List of usage examples for org.apache.hadoop.fs FileSystem exists
public boolean exists(Path f) throws IOException
From source file:JaqlShell.java
License:Apache License
/** * @param dir//from w w w .ja va 2 s . co m * @param numNodes * @param format * @throws Exception */ public void init(String dir, int numNodes) throws Exception { String vInfo = VersionInfo.getVersion(); System.setProperty("test.build.data", dir); m_conf = new Configuration(); // setup conf according to the Hadoop version if (vInfo.indexOf("0.20") < 0) { throw new Exception("Unsupported Hadoop version: " + vInfo); } // setup the mini dfs cluster m_fs = new MiniDFSCluster(m_conf, numNodes, true, (String[]) null); FileSystem filesystem = m_fs.getFileSystem(); m_conf.set("fs.default.name", filesystem.getUri().toString()); Path parentdir = filesystem.getHomeDirectory(); filesystem.mkdirs(parentdir); //FSUtils.setVersion(filesystem, parentdir); // setup hbase cluster (only if OS is not windows) // if(!System.getProperty("os.name").toLowerCase().contains("win")) { // m_conf.set(HConstants.HBASE_DIR, parentdir.toString()); // Path hdfsTestDir = filesystem.makeQualified(new Path(m_conf.get(HConstants.HBASE_DIR))); // // // prime the hdfs for hbase information... // HRegion root = HRegion.createHRegion(HRegionInfo.ROOT_REGIONINFO, hdfsTestDir, (HBaseConfiguration)m_conf); // HRegion meta = HRegion.createHRegion(HRegionInfo.FIRST_META_REGIONINFO, hdfsTestDir, (HBaseConfiguration)m_conf); // HRegion.addRegionToMETA(root, meta); // // // ... and close the root and meta // if (meta != null) { // meta.close(); // meta.getLog().closeAndDelete(); // } // if (root != null) { // root.close(); // root.getLog().closeAndDelete(); // } // // try // { // this.zooKeeperCluster = new MiniZooKeeperCluster(); // File testDir = new File(dir); // int clientPort = this.zooKeeperCluster.startup(testDir); // m_conf.set("hbase.zookeeper.property.clientPort", Integer.toString(clientPort)); // } catch(Exception e) { // LOG.error("Unable to startup zookeeper"); // throw new IOException(e); // } // try { // // start the mini cluster // m_base = new MiniHBaseCluster((HBaseConfiguration)m_conf, numNodes); // } catch(Exception e) { // LOG.error("Unable to startup hbase"); // throw new IOException(e); // } // try { // // opening the META table ensures that cluster is running // new HTable((HBaseConfiguration)m_conf, HConstants.META_TABLE_NAME); // // //setupOverride(conf); // } // catch (Exception e) // { // LOG.warn("Could not verify that hbase is up", e); // } // setupOverride(); // } m_mr = startMRCluster(numNodes, m_fs.getFileSystem().getName(), m_conf); Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); // make the home directory if it does not exist Path hd = fs.getWorkingDirectory(); if (!fs.exists(hd)) fs.mkdirs(hd); // make the $USER/_temporary directory if it does not exist Path tmpPath = new Path(hd, "_temporary"); if (!fs.exists(tmpPath)) fs.mkdirs(tmpPath); // if (m_base != null) // { // try { // m_admin = new HBaseAdmin((HBaseConfiguration) m_conf); // HTableDescriptor[] tables = m_admin.listTables(); // if (tables != null) // { // for (int i = 0; i < tables.length; i++) // { // m_admin.enableTable(tables[i].getName()); // } // } // } catch(Exception e) { // LOG.warn("failed to enable hbase tables"); // } // } }
From source file:JaqlShell.java
License:Apache License
/** * @throws Exception/*ww w.j a v a 2 s. c o m*/ */ public void init() throws Exception { // do nothing in the case of cluster //m_conf = new HBaseConfiguration(); //m_admin = new HBaseAdmin(m_conf); Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); // make the home directory if it does not exist Path hd = fs.getWorkingDirectory(); if (!fs.exists(hd)) fs.mkdirs(hd); }
From source file:LobFileStressTest.java
License:Apache License
