List of usage examples for org.apache.hadoop.conf Configuration addResource
public void addResource(Configuration conf)
From source file:gov.tva.sparky.util.indexer.IndexingAgent.java
public static void DebugSparkyConfig() { Configuration conf = new Configuration(false); conf.addResource("hadoop-default.xml"); conf.addResource("sparky-site.xml"); System.out.println("Debugging Sparky Configuration ------ "); System.out.println("> sparky.http.port: " + conf.get("sparky.http.port")); System.out.println("> fs.default.name: " + conf.get("fs.default.name")); }
From source file:gr.ntua.h2rdf.byteImport.HexastoreBulkImport.java
License:Open Source License
public Job createSubmittableJob(String[] args) { TABLE_NAME = args[1];/* w w w. j av a 2 s .co m*/ Job job = null; try { Configuration conf = new Configuration(); conf.addResource("hbase-default.xml"); conf.addResource("hbase-site.xml"); job = new Job(conf, NAME); job.setJarByClass(HexastoreBulkImport.class); job.setMapperClass(TotalOrderPrep.Map.class); job.setReducerClass(Reduce.class);//sampler.HamaReducer.class); job.setCombinerClass(Combiner.class); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(ImmutableBytesWritable.class); job.setPartitionerClass(TotalOrderPartitioner.class); //TotalOrderPartitioner.setPartitionFile(job.getConfiguration(), new Path("/user/npapa/"+regions+"partitions/part-r-00000")); TotalOrderPartitioner.setPartitionFile(job.getConfiguration(), new Path("partitions/part-r-00000")); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(HFileOutputFormat.class); Path out = new Path("out"); FileOutputFormat.setOutputPath(job, out); FileSystem fs; try { fs = FileSystem.get(conf); if (fs.exists(out)) { fs.delete(out, true); } } catch (IOException e) { e.printStackTrace(); } // c.addResource(new Path("/0/arcomemDB/hadoop-0.20.2-cdh3u3/conf/hbase-site.xml")); HBaseAdmin hadmin = new HBaseAdmin(conf); HTableDescriptor desc = new HTableDescriptor(TABLE_NAME + "_stats"); HColumnDescriptor family = new HColumnDescriptor("size"); desc.addFamily(family); conf.setInt("zookeeper.session.timeout", 600000); if (hadmin.tableExists(TABLE_NAME + "_stats")) { //hadmin.disableTable(TABLE_NAME+"_stats"); //hadmin.deleteTable(TABLE_NAME+"_stats"); } else { hadmin.createTable(desc); } FileInputFormat.setInputPaths(job, new Path(args[0])); //job.getConfiguration().setInt("mapred.map.tasks", 18); job.getConfiguration().set("h2rdf.tableName", TABLE_NAME); job.getConfiguration().setInt("mapred.reduce.tasks", (int) TotalOrderPrep.regions); job.getConfiguration().setBoolean("mapred.map.tasks.speculative.execution", false); job.getConfiguration().setBoolean("mapred.reduce.tasks.speculative.execution", false); job.getConfiguration().setInt("io.sort.mb", 100); job.getConfiguration().setInt("io.file.buffer.size", 131072); job.getConfiguration().setInt("mapred.job.reuse.jvm.num.tasks", -1); //job.getConfiguration().setInt("hbase.hregion.max.filesize", 67108864); job.getConfiguration().setInt("hbase.hregion.max.filesize", 33554432); //job.getConfiguration().setInt("io.sort.mb", 100); } catch (IOException e2) { e2.printStackTrace(); } return job; }
From source file:gr.ntua.h2rdf.loadTriples.TranslateAndImport.java
License:Apache License
private void loadHFiles() throws Exception { Configuration conf = HBaseConfiguration.create(); conf.addResource("hbase-default.xml"); conf.addResource("hbase-site.xml"); HBaseAdmin hadmin = new HBaseAdmin(conf); Path hfofDir = new Path("out/I"); FileSystem fs = hfofDir.getFileSystem(conf); //if (!fs.exists(hfofDir)) { // throw new FileNotFoundException("HFileOutputFormat dir " + // hfofDir + " not found"); //}/*from www . j a va2 s .c om*/ // FileStatus[] familyDirStatuses = fs.listStatus(hfofDir); //if (familyDirStatuses == null) { // throw new FileNotFoundException("No families found in " + hfofDir); //} int length = 0; byte[][] splits = new byte[18000][]; Path[] hfiles = FileUtil.stat2Paths(fs.listStatus(hfofDir)); for (Path hfile : hfiles) { if (hfile.getName().startsWith("_")) continue; HFile.Reader hfr = HFile.createReader(fs, hfile, new CacheConfig(conf)); //HFile.Reader hfr = new HFile.Reader(fs, hfile, null, false); final byte[] first; try { hfr.loadFileInfo(); first = hfr.getFirstRowKey(); } finally { hfr.close(); } //System.out.println("out/I/"+hfile.getName()+" \t "+Bytes.toStringBinary(first)); splits[length] = first.clone(); length++; } byte[][] splits1 = new byte[length][]; for (int i = 0; i < splits1.length; i++) { splits1[i] = splits[i]; } Arrays.sort(splits1, Bytes.BYTES_COMPARATOR); HTableDescriptor desc = new HTableDescriptor(TABLE_NAME); HColumnDescriptor family = new HColumnDescriptor("I"); family.setCompressionType(Algorithm.SNAPPY); desc.addFamily(family); family = new HColumnDescriptor("S"); family.setCompressionType(Algorithm.SNAPPY); desc.addFamily(family); family = new HColumnDescriptor("T"); family.setCompressionType(Algorithm.SNAPPY); desc.addFamily(family); //family= new HColumnDescriptor("C"); //desc.addFamily(family); //for (int i = 0; i < splits.length; i++) { // System.out.println(Bytes.toStringBinary(splits[i])); //} conf.setInt("zookeeper.session.timeout", 600000); if (hadmin.tableExists(TABLE_NAME)) { //hadmin.disableTable(TABLE_NAME); //hadmin.deleteTable(TABLE_NAME); } else { hadmin.createTable(desc, splits1); } //hadmin.createTable(desc); String[] args1 = new String[2]; args1[0] = "out"; args1[1] = TABLE_NAME; //args1[1]="new2"; ToolRunner.run(new LoadIncrementalHFiles(HBaseConfiguration.create()), args1); }
From source file:gws.WordCount.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); conf.addResource(new Path("/home/ucas/bigdata/hadoop-2.6.2/etc/hadoop/core-site.xml")); conf.addResource(new Path("/home/ucas/bigdata/hadoop-2.6.2/etc/hadoop/hdfs-site.xml")); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length < 2) { System.err.println("Usage: wordcount <in> [<in>...] <out>"); System.exit(2);/*from w w w . j ava 2 s . c o m*/ } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumCombiner.class); job.setReducerClass(IntSumReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // add the input paths as given by command line for (int i = 0; i < otherArgs.length - 1; ++i) { FileInputFormat.addInputPath(job, new Path(otherArgs[i])); } // add the output path as given by the command line FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:hadoopdemo.Hadoop.java
private void addFolderButtonActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_addFolderButtonActionPerformed try {/*from ww w.ja v a2s . c om*/ String newFolder = newFolderTextField.getText(); System.out.println(newFolder); Configuration conf = new Configuration(); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/core-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/hdfs-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/mapred-site.xml")); FileSystem fileSystem = FileSystem.get(conf); fileSystem.mkdirs(new Path(newFolder)); } catch (IOException ex) { Logger.getLogger(Hadoop.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:hadoopdemo.Hadoop.java
private void deleteFolderButtonActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_deleteFolderButtonActionPerformed try {//from w ww. ja v a 2 s .c o m String deleteFolder = deleteFolderTextField.getText(); System.out.println(deleteFolder); Configuration conf = new Configuration(); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/core-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/hdfs-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/mapred-site.xml")); FileSystem fileSystem = FileSystem.get(conf); fileSystem.delete(new Path(deleteFolder)); } catch (IOException ex) { Logger.getLogger(Hadoop.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:hadoopdemo.Hadoop.java
