embulk-input-kafka 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-4.10.3-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/input/kafka.rb

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

data/src/main/java/org/embulk/input/kafka/AbstractKafkaInputColumnVisitor.java

@@ -0,0 +1,135 @@
+package org.embulk.input.kafka;
+
+import org.apache.kafka.clients.consumer.ConsumerRecord;
+import org.apache.kafka.common.serialization.DoubleDeserializer;
+import org.apache.kafka.common.serialization.LongDeserializer;
+import org.apache.kafka.common.serialization.StringDeserializer;
+import org.apache.kafka.common.utils.Bytes;
+import org.embulk.input.kafka.KafkaInputPlugin.PluginTask;
+import org.embulk.spi.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.time.TimestampParser;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+public abstract class AbstractKafkaInputColumnVisitor<V> implements ColumnVisitor
+{
+  protected final PluginTask task;
+  protected final PageBuilder pageBuilder;
+  protected final TimestampParser[] timestampParsers;
+
+  protected ConsumerRecord<Bytes, V> consumerRecord;
+  protected V recordValue;
+
+  private static final LongDeserializer longDeserializer = new LongDeserializer();
+  private static final StringDeserializer stringDeserializer = new StringDeserializer();
+  private static final DoubleDeserializer doubleDeserializer = new DoubleDeserializer();
+
+  private static final Logger logger = LoggerFactory.getLogger(AbstractKafkaInputColumnVisitor.class);
+
+  public AbstractKafkaInputColumnVisitor(PluginTask task, PageBuilder pageBuilder, TimestampParser[] timestampParsers)
+  {
+    this.task = task;
+    this.pageBuilder = pageBuilder;
+    this.timestampParsers = timestampParsers;
+  }
+
+  public void reset(ConsumerRecord<Bytes, V> consumerRecord)
+  {
+    this.consumerRecord = consumerRecord;
+    this.recordValue = consumerRecord.value();
+  }
+
+  protected boolean isKeyColumn(Column column)
+  {
+    return column.getName().equals(task.getKeyColumnName());
+  }
+
+  protected boolean isPartitionColumn(Column column)
+  {
+    return column.getName().equals(task.getPartitionColumnName());
+  }
+
+  protected void longColumnForKey(Column column)
+  {
+    if (consumerRecord.serializedKeySize() == 0) {
+      pageBuilder.setNull(column);
+      return;
+    }
+    try {
+      long key = longDeserializer.deserialize("dummy", consumerRecord.key().get());
+      pageBuilder.setLong(column, key);
+    }
+    catch (Exception e) {
+      logDeserializeFailure(consumerRecord);
+      pageBuilder.setNull(column);
+    }
+  }
+
+  protected void longColumnForPartition(Column column)
+  {
+    pageBuilder.setLong(column, Integer.valueOf(consumerRecord.partition()).longValue());
+  }
+
+  public void doubleColumnForKey(Column column)
+  {
+    if (consumerRecord.serializedKeySize() == 0) {
+      pageBuilder.setNull(column);
+      return;
+    }
+    try {
+      double key = doubleDeserializer.deserialize("dummy", consumerRecord.key().get());
+      pageBuilder.setDouble(column, key);
+    }
+    catch (Exception e) {
+      logDeserializeFailure(consumerRecord);
+      pageBuilder.setNull(column);
+    }
+  }
+
+  public void stringColumnForKey(Column column)
+  {
+    if (consumerRecord.serializedKeySize() == 0) {
+      pageBuilder.setNull(column);
+      return;
+    }
+    try {
+      String key = stringDeserializer.deserialize("dummy", consumerRecord.key().get());
+      pageBuilder.setString(column, key);
+    }
+    catch (Exception e) {
+      logDeserializeFailure(consumerRecord);
+      pageBuilder.setNull(column);
+    }
+  }
+
+  public void timestampColumnForKey(Column column)
+  {
+    if (consumerRecord.serializedKeySize() == 0) {
+      pageBuilder.setNull(column);
+      return;
+    }
+    try {
+      String key = stringDeserializer.deserialize("dummy", consumerRecord.key().get());
+      try {
+        Timestamp timestamp = timestampParsers[column.getIndex()].parse(key);
+        pageBuilder.setTimestamp(column, timestamp);
+      }
+      catch (Exception e) {
+        logDeserializeFailure(consumerRecord);
+        pageBuilder.setNull(column);
+      }
+    }
+    catch (Exception e) {
+      logDeserializeFailure(consumerRecord);
+      pageBuilder.setNull(column);
+    }
+  }
+
+  private void logDeserializeFailure(ConsumerRecord<Bytes, V> consumerRecord)
+  {
+    logger.warn("Failed to deserialize record key: key={} value={}", consumerRecord.key(), consumerRecord.value());
+  }
+}

