com.pivotal.hawq.mapreduce.HAWQInputFormat.java Source code

Introduction

Here is the source code for com.pivotal.hawq.mapreduce.HAWQInputFormat.java

Source

package com.pivotal.hawq.mapreduce;

/*
 * 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.
 */

import com.pivotal.hawq.mapreduce.ao.HAWQAOInputFormat;
import com.pivotal.hawq.mapreduce.metadata.HAWQTableFormat;
import com.pivotal.hawq.mapreduce.metadata.MetadataAccessor;
import com.pivotal.hawq.mapreduce.parquet.HAWQParquetInputFormat;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import java.io.IOException;
import java.util.List;

/**
 * An InputFormat that reads tuple from HAWQ table as {@link com.pivotal.hawq.mapreduce.HAWQRecord}.
 * Currently AO and Parquet table are supported.
 */
public class HAWQInputFormat extends FileInputFormat<Void, HAWQRecord> {

    private static final String TABLE_FORMAT = "mapreduce.hawq.table.format";

    private HAWQAOInputFormat aoInputFormat = new HAWQAOInputFormat();
    private HAWQParquetInputFormat parquetInputFormat = new HAWQParquetInputFormat();

    @Override
    public List<InputSplit> getSplits(JobContext job) throws IOException {
        HAWQTableFormat tableFormat = getTableFormat(job.getConfiguration());

        switch (tableFormat) {
        case AO:
            return aoInputFormat.getSplits(job);
        case Parquet:
            return parquetInputFormat.getSplits(job);
        default:
            throw new AssertionError("invalid table format: " + tableFormat);
        }
    }

    @Override
    public RecordReader<Void, HAWQRecord> createRecordReader(InputSplit split, TaskAttemptContext context)
            throws IOException, InterruptedException {

        HAWQTableFormat tableFormat = getTableFormat(context.getConfiguration());

        switch (tableFormat) {
        case AO:
            return aoInputFormat.createRecordReader(split, context);
        case Parquet:
            return parquetInputFormat.createRecordReader(split, context);
        default:
            throw new AssertionError("invalid table format: " + tableFormat);
        }
    }

    private HAWQTableFormat getTableFormat(Configuration conf) {
        String formatName = conf.get(TABLE_FORMAT);
        if (formatName == null) {
            throw new IllegalStateException("Please call HAWQInputFormat.setInput first");
        }
        return HAWQTableFormat.valueOf(formatName);
    }

    /**
     * Initializes the map-part of the job with the appropriate input settings
     * through connecting to Database.
     *
     * @param conf      The map-reduce job configuration
     * @param db_url    The database URL to connect to
     * @param username  The username for setting up a connection to the database
     * @param password  The password for setting up a connection to the database
     * @param tableName The name of the table to access to
     */
    public static void setInput(Configuration conf, String db_url, String username, String password,
            String tableName) {
        MetadataAccessor accessor = MetadataAccessor.newInstanceUsingJDBC(db_url, username, password, tableName);
        setInput(conf, accessor);
    }

    /**
     * Initializes the map-part of the job with the appropriate input settings
     * through reading metadata file stored in local filesystem.
     * <p/>
     * To get metadata file, please use gpextract first
     *
     * @param conf     The map-reduce job configuration
     * @param metadataFile Path to the metadata file generated by gpextract.
     */
    public static void setInput(Configuration conf, String metadataFile) {
        MetadataAccessor accessor = MetadataAccessor.newInstanceUsingFile(metadataFile);
        setInput(conf, accessor);
    }

    private static void setInput(Configuration conf, MetadataAccessor accessor) {
        HAWQTableFormat tableFormat = accessor.getTableFormat();

        switch (tableFormat) {
        case AO:
            HAWQAOInputFormat.setInput(conf, accessor.getAOMetadata());
            break;
        case Parquet:
            HAWQParquetInputFormat.setInput(conf, accessor.getParquetMetadata());
            break;
        default:
            throw new AssertionError("invalid table format: " + tableFormat);
        }

        conf.set(TABLE_FORMAT, tableFormat.name());
    }
}