用MR(MapReduce)查询hbase数据－用到TableMapper和Scan

首先，可以设置scan的startRow, stopRow, filter等属性。于是两种方案：

1.设置scan的filter，然后执行mapper，再reducer成一份结果

2.不用filter过滤，将filter做的事传给mapper做

进行了测试，前者在执行较少量scan记录的时候效率较后者高，但是执行的scan数量多了，便容易导致超时无返回而退出的情况。而为了实现后者，学会了如何向mapper任务中传递参数，走了一点弯路。

最后的一点思考是，用后者效率仍然不高，即便可用前者时效率也不高，因为默认的tablemapper是将对一个region的scan任务放在了一个mapper里，而我一个region有2G多，而我查的数据只占七八个region。于是，想能不能不以region为单位算做mapper，如果不能改，那只有用MR直接操作HBase底层HDFS文件了，这个，…，待研究。

上代码（为了保密，将表名啊，列名列族名啊都改了一下，有改漏的，大家当做没看见啊，另：主要供大家参考下方法，即用mr来查询海量hbase数据，还有如何向mapper传参数）：

package mapreduce.hbase;

import java.io.IOException;

import mapreduce.HDFS_File;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/**
 * 用MR对HBase进行查找，给出Scan的条件诸如startkey endkey;以及filters用来过滤掉不符合条件的记录 LicenseTable
 * 的 RowKey 201101010000000095\xE5\xAE\x81WDTLBZ
 * 
 * @author Wallace
 * 
 */
@SuppressWarnings("unused")
public class MRSearchAuto {
	private static final Log LOG = LogFactory.getLog(MRSearchAuto.class);

	private static String TABLE_NAME = "tablename";
	private static byte[] FAMILY_NAME = Bytes.toBytes("cfname");
	private static byte[][] QUALIFIER_NAME = { Bytes.toBytes("col1"),
			Bytes.toBytes("col2"), Bytes.toBytes("col3") };

	public static class SearchMapper extends
			TableMapper<ImmutableBytesWritable, Text> {
		private int numOfFilter = 0;

		private Text word = new Text();
		String[] strConditionStrings = new String[]{"","",""}/* { "新C87310", "10", "2" } */;

		/*
		 * private void init(Configuration conf) throws IOException,
		 * InterruptedException { strConditionStrings[0] =
		 * conf.get("search.license").trim(); strConditionStrings[1] =
		 * conf.get("search.carColor").trim(); strConditionStrings[2] =
		 * conf.get("search.direction").trim(); LOG.info("license: " +
		 * strConditionStrings[0]); }
		 */
		protected void setup(Context context) throws IOException,
				InterruptedException {
			strConditionStrings[0] = context.getConfiguration().get("search.license").trim();
			strConditionStrings[1] = context.getConfiguration().get("search.color").trim();
			strConditionStrings[2] = context.getConfiguration().get("search.direction").trim();
		}

		protected void map(ImmutableBytesWritable key, Result value,
				Context context) throws InterruptedException, IOException {
			String string = "";
			String tempString;

			/**/
			for (int i = 0; i < 1; i++) {
				// /在此map里进行filter的功能
				tempString = Text.decode(value.getValue(FAMILY_NAME,
						QUALIFIER_NAME[i]));
				if (tempString.equals(/* strConditionStrings[i] */"新C87310")) {
					LOG.info("新C87310. conf: " + strConditionStrings[0]);
					if (tempString.equals(strConditionStrings[i])) {
						string = string + tempString + " ";
					} else {
						return;
					}
				}

				else {
					return;
				}
			}

			word.set(string);
			context.write(null, word);
		}
	}

	public void searchHBase(int numOfDays) throws IOException,
			InterruptedException, ClassNotFoundException {
		long startTime;
		long endTime;

		Configuration conf = HBaseConfiguration.create();
		conf.set("hbase.zookeeper.quorum", "node2,node3,node4");
		conf.set("fs.default.name", "hdfs://node1");
		conf.set("mapred.job.tracker", "node1:54311");
		/*
		 * 传递参数给map
		 */
		conf.set("search.license", "新C87310");
		conf.set("search.color", "10");
		conf.set("search.direction", "2");

		Job job = new Job(conf, "MRSearchHBase");
		System.out.println("search.license: " + conf.get("search.license"));
		job.setNumReduceTasks(0);
		job.setJarByClass(MRSearchAuto.class);
		Scan scan = new Scan();
		scan.addFamily(FAMILY_NAME);
		byte[] startRow = Bytes.toBytes("2011010100000");
		byte[] stopRow;
		switch (numOfDays) {
		case 1:
			stopRow = Bytes.toBytes("2011010200000");
			break;
		case 10:
			stopRow = Bytes.toBytes("2011011100000");
			break;
		case 30:
			stopRow = Bytes.toBytes("2011020100000");
			break;
		case 365:
			stopRow = Bytes.toBytes("2012010100000");
			break;
		default:
			stopRow = Bytes.toBytes("2011010101000");
		}
		// 设置开始和结束key
		scan.setStartRow(startRow);
		scan.setStopRow(stopRow);

