embulk-input-s3 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.
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: a189f02204b02562ddf626857a6fd8a0d07d41f1
4
+ data.tar.gz: bc27649cbbf48e4052cbac15f548e451e990e36f
5
+ SHA512:
6
+ metadata.gz: abef90a11eafb493f993812835d04cfbd268ea805408c9aaffd82b12723b5b5360b7f840575f38653f64d1caad5140c0397c44a0344990c79df5efe083b0eb13
7
+ data.tar.gz: 8e489005081d3efd5d6cb2b9c1e1342f0172323705ab6728938ab2a9fe98c4a948c127848ec003dd83bb96418225b4f06bde35e5449a368304ed438b9cfef173
@@ -0,0 +1,6 @@
1
+ *~
2
+ .idea
3
+ build/
4
+ /classpath/
5
+ /.gradle
6
+ /*.gem
@@ -0,0 +1,34 @@
1
+ # S3 file input plugin for Embulk
2
+
3
+ ## Overview
4
+
5
+ * Plugin type: **file input**
6
+ * Rollback supported: **yes**
7
+ * Resume supported: **yes**
8
+ * Cleanup supported: **yes**
9
+
10
+ ## Configuration
11
+
12
+ - **bucket** S3 bucket name (string, required)
13
+ - **path_prefix** prefix of target keys (string, required)
14
+ - **endpoint** S3 endpoint login user name (string, optional)
15
+ - **access_key_id** AWS access key id (string, required)
16
+ - **secret_access_key** AWS secret key (string, required)
17
+
18
+ ## Example
19
+
20
+ ```yaml
21
+ in:
22
+ type: s3
23
+ bucket: my-s3-bucket
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
+
@@ -0,0 +1,62 @@
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
+ mavenLocal()
10
+ jcenter()
11
+ }
12
+ configurations {
13
+ provided
14
+ }
15
+
16
+ version = "0.1.0"
17
+
18
+ dependencies {
19
+ compile "org.embulk:embulk-core:0.4.0"
20
+ provided "org.embulk:embulk-core:0.4.0"
21
+ compile "com.amazonaws:aws-java-sdk-s3:1.9.17"
22
+ testCompile "junit:junit:4.+"
23
+ testCompile "org.mockito:mockito-core:1.+"
24
+ }
25
+
26
+ task classpath(type: Copy, dependsOn: ["jar"]) {
27
+ doFirst { file("classpath").deleteDir() }
28
+ from (configurations.runtime - configurations.provided + files(jar.archivePath))
29
+ into "classpath"
30
+ }
31
+ clean { delete 'classpath' }
32
+
33
+ task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
34
+ jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
35
+ script "build/gemspec"
36
+ doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
37
+ }
38
+
39
+ task gemspec << { file("build/gemspec").write($/
40
+ Gem::Specification.new do |gem|
41
+ gem.summary = "S3 file input plugin for Embulk, a plugin-based parallel bulk data loader"
42
+
43
+ gem.name = "${project.name}"
44
+ gem.version = "${project.version}"
45
+ gem.description = gem.summary
46
+ gem.authors = ["Sadayuki Furuhashi"]
47
+ gem.email = ["frsyuki@gmail.com"]
48
+ gem.license = "Apache 2.0"
49
+ gem.homepage = "https://github.com/embulk/embulk-input-s3"
50
+
51
+ gem.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
52
+ gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
53
+ gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
54
+ gem.require_paths = ["lib"]
55
+ gem.has_rdoc = false
56
+
57
+ gem.add_development_dependency "bundler", [">= 1.0"]
58
+ gem.add_development_dependency "rake", [">= 0.10.0"]
59
+ gem.add_development_dependency "test-unit", ["~> 3.0.2"]
60
+ end
61
+ /$)
62
+ }
