import java.io.IOException;
import java.util.HashMap;
import java.util.Map;
import java.util.Set;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.MultiTableOutputFormat;
import org.apache.hadoop.hbase.mapreduce.TableInputFormat;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.GenericOptionsParser;
public class IndexBuilder {
private class MyMapper extends TableMapper
{
private Map indexes = new HashMap();
private String columnFamily;
@Override
protected void map(ImmutableBytesWritable key, Result value,
Context context) throws IOException, InterruptedException {
Set keys = indexes.keySet();
for (byte[] k : keys) {
ImmutableBytesWritable indexTableName = indexes.get(k);
byte[] val = value.getValue(Bytes.toBytes(columnFamily), k);
Put put = new Put(val);// 索引表的rowkey為原始表的值
put.add(Bytes.toBytes("f1"), Bytes.toBytes("id"), key.get());// 索引表的內(nèi)容為原始表的rowkey
context.write(indexTableName, put);
}
}
@Override
protected void setup(Context context) throws IOException,
InterruptedException {
Configuration conf = context.getConfiguration();
String tableName = conf.get("tableName");
columnFamily = conf.get("columnFamily");
String[] qualifiers = conf.getStrings("qualifiers");
// indexes的key為列名，value為索引表名
for (String q : qualifiers) {
indexes.put(
Bytes.toBytes(q),
new ImmutableBytesWritable(Bytes.toBytes(tableName
+ "-" + q)));
}
}
}
public static void main(String[] args) throws IOException,
ClassNotFoundException, InterruptedException {
Configuration conf = HBaseConfiguration.create();
String[] otherargs = new GenericOptionsParser(conf, args)
.getRemainingArgs();// 去除掉沒有用的命令行參數(shù)
// 輸入?yún)?shù)：表名，列族名，列名
if (otherargs.length < 3) {
System.exit(-1);
}
String tableName = otherargs[0];
String columnFamily = otherargs[1];
conf.set("tableName", tableName);
conf.set("columnFamily", columnFamily);
String[] qualifiers = new String[otherargs.length - 2];
for (int i = 0; i < qualifiers.length; i++) {
qualifiers[i] = otherargs[i + 2];
}
conf.setStrings("qualifiers", qualifiers);
Job job = new Job(conf, tableName);
job.setJarByClass(IndexBuilder.class);
job.setMapperClass(MyMapper.class);
job.setNumReduceTasks(0);
job.setInputFormatClass(TableInputFormat.class);
// 可以輸出多張表
job.setOutputFormatClass(MultiTableOutputFormat.class);
Scan scan = new Scan();
scan.setCaching(1000);
TableMapReduceUtil.initTableMapperJob(tableName, scan, MyMapper.class,
ImmutableBytesWritable.class, Put.class, job);
job.waitForCompletion(true);
}
}
創(chuàng)新互聯(lián)-專業(yè)網(wǎng)站定制、快速模板網(wǎng)站建設(shè)、高性價比大同網(wǎng)站開發(fā)、企業(yè)建站全套包干低至880元,成熟完善的模板庫,直接使用。一站式大同網(wǎng)站制作公司更省心,省錢,快速模板網(wǎng)站建設(shè)找我們，業(yè)務(wù)覆蓋大同地區(qū)。費用合理售后完善，10多年實體公司更值得信賴。另外有需要云服務(wù)器可以了解下創(chuàng)新互聯(lián)cdcxhl.cn，海內(nèi)外云服務(wù)器15元起步，三天無理由+7*72小時售后在線，公司持有idc許可證，提供“云服務(wù)器、裸金屬服務(wù)器、高防服務(wù)器、香港服務(wù)器、美國服務(wù)器、虛擬主機、免備案服務(wù)器”等云主機租用服務(wù)以及企業(yè)上云的綜合解決方案，具有“安全穩(wěn)定、簡單易用、服務(wù)可用性高、性價比高”等特點與優(yōu)勢，專為企業(yè)上云打造定制，能夠滿足用戶豐富、多元化的應(yīng)用場景需求。
網(wǎng)頁名稱：Mapreduce構(gòu)建hbase二級索引-創(chuàng)新互聯(lián)
標(biāo)題鏈接：http://weahome.cn/article/pisjs.html
重慶分公司
重慶分公司