		TableMapReduceUtil.initTableMapperJob(TABLE_NAME, scan,
				SearchMapper.class, ImmutableBytesWritable.class, Text.class,
				job);
		Path outPath = new Path("searchresult");
		HDFS_File file = new HDFS_File();
		file.DelFile(conf, outPath.getName(), true); // 若已存在，则先删除
		FileOutputFormat.setOutputPath(job, outPath);// 输出结果

		startTime = System.currentTimeMillis();
		job.waitForCompletion(true);
		endTime = System.currentTimeMillis();
		System.out.println("Time used: " + (endTime - startTime));
		System.out.println("startRow:" + Text.decode(startRow));
		System.out.println("stopRow: " + Text.decode(stopRow));
	}

	public static void main(String args[]) throws IOException,
			InterruptedException, ClassNotFoundException {
		MRSearchAuto mrSearchAuto = new MRSearchAuto();
		int numOfDays = 1;
		if (args.length == 1)
			numOfDays = Integer.valueOf(args[0]);
		System.out.println("Num of days: " + numOfDays);
		mrSearchAuto.searchHBase(numOfDays);
	}
}

开始时，我是在外面conf.set了传入的参数，而在mapper的init(Configuration)里get参数并赋给mapper对象。

将参数传给map运行时结果不对
for (int i = 0; i < 1; i++) {
    // /在此map里进行filter的功能
    tempString = Text.decode(value.getValue(FAMILY_NAME,
      QUALIFIER_NAME[i]));
    if (tempString.equals(/*strConditionStrings[i]*/"新C87310"))
     string = string + tempString + " ";
    else {
     return;
    }
   }
如果用下面的mapper的init获取conf传来的参数，然后在上面map函数里进行调用，结果便不对了。
直接指定值时和参数传过来相同的值时，其output的结果分别为1条和0条。
  private void init(Configuration conf) throws IOException,
    InterruptedException {
   strConditionStrings[0] = conf.get("search.licenseNumber").trim();
   strConditionStrings[1] = conf.get("search.carColor").trim();
   strConditionStrings[2] = conf.get("search.direction").trim();
  }
加了个日志写
private static final Log LOG = LogFactory.getLog(MRSearchAuto.class);
init()函数里：
LOG.info("license: " + strConditionStrings[0]);
map里
 if (tempString.equals(/* strConditionStrings[i] */"新C87310")) {
  LOG.info("新C87310. conf: " + strConditionStrings[0]);
然后在网页 namenode:50030上看任务，最终定位到哪台机器执行了那个map，然后看日志
mapreduce.hbase.TestMRHBase: 新C87310. conf: null
在conf.set之后我也写了下，那时正常，但是在map里却是null了，而在map类的init函数打印的却没有打印。
因此，问题应该是：
map类的init()函数没有执行到！
于是init()的获取conf中参数值并赋给map里变量的操作便未执行，同时打印日志也未执行。
OK！看怎么解决
放在setup里获取
  protected void setup(Context context) throws IOException,
    InterruptedException {
  // strConditionStrings[0] = context.getConfiguration().get("search.license").trim();
  // strConditionStrings[1] = context.getConfiguration().get("search.color").trim();
  // strConditionStrings[2] = context.getConfiguration().get("search.direction").trim();
  }
报错
12/01/12 11:21:56 INFO mapred.JobClient:  map 0% reduce 0%
12/01/12 11:22:03 INFO mapred.JobClient: Task Id : attempt_201201100941_0071_m_000000_0, Status : FAILED
java.lang.NullPointerException
 at mapreduce.hbase.MRSearchAuto$SearchMapper.setup(MRSearchAuto.java:66)
 at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142)
 at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:656)
 at org.apache.hadoop.mapred.MapTask.run(MapTask.java:325)
 at org.apache.hadoop.mapred.Child$4.run(Child.java:270)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:396)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1127)
 at org.apache.hadoop.mapred.Child.main(Child.java:264)

attempt_201201100941_0071_m_000000_0: log4j:WARN No appenders could be found for logger (org.apache.hadoop.hdfs.DFSClient).
attempt_201201100941_0071_m_000000_0: log4j:WARN Please initialize the log4j system properly.
12/01/12 11:22:09 INFO mapred.JobClient: Task Id : attempt_201201100941_0071_m_000000_1, Status : FAILED
java.lang.NullPointerException
 at mapreduce.hbase.MRSearchAuto$SearchMapper.setup(MRSearchAuto.java:66)
 at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:142)
 at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:656)
 at org.apache.hadoop.mapred.MapTask.run(MapTask.java:325)
 at org.apache.hadoop.mapred.Child$4.run(Child.java:270)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:396)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1127)
 at org.apache.hadoop.mapred.Child.main(Child.java:264)
然后将setup里的东西注释掉，无错，错误应该在context上，进一步确认，在里面不用context，直接赋值，有结果，好！
说明是context的事了，NullPointerException,应该是context.getConfiguration().get("search.license")这些中有一个是null的。
突然想起来，改了下get时候的属性，而set时候没改，于是不对应，于是context.getConfiguration().get("search.color")及下面的一项都是null，null.trim()报的异常。
  conf.set("search.license", "新C87310");
  conf.set("search.color", "10");
  conf.set("search.direction", "2");
修改后，问题解决。
实现了向map中传参数