Tez示例（WordCount）

这份代码是修改了Tez的示例得到的（已运行通过）。运行前需要在F盘建立“Input”文件夹，并把待统计的文件放入其中，具体可参看代码。结果也是输出在F盘的Output文件中。Windows平台下会报“TaskExit: error (1639): Invalid command line argument. Consult the Windows Installer SDK for detailed command line help.”错误，这是由于win平台本省的原因，并不会影响输出的结果。

package sqllab.tez.shiyan;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.security.UserGroupInformation;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.tez.client.TezClient;
import org.apache.tez.dag.api.DAG;
import org.apache.tez.dag.api.DataSinkDescriptor;
import org.apache.tez.dag.api.DataSourceDescriptor;
import org.apache.tez.dag.api.Edge;
import org.apache.tez.dag.api.ProcessorDescriptor;
import org.apache.tez.dag.api.TezConfiguration;
import org.apache.tez.dag.api.Vertex;
import org.apache.tez.dag.api.client.DAGClient;
import org.apache.tez.dag.api.client.DAGStatus;
import org.apache.tez.mapreduce.input.MRInput;
import org.apache.tez.mapreduce.output.MROutput;
import org.apache.tez.mapreduce.processor.SimpleMRProcessor;
import org.apache.tez.runtime.api.ProcessorContext;
import org.apache.tez.runtime.library.api.KeyValueReader;
import org.apache.tez.runtime.library.api.KeyValueWriter;
import org.apache.tez.runtime.library.api.KeyValuesReader;
import org.apache.tez.runtime.library.api.TezRuntimeConfiguration;
import org.apache.tez.runtime.library.conf.OrderedPartitionedKVEdgeConfig;

import com.google.common.base.Preconditions;

import org.apache.tez.runtime.library.partitioner.HashPartitioner;
import org.apache.tez.runtime.library.processor.SimpleProcessor;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;


public class WCount extends Configured implements Tool {
  static String INPUT = "Input";
  static String OUTPUT = "Output";
  static String TOKENIZER = "Tokenizer";
  static String SUMMATION = "Summation";
  private static final Logger LOG = LoggerFactory.getLogger(WCount.class);
  
  /*
   * Processors typi