embulk-input-gcs 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 82f47e1ec13ce8e83f892c49519930e578440200
+  data.tar.gz: 121ad589176d771d23435bbf914b3724337cab6a
+SHA512:
+  metadata.gz: 9e37e6e60fe77027bf5b2d1929b2f3af9ebcdac22f8be31e30412db1e3c96e20c3fe7a9b2a6c5081d96f46dafcc924dbbc9f5fe25bbd505b4d1537d488a1c32f
+  data.tar.gz: ad9f4ec153c83e317e1f90e4dcf322eecb79ab44b8d4cc17709599b7559aac9edc07b7eb9335c34205464280099ebcb3ee5a94cda7ef536b78bba52628d92fba

data/.gitignore

@@ -0,0 +1,14 @@
+target/
+build/
+pkg/
+*.iml
+*~
+._*
+.idea
+tmp/
+vendor/
+/classpath/
+/.bundle
+.yardoc
+/embulk-*.jar
+/.gradle

data/README.md

@@ -0,0 +1,89 @@
+# Google Cloud Storage file input plugin for Embulk
+
+## Overview
+
+* Plugin type: **file input**
+* Resume supported: **yes**
+* Cleanup supported: **yes**
+
+## Usage
+
+### Install plugin
+
+```
+embulk gem install embulk-input-gcs
+```
+
+### Google Service Account Settings
+1. Make project at [Google Developers Console](https://console.developers.google.com/project).
+
+1. Make "Service Account" with [this step](https://cloud.google.com/storage/docs/authentication#service_accounts).
+   
+	Service Account has two specific scopes: read-only, read-write. 
+  
+	embulk-input-gcs can run "read-only" scopes.
+
+1. Generate private key in P12(PKCS12) format, and upload to machine.
+
+1. Write "EMAIL_ADDRESS" and fullpath of PKCS12 private key in yaml.
+
+### run
+
+```
+embulk run /path/to/config.yml
+```
+
+## Configuration
+
+- **bucket** Google Cloud Storage bucket name (string, required)
+- **path_prefix** prefix of target keys (string, required)
+- **service_accound_email** Google Cloud Storage service_account_email (string, required)
+- **p12_keyfile_fullpath** fullpath of p12 key (string, required)
+- **application_name** application name anything you like (string, optional)
+
+## Example
+
+```yaml
+in:
+  type: gcs
+  bucket: my-gcs-bucket
+  path_prefix: logs/csv-
+  service_accound_email: ABCXYZ123ABCXYZ123.gserviceaccount.com
+  p12_keyfile_path: /path/to/p12_keyfile.p12
+  application_name: Anything you like
+```
+
+Example for "sample_01.csv.gz" , generated by [embulk example](https://github.com/embulk/embulk#trying-examples)
+
+```yaml
+in:
+  type: gcs
+  bucket: my-gcs-bucket
+  path_prefix: sample_
+  service_accound_email: ABCXYZ123ABCXYZ123.gserviceaccount.com
+  p12_keyfile_path: /path/to/p12_keyfile.p12
+  application_name: Anything you like
+  decoders:
+  - {type: gzip}
+  parser:
+    charset: UTF-8
+    newline: CRLF
+    type: csv
+    delimiter: ','
+    quote: '"'
+    header_line: true
+    columns:
+    - {name: id, type: long}
+    - {name: account, type: long}
+    - {name: time, type: timestamp, format: '%Y-%m-%d %H:%M:%S'}
+    - {name: purchase, type: timestamp, format: '%Y%m%d'}
+    - {name: comment, type: string}
+out: {type: stdout}
+```
+
+## Build
+
+```
+./gradlew gem
+```
+

data/build.gradle

@@ -0,0 +1,59 @@
+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()
+    jcenter()
+}
+configurations {
+    provided
+}
+
+version = "0.1.0"
+
+dependencies {
+    compile  "org.embulk:embulk-core:0.4.10"
+    provided "org.embulk:embulk-core:0.4.10"
+
+    compile "com.google.http-client:google-http-client-jackson2:1.19.0"
+    compile ("com.google.apis:google-api-services-storage:v1-rev27-1.19.1") {exclude module: "guava-jdk5"}
+
+    testCompile "junit:junit:4.+"
+}
+
+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($/
+Gem::Specification.new do |spec|
+  spec.name          = "${project.name}"
+  spec.version       = "${project.version}"
+  spec.authors       = ["Satoshi Akama"]
+  spec.summary       = %[Google Cloud Storage input plugin for Embulk]
+  spec.description   = %[gcs input plugin is an Embulk plugin that loads records from Google Cloud Storage. read by any input plugins. Search the output plugins by 'embulk-output' keyword.]
+  spec.email         = ["satoshiakama@gmail.com"]
+  spec.licenses      = ["Apache-2.0"]
+  spec.homepage      = "https://github.com/sakama/embulk-input-gcs"
+
+  spec.files         = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
+  spec.test_files    = spec.files.grep(%r"^(test|spec)/")
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency 'bundler', ['~> 1.0']
+  spec.add_development_dependency 'rake', ['>= 10.0']
+end
+/$)
+}

