MapReduce file and HBase co-enter the package Duogemap; 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.result;import Org.apache.hadoop.hbase.client.scan;import Org.apache.hadoop.hbase.io.immutablebyteswritable;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.io.text;import Org.apache.hadoop.mapreduce.job;import Org.apache.hadoop.mapreduce.Mapper; Import Org.apache.hadoop.mapreduce.reducer;import Org.apache.hadoop.mapreduce.lib.input.multipleinputs;import Org.apache.hadoop.mapreduce.lib.input.textinputformat;import Org.apache.hadoop.mapreduce.lib.output.fileoutputformat;import Org.apache.hadoop.mapreduce.lib.output.textoutputformat; public class Mixmr { pUblic static class Map extends Mapper<object, text, text, text> { public void map (Object key, text value, Conte XT context) throws IOException, interruptedexception {String s = value.tostring (); string[] sa = S.split (","), if (sa.length = = 2) {context.write (new text (Sa[0]), new text (sa[1]));} } } public Static class Tablemap extends Tablemapper<text, text> {public static final byte[] CF = "C F ". GetBytes ();p ublic static final byte[] ATTR1 =" C1 ". GetBytes (); public void Map (immutablebyteswritable row, Result value, Context context) throws IOException, interruptedexception { string key = Bytes.tostring (Row.get ()); String val = new String (Value.getvalue (CF, ATTR1)); context.write (new Text (key), new text (val));}} public static class reduce extends Reducer <object, Text, object, text> {public void reduce (object key, Iterable<text> values, Context context) throws IOException, interruptedexception {String KS = key.tostring (); for (Text val:values) {context.write (new text (KS), Val);} }} public static void Main (string[] args) throws Exception {path inputPath1 = new Path (args[0]); Path inputPath2 = new Path (args[1]); Path OutputPath = new Path (args[2]), string tableName = "Test"; configuration config = Hbaseconfiguration.create (); Job Job = new Job (config, "Exampleread"); Job.setjarbyclass (Mixmr.class); Class that contains mapper scan scan = new scan (); scan.setcaching (500); 1 is the default in Scan, which would be a bad for MapReduce jobsscan.setcacheblocks (false); Don ' t set to True for MR jobsscan.addfamily (bytes.tobytes ("CF")); tablemapreduceutil.inittablemapperjob ( TableName,//input HBase table Namescan,//Scan instance to control CF and attribute Selectiontablemap.class,//Mappert Ext.class,//Mapper output Keytext.class,//Mapper output Valuejob); job.setreducerclass (Reduce.class); Reducer Classjob.setoutputformatclass (Textoutputformat.class); //inPutPath1 here have no effect for HBase tablemultipleinputs.addinputpath (Job, InputPath1, Textinputformat.class, Map.class ); Multipleinputs.addinputpath (Job, InputPath2, Tableinputformat.class, Tablemap.class); Fileoutputformat.setoutputpath (Job, OutputPath); job.waitforcompletion (True);}}
MapReduce file and hbase co-input
