embulk-output-kafka 0.1.0

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/kafka.rb

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

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

@@ -0,0 +1,189 @@
+package org.embulk.output.kafka;
+
+import org.apache.avro.Schema;
+import org.apache.avro.generic.GenericData;
+import org.apache.avro.generic.GenericRecord;
+import org.embulk.spi.Column;
+import org.embulk.spi.PageReader;
+import org.msgpack.value.Value;
+import org.msgpack.value.ValueFactory;
+
+import java.util.HashMap;
+import java.util.Map;
+import java.util.Objects;
+import java.util.Optional;
+import java.util.stream.Collectors;
+
+public class AvroFormatColumnVisitor extends KafkaOutputColumnVisitor
+{
+    private Schema avroSchema;
+    public GenericRecord genericRecord;
+
+    public AvroFormatColumnVisitor(KafkaOutputPlugin.PluginTask task, PageReader pageReader, Schema avroSchema, GenericRecord genericRecord)
+    {
+        super(task, pageReader);
+        this.avroSchema = avroSchema;
+        this.genericRecord = genericRecord;
+    }
+
+    @Override
+    public void booleanColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            genericRecord.put(column.getName(), null);
+            return;
+        }
+
+        genericRecord.put(column.getName(), pageReader.getBoolean(column));
+    }
+
+    @Override
+    public void longColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            genericRecord.put(column.getName(), null);
+            return;
+        }
+
+        genericRecord.put(column.getName(), pageReader.getLong(column));
+        super.longColumn(column);
+    }
+
+    @Override
+    public void doubleColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            genericRecord.put(column.getName(), null);
+            return;
+        }
+
+        genericRecord.put(column.getName(), pageReader.getDouble(column));
+        super.doubleColumn(column);
+    }
+
+    @Override
+    public void stringColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            genericRecord.put(column.getName(), null);
+            return;
+        }
+
+        genericRecord.put(column.getName(), pageReader.getString(column));
+        super.stringColumn(column);
+    }
+
+    @Override
+    public void timestampColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            genericRecord.put(column.getName(), null);
+            return;
+        }
+
+        genericRecord.put(column.getName(), pageReader.getTimestamp(column).getInstant().toEpochMilli());
+    }
+
+    @Override
+    public void jsonColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            genericRecord.put(column.getName(), null);
+            return;
+        }
+
+        Value value = pageReader.getJson(column);
+        try {
+            Object avroValue = convertMsgPackValueToAvroValue(avroSchema.getField(column.getName()).schema(), value);
+            genericRecord.put(column.getName(), avroValue);
+        }
+        catch (RuntimeException ex) {
+            ex.printStackTrace();
+        }
+    }
+
+    private Object convertMsgPackValueToAvroValue(org.apache.avro.Schema avroSchema, Value value)
+    {
+        switch (avroSchema.getType()) {
+            case ARRAY:
+                if (value.isArrayValue()) {
+                    return value.asArrayValue().list().stream().map(item -> {
+                        return convertMsgPackValueToAvroValue(avroSchema.getElementType(), item);
+                    }).filter(Objects::nonNull).collect(Collectors.toList());
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case MAP:
+                if (value.isMapValue()) {
+                    Map<String, Object> map = new HashMap<>();
+                    for (Map.Entry<Value, Value> entry : value.asMapValue().entrySet()) {
+                        if (!entry.getValue().isNilValue()) {
+                            map.put(entry.getKey().asStringValue().toString(), convertMsgPackValueToAvroValue(avroSchema.getValueType(), entry.getValue()));
+                        }
+                    }
+                    return map;
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case RECORD:
+                if (value.isMapValue()) {
+                    GenericRecord record = new GenericData.Record(avroSchema);
+                    Map<Value, Value> valueMap = value.asMapValue().map();
+                    for (org.apache.avro.Schema.Field field : avroSchema.getFields()) {
+                        Optional.ofNullable(valueMap.get(ValueFactory.newString(field.name()))).ifPresent(v -> {
+                            record.put(field.name(), convertMsgPackValueToAvroValue(field.schema(), v));
+                        });
+                    }
+                    return record;
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case LONG:
+                if (value.isIntegerValue()) {
+                    return value.asIntegerValue().toLong();
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case INT:
+                if (value.isIntegerValue()) {
+                    return value.asIntegerValue().toInt();
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case FLOAT:
+                if (value.isFloatValue()) {
+                    return value.asFloatValue().toFloat();
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case DOUBLE:
+                if (value.isFloatValue()) {
+                    return value.asFloatValue().toDouble();
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case BOOLEAN:
+                if (value.isBooleanValue()) {
+                    return value.asBooleanValue().getBoolean();
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case STRING:
+            case ENUM:
+                if (value.isStringValue()) {
+                    return value.asStringValue().toString();
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case NULL:
+                if (value.isNilValue()) {
+                    return null;
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case UNION:
+                for (org.apache.avro.Schema innerSchema : avroSchema.getTypes()) {
+                    try {
+                        return convertMsgPackValueToAvroValue(innerSchema, value);
+                    }
+                    catch (RuntimeException ignored) {
+                    }
+                }
+                throw new RuntimeException(String.format("Schema mismatch: avro: %s, msgpack: %s", avroSchema.getType().getName(), value.getValueType().name()));
+            case BYTES:
+            case FIXED:
+            default:
+                throw new RuntimeException(String.format("Unsupported avro type %s", avroSchema.getType().getName()));
+        }
+    }
+}

