List of usage examples for org.apache.commons.configuration BaseConfiguration setDelimiterParsingDisabled
public void setDelimiterParsingDisabled(boolean delimiterParsingDisabled)
From source file:com.intel.cosbench.config.common.KVConfigParser.java
public static Config parse(String str) { BaseConfiguration config = new BaseConfiguration(); config.setDelimiterParsingDisabled(true); str = StringUtils.trimToEmpty(str);//from www.j a v a 2 s .c o m String[] entries = StringUtils.split(str, ';'); for (String entry : entries) { addConfigEntry(entry, config); } return new COSBConfigApator(config); }
From source file:org.apache.tinkerpop.gremlin.giraph.process.computer.GiraphGraphComputer.java
@Override public GraphComputer program(final VertexProgram vertexProgram) { super.program(vertexProgram); this.memory.addVertexProgramMemoryComputeKeys(this.vertexProgram); final BaseConfiguration apacheConfiguration = new BaseConfiguration(); apacheConfiguration.setDelimiterParsingDisabled(true); vertexProgram.storeState(apacheConfiguration); ConfUtil.mergeApacheIntoHadoopConfiguration(apacheConfiguration, this.giraphConfiguration); this.vertexProgram.getMessageCombiner().ifPresent( combiner -> this.giraphConfiguration.setMessageCombinerClass(GiraphMessageCombiner.class)); return this; }
From source file:org.apache.tinkerpop.gremlin.giraph.process.computer.GiraphGraphComputer.java
@Override public int run(final String[] args) { final Storage storage = FileSystemStorage.open(this.giraphConfiguration); storage.rm(this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION)); this.giraphConfiguration.setBoolean(Constants.GREMLIN_HADOOP_GRAPH_OUTPUT_FORMAT_HAS_EDGES, this.persist.equals(Persist.EDGES)); try {//ww w. ja va 2 s .co m // store vertex and edge filters (will propagate down to native InputFormat or else GiraphVertexInputFormat will process) final BaseConfiguration apacheConfiguration = new BaseConfiguration(); apacheConfiguration.setDelimiterParsingDisabled(true); GraphFilterAware.storeGraphFilter(apacheConfiguration, this.giraphConfiguration, this.graphFilter); // it is possible to run graph computer without a vertex program (and thus, only map reduce jobs if they exist) if (null != this.vertexProgram) { // a way to verify in Giraph whether the traversal will go over the wire or not try { VertexProgram.createVertexProgram(this.hadoopGraph, ConfUtil.makeApacheConfiguration(this.giraphConfiguration)); } catch (final IllegalStateException e) { if (e.getCause() instanceof NumberFormatException) throw new NotSerializableException( "The provided traversal is not serializable and thus, can not be distributed across the cluster"); } // remove historic combiners in configuration propagation (this occurs when job chaining) if (!this.vertexProgram.getMessageCombiner().isPresent()) this.giraphConfiguration.unset(GiraphConstants.MESSAGE_COMBINER_CLASS.getKey()); // split required workers across system (open map slots + max threads per machine = total amount of TinkerPop workers) if (!this.useWorkerThreadsInConfiguration) { final Cluster cluster = new Cluster(GiraphGraphComputer.this.giraphConfiguration); int totalMappers = cluster.getClusterStatus().getMapSlotCapacity() - 1; // 1 is needed for master cluster.close(); if (this.workers <= totalMappers) { this.giraphConfiguration.setWorkerConfiguration(this.workers, this.workers, 100.0F); this.giraphConfiguration.setNumComputeThreads(1); } else { if (totalMappers == 0) totalMappers = 1; // happens in local mode int threadsPerMapper = Long .valueOf(Math.round((double) this.workers / (double) totalMappers)).intValue(); // TODO: need to find least common denominator this.giraphConfiguration.setWorkerConfiguration(totalMappers, totalMappers, 100.0F); this.giraphConfiguration.setNumComputeThreads(threadsPerMapper); } } // prepare the giraph vertex-centric computing job final GiraphJob