embulk-input-s3 0.1.7 → 0.2.0

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.
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: embulk-input-s3
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.1.7
4
+ version: 0.2.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Sadayuki Furuhashi
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2015-03-27 00:00:00.000000000 Z
11
+ date: 2015-06-26 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: bundler
@@ -45,17 +45,9 @@ executables: []
45
45
  extensions: []
46
46
  extra_rdoc_files: []
47
47
  files:
48
- - .gitignore
49
- - ChangeLog
50
- - README.md
51
48
  - build.gradle
52
- - gradle/wrapper/gradle-wrapper.jar
53
- - gradle/wrapper/gradle-wrapper.properties
54
- - gradlew
55
- - gradlew.bat
56
49
  - lib/embulk/input/s3.rb
57
- - src/main/java/org/embulk/input/s3/RetryExecutor.java
58
- - src/main/java/org/embulk/input/s3/RetryableInputStream.java
50
+ - src/main/java/org/embulk/input/s3/AbstractS3FileInputPlugin.java
59
51
  - src/main/java/org/embulk/input/s3/S3FileInputPlugin.java
60
52
  - src/test/java/org/embulk/input/s3/TestS3FileInputPlugin.java
61
53
  - classpath/aws-java-sdk-core-1.9.22.jar
@@ -63,9 +55,10 @@ files:
63
55
  - classpath/aws-java-sdk-s3-1.9.22.jar
64
56
  - classpath/commons-codec-1.6.jar
65
57
  - classpath/commons-logging-1.1.3.jar
66
- - classpath/embulk-input-s3-0.1.7.jar
58
+ - classpath/embulk-input-s3-0.2.0.jar
67
59
  - classpath/httpclient-4.3.4.jar
68
60
  - classpath/httpcore-4.3.2.jar
61
+ - classpath/joda-time-2.8.1.jar
69
62
  homepage: https://github.com/embulk/embulk-input-s3
70
63
  licenses:
71
64
  - Apache 2.0
data/.gitignore DELETED
@@ -1,6 +0,0 @@
1
- *~
2
- .idea
3
- build/
4
- /classpath/
5
- /.gradle
6
- /*.gem
data/ChangeLog DELETED
@@ -1,25 +0,0 @@
1
- Release 0.1.7 - 2015-03-27
2
-
3
- * Keep last_path in case of no input files
4
-
5
- Release 0.1.6 - 2015-03-27
6
-
7
- * Fixed error when there are no input files
8
-
9
- Release 0.1.5 - 2015-03-23
10
-
11
- * Implemented retrying
12
-
13
- Release 0.1.3 - 2015-02-25
14
-
15
- * Upgraded aws-sdk to 1.9.22
16
-
17
- Release 0.1.2 - 2015-02-20
18
-
19
- * Sets last_path to the next config.
20
- * Upgraded embulk version to 0.4.6.
21
-
22
- Release 0.1.1 - 2015-02-20
23
-
24
- * Upgraded embulk version to 0.4.2.
25
-
data/README.md DELETED
@@ -1,34 +0,0 @@
1
- # S3 file input plugin for Embulk
2
-
3
- ## Overview
4
-
5
- * Plugin type: **file input**
6
- * Resume supported: **yes**
7
- * Cleanup supported: **yes**
8
-
9
- ## Configuration
10
-
11
- - **bucket** S3 bucket name (string, required)
12
- - **path_prefix** prefix of target keys (string, required)
13
- - **endpoint** S3 endpoint login user name (string, optional)
14
- - **access_key_id** AWS access key id (string, required)
15
- - **secret_access_key** AWS secret key (string, required)
16
-
17
- ## Example
18
-
19
- ```yaml
20
- in:
21
- type: s3
22
- bucket: my-s3-bucket
23
- path_prefix: logs/csv-
24
- endpoint: s3-us-west-1.amazonaws.com
25
- access_key_id: ABCXYZ123ABCXYZ123
26
- secret_access_key: AbCxYz123aBcXyZ123
27
- ```
28
-
29
- ## Build
30
-
31
- ```
32
- ./gradlew gem
33
- ```
34
-
@@ -1,6 +0,0 @@
1
- #Wed Feb 04 13:46:12 PST 2015
2
- distributionBase=GRADLE_USER_HOME
3
- distributionPath=wrapper/dists
4
- zipStoreBase=GRADLE_USER_HOME
5
- zipStorePath=wrapper/dists
6
- distributionUrl=https\://services.gradle.org/distributions/gradle-2.2.1-bin.zip
data/gradlew DELETED