data/src/main/java/org/embulk/input/kafka/AvroFormatColumnVisitor.java

@@ -0,0 +1,207 @@
+package org.embulk.input.kafka;
+
+import com.google.common.collect.ImmutableMap;
+import org.apache.avro.generic.GenericRecord;
+import org.embulk.input.kafka.KafkaInputPlugin.PluginTask;
+import org.embulk.spi.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.time.TimestampParser;
+import org.msgpack.value.Value;
+import org.msgpack.value.ValueFactory;
+
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+public class AvroFormatColumnVisitor extends AbstractKafkaInputColumnVisitor<Object> implements ColumnVisitor
+{
+  static class UnsupportedValueTypeException extends RuntimeException
+  {
+    public UnsupportedValueTypeException(String message)
+    {
+      super(message);
+    }
+  }
+
+  public AvroFormatColumnVisitor(PluginTask task, PageBuilder pageBuilder, TimestampParser[] timestampParsers)
+  {
+    super(task, pageBuilder, timestampParsers);
+  }
+
+  private GenericRecord genericRecord()
+  {
+    return (GenericRecord) recordValue;
+  }
+
+  @Override
+  public void booleanColumn(Column column)
+  {
+    Object value = genericRecord().get(column.getName());
+    if (value == null) {
+      pageBuilder.setNull(column);
+      return;
+    }
+    pageBuilder.setBoolean(column, (boolean) value);
+  }
+
+  @Override
+  public void longColumn(Column column)
+  {
+    if (super.isKeyColumn(column)) {
+      super.longColumnForKey(column);
+      return;
+    }
+
+    if (isPartitionColumn(column)) {
+      super.longColumnForPartition(column);
+      return;
+    }
+
+    Object value = genericRecord().get(column.getName());
+    if (value == null) {
+      pageBuilder.setNull(column);
+      return;
+    }
+
+    long longValue;
+    if (value instanceof Long) {
+      longValue = (Long) value;
+    }
+    else if (value instanceof Integer) {
+      longValue = ((Integer) value).longValue();
+    }
+    else if (value instanceof Double) {
+      longValue = ((Double) value).longValue();
+    }
+    else if (value instanceof Float) {
+      longValue = ((Float) value).longValue();
+    }
+    else {
+      throw new RuntimeException(String.format("Cannot cast value to long: column=%s value=%s", column, value));
+    }
+    pageBuilder.setLong(column, longValue);
+  }
+
+  @Override
+  public void doubleColumn(Column column)
+  {
+    if (super.isKeyColumn(column)) {
+      super.doubleColumnForKey(column);
+      return;
+    }
+
+    Object value = genericRecord().get(column.getName());
+    if (value == null) {
+      pageBuilder.setNull(column);
+      return;
+    }
+
+    double doubleValue;
+    if (value instanceof Long) {
+      doubleValue = ((Long) value).doubleValue();
+    }
+    else if (value instanceof Integer) {
+      doubleValue = ((Integer) value).doubleValue();
+    }
+    else if (value instanceof Double) {
+      doubleValue = (Double) value;
+    }
+    else if (value instanceof Float) {
+      doubleValue = ((Float) value).doubleValue();
+    }
+    else {
+      throw new RuntimeException(String.format("Cannot cast value to double: column=%s value=%s", column, value));
+    }
+    pageBuilder.setDouble(column, doubleValue);
+  }
+
+  @Override
+  public void stringColumn(Column column)
+  {
+    if (super.isKeyColumn(column)) {
+      super.stringColumnForKey(column);
+      return;
+    }
+
+    Object value = genericRecord().get(column.getName());
+    if (value == null) {
+      pageBuilder.setNull(column);
+      return;
+    }
+
+    pageBuilder.setString(column, value.toString());
+  }
+
+  @Override
+  public void timestampColumn(Column column)
+  {
+    if (super.isKeyColumn(column)) {
+      super.timestampColumnForKey(column);
+      return;
+    }
+
+    Object value = genericRecord().get(column.getName());
+    if (value == null) {
+      pageBuilder.setNull(column);
+      return;
+    }
+
+    Timestamp timestamp = timestampParsers[column.getIndex()].parse(value.toString());
+    pageBuilder.setTimestamp(column, timestamp);
+  }
+
+  @Override
+  public void jsonColumn(Column column)
+  {
+    Object value = genericRecord().get(column.getName());
+    Value jsonValue = convertAvroToValue(value);
+    pageBuilder.setJson(column, jsonValue);
+  }
+
+  private Value convertAvroToValue(Object avroValue)
+  {
+    if (avroValue instanceof GenericRecord) {
+      ImmutableMap.Builder<Value, Value> builder = ImmutableMap.builder();
+      GenericRecord record = (GenericRecord) avroValue;
+      record.getSchema().getFields().forEach(field -> builder
+          .put(convertAvroToValue(field.name()), convertAvroToValue(record.get(field.name()))));
+      return ValueFactory.newMap(builder.build());
+    }
+    else if (avroValue instanceof List<?>) {
+      List<Value> values = ((List<?>) avroValue).stream().map(this::convertAvroToValue)
+          .collect(Collectors.toList());
+      return ValueFactory.newArray(values);
+    }
+    else if (avroValue instanceof Map<?, ?>) {
+      ImmutableMap.Builder<Value, Value> builder = ImmutableMap.builder();
+      ((Map<?, ?>) avroValue).forEach((k, v) -> builder.put(convertAvroToValue(k), convertAvroToValue(v)));
+      return ValueFactory.newMap(builder.build());
+    }
+    else if (avroValue instanceof Boolean) {
+      return ValueFactory.newBoolean((Boolean) avroValue);
+    }
+    else if (avroValue instanceof Integer) {
+      return ValueFactory.newInteger((Integer) avroValue);
+    }
+    else if (avroValue instanceof Long) {
+      return ValueFactory.newInteger((Long) avroValue);
+    }
+    else if (avroValue instanceof Float) {
+      return ValueFactory.newFloat((Float) avroValue);
+    }
+    else if (avroValue instanceof Double) {
+      return ValueFactory.newFloat((Double) avroValue);
+    }
+    else if (avroValue instanceof String) {
+      return ValueFactory.newString((String) avroValue);
+    }
+    else if (avroValue == null) {
+      return ValueFactory.newNil();
+    }
+    else {
+      throw new UnsupportedValueTypeException(String.format("%s is not supported", avroValue));
+    }
+  }
+}