embulk-input-s3 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a189f02204b02562ddf626857a6fd8a0d07d41f1
+  data.tar.gz: bc27649cbbf48e4052cbac15f548e451e990e36f
+SHA512:
+  metadata.gz: abef90a11eafb493f993812835d04cfbd268ea805408c9aaffd82b12723b5b5360b7f840575f38653f64d1caad5140c0397c44a0344990c79df5efe083b0eb13
+  data.tar.gz: 8e489005081d3efd5d6cb2b9c1e1342f0172323705ab6728938ab2a9fe98c4a948c127848ec003dd83bb96418225b4f06bde35e5449a368304ed438b9cfef173

data/.gitignore

@@ -0,0 +1,6 @@
+*~
+.idea
+build/
+/classpath/
+/.gradle
+/*.gem

data/README.md

@@ -0,0 +1,34 @@
+# S3 file input plugin for Embulk
+
+## Overview
+
+* Plugin type: **file input**
+* Rollback supported: **yes**
+* Resume supported: **yes**
+* Cleanup supported: **yes**
+
+## Configuration
+
+- **bucket** S3 bucket name (string, required)
+- **path_prefix** prefix of target keys (string, required)
+- **endpoint** S3 endpoint login user name (string, optional)
+- **access_key_id** AWS access key id (string, required)
+- **secret_access_key** AWS secret key (string, required)
+
+## Example
+
+```yaml
+in:
+  type: s3
+  bucket: my-s3-bucket
+  endpoint: s3-us-west-1.amazonaws.com
+  access_key_id: ABCXYZ123ABCXYZ123
+  secret_access_key: AbCxYz123aBcXyZ123
+```
+
+## Build
+
+```
+./gradlew gem
+```
+

data/build.gradle

@@ -0,0 +1,62 @@
+plugins {
+    id "com.jfrog.bintray" version "1.1"
+    id "com.github.jruby-gradle.base" version "0.1.5"
+    id "java"
+}
+import com.github.jrubygradle.JRubyExec
+repositories {
+    mavenCentral()
+    mavenLocal()
+    jcenter()
+}
+configurations {
+    provided
+}
+
+version = "0.1.0"
+
+dependencies {
+    compile  "org.embulk:embulk-core:0.4.0"
+    provided "org.embulk:embulk-core:0.4.0"
+    compile "com.amazonaws:aws-java-sdk-s3:1.9.17"
+    testCompile "junit:junit:4.+"
+    testCompile "org.mockito:mockito-core:1.+"
+}
+
+task classpath(type: Copy, dependsOn: ["jar"]) {
+    doFirst { file("classpath").deleteDir() }
+    from (configurations.runtime - configurations.provided + files(jar.archivePath))
+    into "classpath"
+}
+clean { delete 'classpath' }
+
+task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
+    jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
+    script "build/gemspec"
+    doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
+}
+
+task gemspec << { file("build/gemspec").write($/
+Gem::Specification.new do |gem|
+  gem.summary       = "S3 file input plugin for Embulk, a plugin-based parallel bulk data loader"
+
+  gem.name          = "${project.name}"
+  gem.version       = "${project.version}"
+  gem.description   = gem.summary
+  gem.authors       = ["Sadayuki Furuhashi"]
+  gem.email         = ["frsyuki@gmail.com"]
+  gem.license       = "Apache 2.0"
+  gem.homepage      = "https://github.com/embulk/embulk-input-s3"
+
+  gem.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.require_paths = ["lib"]
+  gem.has_rdoc      = false
+
+  gem.add_development_dependency "bundler", [">= 1.0"]
+  gem.add_development_dependency "rake", [">= 0.10.0"]
+  gem.add_development_dependency "test-unit", ["~> 3.0.2"]
+end
+/$)
+}