@@ -0,0 +1,6 @@
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 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 "$@"
@@ -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 +1,3 @@
1
+ Embulk::JavaPlugin.register_input(
2
+ :s3, "org.embulk.input.s3.S3FileInputPlugin",
3
+ File.expand_path('../../../../classpath', __FILE__))
@@ -0,0 +1,268 @@
1
+ package org.embulk.input.s3;
2
+
3
+ import java.util.List;
4
+ import java.io.File;
5
+ import java.io.FileInputStream;
6
+ import java.io.InputStream;
7
+ import java.io.IOException;
8
+ import java.nio.file.Path;
9
+ import java.nio.file.Paths;
10
+ import java.nio.file.Files;
11
+ import java.nio.file.SimpleFileVisitor;
12
+ import java.nio.file.FileVisitResult;
13
+ import java.nio.file.attribute.BasicFileAttributes;
14
+ import javax.validation.constraints.NotNull;
15
+ import com.google.common.collect.ImmutableList;
16
+ import com.fasterxml.jackson.annotation.JacksonInject;
17
+ import org.embulk.config.Config;
18
+ import org.embulk.config.Task;
19
+ import org.embulk.config.TaskSource;
20
+ import org.embulk.config.ConfigSource;
21
+ import org.embulk.config.ConfigDiff;
22
+ import org.embulk.config.CommitReport;
23
+ import org.embulk.spi.BufferAllocator;
24
+ import org.embulk.spi.Exec;
25
+ import org.embulk.spi.FileInputPlugin;
26
+ import org.embulk.spi.TransactionalFileInput;
27
+ import org.embulk.spi.util.InputStreamFileInput;
28
+ import org.slf4j.Logger;
29
+
30
+ import static org.embulk.spi.util.Inputs.formatPath;
31
+
32
+ import java.util.List;
33
+ import java.io.IOException;
34
+ import java.io.InputStream;
35
+ import com.google.common.collect.ImmutableList;
36
+ import com.google.common.base.Optional;
37
+ import com.fasterxml.jackson.annotation.JacksonInject;
38
+ import com.amazonaws.auth.AWSCredentials;
39
+ import com.amazonaws.auth.AWSCredentialsProvider;
40
+ import com.amazonaws.auth.BasicAWSCredentials;
41
+ import com.amazonaws.services.s3.AmazonS3Client;
42
+ import com.amazonaws.services.s3.model.ListObjectsRequest;
43
+ import com.amazonaws.services.s3.model.S3ObjectSummary;
44
+ import com.amazonaws.services.s3.model.ObjectListing;
45
+ import com.amazonaws.services.s3.model.GetObjectRequest;
46
+ import com.amazonaws.services.s3.model.S3Object;
47
+ import com.amazonaws.ClientConfiguration;
48
+ import com.amazonaws.Protocol;
49
+ import org.embulk.config.Config;
50
+ import org.embulk.config.ConfigDefault;
51
+ import org.embulk.config.Task;
52
+ import org.embulk.config.TaskSource;
53
+ import org.embulk.config.ConfigSource;
54
+ import org.embulk.config.ConfigDiff;
55
+ import org.embulk.config.CommitReport;
56
+ import org.embulk.spi.BufferAllocator;
57
+ import org.embulk.spi.Exec;
58
+ import org.embulk.spi.FileInputPlugin;
59
+ import org.embulk.spi.TransactionalFileInput;
60
+ import org.embulk.spi.util.InputStreamFileInput;
61
+
62
+ public class S3FileInputPlugin
63
+ implements FileInputPlugin
64
+ {
65
+ public interface PluginTask
66
+ extends Task
67
+ {
68
+ @Config("bucket")
69
+ public String getBucket();
70
+
71
+ @Config("path_prefix")
72
+ public String getPathPrefix();
73
+
74
+ @Config("last_path")
