embulk-input-gcs 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 +14 -0
- data/README.md +89 -0
- data/build.gradle +59 -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/gcs.rb +3 -0
- data/settings.gradle +2 -0
- data/src/main/java/org/embulk/input/gcs/GcsFileInputPlugin.java +288 -0
- data/src/test/java/org/embulk/input/gcs/TestGcsFileInputPlugin.java +9 -0
- metadata +94 -0
checksums.yaml
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
---
|
|
2
|
+
SHA1:
|
|
3
|
+
metadata.gz: 82f47e1ec13ce8e83f892c49519930e578440200
|
|
4
|
+
data.tar.gz: 121ad589176d771d23435bbf914b3724337cab6a
|
|
5
|
+
SHA512:
|
|
6
|
+
metadata.gz: 9e37e6e60fe77027bf5b2d1929b2f3af9ebcdac22f8be31e30412db1e3c96e20c3fe7a9b2a6c5081d96f46dafcc924dbbc9f5fe25bbd505b4d1537d488a1c32f
|
|
7
|
+
data.tar.gz: ad9f4ec153c83e317e1f90e4dcf322eecb79ab44b8d4cc17709599b7559aac9edc07b7eb9335c34205464280099ebcb3ee5a94cda7ef536b78bba52628d92fba
|
data/.gitignore
ADDED
data/README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
# Google Cloud Storage file input plugin for Embulk
|
|
2
|
+
|
|
3
|
+
## Overview
|
|
4
|
+
|
|
5
|
+
* Plugin type: **file input**
|
|
6
|
+
* Resume supported: **yes**
|
|
7
|
+
* Cleanup supported: **yes**
|
|
8
|
+
|
|
9
|
+
## Usage
|
|
10
|
+
|
|
11
|
+
### Install plugin
|
|
12
|
+
|
|
13
|
+
```
|
|
14
|
+
embulk gem install embulk-input-gcs
|
|
15
|
+
```
|
|
16
|
+
|
|
17
|
+
### Google Service Account Settings
|
|
18
|
+
1. Make project at [Google Developers Console](https://console.developers.google.com/project).
|
|
19
|
+
|
|
20
|
+
1. Make "Service Account" with [this step](https://cloud.google.com/storage/docs/authentication#service_accounts).
|
|
21
|
+
|
|
22
|
+
Service Account has two specific scopes: read-only, read-write.
|
|
23
|
+
|
|
24
|
+
embulk-input-gcs can run "read-only" scopes.
|
|
25
|
+
|
|
26
|
+
1. Generate private key in P12(PKCS12) format, and upload to machine.
|
|
27
|
+
|
|
28
|
+
1. Write "EMAIL_ADDRESS" and fullpath of PKCS12 private key in yaml.
|
|
29
|
+
|
|
30
|
+
### run
|
|
31
|
+
|
|
32
|
+
```
|
|
33
|
+
embulk run /path/to/config.yml
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
## Configuration
|
|
37
|
+
|
|
38
|
+
- **bucket** Google Cloud Storage bucket name (string, required)
|
|
39
|
+
- **path_prefix** prefix of target keys (string, required)
|
|
40
|
+
- **service_accound_email** Google Cloud Storage service_account_email (string, required)
|
|
41
|
+
- **p12_keyfile_fullpath** fullpath of p12 key (string, required)
|
|
42
|
+
- **application_name** application name anything you like (string, optional)
|
|
43
|
+
|
|
44
|
+
## Example
|
|
45
|
+
|
|
46
|
+
```yaml
|
|
47
|
+
in:
|
|
48
|
+
type: gcs
|
|
49
|
+
bucket: my-gcs-bucket
|
|
50
|
+
path_prefix: logs/csv-
|
|
51
|
+
service_accound_email: ABCXYZ123ABCXYZ123.gserviceaccount.com
|
|
52
|
+
p12_keyfile_path: /path/to/p12_keyfile.p12
|
|
53
|
+
application_name: Anything you like
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
Example for "sample_01.csv.gz" , generated by [embulk example](https://github.com/embulk/embulk#trying-examples)
|
|
57
|
+
|
|
58
|
+
```yaml
|
|
59
|
+
in:
|
|
60
|
+
type: gcs
|
|
61
|
+
bucket: my-gcs-bucket
|
|
62
|
+
path_prefix: sample_
|
|
63
|
+
service_accound_email: ABCXYZ123ABCXYZ123.gserviceaccount.com
|
|
64
|
+
p12_keyfile_path: /path/to/p12_keyfile.p12
|
|
65
|
+
application_name: Anything you like
|
|
66
|
+
decoders:
|
|
67
|
+
- {type: gzip}
|
|
68
|
+
parser:
|
|
69
|
+
charset: UTF-8
|
|
70
|
+
newline: CRLF
|
|
71
|
+
type: csv
|
|
72
|
+
delimiter: ','
|
|
73
|
+
quote: '"'
