Implements a tool class that can export any number of columns of an hbase arbitrary table to any specified HDFs

 PackageHBase;Importjava.io.IOException;ImportJava.net.URI;Importorg.apache.hadoop.conf.Configuration;ImportOrg.apache.hadoop.fs.FileSystem;ImportOrg.apache.hadoop.fs.Path;ImportOrg.apache.hadoop.hbase.Cell;ImportOrg.apache.hadoop.hbase.CellUtil;Importorg.apache.hadoop.hbase.HBaseConfiguration;ImportOrg.apache.hadoop.hbase.client.Result;ImportOrg.apache.hadoop.hbase.client.Scan;Importorg.apache.hadoop.hbase.io.ImmutableBytesWritable;ImportOrg.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;ImportOrg.apache.hadoop.hbase.mapreduce.TableMapper;ImportOrg.apache.hadoop.io.Text;ImportOrg.apache.hadoop.mapreduce.Job;ImportOrg.apache.hadoop.mapreduce.Mapper;ImportOrg.apache.hadoop.mapreduce.lib.output.FileOutputFormat;ImportOrg.apache.hadoop.mapreduce.lib.output.TextOutputFormat; Public classHbase2hdfsutils {/*** Args[0] Table name * args[1] column family, column name list, format---column family: column * args[2] Output path *@paramargs *@throwsException*/     Public Static voidMain (string[] args)throwsException {//get configuration information for HBase and get configuration information from the Hbase-site.xml file in the resources directoryConfiguration conf =hbaseconfiguration.create (); //set column family, column name information list parameter, format--column family: columnConf.set ("Familycolumnslist", args[1]); //Declare a clientJob Job = job.getinstance (conf, hbase2hdfsutils.class. Getsimplename ()); //executing a JAR package requires specifying the class nameJob.setjarbyclass (hbase2hdfsutils.class); //Specifies the information that is required to export the table in HBase, which is the input to the mapScan Scan =NewScan (); Tablemapreduceutil.inittablemapperjob (args[0], scan, mymapper.class, Text.class, Text.class, Job); //Set input configuration information: Key, type of valueJob.setmapperclass (Mymapper.class); Job.setmapoutputkeyclass (Text.class); Job.setmapoutputvalueclass (Text.class); //reduce is not required to export data from hbase to HDFs, so the number of tasks to set reduce is 0Job.setnumreducetasks (0); //Set configuration information for output: Key, type of value, and output pathJob.setoutputkeyclass (Text.class); Job.setoutputvalueclass (Text.class); Job.setoutputformatclass (Textoutputformat.class); //if the output directory exists, delete the output directoryPath PATH =NewPath (args[2]); FileSystem FS= Filesystem.get (NewURI (args[2]),NewConfiguration ()); if(fs.exists (path)) {Fs.delete (path),true); } fileoutputformat.setoutputpath (Job,NewPath (args[2])); Job.waitforcompletion (true); }    Static classMymapperextendsTablemapper<text, text>{Text K2=NewText (); Text v2=NewText (); @Overrideprotected voidmap (immutablebyteswritable key, Result value, Mapper<immutablebyteswritable, Result, Text, text>. Context context)throwsIOException, interruptedexception {k2.set (""); String V2text= ""; String familycolumnslist= Context.getconfiguration (). Get ("Familycolumnslist"); String[] splited= Familycolumnslist.split (","); String title= "";//title             for(String split:splited) {string[] column= Split.split (":"); //get values based on column family, columnCell cell = Value.getcolumnlatestcell (Column[0].getbytes (), column[1].getbytes ()); //determines if the column gets the cell is not empty, otherwise it will report a null pointer error                if(cell!=NULL) {title+=NewString (Cellutil.clonequalifier (cell)) + ":" +NewString (Cellutil.clonequalifier (cell)) + "\ T" ; V2text+=NewString (Cellutil.clonevalue (cell)) + "\ T" ; }} v2.set (title+ "\ n" +v2text);        Context.write (K2, V2); }    }}

Implements a tool class that can export any number of columns of an hbase arbitrary table to any specified HDFs