把xls的数据导到Hbase

这属于Hbase的一个例子，不过Hbase的例子有点问题，需要更改下。
其实我感觉Hbase属于一个BigTable,感觉和xls真的很像，闲话不说了，上code才是王道。

Java代码  

1.   
2.   
3. import java.io.IOException;   
4.   
5. import org.apache.hadoop.conf.Configuration;   
6. import org.apache.hadoop.fs.Path;   
7. import org.apache.hadoop.hbase.HBaseConfiguration;   
8. import org.apache.hadoop.hbase.client.Put;   
9. import org.apache.hadoop.hbase.io.ImmutableBytesWritable;   
10. import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;   
11. import org.apache.hadoop.hbase.mapreduce.TableReducer;   
12. import org.apache.hadoop.hbase.util.Bytes;   
13. import org.apache.hadoop.io.LongWritable;   
14. import org.apache.hadoop.io.Text;   
15. import org.apache.hadoop.mapreduce.Job;   
16. import org.apache.hadoop.mapreduce.Mapper;   
17. import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;   
18. import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;   
19. import org.apache.hadoop.util.GenericOptionsParser;   
20. import org.apache.log4j.Logger;   
21.   
22. /**  
23.  * Sample Uploader MapReduce  
24.  * <p>  
25.  * This is EXAMPLE code.  You will need to change it to work for your context.  
26.  * <p>  
27.  * Uses {@link TableReducer} to put the data into HBase. Change the InputFormat  
28.  * to suit your data.  In this example, we are importing a CSV file.  
29.  * <p>  
30.  * <pre>row,family,qualifier,value</pre>  
31.  * <p>  
32.  * The table and columnfamily we're to insert into must preexist.  
33.  * <p>  
34.  * There is no reducer in this example as it is not necessary and adds  
35.  * significant overhead.  If you need to do any massaging of data before  
36.  * inserting into HBase, you can do this in the map as well.  
37.  * <p>Do the following to start the MR job:  
38.  * <pre>  
39.  * ./bin/hadoop org.apache.hadoop.hbase.mapreduce.SampleUploader /tmp/input.csv TABLE_NAME  
40.  * </pre>  
41.  * <p>  
42.  * This code was written against HBase 0.21 trunk.  
43.  */  
44. public class SampleUploader {   
45.   
46.     public static Logger loger = Wloger.loger;   
47.   
48.   private static final String NAME = "SampleUploader";   
49.   
50.   static class Uploader   
51.   extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {   
52.   
53.     private long checkpoint = 100;   
54.     private long count = 0;   
55.   
56.     @Override  
57.     public void map(LongWritable key, Text line, Context context)   
58.     throws IOException {   
59.   
60.       // Input is a CSV file   
61.       // Each map() is a single line, where the key is the line number   
62.       // Each line is comma-delimited; row,family,qualifier,value   
63.   
64.       // Split CSV line   
65.       String [] values = line.toString().split(",");   
66.       if(values.length != 4) {   
67.         return;   
68.       }   
69.   
70.       // Extract each value   
71.       byte [] row = Bytes.toBytes(values[0]);   
72.       byte [] family = Bytes.toBytes(values[1]);   
73.       byte [] qualifier = Bytes.toBytes(values[2]);   
74.       byte [] value = Bytes.toBytes(values[3]);   
75.       loger.info(values[0]+":"+values[1]+":"+values[2]+":"+values[3]);   
76.   
77.       // Create Put   
78.       Put put = new Put(row);   
79.       put.add(family, qualifier, value);   
80.   
81.       // Uncomment below to disable WAL. This will improve performance but means   
82.       // you will experience data loss in the case of a RegionServer crash.   
83.       // put.setWriteToWAL(false);   
84.   
85.       try {   
86.         context.write(new ImmutableBytesWritable(row), put);   
87.       } catch (InterruptedException e) {   
88.         e.printStackTrace();   
89.         loger.error("write到hbase 异常:",e);   
90.       }   
91.   
92.       // Set status every checkpoint lines   
93.       if(++count % checkpoint == 0) {   
94.         context.setStatus("Emitting Put " + count);   
95.       }   
96.     }   
97.   }   
98.   
99.   /**  
100.    * Job configuration.  
101.    */  
102.   public static Job configureJob(Configuration conf, String [] args)   
103.   throws IOException {   
104.     Path inputPath = new Path(args[0]);   
105.     String tableName = args[1];   
106.     Job job = new Job(conf, NAME + "_" + tableName);   
107.     job.setJarByClass(Uploader.class);   
108.     FileInputFormat.setInputPaths(job, inputPath);   
109.     job.setInputFormatClass(TextInputFormat.class);   
110.     job.setMapperClass(Uploader.class);   
111.     // No reducers.  Just write straight to table.  Call initTableReducerJob   
112.     // because it sets up the TableOutputFormat.   
113.     loger.error("TableName:"+tableName);   
114.     TableMapReduceUtil.initTableReducerJob(tableName, null, job);   
115.     job.setNumReduceTasks(0);   
116.     return job;   
117.   }   
118.   
119.   /**  
120.    * Main entry point.  
121.    *  
122.    * @param args  The command line parameters.  
123.    * @throws Exception When running the job fails.  
124.    */  
125.   public static void main(String[] args) throws Exception {   
126.     Configuration conf = HBaseConfiguration.create();   
127.     String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();   
128.     if(otherArgs.length != 2) {   
129.       System.err.println("Wrong number of arguments: " + otherArgs.length);   
130.       System.err.println("Usage: " + NAME + " <input> <tablename>");   
131.       System.exit(-1);   
132.     }   
133.     Job job = configureJob(conf, otherArgs);   
134.     System.exit(job.waitForCompletion(true) ? 0 : 1);   
135.   }   
136. }  

