Example usage for org.apache.hadoop.fs FileSystem getFileStatus

List of usage examples for org.apache.hadoop.fs FileSystem getFileStatus

Introduction

In this page you can find the example usage for org.apache.hadoop.fs FileSystem getFileStatus.

Prototype

public abstract FileStatus getFileStatus(Path f) throws IOException;

Source Link

Document

Return a file status object that represents the path.

Usage

From source file:gov.jgi.meta.MetaUtils.java

License:Open Source License

/**
 * reads a fasta file and returns a map with id and sequence contents
 * @param contigFileName the file or file path of the fasta file
 * @return map containing sequences keyed by sequence id
 * @throws IOException if file exists/*ww  w  .  ja  v a2  s  .  c  o  m*/
 */
public static Map<String, String> readSequences(String contigFileName) throws IOException {
    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(conf);
    Path filenamePath = new Path(contigFileName);

    Map<String, String> results = new HashMap<String, String>();

    if (!fs.exists(filenamePath)) {
        throw new IOException("file not found: " + contigFileName);
    }

    for (Path f : findAllPaths(filenamePath)) {
        FSDataInputStream in = fs.open(f);
        FastaBlockLineReader fblr = new FastaBlockLineReader(in);

        Text key = new Text();
        long length = fs.getFileStatus(f).getLen();
        HashMap<String, String> tmpcontigs = new HashMap<String, String>();
        fblr.readLine(key, tmpcontigs, Integer.MAX_VALUE, (int) length);
        results.putAll(tmpcontigs);
        in.close();
        fblr.close();
    }

    return (results);
}

From source file:gov.tva.sparky.hdfs.HistorianArchiveFile.java

/**
 * The constructor for HistorianArchiveFile.
 * /*from   ww w . j  a va  2 s .  c o  m*/
 * @param fs A reference to the FileSystem.
 * @param file_path The path of the file to open.
 * @param conf A hadoop configuration object.
 * @throws IOException
 */
public HistorianArchiveFile(FileSystem fs, Path file_path, Configuration conf) throws IOException {

    this.iPossiblePointsInBlock = 0;
    this.iCurrentBlockPointIndex = 0;
    this.iCurrentBlockIndex = 0;
    this.iPassCounter = 0;
    this.lTotalDatAwareFileLength = 0;
    this.fs = fs;
    this.bufferSize = conf.getInt("io.file.buffer.size", 4096);

    this.file = file_path;

    this.in = openFile(fs, this.file, bufferSize);

    this.conf = conf;

    FileStatus fileStatus = fs.getFileStatus(file);
    this.lTotalDatAwareFileLength = fileStatus.getLen();

    this.ReadFAT();

    this.seek(0);
}

From source file:gr.ntua.h2rdf.LoadTriples.DistinctIds.java

License:Open Source License

public Job createSubmittableJob(String[] args) throws IOException, ClassNotFoundException {
    //io.compression.codecs
    Job job = new Job();

    job.setInputFormatClass(TextInputFormat.class);
    Configuration conf = new Configuration();
    Path blockProjection = new Path("blockIds/");
    Path translations = new Path("translations/");
    Path sample = new Path("sample/");
    Path temp = new Path("temp/");
    Path uniqueIds = new Path("uniqueIds/");
    FileSystem fs;
    try {//  w w  w.  j  a  v a  2s .c  o  m
        fs = FileSystem.get(conf);
        if (fs.exists(uniqueIds)) {
            fs.delete(uniqueIds, true);
        }
        if (fs.exists(translations)) {
            fs.delete(translations, true);
        }
        if (fs.exists(blockProjection)) {
            fs.delete(blockProjection, true);
        }
        if (fs.exists(sample)) {
            fs.delete(sample, true);
        }
        if (fs.exists(temp)) {
            fs.delete(temp, true);
        }