private void addFileButtonActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_addFileButtonActionPerformed try {// w w w.j ava2 s .c o m String addFile = addFileTextField.getText(); String hadoopPath = hadoopPathTextField.getText(); System.out.println(addFile); Configuration conf = new Configuration(); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/core-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/hdfs-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/mapred-site.xml")); FileSystem fileSystem = FileSystem.get(conf); fileSystem.copyFromLocalFile(new Path(addFile), new Path(hadoopPath)); } catch (IOException ex) { Logger.getLogger(Hadoop.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:hadoopdemo.Hadoop.java
private void renameButtonActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_renameButtonActionPerformed try {/*from w w w .j av a 2 s . c om*/ String oldName = oldNameTextField.getText(); String newName = newNameTextFIeld.getText(); Configuration conf = new Configuration(); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/core-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/hdfs-site.xml")); conf.addResource(new Path("/home/ado/hadoop-2.7.3/etc/hadoop/mapred-site.xml")); FileSystem fileSystem = FileSystem.get(conf); fileSystem.rename(new Path(oldName), new Path(newName)); } catch (IOException ex) { Logger.getLogger(Hadoop.class.getName()).log(Level.SEVERE, null, ex); } }
From source file:hitune.analysis.mapreduce.AnalysisConfiguration.java
License:Apache License
/** * Load the current configuration folder recursively * /*w ww .ja v a2 s . c o m*/ * if existing list.xml, go step forward * * @param folder */ public void LoadConfiguration(String folder, Configuration conf) { log.debug("scan folder: " + folder); File listfile = new File(folder + "/list.xml"); File conffile = new File(folder + "/conf.xml"); Configuration newconf = new Configuration(conf); newconf.addResource(new Path(conffile.getAbsolutePath())); try { if (listfile.exists()) { Configuration tempconf = new Configuration(newconf); tempconf.addResource(new Path(listfile.getAbsolutePath())); Configuration _conf = new Configuration(false); _conf.addResource(new Path(listfile.getAbsolutePath())); Iterator<Map.Entry<String, String>> iter = _conf.iterator(); while (iter.hasNext()) { Map.Entry<String, String> pairs = (Map.Entry<String, String>) iter.next(); String key = pairs.getKey(); LoadConfiguration(tempconf.get(key), newconf); } } else { String datasource = newconf.get(AnalysisProcessorConfiguration.datasource); log.debug("datasource: " + datasource); List<Configuration> cflist = null; if (conflist.containsKey(datasource)) { cflist = conflist.get(datasource); } else { cflist = new ArrayList<Configuration>(); } cflist.add(newconf); log.debug("add conf: " + newconf); conflist.put(datasource, cflist); } } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } }
From source file:hydrograph.engine.cascading.assembly.InputFileHiveParquetAssembly.java
License:Apache License
@Override protected void prepareScheme() { LOG.debug("Applying HiveParquetScheme to read data from Hive"); // HiveParquetTableDescriptor is developed specifically for handling // Parquet File format with Hive. Hence, the object of table descriptor // is created in its respective assembly and not in its base class. Configuration conf = new Configuration(); conf.addResource(new Path(HiveConfigurationMapping.getHiveConf("path_to_hive_site_xml"))); Factory factory = new Factory(conf); HiveTableDescriptor tb = factory.newInstance(inputFileHiveParquetEntity.getDatabaseName(), inputFileHiveParquetEntity.getTableName()); tableDesc = new HiveParquetTableDescriptor(tb.getDatabaseName(), tb.getTableName(), tb.getColumnNames(), tb.getColumnTypes(), tb.getPartitionKeys(), getHiveExternalTableLocationPath()); scheme = new HiveParquetScheme(tableDesc); scheme.setSourceFields(tableDesc.toFields()); scheme.setSinkFields(tableDesc.toFields()); }