job = new GiraphJob(this.giraphConfiguration, Constants.GREMLIN_HADOOP_GIRAPH_JOB_PREFIX + this.vertexProgram); job.getInternalJob().setJarByClass(GiraphGraphComputer.class); this.logger.info(Constants.GREMLIN_HADOOP_GIRAPH_JOB_PREFIX + this.vertexProgram); // handle input paths (if any) String inputLocation = this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_INPUT_LOCATION, null); if (null != inputLocation && FileInputFormat.class.isAssignableFrom(this.giraphConfiguration .getClass(Constants.GREMLIN_HADOOP_GRAPH_INPUT_FORMAT, InputFormat.class))) { inputLocation = Constants.getSearchGraphLocation(inputLocation, storage) .orElse(this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_INPUT_LOCATION)); FileInputFormat.setInputPaths(job.getInternalJob(), new Path(inputLocation)); } // handle output paths (if any) String outputLocation = this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION, null); if (null != outputLocation && FileOutputFormat.class.isAssignableFrom(this.giraphConfiguration .getClass(Constants.GREMLIN_HADOOP_GRAPH_OUTPUT_FORMAT, OutputFormat.class))) { outputLocation = Constants.getGraphLocation( this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION)); FileOutputFormat.setOutputPath(job.getInternalJob(), new Path(outputLocation)); } // execute the job and wait until it completes (if it fails, throw an exception) if (!job.run(true)) throw new IllegalStateException( "The GiraphGraphComputer job failed -- aborting all subsequent MapReduce jobs: " + job.getInternalJob().getStatus().getFailureInfo()); // add vertex program memory values to the return memory for (final MemoryComputeKey memoryComputeKey : this.vertexProgram.getMemoryComputeKeys()) { if (!memoryComputeKey.isTransient() && storage.exists(Constants.getMemoryLocation( this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), memoryComputeKey.getKey()))) { final ObjectWritableIterator iterator = new ObjectWritableIterator(this.giraphConfiguration, new Path(Constants.getMemoryLocation( this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), memoryComputeKey.getKey()))); if (iterator.hasNext()) { this.memory.set(memoryComputeKey.getKey(), iterator.next().getValue()); } // vertex program memory items are not stored on disk storage.rm(Constants.getMemoryLocation( this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), memoryComputeKey.getKey())); } } final Path path = new Path(Constants.getMemoryLocation( this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), Constants.HIDDEN_ITERATION)); this.memory.setIteration( (Integer) new ObjectWritableIterator(this.giraphConfiguration, path).next().getValue()); storage.rm(Constants.getMemoryLocation( this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), Constants.HIDDEN_ITERATION)); } // do map reduce jobs this.giraphConfiguration.setBoolean(Constants.GREMLIN_HADOOP_GRAPH_INPUT_FORMAT_HAS_EDGES, this.giraphConfiguration.getBoolean(Constants.GREMLIN_HADOOP_GRAPH_OUTPUT_FORMAT_HAS_EDGES, true)); for (final MapReduce mapReduce : this.mapReducers) { this.memory.addMapReduceMemoryKey(mapReduce); MapReduceHelper.executeMapReduceJob(mapReduce, this.memory, this.giraphConfiguration); } // if no persistence, delete the graph and memory output if (this.persist.equals(Persist.NOTHING)) storage.rm(this.giraphConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION)); } catch (final Exception e) { throw new IllegalStateException(e.getMessage(), e); } return 0; }
From source file:org.apache.tinkerpop.gremlin.hadoop.process.computer.util.MapReduceHelper.java