        FileOutputFormat.setOutputPath(job, uniqueIds);
        Path inp = new Path(args[0]);
        FileInputFormat.setInputPaths(job, inp);

        double type = 1;
        double datasetSize = 0;
        if (fs.isFile(inp)) {
            datasetSize = fs.getFileStatus(inp).getLen();
        } else if (fs.isDirectory(inp)) {
            FileStatus[] s = fs.listStatus(inp);
            for (int i = 0; i < s.length; i++) {
                if (s[i].getPath().getName().toString().endsWith(".gz"))
                    type = 27;
                if (s[i].getPath().getName().toString().endsWith(".snappy"))
                    type = 10;
                datasetSize += s[i].getLen();
            }
        } else {
            FileStatus[] s = fs.globStatus(inp);
            for (int i = 0; i < s.length; i++) {
                if (s[i].getPath().getName().toString().endsWith(".gz"))
                    type = 27;
                if (s[i].getPath().getName().toString().endsWith(".snappy"))
                    type = 10;
                datasetSize += s[i].getLen();
            }
        }
        datasetSize = datasetSize * type;
        System.out.println("type: " + type);
        System.out.println("datasetSize: " + datasetSize);
        samplingRate = (double) sampleChunk / (double) datasetSize;
        if (samplingRate >= 0.1) {
            samplingRate = 0.1;
        }
        if (samplingRate <= 0.001) {
            samplingRate = 0.001;
        }
        numReducers = (int) (datasetSize / ReducerChunk);
        if (numReducers == 0)
            numReducers = 1;
        numReducers++;
    } catch (IOException e) {
        e.printStackTrace();
    }

    HBaseAdmin hadmin = new HBaseAdmin(conf);
    HTableDescriptor desc = new HTableDescriptor(TABLE_NAME);

    HColumnDescriptor family = new HColumnDescriptor("counter");
    desc.addFamily(family);
    if (!hadmin.tableExists(TABLE_NAME)) {
        hadmin.createTable(desc);
    }

    job.setNumReduceTasks(numReducers);
    job.setMapOutputKeyClass(ImmutableBytesWritable.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(ImmutableBytesWritable.class);
    job.setOutputValueClass(ImmutableBytesWritable.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setJarByClass(DistinctIds.class);
    job.setMapperClass(Map.class);
    job.setReducerClass(Reduce.class);

    job.setPartitionerClass(SamplingPartitioner.class);

    FileOutputFormat.setCompressOutput(job, true);
    FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
    job.getConfiguration().set("mapred.compress.map.output", "true");
    job.getConfiguration().set("mapred.map.output.compression.codec",
            "org.apache.hadoop.io.compress.SnappyCodec");

    //job.setCombinerClass(Combiner.class);
    job.setJobName("Distinct Id Wordcount");
    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);

    return job;

}

From source file:guipart.view.GUIOverviewController.java

@FXML
void handleClassifyRF(ActionEvent event) throws IOException {

    String outputFile = "data/out";

    Path dataPath = new Path(textFieldCSVRF.getText()); // test data path
    Path datasetPath = new Path(textFieldDatasetRF.getText()); //info file about data set
    Path modelPath = new Path(textFieldModelRF.getText()); // path where the forest is stored
    Path outputPath = new Path(outputFile); // path to predictions file, if null do not output the predictions

    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(conf);

    FileSystem outFS = FileSystem.get(conf);

    System.out.println("Loading the forest");
    DecisionForest forest = DecisionForest.load(conf, modelPath);

    if (forest == null)
        System.err.println("No decision forest found!");

    // load the dataset
    Dataset dataset = Dataset.load(conf, datasetPath);
    DataConverter converter = new DataConverter(dataset);

    System.out.println("Sequential classification");
    long time = System.currentTimeMillis();

    Random rng = RandomUtils.getRandom();

