這篇文章主要介紹“HBase And MapReduce舉例分析”，在日常操作中，相信很多人在HBase And MapReduce舉例分析問題上存在疑惑，小編查閱了各式資料，整理出簡單好用的操作方法，希望對大家解答”HBase And MapReduce舉例分析”的疑惑有所幫助！接下來，請跟著小編一起來學(xué)習(xí)吧！
成都創(chuàng)新互聯(lián)公司是一家專業(yè)提供?？谄髽I(yè)網(wǎng)站建設(shè),專注與成都網(wǎng)站設(shè)計、成都網(wǎng)站制作、外貿(mào)網(wǎng)站建設(shè)、H5建站、小程序制作等業(yè)務(wù)。10年已為海口眾多企業(yè)、政府機構(gòu)等服務(wù)。創(chuàng)新互聯(lián)專業(yè)網(wǎng)站制作公司優(yōu)惠進(jìn)行中。
在HDFS某目錄文件下有多個文件內(nèi)容，將這些多個文件內(nèi)容中的數(shù)據(jù)通過倒排索引后將結(jié)果寫入到HBase某張表中，代碼如下：
1.InvertedIndexMapper
public class InvertedIndexMapper extends Mapper{
private Text keyInfo = new Text(); // 存儲單詞和URI的組合
private Text valueInfo = new Text(); //存儲詞頻
private FileSplit split; // 存儲split對象。
@Override
protected void map(Object key, Text value, Mapper.Context context)
throws IOException, InterruptedException {
System.out.println( "key-->: " +key + "\n value --> : "+value );
//獲得對所屬的FileSplit對象。
split = (FileSplit) context.getInputSplit();
System.out.println( "split---> "+split.toString() );
//System.out.println("value.tostring()---> "+ value.toString() );
StringTokenizer itr = new StringTokenizer( value.toString());
while( itr.hasMoreTokens() ){
// key值由單詞和URI組成。
keyInfo.set( itr.nextToken()+":"+split.getPath().toString());
//System.out.println("split.getPath().toString() --> "+ split.getPath().toString() );
//詞頻初始為1
valueInfo.set("1");
context.write(keyInfo, valueInfo);
}
}
}
2.InvertedIndexCombiner
public class InvertedIndexCombiner extends Reducer{
private Text info = new Text();
@Override
protected void reduce(Text key, Iterable values, Reducer.Context context)
throws IOException, InterruptedException {
//統(tǒng)計詞頻
int sum = 0;
for (Text value : values) {
sum += Integer.parseInt(value.toString() );
}
int splitIndex = key.toString().indexOf(":");
//重新設(shè)置value值由URI和詞頻組成
info.set( key.toString().substring( splitIndex + 1) +":"+sum );
//重新設(shè)置key值為單詞
key.set( key.toString().substring(0,splitIndex));
context.write(key, info);
}
}
3.InvertedIndexReducer
public class InvertedIndexReducer extends Reducer{
private Text result = new Text();
@Override
protected void reduce(Text key, Iterable values, Reducer.Context context)
throws IOException, InterruptedException {
//生成文檔列表
String fileList = new String();
for (Text value : values) {
fileList += value.toString()+";";
}
result.set(fileList);
context.write(key, result);
}
}
4.HBaseAndInvertedIndex
public class HBaseAndInvertedIndex {
private static Path outPath;
public static void main(String[] args) throws Exception {
run();
System.out.println( "\n\n************************");
runHBase();
}
public static void run() throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf,"Hadoop-InvertedIndex");
job.setJarByClass(HBaseAndInvertedIndex.class);
//實現(xiàn)map函數(shù)，根據(jù)輸入的對生成中間結(jié)果。
job.setMapperClass(InvertedIndexMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setCombinerClass(InvertedIndexCombiner.class);
job.setReducerClass(InvertedIndexReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path("hdfs://192.168.226.129:9000/txt/invertedindex/"));
DateFormat df = new SimpleDateFormat( "yyyyMMddHHmmssS" );
String filename = df.format( new Date() );
outPath = new Path("hdfs://192.168.226.129:9000/rootdir/invertedindexhbase/result/"+filename+"/");
FileOutputFormat.setOutputPath(job, outPath);
int result = job.waitForCompletion(true) ? 0 : 1;
}
public static void runHBase() throws Exception {
Configuration conf = new Configuration();
conf = HBaseConfiguration.create(conf);
conf.set("hbase.zookeeper.quorum", "192.168.226.129");
