embulk-formatter-avro 0.1.0

data/example/sample_01.csv

@@ -0,0 +1,7 @@
+id,account,time,purchase,comment,data,data2,type,md5
+1,32864,2015-01-27 19:23:49,20150127,embulk,"{\"foo\": \"bar\", \"events\": [{\"id\": 1, \"name\": \"Name1\"}, {\"id\": 2, \"name\": \"Name2\"}]}","[{\"hoge\": 1}]","A",6c3983adda53b2136532dbd5b4d668b9
+2,14824,2015-01-27 19:01:23,20150127,embulk jruby,"{\"events\": [{\"id\": 1, \"name\": \"Name1\"}, {\"id\": 2, \"name\": \"Name2\"}]}","[]","B",NULL
+3,27559,2015-01-28 02:20:02,20150128,"Embulk ""csv"" parser plugin",NULL,"[]","C",8c3983ad4jsal42010325kld024954ll
+4,11270,2015-01-29 11:54:36,20150129,NULL,NULL,"[]","A",474a3bdb966b40c80acb069f73441f29
+4,11270,2015-01-29 11:54:36,20150129,NULL,NULL,"[]","D",NULL
+4,11270,2015-01-29 11:54:36,20150129,NULL,NULL,NULL,"A",NULL

data/example/schema.avsc

@@ -0,0 +1,33 @@
+{
+  "type" : "record",
+  "name" : "Item",
+  "namespace" : "example.avro",
+  "fields" : [
+    {"name": "id", "type": "long"},
+    {"name": "account", "type": "long"},
+    {"name": "time", "type": "string"},
+    {"name": "purchase", "type": "string"},
+    {"name": "comment", "type": ["string", "null"]},
+    {"name": "data", "type": [
+      {
+        "type": "record",
+        "name": "data_record",
+        "fields": [
+          {"name": "foo", "type": ["null", "string"]},
+          {"name": "events", "type":  ["null", {"type": "array", "items": {"type": "map", "values": "string"}}]}
+        ]
+      }, "null"]
+    },
+    {"name": "data2", "type": {
+      "type": "array", "items": {
+        "type": "record",
+        "name": "data2_record",
+        "fields": [
+          {"name": "hoge", "type": ["null", "int"]}
+        ]
+      }
+    }},
+    {"name": "type", "type": {"type": "enum", "name": "type_enum", "symbols": ["A", "B", "C"]}},
+    {"name": "md5", "type": ["null", {"type": "fixed", "name": "md5_value", "size": 32}]}
+  ]
+}

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Jan 13 12:41:02 JST 2016
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.10-bin.zip

data/gradlew

@@ -0,0 +1,160 @@
+#!/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
+
+# 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 "$SAVED" >/dev/null
+
+CLASSPATH=$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 "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$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=$APP_BASE_NAME"
+
+exec "$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/formatter/avro.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_formatter(
+  "avro", "org.embulk.formatter.avro.AvroFormatterPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/formatter/avro/AvroFormatterColumnVisitor.java