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/gcs.rb

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

data/settings.gradle

@@ -0,0 +1,2 @@
+rootProject.name = 'embulk-input-gcs'
+

data/src/main/java/org/embulk/input/gcs/GcsFileInputPlugin.java

@@ -0,0 +1,288 @@
+package org.embulk.input.gcs;
+
+import java.util.List;
+import java.util.Arrays;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.io.File;
+import java.io.IOException;
+import java.io.InputStream;
+import java.math.BigInteger;
+import com.google.common.collect.ImmutableList;
+import com.google.common.base.Optional;
+import java.security.GeneralSecurityException;
+
+import org.embulk.config.CommitReport;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.config.CommitReport;
+import org.embulk.spi.Exec;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.FileInputPlugin;
+import org.embulk.spi.TransactionalFileInput;
+import org.embulk.spi.util.InputStreamFileInput;
+
+import org.slf4j.Logger;
+
+import com.google.api.client.googleapis.auth.oauth2.GoogleCredential;
+import com.google.api.client.googleapis.javanet.GoogleNetHttpTransport;
+import com.google.api.client.http.HttpTransport;
+import com.google.api.client.json.JsonFactory;
+import com.google.api.client.json.jackson2.JacksonFactory;
+import com.google.api.services.storage.Storage;
+import com.google.api.services.storage.StorageScopes;
+import com.google.api.services.storage.model.Bucket;
+import com.google.api.services.storage.model.Objects;
+import com.google.api.services.storage.model.StorageObject;
+
+public class GcsFileInputPlugin
+        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("service_accound_email")
+        public String getServiceAccountEmail();
+
+        @Config("application_name")
+        // @todo I want to set default applicaiton name like "embulk-input-gcs". But string format cause JsonParseException.
+        @ConfigDefault("1000000000")
+        public String getApplicationName();
+
+        @Config("p12_keyfile_fullpath")
+        public String getP12KeyfileFullpath();
+
+        public List<String> getFiles();
+        public void setFiles(List<String> files);
+
+        @ConfigInject
+        public BufferAllocator getBufferAllocator();
+    }
+
+    private static final Logger log = Exec.getLogger(GcsFileInputPlugin.class);
+    private static HttpTransport httpTransport;
+    private static JsonFactory jsonFactory;
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config,
+                                  FileInputPlugin.Control control)
+    {
+        final PluginTask task = config.loadConfig(PluginTask.class);
+
+        try {
+            httpTransport = GoogleNetHttpTransport.newTrustedTransport();
+            jsonFactory = new JacksonFactory();
+        } catch (Exception e) {
+            log.warn("Could not generate http transport");
+        }
+
+        // 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 taskCount,
+                             FileInputPlugin.Control control)
+    {
+        final PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        control.run(taskSource, taskCount);
+
+        List<String> files = new ArrayList<String>(task.getFiles());
+        if (files.size() == 0) {
+            return null;
+        }
+        Collections.sort(files);
+        return Exec.newConfigDiff().
+                set("last_path", files.get(files.size() - 1));
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource,
+                        int taskCount,
+                        List<CommitReport> successCommitReports)
+    {
+    }
+
+    /**
+     * @see https://developers.google.com/accounts/docs/OAuth2ServiceAccount#authorizingrequests
+     */
+    private static GoogleCredential getCredentialProvider (PluginTask task)
+    {
+        try {
+            // @see https://cloud.google.com/compute/docs/api/how-tos/authorization
+            // @see https://developers.google.com/resources/api-libraries/documentation/storage/v1/java/latest/com/google/api/services/storage/STORAGE_SCOPE.html
+            GoogleCredential cred = new GoogleCredential.Builder().setTransport(httpTransport)
+                    .setJsonFactory(jsonFactory)
+                    .setServiceAccountId(task.getServiceAccountEmail())
+                    .setServiceAccountScopes(
+                            ImmutableList.of(
+                                    StorageScopes.DEVSTORAGE_READ_ONLY
+                            )
+                    )
+                    .setServiceAccountPrivateKeyFromP12File(new File(task.getP12KeyfileFullpath()))
+                    .build();
+            return cred;
+        } catch (IOException e) {
+            log.warn("Could not load client secrets file " + task.getP12KeyfileFullpath());
+        } catch (GeneralSecurityException e) {
+            log.warn ("Google Authentication was failed");
+        }
+        return null;
+    }
+
+    private static Storage newGcsClient(PluginTask task)
+    {
+        GoogleCredential credentials = getCredentialProvider(task);
+        Storage client = new Storage.Builder(httpTransport, jsonFactory, credentials)
+                .setApplicationName(task.getApplicationName())
+                .build();
+
+        return client;
+    }
+
+    public List<String> listFiles(PluginTask task)
+    {
+        Storage client = newGcsClient(task);
+        String bucket = task.getBucket();
+
+        return listGcsFilesByPrefix(client, bucket, task.getPathPrefix(), task.getLastPath());
+    }
+
+    /**
+     * Lists GCS filenames filtered by prefix.
+     *
+     * The resulting list does not include the file that's size == 0.
+     */
+    public static List<String> listGcsFilesByPrefix(Storage client, String bucket,
+                                             String prefix, Optional<String> lastPath)
+    {
+        ImmutableList.Builder<String> builder = ImmutableList.builder();
+
+        String lastKey = lastPath.orNull();
+
+        // @see https://cloud.google.com/storage/docs/json_api/v1/objects#resource
+        try {
+            Storage.Buckets.Get getBucket = client.buckets().get(bucket);
+            getBucket.setProjection("full");
+            Bucket bk = getBucket.execute();
+            if (log.isDebugEnabled()) {
+                log.debug("bucket name: " + bucket);
+                log.debug("bucket location: " + bk.getLocation());
+                log.debug("bucket timeCreated: " + bk.getTimeCreated());
+                log.debug("bucket owner: " + bk.getOwner());
+            }
+        } catch (Exception e) {
+            log.warn("Could not access to bucket:" + bucket);
+            log.warn(e.getMessage());
+        }
+
+
+        try {
+            // @see https://cloud.google.com/storage/docs/json_api/v1/objects/list
+            Storage.Objects.List listObjects = client.objects().list(bucket);
+            listObjects.setPrefix(prefix);
+            listObjects.setPageToken(lastKey);
+            do {
+                Objects objects = listObjects.execute();
+                List<StorageObject> items = objects.getItems();
+                if (items == null) {
+                    log.info("No file was found in bucket:" + bucket + " prefix:" + prefix);
+                    break;
+                }
+                for (StorageObject o : items) {
+                    if (log.isDebugEnabled()) {
+                        log.debug("filename: " + o.getName());
+                        log.debug("updated: " + o.getUpdated());
+                    }
+                    if (o.getSize().compareTo(BigInteger.ZERO) > 0) {
+                        builder.add(o.getName());
+                    }
+                }
+                lastKey = objects.getNextPageToken();
+                listObjects.setPageToken(lastKey);
+            } while (lastKey != null);
+        } catch (Exception e) {
+            log.warn("Could not get file list from bucket:" + bucket);
+            log.warn(e.getMessage());
+        }
+
+        return builder.build();
+    }
+
+    @Override
+    public TransactionalFileInput open(TaskSource taskSource, int taskIndex)
+    {
+        final PluginTask task = taskSource.loadTask(PluginTask.class);
+        return new GcsFileInput(task, taskIndex);
+    }
+
+    public static class GcsFileInput
+            extends InputStreamFileInput
+            implements TransactionalFileInput
+    {
+        private static class SingleFileProvider
+                implements InputStreamFileInput.Provider
+        {
+            private final Storage client;
+            private final String bucket;
+            private final String key;
+            private boolean opened = false;
+
+            public SingleFileProvider(PluginTask task, int taskIndex)
+            {
+                this.client = newGcsClient(task);
+                this.bucket = task.getBucket();
+                this.key = task.getFiles().get(taskIndex);
+            }
+
+            @Override
+            public InputStream openNext() throws IOException
+            {
+                if (opened) {
+                    return null;
+                }
+                opened = true;
+                Storage.Objects.Get getObject = client.objects().get(bucket, key);
+
+                return getObject.executeMediaAsInputStream();
+            }
+
+            @Override
+            public void close() { }
+        }
+
+        public GcsFileInput(PluginTask task, int taskIndex)
+        {
+            super(task.getBufferAllocator(), new SingleFileProvider(task, taskIndex));
+        }
+
+        public void abort() { }
+
+        public CommitReport commit()
+        {
+            return Exec.newCommitReport();
+        }
+
+        @Override
+        public void close() { }
+    }
+}

