embulk-output-orc 0.0.1

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Mon Aug 14 21:51:29 JST 2017
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-3.2.1-all.zip

data/gradlew

@@ -0,0 +1,169 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  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
+
+# 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=$APP_BASE_NAME"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [[ "$(uname)" == "Darwin" ]] && [[ "$HOME" == "$PWD" ]]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

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/orc.rb

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

data/src/main/java/org/embulk/output/orc/OrcColumnVisitor.java

@@ -0,0 +1,68 @@
+package org.embulk.output.orc;
+
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.embulk.spi.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageReader;
+
+public class OrcColumnVisitor implements ColumnVisitor
+{
+    private PageReader reader;
+    VectorizedRowBatch batch;
+    Integer finalI;
+
+    public OrcColumnVisitor(PageReader pageReader, VectorizedRowBatch rowBatch, Page page, Integer i)
+    {
+        int size = page.getStringReferences().size();
+
+        this.reader = pageReader;
+        this.batch = rowBatch;
+        this.finalI = i;
+    }
+
+    @Override
+    public void booleanColumn(Column column)
+    {
+        if (reader.isNull(column)) {
+            ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = 0;
+        }
+        else {
+            ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = reader.getLong(column);
+        }
+    }
+
+    @Override
+    public void longColumn(Column column)
+    {
+        ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = reader.getLong(column);
+    }
+
+    @Override
+    public void doubleColumn(Column column)
+    {
+        ((DoubleColumnVector) batch.cols[column.getIndex()]).vector[finalI] = reader.getDouble(column);
+    }
+
+    @Override
+    public void stringColumn(Column column)
+    {
+        ((BytesColumnVector) batch.cols[column.getIndex()]).setVal(finalI,
+                reader.getString(column).getBytes());
+    }
+
+    @Override
+    public void timestampColumn(Column column)
+    {
+
+    }
+
+    @Override
+    public void jsonColumn(Column column)
+    {
+        // throw unsupported
+    }
+}

