生成HFile以及入库到HBase

一、MR生成HFile文件

package insert.tools.hfile;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.KeyValueSortReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class TestHFileToHBase {

	public static class TestHFileToHBaseMapper extends Mapper {

		@Override
		protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
			String[] values = value.toString().split("/t", 2);
			byte[] row = Bytes.toBytes(values[0]);
			ImmutableBytesWritable k = new ImmutableBytesWritable(row);
			KeyValue kvProtocol = new KeyValue(row, "PROTOCOLID".getBytes(), "PROTOCOLID".getBytes(), values[1]
					.getBytes());
			context.write(k, kvProtocol);

			// KeyValue kvSrcip = new KeyValue(row, "SRCIP".getBytes(),
			// "SRCIP".getBytes(), values[1].getBytes());
			// context.write(k, kvSrcip);
//			 HFileOutputFormat.getRecordWriter 
		}

	}

	public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
		Configuration conf = HBaseConfiguration.create();
		Job job = new Job(conf, "TestHFileToHBase");
		job.setJarByClass(TestHFileToHBase.class);

		job.setOutputKeyClass(ImmutableBytesWritable.class);
		job.setOutputValueClass(KeyValue.class);

		job.setMapperClass(TestHFileToHBaseMapper.class);
		job.setReducerClass(KeyValueSortReducer.class);
//		job.setOutputFormatClass(org.apache.hadoop.hbase.mapreduce.HFileOutputFormat.class);
		job.setOutputFormatClass(HFileOutputFormat.class);
		// job.setNumReduceTasks(4);
		// job.setPartitionerClass(org.apache.hadoop.hbase.mapreduce.SimpleTotalOrderPartitioner.class);

		// HBaseAdmin admin = new HBaseAdmin(conf);
//		HTable table = new HTable(conf, "hua");

		 HFileOutputFormat.configureIncrementalLoad(job, table);

		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		System.exit(job.waitForCompletion(true) ? 0 : 1);
	}

}

二、改进后的HFileOutputFormat

源码中的HFileOutputFormat只适合一次生成一个列族的HFile，改进后的HFileOutputFormat适合同时多列族生成HFile文件。有add标签的是在源码上添加代码，有revise标签的是在源码上增加代码。参考：https://review.cloudera.org/r/1272/diff/1/?file=17977#file17977line93

/**
 * Copyright 2009 The Apache Software Foundation
 *
 * 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 insert.tools.hfile;

im