75
+ @ConfigDefault("null")
76
+ public Optional<String> getLastPath();
77
+
78
+ @Config("endpoint")
79
+ @ConfigDefault("null")
80
+ public Optional<String> getEndpoint();
81
+
82
+ // TODO timeout, ssl, etc
83
+
84
+ @Config("access_key_id")
85
+ public String getAccessKeyId();
86
+
87
+ @Config("secret_access_key")
88
+ public String getSecretAccessKey();
89
+
90
+ // TODO support more options such as STS
91
+
92
+ public List<String> getFiles();
93
+ public void setFiles(List<String> files);
94
+
95
+ @JacksonInject
96
+ public BufferAllocator getBufferAllocator();
97
+ }
98
+
99
+ @Override
100
+ public ConfigDiff transaction(ConfigSource config, FileInputPlugin.Control control)
101
+ {
102
+ PluginTask task = config.loadConfig(PluginTask.class);
103
+
104
+ // list files recursively
105
+ task.setFiles(listFiles(task));
106
+
107
+ // number of processors is same with number of files
108
+ return resume(task.dump(), task.getFiles().size(), control);
109
+ }
110
+
111
+ @Override
112
+ public ConfigDiff resume(TaskSource taskSource,
113
+ int processorCount,
114
+ FileInputPlugin.Control control)
115
+ {
116
+ control.run(taskSource, processorCount);
117
+ return Exec.newConfigDiff();
118
+ }
119
+
120
+ @Override
121
+ public void cleanup(TaskSource taskSource,
122
+ int processorCount,
123
+ List<CommitReport> successCommitReports)
124
+ {
125
+ // do nothing
126
+ }
127
+
128
+ public static AWSCredentialsProvider getCredentialsProvider(PluginTask task)
129
+ {
130
+ final AWSCredentials cred = new BasicAWSCredentials(
131
+ task.getAccessKeyId(), task.getSecretAccessKey());
132
+ return new AWSCredentialsProvider() {
133
+ public AWSCredentials getCredentials()
134
+ {
135
+ return cred;
136
+ }
137
+
138
+ public void refresh()
139
+ {
140
+ }
141
+ };
142
+ }
143
+
144
+ private static AmazonS3Client newS3Client(PluginTask task)
145
+ {
146
+ AWSCredentialsProvider credentials = getCredentialsProvider(task);
147
+ AmazonS3Client client = newS3Client(credentials, task.getEndpoint());
148
+ return client;
149
+ }
150
+
151
+ private static AmazonS3Client newS3Client(AWSCredentialsProvider credentials,
152
+ Optional<String> endpoint)
153
+ {
154
+ // TODO get config from AmazonS3Task
155
+ ClientConfiguration clientConfig = new ClientConfiguration();
156
+ //clientConfig.setProtocol(Protocol.HTTP);
157
+ clientConfig.setMaxConnections(50); // SDK default: 50
158
+ clientConfig.setMaxErrorRetry(3); // SDK default: 3
159
+ clientConfig.setSocketTimeout(8*60*1000); // SDK default: 50*1000
160
+
161
+ AmazonS3Client client = new AmazonS3Client(credentials, clientConfig);
162
+
163
+ if (endpoint.isPresent()) {
164
+ client.setEndpoint(endpoint.get());
165
+ }
166
+
167
+ return client;
168
+ }
169
+
170
+ public List<String> listFiles(PluginTask task)
171
+ {
172
+ AmazonS3Client client = newS3Client(task);
173
+ String bucketName = task.getBucket();
174
+
175
+ return listS3FilesByPrefix(client, bucketName, task.getPathPrefix(), task.getLastPath());
176
+ }
177
+
178
+ /**
179
+ * Lists S3 filenames filtered by prefix.
180
+ *
181
+ * The resulting list does not include the file that's size == 0.