data/src/test/java/org/embulk/input/gcs/TestGcsFileInputPlugin.java

@@ -0,0 +1,9 @@
+package org.embulk.input.gcs;
+
+import static org.junit.Assert.*;
+import java.util.List;
+import org.junit.Test;
+
+// @todo Write unit test.
+public class TestGcsFileInputPlugin {
+}

metadata

@@ -0,0 +1,94 @@
+--- !ruby/object:Gem::Specification
+name: embulk-input-gcs
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Satoshi Akama
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2015-03-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  name: bundler
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  name: rake
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '10.0'
+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.
+email:
+- satoshiakama@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/gcs.rb
+- settings.gradle
+- src/main/java/org/embulk/input/gcs/GcsFileInputPlugin.java
+- src/test/java/org/embulk/input/gcs/TestGcsFileInputPlugin.java
+- classpath/commons-codec-1.3.jar
+- classpath/commons-logging-1.1.1.jar
+- classpath/embulk-input-gcs-0.1.0.jar
+- classpath/google-api-client-1.19.1.jar
+- classpath/google-api-services-storage-v1-rev27-1.19.1.jar
+- classpath/google-http-client-1.19.0.jar
+- classpath/google-http-client-jackson2-1.19.0.jar
+- classpath/google-oauth-client-1.19.0.jar
+- classpath/httpclient-4.0.1.jar
+- classpath/httpcore-4.0.1.jar
+- classpath/jsr305-1.3.9.jar
+homepage: https://github.com/sakama/embulk-input-gcs
+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: Google Cloud Storage input plugin for Embulk
+test_files: []