List of usage examples for org.apache.hadoop.mapreduce JobContext getConfiguration
public Configuration getConfiguration();
From source file:ml.shifu.shifu.guagua.ShifuInputFormat.java
License:Apache License
public static Path[] getInputPaths(JobContext context) { String dirs = context.getConfiguration().get(CommonConstants.CROSS_VALIDATION_DIR, ""); LOG.info("crossValidation_dir:" + dirs); String[] list = StringUtils.split(dirs); Path[] result = new Path[list.length]; for (int i = 0; i < list.length; i++) { result[i] = new Path(StringUtils.unEscapeString(list[i])); }/*from w ww. j a va 2 s . c om*/ return result; }
From source file:mvm.rya.accumulo.mr.RyaOutputFormat.java
License:Apache License
@Override public void checkOutputSpecs(JobContext jobContext) throws IOException, InterruptedException { Configuration conf = jobContext.getConfiguration(); // make sure that all of the indexers can connect getGeoIndexer(conf);//from ww w . j a v a 2 s . c o m getFreeTextIndexer(conf); getTemporalIndexer(conf); getRyaIndexer(conf); }
From source file:mvm.rya.accumulo.mr.utils.AccumuloHDFSFileInputFormat.java
License:Apache License
@Override public List<InputSplit> getSplits(JobContext jobContext) throws IOException { //read the params from AccumuloInputFormat Configuration conf = jobContext.getConfiguration(); Instance instance = AccumuloProps.getInstance(jobContext); String user = AccumuloProps.getUsername(jobContext); AuthenticationToken password = AccumuloProps.getPassword(jobContext); String table = AccumuloProps.getTablename(jobContext); ArgumentChecker.notNull(instance);/* w w w . j a va2 s . co m*/ ArgumentChecker.notNull(table); //find the files necessary try { AccumuloConfiguration acconf = instance.getConfiguration(); FileSystem fs = FileSystem.get(conf); Connector connector = instance.getConnector(user, password); TableOperations tos = connector.tableOperations(); String tableId = tos.tableIdMap().get(table); String filePrefix = acconf.get(Property.INSTANCE_DFS_DIR) + "/tables/" + tableId; System.out.println(filePrefix); Scanner scanner = connector.createScanner("!METADATA", Constants.NO_AUTHS); //TODO: auths? scanner.setRange(new Range(new Text(tableId + "\u0000"), new Text(tableId + "\uFFFD"))); scanner.fetchColumnFamily(new Text("file")); List<String> files = new ArrayList<String>(); List<InputSplit> fileSplits = new ArrayList<InputSplit>(); Job job = new Job(conf); for (Map.Entry<Key, Value> entry : scanner) { String file = filePrefix + entry.getKey().getColumnQualifier().toString(); files.add(file); Path path = new Path(file); FileStatus fileStatus = fs.getFileStatus(path); long len = fileStatus.getLen(); BlockLocation[] fileBlockLocations = fs.getFileBlockLocations(fileStatus, 0, len); fileSplits.add(new FileSplit(path, 0, len, fileBlockLocations[0].getHosts())); // FileInputFormat.addInputPath(job, path); } System.out.println(files); return fileSplits; // return super.getSplits(job); } catch (Exception e) { throw new IOException(e); } }
From source file:mvm.rya.indexing.accumulo.ConfigUtils.java
License:Apache License
public static String getUsername(JobContext job) { return getUsername(job.getConfiguration()); }
From source file:mvm.rya.indexing.accumulo.ConfigUtils.java
License:Apache License
public static Authorizations getAuthorizations(JobContext job) { return getAuthorizations(job.getConfiguration()); }
From source file:mvm.rya.indexing.accumulo.ConfigUtils.java
License:Apache License
public static Instance getInstance(JobContext job) { return getInstance(job.getConfiguration()); }
From source file:mvm.rya.indexing.accumulo.ConfigUtils.java
License:Apache License
public static String getPassword(JobContext job) { return getPassword(job.getConfiguration()); }
From source file:mvm.rya.indexing.accumulo.ConfigUtils.java
License:Apache License
public static Connector getConnector(JobContext job) throws AccumuloException, AccumuloSecurityException { return getConnector(job.getConfiguration()); }
From source file:net.jarcec.sqoop.data.gen.mr.GeneratorInputFormat.java
License:Apache License
@Override public List<InputSplit> getSplits(JobContext jobContext) throws IOException, InterruptedException { Configuration configuration = jobContext.getConfiguration(); long files = configuration.getLong(Constants.FILES_COUNT, 0); long records = configuration.getLong(Constants.RECORD_COUNT, 0); List<InputSplit> splits = new LinkedList<InputSplit>(); long next = 1; for (int i = 0; i < files; i++) { splits.add(new GeneratorSplit(next, next + records)); next += records;//w w w. j a va2 s .c om } return splits; }
From source file:net.mooncloud.mapreduce.lib.db.DBInputFormat.java
License:Apache License
/** {@inheritDoc} */ public List<InputSplit> getSplits(JobContext job) throws IOException { ResultSet results = null;/*from w ww . j a v a 2 s. c o m*/ Statement statement = null; try { statement = connection.createStatement(); results = statement.executeQuery(getCountQuery()); results.next(); long count = results.getLong(1); int chunks = job.getConfiguration().getInt("mapred.map.tasks", 1); long chunkSize = (count / chunks); results.close(); statement.close(); List<InputSplit> splits = new ArrayList<InputSplit>(); // Split the rows into n-number of chunks and adjust the last chunk // accordingly for (int i = 0; i < chunks; i++) { DBInputSplit split; if ((i + 1) == chunks) split = new DBInputSplit(i * chunkSize, count); else split = new DBInputSplit(i * chunkSize, (i * chunkSize) + chunkSize); splits.add(split); } connection.commit(); return splits; } catch (SQLException e) { throw new IOException("Got SQLException", e); } finally { try { if (results != null) { results.close(); } } catch (SQLException e1) { } try { if (statement != null) { statement.close(); } } catch (SQLException e1) { } closeConnection(); } }