@@ -1,164 +0,0 @@
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 "$@"
@@ -1,90 +0,0 @@
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
@@ -1,130 +0,0 @@
1
- package org.embulk.input.s3;
2
-
3
- import java.util.concurrent.Callable;
4
- import java.util.concurrent.ExecutionException;
5
-
6
- public class RetryExecutor
7
- {
8
- public static RetryExecutor retryExecutor()
9
- {
10
- // TODO default configuration
11
- return new RetryExecutor(3, 500, 30*60*1000);
12
- }
13
-
14
- public static class RetryGiveupException
15
- extends ExecutionException
16
- {
17
- public RetryGiveupException(String message, Exception cause)
18
- {
19
- super(cause);
20
- }
21
-
22
- public RetryGiveupException(Exception cause)
23
- {
24
- super(cause);
25
- }
26
-
27
- public Exception getCause()
28
- {
29
- return (Exception) super.getCause();
30
- }
31
- }
32
-
33
- public static interface Retryable<T>
34
- extends Callable<T>
35
- {
36
- public T call()
37
- throws Exception;
38
-
39
- public boolean isRetryableException(Exception exception);
40
-
41
- public void onRetry(Exception exception, int retryCount, int retryLimit, int retryWait)
42
- throws RetryGiveupException;
43
-
44
- public void onGiveup(Exception firstException, Exception lastException)
45
- throws RetryGiveupException;
46
- }
47
-
48
- private final int retryLimit;
49
- private final int initialRetryWait;
50
- private final int maxRetryWait;
51
-
52
- private RetryExecutor(int retryLimit, int initialRetryWait, int maxRetryWait)
53
- {
54
- this.retryLimit = retryLimit;
55
- this.initialRetryWait = initialRetryWait;
56
- this.maxRetryWait = maxRetryWait;
57
- }
58
-
59
- public RetryExecutor withRetryLimit(int count)
60
- {
61
- return new RetryExecutor(count, initialRetryWait, maxRetryWait);
62
- }
63
-
64
- public RetryExecutor withInitialRetryWait(int msec)
65
- {
66
- return new RetryExecutor(retryLimit, msec, maxRetryWait);
67
- }
68
-
69
- public RetryExecutor withMaxRetryWait(int msec)
70
- {
71
- return new RetryExecutor(retryLimit, initialRetryWait, msec);
72
- }
73
-
74
- public <T> T runInterruptible(Retryable<T> op)
75
- throws InterruptedException, RetryGiveupException
76
- {
77
- return run(op, true);
78
- }
79
-
80
- public <T> T run(Retryable<T> op)
81
- throws RetryGiveupException
82
- {
83
- try {
84
- return run(op, false);
85
- } catch (InterruptedException ex) {
86
- throw new RetryGiveupException("Unexpected interruption", ex);
87
- }
88
- }
89
-
90
- private <T> T run(Retryable<T> op, boolean interruptible)
91
- throws InterruptedException, RetryGiveupException
92
- {
93
- int retryWait = initialRetryWait;
94
- int retryCount = 0;
95
-
96
- Exception firstException = null;
97
-
98
- while(true) {
99
- try {
100
- return op.call();
101
- } catch (Exception exception) {
102
- if (firstException == null) {
103
- firstException = exception;
104
- }
105
- if (!op.isRetryableException(exception) || retryCount >= retryLimit) {
106
- op.onGiveup(firstException, exception);
107
- throw new RetryGiveupException(firstException);
108
- }
109
-
110
- retryCount++;
111
- op.onRetry(exception, retryCount, retryLimit, retryWait);
112
-
113
- try {
114
- Thread.sleep(retryWait);
115
- } catch (InterruptedException ex) {
116
- if (interruptible) {
117
- throw ex;
118
- }
119
- }
120
-
121
- // exponential back-off with hard limit
122
- retryWait *= 2;
123
- if (retryWait > maxRetryWait) {
124
- retryWait = maxRetryWait;
125
- }
126
- }
127
- }
128
- }
129
- }
130
-