|
|
74
|
+
header_line: true
|
|
75
|
+
columns:
|
|
76
|
+
- {name: id, type: long}
|
|
77
|
+
- {name: account, type: long}
|
|
78
|
+
- {name: time, type: timestamp, format: '%Y-%m-%d %H:%M:%S'}
|
|
79
|
+
- {name: purchase, type: timestamp, format: '%Y%m%d'}
|
|
80
|
+
- {name: comment, type: string}
|
|
81
|
+
out: {type: stdout}
|
|
82
|
+
```
|
|
83
|
+
|
|
84
|
+
## Build
|
|
85
|
+
|
|
86
|
+
```
|
|
87
|
+
./gradlew gem
|
|
88
|
+
```
|
|
89
|
+
|
data/build.gradle
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
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:0.4.10"
|
|
19
|
+
provided "org.embulk:embulk-core:0.4.10"
|
|
20
|
+
|
|
21
|
+
compile "com.google.http-client:google-http-client-jackson2:1.19.0"
|
|
22
|
+
compile ("com.google.apis:google-api-services-storage:v1-rev27-1.19.1") {exclude module: "guava-jdk5"}
|
|
23
|
+
|
|
24
|
+
testCompile "junit:junit:4.+"
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
task classpath(type: Copy, dependsOn: ["jar"]) {
|
|
28
|
+
doFirst { file("classpath").deleteDir() }
|
|
29
|
+
from (configurations.runtime - configurations.provided + files(jar.archivePath))
|
|
30
|
+
into "classpath"
|
|
31
|
+
}
|
|
32
|
+
clean { delete 'classpath' }
|
|
33
|
+
|
|
34
|
+
task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
|
|
35
|
+
jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
|
|
36
|
+
script "build/gemspec"
|
|
37
|
+
doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
task gemspec << { file("build/gemspec").write($/
|
|
41
|
+
Gem::Specification.new do |spec|
|
|
42
|
+
spec.name = "${project.name}"
|
|
43
|
+
spec.version = "${project.version}"
|
|
44
|
+
spec.authors = ["Satoshi Akama"]
|
|
45
|
+
spec.summary = %[Google Cloud Storage input plugin for Embulk]
|
|
46
|
+
spec.description = %[gcs input plugin is an Embulk plugin that loads records from Google Cloud Storage. read by any input plugins. Search the output plugins by 'embulk-output' keyword.]
|
|
47
|
+
spec.email = ["satoshiakama@gmail.com"]
|
|
48
|
+
spec.licenses = ["Apache-2.0"]
|
|
49
|
+
spec.homepage = "https://github.com/sakama/embulk-input-gcs"
|
|
50
|
+
|
|
51
|
+
spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
|
|
52
|
+
spec.test_files = spec.files.grep(%r"^(test|spec)/")
|
|
53
|
+
spec.require_paths = ["lib"]
|
|
54
|
+
|
|
55
|
+
spec.add_development_dependency 'bundler', ['~> 1.0']
|
|
56
|
+
spec.add_development_dependency 'rake', ['>= 10.0']
|
|
57
|
+
end
|
|
58
|
+
/$)
|
|
59
|
+
}
|
|
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
|
data/settings.gradle
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
1
|
+
package org.embulk.input.gcs;
|
|
2
|
+
|
|
3
|
+
import java.util.List;
|
|
4
|
+
import java.util.Arrays;
|
|
5
|
+
import java.util.ArrayList;
|
|
6
|
+
import java.util.Collections;
|
|
7
|
+
import java.io.File;
|
|
8
|
+
import java.io.IOException;
|
|
9
|
+
import java.io.InputStream;
|
|
10
|
+
import java.math.BigInteger;
|
|
11
|
+
import com.google.common.collect.ImmutableList;
|
|
12
|
+
import com.google.common.base.Optional;
|
|
13
|
+
import java.security.GeneralSecurityException;
|
|
14
|
+
|
|
15
|
+
import org.embulk.config.CommitReport;
|
|
16
|
+
import org.embulk.config.Config;
|
|
17
|
+
import org.embulk.config.ConfigInject;
|
|
18
|
+
import org.embulk.config.ConfigDiff;
|
|
19
|
+
import org.embulk.config.ConfigDefault;
|
|
20
|
+
import org.embulk.config.ConfigSource;
|
|
21
|
+
import org.embulk.config.Task;
|
|
22
|
+
import org.embulk.config.TaskSource;
|
|
23
|
+
import org.embulk.config.CommitReport;
|
|
24
|
+