public static void executeMapReduceJob(final MapReduce mapReduce, final Memory.Admin memory, final Configuration configuration) throws IOException, ClassNotFoundException, InterruptedException { final Configuration newConfiguration = new Configuration(configuration); final boolean vertexProgramExists = newConfiguration.get(VertexProgram.VERTEX_PROGRAM, null) != null; if (vertexProgramExists) { newConfiguration.set(Constants.GREMLIN_HADOOP_GRAPH_INPUT_FORMAT, InputOutputHelper//from w ww. j a v a2 s . co m .getInputFormat((Class) newConfiguration .getClass(Constants.GREMLIN_HADOOP_GRAPH_OUTPUT_FORMAT, OutputFormat.class)) .getCanonicalName()); newConfiguration.unset(Constants.GREMLIN_HADOOP_GRAPH_FILTER); } final BaseConfiguration apacheConfiguration = new BaseConfiguration(); apacheConfiguration.setDelimiterParsingDisabled(true); mapReduce.storeState(apacheConfiguration); ConfUtil.mergeApacheIntoHadoopConfiguration(apacheConfiguration, newConfiguration); final Optional<Comparator<?>> mapSort = mapReduce.getMapKeySort(); final Optional<Comparator<?>> reduceSort = mapReduce.getReduceKeySort(); newConfiguration.setClass(Constants.GREMLIN_HADOOP_MAP_REDUCE_CLASS, mapReduce.getClass(), MapReduce.class); final Job job = Job.getInstance(newConfiguration, mapReduce.toString()); HadoopGraph.LOGGER.info(Constants.GREMLIN_HADOOP_JOB_PREFIX + mapReduce.toString()); job.setJarByClass(HadoopGraph.class); if (mapSort.isPresent()) job.setSortComparatorClass(ObjectWritableComparator.ObjectWritableMapComparator.class); job.setMapperClass(HadoopMap.class); if (mapReduce.doStage(MapReduce.Stage.REDUCE)) { if (mapReduce.doStage(MapReduce.Stage.COMBINE)) job.setCombinerClass(HadoopCombine.class); job.setReducerClass(HadoopReduce.class); } else { if (mapSort.isPresent()) { job.setReducerClass(Reducer.class); job.setNumReduceTasks(1); // todo: is this necessary to ensure sorted order? } else { job.setNumReduceTasks(0); } } job.setMapOutputKeyClass(ObjectWritable.class); job.setMapOutputValueClass(ObjectWritable.class); job.setOutputKeyClass(ObjectWritable.class); job.setOutputValueClass(ObjectWritable.class); job.setInputFormatClass(GraphFilterInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); // if there is no vertex program, then grab the graph from the input location final Path graphPath; if (vertexProgramExists) { graphPath = new Path( Constants.getGraphLocation(newConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION))); } else { graphPath = new Path(newConfiguration.get(Constants.GREMLIN_HADOOP_INPUT_LOCATION)); } Path memoryPath = new Path( Constants.getMemoryLocation(newConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), (reduceSort.isPresent() ? mapReduce.getMemoryKey() + "-temp" : mapReduce.getMemoryKey()))); if (FileSystem.get(newConfiguration).exists(memoryPath)) { FileSystem.get(newConfiguration).delete(memoryPath, true); } FileInputFormat.setInputPaths(job, graphPath); FileOutputFormat.setOutputPath(job, memoryPath); job.waitForCompletion(true); // if there is a reduce sort, we need to run another identity MapReduce job if (reduceSort.isPresent()) { final Job reduceSortJob = Job.getInstance(newConfiguration, "ReduceKeySort"); reduceSortJob.setSortComparatorClass(ObjectWritableComparator.ObjectWritableReduceComparator.class); reduceSortJob.setMapperClass(Mapper.class); reduceSortJob.setReducerClass(Reducer.class); reduceSortJob.setMapOutputKeyClass(ObjectWritable.class); reduceSortJob.setMapOutputValueClass(ObjectWritable.class); reduceSortJob.setOutputKeyClass(ObjectWritable.class); reduceSortJob.setOutputValueClass(ObjectWritable.class); reduceSortJob.setInputFormatClass(SequenceFileInputFormat.class); reduceSortJob.setOutputFormatClass(SequenceFileOutputFormat.class); reduceSortJob.setNumReduceTasks(1); // todo: is this necessary to ensure sorted order? FileInputFormat.setInputPaths(reduceSortJob, memoryPath); final Path sortedMemoryPath = new Path(Constants.getMemoryLocation( newConfiguration.get(Constants.GREMLIN_HADOOP_OUTPUT_LOCATION), mapReduce.getMemoryKey())); FileOutputFormat.setOutputPath(reduceSortJob, sortedMemoryPath); reduceSortJob.waitForCompletion(true); FileSystem.get(newConfiguration).delete(memoryPath, true); // delete the temporary memory path memoryPath = sortedMemoryPath; } mapReduce.addResultToMemory(memory, new ObjectWritableIterator(newConfiguration, memoryPath)); }