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Feb 04 13:46:12 PST 2015
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.2.1-bin.zip

data/gradlew

@@ -0,0 +1,164 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn ( ) {
+    echo "$*"
+}
+
+die ( ) {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+esac
+
+# For Cygwin, ensure paths are in UNIX format before anything is touched.
+if $cygwin ; then
+    [ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
+fi
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >&-
+APP_HOME="`pwd -P`"
+cd "$SAVED" >&-
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
+function splitJvmOpts() {
+    JVM_OPTS=("$@")
+}
+eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
+JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

data/gradlew.bat

@@ -0,0 +1,90 @@
+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windowz variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+if "%@eval[2+2]" == "4" goto 4NT_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+goto execute
+
+:4NT_args
+@rem Get arguments from the 4NT Shell from JP Software
+set CMD_LINE_ARGS=%$
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="0" goto mainEnd
+
+:fail
+rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
+rem the _cmd.exe /c_ return code!
+if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

data/lib/embulk/input/s3.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_input(
+  :s3, "org.embulk.input.s3.S3FileInputPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/input/s3/S3FileInputPlugin.java

@@ -0,0 +1,268 @@
+package org.embulk.input.s3;
+
+import java.util.List;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.io.IOException;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.nio.file.Files;
+import java.nio.file.SimpleFileVisitor;
+import java.nio.file.FileVisitResult;
+import java.nio.file.attribute.BasicFileAttributes;
+import javax.validation.constraints.NotNull;
+import com.google.common.collect.ImmutableList;
+import com.fasterxml.jackson.annotation.JacksonInject;
+import org.embulk.config.Config;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.CommitReport;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileInputPlugin;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.util.InputStreamFileInput;
+import org.slf4j.Logger;
+
+import static org.embulk.spi.util.Inputs.formatPath;
+
+import java.util.List;
+import java.io.IOException;
+import java.io.InputStream;
+import com.google.common.collect.ImmutableList;
+import com.google.common.base.Optional;
+import com.fasterxml.jackson.annotation.JacksonInject;
+import com.amazonaws.auth.AWSCredentials;
+import com.amazonaws.auth.AWSCredentialsProvider;
+import com.amazonaws.auth.BasicAWSCredentials;
+import com.amazonaws.services.s3.AmazonS3Client;
+import com.amazonaws.services.s3.model.ListObjectsRequest;
+import com.amazonaws.services.s3.model.S3ObjectSummary;
+import com.amazonaws.services.s3.model.ObjectListing;
+import com.amazonaws.services.s3.model.GetObjectRequest;
+import com.amazonaws.services.s3.model.S3Object;
+import com.amazonaws.ClientConfiguration;
+import com.amazonaws.Protocol;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.CommitReport;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileInputPlugin;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.util.InputStreamFileInput;
+
+public class S3FileInputPlugin
+        implements FileInputPlugin
+{
+    public interface PluginTask
+            extends Task
+    {
+        @Config("bucket")
+        public String getBucket();
+
+        @Config("path_prefix")
+        public String getPathPrefix();
+
+        @Config("last_path")
+        @ConfigDefault("null")
+        public Optional<String> getLastPath();
+
+        @Config("endpoint")
+        @ConfigDefault("null")
+        public Optional<String> getEndpoint();
+
+        // TODO timeout, ssl, etc
+
+        @Config("access_key_id")
+        public String getAccessKeyId();
+
+        @Config("secret_access_key")
+        public String getSecretAccessKey();
+
+        // TODO support more options such as STS
+
+        public List<String> getFiles();
+        public void setFiles(List<String> files);
+
+        @JacksonInject
+        public BufferAllocator getBufferAllocator();
+    }
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config, FileInputPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        // list files recursively
+        task.setFiles(listFiles(task));
+
+        // number of processors is same with number of files
+        return resume(task.dump(), task.getFiles().size(), control);
+    }
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource,
+            int processorCount,
+            FileInputPlugin.Control control)
+    {
+        control.run(taskSource, processorCount);
+        return Exec.newConfigDiff();