182
+ */
183
+ public static List<String> listS3FilesByPrefix(AmazonS3Client client, String bucketName,
184
+ String prefix, Optional<String> lastPath)
185
+ {
186
+ ImmutableList.Builder<String> builder = ImmutableList.builder();
187
+
188
+ String lastKey = lastPath.orNull();
189
+ do {
190
+ ListObjectsRequest req = new ListObjectsRequest(bucketName, prefix, lastKey, null, 1024);
191
+ ObjectListing ol = client.listObjects(req);
192
+ for(S3ObjectSummary s : ol.getObjectSummaries()) {
193
+ if (s.getSize() > 0) {
194
+ builder.add(s.getKey());
195
+ }
196
+ }
197
+ lastKey = ol.getNextMarker();
198
+ } while(lastKey != null);
199
+
200
+ return builder.build();
201
+ }
202
+
203
+ @Override
204
+ public TransactionalFileInput open(TaskSource taskSource, int processorIndex)
205
+ {
206
+ PluginTask task = taskSource.loadTask(PluginTask.class);
207
+ return new S3FileInput(task, processorIndex);
208
+ }
209
+
210
+ public static class S3FileInput
211
+ extends InputStreamFileInput
212
+ implements TransactionalFileInput
213
+ {
214
+ // TODO create single-file InputStreamFileInput utility
215
+ private static class SingleFileProvider
216
+ implements InputStreamFileInput.Provider
217
+ {
218
+ private AmazonS3Client client;
219
+ private final String bucket;
220
+ private final String key;
221
+ private boolean opened = false;
222
+
223
+ public SingleFileProvider(PluginTask task, int processorIndex)
224
+ {
225
+ this.client = newS3Client(task);
226
+ this.bucket = task.getBucket();
227
+ this.key = task.getFiles().get(processorIndex);
228
+ }
229
+
230
+ @Override
231
+ public InputStream openNext() throws IOException
232
+ {
233
+ if (opened) {
234
+ return null;
235
+ }
236
+ opened = true;
237
+ GetObjectRequest request = new GetObjectRequest(bucket, key);
238
+ //if (pos > 0) {
239
+ // request.setRange(pos, contentLength);
240
+ //}
241
+ S3Object obj = client.getObject(request);
242
+ //if (pos <= 0) {
243
+ // // first call
244
+ // contentLength = obj.getObjectMetadata().getContentLength();
245
+ //}
246
+ return obj.getObjectContent();
247
+ }
248
+
249
+ @Override
250
+ public void close() { }
251
+ }
252
+
253
+ public S3FileInput(PluginTask task, int processorIndex)
254
+ {
255
+ super(task.getBufferAllocator(), new SingleFileProvider(task, processorIndex));
256
+ }
257
+
258
+ public void abort() { }
259
+
260
+ public CommitReport commit()
261
+ {
262
+ return Exec.newCommitReport();
263
+ }
264
+
265
+ @Override
266
+ public void close() { }
267
+ }
268
+ }
@@ -0,0 +1,42 @@
1
+ package org.embulk.plugin.s3;
2
+
3
+ import static org.junit.Assert.*;
4
+ import java.util.List;
5
+ import org.junit.Test;
6
+ import org.mockito.Mockito;
7
+
8
+ import com.google.common.base.Optional;
9
+ import com.google.common.collect.ImmutableList;
10
+ import com.amazonaws.services.s3.AmazonS3Client;
11
+ import com.amazonaws.services.s3.model.ListObjectsRequest;
12
+ import com.amazonaws.services.s3.model.ObjectListing;
13
+ import com.amazonaws.services.s3.model.S3ObjectSummary;
14
+
15
+ public class TestS3FileInputPlugin
16
+ {
17
+ @Test
18
+ public void listS3FilesByPrefix()
19
+ {
20
+ // AWSS3Client returns list1 for the first iteration and list2 next.
21
+ List<S3ObjectSummary> list1 = ImmutableList.<S3ObjectSummary> of(bucket("in/", 0), bucket("in/file/", 0),
22
+ bucket("in/file/sample.csv.gz", 12345));
23
+ List<S3ObjectSummary> list2 = ImmutableList.<S3ObjectSummary> of(bucket("sample2.csv.gz", 0));
24
+ ObjectListing ol = Mockito.mock(ObjectListing.class);
25
+
26
+ Mockito.doReturn(list1).doReturn(list2).when(ol).getObjectSummaries();
27
+ AmazonS3Client client = Mockito.mock(AmazonS3Client.class);
28
+ Mockito.doReturn(ol).when(client).listObjects(Mockito.any(ListObjectsRequest.class));
29
+ Mockito.doReturn("in/file/").doReturn(null).when(ol).getNextMarker();
30
+
31
+ // It counts only size != 0 files.
