需求：将HDFS上的文件中的数据导入到hbase中
实现上面的需求也有两种办法，一种是自定义mr，一种是使用hbase提供好的import工具
一、hdfs中的数据是这样的
每一行的数据是这样的id name age gender birthday
(my_python_env)[root@hadoop26 ~]# hadoop fs -cat /t1/*
1 zhangsan 10 male NULL
2 lisi NULL NULL NULL
3 wangwu NULL NULL NULL
4 zhaoliu NULL NULL 1993
二、自定义mr
public class HdfsToHBase {
public static void main(String[] args) throws Exception{
Configuration conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "hadoop26:2181");
conf.set("hbase.rootdir", "hdfs://hadoop26:9000/hbase");
conf.set(TableOutputFormat.OUTPUT_TABLE, args[1]);
Job job = Job.getInstance(conf, HdfsToHBase.class.getSimpleName());
TableMapReduceUtil.addDependencyJars(job);
job.setJarByClass(HdfsToHBase.class);
job.setMapperClass(HdfsToHBaseMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setReducerClass(HdfsToHBaseReducer.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
job.setOutputFormatClass(TableOutputFormat.class);
job.waitForCompletion(true);
}
public static class HdfsToHBaseMapper extends Mapper<LongWritable, Text, Text, Text>{
private Text outKey = new Text();
private Text outValue = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String[] splits = value.toString().split("\t");
outKey.set(splits[0]);
outValue.set(splits[1]+"\t"+splits[2]+"\t"+splits[3]+"\t"+splits[4]);
context.write(outKey, outValue);
}
}
public static class HdfsToHBaseReducer extends TableReducer<Text, Text, NullWritable>{
@Override
protected void reduce(Text k2, Iterable<Text> v2s, Context context) throws IOException, InterruptedException {
Put put = new Put(k2.getBytes());
for (Text v2 : v2s) {
String[] splis = v2.toString().split("\t");
if(splis[0]!=null && !"NULL".equals(splis[0])){
put.add("f1".getBytes(), "name".getBytes(),splis[0].getBytes());
}
if(splis[1]!=null && !"NULL".equals(splis[1])){
put.add("f1".getBytes(), "age".getBytes(),splis[1].getBytes());
}
if(splis[2]!=null && !"NULL".equals(splis[2])){
put.add("f1".getBytes(), "gender".getBytes(),splis[2].getBytes());
}
if(splis[3]!=null && !"NULL".equals(splis[3])){
put.add("f1".getBytes(), "birthday".getBytes(),splis[3].getBytes());
}
}
context.write(NullWritable.get(),put);
}
}
}
2.1打包运行
首先在hbase中创建一个表
hbase(main)::> create 'table1','f1'
row(s) in 0.4240 seconds => Hbase::Table - table1
然后运行
hadoop jar HdfsToHBase.jar com.lanyun.hadoop2.HdfsToHBase /t1/part* table1
最后查看table1中的数据
hbase(main)::* scan 'table1'
ROW COLUMN+CELL
column=f1:age, timestamp=, value=
column=f1:gender, timestamp=, value=male
column=f1:name, timestamp=, value=zhangsan
column=f1:name, timestamp=, value=lisi
column=f1:name, timestamp=, value=wangwu
column=f1:birthday, timestamp=, value=
column=f1:name, timestamp=, value=zhaoliu
row(s) in 0.0430 seconds
三、使用habse提供的import工具
首先查看其用法
(my_python_env)[root@hadoop26 ~]# hbase org.apache.hadoop.hbase.mapreduce.Import
ERROR: Wrong number of arguments:
Usage: Import [options] <tablename> <inputdir>
By default Import will load data directly into HBase. To instead generate
HFiles of data to prepare for a bulk data load, pass the option:
-Dimport.bulk.output=/path/for/output
在hbase中创建表table2
hbase(main)::> create 'table2','f1'
row(s) in 0.4080 seconds => Hbase::Table - table2
在命令中中使用命令进行导入
hbase org.apache.hadoop.hbase.mapreduce.Import table2 /t2
查看table2中的数据
hbase(main)::> scan 'table2'
ROW COLUMN+CELL
column=f1:age, timestamp=, value=
column=f1:gender, timestamp=, value=male
column=f1:name, timestamp=, value=zhangsan
column=f1:name, timestamp=, value=lisi
column=f1:name, timestamp=, value=wangwu
column=f1:birthday, timestamp=, value=
column=f1:name, timestamp=, value=zhaoliu
row(s) in 0.0440 seconds
四、注意
import工具很方便，但是只能导入Export导出的数据。