List of usage examples for org.apache.hadoop.fs FileSystem getLocal
public static LocalFileSystem getLocal(Configuration conf) throws IOException
From source file:edu.nyu.vida.data_polygamy.utils.GetMergeFiles.java
License:BSD License
public static void main(String[] args) throws IllegalArgumentException, IOException, URISyntaxException { String fromDirectory = args[0]; String toEventsDirectory = args[1]; String toOutliersDirectory = args[2]; String metadataFile = args[3]; // Detecting datasets. HashSet<String> datasets = new HashSet<String>(); FileReader fileReader = new FileReader(metadataFile); BufferedReader bufferedReader = new BufferedReader(fileReader); String line;//from w w w . j a va 2 s. c o m while ((line = bufferedReader.readLine()) != null) { String[] parts = line.split(","); datasets.add(parts[0]); } bufferedReader.close(); // Downloading relationships. String relationshipPatternStr = "([a-zA-Z0-9]{4}\\-[a-zA-Z0-9]{4})\\-([a-zA-Z0-9]{4}\\-[a-zA-Z0-9]{4})"; Pattern relationshipPattern = Pattern.compile(relationshipPatternStr); Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); FileSystem localFS = FileSystem.getLocal(conf); for (FileStatus status : fs.listStatus(new Path(fs.getHomeDirectory() + "/" + fromDirectory))) { if (!status.isDirectory()) { continue; } Path file = status.getPath(); Matcher m = relationshipPattern.matcher(file.getName()); if (!m.find()) continue; String ds1 = m.group(1); String ds2 = m.group(2); if (!datasets.contains(ds1)) continue; if (!datasets.contains(ds2)) continue; for (FileStatus statusDir : fs.listStatus(file)) { if (!statusDir.isDirectory()) { continue; } Path fromPath = statusDir.getPath(); String toPathStr; if (fromPath.getName().contains("events")) { toPathStr = toEventsDirectory + "/" + fromPath.getParent().getName() + "-" + fromPath.getName(); } else { toPathStr = toOutliersDirectory + "/" + fromPath.getParent().getName() + "-" + fromPath.getName(); } Path toPath = new Path(toPathStr); System.out.println("Copying:"); System.out.println(" From: " + fromPath.toString()); System.out.println(" To: " + toPath.toString()); FileUtil.copyMerge(fs, // HDFS File System fromPath, // HDFS path localFS, // Local File System toPath, // Local Path false, // Do not delete HDFS path conf, // Configuration null); } } }
From source file:edu.purdue.cybercenter.dm.storage.AbstractStorageFileManager.java
public AbstractStorageFileManager() throws IOException { Configuration configuration = new Configuration(); this.localFileSystem = FileSystem.getLocal(configuration).getRawFileSystem(); // the one and only default storage List<Storage> storages = (List<Storage>) Storage.findAllStorages(); if (storages.size() == 1) { localStorage = storages.get(0);/*from w w w . j a va2s .c om*/ } else if (storages.isEmpty()) { throw new RuntimeException("no storage configured"); } else { throw new RuntimeException("more than one storage configured"); } }
From source file:edu.purdue.cybercenter.dm.storage.HdfsStorageFileManager.java
private FileSystem getFileSystemType(String type) throws IOException { FileSystem fs = null;/* ww w . j a va2s . c o m*/ if (type.equals(AccessMethodType.FILE)) { fs = FileSystem.getLocal(configuration).getRawFileSystem(); } return fs; }
From source file:edu.stolaf.cs.wmrserver.JobServiceHandler.java
License:Apache License
private void checkPath(FileSystem fs, Path path) throws PermissionException, NotFoundException, IOException { if (_disallowLocalInput) { // If we update to Hadoop 1.0, we should use the canonical URI which is definitely unique to each file system. However, the normal one should be, too. if (fs.getUri().equals(FileSystem.getLocal(new Configuration()).getUri())) { throw new PermissionException("Not allowed to read from the local file system."); }/*from ww w . j a v a 2 s . c om*/ } if (!fs.exists(path)) throw new NotFoundException("Input path does not exist: " + path.toString()); if (_enforceInputContainment) { // Check that path is inside home directory Path relativePath = relativizePath(_homeDir, path); if (relativePath.isAbsolute()) ; // Has authority or begins with "/" throw new PermissionException("Not allowed to read outside the " + "WebMapReduce home directory (" + _homeDir.toString() + "). Please specify a relative path."); } }
From source file:edu.uci.ics.asterix.aoya.test.YARNCluster.java
License:Apache License
