embulk-output-gcs_streaming 0.1.0

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,5 @@
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-4.1-bin.zip

data/gradlew

@@ -0,0 +1,172 @@
+#!/usr/bin/env sh
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# 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\"`/" >/dev/null
+APP_HOME="`pwd -P`"
+cd "$SAVED" >/dev/null
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+die () {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+nonstop=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+  NONSTOP* )
+    nonstop=true
+    ;;
+esac
+
+CLASSPATH=$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 "$darwin" = "false" -a "$nonstop" = "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 "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$JAVACMD"`
+
+    # 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
+
+# Escape application args
+save () {
+    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+    echo " "
+}
+APP_ARGS=$(save "$@")
+
+# Collect all arguments for the java command, following the shell quoting and substitution rules
+eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "$@"

data/gradlew.bat

@@ -0,0 +1,84 @@
+@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
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@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=
+
+@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 Windows variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_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=%*
+
+: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/output/gcs_streaming.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_output(
+  "gcs_streaming", "org.embulk.output.gcs_streaming.GcsStreamingFileOutputPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/output/gcs_streaming/GcsClient.java

@@ -0,0 +1,58 @@
+package org.embulk.output.gcs_streaming;
+
+import com.google.auth.oauth2.ServiceAccountCredentials;
+
+import com.google.cloud.storage.Storage;
+import com.google.cloud.storage.StorageException;
+import com.google.cloud.storage.StorageOptions;
+
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.Optional;
+
+public class GcsClient
+{
+    public Storage storage;
+    final String projectId;
+    final Optional<String> jsonKeyfile;
+
+    public GcsClient(String projectId, Optional<String> jsonKeyfile)
+    {
+        this.projectId = projectId;
+        this.jsonKeyfile = jsonKeyfile;
+        if (this.jsonKeyfile.isPresent()) {
+            try {
+                String key = jsonKeyfile.get();
+                this.storage = getClientWithJsonKey(this.projectId, key);
+            }
+            catch (IOException | StorageException ex) {
+                throw new RuntimeException(ex);
+            }
+        }
+        else {
+            try {
+                this.storage = getClient(this.projectId);
+            }
+            catch (StorageException ex) {
+                throw new RuntimeException(ex);
+            }
+        }
+    }
+
+    private static Storage getClientWithJsonKey(String projectId, String key) throws IOException, StorageException
+    {
+        return StorageOptions.newBuilder()
+                .setProjectId(projectId)
+                .setCredentials(ServiceAccountCredentials.fromStream(new FileInputStream(key)))
+                .build()
+                .getService();
+    }
+
+    private static Storage getClient(String projectId) throws StorageException
+    {
+        return StorageOptions.newBuilder()
+                .setProjectId(projectId)
+                .build()
+                .getService();
+    }
+}

data/src/main/java/org/embulk/output/gcs_streaming/GcsStreamingFileOutputPlugin.java

@@ -0,0 +1,172 @@
+package org.embulk.output.gcs_streaming;
+
+import com.google.cloud.WriteChannel;
+import com.google.cloud.storage.BlobId;
+import com.google.cloud.storage.BlobInfo;
+import com.google.cloud.storage.Storage;
+import com.google.cloud.storage.StorageException;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigDiff;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskReport;
+import org.embulk.config.TaskSource;
+import org.embulk.spi.Buffer;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileOutputPlugin;
+import org.embulk.spi.TransactionalFileOutput;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import java.io.IOException;
+import java.nio.ByteBuffer;
+import java.util.List;
+import java.util.Optional;
+
+public class GcsStreamingFileOutputPlugin
+        implements FileOutputPlugin
+{
+    public interface PluginTask
+            extends Task
+    {
+        @Config("bucket")
+        public String getBucket();
+
+        @Config("path_prefix")
+        public String getPathPrefix();
+
+        @Config("file_ext")
+        public String getFileNameExtension();
+
+        @Config("sequence_format")
+        @ConfigDefault("\".%03d.%02d.\"")
+        public String getSequenceFormat();
+
+        @Config("project_id")
+        public String getProjectId();
+
+        @Config("content_type")
+        @ConfigDefault("\"application/octet-stream\"")
+        public String getContentType();
+
+        @Config("json_keyfile")
+        @ConfigDefault("null")
+        public Optional<String> getJsonKeyfile();
+    }
+
+    private static final Logger logger = LoggerFactory.getLogger(GcsStreamingFileOutputPlugin.class);
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config, int taskCount,
+                                  FileOutputPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        // retryable (idempotent) output:
+        // return resume(task.dump(), taskCount, control);
+
+        // non-retryable (non-idempotent) output:
+        control.run(task.dump());
+        return Exec.newConfigDiff();
+    }
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource,
+                             int taskCount,
+                             FileOutputPlugin.Control control)
+    {
+        throw new UnsupportedOperationException("gcs_streaming output plugin does not support resuming");
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource,
+            int taskCount,
+            List<TaskReport> successTaskReports)
+    {
+    }
+
+    @Override
+    public TransactionalFileOutput open(TaskSource taskSource, final int taskIndex)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        final String pathPrefix = task.getPathPrefix();
+        final String pathSuffix = task.getFileNameExtension();
+        final String sequenceFormat = task.getSequenceFormat();
+        final String gcpProjectId = task.getProjectId();
+        final String gcsBucketName = task.getBucket();
+        final String gcsObjectContentType = task.getContentType();
+        final Optional<String> gcpJsonKeyfile = task.getJsonKeyfile();
+        Storage storage = new GcsClient(gcpProjectId, gcpJsonKeyfile).storage;
+
+        return new TransactionalFileOutput()
+        {
+            private int fileIndex = 0;
+            private WriteChannel output = null;
+
+            public void nextFile()
+            {
+                closeFile();
+
+                String blobName = pathPrefix + String.format(sequenceFormat, taskIndex, fileIndex) + pathSuffix;
+                BlobId blobId = BlobId.of(gcsBucketName, blobName);
+                BlobInfo blobInfo = BlobInfo.newBuilder(blobId).setContentType(gcsObjectContentType).build();
+
+                logger.info("Writing gs://{}/{}", gcsBucketName, blobName);
+                try {
+                    output = storage.writer(blobInfo);
+                }
+                catch (StorageException ex) {
+                    throw new RuntimeException(ex);
+                }
+                fileIndex++;
+            }
+
+            private void closeFile()
+            {
+                if (output != null) {
+                    try {
+                        output.close();
+                    }
+                    catch (IOException ex) {
+                        throw new RuntimeException(ex);
+                    }
+                }
+            }
+
+            public void add(Buffer buffer)
+            {
+                try {
+                    output.write(ByteBuffer.wrap(buffer.array(), buffer.offset(), buffer.limit()));
+                }
+                catch (IOException ex) {
+                    throw new RuntimeException(ex);
+                }
+                finally {
+                    buffer.release();
+                }
+            }
+
+            public void finish()
+            {
+                closeFile();
+            }
+
+            public void close()
+            {
+                closeFile();
+            }
+
+            public void abort()
+            {
+            }
+
+            public TaskReport commit()
+            {
+                TaskReport report = Exec.newTaskReport();
+                return report;
+            }
+        };
+    }
+}