private void writeIntegerFile(boolean compress) throws Exception { boolean passed = false; try {/*from ww w. j av a2s .com*/ System.out.print("Writing integers file. compress=" + compress + ". "); Path p = getPath(compress); FileSystem fs = FileSystem.getLocal(conf); if (fs.exists(p)) { fs.delete(p, false); } String codecName = compress ? "deflate" : null; LobFile.Writer w = LobFile.create(p, conf, false, codecName); int numRecords = getNumRecords(compress); for (int i = 0; i < numRecords; i++) { setLastRecordPos(w.tell(), compress); OutputStream os = w.writeBlobRecord(0); DataOutputStream dos = new DataOutputStream(os); dos.writeInt(i); dos.close(); os.close(); } w.close(); System.out.println("PASS"); passed = true; } finally { if (!passed) { allPassed = false; System.out.println("FAIL"); } } }
From source file:LobFileStressTest.java
License:Apache License
private void testBigFile(boolean compress) throws Exception { // Write a file containing 5 GB records. final int NUM_RECORDS = 5; boolean passed = false; try {//from w w w . ja v a2 s.c om System.out.print("Testing large file operations. compress=" + compress + ". "); Path p = getBigFilePath(compress); long[] startOffsets = new long[NUM_RECORDS]; // Write the file. Five records, 5 GB a piece. System.out.print("Testing write. "); FileSystem fs = FileSystem.getLocal(conf); if (fs.exists(p)) { fs.delete(p, false); } String codecName = compress ? "deflate" : null; System.out.println("record size: " + LARGE_RECORD_LEN); LobFile.Writer w = LobFile.create(p, conf, false, codecName); for (int i = 0; i < NUM_RECORDS; i++) { startOffsets[i] = w.tell(); System.out.println("Starting record " + i + " at " + startOffsets[i]); OutputStream os = w.writeBlobRecord(0); for (long v = 0; v < LARGE_RECORD_LEN; v++) { long byteVal = (((long) i) + v) & 0xFF; os.write((int) byteVal); } os.close(); } w.close(); System.out.println("PASS"); // Iterate past three records, read the fourth. System.out.print("Testing iterated skipping. "); LobFile.Reader r = LobFile.open(p, conf); for (int i = 0; i < 4; i++) { r.next(); } checkBigRecord(r, 3); System.out.println("PASS"); // Seek directly to record 2, read it through. System.out.print("Testing large backward seek. "); r.seek(startOffsets[2]); r.next(); checkBigRecord(r, 2); System.out.println("PASS"); passed = true; } finally { if (!passed) { allPassed = false; System.out.println("FAIL"); } } }
From source file:HoodieClientExample.java
License:Apache License
public void run() throws Exception { SparkConf sparkConf = new SparkConf().setAppName("hoodie-client-example"); sparkConf.setMaster("local[1]"); sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer"); sparkConf.set("spark.kryoserializer.buffer.max", "512m"); JavaSparkContext jsc = new JavaSparkContext(sparkConf); // Generator of some records to be loaded in. HoodieTestDataGenerator dataGen = new HoodieTestDataGenerator(); // initialize the table, if not done already Path path = new Path(tablePath); FileSystem fs = FSUtils.getFs(tablePath, jsc.hadoopConfiguration()); if (!fs.exists(path)) { HoodieTableMetaClient.initTableType(jsc.hadoopConfiguration(), tablePath, HoodieTableType.valueOf(tableType), tableName, HoodieAvroPayload.class.getName()); }/*w w w . java 2 s. c om*/ // Create the write client to write some records in HoodieWriteConfig cfg = HoodieWriteConfig.newBuilder().withPath(tablePath) .withSchema(HoodieTestDataGenerator.TRIP_EXAMPLE_SCHEMA).withParallelism(2, 2).forTable(tableName) .withIndexConfig(HoodieIndexConfig.newBuilder().withIndexType(IndexType.BLOOM).build()) .withCompactionConfig(HoodieCompactionConfig.newBuilder().archiveCommitsWith(2, 3).build()).build(); HoodieWriteClient client = new HoodieWriteClient(jsc, cfg); /** * Write 1 (only inserts) */ String newCommitTime = client.startCommit(); logger.info("Starting commit " + newCommitTime); List<HoodieRecord> records = dataGen.generateInserts(newCommitTime, 100); JavaRDD<HoodieRecord> writeRecords = jsc.<HoodieRecord>parallelize(records, 1); client.upsert(writeRecords, newCommitTime); /** * Write 2 (updates) */ newCommitTime = client.startCommit(); logger.info("Starting commit " + newCommitTime); records.addAll(dataGen.generateUpdates(newCommitTime, 100)); writeRecords = jsc.<HoodieRecord>parallelize(records, 1); client.upsert(writeRecords, newCommitTime); /** * Schedule a compaction and also perform compaction on a MOR dataset */ if (HoodieTableType.valueOf(tableType) == HoodieTableType.MERGE_ON_READ) { Optional<String> instant = client.scheduleCompaction(Optional.empty()); JavaRDD<WriteStatus> writeStatues = client.compact(instant.get()); client.commitCompaction(instant.get(), writeStatues, Optional.empty()); } }