@@ -0,0 +1,97 @@
+package org.embulk.formatter.avro;
+
+import org.apache.avro.generic.GenericRecord;
+import org.embulk.formatter.avro.converter.AbstractAvroValueConverter;
+import org.embulk.spi.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.PageReader;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.time.TimestampFormatter;
+import org.msgpack.value.Value;
+
+public class AvroFormatterColumnVisitor implements ColumnVisitor {
+    private PageReader pageReader;
+    private TimestampFormatter[] timestampFormatters;
+    private AbstractAvroValueConverter[] avroValueConverters;
+    private GenericRecord record;
+
+    AvroFormatterColumnVisitor(PageReader pageReader, TimestampFormatter[] timestampFormatters, AbstractAvroValueConverter[] avroValueConverters, GenericRecord record) {
+        this.pageReader = pageReader;
+        this.timestampFormatters = timestampFormatters;
+        this.avroValueConverters = avroValueConverters;
+        this.record = record;
+    }
+
+    @Override
+    public void booleanColumn(Column column) {
+        if (pageReader.isNull(column))
+            return;
+        AbstractAvroValueConverter converter = avroValueConverters[column.getIndex()];
+        if (converter == null)
+            return;
+        Boolean value = pageReader.getBoolean(column);
+        Object result = converter.booleanColumn(value);
+        record.put(column.getName(), result);
+    }
+
+    @Override
+    public void longColumn(Column column) {
+        if (pageReader.isNull(column))
+            return;
+        AbstractAvroValueConverter converter = avroValueConverters[column.getIndex()];
+        if (converter == null)
+            return;
+        Long value = pageReader.getLong(column);
+        Object result = converter.longColumn(value);
+        record.put(column.getName(), result);
+    }
+
+    @Override
+    public void doubleColumn(Column column) {
+        if (pageReader.isNull(column))
+            return;
+        AbstractAvroValueConverter converter = avroValueConverters[column.getIndex()];
+        if (converter == null)
+            return;
+        Double value = pageReader.getDouble(column);
+        Object result = converter.doubleColumn(value);
+        record.put(column.getName(), result);
+    }
+
+    @Override
+    public void stringColumn(Column column) {
+        if (pageReader.isNull(column))
+            return;
+        AbstractAvroValueConverter converter = avroValueConverters[column.getIndex()];
+        if (converter == null)
+            return;
+        String value = pageReader.getString(column);
+        Object result = converter.stringColumn(value);
+        record.put(column.getName(), result);
+    }
+
+    @Override
+    public void timestampColumn(Column column) {
+        if (pageReader.isNull(column))
+            return;
+        AbstractAvroValueConverter converter = avroValueConverters[column.getIndex()];
+        if (converter == null)
+            return;
+        Timestamp value = pageReader.getTimestamp(column);
+        String formatted = timestampFormatters[column.getIndex()].format(value);
+        Object result = converter.timestampColumn(formatted);
+        record.put(column.getName(), result);
+    }
+
+    @Override
+    public void jsonColumn(Column column) {
+        if (pageReader.isNull(column))
+            return;
+        AbstractAvroValueConverter converter = avroValueConverters[column.getIndex()];
+        if (converter == null)
+            return;
+        Value value = pageReader.getJson(column);
+        Object result = converter.jsonColumn(value);
+        record.put(column.getName(), result);
+    }
+}