import org.embulk.spi.Exec;
|
|
25
|
+
import org.embulk.spi.BufferAllocator;
|
|
26
|
+
import org.embulk.spi.FileInputPlugin;
|
|
27
|
+
import org.embulk.spi.TransactionalFileInput;
|
|
28
|
+
import org.embulk.spi.util.InputStreamFileInput;
|
|
29
|
+
|
|
30
|
+
import org.slf4j.Logger;
|
|
31
|
+
|
|
32
|
+
import com.google.api.client.googleapis.auth.oauth2.GoogleCredential;
|
|
33
|
+
import com.google.api.client.googleapis.javanet.GoogleNetHttpTransport;
|
|
34
|
+
import com.google.api.client.http.HttpTransport;
|
|
35
|
+
import com.google.api.client.json.JsonFactory;
|
|
36
|
+
import com.google.api.client.json.jackson2.JacksonFactory;
|
|
37
|
+
import com.google.api.services.storage.Storage;
|
|
38
|
+
import com.google.api.services.storage.StorageScopes;
|
|
39
|
+
import com.google.api.services.storage.model.Bucket;
|
|
40
|
+
import com.google.api.services.storage.model.Objects;
|
|
41
|
+
import com.google.api.services.storage.model.StorageObject;
|
|
42
|
+
|
|
43
|
+
public class GcsFileInputPlugin
|
|
44
|
+
implements FileInputPlugin
|
|
45
|
+
{
|
|
46
|
+
public interface PluginTask
|
|
47
|
+
extends Task
|
|
48
|
+
{
|
|
49
|
+
@Config("bucket")
|
|
50
|
+
public String getBucket();
|
|
51
|
+
|
|
52
|
+
@Config("path_prefix")
|
|
53
|
+
public String getPathPrefix();
|
|
54
|
+
|
|
55
|
+
@Config("last_path")
|
|
56
|
+
@ConfigDefault("null")
|
|
57
|
+
public Optional<String> getLastPath();
|
|
58
|
+
|
|
59
|
+
@Config("service_accound_email")
|
|
60
|
+
public String getServiceAccountEmail();
|
|
61
|
+
|
|
62
|
+
@Config("application_name")
|
|
63
|
+
// @todo I want to set default applicaiton name like "embulk-input-gcs". But string format cause JsonParseException.
|
|
64
|
+
@ConfigDefault("1000000000")
|
|
65
|
+
public String getApplicationName();
|
|
66
|
+
|
|
67
|
+
@Config("p12_keyfile_fullpath")
|
|
68
|
+
public String getP12KeyfileFullpath();
|
|
69
|
+
|
|
70
|
+
public List<String> getFiles();
|
|
71
|
+
public void setFiles(List<String> files);
|
|
72
|
+
|
|
73
|
+
@ConfigInject
|
|
74
|
+
public BufferAllocator getBufferAllocator();
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
private static final Logger log = Exec.getLogger(GcsFileInputPlugin.class);
|
|
78
|
+
private static HttpTransport httpTransport;
|
|
79
|
+
private static JsonFactory jsonFactory;
|
|
80
|
+
|
|
81
|
+
@Override
|
|
82
|
+
public ConfigDiff transaction(ConfigSource config,
|
|
83
|
+
FileInputPlugin.Control control)
|
|
84
|
+
{
|
|
85
|
+
final PluginTask task = config.loadConfig(PluginTask.class);
|
|
86
|
+
|
|
87
|
+
try {
|
|
88
|
+
httpTransport = GoogleNetHttpTransport.newTrustedTransport();
|
|
89
|
+
jsonFactory = new JacksonFactory();
|
|
90
|
+
} catch (Exception e) {
|
|
91
|
+
log.warn("Could not generate http transport");
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
// list files recursively
|
|
95
|
+
task.setFiles(listFiles(task));
|
|
96
|
+
// number of processors is same with number of files
|
|
97
|
+
return resume(task.dump(), task.getFiles().size(), control);
|
|
98
|
+
}
|
|
99
|
+
|
|
100
|
+
@Override
|
|
101
|
+
public ConfigDiff resume(TaskSource taskSource,
|
|
102
|
+
int taskCount,
|
|
103
|
+
FileInputPlugin.Control control)
|
|
104
|
+
{
|
|
105
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
106
|
+
|
|
107
|
+
control.run(taskSource, taskCount);
|
|
108
|
+
|
|
109
|
+
List<String> files = new ArrayList<String>(task.getFiles());
|
|
110
|
+
if (files.size() == 0) {
|
|
111
|
+
return null;
|
|
112
|
+
}
|
|
113
|
+
Collections.sort(files);
|
|
114
|
+
return Exec.newConfigDiff().