    List<double[]> resList = Lists.newArrayList();
    if (fs.getFileStatus(dataPath).isDir()) {
        //the input is a directory of files
        Utils.rfTestDirectory(outputPath, converter, forest, dataset, resList, rng, fs, dataPath, outFS,
                guiPart);/*  ww  w  .  ja v  a 2 s .  c  o m*/
    } else {
        // the input is one single file
        Utils.rfTestFile(dataPath, outputPath, converter, forest, dataset, resList, rng, outFS, fs, guiPart);
    }

    time = System.currentTimeMillis() - time;
    //log.info("Classification Time: {}", DFUtils.elapsedTime(time));
    System.out.println("Classification time: " + DFUtils.elapsedTime(time));

    if (dataset.isNumerical(dataset.getLabelId())) {

        RegressionResultAnalyzer regressionAnalyzer = new RegressionResultAnalyzer();
        double[][] results = new double[resList.size()][2];
        regressionAnalyzer.setInstances(resList.toArray(results));
        //log.info("{}", regressionAnalyzer);
        System.out.println(regressionAnalyzer.toString());

    } else {
        ResultAnalyzer analyzer = new ResultAnalyzer(Arrays.asList(dataset.labels()), "unknown");
        for (double[] r : resList) {
            analyzer.addInstance(dataset.getLabelString(r[0]),
                    new ClassifierResult(dataset.getLabelString(r[1]), 1.0));
        }
        //log.info("{}", analyzer);
        System.out.println(analyzer.toString());
        textAnalyze.setText(analyzer.toString());
    }

}

From source file:hadoop.example.hdfs.CoherencyTestCase.java

License:Open Source License

@Test
public void test() throws IOException {
    String uri = "hdfs://exoplatform:9000/user/haint/temp.file";
    Path path = new Path(uri);
    FileSystem fs = FileSystem.get(URI.create(uri), new Configuration());
    try {//from  ww w. j av a2s . com
        FSDataOutputStream output = fs.create(path);
        assertTrue(fs.exists(path));

        //
        output.write("content".getBytes());
        output.flush();
        assertEquals(fs.getFileStatus(path).getLen(), 0L);

        output.sync();
        assertEquals(fs.getFileStatus(path).getLen(), 0L);

        output.close();
        assertEquals(fs.getFileStatus(path).getLen(), "content".length());
    } finally {
        fs.delete(path, false);
    }
}

From source file:hadoop.yarn.distributedshell.DshellClient.java

License:Apache License

/**
 * Main run function for the client/*from   w  w w .  j a  va  2s .c  o m*/
 * 
 * @return true if application completed successfully
 * @throws IOException
 * @throws YarnException
 */
public boolean run() throws IOException, YarnException {

    LOG.info("Running Client");
    yarnClient.start();

    YarnClusterMetrics clusterMetrics = yarnClient.getYarnClusterMetrics();
    LOG.info("Got Cluster metric info from ASM" + ", numNodeManagers=" + clusterMetrics.getNumNodeManagers());

    List<NodeReport> clusterNodeReports = yarnClient.getNodeReports(NodeState.RUNNING);
    LOG.info("Got Cluster node info from ASM");
    for (NodeReport node : clusterNodeReports) {
        LOG.info("Got node report from ASM for" + ", nodeId=" + node.getNodeId() + ", nodeAddress"
                + node.getHttpAddress() + ", nodeRackName" + node.getRackName() + ", nodeNumContainers"
                + node.getNumContainers());
    }

    QueueInfo queueInfo = yarnClient.getQueueInfo(this.amQueue);
    LOG.info("Queue info" + ", queueName=" + queueInfo.getQueueName() + ", queueCurrentCapacity="
            + queueInfo.getCurrentCapacity() + ", queueMaxCapacity=" + queueInfo.getMaximumCapacity()
            + ", queueApplicationCount=" + queueInfo.getApplications().size() + ", queueChildQueueCount="
            + queueInfo.getChildQueues().size());

    List<QueueUserACLInfo> listAclInfo = yarnClient.getQueueAclsInfo();
    for (QueueUserACLInfo aclInfo : listAclInfo) {
        for (QueueACL userAcl : aclInfo.getUserAcls()) {
            LOG.info("User ACL Info for Queue" + ", queueName=" + aclInfo.getQueueName() + ", userAcl="
                    + userAcl.name());
        }
    }