From source file:acromusashi.stream.bolt.hdfs.HdfsPreProcessor.java
License:Open Source License
/** * ????<br>/*from w w w . j a v a2 s . c om*/ * ??????????? * * @param hdfs * @param targetTmpPath ?? * @param tmpSuffix ?? */ private static void renameTmpFile(FileSystem hdfs, String targetTmpPath, String tmpSuffix) { String basePath = extractBasePath(targetTmpPath, tmpSuffix); boolean isFileExists = true; try { isFileExists = hdfs.exists(new Path(basePath)); } catch (IOException ioex) { String logFormat = "Failed to search target file exists. Skip file rename. : TargetUri={0}"; String logMessage = MessageFormat.format(logFormat, basePath); logger.warn(logMessage, ioex); return; } if (isFileExists) { String logFormat = "File exists renamed target. Skip file rename. : BeforeUri={0} , AfterUri={1}"; String logMessage = MessageFormat.format(logFormat, targetTmpPath, basePath); logger.warn(logMessage); } else { try { hdfs.rename(new Path(targetTmpPath), new Path(basePath)); } catch (IOException ioex) { String logFormat = "Failed to HDFS file rename. Skip rename file and continue preprocess. : BeforeUri={0} , AfterUri={1}"; String logMessage = MessageFormat.format(logFormat, targetTmpPath, basePath); logger.warn(logMessage, ioex); } } }
From source file:acromusashi.stream.bolt.hdfs.HdfsStreamWriter.java
License:Open Source License
/** * ??HDFS??Open?// w ww. j a v a 2 s. c o m * * @param filePath HDFS * @param fs * @param isFileSyncEachTime ????????? * @throws IOException Open */ public void open(String filePath, FileSystem fs, boolean isFileSyncEachTime) throws IOException { Path dstPath = new Path(filePath); if (fs.exists(dstPath) == true) { this.delegateStream = fs.append(dstPath); } else { this.delegateStream = fs.create(dstPath); } this.isFileSyncEachTime = isFileSyncEachTime; }
From source file:adts.HbaseClient.java
License:Open Source License
public static void main(String[] args) throws IOException { String[] keys = new String[5]; int keywords_counter = 0; Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); Path inFile = new Path(args[0]); if (!fs.exists(inFile)) System.out.println("Input file not found"); if (!fs.isFile(inFile)) System.out.println("Input should be a file"); else {// ww w. ja v a 2 s .c o m FSDataInputStream fsDataInputStream = fs.open(inFile); BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(fsDataInputStream)); String line; while (((line = bufferedReader.readLine()) != null) && (keywords_counter < 5)) { String[] array = line.split("\t"); String keyword = array[0]; System.out.println("Record : " + keyword); keys[keywords_counter] = keyword; keywords_counter++; } bufferedReader.close(); fs.close(); Configuration config = HBaseConfiguration.create(); HTable table = new HTable(config, "index"); Random randomGenerator = new Random(); for (int i = 0; i < 10; i++) { int randomInt = randomGenerator.nextInt(5); System.out.println("Random chosen keyword : " + keys[randomInt]); FilterList list = new FilterList(FilterList.Operator.MUST_PASS_ALL); SingleColumnValueFilter filter_by_name = new SingleColumnValueFilter(Bytes.toBytes("keyword"), Bytes.toBytes(""), CompareOp.EQUAL, Bytes.toBytes(keys[randomInt])); //filter_by_name.setFilterIfMissing(true); list.addFilter(filter_by_name); Scan scan = new Scan(); scan.setFilter(list); //scan.addFamily(Bytes.toBytes("keyword")); ResultScanner scanner = table.getScanner(scan); try { for (Result rr = scanner.next(); rr != null; rr = scanner.next()) { // print out the row we found and the columns we were looking for byte[] cells = rr.getValue(Bytes.toBytes("article"), Bytes.toBytes("")); System.out.println("Keyword " + keys[randomInt] + "belonging to article with md5 : " + Bytes.toString(cells)); } } catch (Exception e) { e.printStackTrace(); } finally { scanner.close(); } } table.close(); } }
From source file:alluxio.hadoop.mapreduce.KeyValueOutputCommitter.java
License:Apache License
