Hbase结合MapReduce的批量导入
对以下手机流量信息进行模拟导入，放置到HDFS文件系统input文件夹下
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200
1363157985079 13823070001 20-7C-8F-70-68-1F:CMCC 120.196.100.99 6 3 360 180 200
1363157985069 13600217502 00-1F-64-E2-E8-B1:CMCC 120.196.100.55 18 138 1080 186852 200
package Hbase;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
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.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Counter;
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;
public class BatchImport {
static class BatchImportMapper extends Mapper<LongWritable, Text, LongWritable, Text>{
SimpleDateFormat dateformat1=new SimpleDateFormat("yyyyMMddHHmmss");
Text v2 = new Text();
protected void map(LongWritable key, Text value, Context context) throws java.io.IOException ,InterruptedException {
final String[] splited = value.toString().split("\t");
try {
final Date date = new Date(Long.parseLong(splited[0].trim()));
final String dateFormat = dateformat1.format(date);
String rowKey = splited[1]+":"+dateFormat;
v2.set(rowKey+"\t"+value.toString());
context.write(key, v2);
} catch (NumberFormatException e) {
final Counter counter = context.getCounter("BatchImport", "ErrorFormat");
counter.increment(1L);
System.out.println("出错了"+splited[0]+" "+e.getMessage());
}
};
}
static class BatchImportReducer extends TableReducer<LongWritable, Text, NullWritable>{
protected void reduce(LongWritable key, java.lang.Iterable<Text> values, Context context) throws java.io.IOException ,InterruptedException {
for (Text text : values) {
final String[] splited = text.toString().split("\t");
final Put put = new Put(Bytes.toBytes(splited[0]));
put.add(Bytes.toBytes("cf"), Bytes.toBytes("date"), Bytes.toBytes(splited[1]));
put.add(Bytes.toBytes("cf"), Bytes.toBytes("msisdn"), Bytes.toBytes(splited[2]));
put.add(Bytes.toBytes("cf"),Bytes.toBytes("apmac"), Bytes.toBytes(splited[3]));
//省略其他字段，调用put.add(....)即可
context.write(NullWritable.get(), put);
}
};
}
public static void main(String[] args) throws Exception {
final Configuration configuration = new Configuration();
//设置zookeeper
configuration.set("hbase.zookeeper.quorum", "hadoop");
//设置hbase表名称
configuration.set(TableOutputFormat.OUTPUT_TABLE, "wlan_log");
//将该值改大，防止hbase超时退出
configuration.set("dfs.socket.timeout", "180000");
final Job job = new Job(configuration, "HBaseBatchImport");
job.setMapperClass(BatchImportMapper.class);
job.setReducerClass(BatchImportReducer.class);
//设置map的输出，不设置reduce的输出类型
job.setMapOutputKeyClass(LongWritable.class);
job.setMapOutputValueClass(Text.class);
job.setInputFormatClass(TextInputFormat.class);
//不再设置输出路径，而是设置输出格式类型
job.setOutputFormatClass(TableOutputFormat.class);
FileInputFormat.setInputPaths(job, "hdfs://hadoop:9000/input");
job.waitForCompletion(true);
}
}
先后启动Hadoop-->zookeeper-->habase如下
创建与之对应的表结构
RowKey设计：msisdn:日期时间串（yyyyMMddHHmmss）
执行java程序后
查询手机13450456688的所有上网记录
public static void scan(String tableName)throws IOException{
HTable table = new HTable(getConfiguration(),tableName);
Scan scan = new Scan();
scan.setStartRow(Bytes.toBytes("13450456688:/"));
scan.setStopRow(Bytes.toBytes("13450456688::"));
ResultScanner scanner =table.getScanner(scan);
int i=0;
for (Result result : scanner) {
System.out.println("Scan:"+i+++" "+result);
}
}
查询134号段的所有上网记录
public static void scanPeriod(String tableName) throws IOException{
HTable table = new HTable(getConfiguration(),tableName);
Scan scan = new Scan();
scan.setStartRow(Bytes.toBytes("134/"));
scan.setStopRow(
Bytes.toBytes("134:"));
scan.setMaxVersions(1);
ResultScanner scanner =table.getScanner(scan);
int i=0;
for (Result result : scanner) {
System.out.println("Scan:"+i+++" "+result);
}
}