    // Get a new application id
    YarnClientApplication app = yarnClient.createApplication();
    GetNewApplicationResponse appResponse = app.getNewApplicationResponse();
    // TODO get min/max resource capabilities from RM and change memory ask
    // if needed
    // If we do not have min/max, we may not be able to correctly request
    // the required resources from the RM for the app master
    // Memory ask has to be a multiple of min and less than max.
    // Dump out information about cluster capability as seen by the resource
    // manager
    int maxMem = appResponse.getMaximumResourceCapability().getMemory();
    LOG.info("Max mem capabililty of resources in this cluster " + maxMem);

    // A resource ask cannot exceed the max.
    if (amMemory > maxMem) {
        LOG.info("AM memory specified above max threshold of cluster. Using max value." + ", specified="
                + amMemory + ", max=" + maxMem);
        amMemory = maxMem;
    }

    int maxVCores = appResponse.getMaximumResourceCapability().getVirtualCores();
    LOG.info("Max virtual cores capabililty of resources in this cluster " + maxVCores);

    if (amVCores > maxVCores) {
        LOG.info("AM virtual cores specified above max threshold of cluster. " + "Using max value."
                + ", specified=" + amVCores + ", max=" + maxVCores);
        amVCores = maxVCores;
    }

    // set the application name
    ApplicationSubmissionContext appContext = app.getApplicationSubmissionContext();
    ApplicationId appId = appContext.getApplicationId();

    appContext.setKeepContainersAcrossApplicationAttempts(keepContainers);
    appContext.setApplicationName(appName);

    // Set up the container launch context for the application master
    ContainerLaunchContext amContainer = Records.newRecord(ContainerLaunchContext.class);

    // set local resources for the application master
    // local files or archives as needed
    // In this scenario, the jar file for the application master is part of
    // the local resources
    Map<String, LocalResource> localResources = new HashMap<String, LocalResource>();

    LOG.info("Copy App Master jar from local filesystem and add to local environment");
    // Copy the application master jar to the filesystem
    // Create a local resource to point to the destination jar path
    FileSystem fs = FileSystem.get(conf);
    addToLocalResources(fs, appMasterJar, appMasterJarPath, appId.toString(), localResources, null);

    // Set the log4j properties if needed
    if (!log4jPropFile.isEmpty()) {
        addToLocalResources(fs, log4jPropFile, log4jPath, appId.toString(), localResources, null);
    }

    // The shell script has to be made available on the final container(s)
    // where it will be executed.
    // To do this, we need to first copy into the filesystem that is visible
    // to the yarn framework.
    // We do not need to set this as a local resource for the application
    // master as the application master does not need it.
    String hdfsShellScriptLocation = "";
    long hdfsShellScriptLen = 0;
    long hdfsShellScriptTimestamp = 0;
    if (!shellScriptPath.isEmpty()) {
        Path shellSrc = new Path(shellScriptPath);
        String shellPathSuffix = appName + "/" + appId.toString() + "/" + SCRIPT_PATH;
        Path shellDst = new Path(fs.getHomeDirectory(), shellPathSuffix);
        fs.copyFromLocalFile(false, true, shellSrc, shellDst);
        hdfsShellScriptLocation = shellDst.toUri().toString();
        FileStatus shellFileStatus = fs.getFileStatus(shellDst);
        hdfsShellScriptLen = shellFileStatus.getLen();
        hdfsShellScriptTimestamp = shellFileStatus.getModificationTime();
    }

    if (!shellCommand.isEmpty()) {
        addToLocalResources(fs, null, shellCommandPath, appId.toString(), localResources, shellCommand);
    }

    if (shellArgs.length > 0) {
        addToLocalResources(fs, null, shellArgsPath, appId.toString(), localResources,
                StringUtils.join(shellArgs, " "));
    }
    // Set local resource info into app master container launch context
    amContainer.setLocalResources(localResources);

    // Set the necessary security tokens as needed
    // amContainer.setContainerTokens(containerToken);

    // Set the env variables to be setup in the env where the application
    // master will be run
    LOG.info("Set the environment for the application master");
    Map<String, String> env = new HashMap<String, String>();