data/src/main/java/org/embulk/output/kafka/JsonFormatColumnVisitor.java

@@ -0,0 +1,103 @@
+package org.embulk.output.kafka;
+
+import com.fasterxml.jackson.databind.JsonNode;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.databind.node.ObjectNode;
+import org.embulk.spi.Column;
+import org.embulk.spi.PageReader;
+import org.msgpack.value.Value;
+
+import java.io.IOException;
+import java.time.format.DateTimeFormatter;
+
+public class JsonFormatColumnVisitor extends KafkaOutputColumnVisitor
+{
+    private ObjectMapper objectMapper;
+    public ObjectNode jsonNode;
+
+    private static DateTimeFormatter timestampFormatter = DateTimeFormatter.ISO_INSTANT;
+
+    public JsonFormatColumnVisitor(KafkaOutputPlugin.PluginTask task, PageReader pageReader, ObjectMapper objectMapper)
+    {
+        super(task, pageReader);
+        this.objectMapper = objectMapper;
+        this.jsonNode = objectMapper.createObjectNode();
+    }
+
+    @Override
+    public void booleanColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            jsonNode.putNull(column.getName());
+            return;
+        }
+
+        jsonNode.put(column.getName(), pageReader.getBoolean(column));
+    }
+
+    @Override
+    public void longColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            jsonNode.putNull(column.getName());
+            return;
+        }
+
+        jsonNode.put(column.getName(), pageReader.getLong(column));
+        super.longColumn(column);
+    }
+
+    @Override
+    public void doubleColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            jsonNode.putNull(column.getName());
+            return;
+        }
+
+        jsonNode.put(column.getName(), pageReader.getDouble(column));
+        super.doubleColumn(column);
+    }
+
+    @Override
+    public void stringColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            jsonNode.putNull(column.getName());
+            return;
+        }
+
+        jsonNode.put(column.getName(), pageReader.getString(column));
+        super.stringColumn(column);
+    }
+
+    @Override
+    public void timestampColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            jsonNode.putNull(column.getName());
+            return;
+        }
+
+        jsonNode.put(column.getName(), timestampFormatter.format(pageReader.getTimestamp(column).getInstant()));
+    }
+
+    @Override
+    public void jsonColumn(Column column)
+    {
+        if (pageReader.isNull(column)) {
+            jsonNode.putNull(column.getName());
+            return;
+        }
+
+        Value value = pageReader.getJson(column);
+        JsonNode json;
+        try {
+            json = objectMapper.readTree(value.toJson());
+        }
+        catch (IOException e) {
+            return;
+        }
+        jsonNode.set(column.getName(), json);
+    }
+}

data/src/main/java/org/embulk/output/kafka/KafkaJsonSerializer.java

@@ -0,0 +1,23 @@
+package org.embulk.output.kafka;
+
+import com.fasterxml.jackson.core.JsonProcessingException;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.fasterxml.jackson.databind.node.ObjectNode;
+import org.apache.kafka.common.serialization.Serializer;
+
+public class KafkaJsonSerializer implements Serializer<ObjectNode>
+{
+    private static ObjectMapper objectMapper = new ObjectMapper();
+
+    @Override
+    public byte[] serialize(String topic, ObjectNode data)
+    {
+        try {
+            return objectMapper.writeValueAsBytes(data);
+        }
+        catch (JsonProcessingException e) {
+            e.printStackTrace();
+            throw new RuntimeException(e);
+        }
+    }
+}

data/src/main/java/org/embulk/output/kafka/KafkaOutputColumnVisitor.java

@@ -0,0 +1,53 @@
+package org.embulk.output.kafka;
+
+import org.embulk.spi.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.PageReader;
+
+public abstract class KafkaOutputColumnVisitor implements ColumnVisitor
+{
+    KafkaOutputPlugin.PluginTask task;
+    PageReader pageReader;
+
+    public Object recordKey = null;
+    public String topicName = null;
+
+    public KafkaOutputColumnVisitor(KafkaOutputPlugin.PluginTask task, PageReader pageReader)
+    {
+        this.task = task;
+        this.pageReader = pageReader;
+    }
+
+    void setRecordKey(Column column, Object value)
+    {
+        if (task.getKeyColumnName().isPresent() && task.getKeyColumnName().get().equals(column.getName())) {
+            recordKey = value;
+        }
+    }
+
+    void setTopicName(Column column, String value)
+    {
+        if (task.getTopicColumn().isPresent() && task.getTopicColumn().get().equals(column.getName())) {
+            topicName = value;
+        }
+    }
+
+    @Override
+    public void longColumn(Column column)
+    {
+        setRecordKey(column, pageReader.getLong(column));
+    }
+
+    @Override
+    public void doubleColumn(Column column)
+    {
+        setRecordKey(column, pageReader.getDouble(column));
+    }
+
+    @Override
+    public void stringColumn(Column column)
+    {
+        setRecordKey(column, pageReader.getString(column));
+        setTopicName(column, pageReader.getString(column));
+    }
+}