From source file:org.apache.tinkerpop.gremlin.hadoop.structure.util.ConfUtil.java
public static org.apache.commons.configuration.Configuration makeApacheConfiguration( final Configuration hadoopConfiguration) { final BaseConfiguration apacheConfiguration = new BaseConfiguration(); apacheConfiguration.setDelimiterParsingDisabled(true); hadoopConfiguration.iterator()//from ww w. j a va 2 s .co m .forEachRemaining(e -> apacheConfiguration.setProperty(e.getKey(), e.getValue())); return apacheConfiguration; }
From source file:org.apache.tinkerpop.gremlin.spark.AbstractSparkTest.java
protected Configuration getBaseConfiguration() { final BaseConfiguration configuration = new BaseConfiguration(); configuration.setDelimiterParsingDisabled(true); configuration.setProperty("spark.master", "local[4]"); configuration.setProperty(Constants.SPARK_SERIALIZER, GryoSerializer.class.getCanonicalName()); configuration.setProperty("spark.kryo.registrationRequired", true); configuration.setProperty(Graph.GRAPH, HadoopGraph.class.getName()); configuration.setProperty(Constants.GREMLIN_HADOOP_JARS_IN_DISTRIBUTED_CACHE, false); return configuration; }
From source file:org.apache.tinkerpop.gremlin.spark.structure.io.gryo.GryoSerializer.java
private static Configuration makeApacheConfiguration(final SparkConf sparkConfiguration) { final BaseConfiguration apacheConfiguration = new BaseConfiguration(); apacheConfiguration.setDelimiterParsingDisabled(true); for (final Tuple2<String, String> tuple : sparkConfiguration.getAll()) { apacheConfiguration.setProperty(tuple._1(), tuple._2()); }/*from w w w . j ava2s . c om*/ return apacheConfiguration; }
From source file:org.apache.tinkerpop.gremlin.util.SystemUtil.java
/** * Generate a {@link Configuration} from the {@link System#getProperties}. * Only those properties with specified prefix key are aggregated. * If the prefix and a . should be removed, then trim prefix. * * @param prefix the prefix of the keys to include in the configuration * @param trimPrefix whether to trim the prefix + . from the key * @return a configuration generated from the System properties *//* w w w .j av a 2 s. co m*/ public static Configuration getSystemPropertiesConfiguration(final String prefix, final boolean trimPrefix) { final BaseConfiguration apacheConfiguration = new BaseConfiguration(); apacheConfiguration.setDelimiterParsingDisabled(true); for (final Map.Entry<Object, Object> entry : System.getProperties().entrySet()) { final String key = entry.getKey().toString(); final Object value = entry.getValue(); if (key.startsWith(prefix + ".")) apacheConfiguration.setProperty(trimPrefix ? key.substring(prefix.length() + 1) : key, value); } return apacheConfiguration; }
From source file:org.xwiki.configuration.internal.SystemEnvironmentConfigurationSource.java
@Override public void initialize() throws InitializationException { BaseConfiguration configuration = new BaseConfiguration(); configuration.setDelimiterParsingDisabled(true); Map<String, String> environment = System.getenv(); for (String key : environment.keySet()) { configuration.setProperty(key, environment.get(key)); }// ww w.ja v a 2s. co m setConfiguration(configuration); }
From source file:org.xwiki.configuration.internal.SystemPropertiesConfigurationSource.java
@Override public void initialize() throws InitializationException { BaseConfiguration configuration = new BaseConfiguration(); configuration.setDelimiterParsingDisabled(true); Properties properties = System.getProperties(); for (String key : properties.stringPropertyNames()) { configuration.setProperty(key, properties.get(key)); }/*from w w w .j a va2 s. co m*/ setConfiguration(configuration); }