    // put location of shell script into env
    // using the env info, the application master will create the correct
    // local resource for the
    // eventual containers that will be launched to execute the shell
    // scripts
    env.put(DshellDSConstants.DISTRIBUTEDSHELLSCRIPTLOCATION, hdfsShellScriptLocation);
    env.put(DshellDSConstants.DISTRIBUTEDSHELLSCRIPTTIMESTAMP, Long.toString(hdfsShellScriptTimestamp));
    env.put(DshellDSConstants.DISTRIBUTEDSHELLSCRIPTLEN, Long.toString(hdfsShellScriptLen));

    // ========================================jar?
    if (containerJarPaths.length != 0) {
        for (int i = 0; i < containerJarPaths.length; i++) {
            String hdfsJarLocation = "";
            String[] jarNameSplit = containerJarPaths[i].split("/");
            String jarName = jarNameSplit[jarNameSplit.length - 1];

            long hdfsJarLen = 0;
            long hdfsJarTimestamp = 0;
            if (!containerJarPaths[i].isEmpty()) {
                Path jarSrc = new Path(containerJarPaths[i]);
                String jarPathSuffix = appName + "/" + appId.toString() + "/" + jarName;
                Path jarDst = new Path(fs.getHomeDirectory(), jarPathSuffix);
                fs.copyFromLocalFile(false, true, jarSrc, jarDst);
                hdfsJarLocation = jarDst.toUri().toString();
                FileStatus jarFileStatus = fs.getFileStatus(jarDst);
                hdfsJarLen = jarFileStatus.getLen();
                hdfsJarTimestamp = jarFileStatus.getModificationTime();
                env.put(DshellDSConstants.DISTRIBUTEDJARLOCATION + i, hdfsJarLocation);
                env.put(DshellDSConstants.DISTRIBUTEDJARTIMESTAMP + i, Long.toString(hdfsJarTimestamp));
                env.put(DshellDSConstants.DISTRIBUTEDJARLEN + i, Long.toString(hdfsJarLen));
            }
        }
    }
    // ========================================jar?

    // ========================================archive?
    if (containerArchivePaths.length != 0) {
        for (int i = 0; i < containerArchivePaths.length; i++) {
            String hdfsArchiveLocation = "";
            String[] archiveNameSplit = containerArchivePaths[i].split("/");
            String archiveName = archiveNameSplit[archiveNameSplit.length - 1];

            long hdfsArchiveLen = 0;
            long hdfsArchiveTimestamp = 0;
            if (!containerArchivePaths[i].isEmpty()) {
                Path archiveSrc = new Path(containerArchivePaths[i]);
                String archivePathSuffix = appName + "/" + appId.toString() + "/" + archiveName;
                Path archiveDst = new Path(fs.getHomeDirectory(), archivePathSuffix);
                fs.copyFromLocalFile(false, true, archiveSrc, archiveDst);
                hdfsArchiveLocation = archiveDst.toUri().toString();
                FileStatus archiveFileStatus = fs.getFileStatus(archiveDst);
                hdfsArchiveLen = archiveFileStatus.getLen();
                hdfsArchiveTimestamp = archiveFileStatus.getModificationTime();
                env.put(DshellDSConstants.DISTRIBUTEDARCHIVELOCATION + i, hdfsArchiveLocation);
                env.put(DshellDSConstants.DISTRIBUTEDARCHIVETIMESTAMP + i, Long.toString(hdfsArchiveTimestamp));
                env.put(DshellDSConstants.DISTRIBUTEDARCHIVELEN + i, Long.toString(hdfsArchiveLen));
            }
        }
    }
    // ========================================archive?