|
|
115
|
+
set("last_path", files.get(files.size() - 1));
|
|
116
|
+
}
|
|
117
|
+
|
|
118
|
+
@Override
|
|
119
|
+
public void cleanup(TaskSource taskSource,
|
|
120
|
+
int taskCount,
|
|
121
|
+
List<CommitReport> successCommitReports)
|
|
122
|
+
{
|
|
123
|
+
}
|
|
124
|
+
|
|
125
|
+
/**
|
|
126
|
+
* @see https://developers.google.com/accounts/docs/OAuth2ServiceAccount#authorizingrequests
|
|
127
|
+
*/
|
|
128
|
+
private static GoogleCredential getCredentialProvider (PluginTask task)
|
|
129
|
+
{
|
|
130
|
+
try {
|
|
131
|
+
// @see https://cloud.google.com/compute/docs/api/how-tos/authorization
|
|
132
|
+
// @see https://developers.google.com/resources/api-libraries/documentation/storage/v1/java/latest/com/google/api/services/storage/STORAGE_SCOPE.html
|
|
133
|
+
GoogleCredential cred = new GoogleCredential.Builder().setTransport(httpTransport)
|
|
134
|
+
.setJsonFactory(jsonFactory)
|
|
135
|
+
.setServiceAccountId(task.getServiceAccountEmail())
|
|
136
|
+
.setServiceAccountScopes(
|
|
137
|
+
ImmutableList.of(
|
|
138
|
+
StorageScopes.DEVSTORAGE_READ_ONLY
|
|
139
|
+
)
|
|
140
|
+
)
|
|
141
|
+
.setServiceAccountPrivateKeyFromP12File(new File(task.getP12KeyfileFullpath()))
|
|
142
|
+
.build();
|
|
143
|
+
return cred;
|
|
144
|
+
} catch (IOException e) {
|
|
145
|
+
log.warn("Could not load client secrets file " + task.getP12KeyfileFullpath());
|
|
146
|
+
} catch (GeneralSecurityException e) {
|
|
147
|
+
log.warn ("Google Authentication was failed");
|
|
148
|
+
}
|
|
149
|
+
return null;
|
|
150
|
+
}
|
|
151
|
+
|
|
152
|
+
private static Storage newGcsClient(PluginTask task)
|
|
153
|
+
{
|
|
154
|
+
GoogleCredential credentials = getCredentialProvider(task);
|
|
155
|
+
Storage client = new Storage.Builder(httpTransport, jsonFactory, credentials)
|
|
156
|
+
.setApplicationName(task.getApplicationName())
|
|
157
|
+
.build();
|
|
158
|
+
|
|
159
|
+
return client;
|
|
160
|
+
}
|
|
161
|
+
|
|
162
|
+
public List<String> listFiles(PluginTask task)
|
|
163
|
+
{
|
|
164
|
+
Storage client = newGcsClient(task);
|
|
165
|
+
String bucket = task.getBucket();
|
|
166
|
+
|
|
167
|
+
return listGcsFilesByPrefix(client, bucket, task.getPathPrefix(), task.getLastPath());
|
|
168
|
+
}
|
|
169
|
+
|
|
170
|
+
/**
|
|
171
|
+
* Lists GCS filenames filtered by prefix.
|
|
172
|
+
*
|
|
173
|
+
* The resulting list does not include the file that's size == 0.