32
+ assertEquals(1, S3FileInputPlugin.listS3FilesByPrefix(client, "bucketName", "prefix", Optional.<String>absent()).size());
33
+ }
34
+
35
+ private S3ObjectSummary bucket(String key, long size)
36
+ {
37
+ S3ObjectSummary bucket = new S3ObjectSummary();
38
+ bucket.setKey(key);
39
+ bucket.setSize(size);
40
+ return bucket;
41
+ }
42
+ }
metadata ADDED
@@ -0,0 +1,104 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-input-s3
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Sadayuki Furuhashi
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2015-02-16 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: 0.10.0
34
+ requirement: !ruby/object:Gem::Requirement
35
+ requirements:
36
+ - - '>='
37
+ - !ruby/object:Gem::Version
38
+ version: 0.10.0
39
+ prerelease: false
40
+ type: :development
41
+ - !ruby/object:Gem::Dependency
42
+ name: test-unit
43
+ version_requirements: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ~>
46
+ - !ruby/object:Gem::Version
47
+ version: 3.0.2
48
+ requirement: !ruby/object:Gem::Requirement
49
+ requirements:
50
+ - - ~>
51
+ - !ruby/object:Gem::Version
52
+ version: 3.0.2
53
+ prerelease: false
54
+ type: :development
55
+ description: S3 file input plugin for Embulk, a plugin-based parallel bulk data loader
56
+ email:
57
+ - frsyuki@gmail.com
58
+ executables: []
59
+ extensions: []
60
+ extra_rdoc_files: []
61
+ files:
62
+ - .gitignore
63
+ - README.md
64
+ - build.gradle
65
+ - gradle/wrapper/gradle-wrapper.jar
66
+ - gradle/wrapper/gradle-wrapper.properties
67
+ - gradlew
68
+ - gradlew.bat
69
+ - lib/embulk/input/s3.rb
70
+ - src/main/java/org/embulk/input/s3/S3FileInputPlugin.java
71
+ - src/test/java/org/embulk/plugin/s3/TestS3FileInputPlugin.java
72
+ - classpath/aws-java-sdk-core-1.9.17.jar
73
+ - classpath/aws-java-sdk-kms-1.9.17.jar
74
+ - classpath/aws-java-sdk-s3-1.9.17.jar
75
+ - classpath/commons-codec-1.6.jar
76
+ - classpath/commons-logging-1.1.3.jar
77
+ - classpath/embulk-input-s3-0.1.0.jar
78
+ - classpath/httpclient-4.3.4.jar
79
+ - classpath/httpcore-4.3.2.jar
80
+ homepage: https://github.com/embulk/embulk-input-s3
81
+ licenses:
82
+ - Apache 2.0
83
+ metadata: {}
84
+ post_install_message:
85
+ rdoc_options: []
86
+ require_paths:
87
+ - lib
88
+ required_ruby_version: !ruby/object:Gem::Requirement
89
+ requirements:
90
+ - - '>='
91
+ - !ruby/object:Gem::Version
92
+ version: '0'
93
+ required_rubygems_version: !ruby/object:Gem::Requirement
94
+ requirements:
95
+ - - '>='
96
+ - !ruby/object:Gem::Version
97
+ version: '0'
98
+ requirements: []
99
+ rubyforge_project:
100
+ rubygems_version: 2.1.9
101
+ signing_key:
102
+ specification_version: 4
103
+ summary: S3 file input plugin for Embulk, a plugin-based parallel bulk data loader
104
+ test_files: []