    // Add AppMaster.jar location to classpath
    // At some point we should not be required to add
    // the hadoop specific classpaths to the env.
    // It should be provided out of the box.
    // For now setting all required classpaths including
    // the classpath to "." for the application jar
    StringBuilder classPathEnv = new StringBuilder(Environment.CLASSPATH.$$())
            .append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./*");
    for (String c : conf.getStrings(YarnConfiguration.YARN_APPLICATION_CLASSPATH,
            YarnConfiguration.DEFAULT_YARN_CROSS_PLATFORM_APPLICATION_CLASSPATH)) {
        classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR);
        classPathEnv.append(c.trim());
    }
    classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./log4j.properties");

    // add the runtime classpath needed for tests to work
    if (conf.getBoolean(YarnConfiguration.IS_MINI_YARN_CLUSTER, false)) {
        classPathEnv.append(':');
        classPathEnv.append(System.getProperty("java.class.path"));
    }

    env.put("CLASSPATH", classPathEnv.toString());

    amContainer.setEnvironment(env);

    // Set the necessary command to execute the application master
    Vector<CharSequence> vargs = new Vector<CharSequence>(30);

    // Set java executable command
    LOG.info("Setting up app master command");
    vargs.add(Environment.JAVA_HOME.$$() + "/bin/java");
    // Set Xmx based on am memory size
    vargs.add("-Xmx" + amMemory + "m");
    // Set class name
    vargs.add(appMasterMainClass);
    // Set params for Application Master
    vargs.add("--container_memory " + String.valueOf(containerMemory));
    vargs.add("--container_vcores " + String.valueOf(containerVirtualCores));
    vargs.add("--num_containers " + String.valueOf(numContainers));
    vargs.add("--priority " + String.valueOf(shellCmdPriority));

    for (Map.Entry<String, String> entry : shellEnv.entrySet()) {
        vargs.add("--shell_env " + entry.getKey() + "=" + entry.getValue());
    }
    if (debugFlag) {
        vargs.add("--debug");
    }

    vargs.add("1>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stdout");
    vargs.add("2>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stderr");

    // Get final commmand
    StringBuilder command = new StringBuilder();
    for (CharSequence str : vargs) {
        command.append(str).append(" ");
    }

    LOG.info("Completed setting up app master command " + command.toString());
    List<String> commands = new ArrayList<String>();
    commands.add(command.toString());
    amContainer.setCommands(commands);

    // Set up resource type requirements
    // For now, both memory and vcores are supported, so we set memory and
    // vcores requirements
    Resource capability = Records.newRecord(Resource.class);
    capability.setMemory(amMemory);
    capability.setVirtualCores(amVCores);
    appContext.setResource(capability);

    // Service data is a binary blob that can be passed to the application
    // Not needed in this scenario
    // amContainer.setServiceData(serviceData);

    // Setup security tokens
    if (UserGroupInformation.isSecurityEnabled()) {
        Credentials credentials = new Credentials();
        String tokenRenewer = conf.get(YarnConfiguration.RM_PRINCIPAL);
        if (tokenRenewer == null || tokenRenewer.length() == 0) {
            throw new IOException("Can't get Master Kerberos principal for the RM to use as renewer");
        }

        // For now, only getting tokens for the default file-system.
        final Token<?> tokens[] = fs.addDelegationTokens(tokenRenewer, credentials);
        if (tokens != null) {
            for (Token<?> token : tokens) {
                LOG.info("Got dt for " + fs.getUri() + "; " + token);
            }
        }
        DataOutputBuffer dob = new DataOutputBuffer();
        credentials.writeTokenStorageToStream(dob);
        ByteBuffer fsTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength());
        amContainer.setTokens(fsTokens);
    }

    appContext.setAMContainerSpec(amContainer);

    // Set the priority for the application master
    Priority pri = Records.newRecord(Priority.class);
    // TODO - what is the range for priority? how to decide?
    pri.setPriority(amPriority);
    appContext.setPriority(pri);

    // Set the queue to which this application is to be submitted in the RM
    appContext.setQueue(amQueue);

    // Submit the application to the applications manager
    // SubmitApplicationResponse submitResp =
    // applicationsManager.submitApplication(appRequest);
    // Ignore the response as either a valid response object is returned on
    // success
    // or an exception thrown to denote some form of a failure
    LOG.info("Submitting application to ASM");

    yarnClient.submitApplication(appContext);

    // TODO
    // Try submitting the same request again
    // app submission failure?