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource,
+            int processorCount,
+            List<CommitReport> successCommitReports)
+    {
+        // do nothing
+    }
+
+    public static AWSCredentialsProvider getCredentialsProvider(PluginTask task)
+    {
+        final AWSCredentials cred = new BasicAWSCredentials(
+                task.getAccessKeyId(), task.getSecretAccessKey());
+        return new AWSCredentialsProvider() {
+            public AWSCredentials getCredentials()
+            {
+                return cred;
+            }
+
+            public void refresh()
+            {
+            }
+        };
+    }
+
+    private static AmazonS3Client newS3Client(PluginTask task)
+    {
+        AWSCredentialsProvider credentials = getCredentialsProvider(task);
+        AmazonS3Client client = newS3Client(credentials, task.getEndpoint());
+        return client;
+    }
+
+    private static AmazonS3Client newS3Client(AWSCredentialsProvider credentials,
+            Optional<String> endpoint)
+    {
+        // TODO get config from AmazonS3Task
+        ClientConfiguration clientConfig = new ClientConfiguration();
+        //clientConfig.setProtocol(Protocol.HTTP);
+        clientConfig.setMaxConnections(50); // SDK default: 50
+        clientConfig.setMaxErrorRetry(3); // SDK default: 3
+        clientConfig.setSocketTimeout(8*60*1000); // SDK default: 50*1000
+
+        AmazonS3Client client = new AmazonS3Client(credentials, clientConfig);
+
+        if (endpoint.isPresent()) {
+            client.setEndpoint(endpoint.get());
+        }
+
+        return client;
+    }
+
+    public List<String> listFiles(PluginTask task)
+    {
+        AmazonS3Client client = newS3Client(task);
+        String bucketName = task.getBucket();
+
+        return listS3FilesByPrefix(client, bucketName, task.getPathPrefix(), task.getLastPath());
+    }
+
+    /**
+     * Lists S3 filenames filtered by prefix.
+     *
+     * The resulting list does not include the file that's size == 0.
+     */
+    public static List<String> listS3FilesByPrefix(AmazonS3Client client, String bucketName,
+            String prefix, Optional<String> lastPath)
+    {
+        ImmutableList.Builder<String> builder = ImmutableList.builder();
+
+        String lastKey = lastPath.orNull();
+        do {
+            ListObjectsRequest req = new ListObjectsRequest(bucketName, prefix, lastKey, null, 1024);
+            ObjectListing ol = client.listObjects(req);
+            for(S3ObjectSummary s : ol.getObjectSummaries()) {
+                if (s.getSize() > 0) {
+                    builder.add(s.getKey());
+                }
+            }
+            lastKey = ol.getNextMarker();
+        } while(lastKey != null);
+
+        return builder.build();
+    }
+
+    @Override
+    public TransactionalFileInput open(TaskSource taskSource, int processorIndex)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+        return new S3FileInput(task, processorIndex);
+    }
+
+    public static class S3FileInput
+            extends InputStreamFileInput
+            implements TransactionalFileInput
+    {
+        // TODO create single-file InputStreamFileInput utility
+        private static class SingleFileProvider
+                implements InputStreamFileInput.Provider
+        {
+            private AmazonS3Client client;
+            private final String bucket;
+            private final String key;
+            private boolean opened = false;
+
+            public SingleFileProvider(PluginTask task, int processorIndex)
+            {
+                this.client = newS3Client(task);
+                this.bucket = task.getBucket();
+                this.key = task.getFiles().get(processorIndex);
+            }
+
+            @Override
+            public InputStream openNext() throws IOException
+            {
+                if (opened) {
+                    return null;
+                }
+                opened = true;
+                GetObjectRequest request = new GetObjectRequest(bucket, key);
+                //if (pos > 0) {
+                //    request.setRange(pos, contentLength);
+                //}
+                S3Object obj = client.getObject(request);
+                //if (pos <= 0) {
+                //    // first call
+                //    contentLength = obj.getObjectMetadata().getContentLength();
+                //}
+                return obj.getObjectContent();
+            }
+
+            @Override
+            public void close() { }
+        }
+
+        public S3FileInput(PluginTask task, int processorIndex)
+        {
+            super(task.getBufferAllocator(), new SingleFileProvider(task, processorIndex));
+        }
+
+        public void abort() { }
+
+        public CommitReport commit()
+        {
+            return Exec.newCommitReport();
+        }
+
+        @Override
+        public void close() { }
+    }
+}