|
|
174
|
+
*/
|
|
175
|
+
public static List<String> listGcsFilesByPrefix(Storage client, String bucket,
|
|
176
|
+
String prefix, Optional<String> lastPath)
|
|
177
|
+
{
|
|
178
|
+
ImmutableList.Builder<String> builder = ImmutableList.builder();
|
|
179
|
+
|
|
180
|
+
String lastKey = lastPath.orNull();
|
|
181
|
+
|
|
182
|
+
// @see https://cloud.google.com/storage/docs/json_api/v1/objects#resource
|
|
183
|
+
try {
|
|
184
|
+
Storage.Buckets.Get getBucket = client.buckets().get(bucket);
|
|
185
|
+
getBucket.setProjection("full");
|
|
186
|
+
Bucket bk = getBucket.execute();
|
|
187
|
+
if (log.isDebugEnabled()) {
|
|
188
|
+
log.debug("bucket name: " + bucket);
|
|
189
|
+
log.debug("bucket location: " + bk.getLocation());
|
|
190
|
+
log.debug("bucket timeCreated: " + bk.getTimeCreated());
|
|
191
|
+
log.debug("bucket owner: " + bk.getOwner());
|
|
192
|
+
}
|
|
193
|
+
} catch (Exception e) {
|
|
194
|
+
log.warn("Could not access to bucket:" + bucket);
|
|
195
|
+
log.warn(e.getMessage());
|
|
196
|
+
}
|
|
197
|
+
|
|
198
|
+
|
|
199
|
+
try {
|
|
200
|
+
// @see https://cloud.google.com/storage/docs/json_api/v1/objects/list
|
|
201
|
+
Storage.Objects.List listObjects = client.objects().list(bucket);
|
|
202
|
+
listObjects.setPrefix(prefix);
|
|
203
|
+
listObjects.setPageToken(lastKey);
|
|
204
|
+
do {
|
|
205
|
+
Objects objects = listObjects.execute();
|
|
206
|
+
List<StorageObject> items = objects.getItems();
|
|
207
|
+
if (items == null) {
|
|
208
|
+
log.info("No file was found in bucket:" + bucket + " prefix:" + prefix);
|
|
209
|
+
break;
|
|
210
|
+
}
|
|
211
|
+
for (StorageObject o : items) {
|
|
212
|
+
if (log.isDebugEnabled()) {
|
|
213
|
+
log.debug("filename: " + o.getName());
|
|
214
|
+
log.debug("updated: " + o.getUpdated());
|
|
215
|
+
}
|
|
216
|
+
if (o.getSize().compareTo(BigInteger.ZERO) > 0) {
|
|
217
|
+
builder.add(o.getName());
|
|
218
|
+
}
|
|
219
|
+
}
|
|
220
|
+
lastKey = objects.getNextPageToken();
|
|
221
|
+
listObjects.setPageToken(lastKey);
|
|
222
|
+
} while (lastKey != null);
|
|
223
|
+
} catch (Exception e) {
|
|
224
|
+
log.warn("Could not get file list from bucket:" + bucket);
|
|
225
|
+
log.warn(e.getMessage());
|
|
226
|
+
}
|
|
227
|
+
|
|
228
|
+
return builder.build();
|
|
229
|
+
}
|
|
230
|
+
|
|
231
|
+
@Override
|
|
232
|
+
public TransactionalFileInput open(TaskSource taskSource, int taskIndex)
|
|
233
|
+
{
|
|
234
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
|
235
|
+
return new GcsFileInput(task, taskIndex);
|
|
236
|
+
}
|
|
237
|
+
|
|
238
|
+
public static class GcsFileInput
|
|
239
|
+
extends InputStreamFileInput
|
|
240
|
+
implements TransactionalFileInput
|
|
241
|
+
{
|
|
242
|
+
private static class SingleFileProvider
|
|
243
|
+
implements InputStreamFileInput.Provider
|
|
244
|
+
{
|
|
245
|
+
private final Storage client;
|
|
246
|
+
private final String bucket;
|
|
247
|
+
private final String key;
|
|
248
|
+
private boolean opened = false;
|
|
249
|
+
|
|
250
|
+
public SingleFileProvider(PluginTask task, int taskIndex)
|
|
251
|
+
{
|
|
252
|
+
this.client = newGcsClient(task);
|
|
253
|
+
this.bucket = task.getBucket();
|
|
254
|
+
this.key = task.getFiles().get(taskIndex);
|
|
255
|
+
}
|
|
256
|
+
|
|
257
|
+
@Override
