org.apache.carbondata.sdk.file.CSVCarbonWriter.java Source code

Introduction

Here is the source code for org.apache.carbondata.sdk.file.CSVCarbonWriter.java

Source

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.carbondata.sdk.file;

import java.io.IOException;
import java.util.Random;
import java.util.UUID;

import org.apache.carbondata.common.annotations.InterfaceAudience;
import org.apache.carbondata.hadoop.api.CarbonTableOutputFormat;
import org.apache.carbondata.hadoop.internal.ObjectArrayWritable;
import org.apache.carbondata.processing.loading.model.CarbonLoadModel;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.JobID;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.TaskAttemptID;
import org.apache.hadoop.mapreduce.TaskID;
import org.apache.hadoop.mapreduce.TaskType;
import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl;

/**
 * Implementation to write rows in CSV format to carbondata file.
 */
@InterfaceAudience.Internal
class CSVCarbonWriter extends CarbonWriter {

    private RecordWriter<NullWritable, ObjectArrayWritable> recordWriter;
    private TaskAttemptContext context;
    private ObjectArrayWritable writable;

    CSVCarbonWriter(CarbonLoadModel loadModel, Configuration hadoopConf) throws IOException {
        CarbonTableOutputFormat.setLoadModel(hadoopConf, loadModel);
        CarbonTableOutputFormat format = new CarbonTableOutputFormat();
        JobID jobId = new JobID(UUID.randomUUID().toString(), 0);
        Random random = new Random();
        TaskID task = new TaskID(jobId, TaskType.MAP, random.nextInt());
        TaskAttemptID attemptID = new TaskAttemptID(task, random.nextInt());
        TaskAttemptContextImpl context = new TaskAttemptContextImpl(hadoopConf, attemptID);
        this.recordWriter = format.getRecordWriter(context);
        this.context = context;
        this.writable = new ObjectArrayWritable();
    }

    /**
     * Write single row data, input row is of type String[]
     */
    @Override
    public void write(Object object) throws IOException {
        try {
            writable.set((String[]) object);
            recordWriter.write(NullWritable.get(), writable);
        } catch (Exception e) {
            throw new IOException(e);
        }
    }

    /**
     * Flush and close the writer
     */
    @Override
    public void close() throws IOException {
        try {
            recordWriter.close(context);
        } catch (InterruptedException e) {
            throw new IOException(e);
        }
    }
}