data/src/test/java/org/embulk/plugin/s3/TestS3FileInputPlugin.java

@@ -0,0 +1,42 @@
+package org.embulk.plugin.s3;
+
+import static org.junit.Assert.*;
+import java.util.List;
+import org.junit.Test;
+import org.mockito.Mockito;
+
+import com.google.common.base.Optional;
+import com.google.common.collect.ImmutableList;
+import com.amazonaws.services.s3.AmazonS3Client;
+import com.amazonaws.services.s3.model.ListObjectsRequest;
+import com.amazonaws.services.s3.model.ObjectListing;
+import com.amazonaws.services.s3.model.S3ObjectSummary;
+
+public class TestS3FileInputPlugin
+{
+    @Test
+    public void listS3FilesByPrefix()
+    {
+        // AWSS3Client returns list1 for the first iteration and list2 next.
+        List<S3ObjectSummary> list1 = ImmutableList.<S3ObjectSummary> of(bucket("in/", 0), bucket("in/file/", 0),
+                bucket("in/file/sample.csv.gz", 12345));
+        List<S3ObjectSummary> list2 = ImmutableList.<S3ObjectSummary> of(bucket("sample2.csv.gz", 0));
+        ObjectListing ol = Mockito.mock(ObjectListing.class);
+
+        Mockito.doReturn(list1).doReturn(list2).when(ol).getObjectSummaries();
+        AmazonS3Client client = Mockito.mock(AmazonS3Client.class);
+        Mockito.doReturn(ol).when(client).listObjects(Mockito.any(ListObjectsRequest.class));
+        Mockito.doReturn("in/file/").doReturn(null).when(ol).getNextMarker();
+
+        // It counts only size != 0 files.
+        assertEquals(1, S3FileInputPlugin.listS3FilesByPrefix(client, "bucketName", "prefix", Optional.<String>absent()).size());
+    }
+
+    private S3ObjectSummary bucket(String key, long size)
+    {
+        S3ObjectSummary bucket = new S3ObjectSummary();
+        bucket.setKey(key);
+        bucket.setSize(size);
+        return bucket;
+    }
+}

metadata

@@ -0,0 +1,104 @@
+--- !ruby/object:Gem::Specification
+name: embulk-input-s3
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Sadayuki Furuhashi
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2015-02-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rake
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 0.10.0
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 0.10.0
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.0.2
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.0.2
+  prerelease: false
+  type: :development
+description: S3 file input plugin for Embulk, a plugin-based parallel bulk data loader
+email:
+- frsyuki@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- README.md
+- build.gradle
+- gradle/wrapper/gradle-wrapper.jar
+- gradle/wrapper/gradle-wrapper.properties
+- gradlew
+- gradlew.bat
+- lib/embulk/input/s3.rb
+- src/main/java/org/embulk/input/s3/S3FileInputPlugin.java
+- src/test/java/org/embulk/plugin/s3/TestS3FileInputPlugin.java
+- classpath/aws-java-sdk-core-1.9.17.jar
+- classpath/aws-java-sdk-kms-1.9.17.jar
+- classpath/aws-java-sdk-s3-1.9.17.jar
+- classpath/commons-codec-1.6.jar
+- classpath/commons-logging-1.1.3.jar
+- classpath/embulk-input-s3-0.1.0.jar
+- classpath/httpclient-4.3.4.jar
+- classpath/httpcore-4.3.2.jar
+homepage: https://github.com/embulk/embulk-input-s3
+licenses:
+- Apache 2.0
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
+specification_version: 4
+summary: S3 file input plugin for Embulk, a plugin-based parallel bulk data loader
+test_files: []