    // Monitor the application
    return monitorApplication(appId);

}

From source file:hdfs.FileUtil.java

License:Apache License

public static boolean copy(FileSystem srcFS, Path[] srcs, FileSystem dstFS, Path dst, boolean deleteSource,
        boolean overwrite, Configuration conf) throws IOException {
    boolean gotException = false;
    boolean returnVal = true;
    StringBuffer exceptions = new StringBuffer();

    if (srcs.length == 1)
        return copy(srcFS, srcs[0], dstFS, dst, deleteSource, overwrite, conf);

    // Check if dest is directory
    if (!dstFS.exists(dst)) {
        throw new IOException("`" + dst + "': specified destination directory " + "does not exist");
    } else {//from   w ww .  j a va  2 s. com
        FileStatus sdst = dstFS.getFileStatus(dst);
        if (!sdst.isDir())
            throw new IOException("copying multiple files, but last argument `" + dst + "' is not a directory");
    }

    for (Path src : srcs) {
        try {
            if (!copy(srcFS, src, dstFS, dst, deleteSource, overwrite, conf))
                returnVal = false;
        } catch (IOException e) {
            gotException = true;
            exceptions.append(e.getMessage());
            exceptions.append("\n");
        }
    }
    if (gotException) {
        throw new IOException(exceptions.toString());
    }
    return returnVal;
}

From source file:hdfs.FileUtil.java

License:Apache License

/** Copy files between FileSystems. */
public static boolean copy(FileSystem srcFS, Path src, FileSystem dstFS, Path dst, boolean deleteSource,
        boolean overwrite, Configuration conf) throws IOException {
    dst = checkDest(src.getName(), dstFS, dst, overwrite);

    if (srcFS.getFileStatus(src).isDir()) {
        checkDependencies(srcFS, src, dstFS, dst);
        if (!dstFS.mkdirs(dst)) {
            return false;
        }//from w  w w  . j  a  v  a2 s. c o m
        FileStatus contents[] = srcFS.listStatus(src);
        for (int i = 0; i < contents.length; i++) {
            copy(srcFS, contents[i].getPath(), dstFS, new Path(dst, contents[i].getPath().getName()),
                    deleteSource, overwrite, conf);
        }
    } else if (srcFS.isFile(src)) {
        InputStream in = null;
        OutputStream out = null;
        try {
            in = srcFS.open(src);
            out = dstFS.create(dst, overwrite);
            IOUtils.copyBytes(in, out, conf, true);
        } catch (IOException e) {
            IOUtils.closeStream(out);
            IOUtils.closeStream(in);
            throw e;
        }
    } else {
        throw new IOException(src.toString() + ": No such file or directory");
    }
    if (deleteSource) {
        return srcFS.delete(src, true);
    } else {
        return true;
    }

}

From source file:hdfs.FileUtil.java

License:Apache License

/** Copy all files in a directory to one output file (merge). */
public static boolean copyMerge(FileSystem srcFS, Path srcDir, FileSystem dstFS, Path dstFile,
        boolean deleteSource, Configuration conf, String addString) throws IOException {
    dstFile = checkDest(srcDir.getName(), dstFS, dstFile, false);

    if (!srcFS.getFileStatus(srcDir).isDir())
        return false;

    OutputStream out = dstFS.create(dstFile);

    try {//from www.  java 2 s.c  om
        FileStatus contents[] = srcFS.listStatus(srcDir);
        for (int i = 0; i < contents.length; i++) {
            if (!contents[i].isDir()) {
                InputStream in = srcFS.open(contents[i].getPath());
                try {
                    IOUtils.copyBytes(in, out, conf, false);
                    if (addString != null)
                        out.write(addString.getBytes("UTF-8"));

                } finally {
                    in.close();
                }
            }
        }
    } finally {
        out.close();
    }

    if (deleteSource) {
        return srcFS.delete(srcDir, true);
    } else {
        return true;
    }
}