data/src/main/java/org/embulk/output/orc/OrcOutputPlugin.java

@@ -0,0 +1,341 @@
+package org.embulk.output.orc;
+
+import com.google.common.base.Optional;
+import com.google.common.base.Throwables;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.LocalFileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hdfs.DistributedFileSystem;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.hadoop.util.VersionInfo;
+import org.apache.orc.CompressionKind;
+import org.apache.orc.OrcFile;
+import org.apache.orc.TypeDescription;
+import org.apache.orc.Writer;
+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.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.Exec;
+import org.embulk.spi.OutputPlugin;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageReader;
+import org.embulk.spi.Schema;
+import org.embulk.spi.TransactionalPageOutput;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.time.TimestampFormatter;
+import org.embulk.spi.type.Type;
+import org.embulk.spi.util.Timestamps;
+import org.joda.time.DateTimeZone;
+import org.joda.time.format.DateTimeFormat;
+import org.joda.time.format.DateTimeFormatter;
+
+import java.io.IOException;
+import java.util.List;
+import java.util.Map;
+
+public class OrcOutputPlugin
+        implements OutputPlugin
+{
+    public interface PluginTask
+            extends Task, TimestampFormatter.Task
+    {
+        @Config("path_prefix")
+        String getPathPrefix();
+
+        @Config("file_ext")
+        @ConfigDefault("\".orc\"")
+        String getFileNameExtension();
+
+        @Config("column_options")
+        @ConfigDefault("{}")
+        Map<String, TimestampColumnOption> getColumnOptions();
+
+        @Config("sequence_format")
+        @ConfigDefault("\".%03d\"")
+        String getSequenceFormat();
+
+        @Config("overwrite")
+        @ConfigDefault("false")
+        boolean getOverwrite();
+
+        @Config("default_from_timezone")
+        @ConfigDefault("\"UTC\"")
+        DateTimeZone getDefaultFromTimeZone();
+    }
+
+    public interface TimestampColumnOption
+            extends Task, TimestampFormatter.TimestampColumnOption
+    {
+        @Config("from_timezone")
+        @ConfigDefault("null")
+        Optional<DateTimeZone> getFromTimeZone();
+
+        @Config("from_format")
+        @ConfigDefault("null")
+        Optional<List<String>> getFromFormat();
+    }
+
+    @Override
+    public ConfigDiff transaction(ConfigSource config,
+            Schema schema, int taskCount,
+            OutputPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        // retryable (idempotent) output:
+        // return resume(task.dump(), schema, taskCount, control);
+
+        // non-retryable (non-idempotent) output:
+        control.run(task.dump());
+        return Exec.newConfigDiff();
+    }
+
+    @Override
+    public ConfigDiff resume(TaskSource taskSource,
+            Schema schema, int taskCount,
+            OutputPlugin.Control control)
+    {
+        throw new UnsupportedOperationException("orc output plugin does not support resuming");
+    }
+
+    @Override
+    public void cleanup(TaskSource taskSource,
+            Schema schema, int taskCount,
+            List<TaskReport> successTaskReports)
+
+    {
+    }
+
+    @Override
+    public TransactionalPageOutput open(TaskSource taskSource, Schema schema, int taskIndex)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        final PageReader reader = new PageReader(schema);
+        Writer writer = createWriter(task, schema, taskIndex);
+
+        return new OrcTransactionalPageOutput(reader, writer, task);
+        // Write your code here :)
+//        throw new UnsupportedOperationException("OrcOutputPlugin.run method is not implemented yet");
+    }
+
+    private String buildPath(PluginTask task, int processorIndex)
+    {
+        final String pathPrefix = task.getPathPrefix();
+        final String pathSuffix = task.getFileNameExtension();
+        final String sequenceFormat = task.getSequenceFormat();
+        return pathPrefix + String.format(sequenceFormat, processorIndex) + pathSuffix;
+    }
+
+    private TypeDescription getSchema(Schema schema)
+    {
+        TypeDescription oschema = TypeDescription.createStruct();
+        for (int i = 0; i < schema.size(); i++) {
+            Column column = schema.getColumn(i);
+            Type type = column.getType();
+            switch (type.getName()) {
+                case "long":
+                    oschema.addField(column.getName(), TypeDescription.createLong());
+                    break;
+                case "double":
+                    oschema.addField(column.getName(), TypeDescription.createDouble());
+                    break;
+                case "boolean":
+                    oschema.addField(column.getName(), TypeDescription.createBoolean());
+                    break;
+                case "string":
+                    oschema.addField(column.getName(), TypeDescription.createString());
+                    break;
+                case "timestamp":
+                    oschema.addField(column.getName(), TypeDescription.createTimestamp());
+                    break;
+                default:
+                    System.out.println("Unsupported type");
+                    break;
+            }
+        }
+        return oschema;
+    }
+
+    private Configuration getHadoopConfiguration()
+    {
+        Configuration conf = new Configuration();
+
+        // see: https://stackoverflow.com/questions/17265002/hadoop-no-filesystem-for-scheme-file
+        conf.set("fs.hdfs.impl", DistributedFileSystem.class.getName());
+        conf.set("fs.file.impl", LocalFileSystem.class.getName());
+        // see: https://stackoverflow.com/questions/20833444/how-to-set-objects-in-hadoop-configuration
+
+        return conf;
+    }
+
+    private Writer createWriter(PluginTask task, Schema schema, int processorIndex)
+    {
