3

我想运行一个 map reduce 示例：

    package my.test;

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;

import org.apache.commons.cli.BasicParser;
import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.CommandLineParser;
import org.apache.commons.cli.HelpFormatter;
import org.apache.commons.cli.Options;
import org.apache.commons.cli.ParseException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.MultiTableOutputFormat;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;




    /**
     * This class demonstrates the use of the MultiTableOutputFormat class.
     * Using this class we can write the output of a Hadoop map reduce program
     * into different HBase table.
     *
     * @version 1.0 19 Jul 2011
     * @author  Wildnove
     */
    public class TestMultiTable extends Configured implements Tool {

        private static final Logger LOG = Logger.getLogger(TestMultiTable.class);
        private static final String CMDLINE = "com.wildnove.tutorial.TestMultiTable <inputFile> [-n name] [-s]";

        public static void main(String[] args) throws Exception {
            int res = ToolRunner.run(new TestMultiTable(), args);
            System.exit(res);
        }

        @Override
        public int run(String[] args) throws Exception {
            HelpFormatter help = new HelpFormatter();
            Options options = new Options();
            options.addOption("h", "help", false, "print program usage");
            options.addOption("n", "name", true, "sets job name");
            CommandLineParser parser = new BasicParser();
            CommandLine cline;
            try {
                cline = parser.parse(options, args);
                args = cline.getArgs();
                if (args.length < 1) {
                    help.printHelp(CMDLINE, options);
                    return -1;
                }
            } catch (ParseException e) {
                System.out.println(e);
                e.printStackTrace();
                help.printHelp(CMDLINE, options);
                return -1;
            }

            String name = null;
            try {
                if (cline.hasOption('n'))
                    name = cline.getOptionValue('n');
                else
                    name = "wildnove.com - Tutorial MultiTableOutputFormat ";
                Configuration conf = getConf();
                FileSystem fs = FileSystem.get(conf);
                Path inputFile = new Path(fs.makeQualified(new Path(args[0])).toUri().getPath());
                if (!getMultiTableOutputJob(name, inputFile).waitForCompletion(true))
                    return -1;
            } catch (Exception e) {
                System.out.println(e);
                e.printStackTrace();
                help.printHelp(CMDLINE, options);
                return -1;
            }
            return 0;
        }

        /**
         * Here we configure our job to use MultiTableOutputFormat class as map reduce output.
         * Note that we use 1 reduce only for debugging purpose, but you can use more than 1 reduce.
         */
        private Job getMultiTableOutputJob(String name, Path inputFile) throws IOException {
            if (LOG.isInfoEnabled()) {
                LOG.info(name + " starting...");
                LOG.info("computing file: " + inputFile);
            }
            Job job = new Job(getConf(), name);
            job.setJarByClass(TestMultiTable.class);
            job.setMapperClass(Mapper.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            FileInputFormat.addInputPath(job, inputFile);
            job.setOutputFormatClass(MultiTableOutputFormat.class);
            job.setNumReduceTasks(1);
            job.setReducerClass(Reducer.class);

            return job;
        }

        private static class Mapper extends org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, Text> {

            private Text outKey = new Text();
            private Text outValue = new Text();

            /**
             * The map method splits the csv file according to this structure
             * brand,model,size (e.g. Cadillac,Seville,Midsize) and output all data using
             * brand as key and the couple model,size as value.
             */
            @Override
            public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
                String[] valueSplitted = value.toString().split(",");
                if (valueSplitted.length == 3) {
                    String brand = valueSplitted[0];
                    String model = valueSplitted[1];
                    String size = valueSplitted[2];

                    outKey.set(brand);
                    outValue.set(model + "," + size);
                    context.write(outKey, outValue);
                }
            }
        }

        private static class Reducer extends org.apache.hadoop.mapreduce.Reducer<Text, Text, ImmutableBytesWritable, Writable> {

            /**
             * The reduce method fill the TestCars table with all csv data,
             * compute some counters and save those counters into the TestBrandsSizes table.
             * So we use two different HBase table as output for the reduce method.
             */
            @Override
            protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
                Map<String, Integer> statsSizeCounters = new HashMap<String, Integer>();
                String brand = key.toString();
                // We are receiving all models,size grouped by brand.
                for (Text value : values) {
                    String[] valueSplitted = value.toString().split(",");
                    if (valueSplitted.length == 2) {
                        String model = valueSplitted[0];
                        String size = valueSplitted[1];