Job job = Job.getInstance(conf, "HBase-InvertedIndex");
job.setJarByClass(HBaseAndInvertedIndex.class);
job.setInputFormatClass(KeyValueTextInputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// 把數(shù)據(jù)寫入Hbase數(shù)據(jù)庫
FileInputFormat.addInputPath(job, new Path(outPath.toString()+"/part-r-00000") );
System.out.println( "path---> "+ outPath.toString() );
TableMapReduceUtil.initTableReducerJob("invertedindex",InvertedIndexHBaseReducer.class, job);
//將數(shù)據(jù)寫入HBase數(shù)據(jù)庫
//首先先檢查表是否存在
checkTable(conf);
System.exit( job.waitForCompletion(true) ? 0 : 1 );
}
private static void checkTable(Configuration conf) throws Exception {
Connection con = ConnectionFactory.createConnection(conf);
Admin admin = con.getAdmin();
TableName tn = TableName.valueOf("invertedindex");
if (!admin.tableExists(tn)){
HTableDescriptor htd = new HTableDescriptor(tn);
HColumnDescriptor hcd = new HColumnDescriptor("indexKey");
htd.addFamily(hcd);
admin.createTable(htd);
System.out.println("表不存在，新創(chuàng)建表成功....");
}
}
/**
* 1. 因為map是從hdfs中取數(shù)據(jù)，因此沒有太大變化；而reduce需要輸出結(jié)果到hbase中，
* 所以這里繼承了TableReduce，這里沒有valueout，
* 但是規(guī)定TableReduce的valueout必須是Put或者Delete實例
*
* 2.ImmutableBytesWritable:它是一個可以用作key或value類型的字節(jié)序列，
* */
public static class InvertedIndexHBaseReducer extends TableReducer {
@Override
protected void reduce(
Text key,
Iterable values,
Reducer.Context context)
throws IOException, InterruptedException {
System.out.println( "key---> " + key.toString() );
//注意行健參數(shù)的書寫。
Put put = new Put(key.toString().getBytes());
put.addColumn(Bytes.toBytes( "indexKey" ), Bytes.toBytes("indexUrlWeight"),values.iterator().next().getBytes());
context.write(new ImmutableBytesWritable(key.getBytes()), put);
}
}
}///原數(shù)據(jù)目錄文件：
invertedindex1.txt
Hello I will Learning Hadoop
HDFS MapReduce
Other I will Learning HBase
invertedindex2.txt ：
Hello HBase
MapReduce HDFS
查看結(jié)果：scan：
hbase(main):002:0> scan 'invertedindex'
ROW COLUMN+CELL
HBase column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex2.txt:1;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex1.txt:1;
HDFS column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:1;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
Hadoop column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:1;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
Hello column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:1;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
I column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:2;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
Learning column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:2;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
MapReduce column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:1;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
Other column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:1;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
will column=indexKey:indexUrlWeight, timestamp=1463578091308, value=hdfs://192.168.226.129:900
0/txt/invertedindex/invertedindex1.txt:2;hdfs://192.168.226.129:9000/txt/invertedindex/in
vertedindex2.txt:1;
9 row(s) in 0.2240 seconds
到此，關(guān)于“HBase And MapReduce舉例分析”的學(xué)習(xí)就結(jié)束了，希望能夠解決大家的疑惑。理論與實踐的搭配能更好的幫助大家學(xué)習(xí)，快去試試吧！若想繼續(xù)學(xué)習(xí)更多相關(guān)知識，請繼續(xù)關(guān)注創(chuàng)新互聯(lián)網(wǎng)站，小編會繼續(xù)努力為大家?guī)砀鄬嵱玫奈恼拢?/p>
當(dāng)前名稱：HBaseAndMapReduce舉例分析
文章鏈接：http://weahome.cn/article/pcdijh.html
重慶分公司
重慶分公司