+        final TimestampFormatter[] timestampFormatters = Timestamps.newTimestampColumnFormatters(task, schema, task.getColumnOptions());
+
+        Configuration conf = getHadoopConfiguration();
+        TypeDescription oschema = getSchema(schema);
+
+        // see: https://groups.google.com/forum/#!topic/vertx/lLb-slzpWVg
+        Thread.currentThread().setContextClassLoader(VersionInfo.class.getClassLoader());
+
+        Writer writer = null;
+        try {
+            // see: https://stackoverflow.com/questions/9256733/how-to-connect-hive-in-ireport
+            // see: https://community.hortonworks.com/content/kbentry/73458/connecting-dbvisualizer-and-datagrip-to-hive-with.html
+            writer = OrcFile.createWriter(new Path(buildPath(task, processorIndex)),
+                    OrcFile.writerOptions(conf)
+                            .setSchema(oschema)
+                            .compress(CompressionKind.ZLIB)
+                            .version(OrcFile.Version.V_0_12));
+        }
+        catch (IOException e) {
+            e.printStackTrace();
+        }
+        return writer;
+    }
+
+    class OrcTransactionalPageOutput
+            implements TransactionalPageOutput
+    {
+        private PageReader reader;
+        private Writer writer;
+        private DateTimeFormatter formatter;
+
+        public OrcTransactionalPageOutput(PageReader reader, Writer writer, PluginTask task)
+        {
+            this.reader = reader;
+            this.writer = writer;
+
+            // formatter
+            DateTimeZone defaultTimeZone = DateTimeZone.forTimeZone(task.getDefaultFromTimeZone().toTimeZone());
+            formatter = DateTimeFormat.forPattern("yyyy-MM-dd HH:mm:ss").withZone(defaultTimeZone);
+        }
+
+        @Override
+        public void add(Page page)
+        {
+            List<String> strings = page.getStringReferences();
+            TypeDescription schema = getSchema(reader.getSchema());
+            VectorizedRowBatch batch = schema.createRowBatch();
+            batch.size = strings.size();
+
+            reader.setPage(page);
+            int i = 0;
+            while (reader.nextRecord()) {
+                // batch.size = page.getStringReferences().size();
+                final int finalI = i;
+
+                reader.getSchema().visitColumns(new ColumnVisitor()
+                {
+
+                    @Override
+                    public void booleanColumn(Column column)
+                    {
+                        if (reader.isNull(column)) {
+                            ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = 0;
+                        }
+                        else {
+                            // TODO; Fix all true bug
+                            if (reader.getBoolean(column)) {
+                                ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = 1;
+                            }
+                            else {
+                                ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = 0;
+                            }
+                        }
+                    }
+
+                    @Override
+                    public void longColumn(Column column)
+                    {
+                        ((LongColumnVector) batch.cols[column.getIndex()]).vector[finalI] = reader.getLong(column);
+                    }
+
+                    @Override
+                    public void doubleColumn(Column column)
+                    {
+                        ((DoubleColumnVector) batch.cols[column.getIndex()]).vector[finalI] = reader.getDouble(column);
+                    }
+
+                    @Override
+                    public void stringColumn(Column column)
+                    {
+                        ((BytesColumnVector) batch.cols[column.getIndex()]).setVal(finalI,
+                                reader.getString(column).getBytes());
+                    }
+
+                    @Override
+                    public void timestampColumn(Column column)
+                    {
+                        if (reader.isNull(column)) {
+                            ((TimestampColumnVector) batch.cols[column.getIndex()]).setNullValue(finalI);
+                        }
+                        else {
+                            Timestamp timestamp = reader.getTimestamp(column);
+                            if (!timestamp.equals("")) {
+                                java.sql.Timestamp ts = new java.sql.Timestamp(timestamp.getEpochSecond() * 1000);
+                                ((TimestampColumnVector) batch.cols[column.getIndex()]).set(finalI, ts);
+                            }
+                            // throw new UnsupportedOperationException("orc output plugin does not support timestamp yet");
+                        }
+                    }
+
+                    @Override
+                    public void jsonColumn(Column column)
+                    {
+                        throw new UnsupportedOperationException("orc output plugin does not support json type");
+                    }
+                });
+                i++;
+            }
+            try {
+                writer.addRowBatch(batch);
+            }
+            catch (IOException e) {
+                e.printStackTrace();
+            }
+        }
+
+        @Override
+        public void finish()
+        {
+            try {
+                writer.close();
+                writer = null;
+            }
+            catch (IOException e) {
+                Throwables.propagate(e);
+            }
+        }
+
+        @Override
+        public void close()
+        {
+            // TODO: something
+        }
+
+        @Override
+        public void abort()
+        {
+            // TODO: something
+        }
+
+        @Override
+        public TaskReport commit()
+        {
+            // TODO: something
+            return Exec.newTaskReport();
+        }
+    }
+}