data/src/main/java/org/embulk/formatter/avro/AvroFormatterPlugin.java

@@ -0,0 +1,183 @@
+package org.embulk.formatter.avro;
+
+import org.apache.avro.file.DataFileWriter;
+import org.apache.avro.generic.GenericData;
+import org.apache.avro.generic.GenericDatumWriter;
+import org.apache.avro.generic.GenericRecord;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigException;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.formatter.avro.converter.AbstractAvroValueConverter;
+import org.embulk.formatter.avro.converter.AvroValueConverterFactory;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.Column;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FileOutput;
+import org.embulk.spi.FormatterPlugin;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageOutput;
+import org.embulk.spi.PageReader;
+import org.embulk.spi.Schema;
+import org.embulk.spi.time.TimestampFormatter;
+import org.embulk.spi.unit.LocalFile;
+import org.embulk.spi.util.FileOutputOutputStream;
+import org.embulk.spi.util.Timestamps;
+import org.slf4j.Logger;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+public class AvroFormatterPlugin
+        implements FormatterPlugin
+{
+    public interface PluginTask
+            extends Task, TimestampFormatter.Task
+    {
+        @Config("avsc")
+        LocalFile getAvsc();
+
+        @Config("column_options")
+        @ConfigDefault("{}")
+        Map<String, TimestampFormatter.TimestampColumnOption> getColumnOptions();
+
+        @Config("skip_error_record")
+        @ConfigDefault("false")
+        Boolean getSkipErrorRecord();
+
+        @ConfigInject
+        public BufferAllocator getBufferAllocator();
+    }
+
+    @Override
+    public void transaction(ConfigSource config, Schema schema,
+            FormatterPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        // validate avsc option
+        try {
+            File avsc = task.getAvsc().getFile();
+            new org.apache.avro.Schema.Parser().parse(avsc);
+        } catch (IOException e) {
+            throw new ConfigException("avsc file is not found");
+        }
+
+
+        // validate column_options
+        for (String columnName : task.getColumnOptions().keySet()) {
+            schema.lookupColumn(columnName);  // throws SchemaConfigException
+        }
+
+        control.run(task.dump());
+    }
+
+    final Logger logger = Exec.getLogger(this.getClass());
+
+    @Override
+    public PageOutput open(TaskSource taskSource, final Schema schema,
+            FileOutput output)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        final Boolean skipErrorRecord = task.getSkipErrorRecord();
+        final TimestampFormatter[] timestampFormatters = Timestamps.newTimestampColumnFormatters(task, schema, task.getColumnOptions());
+        final FileOutputOutputStream stream = new FileOutputOutputStream(output, task.getBufferAllocator(), FileOutputOutputStream.CloseMode.CLOSE);
+
+        final org.apache.avro.Schema avroSchema;
+        final DataFileWriter<GenericRecord> writer;
+        try {
+            File avsc = task.getAvsc().getFile();
+            avroSchema = new org.apache.avro.Schema.Parser().parse(avsc);
+            GenericDatumWriter<GenericRecord> datumWriter = new GenericDatumWriter<>(avroSchema);
+            writer = new DataFileWriter<>(datumWriter);
+            stream.nextFile();
+            writer.create(avroSchema, stream);
+        } catch (IOException e) {
+            throw new ConfigException("avsc file is not found");
+        }
+
+        final AbstractAvroValueConverter[] avroValueConverters = new AbstractAvroValueConverter[schema.size()];
+        List<AbstractAvroValueConverter> array = new ArrayList<>();
+        for (Column c : schema.getColumns()) {
+            org.apache.avro.Schema.Field field = avroSchema.getField(c.getName());
+            if (field != null) {
+                avroValueConverters[c.getIndex()] = AvroValueConverterFactory.createConverter(field);
+            }
+        }
+
+        return new PageOutput() {
+            private final PageReader pageReader = new PageReader(schema);
+
+            @Override
+            public void add(Page page) {
+                pageReader.setPage(page);
+
+                while (pageReader.nextRecord()) {
+                    GenericRecord record = new GenericData.Record(avroSchema);
+
+                    try {
+                        schema.visitColumns(new AvroFormatterColumnVisitor(pageReader, timestampFormatters, avroValueConverters, record));
+                    } catch (RuntimeException ex) {
+                        if (skipErrorRecord) {
+                            logger.warn(ex.getMessage());
+                            logger.warn(String.format("skip record: %s", record));
+                            continue;
+                        } else {
+                            throw ex;
+                        }
+                    }
+
+                    try {
+                        writer.append(record);
+                    } catch (RuntimeException ex) {
+                        if (skipErrorRecord) {
+                            logger.warn(ex.getMessage());
+                            logger.warn(String.format("skip record: %s", record));
+                        } else {
+                            throw ex;
+                        }
+                    } catch (IOException e) {
+                        e.printStackTrace();
+                        throw new RuntimeException("failed to write");
+                    }
+                }
+
+                try {
+                    writer.flush();
+                } catch (IOException e) {
+                    e.printStackTrace();
+                    throw new RuntimeException("failed to write");
+                }
+            }
+
+            @Override
+            public void finish() {
+                try {
+                    writer.flush();
+                } catch (IOException e) {
+                    e.printStackTrace();
+                    throw new RuntimeException("failed to write");
+                }
+                stream.finish();
+            }
+
+            @Override
+            public void close() {
+                try {
+                    writer.close();
+                } catch (IOException e) {
+                    e.printStackTrace();
+                    throw new RuntimeException("failed to write");
+                }
+                stream.close();
+            }
+        };
+    }
+}