private void cleanupLocal() throws IOException { // cleanup artifacts created on the local file system FileSystem lfs = FileSystem.getLocal(new Configuration()); lfs.delete(new Path("build"), true); System.setProperty("hadoop.log.dir", "logs"); }
From source file:edu.uci.ics.hyracks.hdfs.dataflow.DataflowTest.java
License:Apache License
/** * Start the HDFS cluster and setup the data files * /*from w ww. ja va2 s . c o m*/ * @throws IOException */ private void startHDFS() throws IOException { conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml")); FileSystem lfs = FileSystem.getLocal(new Configuration()); lfs.delete(new Path("build"), true); System.setProperty("hadoop.log.dir", "logs"); dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null); FileSystem dfs = FileSystem.get(conf); Path src = new Path(DATA_PATH); Path dest = new Path(HDFS_INPUT_PATH); Path result = new Path(HDFS_OUTPUT_PATH); dfs.mkdirs(dest); dfs.mkdirs(result); dfs.copyFromLocalFile(src, dest); DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH))); conf.writeXml(confOutput); confOutput.flush(); confOutput.close(); }
From source file:edu.uci.ics.hyracks.hdfs2.dataflow.DataflowTest.java
License:Apache License
/** * Start the HDFS cluster and setup the data files * /*from www.jav a 2 s . c o m*/ * @throws IOException */ private void startHDFS() throws IOException { conf.getConfiguration().addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml")); conf.getConfiguration().addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml")); conf.getConfiguration().addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml")); FileSystem lfs = FileSystem.getLocal(new Configuration()); lfs.delete(new Path("build"), true); System.setProperty("hadoop.log.dir", "logs"); dfsCluster = dfsClusterFactory.getMiniDFSCluster(conf.getConfiguration(), numberOfNC); FileSystem dfs = FileSystem.get(conf.getConfiguration()); Path src = new Path(DATA_PATH); Path dest = new Path(HDFS_INPUT_PATH); Path result = new Path(HDFS_OUTPUT_PATH); dfs.mkdirs(dest); dfs.mkdirs(result); dfs.copyFromLocalFile(src, dest); DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH))); conf.getConfiguration().writeXml(confOutput); confOutput.flush(); confOutput.close(); }
From source file:edu.uci.ics.pregelix.example.asterixdb.ConnectorTest.java
License:Apache License
@SuppressWarnings("deprecation") private static void startHDFS() throws IOException { conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml")); FileSystem lfs = FileSystem.getLocal(new Configuration()); lfs.delete(new Path("build"), true); System.setProperty("hadoop.log.dir", "logs"); dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null); DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH))); conf.writeXml(confOutput);/*from w ww . j a va 2 s .c o m*/ confOutput.flush(); confOutput.close(); }
From source file:edu.uci.ics.pregelix.example.dataload.DataLoadTest.java
License:Apache License
private void startHDFS() throws IOException { conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml")); FileSystem lfs = FileSystem.getLocal(new Configuration()); lfs.delete(new Path("build"), true); System.setProperty("hadoop.log.dir", "logs"); dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null); }
From source file:edu.uci.ics.pregelix.example.jobrun.RunJobTestSuite.java
License:Apache License
private void startHDFS() throws IOException { conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/core-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/mapred-site.xml")); conf.addResource(new Path(PATH_TO_HADOOP_CONF + "/hdfs-site.xml")); FileSystem lfs = FileSystem.getLocal(new Configuration()); lfs.delete(new Path("build"), true); System.setProperty("hadoop.log.dir", "logs"); dfsCluster = new MiniDFSCluster(conf, numberOfNC, true, null); FileSystem dfs = FileSystem.get(conf); Path src = new Path(DATA_PATH); Path dest = new Path(HDFS_PATH); dfs.mkdirs(dest);/*w ww. j a va 2 s . c om*/ dfs.copyFromLocalFile(src, dest); src = new Path(DATA_PATH2); dest = new Path(HDFS_PATH2); dfs.mkdirs(dest); dfs.copyFromLocalFile(src, dest); src = new Path(DATA_PATH3); dest = new Path(HDFS_PATH3); dfs.mkdirs(dest); dfs.copyFromLocalFile(src, dest); DataOutputStream confOutput = new DataOutputStream(new FileOutputStream(new File(HADOOP_CONF_PATH))); conf.writeXml(confOutput); confOutput.flush(); confOutput.close(); }