                        // Fill the TestCars table
                        ImmutableBytesWritable putTable = new ImmutableBytesWritable(Bytes.toBytes("TestCars"));
                        byte[] putKey = Bytes.toBytes(brand + "," + model);
                        byte[] putFamily = Bytes.toBytes("Car");
                        Put put = new Put(putKey);
                        // qualifier brand
                        byte[] putQualifier = Bytes.toBytes("brand");
                        byte[] putValue = Bytes.toBytes(brand);
                        put.add(putFamily, putQualifier, putValue);
                        // qualifier model
                        putQualifier = Bytes.toBytes("model");
                        putValue = Bytes.toBytes(model);
                        put.add(putFamily, putQualifier, putValue);
                        // qualifier size
                        putQualifier = Bytes.toBytes("size");
                        putValue = Bytes.toBytes(size);
                        put.add(putFamily, putQualifier, putValue);
                        context.write(putTable, put);

                        // Compute some counters: number of different sizes for a brand
                        if (!statsSizeCounters.containsKey(size))
                            statsSizeCounters.put(size, 1);
                        else
                            statsSizeCounters.put(size, statsSizeCounters.get(size) + 1);
                    }
                }

                for (Entry<String, Integer> entry : statsSizeCounters.entrySet()) {
                    // Fill the TestBrandsSizes table
                    ImmutableBytesWritable putTable = new ImmutableBytesWritable(Bytes.toBytes("TestBrandsSizes"));
                    byte[] putKey = Bytes.toBytes(brand);
                    byte[] putFamily = Bytes.toBytes("BrandSizes");
                    Put put = new Put(putKey);
                    // We can use as qualifier the sizes
                    byte[] putQualifier = Bytes.toBytes(entry.getKey());
                    byte[] putValue = Bytes.toBytes(entry.getValue());
                    put.add(putFamily, putQualifier, putValue);
                    context.write(putTable, put);
                }
            }
        }
    }

使用 Eclipse 选项构建到 jar mt.jar :jar 文件

运行 mapreduce：

[zhouhh@Hadoop48 ~]$ HADOOP_CLASSPATH= ${HBASE_HOME}/bin/hbase classpath:${HADOOP_HOME}/bin/hadoop classpath ${HADOOP_HOME}/bin/hadoop jar mt.jar cars.csv 12/06/11 20:14:33 INFO test.TestMultiTable: wildnove.com - 教程 MultiTableOutputFormat 开始... 12/06/11 20:14:33 INFO test.TestMultiTable：计算文件：/user/zhouhh/cars.csv 12/06/11 20:14:34 INFO input.FileInputFormat：要处理的总输入路径：1 12/06/11 20:14:34 INFO util .NativeCodeLoader：加载了本机 Hadoop 库 12/06/11 20:14:34 WARN snappy.LoadSnappy：Snappy 本机库未加载 12/06/11 20:14:35 信息 mapred.JobClient：正在运行的作业：job_201206111811_0012 12/ 06/11 20:14:36 信息 mapred.JobClient：映射 0% 减少 0% 12/06/11 20:14:42 信息 mapred.JobClient：任务 ID：尝试_201206111811_0012_m_000002_0，状态：失败 java.lang.RuntimeException：java。 lang.ClassNotFoundException：org.apache.hadoop.hbase.mapreduce。org.apache.hadoop.mapreduce.JobContext.getOutputFormatClass(JobContext.java:235) 的 org.apache.hadoop.mapred.Task 的 org.apache.hadoop.conf.Configuration.getClass(Configuration.java:867) 的 MultiTableOutputFormat。在 org.apache.hadoop.mapred.Child$4.run(Child.java:255) 在 java 的 org.apache.hadoop.mapred.MapTask.run(MapTask.java:353) 初始化(Task.java:513)。 security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1121) at org.apache。 hadoop.mapred.Child.main(Child.java:249) 原因：java.lang.ClassNotFoundException: org.apache.hadoop.hbase.mapreduce.MultiTableOutputFormat at java.net.URLClassLoader$1。在 java.net.URLClassLoader.findClass(URLClassLoader.java:354) 在 java.security.AccessController.doPrivileged(Native Method) 在 java.net.URLClassLoader$1.run(URLClassLoader.java:355) 运行(URLClassLoader.java:366) ) 在 java.lang.ClassLoader.loadClass(ClassLoader.java:423) 在 sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308) 在 java.lang.ClassLoader.loadClass(ClassLoader.java:356) 在 java .lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:264) at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:820) at org.apache.hadoop .conf.Configuration.getClass(Configuration.java:865)doPrivileged(Native Method) at java.net.URLClassLoader.findClass(URLClassLoader.java:354) at java.lang.ClassLoader.loadClass(ClassLoader.java:423) at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java: 308) 在 java.lang.ClassLoader.loadClass(ClassLoader.java:356) 在 java.lang.Class.forName0(Native Method) 在 java.lang.Class.forName(Class.java:264) 在 org.apache.hadoop .conf.Configuration.getClassByName(Configuration.java:820) 在 org.apache.hadoop.conf.Configuration.getClass(Configuration.java:865)doPrivileged(Native Method) at java.net.URLClassLoader.findClass(URLClassLoader.java:354) at java.lang.ClassLoader.loadClass(ClassLoader.java:423) at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java: 308) 在 java.lang.ClassLoader.loadClass(ClassLoader.java:356) 在 java.lang.Class.forName0(Native Method) 在 java.lang.Class.forName(Class.java:264) 在 org.apache.hadoop .conf.Configuration.getClassByName(Configuration.java:820) 在 org.apache.hadoop.conf.Configuration.getClass(Configuration.java:865)loadClass(ClassLoader.java:356) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:264) at org.apache.hadoop.conf.Configuration.getClassByName(Configuration. java:820) 在 org.apache.hadoop.conf.Configuration.getClass(Configuration.java:865)loadClass(ClassLoader.java:356) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:264) at org.apache.hadoop.conf.Configuration.getClassByName(Configuration. java:820) 在 org.apache.hadoop.conf.Configuration.getClass(Configuration.java:865)