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.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
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.input.TextInputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.log4j.Logger;

/**
 * Sample Uploader MapReduce
 * <p>
 * This is EXAMPLE code.  You will need to change it to work for your context.
 * <p>
 * Uses {@link TableReducer} to put the data into HBase. Change the InputFormat
 * to suit your data.  In this example, we are importing a CSV file.
 * <p>
 * <pre>row,family,qualifier,value</pre>
 * <p>
 * The table and columnfamily we're to insert into must preexist.
 * <p>
 * There is no reducer in this example as it is not necessary and adds
 * significant overhead.  If you need to do any massaging of data before
 * inserting into HBase, you can do this in the map as well.
 * <p>Do the following to start the MR job:
 * <pre>
 * ./bin/hadoop org.apache.hadoop.hbase.mapreduce.SampleUploader /tmp/input.csv TABLE_NAME
 * </pre>
 * <p>
 * This code was written against HBase 0.21 trunk.
 */
public class SampleUploader {

	public static Logger loger = Wloger.loger;

  private static final String NAME = "SampleUploader";

  static class Uploader
  extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {

    private long checkpoint = 100;
    private long count = 0;

    @Override
    public void map(LongWritable key, Text line, Context context)
    throws IOException {

      // Input is a CSV file
      // Each map() is a single line, where the key is the line number
      // Each line is comma-delimited; row,family,qualifier,value

      // Split CSV line
      String [] values = line.toString().split(",");
      if(values.length != 4) {
        return;
      }

      // Extract each value
      byte [] row = Bytes.toBytes(values[0]);
      byte [] family = Bytes.toBytes(values[1]);
      byte [] qualifier = Bytes.toBytes(values[2]);
      byte [] value = Bytes.toBytes(values[3]);
      loger.info(values[0]+":"+values[1]+":"+values[2]+":"+values[3]);

      // Create Put
      Put put = new Put(row);
      put.add(family, qualifier, value);

      // Uncomment below to disable WAL. This will improve performance but means
      // you will experience data loss in the case of a RegionServer crash.
      // put.setWriteToWAL(false);

      try {
        context.write(new ImmutableBytesWritable(row), put);
      } catch (InterruptedException e) {
        e.printStackTrace();
        loger.error("write到hbase 异常:",e);
      }

      // Set status every checkpoint lines
      if(++count % checkpoint == 0) {
        context.setStatus("Emitting Put " + count);
      }
    }
  }

  /**
   * Job configuration.
   */
  public static Job configureJob(Configuration conf, String [] args)
  throws IOException {
    Path inputPath = new Path(args[0]);
    String tableName = args[1];
    Job job = new Job(conf, NAME + "_" + tableName);
    job.setJarByClass(Uploader.class);
    FileInputFormat.setInputPaths(job, inputPath);
    job.setInputFormatClass(TextInputFormat.class);
    job.setMapperClass(Uploader.class);
    // No reducers.  Just write straight to table.  Call initTableReducerJob
    // because it sets up the TableOutputFormat.
    loger.error("TableName:"+tableName);
    TableMapReduceUtil.initTableReducerJob(tableName, null, job);
    job.setNumReduceTasks(0);
    return job;
  }

  /**
   * Main entry point.
   *
   * @param args  The command line parameters.
   * @throws Exception When running the job fails.
   */
  public static void main(String[] args) throws Exception {
    Configuration conf = HBaseConfiguration.create();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if(otherArgs.length != 2) {
      System.err.println("Wrong number of arguments: " + otherArgs.length);
      System.err.println("Usage: " + NAME + " <input> <tablename>");
      System.exit(-1);
    }
    Job job = configureJob(conf, otherArgs);
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

Map/Reduce的输入/输出就不说了，不懂的，可以看hadoop专栏去.
[这个任务调用和上一个IndexBuilder有些不同哦，具体的可以参照上一个例子，相同点：都只有map任务]
xls内容如下:

Java代码  

1. key3,family1,column1,xls1   
2. key3,family1,column2,xls11   
3. key4,family1,column1,xls2   
4. key4,family1,column2,xls12  

key3,family1,column1,xls1
key3,family1,column2,xls11
key4,family1,column1,xls2
key4,family1,column2,xls12

这是csv格式的，如果是xls是可以导为csv格式的，具体可以google一下.
运行命令如下:

Java代码  

1. bin/hadoop jar SampleUploader.jar SampleUploader /tmp/input.csv 'table1'  

bin/hadoop jar SampleUploader.jar SampleUploader /tmp/input.csv 'table1'

这里的'table1'是上一遍IndexBuilder的时候建的表，表就使用上一张表[懒]
注意，这里使用的文件需要提交到hdfs上，否则会提示找不到，因为map/reduce是使用的是hdfs的文件系统.

 

http://www.iteye.com/topic/1117572