List of usage examples for org.apache.hadoop.conf Configuration set
public void set(String name, String value)
value
of the name
property. From source file:com.cloudera.crunch.impl.mr.run.CrunchInputs.java
License:Apache License
public static void addInputPath(Job job, Path path, Class<? extends InputFormat> inputFormatClass, int nodeIndex) { Configuration conf = job.getConfiguration(); String inputs = JOINER.join(inputFormatClass.getName(), nodeIndex, path.toString()); String existing = conf.get(RuntimeParameters.MULTI_INPUTS); conf.set(RuntimeParameters.MULTI_INPUTS, existing == null ? inputs : existing + RECORD_SEP + inputs); }
From source file:com.cloudera.crunch.impl.mr.run.RTNodeSerializer.java
License:Open Source License
public void serialize(List<DoNode> nodes, Configuration conf, NodeContext context) throws IOException { List<RTNode> rtNodes = Lists.newArrayList(); for (DoNode node : nodes) { rtNodes.add(node.toRTNode(true, conf, context)); }//from ww w. j ava 2s . c om ByteArrayOutputStream baos = new ByteArrayOutputStream(); ObjectOutputStream oos = new ObjectOutputStream(baos); oos.writeObject(rtNodes); String serialized = Base64.encodeBase64String(baos.toByteArray()); conf.set(context.getConfigurationKey(), serialized); }
From source file:com.cloudera.crunch.io.avro.AvroFileSourceTarget.java
License:Open Source License
@Override public void configureSource(Job job, int inputId) throws IOException { SourceTargetHelper.configureSource(job, inputId, AvroInputFormat.class, path); Configuration conf = job.getConfiguration(); String inputSchema = conf.get("avro.input.schema"); if (inputSchema == null) { conf.set("avro.input.schema", ptype.getSchema().toString()); } else if (!inputSchema.equals(ptype.getSchema().toString())) { throw new IllegalStateException("Multiple Avro sources must use the same schema"); }/*from w w w.ja v a 2s.c o m*/ }
From source file:com.cloudera.crunch.io.avro.AvroFileTarget.java
License:Open Source License
@Override public void configureForMapReduce(Job job, PType<?> ptype, Path outputPath, String name) { AvroType<?> atype = (AvroType<?>) ptype; Configuration conf = job.getConfiguration(); String outputSchema = conf.get("avro.output.schema"); if (outputSchema == null) { conf.set("avro.output.schema", atype.getSchema().toString()); } else if (!outputSchema.equals(atype.getSchema().toString())) { throw new IllegalStateException("Avro targets must use the same output schema"); }/*from w w w . j a v a 2s . c o m*/ SourceTargetHelper.configureTarget(job, AvroOutputFormat.class, ptype.getDataBridge(), outputPath, name); }
From source file:com.cloudera.crunch.io.hbase.HBaseSourceTarget.java
License:Open Source License
@Override public void configureSource(Job job, int inputId) throws IOException { Configuration conf = job.getConfiguration(); job.setInputFormatClass(TableInputFormat.class); job.setMapperClass(CrunchMapper.class); HBaseConfiguration.addHbaseResources(conf); conf.set(TableInputFormat.INPUT_TABLE, table); conf.set(TableInputFormat.SCAN, convertScanToString(scan)); TableMapReduceUtil.addDependencyJars(job); }
From source file:com.cloudera.crunch.io.hbase.HBaseTarget.java
License:Open Source License
@Override public void configureForMapReduce(Job job, PType<?> ptype, Path outputPath, String name) { Configuration conf = job.getConfiguration(); HBaseConfiguration.addHbaseResources(conf); job.setOutputFormatClass(TableOutputFormat.class); conf.set(TableOutputFormat.OUTPUT_TABLE, table); try {/*from w ww. j av a 2s . c o m*/ TableMapReduceUtil.addDependencyJars(job); } catch (IOException e) { throw new CrunchRuntimeException(e); } }
From source file:com.cloudera.crunch.lib.Sort.java
License:Open Source License
private static GroupingOptions buildGroupingOptions(Configuration conf, PTypeFamily tf, PType ptype, Order order) {//from w w w.ja v a 2 s. c o m Builder builder = GroupingOptions.builder(); if (order == Order.DESCENDING) { if (tf == WritableTypeFamily.getInstance()) { builder.sortComparatorClass(ReverseWritableComparator.class); } else if (tf == AvroTypeFamily.getInstance()) { AvroType avroType = (AvroType) ptype; Schema schema = avroType.getSchema(); conf.set("crunch.schema", schema.toString()); builder.sortComparatorClass(ReverseAvroComparator.class); } else { throw new RuntimeException("Unrecognized type family: " + tf); } } return builder.build(); }
From source file:com.cloudera.crunch.WordCountHBaseTest.java
License:Open Source License
@Before public void setUp() throws Exception { Configuration conf = hbaseTestUtil.getConfiguration(); File tmpDir = File.createTempFile("logdir", ""); tmpDir.delete();/*ww w .ja v a 2 s . c o m*/ tmpDir.mkdir(); tmpDir.deleteOnExit(); conf.set("hadoop.log.dir", tmpDir.getAbsolutePath()); conf.set(HConstants.ZOOKEEPER_ZNODE_PARENT, "/1"); conf.setInt("hbase.master.info.port", -1); conf.setInt("hbase.regionserver.info.port", -1); hbaseTestUtil.startMiniZKCluster(); hbaseTestUtil.startMiniCluster(); hbaseTestUtil.startMiniMapReduceCluster(); }
From source file:com.cloudera.data.filesystem.TestFileSystemDatasetRepository.java
License:Apache License
@Before public void setUp() throws IOException { Configuration conf = new Configuration(); conf.set("fs.default.name", "file:///"); fileSystem = FileSystem.get(conf); testDirectory = new Path(Files.createTempDir().getAbsolutePath()); repo = new FileSystemDatasetRepository(fileSystem, testDirectory); testSchema = Schema.createRecord("Test", "Test record schema", "com.cloudera.data.filesystem", false); testSchema.setFields(Lists.newArrayList(new Field("name", Schema.create(Type.STRING), null, null))); }
From source file:com.cloudera.data.filesystem.TestFileSystemDatasetWriter.java
License:Apache License
@Before public void setUp() throws IOException { testDirectory = Files.createTempDir(); Configuration conf = new Configuration(); conf.set("fs.default.name", "file:///"); fileSystem = FileSystem.get(conf); }