汽车.csv：

[zhouhh@Hadoop48 ~]$ cat cars.csv Acura,Integra,Small Acura,Legend,Midsize Audi,90,Compact Audi,100,Midsize BMW,535i,Midsize Buick,Century,Midsize Buick,LeSabre,Large Buick,Roadmaster,大别克,里维埃拉,中型凯迪拉克,德维尔,大凯迪拉克,塞维利亚,中型

MultiTableOutputFormat.class 在 Hbase.0.94.jar

[zhouhh@Hadoop48 ~]$ echo $HADOOP_CLASSPATH |tr ':' '\n' | grep hbase /home/zhouhh/hbase-0.94.0/conf /home/zhouhh/hbase-0.94.0 /home/zhouhh/hbase-0.94.0/hbase-0.94.0.jar /home/zhouhh/hbase-0.94 .0/hbase-0.94.0-tests.jar /home/zhouhh/hbase-0.94.0/lib/activation-1.1.jar /home/zhouhh/hbase-0.94.0/lib/asm-3.1.jar /home /zhouhh/hbase-0.94.0/lib/avro-1.5.3.jar /home/zhouhh/hbase-0.94.0/lib/avro-ipc-1.5.3.jar /home/zhouhh/hbase-0.94.0 /lib/commons-beanutils-1.7.0.jar /home/zhouhh/hbase-0.94.0/lib/commons-beanutils-core-1.8.0.jar /home/zhouhh/hbase-0.94.0/lib/commons -cli-1.2.jar /home/zhouhh/hbase-0.94.0/lib/commons-codec-1.4.jar /home/zhouhh/hbase-0.94.0/lib/commons-collections-3.2.1.jar /home /zhouhh/hbase-0.94.0/lib/commons-configuration-1.6.jar /home/zhouhh/hbase-0.94.0/lib/commons-digester-1.8.

我已经尝试了很多方法，但同样的错误仍然存​​在。

任何人都可以帮助我吗？谢谢

4

4 回答 4

4

您有两个简单的选择：

1）建立一个胖罐，你的mt.jar文件包括hbase-0.94.0.jar （可以用mvn package -Dfatjar）

2）使用GenericOptionsParser（我认为您正在尝试通过实现Tool），然后在命令行上指定 -libjars 参数。

于 2012-06-12T15:31:52.157 回答
2

我也遇到了同样的问题。我的这篇文章可以正常工作 - https://my-bigdata-blog.blogspot.in/2017/08/Hbase-Programming-Java-Netbeans-Maven.html 您需要下面的代码行以及设置 Hadoop_classpath。TableMapReduceUtil.addDependencyJars(job);

于 2017-08-14T14:27:52.073 回答
1 
 `hadoop classpath`

和

`hbase classpath`

会将集群类路径导出到 HADOOP_CLASSPATH。（是利用集群本地环境的标准方式）。

  • 在变量中捕获上面的内容，我们需要使用 Linux 命令进行格式化。-libjars如果没有找到您正在寻找的 jar，请将其添加到mapreduce 的选项中。
于 2015-11-13T12:41:06.787 回答
0

我正在使用以下脚本将作业的依赖项添加到 lib 文件夹中，并将 hbase 的依赖项添加到作业的类路径中：

cp=$(find `pwd` -name '*.jar' | tr '\n', ',')
cp=$cp$(hbase mapredcp 2>&1 | tail -1 | tr ':' ',')
export HADOOP_CLASSPATH=`echo ${cp} | sed s/,/:/g`
hadoop jar `pwd`/bin/mr.jar \
--libjars ${cp} \
$@
于 2015-07-16T14:31:31.970 回答