0919/embulk-filter-woothee
|
63
|
+
licenses:
|
64
|
+
- MIT
|
65
|
+
metadata: {}
|
66
|
+
post_install_message:
|
67
|
+
rdoc_options: []
|
68
|
+
require_paths:
|
69
|
+
- lib
|
70
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - '>='
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
76
|
+
requirements:
|
77
|
+
- - '>='
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
requirements: []
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 2.1.9
|
83
|
+
signing_key:
|
84
|
+
specification_version: 4
|
85
|
+
summary: Woothee filter plugin for Embulk
|
86
|
+
test_files: []
|
87
|
+
has_rdoc:
|