/** * @param taskContext MapReduce task configuration * @return true if the task output directory exists, otherwise false * @throws IOException if fails to determine whether the output directory exists *//* w w w . j a va2 s .com*/ @Override public boolean needsTaskCommit(TaskAttemptContext taskContext) throws IOException { Path taskOutputPath = new Path(KeyValueOutputFormat.getTaskOutputURI(taskContext).toString()); FileSystem fs = taskOutputPath.getFileSystem(taskContext.getConfiguration()); return fs.exists(taskOutputPath); }
From source file:arpserver.HadoopTool.java
@Override public int run(String[] strings) throws Exception { Configuration conf = new Configuration(); String in = strings[0];/*from ww w. ja v a2 s .co m*/ String out = strings[1]; FileSystem fs = FileSystem.get(conf); if (fs.exists(new Path(out))) { fs.delete(new Path(out), true); fs.delete(new Path(out + "Src"), true); fs.delete(new Path(out + "Mitm"), true); fs.delete(new Path(out + "ArpScn"), true); fs.delete(new Path(out + "s"), true); fs.delete(new Path(out + "d"), true); fs.delete(new Path(out + "t"), true); } Job job = new Job(); Job job2 = new Job(); Job job3 = new Job(); Job job4 = new Job(); Job job5 = new Job(); Job job6 = new Job(); Job job7 = new Job(); job.setJobName("Q"); job2.setJobName("Src"); job3.setJobName("Mitm"); job4.setJobName("ArpScn"); job5.setJobName("s"); job6.setJobName("d"); job7.setJobName("time"); job.setJarByClass(QuickDetect.class); job.setMapperClass(Qmapper.class); job.setReducerClass(Qreducer.class); job2.setMapperClass(Srcmapper.class); job2.setReducerClass(Srcreducer.class); job3.setMapperClass(ArpScanmapper.class); job3.setReducerClass(ArpScanreducer.class); job4.setMapperClass(Mitmmapper.class); job4.setReducerClass(Mitmreducer.class); job5.setMapperClass(Smapper.class); job5.setReducerClass(Sreducer.class); job6.setMapperClass(Dmapper.class); job6.setReducerClass(Dreducer.class); job7.setMapperClass(timemapper.class); job7.setReducerClass(timereducer.class); //testFinal168.txt job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Text.class); job2.setOutputKeyClass(NullWritable.class); job2.setOutputValueClass(Text.class); job3.setOutputKeyClass(NullWritable.class); job3.setOutputValueClass(IntWritable.class); job4.setOutputKeyClass(NullWritable.class); job4.setOutputValueClass(Text.class); job5.setOutputKeyClass(NullWritable.class); job5.setOutputValueClass(Text.class); job6.setOutputKeyClass(NullWritable.class); job6.setOutputValueClass(Text.class); job7.setOutputKeyClass(NullWritable.class); job7.setOutputValueClass(Text.class); job.setMapOutputKeyClass(QuickDetect.class); job.setMapOutputValueClass(IntWritable.class); //job.setOutputFormatClass(YearMultipleTextOutputFormat.class); job2.setMapOutputKeyClass(DetectSrc.class); job2.setMapOutputValueClass(IntWritable.class); job3.setMapOutputKeyClass(DetectArpScan.class); job3.setMapOutputValueClass(IntWritable.class); job4.setMapOutputKeyClass(DetectMitm.class); job4.setMapOutputValueClass(IntWritable.class); job5.setMapOutputKeyClass(SMac.class); job5.setMapOutputValueClass(IntWritable.class); job6.setMapOutputKeyClass(DMac.class); job6.setMapOutputValueClass(IntWritable.class); job7.setMapOutputKeyClass(timeMac.class); job7.setMapOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(in)); FileOutputFormat.setOutputPath(job, new Path(out)); if (job.waitForCompletion(true)) { FileInputFormat.addInputPath(job2, new Path(in)); FileOutputFormat.setOutputPath(job2, new Path(out + "Src")); if (job2.waitForCompletion(true)) { FileInputFormat.addInputPath(job3, new Path(in)); FileOutputFormat.setOutputPath(job3, new Path(out + "ArpScn")); if (job3.waitForCompletion(true)) { FileInputFormat.addInputPath(job4, new Path(in)); FileOutputFormat.setOutputPath(job4, new Path(out + "Mitm")); if (job4.waitForCompletion(true)) { FileInputFormat.addInputPath(job5, new Path(in)); FileOutputFormat.setOutputPath(job5, new Path(out + "s")); if (job5.waitForCompletion(true)) { FileInputFormat.addInputPath(job6, new Path(in)); FileOutputFormat.setOutputPath(job6, new Path(out + "d")); if (job6.waitForCompletion(true)) { FileInputFormat.addInputPath(job7, new Path(in)); FileOutputFormat.setOutputPath(job7, new Path(out + "t")); job7.waitForCompletion(true); } else { return 1; } } else { return 1; } } else { return 1; } } else { return 1; } } else { return 1; } } else { return 1; } return 0; }