|
|
258
|
+
public InputStream openNext() throws IOException
|
|
259
|
+
{
|
|
260
|
+
if (opened) {
|
|
261
|
+
return null;
|
|
262
|
+
}
|
|
263
|
+
opened = true;
|
|
264
|
+
Storage.Objects.Get getObject = client.objects().get(bucket, key);
|
|
265
|
+
|
|
266
|
+
return getObject.executeMediaAsInputStream();
|
|
267
|
+
}
|
|
268
|
+
|
|
269
|
+
@Override
|
|
270
|
+
public void close() { }
|
|
271
|
+
}
|
|
272
|
+
|
|
273
|
+
public GcsFileInput(PluginTask task, int taskIndex)
|
|
274
|
+
{
|
|
275
|
+
super(task.getBufferAllocator(), new SingleFileProvider(task, taskIndex));
|
|
276
|
+
}
|
|
277
|
+
|
|
278
|
+
public void abort() { }
|
|
279
|
+
|
|
280
|
+
public CommitReport commit()
|
|
281
|
+
{
|
|
282
|
+
return Exec.newCommitReport();
|
|
283
|
+
}
|
|
284
|
+
|
|
285
|
+
@Override
|
|
286
|
+
public void close() { }
|
|
287
|
+
}
|
|
288
|
+
}
|
metadata
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: embulk-input-gcs
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Satoshi Akama
|
|
8
|
+
autorequire:
|
|
9
|
+
bindir: bin
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 2015-03-01 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: gcs input plugin is an Embulk plugin that loads records from Google Cloud Storage. read by any input plugins. Search the output plugins by 'embulk-output' keyword.
|
|
42
|
+
email:
|
|
43
|
+
- satoshiakama@gmail.com
|
|
44
|
+
executables: []
|
|
45
|
+
extensions: []
|
|
46
|
+
extra_rdoc_files: []
|
|
47
|
+
files:
|
|
48
|
+
- .gitignore
|
|
49
|
+
- README.md
|
|
50
|
+
- build.gradle
|
|
51
|
+
- gradle/wrapper/gradle-wrapper.jar
|
|
52
|
+
- gradle/wrapper/gradle-wrapper.properties
|
|
53
|
+
- gradlew
|
|
54
|
+
- gradlew.bat
|
|
55
|
+
- lib/embulk/input/gcs.rb
|
|
56
|
+
- settings.gradle
|
|
57
|
+
- src/main/java/org/embulk/input/gcs/GcsFileInputPlugin.java
|
|
58
|
+
- src/test/java/org/embulk/input/gcs/TestGcsFileInputPlugin.java
|
|
59
|
+
- classpath/commons-codec-1.3.jar
|
|
60
|
+
- classpath/commons-logging-1.1.1.jar
|
|
61
|
+
- classpath/embulk-input-gcs-0.1.0.jar
|
|
62
|
+
- classpath/google-api-client-1.19.1.jar
|
|
63
|
+
- classpath/google-api-services-storage-v1-rev27-1.19.1.jar
|
|
64
|
+
- classpath/google-http-client-1.19.0.jar
|
|
65
|
+
- classpath/google-http-client-jackson2-1.19.0.jar
|
|
66
|
+
- classpath/google-oauth-client-1.19.0.jar
|
|
67
|
+
- classpath/httpclient-4.0.1.jar
|
|
68
|
+
- classpath/httpcore-4.0.1.jar
|
|
69
|
+
- classpath/jsr305-1.3.9.jar
|
|
70
|
+
homepage: https://github.com/sakama/embulk-input-gcs
|
|
71
|
+
licenses:
|
|
72
|
+
- Apache-2.0
|
|
73
|
+
metadata: {}
|
|
74
|
+
post_install_message:
|
|
75
|
+
rdoc_options: []
|
|
76
|
+
require_paths:
|
|
77
|
+
- lib
|
|
78
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - '>='
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '0'
|
|
83
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
84
|
+
requirements:
|
|
85
|
+
- - '>='
|
|
86
|
+
- !ruby/object:Gem::Version
|
|
87
|
+
version: '0'
|
|
88
|
+
requirements: []
|
|
89
|
+
rubyforge_project:
|
|
90
|
+
rubygems_version: 2.1.9
|
|
91
|
+
signing_key:
|
|
92
|
+
specification_version: 4
|
|
93
|
+
summary: Google Cloud Storage input plugin for Embulk
|
|
94
|
+
test_files: []
|